diff --git a/sub694rizhi.txt b/sub694rizhi.txt deleted file mode 100644 index 797e6c32..00000000 --- a/sub694rizhi.txt +++ /dev/null @@ -1,2928 +0,0 @@ -===== submission 694 attempt 1/3 ===== -[2026-08-13 03:14:04,620] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 started — model=llm endpoint=http://172.28.22.18:43325 benchmark_id=44 module=None -[2026-08-13 03:14:04,630] [PID 12] [Thread-4] [root] [INFO] guidellm report Path: /app/ui/index.html -[2026-08-13 03:14:04,651] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 starting module functional_acceptance (bm_id=102 order=0) -[2026-08-13 03:14:04,923] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module functional_acceptance: concurrency_override=1 requested but this module has no concurrency-equivalent param — not applied. -[2026-08-13 03:14:04,924] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] skip_tests: 4 check(s) will be skipped (recorded SKIP): d08_image_url_blocked, t11a_no_auth, t11b_wrong_auth, t16b_missing_content -[2026-08-13 03:14:04,931] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] backend_style=auto → resolved=direct (native endpoint /version → 200 (vLLM)) -[2026-08-13 03:14:04,931] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] multimodal=on → resolved=on (explicit override) -[2026-08-13 03:14:19,860] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d01_basic_nostream — content[11] reasoning[420] tok=139 (14.93s) -[2026-08-13 03:14:25,012] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d02_stream_usage — chunks=53 done=1 usage=52 (5.15s) -[2026-08-13 03:14:31,332] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d03_tool_call — tool=get_weather args="{'city': 'Beijing'}" finish=tool_calls (tool_choice=auto) (6.32s) -[2026-08-13 03:15:06,563] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d04_reasoning — content[213] reasoning[957] (35.23s) -[2026-08-13 03:15:43,422] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d05_multimodal — content[37]='\n\nThe image is a solid **red** color.' (36.86s) -[2026-08-13 03:15:50,846] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d06_cache_hit — 1st(pt=311,cached=0) 2nd(pt=311,cached=304) (7.42s) -[2026-08-13 03:17:42,062] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d07_reasoning_plus_content — reasoning[3143] content[1076] (111.22s) -[2026-08-13 03:17:47,778] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] d08_image_url_blocked skipped by config (skip_tests); computed PASS discarded -[2026-08-13 03:17:47,778] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP d08_image_url_blocked — skipped by config (skip_tests) (5.72s) -[2026-08-13 03:17:49,895] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d09_thinking_disable_top — reasoning[0] content='4' finish=stop (converted to chat_template_kwargs for direct backend) (2.12s) -[2026-08-13 03:17:50,987] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d10_thinking_disable_ctk — reasoning[0] content='4' finish=stop (chat_template_kwargs) (1.09s) -[2026-08-13 03:18:08,386] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1a_thinking_true — HTTP 200 reasoning[635] (expect >0) (17.40s) -[2026-08-13 03:18:10,278] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1b_thinking_false — HTTP 200 reasoning[0] (expect =0) (1.89s) -[2026-08-13 03:18:25,404] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1c_thinking_default — HTTP 200 reasoning[516] (expect >0, default on) (15.13s) -[2026-08-13 03:18:28,141] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_0_0 — HTTP 200 (2.74s) -[2026-08-13 03:18:30,868] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_1_0 — HTTP 200 (2.73s) -[2026-08-13 03:18:33,598] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_1_1 — HTTP 200 (2.73s) -[2026-08-13 03:18:36,327] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_2_0 — HTTP 200 (2.73s) -[2026-08-13 03:18:36,456] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_0 — HTTP 400 (direct: accept 2xx or 4xx) (0.13s) -[2026-08-13 03:18:39,196] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_01 — HTTP 200 (2.74s) -[2026-08-13 03:18:41,932] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_95 — HTTP 200 (2.74s) -[2026-08-13 03:18:44,663] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_1_0 — HTTP 200 (2.73s) -[2026-08-13 03:18:44,793] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_1_1 — HTTP 400 (expect 4xx) (0.13s) -[2026-08-13 03:18:47,523] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_neg2 — HTTP 200 (2.73s) -[2026-08-13 03:18:50,258] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_0 — HTTP 200 (2.73s) -[2026-08-13 03:18:53,017] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_2 — HTTP 200 (2.76s) -[2026-08-13 03:18:55,750] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_neg2 — HTTP 200 (2.73s) -[2026-08-13 03:18:58,489] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_0 — HTTP 200 (2.74s) -[2026-08-13 03:19:01,216] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_2 — HTTP 200 (2.73s) -[2026-08-13 03:19:03,983] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_n_1 — HTTP 200 (2.77s) -[2026-08-13 03:19:03,985] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t2_n_2 — HTTP 400 (0.00s) -[2026-08-13 03:24:03,995] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t3_max_tokens_none — HTTP -1 finish= (300.01s) -[2026-08-13 03:24:05,388] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_1 — HTTP 200 finish=length (1.39s) -[2026-08-13 03:24:11,919] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_64 — HTTP 200 finish=length (6.53s) -[2026-08-13 03:29:12,012] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t3_max_tokens_mid — HTTP -1 finish= (300.09s) -[2026-08-13 03:29:12,187] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t3_max_tokens_max — HTTP 400 finish= (0.17s) -[2026-08-13 03:29:12,318] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_neg1 — HTTP 400 (expect 4xx) (0.13s) -[2026-08-13 03:29:12,449] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_over — HTTP 400 (expect 4xx) (0.13s) -[2026-08-13 03:29:14,660] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t4a_no_system — HTTP 200 content='_NO_SYSTEM' reasoning[0] (2.21s) -[2026-08-13 03:29:16,953] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t4b_system_control — HTTP 200 content='_SYSTEM_CONTROL' reasoning[0] (2.29s) -[2026-08-13 03:29:20,181] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t5_function_calling — tool=get_weather args="{'city': 'Beijing'}" finish=tool_calls (tool_choice=auto) (3.23s) -[2026-08-13 03:29:23,197] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t6_multi_turn — HTTP 200 reply='BLUE_42' reasoning[0] (3.02s) -[2026-08-13 03:29:31,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t7_streaming_sse — HTTP 200 chunks=83 done=1 usage=82 (8.28s) -[2026-08-13 03:30:21,307] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t8_json_object — parsed={'name': 'Alice', 'age': 30} (49.82s) -[2026-08-13 03:30:27,669] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t9_json_schema — parsed={'name': 'Alice', 'age': 30} (6.36s) -[2026-08-13 03:30:32,710] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t10_stop_word — HTTP 200 content='1 2 3 4 5 6 7 8 9 10 11 12 13 14 ' finish=stop (5.04s) -[2026-08-13 03:30:34,207] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t11a_no_auth — skipped by config (skip_tests) (0.00s) -[2026-08-13 03:30:34,207] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t11b_wrong_auth — skipped by config (skip_tests) (0.00s) -[2026-08-13 03:30:36,746] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_chinese — HTTP 200 content="'中文测试：你好世界'" reasoning[0] (2.54s) -[2026-08-13 03:30:39,024] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_japanese — HTTP 200 content="'日本語: こんにちは'" reasoning[0] (2.28s) -[2026-08-13 03:30:42,519] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_emoji — HTTP 200 content='Emoji: 🎉🚀✨🇨🇳' reasoning[0] (3.49s) -[2026-08-13 03:35:42,783] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] t13 quadrant image: HTTP -1 missing=['red', 'green', 'blue', 'yellow'] content='' reasoning='' -[2026-08-13 03:35:42,783] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t13_multimodal_base64 — HTTP -1 missing=['red', 'green', 'blue', 'yellow'] content='' (300.03s) -[2026-08-13 03:35:42,787] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t14_empty_body — HTTP 400 (expect 4xx) (0.00s) -[2026-08-13 03:36:52,832] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t15_idempotency_seed — call1='Hello' call2='Hello' (70.04s) -[2026-08-13 03:36:52,835] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t16a_missing_role — HTTP 400 (expect 4xx) (0.00s) -[2026-08-13 03:36:52,837] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] t16b_missing_content skipped by config (skip_tests); computed PASS discarded -[2026-08-13 03:36:52,837] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t16b_missing_content — skipped by config (skip_tests) (0.00s) -[2026-08-13 03:36:52,838] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t16c_empty_messages — HTTP 400 (expect 4xx) (0.00s) -[2026-08-13 03:36:52,839] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [functional_acceptance] pass_rate=0.904 passed=47 failed=5 skipped=4 failed_keys=['t2_n_2', 't3_max_tokens_none', 't3_max_tokens_mid', 't3_max_tokens_max', 't13_multimodal_base64'] -[2026-08-13 03:37:01,900] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module functional_acceptance done — passed=False score=0.9038 -[2026-08-13 03:37:02,414] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 starting module case_truncation (bm_id=103 order=1) -[2026-08-13 03:37:10,102] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module case_truncation: CONCURRENCY OVERRIDE concurrency=4 -> 1. -[2026-08-13 03:37:23,802] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [long_output_truncation] Starting 1 concurrent requests (max_tokens=8192) -[2026-08-13 03:48:52,652] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [long_output_truncation] PASSED — avg_output_tokens=8192, elapsed=688.8s -[2026-08-13 03:48:52,653] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [case_truncation] truncation_rate=0.0 completion_ratio=1.0 -[2026-08-13 03:48:52,736] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module case_truncation done — passed=True score=1.0000 -[2026-08-13 03:48:52,775] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 starting module replay_tencent (bm_id=104 order=2) -[2026-08-13 03:48:58,386] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module replay_tencent: CONCURRENCY OVERRIDE concurrency=8 -> 1. -[2026-08-13 03:49:20,278] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Replaying 881 requests, concurrency=1 -[2026-08-13 03:49:20,278] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] SAVING per-request request/response capture to /tmp/perfbench_submission_694_4hv5__9n/replay_tencent_104/replay_responses.jsonl (<=65536 raw bytes each; REPLAY_SAVE_RESPONSES_MAX_BYTES=0 for full). Inspect with: kubectl exec -- cat /tmp/perfbench_submission_694_4hv5__9n/replay_tencent_104/replay_responses.jsonl -[2026-08-13 03:49:25,212] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] tool-support preflight OK (HTTP 200); 690/881 scanned records carry tool messages. -[2026-08-13 03:49:25,212] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] BEGIN batch total=881 concurrency=1 window=4 url=http://172.28.22.18:43325/v1/chat/completions -[2026-08-13 03:49:25,221] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a58f13fba3a7932488e00d79515e12dd attempt=1 -[2026-08-13 03:49:25,660] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a58f13fba3a7932488e00d79515e12dd status=200 post_dur=0.438s -[2026-08-13 03:50:08,493] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a58f13fba3a7932488e00d79515e12dd total=43271.4ms bytes=10361 finished=True finish=tool_calls stop=None out_tok=167 prompt_tok=24546 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:50:08,499] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6a84efa4064631019cccbcc326d46012 attempt=1 -[2026-08-13 03:50:08,971] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6a84efa4064631019cccbcc326d46012 status=200 post_dur=0.473s -[2026-08-13 03:51:39,375] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6a84efa4064631019cccbcc326d46012 total=90876.1ms bytes=164569 finished=True finish=stop stop=None out_tok=572 prompt_tok=28929 tps=6.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:51:39,383] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d8da3191f5f8fb3583bb9f63573df16f attempt=1 -[2026-08-13 03:51:39,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d8da3191f5f8fb3583bb9f63573df16f status=200 post_dur=0.463s -[2026-08-13 03:52:19,405] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d8da3191f5f8fb3583bb9f63573df16f total=40021.5ms bytes=18682 finished=True finish=tool_calls stop=None out_tok=174 prompt_tok=25948 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:52:19,409] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a68af618dd7b34c86b59fdcb52d5c6a5 attempt=1 -[2026-08-13 03:52:19,845] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a68af618dd7b34c86b59fdcb52d5c6a5 status=200 post_dur=0.436s -[2026-08-13 03:52:53,384] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a68af618dd7b34c86b59fdcb52d5c6a5 total=33975.1ms bytes=31199 finished=True finish=tool_calls stop=None out_tok=290 prompt_tok=7438 tps=8.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:52:53,388] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fd7d52d45bac317c237f5af46800d51d attempt=1 -[2026-08-13 03:52:53,861] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fd7d52d45bac317c237f5af46800d51d status=200 post_dur=0.473s -[2026-08-13 03:54:19,626] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fd7d52d45bac317c237f5af46800d51d total=86238.0ms bytes=168858 finished=True finish=stop stop=None out_tok=593 prompt_tok=26913 tps=6.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:54:19,631] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=70823b5ac845bd1f8774ee42d21bafee attempt=1 -[2026-08-13 03:54:19,921] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=70823b5ac845bd1f8774ee42d21bafee status=200 post_dur=0.290s -[2026-08-13 03:58:20,615] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=70823b5ac845bd1f8774ee42d21bafee total=240984.0ms bytes=819455 finished=True finish=stop stop=None out_tok=2816 prompt_tok=918 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:58:20,625] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2682fb6fd37b4f24e968d764437a25e1 attempt=1 -[2026-08-13 03:58:21,148] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2682fb6fd37b4f24e968d764437a25e1 status=200 post_dur=0.523s -[2026-08-13 03:59:54,193] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2682fb6fd37b4f24e968d764437a25e1 total=93568.9ms bytes=55550 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=45454 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 03:59:54,201] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=585c250747371801b7e793d8b4c0f1c2 attempt=1 -[2026-08-13 03:59:54,665] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=585c250747371801b7e793d8b4c0f1c2 status=200 post_dur=0.464s -[2026-08-13 04:00:19,742] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=585c250747371801b7e793d8b4c0f1c2 total=25540.5ms bytes=14676 finished=True finish=tool_calls stop=None out_tok=168 prompt_tok=26143 tps=6.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:00:19,744] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7db3dd955c38e4306ae474ec656cb93d attempt=1 -[2026-08-13 04:00:20,167] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7db3dd955c38e4306ae474ec656cb93d status=200 post_dur=0.422s -[2026-08-13 04:00:36,536] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7db3dd955c38e4306ae474ec656cb93d total=16791.7ms bytes=18209 finished=True finish=tool_calls stop=None out_tok=125 prompt_tok=3334 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:00:36,543] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03fe467d3f55594f27596be0c817de64 attempt=1 -[2026-08-13 04:00:37,033] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03fe467d3f55594f27596be0c817de64 status=200 post_dur=0.490s -[2026-08-13 04:01:45,232] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03fe467d3f55594f27596be0c817de64 total=68688.5ms bytes=7962 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=41634 tps=1.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:01:45,238] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd attempt=1 -[2026-08-13 04:01:45,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd status=200 post_dur=0.452s -[2026-08-13 04:02:21,916] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd total=36678.3ms bytes=8338 finished=True finish=tool_calls stop=None out_tok=154 prompt_tok=16600 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:02:21,920] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4da63363793b798959b852923d0b1a75 attempt=1 -[2026-08-13 04:02:22,370] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4da63363793b798959b852923d0b1a75 status=200 post_dur=0.450s -[2026-08-13 04:02:48,057] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4da63363793b798959b852923d0b1a75 total=26136.7ms bytes=10694 finished=True finish=tool_calls stop=None out_tok=135 prompt_tok=16183 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:02:48,061] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1009845b9f7199b5af1dcc9732c85401 attempt=1 -[2026-08-13 04:02:48,515] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1009845b9f7199b5af1dcc9732c85401 status=200 post_dur=0.454s -[2026-08-13 04:03:14,353] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1009845b9f7199b5af1dcc9732c85401 total=26292.3ms bytes=9028 finished=True finish=stop stop=None out_tok=30 prompt_tok=17014 tps=1.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:03:14,357] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21ce0a97bf87bbe568bf685f1a6489e6 attempt=1 -[2026-08-13 04:03:14,793] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21ce0a97bf87bbe568bf685f1a6489e6 status=200 post_dur=0.436s -[2026-08-13 04:03:48,334] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=21ce0a97bf87bbe568bf685f1a6489e6 total=33977.3ms bytes=13770 finished=True finish=tool_calls stop=None out_tok=212 prompt_tok=11310 tps=6.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:03:48,337] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18124d640da68a1ca39ea1da607626bc attempt=1 -[2026-08-13 04:03:48,778] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18124d640da68a1ca39ea1da607626bc status=200 post_dur=0.441s -[2026-08-13 04:04:33,661] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=18124d640da68a1ca39ea1da607626bc total=45324.2ms bytes=66453 finished=True finish=stop stop=None out_tok=229 prompt_tok=17216 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:04:33,665] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2f4bd5b73828650b91e3203f36a89b96 attempt=1 -[2026-08-13 04:04:34,115] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2f4bd5b73828650b91e3203f36a89b96 status=200 post_dur=0.449s -[2026-08-13 04:05:17,648] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2f4bd5b73828650b91e3203f36a89b96 total=43983.1ms bytes=56791 finished=True finish=stop stop=None out_tok=199 prompt_tok=21577 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:05:17,652] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 attempt=1 -[2026-08-13 04:05:18,079] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 status=200 post_dur=0.427s -[2026-08-13 04:05:55,952] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 total=38300.1ms bytes=36217 finished=True finish=tool_calls stop=None out_tok=278 prompt_tok=11631 tps=7.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:05:55,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7cbdab7b46e95ec6366386836cba94c5 attempt=1 -[2026-08-13 04:05:56,472] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7cbdab7b46e95ec6366386836cba94c5 status=200 post_dur=0.509s -[2026-08-13 04:06:19,140] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7cbdab7b46e95ec6366386836cba94c5 total=23178.2ms bytes=12655 finished=True finish=tool_calls stop=None out_tok=111 prompt_tok=49084 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:06:19,147] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=376a3e1437ef36f81003e0637ea935a3 attempt=1 -[2026-08-13 04:06:19,587] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=376a3e1437ef36f81003e0637ea935a3 status=200 post_dur=0.440s -[2026-08-13 04:06:53,864] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=376a3e1437ef36f81003e0637ea935a3 total=34717.1ms bytes=9718 finished=True finish=tool_calls stop=None out_tok=61 prompt_tok=25388 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:06:53,868] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=339ca333c681e7919cb517c87404dd63 attempt=1 -[2026-08-13 04:06:54,311] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=339ca333c681e7919cb517c87404dd63 status=200 post_dur=0.443s -[2026-08-13 04:07:19,545] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=339ca333c681e7919cb517c87404dd63 total=25676.7ms bytes=28912 finished=True finish=stop stop=None out_tok=99 prompt_tok=13787 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:07:19,549] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ec64948e84e3de297ff24346fcaf6c2 attempt=1 -[2026-08-13 04:07:20,003] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ec64948e84e3de297ff24346fcaf6c2 status=200 post_dur=0.454s -[2026-08-13 04:07:51,976] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ec64948e84e3de297ff24346fcaf6c2 total=32426.5ms bytes=7198 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=19408 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:07:51,980] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0bcc15254f1e81443ea18c89ec99619b attempt=1 -[2026-08-13 04:07:52,430] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0bcc15254f1e81443ea18c89ec99619b status=200 post_dur=0.449s -[2026-08-13 04:08:34,506] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0bcc15254f1e81443ea18c89ec99619b total=42525.4ms bytes=25619 finished=True finish=tool_calls stop=None out_tok=136 prompt_tok=21586 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:08:34,509] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5f5e5cb5b40f1964a4da622bb0ff39d attempt=1 -[2026-08-13 04:08:34,944] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5f5e5cb5b40f1964a4da622bb0ff39d status=200 post_dur=0.435s -[2026-08-13 04:08:58,887] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e5f5e5cb5b40f1964a4da622bb0ff39d total=24377.7ms bytes=11209 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=13625 tps=3.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:08:58,901] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3de56e7ddccd49d37365f311c73b68ee attempt=1 -[2026-08-13 04:08:59,541] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3de56e7ddccd49d37365f311c73b68ee status=200 post_dur=0.637s -[2026-08-13 04:12:14,500] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3de56e7ddccd49d37365f311c73b68ee total=195599.2ms bytes=9218 finished=True finish=tool_calls stop=None out_tok=71 prompt_tok=107153 tps=0.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:12:14,514] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f7b93cf7bf0ac456356481ba0a3c0869 attempt=1 -[2026-08-13 04:12:14,977] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f7b93cf7bf0ac456356481ba0a3c0869 status=200 post_dur=0.463s -[2026-08-13 04:12:45,037] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f7b93cf7bf0ac456356481ba0a3c0869 total=30522.7ms bytes=9678 finished=True finish=stop stop=None out_tok=32 prompt_tok=21726 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:12:45,043] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=813a4c2ed840077d3e58e7ef7d0ba1fc attempt=1 -[2026-08-13 04:12:45,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=813a4c2ed840077d3e58e7ef7d0ba1fc status=200 post_dur=0.470s -[2026-08-13 04:13:48,846] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=813a4c2ed840077d3e58e7ef7d0ba1fc total=63803.1ms bytes=53873 finished=True finish=stop stop=None out_tok=182 prompt_tok=33351 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:13:48,859] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=00f17c302646afed467a87ea313afde5 attempt=1 -[2026-08-13 04:13:49,373] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=00f17c302646afed467a87ea313afde5 status=200 post_dur=0.515s -[2026-08-13 04:14:12,581] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=00f17c302646afed467a87ea313afde5 total=23721.9ms bytes=9689 finished=True finish=tool_calls stop=None out_tok=82 prompt_tok=49263 tps=3.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:14:12,589] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9059eb022c6e80edfecc26f6afd3af84 attempt=1 -[2026-08-13 04:14:13,019] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9059eb022c6e80edfecc26f6afd3af84 status=200 post_dur=0.429s -[2026-08-13 04:14:43,162] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9059eb022c6e80edfecc26f6afd3af84 total=30573.1ms bytes=22430 finished=True finish=tool_calls stop=None out_tok=313 prompt_tok=7940 tps=10.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:14:43,169] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e89e3e63625e700c56b71773c4c7eab4 attempt=1 -[2026-08-13 04:14:43,667] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e89e3e63625e700c56b71773c4c7eab4 status=200 post_dur=0.498s -[2026-08-13 04:15:36,474] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e89e3e63625e700c56b71773c4c7eab4 total=53305.5ms bytes=12378 finished=True finish=tool_calls stop=None out_tok=73 prompt_tok=48213 tps=1.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:15:36,479] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=360c6b0cfb2a4dd1100d416a70e7e657 attempt=1 -[2026-08-13 04:15:36,900] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=360c6b0cfb2a4dd1100d416a70e7e657 status=200 post_dur=0.421s -[2026-08-13 04:16:14,412] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=360c6b0cfb2a4dd1100d416a70e7e657 total=37933.8ms bytes=30716 finished=True finish=tool_calls stop=None out_tok=399 prompt_tok=7229 tps=10.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:16:14,415] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 attempt=1 -[2026-08-13 04:16:14,833] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 status=200 post_dur=0.418s -[2026-08-13 04:16:43,205] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 total=28789.8ms bytes=20334 finished=True finish=tool_calls stop=None out_tok=297 prompt_tok=8044 tps=10.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:16:43,208] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=89f6e2c636fdff89a84f43f2da82dcd2 attempt=1 -[2026-08-13 04:16:43,627] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=89f6e2c636fdff89a84f43f2da82dcd2 status=200 post_dur=0.419s -[2026-08-13 04:17:07,426] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=89f6e2c636fdff89a84f43f2da82dcd2 total=24218.5ms bytes=27914 finished=True finish=tool_calls stop=None out_tok=243 prompt_tok=7197 tps=10.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:17:07,434] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80270320a8dff29e764f3e51f2457048 attempt=1 -[2026-08-13 04:17:07,915] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80270320a8dff29e764f3e51f2457048 status=200 post_dur=0.481s -[2026-08-13 04:18:18,380] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80270320a8dff29e764f3e51f2457048 total=70946.3ms bytes=12411 finished=True finish=tool_calls stop=None out_tok=128 prompt_tok=40506 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:18:18,386] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5d339eab458d8528d67a43e72e6fb280 attempt=1 -[2026-08-13 04:18:18,804] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5d339eab458d8528d67a43e72e6fb280 status=200 post_dur=0.418s -[2026-08-13 04:18:40,125] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5d339eab458d8528d67a43e72e6fb280 total=21739.4ms bytes=13934 finished=True finish=tool_calls stop=None out_tok=163 prompt_tok=9054 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:18:40,128] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d attempt=1 -[2026-08-13 04:18:40,548] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d status=200 post_dur=0.420s -[2026-08-13 04:19:11,075] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d total=30947.2ms bytes=16699 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=8499 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:19:11,076] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f3d7ddfa95b6d6451c33fb084bbca83 attempt=1 -[2026-08-13 04:19:11,366] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f3d7ddfa95b6d6451c33fb084bbca83 status=200 post_dur=0.290s -[2026-08-13 04:21:46,147] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f3d7ddfa95b6d6451c33fb084bbca83 total=155070.8ms bytes=519950 finished=True finish=stop stop=None out_tok=1787 prompt_tok=722 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:21:46,150] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=712fd074b7d4ea4b83bfcea317b58ce1 attempt=1 -[2026-08-13 04:21:46,579] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=712fd074b7d4ea4b83bfcea317b58ce1 status=200 post_dur=0.428s -[2026-08-13 04:21:58,609] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=712fd074b7d4ea4b83bfcea317b58ce1 total=12459.1ms bytes=10011 finished=True finish=tool_calls stop=None out_tok=75 prompt_tok=7322 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:21:58,613] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a395f30cab08fc845d5d9611fa68f99e attempt=1 -[2026-08-13 04:21:59,048] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a395f30cab08fc845d5d9611fa68f99e status=200 post_dur=0.434s -[2026-08-13 04:22:10,899] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a395f30cab08fc845d5d9611fa68f99e total=12285.7ms bytes=6236 finished=True finish=tool_calls stop=None out_tok=69 prompt_tok=20944 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:22:10,902] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad2442913856511942e1b75e3e16026f attempt=1 -[2026-08-13 04:22:11,307] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad2442913856511942e1b75e3e16026f status=200 post_dur=0.404s -[2026-08-13 04:22:24,012] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ad2442913856511942e1b75e3e16026f total=13109.5ms bytes=7938 finished=True finish=tool_calls stop=None out_tok=71 prompt_tok=7664 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:22:24,016] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be69437c717502c0a63e8a525b38648c attempt=1 -[2026-08-13 04:22:24,456] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be69437c717502c0a63e8a525b38648c status=200 post_dur=0.440s -[2026-08-13 04:22:38,098] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=be69437c717502c0a63e8a525b38648c total=14081.6ms bytes=7796 finished=True finish=tool_calls stop=None out_tok=102 prompt_tok=21810 tps=7.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:22:38,101] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b3ee41175527902f6fbcd82eb8223f16 attempt=1 -[2026-08-13 04:22:38,508] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b3ee41175527902f6fbcd82eb8223f16 status=200 post_dur=0.407s -[2026-08-13 04:23:07,677] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b3ee41175527902f6fbcd82eb8223f16 total=29576.1ms bytes=40838 finished=True finish=tool_calls stop=None out_tok=210 prompt_tok=9643 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:23:07,680] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23562599c4adb3e90d36122c9fb0f170 attempt=1 -[2026-08-13 04:23:08,099] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23562599c4adb3e90d36122c9fb0f170 status=200 post_dur=0.419s -[2026-08-13 04:23:22,092] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=23562599c4adb3e90d36122c9fb0f170 total=14412.4ms bytes=23170 finished=True finish=stop stop=None out_tok=79 prompt_tok=7873 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:23:22,095] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07a68b8da39a6f982e88d0cd82940b3f attempt=1 -[2026-08-13 04:23:22,506] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07a68b8da39a6f982e88d0cd82940b3f status=200 post_dur=0.412s -[2026-08-13 04:23:33,268] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=07a68b8da39a6f982e88d0cd82940b3f total=11173.6ms bytes=16081 finished=True finish=stop stop=None out_tok=54 prompt_tok=7975 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:23:33,272] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=219b40a8c965d11add7bd2c508c7791d attempt=1 -[2026-08-13 04:23:33,612] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=219b40a8c965d11add7bd2c508c7791d status=200 post_dur=0.340s -[2026-08-13 04:24:08,832] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=219b40a8c965d11add7bd2c508c7791d total=35560.0ms bytes=3672 finished=True finish=stop stop= out_tok=7 prompt_tok=27241 tps=0.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:24:08,835] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0d42f70c177f45adc313f51314e9f310 attempt=1 -[2026-08-13 04:24:08,835] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 14% (44/881) has_cb=True -[2026-08-13 04:24:09,279] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0d42f70c177f45adc313f51314e9f310 status=200 post_dur=0.444s -[2026-08-13 04:24:36,560] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0d42f70c177f45adc313f51314e9f310 total=27725.2ms bytes=13959 finished=True finish=tool_calls stop=None out_tok=227 prompt_tok=9964 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:24:36,565] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f699dd3ebdf7c24caa4d8288ae6306c9 attempt=1 -[2026-08-13 04:24:37,034] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f699dd3ebdf7c24caa4d8288ae6306c9 status=200 post_dur=0.470s -[2026-08-13 04:24:51,978] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f699dd3ebdf7c24caa4d8288ae6306c9 total=15412.9ms bytes=8299 finished=True finish=tool_calls stop=None out_tok=73 prompt_tok=22107 tps=4.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:24:51,981] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a56c2293beb6e091c063773919a7b85a attempt=1 -[2026-08-13 04:24:52,392] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a56c2293beb6e091c063773919a7b85a status=200 post_dur=0.411s -[2026-08-13 04:25:05,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a56c2293beb6e091c063773919a7b85a total=13202.5ms bytes=24620 finished=True finish=stop stop=None out_tok=84 prompt_tok=8163 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:25:05,188] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5a0840884edeb8f37a79e2a99b091fff attempt=1 -[2026-08-13 04:25:05,653] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5a0840884edeb8f37a79e2a99b091fff status=200 post_dur=0.465s -[2026-08-13 04:25:20,085] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5a0840884edeb8f37a79e2a99b091fff total=14897.1ms bytes=7992 finished=True finish=tool_calls stop=None out_tok=72 prompt_tok=22416 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:25:20,095] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=54a7844586d857514e3829e8ef560825 attempt=1 -[2026-08-13 04:25:20,583] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=54a7844586d857514e3829e8ef560825 status=200 post_dur=0.488s -[2026-08-13 04:25:54,913] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=54a7844586d857514e3829e8ef560825 total=34818.6ms bytes=46418 finished=True finish=tool_calls stop=None out_tok=191 prompt_tok=49698 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:25:54,918] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 attempt=1 -[2026-08-13 04:25:55,211] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 status=200 post_dur=0.293s -[2026-08-13 04:32:13,266] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 total=378347.9ms bytes=1296001 finished=True finish=stop stop=None out_tok=4461 prompt_tok=543 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:32:13,272] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8e95ef4c8df8d98f53d1f3578d275be attempt=1 -[2026-08-13 04:32:13,709] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8e95ef4c8df8d98f53d1f3578d275be status=200 post_dur=0.437s -[2026-08-13 04:33:04,333] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a8e95ef4c8df8d98f53d1f3578d275be total=51061.1ms bytes=134714 finished=True finish=stop stop=None out_tok=464 prompt_tok=9644 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:33:04,337] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 attempt=1 -[2026-08-13 04:33:04,767] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 status=200 post_dur=0.429s -[2026-08-13 04:33:43,790] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 total=39452.2ms bytes=8813 finished=True finish=tool_calls stop=None out_tok=354 prompt_tok=13629 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:33:43,791] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39102a614c8ccec8e7ca9bcfb647d006 attempt=1 -[2026-08-13 04:33:44,100] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39102a614c8ccec8e7ca9bcfb647d006 status=200 post_dur=0.308s -[2026-08-13 04:36:03,863] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=39102a614c8ccec8e7ca9bcfb647d006 total=140072.3ms bytes=466312 finished=True finish=stop stop=None out_tok=1605 prompt_tok=340 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:36:03,867] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ce01f9017d9d711130b41c2ddbae17c attempt=1 -[2026-08-13 04:36:04,335] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ce01f9017d9d711130b41c2ddbae17c status=200 post_dur=0.468s -[2026-08-13 04:36:43,331] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ce01f9017d9d711130b41c2ddbae17c total=39463.7ms bytes=39203 finished=True finish=tool_calls stop=None out_tok=367 prompt_tok=10478 tps=9.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:36:43,335] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=efd73b6b2b7ff74dd1c2c06494d7075d attempt=1 -[2026-08-13 04:36:43,786] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=efd73b6b2b7ff74dd1c2c06494d7075d status=200 post_dur=0.450s -[2026-08-13 04:36:57,455] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=efd73b6b2b7ff74dd1c2c06494d7075d total=14119.4ms bytes=6892 finished=True finish=tool_calls stop=None out_tok=120 prompt_tok=22532 tps=8.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:36:57,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a2b735acf3a16ed3e21d3f5098df2ba7 attempt=1 -[2026-08-13 04:36:57,862] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a2b735acf3a16ed3e21d3f5098df2ba7 status=200 post_dur=0.404s -[2026-08-13 04:37:29,241] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a2b735acf3a16ed3e21d3f5098df2ba7 total=31783.0ms bytes=10465 finished=True finish=tool_calls stop=None out_tok=283 prompt_tok=10715 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:37:29,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=75640a175567399b71ba112bebff92dc attempt=1 -[2026-08-13 04:37:29,663] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=75640a175567399b71ba112bebff92dc status=200 post_dur=0.419s -[2026-08-13 04:37:46,347] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=75640a175567399b71ba112bebff92dc total=17102.8ms bytes=33451 finished=True finish=stop stop=None out_tok=115 prompt_tok=8287 tps=6.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:37:46,351] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c0c3e503a9bb2dffb86498602abab0f8 attempt=1 -[2026-08-13 04:37:46,757] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c0c3e503a9bb2dffb86498602abab0f8 status=200 post_dur=0.406s -[2026-08-13 04:38:03,437] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c0c3e503a9bb2dffb86498602abab0f8 total=17085.7ms bytes=29963 finished=True finish=stop stop=None out_tok=103 prompt_tok=8410 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:38:03,441] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac347710b223a90a91abea5cc1a4953a attempt=1 -[2026-08-13 04:38:03,871] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac347710b223a90a91abea5cc1a4953a status=200 post_dur=0.430s -[2026-08-13 04:38:18,727] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ac347710b223a90a91abea5cc1a4953a total=15285.5ms bytes=8580 finished=True finish=tool_calls stop=None out_tok=131 prompt_tok=22692 tps=8.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:38:18,733] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8463c2c502f1f0534d61b5ca2d393ebe attempt=1 -[2026-08-13 04:38:19,170] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8463c2c502f1f0534d61b5ca2d393ebe status=200 post_dur=0.437s -[2026-08-13 04:39:05,184] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8463c2c502f1f0534d61b5ca2d393ebe total=46451.4ms bytes=29093 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=24349 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:39:05,194] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b0e4b0f5b0ca97ed4d751c75618548c attempt=1 -[2026-08-13 04:39:05,704] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b0e4b0f5b0ca97ed4d751c75618548c status=200 post_dur=0.509s -[2026-08-13 04:39:41,674] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b0e4b0f5b0ca97ed4d751c75618548c total=36479.3ms bytes=36371 finished=True finish=tool_calls stop=None out_tok=219 prompt_tok=50019 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:39:41,680] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a391bb70b9e2ba5c7e520aab15e3def1 attempt=1 -[2026-08-13 04:39:42,110] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a391bb70b9e2ba5c7e520aab15e3def1 status=200 post_dur=0.430s -[2026-08-13 04:39:54,757] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a391bb70b9e2ba5c7e520aab15e3def1 total=13077.6ms bytes=22165 finished=True finish=stop stop=None out_tok=76 prompt_tok=8534 tps=5.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:39:54,760] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f37ea383d6ec06c307d5f3744b934942 attempt=1 -[2026-08-13 04:39:55,188] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f37ea383d6ec06c307d5f3744b934942 status=200 post_dur=0.428s -[2026-08-13 04:40:20,161] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f37ea383d6ec06c307d5f3744b934942 total=25401.1ms bytes=31411 finished=True finish=tool_calls stop=None out_tok=223 prompt_tok=8664 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:40:20,167] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=311152e5f6fe095f516df19d0f9295a3 attempt=1 -[2026-08-13 04:40:20,629] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=311152e5f6fe095f516df19d0f9295a3 status=200 post_dur=0.462s -[2026-08-13 04:40:48,618] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=311152e5f6fe095f516df19d0f9295a3 total=28450.9ms bytes=8072 finished=True finish=tool_calls stop=None out_tok=94 prompt_tok=32388 tps=3.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:40:48,625] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6b0d07d4e32c236ad057a1909c20b94c attempt=1 -[2026-08-13 04:40:49,118] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6b0d07d4e32c236ad057a1909c20b94c status=200 post_dur=0.492s -[2026-08-13 04:43:21,386] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6b0d07d4e32c236ad057a1909c20b94c total=152760.2ms bytes=162310 finished=True finish=stop stop=None out_tok=556 prompt_tok=55542 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:43:21,393] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1553e713a265e3e047100572f79b3970 attempt=1 -[2026-08-13 04:43:21,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1553e713a265e3e047100572f79b3970 status=200 post_dur=0.459s -[2026-08-13 04:44:10,451] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1553e713a265e3e047100572f79b3970 total=49057.3ms bytes=58247 finished=True finish=stop stop=None out_tok=197 prompt_tok=24478 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:44:10,455] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7f48075c85514d36f9123d4d520ad38 attempt=1 -[2026-08-13 04:44:10,878] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7f48075c85514d36f9123d4d520ad38 status=200 post_dur=0.423s -[2026-08-13 04:44:21,167] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7f48075c85514d36f9123d4d520ad38 total=10711.9ms bytes=13453 finished=True finish=stop stop=None out_tok=45 prompt_tok=8783 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:44:21,172] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5834b503b1451d5964dff9ea1d95cdfd attempt=1 -[2026-08-13 04:44:21,611] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5834b503b1451d5964dff9ea1d95cdfd status=200 post_dur=0.440s -[2026-08-13 04:44:59,912] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5834b503b1451d5964dff9ea1d95cdfd total=38740.4ms bytes=31421 finished=True finish=stop stop=None out_tok=106 prompt_tok=24997 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:44:59,917] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c99a9bde00a04b8817a94ee39e4d79b5 attempt=1 -[2026-08-13 04:45:00,348] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c99a9bde00a04b8817a94ee39e4d79b5 status=200 post_dur=0.431s -[2026-08-13 04:45:39,504] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c99a9bde00a04b8817a94ee39e4d79b5 total=39587.2ms bytes=57684 finished=True finish=tool_calls stop=None out_tok=345 prompt_tok=14545 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:45:39,510] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=074a482ddedc3555e604c834ff66c671 attempt=1 -[2026-08-13 04:45:39,984] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=074a482ddedc3555e604c834ff66c671 status=200 post_dur=0.473s -[2026-08-13 04:45:55,586] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=074a482ddedc3555e604c834ff66c671 total=16075.7ms bytes=9010 finished=True finish=tool_calls stop=None out_tok=137 prompt_tok=32594 tps=8.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:45:55,591] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bf9397c366a1037bdd145249dee8b6cd attempt=1 -[2026-08-13 04:45:55,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bf9397c366a1037bdd145249dee8b6cd status=200 post_dur=0.335s -[2026-08-13 04:46:35,246] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bf9397c366a1037bdd145249dee8b6cd total=39654.9ms bytes=3953 finished=True finish=stop stop= out_tok=7 prompt_tok=27569 tps=0.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:46:35,250] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a0ee8f7cc01879cf295f23c02c4d1655 attempt=1 -[2026-08-13 04:46:35,688] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a0ee8f7cc01879cf295f23c02c4d1655 status=200 post_dur=0.439s -[2026-08-13 04:47:09,010] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a0ee8f7cc01879cf295f23c02c4d1655 total=33760.0ms bytes=23902 finished=True finish=tool_calls stop=None out_tok=293 prompt_tok=12033 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:47:09,014] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=784782f027a97cabd3ecf7d581aaf95f attempt=1 -[2026-08-13 04:47:09,451] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=784782f027a97cabd3ecf7d581aaf95f status=200 post_dur=0.437s -[2026-08-13 04:47:53,959] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=784782f027a97cabd3ecf7d581aaf95f total=44944.7ms bytes=21758 finished=True finish=tool_calls stop=None out_tok=475 prompt_tok=14122 tps=10.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:47:53,983] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0095eee8517acdd4d3777bb0dad225d0 attempt=1 -[2026-08-13 04:47:54,522] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0095eee8517acdd4d3777bb0dad225d0 status=400 post_dur=0.539s -[2026-08-13 04:47:54,522] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0095eee8517acdd4d3777bb0dad225d0 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 185059 tokens in the messages, Please reduce the length of the messages. (retryable=False, attempt=1) -[2026-08-13 04:47:54,538] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a05d3a420be46da851a6bd2697078069 attempt=1 -[2026-08-13 04:47:54,975] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a05d3a420be46da851a6bd2697078069 status=200 post_dur=0.435s -[2026-08-13 04:48:13,229] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a05d3a420be46da851a6bd2697078069 total=18691.6ms bytes=5731 finished=True finish=tool_calls stop=None out_tok=111 prompt_tok=32724 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:48:13,239] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e35b4624c19687e1ea219c3ac378c64 attempt=1 -[2026-08-13 04:48:13,725] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e35b4624c19687e1ea219c3ac378c64 status=200 post_dur=0.484s -[2026-08-13 04:49:20,966] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e35b4624c19687e1ea219c3ac378c64 total=67727.5ms bytes=9693 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=43882 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:49:20,975] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f4bf992edfbf1935605b2c80b414d03 attempt=1 -[2026-08-13 04:49:21,429] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f4bf992edfbf1935605b2c80b414d03 status=200 post_dur=0.454s -[2026-08-13 04:49:57,437] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f4bf992edfbf1935605b2c80b414d03 total=36462.4ms bytes=27327 finished=True finish=stop stop=None out_tok=92 prompt_tok=23705 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:49:57,443] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40959c2050879969f36ed4f3b444dacd attempt=1 -[2026-08-13 04:49:57,897] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40959c2050879969f36ed4f3b444dacd status=200 post_dur=0.454s -[2026-08-13 04:50:51,272] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40959c2050879969f36ed4f3b444dacd total=53828.6ms bytes=50194 finished=True finish=tool_calls stop=None out_tok=275 prompt_tok=22948 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:50:51,279] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aeabdeb121230304d17740b28591d176 attempt=1 -[2026-08-13 04:50:51,755] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aeabdeb121230304d17740b28591d176 status=200 post_dur=0.476s -[2026-08-13 04:51:11,980] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=aeabdeb121230304d17740b28591d176 total=20701.7ms bytes=12231 finished=True finish=tool_calls stop=None out_tok=108 prompt_tok=33199 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:51:11,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f8d05205e676b25e02ee83b3f6ed2502 attempt=1 -[2026-08-13 04:51:12,410] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f8d05205e676b25e02ee83b3f6ed2502 status=200 post_dur=0.425s -[2026-08-13 04:51:28,333] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f8d05205e676b25e02ee83b3f6ed2502 total=16348.0ms bytes=12994 finished=True finish=tool_calls stop=None out_tok=130 prompt_tok=11658 tps=8.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:51:28,339] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a21ccfb1e67b5d347d1c44d30403b795 attempt=1 -[2026-08-13 04:51:28,801] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a21ccfb1e67b5d347d1c44d30403b795 status=200 post_dur=0.462s -[2026-08-13 04:51:50,944] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a21ccfb1e67b5d347d1c44d30403b795 total=22605.5ms bytes=8432 finished=True finish=tool_calls stop=None out_tok=145 prompt_tok=32921 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:51:50,949] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2f83fc5e61ae17754909b5b0d66e6ca5 attempt=1 -[2026-08-13 04:51:51,387] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2f83fc5e61ae17754909b5b0d66e6ca5 status=200 post_dur=0.437s -[2026-08-13 04:52:20,390] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2f83fc5e61ae17754909b5b0d66e6ca5 total=29440.3ms bytes=8462 finished=True finish=tool_calls stop=None out_tok=58 prompt_tok=17499 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:52:20,400] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bbff126da08af9ca0d698e918bd39573 attempt=1 -[2026-08-13 04:52:20,998] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bbff126da08af9ca0d698e918bd39573 status=200 post_dur=0.597s -[2026-08-13 04:55:51,898] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bbff126da08af9ca0d698e918bd39573 total=211497.9ms bytes=76930 finished=True finish=stop stop=None out_tok=258 prompt_tok=101884 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:55:51,910] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b65fcd82491c19e8d7d0d34518546e5a attempt=1 -[2026-08-13 04:55:52,395] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b65fcd82491c19e8d7d0d34518546e5a status=200 post_dur=0.484s -[2026-08-13 04:56:12,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b65fcd82491c19e8d7d0d34518546e5a total=20548.2ms bytes=6595 finished=True finish=tool_calls stop=None out_tok=89 prompt_tok=33356 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 04:56:12,461] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77b618402ff95dd4ff23bd2310cb8318 attempt=1 -[2026-08-13 04:56:12,743] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77b618402ff95dd4ff23bd2310cb8318 status=200 post_dur=0.281s -[2026-08-13 05:00:31,283] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=77b618402ff95dd4ff23bd2310cb8318 total=258821.8ms bytes=889834 finished=True finish=stop stop=None out_tok=3054 prompt_tok=122 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:00:31,292] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d32f68c92aef9a9648a699a77ef05b26 attempt=1 -[2026-08-13 05:00:31,794] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d32f68c92aef9a9648a699a77ef05b26 status=200 post_dur=0.503s -[2026-08-13 05:00:46,970] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d32f68c92aef9a9648a699a77ef05b26 total=15678.3ms bytes=8070 finished=True finish=tool_calls stop=None out_tok=92 prompt_tok=33760 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:00:46,973] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=918aec365fd6259a7e6b60476f6088a4 attempt=1 -[2026-08-13 05:00:47,231] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=918aec365fd6259a7e6b60476f6088a4 status=200 post_dur=0.257s -[2026-08-13 05:09:05,485] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=918aec365fd6259a7e6b60476f6088a4 total=498512.2ms bytes=1714052 finished=True finish=stop stop=None out_tok=5913 prompt_tok=543 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:09:05,499] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a64b40ed62a4f1699c75f575d5608d10 attempt=1 -[2026-08-13 05:09:06,055] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a64b40ed62a4f1699c75f575d5608d10 status=200 post_dur=0.555s -[2026-08-13 05:12:24,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a64b40ed62a4f1699c75f575d5608d10 total=198745.4ms bytes=152414 finished=True finish=stop stop=None out_tok=524 prompt_tok=78991 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:12:24,254] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ca31eadeeaf52359665b0d1944272c8 attempt=1 -[2026-08-13 05:12:24,254] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 18% (88/881) has_cb=True -[2026-08-13 05:12:24,756] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ca31eadeeaf52359665b0d1944272c8 status=200 post_dur=0.501s -[2026-08-13 05:14:44,453] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8ca31eadeeaf52359665b0d1944272c8 total=140199.2ms bytes=170111 finished=True finish=stop stop=None out_tok=598 prompt_tok=47178 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:14:44,460] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=78ea5bb2fab0a10263af727c1c9c09b5 attempt=1 -[2026-08-13 05:14:44,891] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=78ea5bb2fab0a10263af727c1c9c09b5 status=200 post_dur=0.431s -[2026-08-13 05:15:22,288] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=78ea5bb2fab0a10263af727c1c9c09b5 total=37827.4ms bytes=23851 finished=True finish=tool_calls stop=None out_tok=344 prompt_tok=13068 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:15:22,290] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a96ee2366817370eea1cef47ad091443 attempt=1 -[2026-08-13 05:15:22,710] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a96ee2366817370eea1cef47ad091443 status=200 post_dur=0.420s -[2026-08-13 05:15:43,587] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a96ee2366817370eea1cef47ad091443 total=21296.1ms bytes=12788 finished=True finish=tool_calls stop=None out_tok=110 prompt_tok=7510 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:15:43,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0bea91b5ded418d8d4a581db599a3427 attempt=1 -[2026-08-13 05:15:44,055] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0bea91b5ded418d8d4a581db599a3427 status=200 post_dur=0.463s -[2026-08-13 05:16:01,946] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0bea91b5ded418d8d4a581db599a3427 total=18354.1ms bytes=7466 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=34060 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:16:01,953] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1a96f880493d5949c2df7e1cf3b2a6ef attempt=1 -[2026-08-13 05:16:02,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1a96f880493d5949c2df7e1cf3b2a6ef status=200 post_dur=0.504s -[2026-08-13 05:17:08,318] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1a96f880493d5949c2df7e1cf3b2a6ef total=66365.2ms bytes=9509 finished=True finish=tool_calls stop=None out_tok=94 prompt_tok=42832 tps=1.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:17:08,323] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=06537fb205ebfa74b468388f0205c0b6 attempt=1 -[2026-08-13 05:17:08,757] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=06537fb205ebfa74b468388f0205c0b6 status=200 post_dur=0.434s -[2026-08-13 05:17:46,435] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=06537fb205ebfa74b468388f0205c0b6 total=38112.1ms bytes=47055 finished=True finish=tool_calls stop=None out_tok=394 prompt_tok=13375 tps=10.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:17:46,438] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6cd5c62d32dcdbcbbb415bd7854e91ca attempt=1 -[2026-08-13 05:17:46,865] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6cd5c62d32dcdbcbbb415bd7854e91ca status=200 post_dur=0.426s -[2026-08-13 05:17:58,594] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6cd5c62d32dcdbcbbb415bd7854e91ca total=12155.4ms bytes=16673 finished=True finish=stop stop=None out_tok=57 prompt_tok=7694 tps=4.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:17:58,600] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ec1d220a384aea3297a253a297cf1a9 attempt=1 -[2026-08-13 05:17:59,071] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ec1d220a384aea3297a253a297cf1a9 status=200 post_dur=0.471s -[2026-08-13 05:18:19,981] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ec1d220a384aea3297a253a297cf1a9 total=21381.7ms bytes=6725 finished=True finish=tool_calls stop=None out_tok=136 prompt_tok=34971 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:18:19,989] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e88b521cf3df9fb0cbc8d992a2449aee attempt=1 -[2026-08-13 05:18:20,453] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e88b521cf3df9fb0cbc8d992a2449aee status=200 post_dur=0.464s -[2026-08-13 05:18:35,875] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e88b521cf3df9fb0cbc8d992a2449aee total=15886.2ms bytes=19204 finished=True finish=tool_calls stop=None out_tok=94 prompt_tok=34581 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:18:35,882] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=359993faafbbf5e1f8c854e67edd7b28 attempt=1 -[2026-08-13 05:18:36,298] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=359993faafbbf5e1f8c854e67edd7b28 status=200 post_dur=0.416s -[2026-08-13 05:19:13,027] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=359993faafbbf5e1f8c854e67edd7b28 total=37144.7ms bytes=16243 finished=True finish=tool_calls stop=None out_tok=333 prompt_tok=14631 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:19:13,031] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5287e77e7d3f01ce0ec64229252926f1 attempt=1 -[2026-08-13 05:19:13,478] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5287e77e7d3f01ce0ec64229252926f1 status=200 post_dur=0.446s -[2026-08-13 05:20:05,271] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5287e77e7d3f01ce0ec64229252926f1 total=52239.8ms bytes=64457 finished=True finish=stop stop=None out_tok=220 prompt_tok=24262 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:20:05,274] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4074aa7dc7eeae406e1611ba25d09f4 attempt=1 -[2026-08-13 05:20:05,563] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4074aa7dc7eeae406e1611ba25d09f4 status=200 post_dur=0.289s -[2026-08-13 05:24:26,779] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4074aa7dc7eeae406e1611ba25d09f4 total=261504.6ms bytes=899341 finished=True finish=stop stop=None out_tok=3084 prompt_tok=329 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:24:26,787] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=72ac37b8e14256ef5f1f6b17c95816e3 attempt=1 -[2026-08-13 05:24:27,299] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=72ac37b8e14256ef5f1f6b17c95816e3 status=200 post_dur=0.513s -[2026-08-13 05:24:50,414] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=72ac37b8e14256ef5f1f6b17c95816e3 total=23627.3ms bytes=4660 finished=True finish=tool_calls stop=None out_tok=126 prompt_tok=35268 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:24:50,417] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6c94c67fba670cdb7e87d0346aaa846d attempt=1 -[2026-08-13 05:24:50,693] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6c94c67fba670cdb7e87d0346aaa846d status=200 post_dur=0.276s -[2026-08-13 05:29:51,734] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6c94c67fba670cdb7e87d0346aaa846d total=301317.4ms bytes=1040476 finished=True finish=stop stop=None out_tok=3551 prompt_tok=1147 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:29:51,741] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d90b76d18c2aa143a4aa12ca4b73a91f attempt=1 -[2026-08-13 05:29:52,216] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d90b76d18c2aa143a4aa12ca4b73a91f status=200 post_dur=0.474s -[2026-08-13 05:31:57,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d90b76d18c2aa143a4aa12ca4b73a91f total=126110.0ms bytes=58092 finished=True finish=tool_calls stop=None out_tok=1054 prompt_tok=25652 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:31:57,855] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ee3b59eca4ff424eeeeb06f0f9807899 attempt=1 -[2026-08-13 05:31:58,279] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ee3b59eca4ff424eeeeb06f0f9807899 status=200 post_dur=0.424s -[2026-08-13 05:32:24,278] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ee3b59eca4ff424eeeeb06f0f9807899 total=26423.2ms bytes=50214 finished=True finish=stop stop=None out_tok=173 prompt_tok=7419 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:32:24,281] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b08d07aa190488d2ee3424334d75e8ba attempt=1 -[2026-08-13 05:32:24,723] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b08d07aa190488d2ee3424334d75e8ba status=200 post_dur=0.441s -[2026-08-13 05:32:50,457] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b08d07aa190488d2ee3424334d75e8ba total=26175.7ms bytes=21171 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=15084 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:32:50,464] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8da9e2d6b6813eaddab9b4575a1a83f attempt=1 -[2026-08-13 05:32:50,935] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8da9e2d6b6813eaddab9b4575a1a83f status=200 post_dur=0.471s -[2026-08-13 05:33:16,643] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a8da9e2d6b6813eaddab9b4575a1a83f total=26179.0ms bytes=18255 finished=True finish=tool_calls stop=None out_tok=180 prompt_tok=36306 tps=6.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:33:16,650] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad67a766c04ea6887f061628a3a3d818 attempt=1 -[2026-08-13 05:33:17,090] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad67a766c04ea6887f061628a3a3d818 status=200 post_dur=0.440s -[2026-08-13 05:33:57,882] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ad67a766c04ea6887f061628a3a3d818 total=41231.7ms bytes=17438 finished=True finish=tool_calls stop=None out_tok=113 prompt_tok=24662 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:33:57,885] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 attempt=1 -[2026-08-13 05:33:58,298] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 status=200 post_dur=0.413s -[2026-08-13 05:34:34,740] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 total=36855.0ms bytes=22925 finished=True finish=tool_calls stop=None out_tok=331 prompt_tok=7433 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:34:34,746] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b316df0c85c0582bbe29e8ec225bc084 attempt=1 -[2026-08-13 05:34:35,232] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b316df0c85c0582bbe29e8ec225bc084 status=200 post_dur=0.486s -[2026-08-13 05:34:51,896] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b316df0c85c0582bbe29e8ec225bc084 total=17149.6ms bytes=5920 finished=True finish=tool_calls stop=None out_tok=63 prompt_tok=36648 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:34:51,904] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 attempt=1 -[2026-08-13 05:34:52,374] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 status=200 post_dur=0.471s -[2026-08-13 05:35:22,403] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 total=30499.3ms bytes=21799 finished=True finish=tool_calls stop=None out_tok=188 prompt_tok=36970 tps=6.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:35:22,408] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=644f50cec5c5a17c7ed68cd3d209a327 attempt=1 -[2026-08-13 05:35:22,835] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=644f50cec5c5a17c7ed68cd3d209a327 status=200 post_dur=0.427s -[2026-08-13 05:36:01,931] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=644f50cec5c5a17c7ed68cd3d209a327 total=39522.9ms bytes=64187 finished=True finish=tool_calls stop=None out_tok=346 prompt_tok=16293 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:36:01,938] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea32e9659a5417289b1ca305dae84ea7 attempt=1 -[2026-08-13 05:36:02,383] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea32e9659a5417289b1ca305dae84ea7 status=200 post_dur=0.445s -[2026-08-13 05:36:32,630] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea32e9659a5417289b1ca305dae84ea7 total=30692.3ms bytes=18912 finished=True finish=tool_calls stop=None out_tok=228 prompt_tok=18482 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:36:32,637] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 attempt=1 -[2026-08-13 05:36:33,124] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 status=200 post_dur=0.487s -[2026-08-13 05:37:03,394] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 total=30757.7ms bytes=22691 finished=True finish=tool_calls stop=None out_tok=191 prompt_tok=37363 tps=6.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:37:03,417] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fe7722e1ac0ce6b82619d5486a7d745f attempt=1 -[2026-08-13 05:37:04,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fe7722e1ac0ce6b82619d5486a7d745f status=400 post_dur=0.592s -[2026-08-13 05:37:04,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=fe7722e1ac0ce6b82619d5486a7d745f status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 258432 tokens (254336 in the messages, 4096 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 05:37:04,024] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea0d61904cec5ffd9962be89b52a5533 attempt=1 -[2026-08-13 05:37:04,463] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea0d61904cec5ffd9962be89b52a5533 status=200 post_dur=0.439s -[2026-08-13 05:37:22,789] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea0d61904cec5ffd9962be89b52a5533 total=18764.5ms bytes=6564 finished=True finish=tool_calls stop=None out_tok=87 prompt_tok=37547 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:37:22,793] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17ed153b31dbaf712162b2e8efcf5f83 attempt=1 -[2026-08-13 05:37:23,186] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17ed153b31dbaf712162b2e8efcf5f83 status=200 post_dur=0.392s -[2026-08-13 05:37:47,764] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17ed153b31dbaf712162b2e8efcf5f83 total=24970.8ms bytes=10624 finished=True finish=tool_calls stop=None out_tok=151 prompt_tok=7670 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:37:47,766] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8594181c733137b3501cbdef6c8ca480 attempt=1 -[2026-08-13 05:37:48,165] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8594181c733137b3501cbdef6c8ca480 status=200 post_dur=0.399s -[2026-08-13 05:38:05,129] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8594181c733137b3501cbdef6c8ca480 total=17362.9ms bytes=28106 finished=True finish=stop stop=None out_tok=95 prompt_tok=8974 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:38:05,134] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab3a26a3b1baafac01deca1e9c297be3 attempt=1 -[2026-08-13 05:38:05,570] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab3a26a3b1baafac01deca1e9c297be3 status=200 post_dur=0.437s -[2026-08-13 05:38:38,844] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ab3a26a3b1baafac01deca1e9c297be3 total=33710.4ms bytes=9378 finished=True finish=stop stop=None out_tok=31 prompt_tok=23584 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:38:38,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bd7ef39fe969b9fc6d359b5c1627bbbc attempt=1 -[2026-08-13 05:38:39,261] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bd7ef39fe969b9fc6d359b5c1627bbbc status=200 post_dur=0.414s -[2026-08-13 05:39:03,232] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bd7ef39fe969b9fc6d359b5c1627bbbc total=24384.6ms bytes=14857 finished=True finish=tool_calls stop=None out_tok=243 prompt_tok=7955 tps=10.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:39:03,236] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=70bdd90760d1a4809ceb24b904b635f7 attempt=1 -[2026-08-13 05:39:03,688] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=70bdd90760d1a4809ceb24b904b635f7 status=200 post_dur=0.452s -[2026-08-13 05:39:47,894] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=70bdd90760d1a4809ceb24b904b635f7 total=44658.1ms bytes=21392 finished=True finish=stop stop=None out_tok=72 prompt_tok=30020 tps=1.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:39:47,897] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b115b076b436975dd0bdc04a97b0250d attempt=1 -[2026-08-13 05:39:48,314] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b115b076b436975dd0bdc04a97b0250d status=200 post_dur=0.417s -[2026-08-13 05:40:11,658] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b115b076b436975dd0bdc04a97b0250d total=23760.1ms bytes=11880 finished=True finish=tool_calls stop=None out_tok=223 prompt_tok=8108 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:40:11,659] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=05c88893744ef06a571e677dea1d4b35 attempt=1 -[2026-08-13 05:40:11,932] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=05c88893744ef06a571e677dea1d4b35 status=200 post_dur=0.273s -[2026-08-13 05:43:07,250] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=05c88893744ef06a571e677dea1d4b35 total=175590.8ms bytes=596346 finished=True finish=length stop=None out_tok=2048 prompt_tok=665 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:43:07,258] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 attempt=1 -[2026-08-13 05:43:07,767] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 status=200 post_dur=0.508s -[2026-08-13 05:43:31,489] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 total=24230.9ms bytes=19622 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=38777 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:43:31,497] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=98ccba13269d9b590af730b62743e33b attempt=1 -[2026-08-13 05:43:31,904] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=98ccba13269d9b590af730b62743e33b status=200 post_dur=0.407s -[2026-08-13 05:43:53,012] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=98ccba13269d9b590af730b62743e33b total=21514.9ms bytes=18935 finished=True finish=tool_calls stop=None out_tok=143 prompt_tok=8897 tps=6.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:43:53,016] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b621098765131843ffeab6dfd48accd attempt=1 -[2026-08-13 05:43:53,456] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b621098765131843ffeab6dfd48accd status=200 post_dur=0.441s -[2026-08-13 05:44:26,824] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b621098765131843ffeab6dfd48accd total=33807.9ms bytes=23586 finished=True finish=tool_calls stop=None out_tok=296 prompt_tok=18180 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:44:26,830] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c2c871af3ea2bfd0969ab05edf0d3656 attempt=1 -[2026-08-13 05:44:27,276] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c2c871af3ea2bfd0969ab05edf0d3656 status=200 post_dur=0.447s -[2026-08-13 05:44:49,518] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c2c871af3ea2bfd0969ab05edf0d3656 total=22688.4ms bytes=7915 finished=True finish=stop stop=None out_tok=26 prompt_tok=24144 tps=1.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:44:49,526] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=99cf6f20ee57cda5eb49ae34d8d3e834 attempt=1 -[2026-08-13 05:44:50,021] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=99cf6f20ee57cda5eb49ae34d8d3e834 status=200 post_dur=0.496s -[2026-08-13 05:45:11,468] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=99cf6f20ee57cda5eb49ae34d8d3e834 total=21942.9ms bytes=10130 finished=True finish=tool_calls stop=None out_tok=92 prompt_tok=39816 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:45:11,478] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7967bc80bba6d05abe4d2ab9846fd01d attempt=1 -[2026-08-13 05:45:11,934] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7967bc80bba6d05abe4d2ab9846fd01d status=200 post_dur=0.456s -[2026-08-13 05:45:25,330] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7967bc80bba6d05abe4d2ab9846fd01d total=13852.4ms bytes=5658 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=39078 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:45:25,335] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e82a541b8876c7ce47306d2d774519ff attempt=1 -[2026-08-13 05:45:25,740] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e82a541b8876c7ce47306d2d774519ff status=200 post_dur=0.405s -[2026-08-13 05:45:40,752] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e82a541b8876c7ce47306d2d774519ff total=15417.2ms bytes=18160 finished=True finish=tool_calls stop=None out_tok=102 prompt_tok=8582 tps=6.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:45:40,759] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9714fabdd0f00bbb50c5ac49930bf1e4 attempt=1 -[2026-08-13 05:45:41,269] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9714fabdd0f00bbb50c5ac49930bf1e4 status=200 post_dur=0.511s -[2026-08-13 05:47:26,621] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9714fabdd0f00bbb50c5ac49930bf1e4 total=105862.6ms bytes=26398 finished=True finish=stop stop=None out_tok=89 prompt_tok=71245 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:47:26,626] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3e56365379b717c910e903207fc67f9 attempt=1 -[2026-08-13 05:47:26,915] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3e56365379b717c910e903207fc67f9 status=200 post_dur=0.289s -[2026-08-13 05:47:29,466] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3e56365379b717c910e903207fc67f9 total=2840.3ms bytes=1115 finished=True finish=length stop=None out_tok=1 prompt_tok=100 tps=0.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:47:29,472] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f41046205744415148dca979685e81eb attempt=1 -[2026-08-13 05:47:29,949] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f41046205744415148dca979685e81eb status=200 post_dur=0.478s -[2026-08-13 05:47:42,309] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f41046205744415148dca979685e81eb total=12837.4ms bytes=7387 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=39937 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:47:42,316] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b3452ce4a8b51cc2663f5a17101f4c12 attempt=1 -[2026-08-13 05:47:42,316] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 22% (132/881) has_cb=True -[2026-08-13 05:47:42,764] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b3452ce4a8b51cc2663f5a17101f4c12 status=200 post_dur=0.448s -[2026-08-13 05:48:43,989] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b3452ce4a8b51cc2663f5a17101f4c12 total=61673.1ms bytes=43786 finished=True finish=stop stop=None out_tok=148 prompt_tok=34414 tps=2.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:48:43,994] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f5732edcfa094a4f5437d9960ecb1cf5 attempt=1 -[2026-08-13 05:48:44,414] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f5732edcfa094a4f5437d9960ecb1cf5 status=200 post_dur=0.420s -[2026-08-13 05:48:56,840] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f5732edcfa094a4f5437d9960ecb1cf5 total=12846.8ms bytes=24072 finished=True finish=tool_calls stop=None out_tok=126 prompt_tok=7197 tps=9.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:48:56,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7d534d19ae66525152a691c5fb1453b2 attempt=1 -[2026-08-13 05:48:57,322] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7d534d19ae66525152a691c5fb1453b2 status=200 post_dur=0.475s -[2026-08-13 05:49:13,094] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7d534d19ae66525152a691c5fb1453b2 total=16246.4ms bytes=7081 finished=True finish=tool_calls stop=None out_tok=62 prompt_tok=40779 tps=3.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:49:13,103] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6cf82700ecbf1dcdddc9a112b28a8fcc attempt=1 -[2026-08-13 05:49:13,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6cf82700ecbf1dcdddc9a112b28a8fcc status=200 post_dur=0.490s -[2026-08-13 05:49:24,609] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6cf82700ecbf1dcdddc9a112b28a8fcc total=11506.1ms bytes=6799 finished=True finish=tool_calls stop=None out_tok=64 prompt_tok=40866 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:49:24,613] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e919424545dba016f1344168295d939 attempt=1 -[2026-08-13 05:49:25,016] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e919424545dba016f1344168295d939 status=200 post_dur=0.403s -[2026-08-13 05:49:33,223] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e919424545dba016f1344168295d939 total=8609.7ms bytes=8172 finished=True finish=stop stop=None out_tok=27 prompt_tok=7656 tps=3.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:49:33,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff32a774226d5c886a88aa72901e86f2 attempt=1 -[2026-08-13 05:49:33,613] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff32a774226d5c886a88aa72901e86f2 status=200 post_dur=0.389s -[2026-08-13 05:49:42,696] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff32a774226d5c886a88aa72901e86f2 total=9471.0ms bytes=9058 finished=True finish=stop stop=None out_tok=30 prompt_tok=7767 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:49:42,702] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3137024ca0b158f7fbce02895f3b8b8a attempt=1 -[2026-08-13 05:49:43,197] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3137024ca0b158f7fbce02895f3b8b8a status=200 post_dur=0.495s -[2026-08-13 05:49:56,550] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3137024ca0b158f7fbce02895f3b8b8a total=13847.9ms bytes=4731 finished=True finish=tool_calls stop=None out_tok=59 prompt_tok=40952 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:49:56,565] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dd2b4e9f218fe5b238ad972d25e4ce9c attempt=1 -[2026-08-13 05:49:56,955] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dd2b4e9f218fe5b238ad972d25e4ce9c status=400 post_dur=0.390s -[2026-08-13 05:49:56,956] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=dd2b4e9f218fe5b238ad972d25e4ce9c status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 145398 tokens (113398 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 05:49:56,964] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=826f76de33da93cb52b68dd1e522fce0 attempt=1 -[2026-08-13 05:49:57,335] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=826f76de33da93cb52b68dd1e522fce0 status=200 post_dur=0.370s -[2026-08-13 05:50:13,719] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=826f76de33da93cb52b68dd1e522fce0 total=16754.8ms bytes=22618 finished=True finish=tool_calls stop=None out_tok=119 prompt_tok=9003 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:50:13,725] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c6619b3df2f17997a2d9a003a5c4e4a4 attempt=1 -[2026-08-13 05:50:14,226] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c6619b3df2f17997a2d9a003a5c4e4a4 status=200 post_dur=0.500s -[2026-08-13 05:50:30,823] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c6619b3df2f17997a2d9a003a5c4e4a4 total=17097.6ms bytes=5351 finished=True finish=tool_calls stop=None out_tok=66 prompt_tok=41836 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:50:30,832] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=667576259d250af5b1b7f7d5fa6cc434 attempt=1 -[2026-08-13 05:50:31,318] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=667576259d250af5b1b7f7d5fa6cc434 status=200 post_dur=0.486s -[2026-08-13 05:51:06,234] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=667576259d250af5b1b7f7d5fa6cc434 total=35402.3ms bytes=8223 finished=True finish=tool_calls stop=None out_tok=192 prompt_tok=42215 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:51:06,239] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8f202a6a1eeeb4687c0f209503e5d7bc attempt=1 -[2026-08-13 05:51:06,651] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8f202a6a1eeeb4687c0f209503e5d7bc status=200 post_dur=0.411s -[2026-08-13 05:51:26,865] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8f202a6a1eeeb4687c0f209503e5d7bc total=20626.0ms bytes=15174 finished=True finish=tool_calls stop=None out_tok=161 prompt_tok=9686 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:51:26,868] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=653bed13cc029a74eaccc52263ef6f80 attempt=1 -[2026-08-13 05:51:27,290] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=653bed13cc029a74eaccc52263ef6f80 status=200 post_dur=0.422s -[2026-08-13 05:51:39,861] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=653bed13cc029a74eaccc52263ef6f80 total=12993.5ms bytes=14630 finished=True finish=tool_calls stop=None out_tok=101 prompt_tok=9216 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:51:39,879] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f3ce331e0f79fbdcce0ad93e2af6686f attempt=1 -[2026-08-13 05:51:40,531] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f3ce331e0f79fbdcce0ad93e2af6686f status=200 post_dur=0.653s -[2026-08-13 05:57:30,759] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f3ce331e0f79fbdcce0ad93e2af6686f total=350880.2ms bytes=25095 finished=True finish=tool_calls stop=None out_tok=844 prompt_tok=116544 tps=2.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:57:30,771] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77ffdf78bc0eae6e20df04d7ebf53e40 attempt=1 -[2026-08-13 05:57:31,248] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77ffdf78bc0eae6e20df04d7ebf53e40 status=200 post_dur=0.477s -[2026-08-13 05:58:19,038] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=77ffdf78bc0eae6e20df04d7ebf53e40 total=48267.4ms bytes=22784 finished=True finish=tool_calls stop=None out_tok=142 prompt_tok=27697 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:58:19,044] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=16a2123e386b959af0777eb22067ee15 attempt=1 -[2026-08-13 05:58:19,509] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=16a2123e386b959af0777eb22067ee15 status=200 post_dur=0.465s -[2026-08-13 05:58:56,690] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=16a2123e386b959af0777eb22067ee15 total=37645.8ms bytes=8330 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=23974 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:58:56,693] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b678cc3606725f288a48f46eb1c7c835 attempt=1 -[2026-08-13 05:58:57,150] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b678cc3606725f288a48f46eb1c7c835 status=200 post_dur=0.457s -[2026-08-13 05:59:20,955] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b678cc3606725f288a48f46eb1c7c835 total=24262.6ms bytes=30895 finished=True finish=tool_calls stop=None out_tok=253 prompt_tok=7229 tps=10.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 05:59:20,958] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9958a4cb4e36707148f90bb3f0622f40 attempt=1 -[2026-08-13 05:59:21,406] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9958a4cb4e36707148f90bb3f0622f40 status=200 post_dur=0.448s -[2026-08-13 06:00:05,272] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9958a4cb4e36707148f90bb3f0622f40 total=44314.2ms bytes=13245 finished=True finish=tool_calls stop=None out_tok=416 prompt_tok=11236 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:00:05,277] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=494364739f0e59882dd28de5f5fde603 attempt=1 -[2026-08-13 06:00:05,754] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=494364739f0e59882dd28de5f5fde603 status=200 post_dur=0.477s -[2026-08-13 06:00:43,671] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=494364739f0e59882dd28de5f5fde603 total=38393.9ms bytes=11797 finished=True finish=tool_calls stop=None out_tok=79 prompt_tok=24275 tps=2.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:00:43,676] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40ae7ef2c5585416574d7b9e4ed73887 attempt=1 -[2026-08-13 06:00:44,173] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40ae7ef2c5585416574d7b9e4ed73887 status=200 post_dur=0.497s -[2026-08-13 06:01:44,375] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40ae7ef2c5585416574d7b9e4ed73887 total=60699.4ms bytes=17790 finished=True finish=tool_calls stop=None out_tok=213 prompt_tok=29279 tps=3.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:01:44,379] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=eef03a856669cef40ea937442e7b272e attempt=1 -[2026-08-13 06:01:44,812] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=eef03a856669cef40ea937442e7b272e status=200 post_dur=0.433s -[2026-08-13 06:02:09,952] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=eef03a856669cef40ea937442e7b272e total=25572.3ms bytes=14319 finished=True finish=tool_calls stop=None out_tok=192 prompt_tok=11866 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:02:09,954] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17cd2d1094cc3755b606aea1e0b43293 attempt=1 -[2026-08-13 06:02:10,365] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17cd2d1094cc3755b606aea1e0b43293 status=200 post_dur=0.411s -[2026-08-13 06:02:46,611] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17cd2d1094cc3755b606aea1e0b43293 total=36656.8ms bytes=15027 finished=True finish=tool_calls stop=None out_tok=384 prompt_tok=7689 tps=10.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:02:46,618] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=51f93e4fe99fc13f642b02b7625e12e9 attempt=1 -[2026-08-13 06:02:47,121] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=51f93e4fe99fc13f642b02b7625e12e9 status=200 post_dur=0.502s -[2026-08-13 06:03:27,412] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=51f93e4fe99fc13f642b02b7625e12e9 total=40793.9ms bytes=31664 finished=True finish=tool_calls stop=None out_tok=264 prompt_tok=42481 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:03:27,422] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9fb1a641cbd4ac84202fa6d111341dd9 attempt=1 -[2026-08-13 06:03:27,981] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9fb1a641cbd4ac84202fa6d111341dd9 status=200 post_dur=0.557s -[2026-08-13 06:05:48,301] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9fb1a641cbd4ac84202fa6d111341dd9 total=140879.0ms bytes=14027 finished=True finish=tool_calls stop=None out_tok=204 prompt_tok=73323 tps=1.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:05:48,309] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=079d189247c2005954c0ffafbc90f546 attempt=1 -[2026-08-13 06:05:48,793] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=079d189247c2005954c0ffafbc90f546 status=200 post_dur=0.484s -[2026-08-13 06:06:35,735] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=079d189247c2005954c0ffafbc90f546 total=47425.8ms bytes=7437 finished=True finish=tool_calls stop=None out_tok=118 prompt_tok=28542 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:06:35,744] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ccb525ec15458844aa875194b2936b8 attempt=1 -[2026-08-13 06:06:36,346] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ccb525ec15458844aa875194b2936b8 status=200 post_dur=0.602s -[2026-08-13 06:09:09,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8ccb525ec15458844aa875194b2936b8 total=153438.3ms bytes=21990 finished=True finish=tool_calls stop=None out_tok=265 prompt_tok=89252 tps=1.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:09:09,191] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f4a0366dc8299d3f5ac66271db2df9a attempt=1 -[2026-08-13 06:09:09,627] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f4a0366dc8299d3f5ac66271db2df9a status=200 post_dur=0.436s -[2026-08-13 06:09:38,358] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f4a0366dc8299d3f5ac66271db2df9a total=29167.6ms bytes=17295 finished=True finish=tool_calls stop=None out_tok=256 prompt_tok=11967 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:09:38,377] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cebd4d9abe71d1d144a78ed61dd6c4dc attempt=1 -[2026-08-13 06:09:39,021] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cebd4d9abe71d1d144a78ed61dd6c4dc status=200 post_dur=0.643s -[2026-08-13 06:13:39,338] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cebd4d9abe71d1d144a78ed61dd6c4dc total=240960.7ms bytes=7999 finished=True finish=tool_calls stop=None out_tok=217 prompt_tok=117319 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:13:39,351] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b91db1e602c6992d29502b3359891b9c attempt=1 -[2026-08-13 06:13:39,866] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b91db1e602c6992d29502b3359891b9c status=200 post_dur=0.515s -[2026-08-13 06:16:53,906] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b91db1e602c6992d29502b3359891b9c total=194554.7ms bytes=330072 finished=True finish=stop stop=None out_tok=1143 prompt_tok=44013 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:16:53,929] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=88449d7c1e901f5dc7b8950e03ee286a attempt=1 -[2026-08-13 06:16:54,597] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=88449d7c1e901f5dc7b8950e03ee286a status=200 post_dur=0.668s -[2026-08-13 06:18:20,452] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=88449d7c1e901f5dc7b8950e03ee286a total=86522.5ms bytes=28752 finished=True finish=tool_calls stop=None out_tok=466 prompt_tok=117785 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:18:20,464] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a52e198bc3b053b9794f62a54f694d58 attempt=1 -[2026-08-13 06:18:20,944] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a52e198bc3b053b9794f62a54f694d58 status=200 post_dur=0.480s -[2026-08-13 06:18:48,249] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a52e198bc3b053b9794f62a54f694d58 total=27785.3ms bytes=16047 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=27642 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:18:48,262] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1e8a1d182746d47cd271f17406d129a5 attempt=1 -[2026-08-13 06:18:48,270] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1e8a1d182746d47cd271f17406d129a5 status=400 post_dur=0.007s -[2026-08-13 06:18:48,270] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1e8a1d182746d47cd271f17406d129a5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 06:18:48,281] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff264c049c849d4f5084847624476a1e attempt=1 -[2026-08-13 06:18:48,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff264c049c849d4f5084847624476a1e status=200 post_dur=0.499s -[2026-08-13 06:24:33,431] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff264c049c849d4f5084847624476a1e total=345149.7ms bytes=469083 finished=True finish=tool_calls stop=None out_tok=2447 prompt_tok=47563 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:24:33,439] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74e4c061b27775a11f5fcde024f01279 attempt=1 -[2026-08-13 06:24:33,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74e4c061b27775a11f5fcde024f01279 status=200 post_dur=0.487s -[2026-08-13 06:25:04,555] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74e4c061b27775a11f5fcde024f01279 total=31116.1ms bytes=5905 finished=True finish=tool_calls stop=None out_tok=55 prompt_tok=29042 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:25:04,560] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=15ae6478087342edb4fccc7ff69d87ac attempt=1 -[2026-08-13 06:25:04,987] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=15ae6478087342edb4fccc7ff69d87ac status=200 post_dur=0.427s -[2026-08-13 06:25:27,893] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=15ae6478087342edb4fccc7ff69d87ac total=23333.1ms bytes=21580 finished=True finish=tool_calls stop=None out_tok=170 prompt_tok=15058 tps=7.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:25:27,898] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=058c90071a1209165674024c2bed02ab attempt=1 -[2026-08-13 06:25:28,383] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=058c90071a1209165674024c2bed02ab status=200 post_dur=0.485s -[2026-08-13 06:26:12,241] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=058c90071a1209165674024c2bed02ab total=44343.1ms bytes=119932 finished=True finish=stop stop=None out_tok=419 prompt_tok=29199 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:26:12,246] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=afa1d00e3635cde58cca667f6ee50fef attempt=1 -[2026-08-13 06:26:12,690] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=afa1d00e3635cde58cca667f6ee50fef status=200 post_dur=0.444s -[2026-08-13 06:26:48,709] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=afa1d00e3635cde58cca667f6ee50fef total=36462.4ms bytes=40222 finished=True finish=tool_calls stop=None out_tok=301 prompt_tok=15965 tps=8.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:26:48,721] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bfecd14065d52362c7d2fac1bfc696f2 attempt=1 -[2026-08-13 06:26:49,118] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bfecd14065d52362c7d2fac1bfc696f2 status=400 post_dur=0.397s -[2026-08-13 06:26:49,119] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bfecd14065d52362c7d2fac1bfc696f2 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 142846 tokens (110846 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 06:26:49,126] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cb98ecfe0b976a41aa206ff09cf1a59a attempt=1 -[2026-08-13 06:26:49,539] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cb98ecfe0b976a41aa206ff09cf1a59a status=200 post_dur=0.404s -[2026-08-13 06:27:08,663] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cb98ecfe0b976a41aa206ff09cf1a59a total=19536.4ms bytes=15059 finished=True finish=tool_calls stop=None out_tok=103 prompt_tok=18014 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:27:08,665] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9b50b9d920eefddcc46c2bdbe4efe955 attempt=1 -[2026-08-13 06:27:08,939] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9b50b9d920eefddcc46c2bdbe4efe955 status=200 post_dur=0.274s -[2026-08-13 06:37:52,742] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9b50b9d920eefddcc46c2bdbe4efe955 total=644076.9ms bytes=2226437 finished=True finish=stop stop=None out_tok=7663 prompt_tok=536 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:37:52,751] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ad06619f68dc319f128ab083bc9035e attempt=1 -[2026-08-13 06:37:53,215] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ad06619f68dc319f128ab083bc9035e status=200 post_dur=0.464s -[2026-08-13 06:38:30,512] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8ad06619f68dc319f128ab083bc9035e total=37760.8ms bytes=23272 finished=True finish=tool_calls stop=None out_tok=283 prompt_tok=19077 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:38:30,530] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5b8abb39b4e491d993523c0eca33a733 attempt=1 -[2026-08-13 06:38:31,201] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5b8abb39b4e491d993523c0eca33a733 status=200 post_dur=0.671s -[2026-08-13 06:40:09,057] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5b8abb39b4e491d993523c0eca33a733 total=98526.3ms bytes=15772 finished=True finish=tool_calls stop=None out_tok=484 prompt_tok=119834 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:40:09,082] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=38fa4bbb7e77481d6d22ca00a573bd1d attempt=1 -[2026-08-13 06:40:09,750] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=38fa4bbb7e77481d6d22ca00a573bd1d status=200 post_dur=0.667s -[2026-08-13 06:40:42,894] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=38fa4bbb7e77481d6d22ca00a573bd1d total=33812.4ms bytes=9271 finished=True finish=tool_calls stop=None out_tok=86 prompt_tok=121918 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:40:42,907] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6370cfdf8af78056bb4f79167cc689e1 attempt=1 -[2026-08-13 06:40:43,341] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6370cfdf8af78056bb4f79167cc689e1 status=200 post_dur=0.434s -[2026-08-13 06:41:19,387] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6370cfdf8af78056bb4f79167cc689e1 total=36479.7ms bytes=108201 finished=True finish=stop stop=None out_tok=371 prompt_tok=19748 tps=10.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:41:19,396] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 26% (176/881) has_cb=True -[2026-08-13 06:41:19,405] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e83d730f4005cd76724ac91454d8f354 attempt=1 -[2026-08-13 06:41:20,067] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e83d730f4005cd76724ac91454d8f354 status=200 post_dur=0.663s -[2026-08-13 06:42:36,485] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e83d730f4005cd76724ac91454d8f354 total=77080.2ms bytes=11372 finished=True finish=tool_calls stop=None out_tok=399 prompt_tok=120337 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:42:36,495] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1f87d33fb2f2650b0513a62f57a7f997 attempt=1 -[2026-08-13 06:42:36,921] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1f87d33fb2f2650b0513a62f57a7f997 status=200 post_dur=0.425s -[2026-08-13 06:43:03,705] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1f87d33fb2f2650b0513a62f57a7f997 total=27209.4ms bytes=10458 finished=True finish=tool_calls stop=None out_tok=226 prompt_tok=8693 tps=8.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:43:03,708] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=777c59452201b179009a4078f2a02391 attempt=1 -[2026-08-13 06:43:04,146] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=777c59452201b179009a4078f2a02391 status=200 post_dur=0.438s -[2026-08-13 06:43:33,166] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=777c59452201b179009a4078f2a02391 total=29458.0ms bytes=49268 finished=True finish=tool_calls stop=None out_tok=242 prompt_tok=20156 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:43:33,171] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=13ef3fc060013bd95196da61a1bf3df1 attempt=1 -[2026-08-13 06:43:33,609] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=13ef3fc060013bd95196da61a1bf3df1 status=200 post_dur=0.438s -[2026-08-13 06:44:04,810] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=13ef3fc060013bd95196da61a1bf3df1 total=31638.6ms bytes=92578 finished=True finish=stop stop=None out_tok=321 prompt_tok=20034 tps=10.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:44:04,813] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d0073c44f216fc29f0a510fc3fb6f88f attempt=1 -[2026-08-13 06:44:05,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d0073c44f216fc29f0a510fc3fb6f88f status=200 post_dur=0.412s -[2026-08-13 06:44:40,199] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d0073c44f216fc29f0a510fc3fb6f88f total=35385.3ms bytes=21813 finished=True finish=tool_calls stop=None out_tok=281 prompt_tok=9626 tps=7.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:44:40,202] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1e11e493ec17ec803d1b586f3fc4b8ee attempt=1 -[2026-08-13 06:44:40,656] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1e11e493ec17ec803d1b586f3fc4b8ee status=200 post_dur=0.453s -[2026-08-13 06:45:46,216] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1e11e493ec17ec803d1b586f3fc4b8ee total=66013.9ms bytes=72376 finished=True finish=tool_calls stop=None out_tok=682 prompt_tok=21261 tps=10.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:45:46,219] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ee033f311208961f19432ec0d1c43f74 attempt=1 -[2026-08-13 06:45:46,504] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ee033f311208961f19432ec0d1c43f74 status=200 post_dur=0.285s -[2026-08-13 06:48:21,912] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ee033f311208961f19432ec0d1c43f74 total=155692.9ms bytes=523799 finished=True finish=stop stop=None out_tok=1801 prompt_tok=370 tps=11.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:48:21,931] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d18c2e5de51873f089bfbe539048656e attempt=1 -[2026-08-13 06:48:22,615] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d18c2e5de51873f089bfbe539048656e status=200 post_dur=0.683s -[2026-08-13 06:49:29,610] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d18c2e5de51873f089bfbe539048656e total=67678.6ms bytes=6366 finished=True finish=tool_calls stop=None out_tok=345 prompt_tok=121045 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:49:29,618] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03b5d62aa68619706ebb2d1ea390d59e attempt=1 -[2026-08-13 06:49:29,904] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03b5d62aa68619706ebb2d1ea390d59e status=200 post_dur=0.286s -[2026-08-13 06:54:39,319] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03b5d62aa68619706ebb2d1ea390d59e total=309700.9ms bytes=1068631 finished=True finish=stop stop=None out_tok=3684 prompt_tok=536 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:54:39,341] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=966d726aa90dd5d5b683f08f61b54b3d attempt=1 -[2026-08-13 06:54:40,035] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=966d726aa90dd5d5b683f08f61b54b3d status=200 post_dur=0.681s -[2026-08-13 06:55:59,893] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=966d726aa90dd5d5b683f08f61b54b3d total=80552.3ms bytes=21958 finished=True finish=tool_calls stop=None out_tok=413 prompt_tok=121392 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:55:59,905] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45573e6a72fff1a858f00441c401c4c4 attempt=1 -[2026-08-13 06:56:00,368] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45573e6a72fff1a858f00441c401c4c4 status=200 post_dur=0.463s -[2026-08-13 06:56:36,942] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45573e6a72fff1a858f00441c401c4c4 total=37037.0ms bytes=109135 finished=True finish=stop stop=None out_tok=378 prompt_tok=21583 tps=10.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:56:36,947] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=76c94ffa10f26e0703a5abb6aa70e111 attempt=1 -[2026-08-13 06:56:37,400] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=76c94ffa10f26e0703a5abb6aa70e111 status=200 post_dur=0.453s -[2026-08-13 06:56:59,597] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=76c94ffa10f26e0703a5abb6aa70e111 total=22649.9ms bytes=61878 finished=True finish=stop stop=None out_tok=213 prompt_tok=21832 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:56:59,671] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=71d4542befba35217656f1d77ae23ee3 attempt=1 -[2026-08-13 06:57:00,109] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=71d4542befba35217656f1d77ae23ee3 status=400 post_dur=0.438s -[2026-08-13 06:57:00,109] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=71d4542befba35217656f1d77ae23ee3 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 131962 tokens in the messages, Please reduce the length of the messages. (retryable=False, attempt=1) -[2026-08-13 06:57:00,119] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a374aadb665f75a3226b2641582b9df0 attempt=1 -[2026-08-13 06:57:00,509] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a374aadb665f75a3226b2641582b9df0 status=200 post_dur=0.390s -[2026-08-13 06:57:14,722] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a374aadb665f75a3226b2641582b9df0 total=14603.3ms bytes=10182 finished=True finish=stop stop=None out_tok=34 prompt_tok=7390 tps=2.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:57:14,724] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f69182640ddc1ee2d8fb9e0354826a6c attempt=1 -[2026-08-13 06:57:15,138] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f69182640ddc1ee2d8fb9e0354826a6c status=200 post_dur=0.413s -[2026-08-13 06:57:26,149] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f69182640ddc1ee2d8fb9e0354826a6c total=11424.8ms bytes=11671 finished=True finish=tool_calls stop=None out_tok=64 prompt_tok=7479 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:57:26,161] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=98fef617f4f3b71afa4ed7f95fd3e8cf attempt=1 -[2026-08-13 06:57:26,169] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=98fef617f4f3b71afa4ed7f95fd3e8cf status=400 post_dur=0.006s -[2026-08-13 06:57:26,169] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=98fef617f4f3b71afa4ed7f95fd3e8cf status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 06:57:26,177] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e0931547ccd69d58ff457e4e8a232a2e attempt=1 -[2026-08-13 06:57:26,584] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e0931547ccd69d58ff457e4e8a232a2e status=200 post_dur=0.406s -[2026-08-13 06:58:11,620] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e0931547ccd69d58ff457e4e8a232a2e total=45442.9ms bytes=33996 finished=True finish=tool_calls stop=None out_tok=507 prompt_tok=7229 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 06:58:11,621] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=59c442b5a51cadb423c6b60f147cb1d6 attempt=1 -[2026-08-13 06:58:11,913] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=59c442b5a51cadb423c6b60f147cb1d6 status=200 post_dur=0.292s -[2026-08-13 07:01:00,654] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=59c442b5a51cadb423c6b60f147cb1d6 total=169032.5ms bytes=574519 finished=True finish=stop stop=None out_tok=1975 prompt_tok=674 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:01:00,658] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad97d90fb5b28a960b1c03c66639d428 attempt=1 -[2026-08-13 07:01:01,105] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad97d90fb5b28a960b1c03c66639d428 status=200 post_dur=0.447s -[2026-08-13 07:01:23,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ad97d90fb5b28a960b1c03c66639d428 total=23268.5ms bytes=9667 finished=True finish=tool_calls stop=None out_tok=131 prompt_tok=7646 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:01:23,929] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5de2573e7ffdf925143010f6e6d9c571 attempt=1 -[2026-08-13 07:01:24,345] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5de2573e7ffdf925143010f6e6d9c571 status=200 post_dur=0.417s -[2026-08-13 07:01:57,222] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5de2573e7ffdf925143010f6e6d9c571 total=33293.3ms bytes=27414 finished=True finish=tool_calls stop=None out_tok=304 prompt_tok=8402 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:01:57,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b68737ce69afc08685d35bf935d2eb2 attempt=1 -[2026-08-13 07:01:57,649] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b68737ce69afc08685d35bf935d2eb2 status=200 post_dur=0.425s -[2026-08-13 07:02:43,198] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b68737ce69afc08685d35bf935d2eb2 total=45973.3ms bytes=67424 finished=True finish=tool_calls stop=None out_tok=419 prompt_tok=11385 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:02:43,201] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bb6de925ae6246f4b54248dbf225fb8b attempt=1 -[2026-08-13 07:02:43,637] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bb6de925ae6246f4b54248dbf225fb8b status=200 post_dur=0.436s -[2026-08-13 07:03:04,351] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bb6de925ae6246f4b54248dbf225fb8b total=21149.8ms bytes=42176 finished=True finish=stop stop=None out_tok=143 prompt_tok=9348 tps=6.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:03:04,354] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7c0c1024bfb5552c607eb33016de858 attempt=1 -[2026-08-13 07:03:04,775] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7c0c1024bfb5552c607eb33016de858 status=200 post_dur=0.421s -[2026-08-13 07:03:30,152] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7c0c1024bfb5552c607eb33016de858 total=25798.5ms bytes=72643 finished=True finish=stop stop=None out_tok=247 prompt_tok=9998 tps=9.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:03:30,171] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=009dde816fc3acb4cc10671f347bbd03 attempt=1 -[2026-08-13 07:03:30,833] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=009dde816fc3acb4cc10671f347bbd03 status=200 post_dur=0.663s -[2026-08-13 07:04:13,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=009dde816fc3acb4cc10671f347bbd03 total=43813.8ms bytes=7476 finished=True finish=tool_calls stop=None out_tok=136 prompt_tok=124666 tps=3.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:04:13,994] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=458a7fd31d1b277ba75cc38c2eb73c1d attempt=1 -[2026-08-13 07:04:14,428] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=458a7fd31d1b277ba75cc38c2eb73c1d status=200 post_dur=0.433s -[2026-08-13 07:04:55,047] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=458a7fd31d1b277ba75cc38c2eb73c1d total=41052.3ms bytes=25026 finished=True finish=tool_calls stop=None out_tok=315 prompt_tok=9805 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:04:55,049] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17b6876da090ee233e27a16837a4388d attempt=1 -[2026-08-13 07:04:55,485] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17b6876da090ee233e27a16837a4388d status=200 post_dur=0.436s -[2026-08-13 07:05:14,401] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17b6876da090ee233e27a16837a4388d total=19351.4ms bytes=14250 finished=True finish=tool_calls stop=None out_tok=160 prompt_tok=11629 tps=8.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:05:14,404] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44ee2e606690216969520a15bba4e844 attempt=1 -[2026-08-13 07:05:14,824] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44ee2e606690216969520a15bba4e844 status=200 post_dur=0.421s -[2026-08-13 07:05:45,808] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44ee2e606690216969520a15bba4e844 total=31404.7ms bytes=35232 finished=True finish=tool_calls stop=None out_tok=236 prompt_tok=10021 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:05:45,812] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48f34154f82351bd849d658039fa2da1 attempt=1 -[2026-08-13 07:05:46,238] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48f34154f82351bd849d658039fa2da1 status=200 post_dur=0.426s -[2026-08-13 07:06:06,804] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48f34154f82351bd849d658039fa2da1 total=20991.9ms bytes=28710 finished=True finish=tool_calls stop=None out_tok=142 prompt_tok=7197 tps=6.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:06:06,819] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=554c0cc7053b81d2ac40541165710ef5 attempt=1 -[2026-08-13 07:06:06,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=554c0cc7053b81d2ac40541165710ef5 status=400 post_dur=0.007s -[2026-08-13 07:06:06,826] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=554c0cc7053b81d2ac40541165710ef5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 07:06:06,835] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c4908254d2033142cf448b88583d10a0 attempt=1 -[2026-08-13 07:06:07,258] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c4908254d2033142cf448b88583d10a0 status=200 post_dur=0.423s -[2026-08-13 07:06:31,652] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c4908254d2033142cf448b88583d10a0 total=24817.2ms bytes=17141 finished=True finish=tool_calls stop=None out_tok=193 prompt_tok=11879 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:06:31,654] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6c12607de0607a2542939b0805f7e16f attempt=1 -[2026-08-13 07:06:32,081] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6c12607de0607a2542939b0805f7e16f status=200 post_dur=0.426s -[2026-08-13 07:06:43,338] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6c12607de0607a2542939b0805f7e16f total=11683.4ms bytes=9962 finished=True finish=tool_calls stop=None out_tok=70 prompt_tok=7419 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:06:43,340] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=eab9e55d270895fac52faab687b358d6 attempt=1 -[2026-08-13 07:06:43,764] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=eab9e55d270895fac52faab687b358d6 status=200 post_dur=0.424s -[2026-08-13 07:06:58,347] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=eab9e55d270895fac52faab687b358d6 total=15006.3ms bytes=9796 finished=True finish=tool_calls stop=None out_tok=91 prompt_tok=12157 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:06:58,349] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d5066b7438d6fab3349d202019b3d923 attempt=1 -[2026-08-13 07:06:58,746] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d5066b7438d6fab3349d202019b3d923 status=200 post_dur=0.397s -[2026-08-13 07:07:07,970] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d5066b7438d6fab3349d202019b3d923 total=9621.4ms bytes=11672 finished=True finish=stop stop=None out_tok=39 prompt_tok=7703 tps=4.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:07:07,988] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f6ba3a16a963f964c09513ef3f2ecdf4 attempt=1 -[2026-08-13 07:07:08,663] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f6ba3a16a963f964c09513ef3f2ecdf4 status=200 post_dur=0.674s -[2026-08-13 07:07:45,218] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f6ba3a16a963f964c09513ef3f2ecdf4 total=37230.2ms bytes=7481 finished=True finish=tool_calls stop=None out_tok=78 prompt_tok=126066 tps=2.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:07:45,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77a2c20c0bf4bd84bd95d71569134530 attempt=1 -[2026-08-13 07:07:45,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77a2c20c0bf4bd84bd95d71569134530 status=200 post_dur=0.682s -[2026-08-13 07:09:00,216] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=77a2c20c0bf4bd84bd95d71569134530 total=74971.7ms bytes=11222 finished=True finish=tool_calls stop=None out_tok=327 prompt_tok=127279 tps=4.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:09:00,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f525460d67a79e7c9785eeca7c9c368b attempt=1 -[2026-08-13 07:09:00,656] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f525460d67a79e7c9785eeca7c9c368b status=200 post_dur=0.430s -[2026-08-13 07:09:10,615] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f525460d67a79e7c9785eeca7c9c368b total=10389.5ms bytes=12844 finished=True finish=stop stop=None out_tok=43 prompt_tok=7814 tps=4.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:09:10,617] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f565b7fa99ac804074f2c75449643828 attempt=1 -[2026-08-13 07:09:11,013] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f565b7fa99ac804074f2c75449643828 status=200 post_dur=0.396s -[2026-08-13 07:09:16,860] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f565b7fa99ac804074f2c75449643828 total=6242.8ms bytes=7569 finished=True finish=stop stop=None out_tok=25 prompt_tok=8074 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:09:16,862] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9133cdea736e26b36553213ed50256df attempt=1 -[2026-08-13 07:09:17,247] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9133cdea736e26b36553213ed50256df status=200 post_dur=0.385s -[2026-08-13 07:09:22,693] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9133cdea736e26b36553213ed50256df total=5831.2ms bytes=7576 finished=True finish=stop stop=None out_tok=25 prompt_tok=7944 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:09:22,711] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ae7a4ff3045ad8b088a55a71be801710 attempt=1 -[2026-08-13 07:09:23,375] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ae7a4ff3045ad8b088a55a71be801710 status=200 post_dur=0.664s -[2026-08-13 07:17:05,748] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ae7a4ff3045ad8b088a55a71be801710 total=463036.7ms bytes=10624 finished=True finish=tool_calls stop=None out_tok=2484 prompt_tok=128589 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:17:05,760] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b645cf1d05ada3289f87b46397f9efc attempt=1 -[2026-08-13 07:17:06,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b645cf1d05ada3289f87b46397f9efc status=200 post_dur=0.468s -[2026-08-13 07:17:39,359] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b645cf1d05ada3289f87b46397f9efc total=33599.5ms bytes=32383 finished=True finish=tool_calls stop=None out_tok=292 prompt_tok=12841 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:17:39,362] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0659326491f8067412c4f1c8f9ae6c01 attempt=1 -[2026-08-13 07:17:39,814] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0659326491f8067412c4f1c8f9ae6c01 status=200 post_dur=0.452s -[2026-08-13 07:18:03,647] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0659326491f8067412c4f1c8f9ae6c01 total=24284.9ms bytes=19235 finished=True finish=tool_calls stop=None out_tok=187 prompt_tok=13182 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:18:03,649] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=37986f79399dfb3e4b1b70aa905c22e6 attempt=1 -[2026-08-13 07:18:03,938] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=37986f79399dfb3e4b1b70aa905c22e6 status=200 post_dur=0.289s -[2026-08-13 07:20:40,150] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=37986f79399dfb3e4b1b70aa905c22e6 total=156501.5ms bytes=528292 finished=True finish=stop stop=None out_tok=1815 prompt_tok=571 tps=11.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:20:40,154] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48458299fcceb2bf195b62b03f2590a7 attempt=1 -[2026-08-13 07:20:40,601] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48458299fcceb2bf195b62b03f2590a7 status=200 post_dur=0.447s -[2026-08-13 07:21:12,804] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48458299fcceb2bf195b62b03f2590a7 total=32650.3ms bytes=21818 finished=True finish=tool_calls stop=None out_tok=299 prompt_tok=13381 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:21:12,823] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cf84a1354f68d39cea0201b556ad5c96 attempt=1 -[2026-08-13 07:21:13,490] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cf84a1354f68d39cea0201b556ad5c96 status=200 post_dur=0.667s -[2026-08-13 07:21:53,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cf84a1354f68d39cea0201b556ad5c96 total=41137.8ms bytes=5954 finished=True finish=tool_calls stop=None out_tok=186 prompt_tok=128002 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:21:53,969] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e1bb149f25198dfd6e3cabea2fc78fb attempt=1 -[2026-08-13 07:21:53,970] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 30% (220/881) has_cb=True -[2026-08-13 07:21:54,265] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e1bb149f25198dfd6e3cabea2fc78fb status=200 post_dur=0.295s -[2026-08-13 07:31:53,233] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e1bb149f25198dfd6e3cabea2fc78fb total=599263.8ms bytes=2049271 finished=True finish=stop stop=None out_tok=7028 prompt_tok=4570 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:31:53,259] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d566dbf5f98af5b5e4a14afb454bcd4a attempt=1 -[2026-08-13 07:31:54,200] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d566dbf5f98af5b5e4a14afb454bcd4a status=200 post_dur=0.941s -[2026-08-13 07:32:19,918] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d566dbf5f98af5b5e4a14afb454bcd4a total=26659.1ms bytes=6371 finished=True finish=tool_calls stop=None out_tok=107 prompt_tok=128239 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:32:19,928] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1bffc6d6fac1750d40cc0e93a6ef3758 attempt=1 -[2026-08-13 07:32:20,219] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1bffc6d6fac1750d40cc0e93a6ef3758 status=200 post_dur=0.291s -[2026-08-13 07:47:36,316] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1bffc6d6fac1750d40cc0e93a6ef3758 total=916388.1ms bytes=3113537 finished=True finish=stop stop=None out_tok=10732 prompt_tok=7026 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:47:36,327] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23682db8af25c58464b1efba92034f89 attempt=1 -[2026-08-13 07:47:36,791] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23682db8af25c58464b1efba92034f89 status=200 post_dur=0.465s -[2026-08-13 07:48:08,454] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=23682db8af25c58464b1efba92034f89 total=32127.5ms bytes=17882 finished=True finish=tool_calls stop=None out_tok=311 prompt_tok=14926 tps=9.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:48:08,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40cd8d8aed528adbf0c19beeb7f32ea0 attempt=1 -[2026-08-13 07:48:08,952] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40cd8d8aed528adbf0c19beeb7f32ea0 status=200 post_dur=0.494s -[2026-08-13 07:48:33,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40cd8d8aed528adbf0c19beeb7f32ea0 total=24937.6ms bytes=21258 finished=True finish=tool_calls stop=None out_tok=238 prompt_tok=15858 tps=9.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:48:33,405] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=efcd74850ca1e15747878498ed0d6a3a attempt=1 -[2026-08-13 07:48:33,737] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=efcd74850ca1e15747878498ed0d6a3a status=400 post_dur=0.330s -[2026-08-13 07:48:33,737] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=efcd74850ca1e15747878498ed0d6a3a status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 144081 tokens (78545 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 07:48:33,742] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c4f19bd7d83f90e15736800abb3d9c11 attempt=1 -[2026-08-13 07:48:34,003] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c4f19bd7d83f90e15736800abb3d9c11 status=200 post_dur=0.261s -[2026-08-13 07:51:29,350] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c4f19bd7d83f90e15736800abb3d9c11 total=175608.1ms bytes=590073 finished=True finish=length stop=None out_tok=2048 prompt_tok=620 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:51:29,354] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=315ef0cd61b2a648f9a133900198f1cf attempt=1 -[2026-08-13 07:51:29,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=315ef0cd61b2a648f9a133900198f1cf status=200 post_dur=0.471s -[2026-08-13 07:52:00,329] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=315ef0cd61b2a648f9a133900198f1cf total=30974.6ms bytes=15923 finished=True finish=tool_calls stop=None out_tok=257 prompt_tok=16471 tps=8.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:52:00,333] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48155b6bee74a3bae6e9b0e741b22729 attempt=1 -[2026-08-13 07:52:00,778] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48155b6bee74a3bae6e9b0e741b22729 status=200 post_dur=0.445s -[2026-08-13 07:52:19,488] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48155b6bee74a3bae6e9b0e741b22729 total=19154.9ms bytes=30239 finished=True finish=stop stop=None out_tok=103 prompt_tok=16668 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:52:19,490] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e0911ecde78482595ec62539993f1a51 attempt=1 -[2026-08-13 07:52:19,766] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e0911ecde78482595ec62539993f1a51 status=200 post_dur=0.276s -[2026-08-13 07:55:55,868] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e0911ecde78482595ec62539993f1a51 total=216378.5ms bytes=731108 finished=True finish=stop stop=None out_tok=2511 prompt_tok=365 tps=11.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:55:55,871] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f1b45eab94135ecedbd73838841b83dd attempt=1 -[2026-08-13 07:55:56,170] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f1b45eab94135ecedbd73838841b83dd status=200 post_dur=0.299s -[2026-08-13 07:58:51,267] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f1b45eab94135ecedbd73838841b83dd total=175396.0ms bytes=596157 finished=True finish=length stop=None out_tok=2048 prompt_tok=347 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:58:51,270] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=25c94e38181bd1e5ae0bfc0937fd46f3 attempt=1 -[2026-08-13 07:58:51,715] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=25c94e38181bd1e5ae0bfc0937fd46f3 status=200 post_dur=0.445s -[2026-08-13 07:59:27,017] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=25c94e38181bd1e5ae0bfc0937fd46f3 total=35747.2ms bytes=36709 finished=True finish=tool_calls stop=None out_tok=410 prompt_tok=7229 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:59:27,019] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea138743339a5ff7727e824177ddc131 attempt=1 -[2026-08-13 07:59:27,446] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea138743339a5ff7727e824177ddc131 status=200 post_dur=0.427s -[2026-08-13 07:59:39,016] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea138743339a5ff7727e824177ddc131 total=11996.9ms bytes=24351 finished=True finish=tool_calls stop=None out_tok=127 prompt_tok=7197 tps=10.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:59:39,018] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4974db681bd93f2c8b2352385fdd97c3 attempt=1 -[2026-08-13 07:59:39,421] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4974db681bd93f2c8b2352385fdd97c3 status=200 post_dur=0.403s -[2026-08-13 07:59:58,823] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4974db681bd93f2c8b2352385fdd97c3 total=19804.9ms bytes=10746 finished=True finish=tool_calls stop=None out_tok=100 prompt_tok=7307 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 07:59:58,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49b88cd23e172cd2b84ae1c44804a9ea attempt=1 -[2026-08-13 07:59:59,236] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49b88cd23e172cd2b84ae1c44804a9ea status=200 post_dur=0.410s -[2026-08-13 08:00:11,876] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=49b88cd23e172cd2b84ae1c44804a9ea total=13050.6ms bytes=10217 finished=True finish=tool_calls stop=None out_tok=101 prompt_tok=7759 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:00:11,894] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e0d5a0196fbbbe5a3bf287e9d26718a attempt=1 -[2026-08-13 08:00:12,574] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e0d5a0196fbbbe5a3bf287e9d26718a status=200 post_dur=0.679s -[2026-08-13 08:01:02,876] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3e0d5a0196fbbbe5a3bf287e9d26718a total=50982.4ms bytes=5783 finished=True finish=tool_calls stop=None out_tok=213 prompt_tok=130860 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:01:02,887] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f4ba4ddb09108e29c6acde545ccf2ce2 attempt=1 -[2026-08-13 08:01:03,325] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f4ba4ddb09108e29c6acde545ccf2ce2 status=200 post_dur=0.438s -[2026-08-13 08:01:13,597] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f4ba4ddb09108e29c6acde545ccf2ce2 total=10710.0ms bytes=22833 finished=True finish=stop stop=None out_tok=77 prompt_tok=8029 tps=7.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:01:13,599] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9f749b36e5f09b5dadad96cbc136ca65 attempt=1 -[2026-08-13 08:01:14,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9f749b36e5f09b5dadad96cbc136ca65 status=200 post_dur=0.409s -[2026-08-13 08:01:41,744] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9f749b36e5f09b5dadad96cbc136ca65 total=28145.2ms bytes=13368 finished=True finish=tool_calls stop=None out_tok=228 prompt_tok=9450 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:01:41,747] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7171fc3bc036a7e3f7f8483edd20c795 attempt=1 -[2026-08-13 08:01:42,187] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7171fc3bc036a7e3f7f8483edd20c795 status=200 post_dur=0.440s -[2026-08-13 08:02:02,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7171fc3bc036a7e3f7f8483edd20c795 total=21103.6ms bytes=30456 finished=True finish=stop stop=None out_tok=103 prompt_tok=9787 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:02:02,853] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6ebcfc88241a7349a60a9b64addf2725 attempt=1 -[2026-08-13 08:02:03,271] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6ebcfc88241a7349a60a9b64addf2725 status=200 post_dur=0.418s -[2026-08-13 08:02:15,779] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6ebcfc88241a7349a60a9b64addf2725 total=12926.3ms bytes=19739 finished=True finish=stop stop=None out_tok=67 prompt_tok=8386 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:02:15,782] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff73752fbb7433419099a8511754f987 attempt=1 -[2026-08-13 08:02:16,201] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff73752fbb7433419099a8511754f987 status=200 post_dur=0.419s -[2026-08-13 08:02:26,876] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff73752fbb7433419099a8511754f987 total=11093.8ms bytes=23767 finished=True finish=stop stop=None out_tok=81 prompt_tok=8608 tps=7.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:02:26,935] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=90d12d82d9614d497c44f712d66d057d attempt=1 -[2026-08-13 08:02:27,349] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=90d12d82d9614d497c44f712d66d057d status=400 post_dur=0.413s -[2026-08-13 08:02:27,349] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=90d12d82d9614d497c44f712d66d057d status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 131150 tokens in the messages, Please reduce the length of the messages. (retryable=False, attempt=1) -[2026-08-13 08:02:27,359] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=78a85b9994fd97dcbc014c08a24db6d0 attempt=1 -[2026-08-13 08:02:27,762] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=78a85b9994fd97dcbc014c08a24db6d0 status=200 post_dur=0.402s -[2026-08-13 08:02:50,229] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=78a85b9994fd97dcbc014c08a24db6d0 total=22869.8ms bytes=51009 finished=True finish=stop stop=None out_tok=175 prompt_tok=8615 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:02:50,232] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5662b2bbd9e414513008b4bceb92f818 attempt=1 -[2026-08-13 08:02:50,666] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5662b2bbd9e414513008b4bceb92f818 status=200 post_dur=0.434s -[2026-08-13 08:03:19,283] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5662b2bbd9e414513008b4bceb92f818 total=29051.4ms bytes=73136 finished=True finish=stop stop=None out_tok=247 prompt_tok=10916 tps=8.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:03:19,286] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ddb6a8dffccee8b7bfbd59c50410c50 attempt=1 -[2026-08-13 08:03:19,707] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ddb6a8dffccee8b7bfbd59c50410c50 status=200 post_dur=0.421s -[2026-08-13 08:03:47,662] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ddb6a8dffccee8b7bfbd59c50410c50 total=28376.0ms bytes=20711 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=8831 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:03:47,664] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dc73696f73b0fe3f59a59ffe53007225 attempt=1 -[2026-08-13 08:03:47,945] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dc73696f73b0fe3f59a59ffe53007225 status=200 post_dur=0.281s -[2026-08-13 08:06:39,749] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dc73696f73b0fe3f59a59ffe53007225 total=172085.6ms bytes=586873 finished=True finish=stop stop=None out_tok=2018 prompt_tok=392 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:06:39,752] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6375e08fbebeb80f77edcc00d59b289 attempt=1 -[2026-08-13 08:06:40,047] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6375e08fbebeb80f77edcc00d59b289 status=200 post_dur=0.294s -[2026-08-13 08:08:47,356] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6375e08fbebeb80f77edcc00d59b289 total=127603.9ms bytes=440857 finished=True finish=stop stop=None out_tok=1515 prompt_tok=392 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:08:47,374] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d427f650b2405bc6faf0259ec53fa73 attempt=1 -[2026-08-13 08:08:47,791] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d427f650b2405bc6faf0259ec53fa73 status=400 post_dur=0.417s -[2026-08-13 08:08:47,791] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3d427f650b2405bc6faf0259ec53fa73 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 157231 tokens (125231 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:08:47,802] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=50b915b9dfb222d7395005cef54051a5 attempt=1 -[2026-08-13 08:08:48,271] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=50b915b9dfb222d7395005cef54051a5 status=200 post_dur=0.468s -[2026-08-13 08:09:34,043] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=50b915b9dfb222d7395005cef54051a5 total=46240.8ms bytes=12913 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=31595 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:09:34,046] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c6b7b47ee76b8533b7a98cc16c313084 attempt=1 -[2026-08-13 08:09:34,474] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c6b7b47ee76b8533b7a98cc16c313084 status=200 post_dur=0.427s -[2026-08-13 08:09:59,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c6b7b47ee76b8533b7a98cc16c313084 total=25778.3ms bytes=15567 finished=True finish=tool_calls stop=None out_tok=152 prompt_tok=8030 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:09:59,830] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ec2ff62b72bbcd3995e27d992648334 attempt=1 -[2026-08-13 08:10:00,327] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ec2ff62b72bbcd3995e27d992648334 status=200 post_dur=0.498s -[2026-08-13 08:11:06,646] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ec2ff62b72bbcd3995e27d992648334 total=66816.4ms bytes=33620 finished=True finish=tool_calls stop=None out_tok=197 prompt_tok=34100 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:11:06,650] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3cefef050a3ee8ca33860c658f11845c attempt=1 -[2026-08-13 08:11:07,084] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3cefef050a3ee8ca33860c658f11845c status=200 post_dur=0.434s -[2026-08-13 08:11:36,047] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3cefef050a3ee8ca33860c658f11845c total=29396.2ms bytes=16376 finished=True finish=tool_calls stop=None out_tok=231 prompt_tok=10219 tps=7.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:11:36,049] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6be2b53962c07f34e880a823f1851772 attempt=1 -[2026-08-13 08:11:36,472] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6be2b53962c07f34e880a823f1851772 status=200 post_dur=0.423s -[2026-08-13 08:12:04,045] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6be2b53962c07f34e880a823f1851772 total=27995.8ms bytes=14673 finished=True finish=tool_calls stop=None out_tok=235 prompt_tok=10116 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:12:04,052] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea089eece066038a01e1b9b1e6364808 attempt=1 -[2026-08-13 08:12:04,605] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea089eece066038a01e1b9b1e6364808 status=200 post_dur=0.553s -[2026-08-13 08:14:06,829] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea089eece066038a01e1b9b1e6364808 total=122777.0ms bytes=106145 finished=True finish=tool_calls stop=None out_tok=479 prompt_tok=62737 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:14:06,842] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=de6c6ace906958e9ff36c812a170106f attempt=1 -[2026-08-13 08:14:07,153] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=de6c6ace906958e9ff36c812a170106f status=400 post_dur=0.312s -[2026-08-13 08:14:07,154] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=de6c6ace906958e9ff36c812a170106f status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 131165 tokens (65629 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:14:07,159] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aa52e474fe7d8b89a4059e7a699515ad attempt=1 -[2026-08-13 08:14:07,566] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aa52e474fe7d8b89a4059e7a699515ad status=200 post_dur=0.407s -[2026-08-13 08:14:32,629] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=aa52e474fe7d8b89a4059e7a699515ad total=25470.5ms bytes=14620 finished=True finish=tool_calls stop=None out_tok=221 prompt_tok=10728 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:14:32,632] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1758f90e7869e81ba0a715fe723dcce5 attempt=1 -[2026-08-13 08:14:33,067] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1758f90e7869e81ba0a715fe723dcce5 status=200 post_dur=0.435s -[2026-08-13 08:15:04,027] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1758f90e7869e81ba0a715fe723dcce5 total=31395.7ms bytes=29964 finished=True finish=tool_calls stop=None out_tok=263 prompt_tok=7438 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:15:04,030] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e56c04311574c6d317528df03e22ff8d attempt=1 -[2026-08-13 08:15:04,454] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e56c04311574c6d317528df03e22ff8d status=200 post_dur=0.424s -[2026-08-13 08:15:24,807] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e56c04311574c6d317528df03e22ff8d total=20777.4ms bytes=24739 finished=True finish=tool_calls stop=None out_tok=232 prompt_tok=7229 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:15:24,814] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44c3fc821cbb980be109c776553f457f attempt=1 -[2026-08-13 08:15:25,324] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44c3fc821cbb980be109c776553f457f status=200 post_dur=0.509s -[2026-08-13 08:17:02,005] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44c3fc821cbb980be109c776553f457f total=97191.1ms bytes=55668 finished=True finish=tool_calls stop=None out_tok=249 prompt_tok=46759 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:17:02,011] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=da2858b1e39d4081b580f847d3e3f155 attempt=1 -[2026-08-13 08:17:02,461] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=da2858b1e39d4081b580f847d3e3f155 status=200 post_dur=0.450s -[2026-08-13 08:17:30,273] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=da2858b1e39d4081b580f847d3e3f155 total=28261.9ms bytes=17599 finished=True finish=tool_calls stop=None out_tok=231 prompt_tok=11769 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:17:30,275] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=69cdc6f065632f2d1d96158896d8c6a7 attempt=1 -[2026-08-13 08:17:30,706] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=69cdc6f065632f2d1d96158896d8c6a7 status=200 post_dur=0.430s -[2026-08-13 08:17:59,344] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=69cdc6f065632f2d1d96158896d8c6a7 total=29069.0ms bytes=12597 finished=True finish=tool_calls stop=None out_tok=261 prompt_tok=8405 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:17:59,358] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4cf272cf5d7e74a687b41f792ebb351e attempt=1 -[2026-08-13 08:17:59,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4cf272cf5d7e74a687b41f792ebb351e status=400 post_dur=0.423s -[2026-08-13 08:17:59,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4cf272cf5d7e74a687b41f792ebb351e status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 159840 tokens (127840 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:17:59,789] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b7d8d571e00650e7f699591ac8f87918 attempt=1 -[2026-08-13 08:18:00,189] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b7d8d571e00650e7f699591ac8f87918 status=200 post_dur=0.399s -[2026-08-13 08:18:12,186] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b7d8d571e00650e7f699591ac8f87918 total=12396.8ms bytes=21987 finished=True finish=stop stop=None out_tok=75 prompt_tok=7530 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:18:12,188] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=127c1094b08c47e9a10959202bef52a2 attempt=1 -[2026-08-13 08:18:12,599] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=127c1094b08c47e9a10959202bef52a2 status=200 post_dur=0.411s -[2026-08-13 08:18:21,544] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=127c1094b08c47e9a10959202bef52a2 total=9355.6ms bytes=9038 finished=True finish=stop stop=None out_tok=30 prompt_tok=7706 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:18:21,547] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0932353bade1e13b7847c64c1ecfd729 attempt=1 -[2026-08-13 08:18:21,547] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 34% (264/881) has_cb=True -[2026-08-13 08:18:21,976] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0932353bade1e13b7847c64c1ecfd729 status=200 post_dur=0.429s -[2026-08-13 08:19:56,384] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0932353bade1e13b7847c64c1ecfd729 total=94837.8ms bytes=281765 finished=True finish=stop stop=None out_tok=982 prompt_tok=10844 tps=10.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:19:56,388] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f401ee7d8921bc0e3fa2e05e5ceee02b attempt=1 -[2026-08-13 08:19:56,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f401ee7d8921bc0e3fa2e05e5ceee02b status=200 post_dur=0.445s -[2026-08-13 08:20:46,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f401ee7d8921bc0e3fa2e05e5ceee02b total=50300.6ms bytes=21656 finished=True finish=tool_calls stop=None out_tok=496 prompt_tok=9718 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:20:46,692] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bba8acbaa74a3dc870febf0bfdbcf32e attempt=1 -[2026-08-13 08:20:47,142] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bba8acbaa74a3dc870febf0bfdbcf32e status=200 post_dur=0.450s -[2026-08-13 08:21:06,917] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bba8acbaa74a3dc870febf0bfdbcf32e total=20225.2ms bytes=38027 finished=True finish=stop stop=None out_tok=129 prompt_tok=12369 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:21:06,925] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c7dc349c3ee6663fc23399a22b9654f attempt=1 -[2026-08-13 08:21:07,428] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c7dc349c3ee6663fc23399a22b9654f status=200 post_dur=0.503s -[2026-08-13 08:22:17,704] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c7dc349c3ee6663fc23399a22b9654f total=70778.9ms bytes=10123 finished=True finish=tool_calls stop=None out_tok=96 prompt_tok=43466 tps=1.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:22:17,720] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=305b7df9874d7557abe9b73388420205 attempt=1 -[2026-08-13 08:22:17,731] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=305b7df9874d7557abe9b73388420205 status=400 post_dur=0.011s -[2026-08-13 08:22:17,731] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=305b7df9874d7557abe9b73388420205 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 08:22:17,741] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b4c7ff25b9f196398801d56e1e9179a attempt=1 -[2026-08-13 08:22:18,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b4c7ff25b9f196398801d56e1e9179a status=200 post_dur=0.441s -[2026-08-13 08:22:51,537] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b4c7ff25b9f196398801d56e1e9179a total=33796.1ms bytes=21104 finished=True finish=tool_calls stop=None out_tok=241 prompt_tok=11114 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:22:51,540] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e attempt=1 -[2026-08-13 08:22:51,997] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e status=200 post_dur=0.456s -[2026-08-13 08:23:06,236] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e total=14696.0ms bytes=18017 finished=True finish=tool_calls stop=None out_tok=105 prompt_tok=14186 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:23:06,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 attempt=1 -[2026-08-13 08:23:06,540] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 status=400 post_dur=0.296s -[2026-08-13 08:23:06,540] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 135433 tokens (69897 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:23:06,546] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c3db67d9e27ff560abfb31e5a355ea4 attempt=1 -[2026-08-13 08:23:06,970] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c3db67d9e27ff560abfb31e5a355ea4 status=200 post_dur=0.423s -[2026-08-13 08:23:44,566] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c3db67d9e27ff560abfb31e5a355ea4 total=38019.2ms bytes=35148 finished=True finish=tool_calls stop=None out_tok=328 prompt_tok=15755 tps=8.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:23:44,569] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a22e26e27968bee0c2aca034a1400e1a attempt=1 -[2026-08-13 08:23:45,026] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a22e26e27968bee0c2aca034a1400e1a status=200 post_dur=0.457s -[2026-08-13 08:24:25,600] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a22e26e27968bee0c2aca034a1400e1a total=41030.8ms bytes=15605 finished=True finish=tool_calls stop=None out_tok=442 prompt_tok=15885 tps=10.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:24:25,603] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d3c81ea36a70eb17df97031eb88e3a93 attempt=1 -[2026-08-13 08:24:26,048] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d3c81ea36a70eb17df97031eb88e3a93 status=200 post_dur=0.445s -[2026-08-13 08:25:08,646] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d3c81ea36a70eb17df97031eb88e3a93 total=43042.5ms bytes=26051 finished=True finish=tool_calls stop=None out_tok=398 prompt_tok=11557 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:25:08,654] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=761173bbfd9c45a4a912f7e8a06bfd21 attempt=1 -[2026-08-13 08:25:08,979] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=761173bbfd9c45a4a912f7e8a06bfd21 status=400 post_dur=0.324s -[2026-08-13 08:25:08,979] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=761173bbfd9c45a4a912f7e8a06bfd21 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 135847 tokens (70311 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:25:08,986] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff attempt=1 -[2026-08-13 08:25:09,404] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff status=200 post_dur=0.418s -[2026-08-13 08:25:39,776] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff total=30790.4ms bytes=24918 finished=True finish=tool_calls stop=None out_tok=287 prompt_tok=16409 tps=9.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:25:39,780] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7cc9a754c24107848331586e88d4b52 attempt=1 -[2026-08-13 08:25:40,221] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7cc9a754c24107848331586e88d4b52 status=200 post_dur=0.441s -[2026-08-13 08:26:01,699] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7cc9a754c24107848331586e88d4b52 total=21919.5ms bytes=24927 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=16259 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:26:01,703] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2bc0097e24faffcef96c571f2c6fa0b2 attempt=1 -[2026-08-13 08:26:02,148] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2bc0097e24faffcef96c571f2c6fa0b2 status=200 post_dur=0.445s -[2026-08-13 08:26:25,441] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2bc0097e24faffcef96c571f2c6fa0b2 total=23737.7ms bytes=56419 finished=True finish=stop stop=None out_tok=194 prompt_tok=16899 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:26:25,445] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=208c93456a81bd6e6eb789edcbaad815 attempt=1 -[2026-08-13 08:26:25,876] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=208c93456a81bd6e6eb789edcbaad815 status=200 post_dur=0.431s -[2026-08-13 08:26:58,560] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=208c93456a81bd6e6eb789edcbaad815 total=33114.9ms bytes=19038 finished=True finish=tool_calls stop=None out_tok=295 prompt_tok=11829 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:26:58,563] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=489e3bf4f1669a09c4d84b22d29c76fa attempt=1 -[2026-08-13 08:26:59,003] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=489e3bf4f1669a09c4d84b22d29c76fa status=200 post_dur=0.440s -[2026-08-13 08:27:31,982] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=489e3bf4f1669a09c4d84b22d29c76fa total=33419.6ms bytes=14335 finished=True finish=tool_calls stop=None out_tok=300 prompt_tok=12338 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:27:31,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 attempt=1 -[2026-08-13 08:27:32,436] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 status=200 post_dur=0.450s -[2026-08-13 08:28:05,568] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 total=33582.4ms bytes=17452 finished=True finish=tool_calls stop=None out_tok=282 prompt_tok=13434 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:28:05,571] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=897720c5f0ce3aa6b53435be41b4854d attempt=1 -[2026-08-13 08:28:06,022] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=897720c5f0ce3aa6b53435be41b4854d status=200 post_dur=0.451s -[2026-08-13 08:28:48,409] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=897720c5f0ce3aa6b53435be41b4854d total=42837.7ms bytes=34385 finished=True finish=tool_calls stop=None out_tok=383 prompt_tok=14844 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:28:48,412] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=030f9998f1b00aacffc6a63891bbd937 attempt=1 -[2026-08-13 08:28:48,850] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=030f9998f1b00aacffc6a63891bbd937 status=200 post_dur=0.438s -[2026-08-13 08:29:07,085] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=030f9998f1b00aacffc6a63891bbd937 total=18673.5ms bytes=13215 finished=True finish=tool_calls stop=None out_tok=127 prompt_tok=8563 tps=6.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:29:07,087] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b6eef4c55d5057023dfae4e40cb45ca7 attempt=1 -[2026-08-13 08:29:07,510] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b6eef4c55d5057023dfae4e40cb45ca7 status=200 post_dur=0.422s -[2026-08-13 08:29:24,344] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b6eef4c55d5057023dfae4e40cb45ca7 total=17256.1ms bytes=8231 finished=True finish=tool_calls stop=None out_tok=112 prompt_tok=8220 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:29:24,351] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2320f9838fc0fa37eb8c4d4e50dbc091 attempt=1 -[2026-08-13 08:29:24,858] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2320f9838fc0fa37eb8c4d4e50dbc091 status=200 post_dur=0.506s -[2026-08-13 08:30:32,763] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2320f9838fc0fa37eb8c4d4e50dbc091 total=68412.3ms bytes=6236 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=45828 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:30:32,770] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=781df8a628086f0bbb1a8d47df29c678 attempt=1 -[2026-08-13 08:30:33,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=781df8a628086f0bbb1a8d47df29c678 status=200 post_dur=0.625s -[2026-08-13 08:31:03,017] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=781df8a628086f0bbb1a8d47df29c678 total=30246.2ms bytes=27050 finished=True finish=tool_calls stop=None out_tok=237 prompt_tok=15361 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:31:03,019] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca38125c983fc73af3bd211a8d7b63eb attempt=1 -[2026-08-13 08:31:03,447] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca38125c983fc73af3bd211a8d7b63eb status=200 post_dur=0.428s -[2026-08-13 08:31:22,974] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca38125c983fc73af3bd211a8d7b63eb total=19954.4ms bytes=15344 finished=True finish=tool_calls stop=None out_tok=128 prompt_tok=8705 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:31:22,976] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7e67de6f8dee2746ed569e299f51c644 attempt=1 -[2026-08-13 08:31:23,384] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7e67de6f8dee2746ed569e299f51c644 status=200 post_dur=0.407s -[2026-08-13 08:31:36,868] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7e67de6f8dee2746ed569e299f51c644 total=13891.8ms bytes=10809 finished=True finish=stop stop=None out_tok=36 prompt_tok=8770 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:31:36,871] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dab19ab6560dab4f147969a4e86d9585 attempt=1 -[2026-08-13 08:31:37,294] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dab19ab6560dab4f147969a4e86d9585 status=200 post_dur=0.423s -[2026-08-13 08:31:57,951] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dab19ab6560dab4f147969a4e86d9585 total=21080.5ms bytes=20521 finished=True finish=tool_calls stop=None out_tok=111 prompt_tok=9005 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:31:57,954] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18969f5ebf290953286b44f51e87c15e attempt=1 -[2026-08-13 08:31:58,378] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18969f5ebf290953286b44f51e87c15e status=200 post_dur=0.424s -[2026-08-13 08:32:12,062] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=18969f5ebf290953286b44f51e87c15e total=14108.0ms bytes=12893 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=9181 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:32:12,064] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bd58eef4ec4a56d53f985821361907f2 attempt=1 -[2026-08-13 08:32:12,479] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bd58eef4ec4a56d53f985821361907f2 status=200 post_dur=0.414s -[2026-08-13 08:32:19,122] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bd58eef4ec4a56d53f985821361907f2 total=7058.2ms bytes=10524 finished=True finish=stop stop=None out_tok=35 prompt_tok=9032 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:32:19,130] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dcdddd3cfd29ed17e082111c49ce2fe6 attempt=1 -[2026-08-13 08:32:19,609] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dcdddd3cfd29ed17e082111c49ce2fe6 status=200 post_dur=0.478s -[2026-08-13 08:32:31,599] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dcdddd3cfd29ed17e082111c49ce2fe6 total=12469.3ms bytes=6534 finished=True finish=tool_calls stop=None out_tok=69 prompt_tok=45923 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:32:31,605] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a78369072b9c53f0d464d0c5199cdc6d attempt=1 -[2026-08-13 08:32:32,036] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a78369072b9c53f0d464d0c5199cdc6d status=200 post_dur=0.432s -[2026-08-13 08:33:01,063] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a78369072b9c53f0d464d0c5199cdc6d total=29457.9ms bytes=74651 finished=True finish=stop stop=None out_tok=256 prompt_tok=9840 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:33:01,066] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=da150dbed66672f1597e924c9b8bfd17 attempt=1 -[2026-08-13 08:33:01,497] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=da150dbed66672f1597e924c9b8bfd17 status=200 post_dur=0.431s -[2026-08-13 08:33:08,172] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=da150dbed66672f1597e924c9b8bfd17 total=7105.9ms bytes=8749 finished=True finish=stop stop=None out_tok=29 prompt_tok=9699 tps=4.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:33:08,175] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=81dc399d3b76594fed6c228e74aa9177 attempt=1 -[2026-08-13 08:33:08,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=81dc399d3b76594fed6c228e74aa9177 status=200 post_dur=0.409s -[2026-08-13 08:33:18,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=81dc399d3b76594fed6c228e74aa9177 total=10410.0ms bytes=10507 finished=True finish=stop stop=None out_tok=35 prompt_tok=9801 tps=3.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:33:18,588] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=67679b9ac717784d43dba75b443d00d5 attempt=1 -[2026-08-13 08:33:19,005] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=67679b9ac717784d43dba75b443d00d5 status=200 post_dur=0.416s -[2026-08-13 08:33:26,615] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=67679b9ac717784d43dba75b443d00d5 total=8026.7ms bytes=14372 finished=True finish=stop stop=None out_tok=49 prompt_tok=9902 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:33:26,618] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fde534bf37958b32c69dd33dea05e6d attempt=1 -[2026-08-13 08:33:27,033] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fde534bf37958b32c69dd33dea05e6d status=200 post_dur=0.416s -[2026-08-13 08:33:52,968] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fde534bf37958b32c69dd33dea05e6d total=26350.0ms bytes=32046 finished=True finish=tool_calls stop=None out_tok=271 prompt_tok=7229 tps=10.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:33:52,970] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39d36ff3385f88aef025fd09d38417d2 attempt=1 -[2026-08-13 08:33:53,401] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39d36ff3385f88aef025fd09d38417d2 status=200 post_dur=0.431s -[2026-08-13 08:34:08,584] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=39d36ff3385f88aef025fd09d38417d2 total=15613.4ms bytes=13288 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=10399 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:34:08,587] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3be58ea636a67e6431609e2bbfde0c8e attempt=1 -[2026-08-13 08:34:09,141] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3be58ea636a67e6431609e2bbfde0c8e status=200 post_dur=0.554s -[2026-08-13 08:34:44,783] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3be58ea636a67e6431609e2bbfde0c8e total=36196.7ms bytes=29587 finished=True finish=tool_calls stop=None out_tok=331 prompt_tok=10762 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:34:44,786] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=739d74764d68eac2906cc142d1c4dc0a attempt=1 -[2026-08-13 08:34:45,086] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=739d74764d68eac2906cc142d1c4dc0a status=200 post_dur=0.300s -[2026-08-13 08:36:14,660] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=739d74764d68eac2906cc142d1c4dc0a total=89874.5ms bytes=275484 finished=True finish=stop stop=None out_tok=949 prompt_tok=7926 tps=10.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:36:14,663] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=534861acba13709ce90e3532fec86ba0 attempt=1 -[2026-08-13 08:36:15,121] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=534861acba13709ce90e3532fec86ba0 status=200 post_dur=0.458s -[2026-08-13 08:36:28,596] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=534861acba13709ce90e3532fec86ba0 total=13933.0ms bytes=11332 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=7626 tps=6.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:36:28,600] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a85cdbec78c97f2960cda954365e3b15 attempt=1 -[2026-08-13 08:36:29,062] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a85cdbec78c97f2960cda954365e3b15 status=200 post_dur=0.462s -[2026-08-13 08:37:04,498] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a85cdbec78c97f2960cda954365e3b15 total=35897.3ms bytes=8155 finished=True finish=stop stop=None out_tok=27 prompt_tok=24820 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:37:04,501] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=591d6bcdfc7fa47d9c8d0923dba82161 attempt=1 -[2026-08-13 08:37:04,948] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=591d6bcdfc7fa47d9c8d0923dba82161 status=200 post_dur=0.447s -[2026-08-13 08:37:45,381] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=591d6bcdfc7fa47d9c8d0923dba82161 total=40880.2ms bytes=65044 finished=True finish=tool_calls stop=None out_tok=380 prompt_tok=10073 tps=9.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:37:45,383] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7a94fb833580b70db22b2c6646da818e attempt=1 -[2026-08-13 08:37:45,671] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7a94fb833580b70db22b2c6646da818e status=200 post_dur=0.288s -[2026-08-13 08:40:04,869] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7a94fb833580b70db22b2c6646da818e total=139486.3ms bytes=474416 finished=True finish=stop stop=None out_tok=1631 prompt_tok=126 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:40:04,871] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=543eb2ee52a87501fabacd48dd360270 attempt=1 -[2026-08-13 08:40:05,159] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=543eb2ee52a87501fabacd48dd360270 status=200 post_dur=0.288s -[2026-08-13 08:44:19,634] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=543eb2ee52a87501fabacd48dd360270 total=254762.3ms bytes=872656 finished=True finish=stop stop=None out_tok=3008 prompt_tok=122 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:44:19,646] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=30f411698380613107fd553990855b29 attempt=1 -[2026-08-13 08:44:20,030] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=30f411698380613107fd553990855b29 status=400 post_dur=0.374s -[2026-08-13 08:44:20,030] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=30f411698380613107fd553990855b29 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 159479 tokens (93943 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:44:20,039] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d359c33479ab1219a4b91fb3192ff84f attempt=1 -[2026-08-13 08:44:20,454] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d359c33479ab1219a4b91fb3192ff84f status=200 post_dur=0.415s -[2026-08-13 08:44:33,060] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d359c33479ab1219a4b91fb3192ff84f total=13021.0ms bytes=12744 finished=True finish=tool_calls stop=None out_tok=97 prompt_tok=11589 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:44:33,062] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e6e3b089f22fe8c96166bd8684b699b attempt=1 -[2026-08-13 08:44:33,062] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 38% (308/881) has_cb=True -[2026-08-13 08:44:33,339] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e6e3b089f22fe8c96166bd8684b699b status=200 post_dur=0.277s -[2026-08-13 08:50:07,352] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e6e3b089f22fe8c96166bd8684b699b total=334289.9ms bytes=1154910 finished=True finish=stop stop=None out_tok=3959 prompt_tok=310 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:50:07,369] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bee17ca5762fa519f395a394d63c923e attempt=1 -[2026-08-13 08:50:07,815] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bee17ca5762fa519f395a394d63c923e status=400 post_dur=0.445s -[2026-08-13 08:50:07,815] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bee17ca5762fa519f395a394d63c923e status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 166404 tokens (134404 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:50:07,824] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=42d7ff74e68564a4c55eab4bbf0e5455 attempt=1 -[2026-08-13 08:50:08,245] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=42d7ff74e68564a4c55eab4bbf0e5455 status=200 post_dur=0.421s -[2026-08-13 08:50:37,785] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=42d7ff74e68564a4c55eab4bbf0e5455 total=29961.2ms bytes=67493 finished=True finish=stop stop=None out_tok=233 prompt_tok=11572 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:50:37,788] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b2b836d03a813f24d41f6852aa59ec0d attempt=1 -[2026-08-13 08:50:38,314] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b2b836d03a813f24d41f6852aa59ec0d status=200 post_dur=0.526s -[2026-08-13 08:50:47,747] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b2b836d03a813f24d41f6852aa59ec0d total=9958.8ms bytes=8821 finished=True finish=tool_calls stop=None out_tok=74 prompt_tok=7319 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:50:47,750] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=20381136fd4119d82879fa066f8a4da3 attempt=1 -[2026-08-13 08:50:48,164] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=20381136fd4119d82879fa066f8a4da3 status=200 post_dur=0.414s -[2026-08-13 08:51:14,435] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=20381136fd4119d82879fa066f8a4da3 total=26684.7ms bytes=14817 finished=True finish=tool_calls stop=None out_tok=155 prompt_tok=11674 tps=5.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:51:14,438] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44e6047d34f4018aa8ad7dee8d50d616 attempt=1 -[2026-08-13 08:51:15,044] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44e6047d34f4018aa8ad7dee8d50d616 status=200 post_dur=0.606s -[2026-08-13 08:51:41,886] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44e6047d34f4018aa8ad7dee8d50d616 total=27447.9ms bytes=80018 finished=True finish=stop stop=None out_tok=276 prompt_tok=11705 tps=10.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:51:41,889] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1fb23507e631016b81cf5d1cf81d126e attempt=1 -[2026-08-13 08:51:42,325] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1fb23507e631016b81cf5d1cf81d126e status=200 post_dur=0.436s -[2026-08-13 08:51:51,520] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1fb23507e631016b81cf5d1cf81d126e total=9630.2ms bytes=7592 finished=True finish=stop stop=None out_tok=25 prompt_tok=8093 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:51:51,523] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b8525370526bef040d70756d7f0ee140 attempt=1 -[2026-08-13 08:51:52,081] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b8525370526bef040d70756d7f0ee140 status=200 post_dur=0.557s -[2026-08-13 08:52:29,804] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b8525370526bef040d70756d7f0ee140 total=38280.7ms bytes=17875 finished=True finish=tool_calls stop=None out_tok=167 prompt_tok=17354 tps=4.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:52:29,807] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3a44fcf5b4a683a78a5648a97793dd1 attempt=1 -[2026-08-13 08:52:30,253] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3a44fcf5b4a683a78a5648a97793dd1 status=200 post_dur=0.446s -[2026-08-13 08:52:45,011] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3a44fcf5b4a683a78a5648a97793dd1 total=15203.8ms bytes=24299 finished=True finish=stop stop=None out_tok=82 prompt_tok=8382 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:52:45,028] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=429e2ec8a4bb7e555738313a9f787546 attempt=1 -[2026-08-13 08:52:45,449] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=429e2ec8a4bb7e555738313a9f787546 status=400 post_dur=0.421s -[2026-08-13 08:52:45,449] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=429e2ec8a4bb7e555738313a9f787546 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 169134 tokens (137134 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 08:52:45,457] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=472fa9b9163a07a78ee1e76d69b4034d attempt=1 -[2026-08-13 08:52:45,867] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=472fa9b9163a07a78ee1e76d69b4034d status=200 post_dur=0.409s -[2026-08-13 08:52:57,899] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=472fa9b9163a07a78ee1e76d69b4034d total=12442.0ms bytes=14401 finished=True finish=stop stop=None out_tok=49 prompt_tok=8363 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:52:57,901] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e8b63715a54029132096ddb713de5080 attempt=1 -[2026-08-13 08:52:58,205] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e8b63715a54029132096ddb713de5080 status=200 post_dur=0.303s -[2026-08-13 08:54:23,527] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e8b63715a54029132096ddb713de5080 total=85625.3ms bytes=239381 finished=True finish=stop stop=None out_tok=832 prompt_tok=10317 tps=9.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:54:23,530] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=279ef80c5ca400b7a2a8e9d9709257db attempt=1 -[2026-08-13 08:54:23,892] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=279ef80c5ca400b7a2a8e9d9709257db status=200 post_dur=0.362s -[2026-08-13 08:54:48,905] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=279ef80c5ca400b7a2a8e9d9709257db total=25374.9ms bytes=3391 finished=True finish=stop stop= out_tok=7 prompt_tok=19541 tps=0.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:54:48,909] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=609555a434d06a6739b49a1a6e188512 attempt=1 -[2026-08-13 08:54:49,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=609555a434d06a6739b49a1a6e188512 status=200 post_dur=0.487s -[2026-08-13 08:56:09,285] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=609555a434d06a6739b49a1a6e188512 total=80375.7ms bytes=49010 finished=True finish=tool_calls stop=None out_tok=522 prompt_tok=27365 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:56:09,296] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f162e5772523b77f1fd6f11119aba52e attempt=1 -[2026-08-13 08:56:09,911] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f162e5772523b77f1fd6f11119aba52e status=200 post_dur=0.615s -[2026-08-13 08:58:53,158] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f162e5772523b77f1fd6f11119aba52e total=163862.5ms bytes=98110 finished=True finish=stop stop=None out_tok=332 prompt_tok=75206 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:58:53,165] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7dfdc826123166286f9350e95ba9dd74 attempt=1 -[2026-08-13 08:58:53,616] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7dfdc826123166286f9350e95ba9dd74 status=200 post_dur=0.451s -[2026-08-13 08:59:09,504] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7dfdc826123166286f9350e95ba9dd74 total=16338.9ms bytes=18142 finished=True finish=stop stop=None out_tok=61 prompt_tok=8747 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:59:09,508] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07245351d69936bcf5160d35c7986d38 attempt=1 -[2026-08-13 08:59:10,115] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07245351d69936bcf5160d35c7986d38 status=200 post_dur=0.606s -[2026-08-13 08:59:54,036] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=07245351d69936bcf5160d35c7986d38 total=44528.2ms bytes=61913 finished=True finish=stop stop=None out_tok=209 prompt_tok=19366 tps=4.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 08:59:54,041] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2c279398e5811a0668d2c99bba40f0f1 attempt=1 -[2026-08-13 08:59:54,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2c279398e5811a0668d2c99bba40f0f1 status=200 post_dur=0.472s -[2026-08-13 09:00:31,147] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2c279398e5811a0668d2c99bba40f0f1 total=37105.2ms bytes=17276 finished=True finish=tool_calls stop=None out_tok=120 prompt_tok=20282 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:00:31,151] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ecce35417f652721e8b3d83ebdbe97b8 attempt=1 -[2026-08-13 09:00:31,824] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ecce35417f652721e8b3d83ebdbe97b8 status=200 post_dur=0.673s -[2026-08-13 09:01:16,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ecce35417f652721e8b3d83ebdbe97b8 total=45092.6ms bytes=19755 finished=True finish=tool_calls stop=None out_tok=114 prompt_tok=27038 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:01:16,248] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=274a2ea60d0d6699ae57042b9df59a9c attempt=1 -[2026-08-13 09:01:16,687] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=274a2ea60d0d6699ae57042b9df59a9c status=200 post_dur=0.438s -[2026-08-13 09:01:58,939] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=274a2ea60d0d6699ae57042b9df59a9c total=42691.0ms bytes=41850 finished=True finish=tool_calls stop=None out_tok=359 prompt_tok=7438 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:01:58,945] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=92bc65caec466c196c5c29641b61fab3 attempt=1 -[2026-08-13 09:01:59,422] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=92bc65caec466c196c5c29641b61fab3 status=200 post_dur=0.477s -[2026-08-13 09:02:45,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=92bc65caec466c196c5c29641b61fab3 total=46238.5ms bytes=55505 finished=True finish=stop stop=None out_tok=188 prompt_tok=24852 tps=4.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:02:45,191] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f638e6d289e6c0155b99340453e7f6cd attempt=1 -[2026-08-13 09:02:45,871] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f638e6d289e6c0155b99340453e7f6cd status=200 post_dur=0.680s -[2026-08-13 09:03:38,908] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f638e6d289e6c0155b99340453e7f6cd total=53716.8ms bytes=56975 finished=True finish=stop stop=None out_tok=193 prompt_tok=28519 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:03:38,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18402a4e7df20b9b0a2378d8d829f2da attempt=1 -[2026-08-13 09:03:39,539] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18402a4e7df20b9b0a2378d8d829f2da status=400 post_dur=0.613s -[2026-08-13 09:03:39,540] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=18402a4e7df20b9b0a2378d8d829f2da status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 166170 tokens (134170 in the messages, 32000 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 09:03:39,549] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=861831dca52df0c5fa277aa51ba52f02 attempt=1 -[2026-08-13 09:03:40,120] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=861831dca52df0c5fa277aa51ba52f02 status=200 post_dur=0.571s -[2026-08-13 09:04:06,858] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=861831dca52df0c5fa277aa51ba52f02 total=27309.2ms bytes=21598 finished=True finish=tool_calls stop=None out_tok=244 prompt_tok=7865 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:04:06,860] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca2a5777ff1428d41f12b0b0e98f650a attempt=1 -[2026-08-13 09:04:07,296] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca2a5777ff1428d41f12b0b0e98f650a status=200 post_dur=0.435s -[2026-08-13 09:04:47,964] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca2a5777ff1428d41f12b0b0e98f650a total=41103.1ms bytes=23635 finished=True finish=tool_calls stop=None out_tok=370 prompt_tok=9570 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:04:47,966] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=19a5b1d36a0575436b7d58259b731048 attempt=1 -[2026-08-13 09:04:48,568] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=19a5b1d36a0575436b7d58259b731048 status=200 post_dur=0.602s -[2026-08-13 09:05:09,747] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=19a5b1d36a0575436b7d58259b731048 total=21780.7ms bytes=17359 finished=True finish=tool_calls stop=None out_tok=122 prompt_tok=9201 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:05:09,749] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2cae3880668cf3586211138d03ca36dc attempt=1 -[2026-08-13 09:05:10,305] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2cae3880668cf3586211138d03ca36dc status=200 post_dur=0.555s -[2026-08-13 09:05:55,214] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2cae3880668cf3586211138d03ca36dc total=45464.1ms bytes=22169 finished=True finish=tool_calls stop=None out_tok=380 prompt_tok=9937 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:05:55,226] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=12c6c48470de526ecb2c2b7c0aa856de attempt=1 -[2026-08-13 09:05:55,237] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=12c6c48470de526ecb2c2b7c0aa856de status=400 post_dur=0.010s -[2026-08-13 09:05:55,237] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=12c6c48470de526ecb2c2b7c0aa856de status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 09:05:55,246] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e1491602678c1921e5fb02c410f76d3 attempt=1 -[2026-08-13 09:05:55,856] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e1491602678c1921e5fb02c410f76d3 status=200 post_dur=0.609s -[2026-08-13 09:06:30,353] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e1491602678c1921e5fb02c410f76d3 total=35106.9ms bytes=33848 finished=True finish=tool_calls stop=None out_tok=374 prompt_tok=7229 tps=10.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:06:30,357] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0479e081fd710787d7263de415b808ce attempt=1 -[2026-08-13 09:06:30,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0479e081fd710787d7263de415b808ce status=200 post_dur=0.477s -[2026-08-13 09:08:21,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0479e081fd710787d7263de415b808ce total=110870.5ms bytes=21647 finished=True finish=tool_calls stop=None out_tok=772 prompt_tok=29749 tps=7.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:08:21,232] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca6258bbd7739ea06692f037e73af14c attempt=1 -[2026-08-13 09:08:21,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca6258bbd7739ea06692f037e73af14c status=200 post_dur=0.620s -[2026-08-13 09:08:39,213] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca6258bbd7739ea06692f037e73af14c total=17981.3ms bytes=22904 finished=True finish=tool_calls stop=None out_tok=176 prompt_tok=7197 tps=9.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:08:39,215] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb259d9b4105065222a81d4ee0ba25d1 attempt=1 -[2026-08-13 09:08:39,547] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb259d9b4105065222a81d4ee0ba25d1 status=200 post_dur=0.332s -[2026-08-13 09:09:07,642] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fb259d9b4105065222a81d4ee0ba25d1 total=28426.9ms bytes=3672 finished=True finish=stop stop= out_tok=7 prompt_tok=19894 tps=0.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:09:07,645] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7529578e135854befe7cb7538706fd49 attempt=1 -[2026-08-13 09:09:08,234] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7529578e135854befe7cb7538706fd49 status=200 post_dur=0.589s -[2026-08-13 09:09:19,519] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7529578e135854befe7cb7538706fd49 total=11874.3ms bytes=9940 finished=True finish=tool_calls stop=None out_tok=67 prompt_tok=7294 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:09:19,521] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db8031b46e0d570d6672546b905d59da attempt=1 -[2026-08-13 09:09:20,088] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db8031b46e0d570d6672546b905d59da status=200 post_dur=0.567s -[2026-08-13 09:09:53,656] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db8031b46e0d570d6672546b905d59da total=34134.4ms bytes=21478 finished=True finish=tool_calls stop=None out_tok=303 prompt_tok=8599 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:09:53,658] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2e431b6fccc5248fd9864f7ccce4ecf4 attempt=1 -[2026-08-13 09:09:54,093] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2e431b6fccc5248fd9864f7ccce4ecf4 status=200 post_dur=0.435s -[2026-08-13 09:10:06,844] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2e431b6fccc5248fd9864f7ccce4ecf4 total=13185.5ms bytes=11257 finished=True finish=tool_calls stop=None out_tok=92 prompt_tok=10928 tps=7.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:10:06,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=43b55004efbaf0f8acfcbf32ac94aef1 attempt=1 -[2026-08-13 09:10:07,184] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=43b55004efbaf0f8acfcbf32ac94aef1 status=200 post_dur=0.337s -[2026-08-13 09:10:14,970] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=43b55004efbaf0f8acfcbf32ac94aef1 total=8123.9ms bytes=3158 finished=True finish=stop stop= out_tok=7 prompt_tok=20050 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:10:14,983] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b20030ac5b5832f877f2b30f9f5e01a8 attempt=1 -[2026-08-13 09:10:14,993] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b20030ac5b5832f877f2b30f9f5e01a8 status=400 post_dur=0.009s -[2026-08-13 09:10:14,993] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b20030ac5b5832f877f2b30f9f5e01a8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 09:10:15,002] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d06150a2df906c2e476c45b973b43bee attempt=1 -[2026-08-13 09:10:15,594] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d06150a2df906c2e476c45b973b43bee status=200 post_dur=0.592s -[2026-08-13 09:10:44,054] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d06150a2df906c2e476c45b973b43bee total=29052.0ms bytes=63766 finished=True finish=stop stop=None out_tok=215 prompt_tok=11163 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:10:44,057] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7f2d3841e1eeef072d0c35f7e26f1f8d attempt=1 -[2026-08-13 09:10:44,481] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7f2d3841e1eeef072d0c35f7e26f1f8d status=200 post_dur=0.423s -[2026-08-13 09:10:58,958] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7f2d3841e1eeef072d0c35f7e26f1f8d total=14900.9ms bytes=13863 finished=True finish=tool_calls stop=None out_tok=91 prompt_tok=11354 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:10:58,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3de25793ade30c457cac9eb6599596c0 attempt=1 -[2026-08-13 09:10:59,387] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3de25793ade30c457cac9eb6599596c0 status=200 post_dur=0.426s -[2026-08-13 09:11:28,271] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3de25793ade30c457cac9eb6599596c0 total=29309.6ms bytes=13468 finished=True finish=tool_calls stop=None out_tok=184 prompt_tok=10488 tps=6.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:11:28,273] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=635214b9e34c72c0130f432a0cef31b0 attempt=1 -[2026-08-13 09:11:28,875] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=635214b9e34c72c0130f432a0cef31b0 status=200 post_dur=0.601s -[2026-08-13 09:12:04,095] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=635214b9e34c72c0130f432a0cef31b0 total=35821.3ms bytes=12793 finished=True finish=tool_calls stop=None out_tok=254 prompt_tok=10895 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:12:04,098] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=85f151be1e5f546e001316abfc2f790d attempt=1 -[2026-08-13 09:12:04,546] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=85f151be1e5f546e001316abfc2f790d status=200 post_dur=0.449s -[2026-08-13 09:12:44,298] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=85f151be1e5f546e001316abfc2f790d total=40200.3ms bytes=20606 finished=True finish=tool_calls stop=None out_tok=359 prompt_tok=11738 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:12:44,301] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b2e77e30bc470141455b116c301d01c7 attempt=1 -[2026-08-13 09:12:44,899] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b2e77e30bc470141455b116c301d01c7 status=200 post_dur=0.598s -[2026-08-13 09:13:31,315] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b2e77e30bc470141455b116c301d01c7 total=47013.7ms bytes=30480 finished=True finish=tool_calls stop=None out_tok=446 prompt_tok=10885 tps=9.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:13:31,319] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8cbebc1418321449b8337a4b6a8a419 attempt=1 -[2026-08-13 09:13:31,925] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8cbebc1418321449b8337a4b6a8a419 status=200 post_dur=0.606s -[2026-08-13 09:14:29,147] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a8cbebc1418321449b8337a4b6a8a419 total=57827.5ms bytes=173530 finished=True finish=stop stop=None out_tok=605 prompt_tok=11236 tps=10.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:14:29,155] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 42% (352/881) has_cb=True -[2026-08-13 09:14:29,161] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2c9a026e503ef8037293cb832698e683 attempt=1 -[2026-08-13 09:14:29,168] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2c9a026e503ef8037293cb832698e683 status=400 post_dur=0.008s -[2026-08-13 09:14:29,169] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2c9a026e503ef8037293cb832698e683 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 09:14:29,185] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=df387d4c577f944c69a77089501c6af5 attempt=1 -[2026-08-13 09:14:29,756] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=df387d4c577f944c69a77089501c6af5 status=200 post_dur=0.570s -[2026-08-13 09:15:48,525] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=df387d4c577f944c69a77089501c6af5 total=79339.3ms bytes=20050 finished=True finish=stop stop=None out_tok=67 prompt_tok=69540 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:15:48,531] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac8d56b6daae31f8e66ac545d6ddcb6d attempt=1 -[2026-08-13 09:15:49,146] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac8d56b6daae31f8e66ac545d6ddcb6d status=200 post_dur=0.615s -[2026-08-13 09:16:14,000] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ac8d56b6daae31f8e66ac545d6ddcb6d total=25469.2ms bytes=20790 finished=True finish=tool_calls stop=None out_tok=187 prompt_tok=11582 tps=7.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:16:14,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fb7f8200244661a9e24b010c5b57fa8 attempt=1 -[2026-08-13 09:16:14,537] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fb7f8200244661a9e24b010c5b57fa8 status=200 post_dur=0.529s -[2026-08-13 09:17:13,434] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fb7f8200244661a9e24b010c5b57fa8 total=59425.3ms bytes=10644 finished=True finish=stop stop=None out_tok=35 prompt_tok=61391 tps=0.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:17:13,440] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14ff5b55b889e97c1a7e80193796aa58 attempt=1 -[2026-08-13 09:17:14,045] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14ff5b55b889e97c1a7e80193796aa58 status=200 post_dur=0.605s -[2026-08-13 09:17:38,178] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14ff5b55b889e97c1a7e80193796aa58 total=24738.0ms bytes=22820 finished=True finish=tool_calls stop=None out_tok=190 prompt_tok=13139 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:17:38,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 attempt=1 -[2026-08-13 09:17:38,651] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 status=200 post_dur=0.468s -[2026-08-13 09:17:56,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 total=17825.6ms bytes=5609 finished=True finish=tool_calls stop=None out_tok=58 prompt_tok=30912 tps=3.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:17:56,013] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=60ede395352414a38079a484eaf198de attempt=1 -[2026-08-13 09:17:56,627] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=60ede395352414a38079a484eaf198de status=200 post_dur=0.614s -[2026-08-13 09:18:37,512] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=60ede395352414a38079a484eaf198de total=41498.7ms bytes=26297 finished=True finish=tool_calls stop=None out_tok=337 prompt_tok=13720 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:18:37,515] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0144b8b9927afe3007c1368bb0ccda39 attempt=1 -[2026-08-13 09:18:37,921] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0144b8b9927afe3007c1368bb0ccda39 status=200 post_dur=0.406s -[2026-08-13 09:23:03,321] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0144b8b9927afe3007c1368bb0ccda39 total=265806.3ms bytes=152485 finished=True finish=stop stop=None out_tok=539 prompt_tok=790 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:23:03,324] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e416fbe4d56d069fc7e605809cfba44d attempt=1 -[2026-08-13 09:23:03,619] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e416fbe4d56d069fc7e605809cfba44d status=200 post_dur=0.295s -[2026-08-13 09:25:33,671] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e416fbe4d56d069fc7e605809cfba44d total=150347.7ms bytes=481147 finished=True finish=stop stop=None out_tok=1656 prompt_tok=251 tps=11.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:25:33,676] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cc81042dc54416c8768e82fee13770b3 attempt=1 -[2026-08-13 09:25:34,293] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cc81042dc54416c8768e82fee13770b3 status=200 post_dur=0.617s -[2026-08-13 09:26:07,430] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cc81042dc54416c8768e82fee13770b3 total=33754.1ms bytes=37873 finished=True finish=tool_calls stop=None out_tok=382 prompt_tok=7433 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:26:07,435] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b21c998e2c72a301cbf8c9a5abdb4068 attempt=1 -[2026-08-13 09:26:07,926] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b21c998e2c72a301cbf8c9a5abdb4068 status=200 post_dur=0.491s -[2026-08-13 09:26:28,742] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b21c998e2c72a301cbf8c9a5abdb4068 total=21306.8ms bytes=8113 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=32060 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:26:28,752] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b31287524a5bdde3d489b19723abeb8d attempt=1 -[2026-08-13 09:26:29,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b31287524a5bdde3d489b19723abeb8d status=200 post_dur=0.705s -[2026-08-13 09:27:31,179] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b31287524a5bdde3d489b19723abeb8d total=62427.1ms bytes=10028 finished=True finish=stop stop=None out_tok=33 prompt_tok=61393 tps=0.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:27:31,184] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e3ed7dd1515cb0be028e2775fe5a4600 attempt=1 -[2026-08-13 09:27:31,642] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e3ed7dd1515cb0be028e2775fe5a4600 status=200 post_dur=0.457s -[2026-08-13 09:27:41,633] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e3ed7dd1515cb0be028e2775fe5a4600 total=10449.2ms bytes=12928 finished=True finish=tool_calls stop=None out_tok=85 prompt_tok=7307 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:27:41,635] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4848e81852f3718e4afa6f6db26720e6 attempt=1 -[2026-08-13 09:27:42,057] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4848e81852f3718e4afa6f6db26720e6 status=200 post_dur=0.422s -[2026-08-13 09:27:47,443] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4848e81852f3718e4afa6f6db26720e6 total=5807.3ms bytes=8176 finished=True finish=stop stop=None out_tok=27 prompt_tok=7414 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:27:47,445] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9571bb4868f83194065d93aefe25be3f attempt=1 -[2026-08-13 09:27:47,857] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9571bb4868f83194065d93aefe25be3f status=200 post_dur=0.412s -[2026-08-13 09:27:55,888] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9571bb4868f83194065d93aefe25be3f total=8443.5ms bytes=9330 finished=True finish=stop stop=None out_tok=31 prompt_tok=7515 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:27:55,889] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d77d4756eca9a5bfb7c18e94cd149cf2 attempt=1 -[2026-08-13 09:27:56,154] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d77d4756eca9a5bfb7c18e94cd149cf2 status=200 post_dur=0.264s -[2026-08-13 09:31:27,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d77d4756eca9a5bfb7c18e94cd149cf2 total=212071.7ms bytes=711111 finished=True finish=stop stop=None out_tok=2441 prompt_tok=388 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:31:27,966] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0254959a6925f264971a93e914090cbc attempt=1 -[2026-08-13 09:31:28,418] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0254959a6925f264971a93e914090cbc status=200 post_dur=0.452s -[2026-08-13 09:31:48,207] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0254959a6925f264971a93e914090cbc total=20240.5ms bytes=13321 finished=True finish=tool_calls stop=None out_tok=133 prompt_tok=8705 tps=6.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:31:48,209] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3fe50daa51b851305e691f1bb7c0057c attempt=1 -[2026-08-13 09:31:48,620] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3fe50daa51b851305e691f1bb7c0057c status=200 post_dur=0.411s -[2026-08-13 09:31:58,286] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3fe50daa51b851305e691f1bb7c0057c total=10076.6ms bytes=10506 finished=True finish=stop stop=None out_tok=35 prompt_tok=8055 tps=3.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:31:58,288] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e9f02c35f7a9f4f68a6a144193fac24 attempt=1 -[2026-08-13 09:31:58,706] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e9f02c35f7a9f4f68a6a144193fac24 status=200 post_dur=0.418s -[2026-08-13 09:32:09,001] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e9f02c35f7a9f4f68a6a144193fac24 total=10712.7ms bytes=8459 finished=True finish=stop stop=None out_tok=28 prompt_tok=8507 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:32:09,003] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=66a411a3713d8ad4fd1d1790a0d2c5ac attempt=1 -[2026-08-13 09:32:09,430] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=66a411a3713d8ad4fd1d1790a0d2c5ac status=200 post_dur=0.426s -[2026-08-13 09:32:26,168] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=66a411a3713d8ad4fd1d1790a0d2c5ac total=17164.9ms bytes=19013 finished=True finish=stop stop=None out_tok=64 prompt_tok=9334 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:32:26,172] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ce4171917f54dcc759f9601e14f5215 attempt=1 -[2026-08-13 09:32:26,735] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ce4171917f54dcc759f9601e14f5215 status=200 post_dur=0.563s -[2026-08-13 09:32:40,691] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ce4171917f54dcc759f9601e14f5215 total=14518.9ms bytes=21969 finished=True finish=tool_calls stop=None out_tok=117 prompt_tok=9221 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:32:40,697] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=727f330a2980b24d2bab5ccecfbe5d55 attempt=1 -[2026-08-13 09:32:41,173] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=727f330a2980b24d2bab5ccecfbe5d55 status=200 post_dur=0.476s -[2026-08-13 09:32:59,687] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=727f330a2980b24d2bab5ccecfbe5d55 total=18990.4ms bytes=7109 finished=True finish=tool_calls stop=None out_tok=70 prompt_tok=33492 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:32:59,693] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c321c704b52eb67b2ca92cf66d9e016 attempt=1 -[2026-08-13 09:33:00,179] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c321c704b52eb67b2ca92cf66d9e016 status=200 post_dur=0.485s -[2026-08-13 09:33:20,844] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c321c704b52eb67b2ca92cf66d9e016 total=21150.6ms bytes=6831 finished=True finish=tool_calls stop=None out_tok=70 prompt_tok=33606 tps=3.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:33:20,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=405548cab3cb18d726be17fc7c373ecd attempt=1 -[2026-08-13 09:33:21,346] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=405548cab3cb18d726be17fc7c373ecd status=200 post_dur=0.495s -[2026-08-13 09:33:31,918] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=405548cab3cb18d726be17fc7c373ecd total=11067.3ms bytes=10285 finished=True finish=tool_calls stop=None out_tok=57 prompt_tok=33834 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:33:31,922] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b0fe3c8521896490e23da8dfe4e63b38 attempt=1 -[2026-08-13 09:33:32,339] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b0fe3c8521896490e23da8dfe4e63b38 status=200 post_dur=0.418s -[2026-08-13 09:34:13,020] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b0fe3c8521896490e23da8dfe4e63b38 total=41098.1ms bytes=22360 finished=True finish=tool_calls stop=None out_tok=368 prompt_tok=9252 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:34:13,026] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 attempt=1 -[2026-08-13 09:34:13,540] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 status=200 post_dur=0.513s -[2026-08-13 09:36:25,258] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 total=132231.6ms bytes=20308 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=34716 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:36:25,263] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 attempt=1 -[2026-08-13 09:36:25,696] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 status=200 post_dur=0.433s -[2026-08-13 09:36:37,629] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 total=12366.4ms bytes=10655 finished=True finish=tool_calls stop=None out_tok=116 prompt_tok=8017 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:36:37,631] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7383fb22c93f6890d7647632036c16bb attempt=1 -[2026-08-13 09:36:38,135] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7383fb22c93f6890d7647632036c16bb status=200 post_dur=0.504s -[2026-08-13 09:37:08,688] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7383fb22c93f6890d7647632036c16bb total=31056.9ms bytes=12063 finished=True finish=tool_calls stop=None out_tok=278 prompt_tok=8435 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:37:08,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80a75b9fec157ea6e81ad68cf15a50c3 attempt=1 -[2026-08-13 09:37:08,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80a75b9fec157ea6e81ad68cf15a50c3 status=200 post_dur=0.296s -[2026-08-13 09:38:25,126] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80a75b9fec157ea6e81ad68cf15a50c3 total=76436.3ms bytes=233617 finished=True finish=stop stop=None out_tok=823 prompt_tok=1471 tps=10.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:38:25,133] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=edb89c582b082458dd3e33b1761b8d78 attempt=1 -[2026-08-13 09:38:25,672] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=edb89c582b082458dd3e33b1761b8d78 status=200 post_dur=0.539s -[2026-08-13 09:39:46,436] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=edb89c582b082458dd3e33b1761b8d78 total=81303.0ms bytes=28327 finished=True finish=stop stop=None out_tok=98 prompt_tok=48211 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:39:46,445] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=82ff65cddafe6fb19c5b0f6e6c95f64f attempt=1 -[2026-08-13 09:39:46,971] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=82ff65cddafe6fb19c5b0f6e6c95f64f status=200 post_dur=0.526s -[2026-08-13 09:42:26,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=82ff65cddafe6fb19c5b0f6e6c95f64f total=160243.2ms bytes=50874 finished=True finish=tool_calls stop=None out_tok=315 prompt_tok=35317 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:42:26,698] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 attempt=1 -[2026-08-13 09:42:27,220] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 status=200 post_dur=0.522s -[2026-08-13 09:42:47,890] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 total=21192.5ms bytes=11137 finished=True finish=tool_calls stop=None out_tok=137 prompt_tok=35129 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:42:47,899] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5602bdaf443488e897d8b901f4f001a5 attempt=1 -[2026-08-13 09:42:48,399] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5602bdaf443488e897d8b901f4f001a5 status=200 post_dur=0.500s -[2026-08-13 09:44:12,329] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5602bdaf443488e897d8b901f4f001a5 total=84430.1ms bytes=57582 finished=True finish=stop stop=None out_tok=195 prompt_tok=42852 tps=2.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:44:12,343] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=50b3dd5c165a5799ea46b1a4bf5196e1 attempt=1 -[2026-08-13 09:44:12,928] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=50b3dd5c165a5799ea46b1a4bf5196e1 status=200 post_dur=0.582s -[2026-08-13 09:46:43,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=50b3dd5c165a5799ea46b1a4bf5196e1 total=151242.2ms bytes=67765 finished=True finish=tool_calls stop=None out_tok=325 prompt_tok=71370 tps=2.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:46:43,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab2963e3325789542c112702c80b5fbe attempt=1 -[2026-08-13 09:46:44,043] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab2963e3325789542c112702c80b5fbe status=200 post_dur=0.450s -[2026-08-13 09:46:54,241] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ab2963e3325789542c112702c80b5fbe total=10648.5ms bytes=3457 finished=True finish=stop stop=None out_tok=11 prompt_tok=7823 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:46:54,242] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8b8e1a9e1c4915fded776b3a404e5900 attempt=1 -[2026-08-13 09:46:54,657] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8b8e1a9e1c4915fded776b3a404e5900 status=200 post_dur=0.415s -[2026-08-13 09:47:07,661] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8b8e1a9e1c4915fded776b3a404e5900 total=13419.3ms bytes=16779 finished=True finish=stop stop=None out_tok=57 prompt_tok=1893 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:47:07,668] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c3380e499ef38094b85d8b9cbb72383e attempt=1 -[2026-08-13 09:47:08,183] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c3380e499ef38094b85d8b9cbb72383e status=200 post_dur=0.514s -[2026-08-13 09:48:34,053] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c3380e499ef38094b85d8b9cbb72383e total=86384.7ms bytes=8088 finished=True finish=tool_calls stop=None out_tok=114 prompt_tok=50515 tps=1.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:48:34,062] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ee3baaad3fa44bbe74cc7e9858accee attempt=1 -[2026-08-13 09:48:34,573] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ee3baaad3fa44bbe74cc7e9858accee status=200 post_dur=0.511s -[2026-08-13 09:50:09,067] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ee3baaad3fa44bbe74cc7e9858accee total=95005.0ms bytes=107844 finished=True finish=stop stop=None out_tok=373 prompt_tok=35902 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:50:09,074] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=28710330b7557818f6edad22899b9bf9 attempt=1 -[2026-08-13 09:50:09,697] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=28710330b7557818f6edad22899b9bf9 status=200 post_dur=0.623s -[2026-08-13 09:50:33,463] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=28710330b7557818f6edad22899b9bf9 total=24389.2ms bytes=22432 finished=True finish=tool_calls stop=None out_tok=182 prompt_tok=10773 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:50:33,465] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=542cc693537603e442f286c26145e05d attempt=1 -[2026-08-13 09:50:33,891] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=542cc693537603e442f286c26145e05d status=200 post_dur=0.426s -[2026-08-13 09:51:06,483] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=542cc693537603e442f286c26145e05d total=33017.4ms bytes=32007 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=7438 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:51:06,493] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e9cade087de6458ef3ed3970deba4b8 attempt=1 -[2026-08-13 09:51:06,792] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e9cade087de6458ef3ed3970deba4b8 status=400 post_dur=0.300s -[2026-08-13 09:51:06,793] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0e9cade087de6458ef3ed3970deba4b8 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 132799 tokens (67263 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 09:51:06,805] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 attempt=1 -[2026-08-13 09:51:07,361] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 status=200 post_dur=0.556s -[2026-08-13 09:53:17,223] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 total=130417.8ms bytes=8612 finished=True finish=tool_calls stop=None out_tok=167 prompt_tok=73075 tps=1.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:53:17,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=df0a36329f95a99cf3f2b09499f56721 attempt=1 -[2026-08-13 09:53:17,674] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=df0a36329f95a99cf3f2b09499f56721 status=200 post_dur=0.446s -[2026-08-13 09:53:35,332] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=df0a36329f95a99cf3f2b09499f56721 total=18103.8ms bytes=18270 finished=True finish=tool_calls stop=None out_tok=166 prompt_tok=7752 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:53:35,334] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14de2d899fc8516106395c4d9b78336b attempt=1 -[2026-08-13 09:53:35,762] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14de2d899fc8516106395c4d9b78336b status=200 post_dur=0.428s -[2026-08-13 09:53:53,633] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14de2d899fc8516106395c4d9b78336b total=18299.2ms bytes=10249 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=7319 tps=4.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:53:53,636] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7854323f23998fa50f3c845880c2ecb1 attempt=1 -[2026-08-13 09:53:53,636] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 46% (396/881) has_cb=True -[2026-08-13 09:53:54,070] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7854323f23998fa50f3c845880c2ecb1 status=200 post_dur=0.434s -[2026-08-13 09:54:18,883] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7854323f23998fa50f3c845880c2ecb1 total=25247.4ms bytes=14829 finished=True finish=tool_calls stop=None out_tok=151 prompt_tok=11555 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:54:18,886] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9f2bbd7143b34ed94b65a7193a898be9 attempt=1 -[2026-08-13 09:54:19,320] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9f2bbd7143b34ed94b65a7193a898be9 status=200 post_dur=0.434s -[2026-08-13 09:54:44,734] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9f2bbd7143b34ed94b65a7193a898be9 total=25848.0ms bytes=17219 finished=True finish=tool_calls stop=None out_tok=244 prompt_tok=7646 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:54:44,743] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e840166adea29bc2e6f86c559ff8e93f attempt=1 -[2026-08-13 09:54:45,344] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e840166adea29bc2e6f86c559ff8e93f status=200 post_dur=0.600s -[2026-08-13 09:57:04,334] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e840166adea29bc2e6f86c559ff8e93f total=139591.1ms bytes=28344 finished=True finish=tool_calls stop=None out_tok=176 prompt_tok=74107 tps=1.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:57:04,350] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0f28b08a0330b59170b78e9c386a68ab attempt=1 -[2026-08-13 09:57:04,942] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0f28b08a0330b59170b78e9c386a68ab status=200 post_dur=0.591s -[2026-08-13 09:57:40,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0f28b08a0330b59170b78e9c386a68ab total=35874.4ms bytes=20040 finished=True finish=tool_calls stop=None out_tok=180 prompt_tok=73569 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 09:57:40,245] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c2d8fbfc292584bf8cb1f080e8b57140 attempt=1 -[2026-08-13 09:57:40,887] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c2d8fbfc292584bf8cb1f080e8b57140 status=200 post_dur=0.642s -[2026-08-13 10:00:46,271] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c2d8fbfc292584bf8cb1f080e8b57140 total=186026.3ms bytes=13989 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=103726 tps=0.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:00:46,282] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=12c40991cbb4006666b23ef1bb6db526 attempt=1 -[2026-08-13 10:00:46,729] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=12c40991cbb4006666b23ef1bb6db526 status=200 post_dur=0.447s -[2026-08-13 10:00:56,626] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=12c40991cbb4006666b23ef1bb6db526 total=10344.2ms bytes=13149 finished=True finish=stop stop=None out_tok=44 prompt_tok=7865 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:00:56,628] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ba1621bc6e605ee9a62e281355307441 attempt=1 -[2026-08-13 10:00:57,047] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ba1621bc6e605ee9a62e281355307441 status=200 post_dur=0.419s -[2026-08-13 10:01:55,367] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ba1621bc6e605ee9a62e281355307441 total=58738.5ms bytes=166310 finished=True finish=stop stop=None out_tok=582 prompt_tok=8979 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:01:55,370] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fa88e748c5c989d4bf7b78d539747aba attempt=1 -[2026-08-13 10:01:55,976] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fa88e748c5c989d4bf7b78d539747aba status=200 post_dur=0.606s -[2026-08-13 10:02:22,383] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fa88e748c5c989d4bf7b78d539747aba total=27012.6ms bytes=39262 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=8024 tps=10.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:02:22,391] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 attempt=1 -[2026-08-13 10:02:22,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 status=200 post_dur=0.593s -[2026-08-13 10:04:10,541] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 total=108149.8ms bytes=3112 finished=True finish=tool_calls stop=None out_tok=89 prompt_tok=74884 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:04:10,560] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9fa1231b3de4a2ea9f5c284274cd70e3 attempt=1 -[2026-08-13 10:04:11,440] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9fa1231b3de4a2ea9f5c284274cd70e3 status=200 post_dur=0.880s -[2026-08-13 10:07:46,329] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9fa1231b3de4a2ea9f5c284274cd70e3 total=215768.8ms bytes=53030 finished=True finish=tool_calls stop=None out_tok=260 prompt_tok=104668 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:07:46,338] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=665356988c08c18ac7adebe5d1ab25d1 attempt=1 -[2026-08-13 10:07:46,951] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=665356988c08c18ac7adebe5d1ab25d1 status=200 post_dur=0.613s -[2026-08-13 10:08:21,454] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=665356988c08c18ac7adebe5d1ab25d1 total=35115.2ms bytes=48444 finished=True finish=tool_calls stop=None out_tok=309 prompt_tok=8990 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:08:21,455] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab attempt=1 -[2026-08-13 10:08:21,885] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab status=200 post_dur=0.429s -[2026-08-13 10:08:35,265] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab total=13809.5ms bytes=9999 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=1791 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:08:35,281] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9ba23d4edca7c884690c522163db9e69 attempt=1 -[2026-08-13 10:08:36,129] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9ba23d4edca7c884690c522163db9e69 status=200 post_dur=0.848s -[2026-08-13 10:09:02,584] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9ba23d4edca7c884690c522163db9e69 total=27303.6ms bytes=10435 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=104865 tps=3.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:09:02,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ec6541c7e7d698b8550e27e7eb95dd5e attempt=1 -[2026-08-13 10:09:02,887] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ec6541c7e7d698b8550e27e7eb95dd5e status=200 post_dur=0.295s -[2026-08-13 10:10:00,054] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ec6541c7e7d698b8550e27e7eb95dd5e total=57462.3ms bytes=164120 finished=True finish=stop stop=None out_tok=576 prompt_tok=1344 tps=10.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:10:00,070] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5eba948b1bd4c4fb79495e2a81f56a7 attempt=1 -[2026-08-13 10:10:00,956] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5eba948b1bd4c4fb79495e2a81f56a7 status=200 post_dur=0.886s -[2026-08-13 10:12:03,795] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e5eba948b1bd4c4fb79495e2a81f56a7 total=123725.7ms bytes=206717 finished=True finish=stop stop=None out_tok=710 prompt_tok=104734 tps=5.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:12:03,804] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d3fed72e042e604e764c644de6d2aceb attempt=1 -[2026-08-13 10:12:04,100] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d3fed72e042e604e764c644de6d2aceb status=200 post_dur=0.296s -[2026-08-13 10:15:04,716] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d3fed72e042e604e764c644de6d2aceb total=180912.0ms bytes=596555 finished=True finish=length stop=None out_tok=2048 prompt_tok=349 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:15:04,726] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9216bd6b4a6d971042b413ba0da531cb attempt=1 -[2026-08-13 10:15:05,346] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9216bd6b4a6d971042b413ba0da531cb status=200 post_dur=0.620s -[2026-08-13 10:17:08,739] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9216bd6b4a6d971042b413ba0da531cb total=124012.7ms bytes=55784 finished=True finish=stop stop=None out_tok=194 prompt_tok=75657 tps=1.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:17:08,754] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d6b8abbcc880d4e08cd5bee4a446b26 attempt=1 -[2026-08-13 10:17:09,543] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d6b8abbcc880d4e08cd5bee4a446b26 status=200 post_dur=0.789s -[2026-08-13 10:17:58,655] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3d6b8abbcc880d4e08cd5bee4a446b26 total=49901.0ms bytes=52637 finished=True finish=tool_calls stop=None out_tok=235 prompt_tok=74587 tps=4.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:17:58,661] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e695214d50c8e016a8d2a6f6739cc5a attempt=1 -[2026-08-13 10:17:59,289] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e695214d50c8e016a8d2a6f6739cc5a status=200 post_dur=0.628s -[2026-08-13 10:18:21,326] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6e695214d50c8e016a8d2a6f6739cc5a total=22664.9ms bytes=11313 finished=True finish=tool_calls stop=None out_tok=132 prompt_tok=7331 tps=5.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:18:21,328] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ba126c1bdb15e40c22f9a58d1791b733 attempt=1 -[2026-08-13 10:18:21,754] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ba126c1bdb15e40c22f9a58d1791b733 status=200 post_dur=0.425s -[2026-08-13 10:18:42,432] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ba126c1bdb15e40c22f9a58d1791b733 total=21103.1ms bytes=10250 finished=True finish=tool_calls stop=None out_tok=90 prompt_tok=8006 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:18:42,448] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=57832f49558fd182b94b8e85dacaec5a attempt=1 -[2026-08-13 10:18:42,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=57832f49558fd182b94b8e85dacaec5a status=400 post_dur=0.010s -[2026-08-13 10:18:42,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=57832f49558fd182b94b8e85dacaec5a status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 10:18:42,472] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fcbb0eefee83b04e30d08fc49880dfc5 attempt=1 -[2026-08-13 10:18:43,052] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fcbb0eefee83b04e30d08fc49880dfc5 status=200 post_dur=0.580s -[2026-08-13 10:19:00,008] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fcbb0eefee83b04e30d08fc49880dfc5 total=17536.2ms bytes=15055 finished=True finish=tool_calls stop=None out_tok=117 prompt_tok=8465 tps=6.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:19:00,024] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6b03c10d014a17217b95d102b07ca8a attempt=1 -[2026-08-13 10:19:00,031] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6b03c10d014a17217b95d102b07ca8a status=400 post_dur=0.008s -[2026-08-13 10:19:00,032] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e6b03c10d014a17217b95d102b07ca8a status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 10:19:00,042] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=294958e82a507ea8e7ff8b02009ab9e7 attempt=1 -[2026-08-13 10:19:00,463] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=294958e82a507ea8e7ff8b02009ab9e7 status=200 post_dur=0.422s -[2026-08-13 10:19:12,220] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=294958e82a507ea8e7ff8b02009ab9e7 total=12178.0ms bytes=14390 finished=True finish=tool_calls stop=None out_tok=91 prompt_tok=8983 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:19:12,222] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b8af517857e40649f6620ab38d8fa42 attempt=1 -[2026-08-13 10:19:12,645] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b8af517857e40649f6620ab38d8fa42 status=200 post_dur=0.423s -[2026-08-13 10:19:31,805] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b8af517857e40649f6620ab38d8fa42 total=19582.4ms bytes=37814 finished=True finish=stop stop=None out_tok=132 prompt_tok=9096 tps=6.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:19:31,817] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=04da7c9b034138a392ec3af7a144cf3a attempt=1 -[2026-08-13 10:19:32,546] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=04da7c9b034138a392ec3af7a144cf3a status=200 post_dur=0.729s -[2026-08-13 10:20:56,282] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=04da7c9b034138a392ec3af7a144cf3a total=84465.2ms bytes=136012 finished=True finish=stop stop=None out_tok=469 prompt_tok=75859 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:20:56,298] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7bbff6735d1705bc9b1049a1a56a3e54 attempt=1 -[2026-08-13 10:20:57,098] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7bbff6735d1705bc9b1049a1a56a3e54 status=200 post_dur=0.799s -[2026-08-13 10:22:19,262] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7bbff6735d1705bc9b1049a1a56a3e54 total=82963.8ms bytes=135773 finished=True finish=stop stop=None out_tok=473 prompt_tok=76785 tps=5.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:22:19,269] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87fdd72f02bf9189b4ee2f90e8d96b02 attempt=1 -[2026-08-13 10:22:19,566] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87fdd72f02bf9189b4ee2f90e8d96b02 status=200 post_dur=0.297s -[2026-08-13 10:24:52,279] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=87fdd72f02bf9189b4ee2f90e8d96b02 total=153010.8ms bytes=496372 finished=True finish=stop stop=None out_tok=1708 prompt_tok=265 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:24:52,282] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40260b037528a86dc15250ad42f50767 attempt=1 -[2026-08-13 10:24:52,683] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40260b037528a86dc15250ad42f50767 status=200 post_dur=0.401s -[2026-08-13 10:27:24,986] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40260b037528a86dc15250ad42f50767 total=152704.1ms bytes=502271 finished=True finish=stop stop=None out_tok=1727 prompt_tok=262 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:27:24,990] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e89471cb9498a6c5ff350a3461b6dff attempt=1 -[2026-08-13 10:27:25,451] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e89471cb9498a6c5ff350a3461b6dff status=200 post_dur=0.460s -[2026-08-13 10:27:44,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e89471cb9498a6c5ff350a3461b6dff total=19405.8ms bytes=49103 finished=True finish=stop stop=None out_tok=172 prompt_tok=9895 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:27:44,414] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab8099c4a0532cc5d8d25a833bae242e attempt=1 -[2026-08-13 10:27:44,422] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab8099c4a0532cc5d8d25a833bae242e status=400 post_dur=0.008s -[2026-08-13 10:27:44,422] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ab8099c4a0532cc5d8d25a833bae242e status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 10:27:44,433] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be5a6db40cdfc03ac81ff32cb810a7d1 attempt=1 -[2026-08-13 10:27:44,862] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be5a6db40cdfc03ac81ff32cb810a7d1 status=200 post_dur=0.428s -[2026-08-13 10:27:55,634] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=be5a6db40cdfc03ac81ff32cb810a7d1 total=11200.9ms bytes=9984 finished=True finish=stop stop=None out_tok=33 prompt_tok=10277 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:27:55,636] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=04524a5823cf67123c6a01475b370390 attempt=1 -[2026-08-13 10:27:56,204] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=04524a5823cf67123c6a01475b370390 status=200 post_dur=0.568s -[2026-08-13 10:28:41,012] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=04524a5823cf67123c6a01475b370390 total=45375.3ms bytes=30667 finished=True finish=tool_calls stop=None out_tok=424 prompt_tok=7229 tps=9.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:28:41,013] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=007f176bf501898e1efca138dc288c0c attempt=1 -[2026-08-13 10:28:41,311] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=007f176bf501898e1efca138dc288c0c status=200 post_dur=0.298s -[2026-08-13 10:31:42,336] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=007f176bf501898e1efca138dc288c0c total=181323.2ms bytes=597005 finished=True finish=length stop=None out_tok=2048 prompt_tok=766 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:31:42,339] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d6e4320c6266d9ba375d9869e784508d attempt=1 -[2026-08-13 10:31:42,640] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d6e4320c6266d9ba375d9869e784508d status=200 post_dur=0.301s -[2026-08-13 10:34:03,500] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d6e4320c6266d9ba375d9869e784508d total=141161.2ms bytes=472511 finished=True finish=stop stop=None out_tok=1624 prompt_tok=766 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:34:03,503] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3546faf14839049a620c533440ef2728 attempt=1 -[2026-08-13 10:34:03,955] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3546faf14839049a620c533440ef2728 status=200 post_dur=0.452s -[2026-08-13 10:34:26,637] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3546faf14839049a620c533440ef2728 total=23134.4ms bytes=29588 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=7197 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:34:26,653] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5c59f84adacc104b26d222ffc941feb9 attempt=1 -[2026-08-13 10:34:26,667] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5c59f84adacc104b26d222ffc941feb9 status=400 post_dur=0.009s -[2026-08-13 10:34:26,667] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5c59f84adacc104b26d222ffc941feb9 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 10:34:26,679] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bf5edec2786bc068979f6c1af9534bcb attempt=1 -[2026-08-13 10:34:27,109] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bf5edec2786bc068979f6c1af9534bcb status=200 post_dur=0.430s -[2026-08-13 10:35:08,730] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bf5edec2786bc068979f6c1af9534bcb total=42051.1ms bytes=18137 finished=True finish=tool_calls stop=None out_tok=326 prompt_tok=8745 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:35:08,732] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db72c2d754aa0d17bdb0cc491861ead4 attempt=1 -[2026-08-13 10:35:09,332] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db72c2d754aa0d17bdb0cc491861ead4 status=200 post_dur=0.600s -[2026-08-13 10:35:22,785] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db72c2d754aa0d17bdb0cc491861ead4 total=14053.0ms bytes=9011 finished=True finish=stop stop=None out_tok=30 prompt_tok=7346 tps=2.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:35:22,796] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=feaafb10695ae5754022c5c4960adf18 attempt=1 -[2026-08-13 10:35:23,345] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=feaafb10695ae5754022c5c4960adf18 status=200 post_dur=0.549s -[2026-08-13 10:38:18,576] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=feaafb10695ae5754022c5c4960adf18 total=175780.1ms bytes=140058 finished=True finish=stop stop=None out_tok=475 prompt_tok=73195 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:38:18,584] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a226a9108affcc69382a56d80100595d attempt=1 -[2026-08-13 10:38:19,199] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a226a9108affcc69382a56d80100595d status=200 post_dur=0.615s -[2026-08-13 10:38:31,357] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a226a9108affcc69382a56d80100595d total=12773.4ms bytes=9658 finished=True finish=tool_calls stop=None out_tok=73 prompt_tok=7573 tps=5.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:38:31,359] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a6092c183888b28b15f5c45bbb0fadf2 attempt=1 -[2026-08-13 10:38:31,644] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a6092c183888b28b15f5c45bbb0fadf2 status=200 post_dur=0.286s -[2026-08-13 10:42:09,663] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a6092c183888b28b15f5c45bbb0fadf2 total=218304.5ms bytes=724511 finished=True finish=stop stop=None out_tok=2494 prompt_tok=370 tps=11.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:42:09,666] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0565df1a12f2ca6e37273d15f3d14b4d attempt=1 -[2026-08-13 10:42:10,071] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0565df1a12f2ca6e37273d15f3d14b4d status=200 post_dur=0.404s -[2026-08-13 10:44:27,528] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0565df1a12f2ca6e37273d15f3d14b4d total=137862.2ms bytes=453187 finished=True finish=stop stop=None out_tok=1560 prompt_tok=249 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:44:27,532] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b900e4d7a184b278ed832645f55ab2b8 attempt=1 -[2026-08-13 10:44:28,168] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b900e4d7a184b278ed832645f55ab2b8 status=200 post_dur=0.636s -[2026-08-13 10:44:51,422] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b900e4d7a184b278ed832645f55ab2b8 total=23890.4ms bytes=11644 finished=True finish=tool_calls stop=None out_tok=174 prompt_tok=9083 tps=7.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:44:51,425] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=022d2b2b8c7d13cbff0c1b9628f84a6c attempt=1 -[2026-08-13 10:44:51,425] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 50% (440/881) has_cb=True -[2026-08-13 10:44:51,858] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=022d2b2b8c7d13cbff0c1b9628f84a6c status=200 post_dur=0.433s -[2026-08-13 10:45:22,771] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=022d2b2b8c7d13cbff0c1b9628f84a6c total=31346.4ms bytes=60386 finished=True finish=stop stop=None out_tok=205 prompt_tok=9567 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:45:22,798] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7581d09638f73e2b378c66ff03b96dd8 attempt=1 -[2026-08-13 10:45:22,810] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7581d09638f73e2b378c66ff03b96dd8 status=400 post_dur=0.012s -[2026-08-13 10:45:22,810] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7581d09638f73e2b378c66ff03b96dd8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 10:45:22,842] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7e4f846bbcd425fc5db38309beee377 attempt=1 -[2026-08-13 10:45:22,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7e4f846bbcd425fc5db38309beee377 status=400 post_dur=0.010s -[2026-08-13 10:45:22,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d7e4f846bbcd425fc5db38309beee377 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 10:45:22,861] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=32b82933b54025b46106559643673cf8 attempt=1 -[2026-08-13 10:45:23,246] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=32b82933b54025b46106559643673cf8 status=200 post_dur=0.383s -[2026-08-13 10:48:14,555] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=32b82933b54025b46106559643673cf8 total=171693.8ms bytes=560129 finished=True finish=stop stop=None out_tok=1927 prompt_tok=355 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:48:14,559] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f8c1bca56172e3337fbea71b510b6ea9 attempt=1 -[2026-08-13 10:48:14,956] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f8c1bca56172e3337fbea71b510b6ea9 status=200 post_dur=0.397s -[2026-08-13 10:50:36,902] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f8c1bca56172e3337fbea71b510b6ea9 total=142342.6ms bytes=465151 finished=True finish=stop stop=None out_tok=1600 prompt_tok=319 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:50:36,904] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 attempt=1 -[2026-08-13 10:50:37,202] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 status=200 post_dur=0.298s -[2026-08-13 10:53:35,479] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 total=178575.3ms bytes=591869 finished=True finish=stop stop=None out_tok=2036 prompt_tok=355 tps=11.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:53:35,485] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bea2801c53f38667fdbb545d12a6c42d attempt=1 -[2026-08-13 10:53:36,147] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bea2801c53f38667fdbb545d12a6c42d status=200 post_dur=0.662s -[2026-08-13 10:54:14,390] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bea2801c53f38667fdbb545d12a6c42d total=38904.8ms bytes=14896 finished=True finish=tool_calls stop=None out_tok=99 prompt_tok=20956 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:54:14,393] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ebb27d04a82dc701ceff0fc7cf634ca4 attempt=1 -[2026-08-13 10:54:14,692] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ebb27d04a82dc701ceff0fc7cf634ca4 status=200 post_dur=0.299s -[2026-08-13 10:57:14,023] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ebb27d04a82dc701ceff0fc7cf634ca4 total=179629.9ms bytes=596504 finished=True finish=length stop=None out_tok=2048 prompt_tok=355 tps=11.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:57:14,029] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b31f436e5f5e703425729a09d9384f7f attempt=1 -[2026-08-13 10:57:14,690] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b31f436e5f5e703425729a09d9384f7f status=200 post_dur=0.661s -[2026-08-13 10:57:58,325] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b31f436e5f5e703425729a09d9384f7f total=44295.8ms bytes=11174 finished=True finish=stop stop=None out_tok=37 prompt_tok=28646 tps=0.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:57:58,331] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1a6522cc010c520c4373d69e9a17ac82 attempt=1 -[2026-08-13 10:57:58,823] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1a6522cc010c520c4373d69e9a17ac82 status=200 post_dur=0.491s -[2026-08-13 10:58:41,763] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1a6522cc010c520c4373d69e9a17ac82 total=43431.8ms bytes=13527 finished=True finish=stop stop=None out_tok=45 prompt_tok=28785 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:58:41,769] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5c3932b77a057da7caec4c8336852f26 attempt=1 -[2026-08-13 10:58:42,248] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5c3932b77a057da7caec4c8336852f26 status=200 post_dur=0.478s -[2026-08-13 10:59:30,923] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5c3932b77a057da7caec4c8336852f26 total=49153.8ms bytes=40441 finished=True finish=tool_calls stop=None out_tok=174 prompt_tok=25038 tps=3.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:59:30,929] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ef445c15cceed8edec782bd8c1dd7481 attempt=1 -[2026-08-13 10:59:31,418] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ef445c15cceed8edec782bd8c1dd7481 status=200 post_dur=0.489s -[2026-08-13 10:59:43,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ef445c15cceed8edec782bd8c1dd7481 total=12466.1ms bytes=14430 finished=True finish=stop stop=None out_tok=48 prompt_tok=28795 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 10:59:43,402] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7951297b80918735c3976ec42dd1bc3a attempt=1 -[2026-08-13 10:59:43,863] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7951297b80918735c3976ec42dd1bc3a status=200 post_dur=0.461s -[2026-08-13 11:00:23,435] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7951297b80918735c3976ec42dd1bc3a total=40032.6ms bytes=13234 finished=True finish=stop stop=None out_tok=44 prompt_tok=28814 tps=1.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:00:23,439] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=72357751f6256ba81c96cf1c75bf20de attempt=1 -[2026-08-13 11:00:23,886] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=72357751f6256ba81c96cf1c75bf20de status=200 post_dur=0.447s -[2026-08-13 11:01:02,555] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=72357751f6256ba81c96cf1c75bf20de total=39115.9ms bytes=34200 finished=True finish=tool_calls stop=None out_tok=335 prompt_tok=9513 tps=8.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:01:02,561] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c3bc9ee2e12489608e0a6a7632bfac67 attempt=1 -[2026-08-13 11:01:03,217] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c3bc9ee2e12489608e0a6a7632bfac67 status=200 post_dur=0.656s -[2026-08-13 11:01:20,629] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c3bc9ee2e12489608e0a6a7632bfac67 total=18068.0ms bytes=15015 finished=True finish=stop stop=None out_tok=50 prompt_tok=28865 tps=2.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:01:20,657] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a9acfcad7d4f81bdf956b49c8c9237d2 attempt=1 -[2026-08-13 11:01:20,667] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a9acfcad7d4f81bdf956b49c8c9237d2 status=400 post_dur=0.010s -[2026-08-13 11:01:20,668] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a9acfcad7d4f81bdf956b49c8c9237d2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 11:01:20,687] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=af727512758092d747ce2d61d07ef790 attempt=1 -[2026-08-13 11:01:21,118] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=af727512758092d747ce2d61d07ef790 status=200 post_dur=0.430s -[2026-08-13 11:01:43,485] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=af727512758092d747ce2d61d07ef790 total=22798.1ms bytes=13204 finished=True finish=stop stop=None out_tok=44 prompt_tok=11655 tps=1.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:01:43,501] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7bd2b82352eb49f5bd56ff3259de2476 attempt=1 -[2026-08-13 11:01:43,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7bd2b82352eb49f5bd56ff3259de2476 status=400 post_dur=0.011s -[2026-08-13 11:01:43,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7bd2b82352eb49f5bd56ff3259de2476 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) -[2026-08-13 11:01:43,523] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac0b6fa67eeb91675b178489e49d32c3 attempt=1 -[2026-08-13 11:01:44,125] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac0b6fa67eeb91675b178489e49d32c3 status=200 post_dur=0.601s -[2026-08-13 11:02:06,757] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ac0b6fa67eeb91675b178489e49d32c3 total=23234.2ms bytes=13546 finished=True finish=tool_calls stop=None out_tok=122 prompt_tok=10017 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:02:06,760] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03592b84d37aac489062c3649a7a54da attempt=1 -[2026-08-13 11:02:07,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03592b84d37aac489062c3649a7a54da status=200 post_dur=0.468s -[2026-08-13 11:02:34,771] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03592b84d37aac489062c3649a7a54da total=28011.4ms bytes=37777 finished=True finish=tool_calls stop=None out_tok=217 prompt_tok=10337 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:02:34,775] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b97f3d051c2822653eed010996e8984 attempt=1 -[2026-08-13 11:02:35,264] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b97f3d051c2822653eed010996e8984 status=200 post_dur=0.490s -[2026-08-13 11:02:53,015] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b97f3d051c2822653eed010996e8984 total=18239.9ms bytes=36735 finished=True finish=stop stop=None out_tok=127 prompt_tok=10441 tps=7.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:02:53,018] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07b3a87bce0f474baa82b6ea7fb90697 attempt=1 -[2026-08-13 11:02:53,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07b3a87bce0f474baa82b6ea7fb90697 status=200 post_dur=0.440s -[2026-08-13 11:03:21,664] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=07b3a87bce0f474baa82b6ea7fb90697 total=28646.1ms bytes=81654 finished=True finish=stop stop=None out_tok=282 prompt_tok=10705 tps=9.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:03:21,691] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a65800f42cc9ccda52bc1ca4aa090ef9 attempt=1 -[2026-08-13 11:03:21,701] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a65800f42cc9ccda52bc1ca4aa090ef9 status=400 post_dur=0.010s -[2026-08-13 11:03:21,701] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a65800f42cc9ccda52bc1ca4aa090ef9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 11:03:21,728] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=788d64d04c24ba7f49b287783b7df63d attempt=1 -[2026-08-13 11:03:22,293] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=788d64d04c24ba7f49b287783b7df63d status=200 post_dur=0.565s -[2026-08-13 11:06:02,627] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=788d64d04c24ba7f49b287783b7df63d total=160899.3ms bytes=19423 finished=True finish=tool_calls stop=None out_tok=771 prompt_tok=77491 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:06:02,634] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=56672c2a06386f9216084b205d91a299 attempt=1 -[2026-08-13 11:06:03,078] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=56672c2a06386f9216084b205d91a299 status=200 post_dur=0.444s -[2026-08-13 11:06:25,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=56672c2a06386f9216084b205d91a299 total=22590.8ms bytes=32309 finished=True finish=tool_calls stop=None out_tok=250 prompt_tok=7229 tps=11.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:06:25,227] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=90fdbd989225f791f22a8d7c6713b8c8 attempt=1 -[2026-08-13 11:06:25,659] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=90fdbd989225f791f22a8d7c6713b8c8 status=200 post_dur=0.432s -[2026-08-13 11:06:40,965] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=90fdbd989225f791f22a8d7c6713b8c8 total=15738.2ms bytes=37556 finished=True finish=tool_calls stop=None out_tok=172 prompt_tok=7197 tps=10.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:06:40,977] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b16c5379cbe4ac359fe045f1b251d1fd attempt=1 -[2026-08-13 11:06:41,666] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b16c5379cbe4ac359fe045f1b251d1fd status=200 post_dur=0.688s -[2026-08-13 11:08:44,518] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b16c5379cbe4ac359fe045f1b251d1fd total=123541.6ms bytes=43553 finished=True finish=tool_calls stop=None out_tok=723 prompt_tok=76329 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:08:44,525] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9408271375a3c55f61a62d7d54438f65 attempt=1 -[2026-08-13 11:08:44,971] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9408271375a3c55f61a62d7d54438f65 status=200 post_dur=0.446s -[2026-08-13 11:08:52,985] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9408271375a3c55f61a62d7d54438f65 total=8459.3ms bytes=7902 finished=True finish=tool_calls stop=None out_tok=56 prompt_tok=7294 tps=6.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:08:52,987] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=91cde38354627ab0586a9bb7228a330f attempt=1 -[2026-08-13 11:08:53,409] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=91cde38354627ab0586a9bb7228a330f status=200 post_dur=0.423s -[2026-08-13 11:09:04,767] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=91cde38354627ab0586a9bb7228a330f total=11780.5ms bytes=8206 finished=True finish=tool_calls stop=None out_tok=65 prompt_tok=7526 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:09:04,769] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a79e369cb5dfffe7d98a4253cf78c0f7 attempt=1 -[2026-08-13 11:09:05,186] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a79e369cb5dfffe7d98a4253cf78c0f7 status=200 post_dur=0.416s -[2026-08-13 11:09:15,387] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a79e369cb5dfffe7d98a4253cf78c0f7 total=10617.6ms bytes=11391 finished=True finish=stop stop=None out_tok=38 prompt_tok=7841 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:09:15,389] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=767d433df35a797c831a6b269551a636 attempt=1 -[2026-08-13 11:09:15,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=767d433df35a797c831a6b269551a636 status=200 post_dur=0.435s -[2026-08-13 11:09:53,732] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=767d433df35a797c831a6b269551a636 total=38343.0ms bytes=13311 finished=True finish=tool_calls stop=None out_tok=340 prompt_tok=9886 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:09:53,735] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=559a25c823109c7916b634842e21d19b attempt=1 -[2026-08-13 11:09:54,184] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=559a25c823109c7916b634842e21d19b status=200 post_dur=0.449s -[2026-08-13 11:10:29,830] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=559a25c823109c7916b634842e21d19b total=36095.3ms bytes=72198 finished=True finish=stop stop=None out_tok=245 prompt_tok=13070 tps=6.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:10:29,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=91d117794014a96bf3b9ac1a4934dd78 attempt=1 -[2026-08-13 11:10:30,266] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=91d117794014a96bf3b9ac1a4934dd78 status=200 post_dur=0.432s -[2026-08-13 11:11:01,131] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=91d117794014a96bf3b9ac1a4934dd78 total=31297.4ms bytes=21639 finished=True finish=tool_calls stop=None out_tok=309 prompt_tok=10465 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:11:01,141] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=520d3bd3fc64de70453268e5baa2ea62 attempt=1 -[2026-08-13 11:11:01,751] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=520d3bd3fc64de70453268e5baa2ea62 status=200 post_dur=0.609s -[2026-08-13 11:22:37,907] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=520d3bd3fc64de70453268e5baa2ea62 total=696765.2ms bytes=123625 finished=True finish=tool_calls stop=None out_tok=3394 prompt_tok=98289 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:22:37,917] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2a8de1821196671dc704bbcafe61dde0 attempt=1 -[2026-08-13 11:22:38,388] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2a8de1821196671dc704bbcafe61dde0 status=200 post_dur=0.471s -[2026-08-13 11:23:28,164] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2a8de1821196671dc704bbcafe61dde0 total=50247.0ms bytes=26960 finished=True finish=tool_calls stop=None out_tok=280 prompt_tok=18425 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:23:28,168] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b4a18254d28c23095f6b4b7e35069a0 attempt=1 -[2026-08-13 11:23:28,628] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b4a18254d28c23095f6b4b7e35069a0 status=200 post_dur=0.459s -[2026-08-13 11:23:58,504] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b4a18254d28c23095f6b4b7e35069a0 total=30335.0ms bytes=13306 finished=True finish=tool_calls stop=None out_tok=277 prompt_tok=14200 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:23:58,518] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e5337acd0606cabf3bc95ef01ec4094 attempt=1 -[2026-08-13 11:23:59,095] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e5337acd0606cabf3bc95ef01ec4094 status=200 post_dur=0.575s -[2026-08-13 11:25:37,734] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6e5337acd0606cabf3bc95ef01ec4094 total=99216.7ms bytes=17293 finished=True finish=tool_calls stop=None out_tok=499 prompt_tok=78305 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:25:37,748] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=88c78115aced7a36e2a38629c6a9a3d0 attempt=1 -[2026-08-13 11:25:38,265] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=88c78115aced7a36e2a38629c6a9a3d0 status=200 post_dur=0.517s -[2026-08-13 11:26:53,602] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=88c78115aced7a36e2a38629c6a9a3d0 total=75854.1ms bytes=17449 finished=True finish=tool_calls stop=None out_tok=134 prompt_tok=45523 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:26:53,607] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2cf15ec1aeb8db5364671bff24998087 attempt=1 -[2026-08-13 11:26:53,923] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2cf15ec1aeb8db5364671bff24998087 status=200 post_dur=0.316s -[2026-08-13 11:29:40,647] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2cf15ec1aeb8db5364671bff24998087 total=167040.3ms bytes=571454 finished=True finish=stop stop=None out_tok=1948 prompt_tok=1133 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:29:40,651] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b attempt=1 -[2026-08-13 11:29:41,124] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b status=200 post_dur=0.472s -[2026-08-13 11:29:58,390] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b total=17739.0ms bytes=9758 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=14789 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:29:58,399] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=82c6bb52d3c3ce2441c194cc6392b9c9 attempt=1 -[2026-08-13 11:29:58,902] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=82c6bb52d3c3ce2441c194cc6392b9c9 status=200 post_dur=0.501s -[2026-08-13 11:30:34,599] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=82c6bb52d3c3ce2441c194cc6392b9c9 total=36199.6ms bytes=12628 finished=True finish=tool_calls stop=None out_tok=107 prompt_tok=45890 tps=3.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:30:34,605] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6a9a7675f53ca7c151831eb61229b018 attempt=1 -[2026-08-13 11:30:35,046] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6a9a7675f53ca7c151831eb61229b018 status=200 post_dur=0.441s -[2026-08-13 11:31:10,496] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6a9a7675f53ca7c151831eb61229b018 total=35891.4ms bytes=92729 finished=True finish=stop stop=None out_tok=319 prompt_tok=7707 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:31:10,500] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a attempt=1 -[2026-08-13 11:31:10,951] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a status=200 post_dur=0.451s -[2026-08-13 11:31:53,158] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a total=42658.1ms bytes=20753 finished=True finish=tool_calls stop=None out_tok=440 prompt_tok=16388 tps=10.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:31:53,162] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f51294fa1775431852330ac7c37db7e6 attempt=1 -[2026-08-13 11:31:53,615] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f51294fa1775431852330ac7c37db7e6 status=200 post_dur=0.454s -[2026-08-13 11:32:21,167] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f51294fa1775431852330ac7c37db7e6 total=28004.9ms bytes=11842 finished=True finish=tool_calls stop=None out_tok=134 prompt_tok=13638 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:32:21,175] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 54% (484/881) has_cb=True -[2026-08-13 11:32:21,179] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=baeb99b5aa23fd7430855568b3879abe attempt=1 -[2026-08-13 11:32:21,773] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=baeb99b5aa23fd7430855568b3879abe status=200 post_dur=0.594s -[2026-08-13 11:32:46,393] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=baeb99b5aa23fd7430855568b3879abe total=25214.0ms bytes=13722 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=78786 tps=3.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:32:46,401] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b688f7b1b297cd106f543711cae9a4f attempt=1 -[2026-08-13 11:32:46,862] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b688f7b1b297cd106f543711cae9a4f status=200 post_dur=0.460s -[2026-08-13 11:33:23,678] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b688f7b1b297cd106f543711cae9a4f total=37276.4ms bytes=87266 finished=True finish=stop stop=None out_tok=298 prompt_tok=17895 tps=8.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:33:23,691] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=94370a3b621376ee8fb9653c0a249680 attempt=1 -[2026-08-13 11:33:24,320] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=94370a3b621376ee8fb9653c0a249680 status=200 post_dur=0.629s -[2026-08-13 11:34:00,907] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=94370a3b621376ee8fb9653c0a249680 total=37215.6ms bytes=20284 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=79508 tps=5.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:34:00,924] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49c00854c28f996edc5e6ad0f28a6956 attempt=1 -[2026-08-13 11:34:01,502] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49c00854c28f996edc5e6ad0f28a6956 status=200 post_dur=0.578s -[2026-08-13 11:34:24,632] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=49c00854c28f996edc5e6ad0f28a6956 total=23708.1ms bytes=9507 finished=True finish=tool_calls stop=None out_tok=89 prompt_tok=79655 tps=3.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:34:24,646] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0ab5af499b282cf1341f1a64bf036563 attempt=1 -[2026-08-13 11:34:24,953] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0ab5af499b282cf1341f1a64bf036563 status=400 post_dur=0.307s -[2026-08-13 11:34:24,954] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0ab5af499b282cf1341f1a64bf036563 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 132798 tokens (67262 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 11:34:24,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ffee06953f66beac62e984c64cd4921f attempt=1 -[2026-08-13 11:34:25,427] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ffee06953f66beac62e984c64cd4921f status=200 post_dur=0.465s -[2026-08-13 11:36:03,382] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ffee06953f66beac62e984c64cd4921f total=98420.8ms bytes=202949 finished=True finish=stop stop=None out_tok=703 prompt_tok=30128 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:36:03,387] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c8407aa57c901822bd4a7f1a4824282e attempt=1 -[2026-08-13 11:36:03,830] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c8407aa57c901822bd4a7f1a4824282e status=200 post_dur=0.443s -[2026-08-13 11:36:34,664] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c8407aa57c901822bd4a7f1a4824282e total=31277.4ms bytes=12464 finished=True finish=tool_calls stop=None out_tok=222 prompt_tok=8054 tps=7.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:36:34,665] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87666946e7ef49235aaaad7bba67d7aa attempt=1 -[2026-08-13 11:36:34,953] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87666946e7ef49235aaaad7bba67d7aa status=200 post_dur=0.288s -[2026-08-13 11:42:44,840] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=87666946e7ef49235aaaad7bba67d7aa total=370174.6ms bytes=1266317 finished=True finish=stop stop=None out_tok=4377 prompt_tok=986 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:42:44,855] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e146957b208859356a77b2cdf7a8b5f7 attempt=1 -[2026-08-13 11:42:45,472] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e146957b208859356a77b2cdf7a8b5f7 status=200 post_dur=0.616s -[2026-08-13 11:43:53,879] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e146957b208859356a77b2cdf7a8b5f7 total=69024.1ms bytes=114267 finished=True finish=stop stop=None out_tok=398 prompt_tok=80081 tps=5.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:43:53,888] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b4c1b81c547fe11edcb629e03e4c76d5 attempt=1 -[2026-08-13 11:43:54,357] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b4c1b81c547fe11edcb629e03e4c76d5 status=200 post_dur=0.468s -[2026-08-13 11:44:15,352] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b4c1b81c547fe11edcb629e03e4c76d5 total=21463.7ms bytes=54254 finished=True finish=stop stop=None out_tok=187 prompt_tok=17360 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:44:15,362] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aea1d259d89a2eb16856934b75f0d484 attempt=1 -[2026-08-13 11:44:15,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aea1d259d89a2eb16856934b75f0d484 status=200 post_dur=0.485s -[2026-08-13 11:45:14,241] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=aea1d259d89a2eb16856934b75f0d484 total=58878.8ms bytes=20639 finished=True finish=stop stop=None out_tok=69 prompt_tok=35132 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:45:14,301] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2184f21cdc712067bbc06b55f9b93333 attempt=1 -[2026-08-13 11:45:14,898] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2184f21cdc712067bbc06b55f9b93333 status=200 post_dur=0.598s -[2026-08-13 11:46:02,373] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2184f21cdc712067bbc06b55f9b93333 total=48072.7ms bytes=9847 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=82118 tps=2.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:46:02,382] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6d2e1495524d98b499229d18fb2719f4 attempt=1 -[2026-08-13 11:46:02,858] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6d2e1495524d98b499229d18fb2719f4 status=200 post_dur=0.476s -[2026-08-13 11:46:39,424] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6d2e1495524d98b499229d18fb2719f4 total=37042.2ms bytes=7407 finished=True finish=tool_calls stop=None out_tok=72 prompt_tok=20316 tps=1.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:46:39,428] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f3d7b0a4eef9318758a46bef9644daaf attempt=1 -[2026-08-13 11:46:40,049] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f3d7b0a4eef9318758a46bef9644daaf status=200 post_dur=0.620s -[2026-08-13 11:49:31,200] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f3d7b0a4eef9318758a46bef9644daaf total=171772.1ms bytes=14826 finished=True finish=tool_calls stop=None out_tok=1787 prompt_tok=18563 tps=10.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:49:31,204] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c132e981015feb774a6b40404413fe48 attempt=1 -[2026-08-13 11:49:31,652] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c132e981015feb774a6b40404413fe48 status=200 post_dur=0.447s -[2026-08-13 11:49:39,268] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c132e981015feb774a6b40404413fe48 total=8063.6ms bytes=8760 finished=True finish=stop stop=None out_tok=29 prompt_tok=7388 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:49:39,270] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6056fb65ba8b11e1671ac10b9b26c05d attempt=1 -[2026-08-13 11:49:39,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6056fb65ba8b11e1671ac10b9b26c05d status=200 post_dur=0.419s -[2026-08-13 11:49:50,448] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6056fb65ba8b11e1671ac10b9b26c05d total=11178.1ms bytes=7302 finished=True finish=tool_calls stop=None out_tok=57 prompt_tok=7615 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:49:50,462] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39933fc2a7732142be84b5021b6bc226 attempt=1 -[2026-08-13 11:49:51,043] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39933fc2a7732142be84b5021b6bc226 status=200 post_dur=0.579s -[2026-08-13 11:51:03,696] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=39933fc2a7732142be84b5021b6bc226 total=73234.1ms bytes=85544 finished=True finish=tool_calls stop=None out_tok=401 prompt_tok=81477 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:51:03,706] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c432ceec50900a040871794ff14c8428 attempt=1 -[2026-08-13 11:51:04,188] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c432ceec50900a040871794ff14c8428 status=200 post_dur=0.481s -[2026-08-13 11:53:51,864] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c432ceec50900a040871794ff14c8428 total=168157.5ms bytes=487543 finished=True finish=stop stop=None out_tok=1669 prompt_tok=21151 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:53:51,878] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d1c10cd2b23d301652b17f5d21203516 attempt=1 -[2026-08-13 11:53:52,478] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d1c10cd2b23d301652b17f5d21203516 status=200 post_dur=0.599s -[2026-08-13 11:54:12,074] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d1c10cd2b23d301652b17f5d21203516 total=20196.1ms bytes=6287 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=81817 tps=4.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:54:12,092] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4836e6b5c8ea8ec79be47dfcfee4d22d attempt=1 -[2026-08-13 11:54:12,676] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4836e6b5c8ea8ec79be47dfcfee4d22d status=200 post_dur=0.584s -[2026-08-13 11:54:36,695] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4836e6b5c8ea8ec79be47dfcfee4d22d total=24603.2ms bytes=18969 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=81912 tps=5.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:54:36,702] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3f2ec22ac04405739c4822521d9783d attempt=1 -[2026-08-13 11:54:37,126] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3f2ec22ac04405739c4822521d9783d status=200 post_dur=0.423s -[2026-08-13 11:55:09,170] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3f2ec22ac04405739c4822521d9783d total=32467.4ms bytes=36113 finished=True finish=tool_calls stop=None out_tok=279 prompt_tok=7229 tps=8.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:55:09,174] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d76c7b7e31583f037d3fc46a28a67e2 attempt=1 -[2026-08-13 11:55:09,632] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d76c7b7e31583f037d3fc46a28a67e2 status=200 post_dur=0.458s -[2026-08-13 11:55:42,824] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3d76c7b7e31583f037d3fc46a28a67e2 total=33650.7ms bytes=5939 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=20475 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:55:42,828] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e25283e725bb1320f8ffb894b685a76 attempt=1 -[2026-08-13 11:55:43,268] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e25283e725bb1320f8ffb894b685a76 status=200 post_dur=0.440s -[2026-08-13 11:56:10,528] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3e25283e725bb1320f8ffb894b685a76 total=27700.8ms bytes=9783 finished=True finish=tool_calls stop=None out_tok=176 prompt_tok=7969 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:56:10,531] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab42192d9e63327faa6d9d6bd7232041 attempt=1 -[2026-08-13 11:56:10,958] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab42192d9e63327faa6d9d6bd7232041 status=200 post_dur=0.428s -[2026-08-13 11:56:38,657] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ab42192d9e63327faa6d9d6bd7232041 total=28125.9ms bytes=24208 finished=True finish=tool_calls stop=None out_tok=218 prompt_tok=9998 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:56:38,662] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=248cac21ae65186381de6e8118230699 attempt=1 -[2026-08-13 11:56:39,150] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=248cac21ae65186381de6e8118230699 status=200 post_dur=0.487s -[2026-08-13 11:57:37,620] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=248cac21ae65186381de6e8118230699 total=58957.8ms bytes=27625 finished=True finish=tool_calls stop=None out_tok=170 prompt_tok=32443 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:57:37,626] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e972aa3942f148deda44f4aa7cd39dc attempt=1 -[2026-08-13 11:57:38,092] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e972aa3942f148deda44f4aa7cd39dc status=200 post_dur=0.466s -[2026-08-13 11:57:49,558] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3e972aa3942f148deda44f4aa7cd39dc total=11932.5ms bytes=7123 finished=True finish=tool_calls stop=None out_tok=71 prompt_tok=19711 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:57:49,561] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6cbde6783a8c4561e1b19c6a34c73fe attempt=1 -[2026-08-13 11:57:49,989] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6cbde6783a8c4561e1b19c6a34c73fe status=200 post_dur=0.427s -[2026-08-13 11:58:05,893] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6cbde6783a8c4561e1b19c6a34c73fe total=16331.6ms bytes=11314 finished=True finish=tool_calls stop=None out_tok=90 prompt_tok=8760 tps=5.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:58:05,895] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=10c0375f972ee141fef6d820741d7b67 attempt=1 -[2026-08-13 11:58:06,314] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=10c0375f972ee141fef6d820741d7b67 status=200 post_dur=0.418s -[2026-08-13 11:58:26,224] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=10c0375f972ee141fef6d820741d7b67 total=20328.8ms bytes=33216 finished=True finish=stop stop=None out_tok=116 prompt_tok=9001 tps=5.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 11:58:26,226] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 attempt=1 -[2026-08-13 11:58:26,503] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 status=200 post_dur=0.277s -[2026-08-13 12:01:51,060] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 total=204834.1ms bytes=704834 finished=True finish=stop stop=None out_tok=2425 prompt_tok=124 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:01:51,065] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=92d54e76e1e8c369e8d915b943330332 attempt=1 -[2026-08-13 12:01:51,533] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=92d54e76e1e8c369e8d915b943330332 status=200 post_dur=0.469s -[2026-08-13 12:02:28,747] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=92d54e76e1e8c369e8d915b943330332 total=37682.8ms bytes=41724 finished=True finish=tool_calls stop=None out_tok=358 prompt_tok=14403 tps=9.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:02:28,754] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=faec012895ed44b46198171888c58f68 attempt=1 -[2026-08-13 12:02:29,251] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=faec012895ed44b46198171888c58f68 status=200 post_dur=0.497s -[2026-08-13 12:05:14,326] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=faec012895ed44b46198171888c58f68 total=165572.1ms bytes=10972 finished=True finish=tool_calls stop=None out_tok=992 prompt_tok=38041 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:05:14,352] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4afe8af206a3e5fb423fcf90962c2a82 attempt=1 -[2026-08-13 12:05:14,990] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4afe8af206a3e5fb423fcf90962c2a82 status=200 post_dur=0.638s -[2026-08-13 12:07:42,870] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4afe8af206a3e5fb423fcf90962c2a82 total=148517.8ms bytes=5550 finished=True finish=stop stop=None out_tok=18 prompt_tok=90087 tps=0.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:07:42,880] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f43101c82dd79fd6bc3f8bb7001b13cb attempt=1 -[2026-08-13 12:07:43,313] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f43101c82dd79fd6bc3f8bb7001b13cb status=200 post_dur=0.433s -[2026-08-13 12:08:08,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f43101c82dd79fd6bc3f8bb7001b13cb total=25705.2ms bytes=29607 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=7197 tps=7.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:08:08,598] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=afd019506d9c67fb54a1f7cb6b1512bc attempt=1 -[2026-08-13 12:08:09,182] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=afd019506d9c67fb54a1f7cb6b1512bc status=200 post_dur=0.583s -[2026-08-13 12:09:40,244] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=afd019506d9c67fb54a1f7cb6b1512bc total=91646.2ms bytes=158292 finished=True finish=stop stop=None out_tok=548 prompt_tok=84871 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:09:40,272] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f0fc3c03f50f31f76829a71a499d92e attempt=1 -[2026-08-13 12:09:40,907] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f0fc3c03f50f31f76829a71a499d92e status=200 post_dur=0.635s -[2026-08-13 12:12:10,689] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f0fc3c03f50f31f76829a71a499d92e total=150417.0ms bytes=17352 finished=True finish=stop stop=None out_tok=58 prompt_tok=90266 tps=0.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:12:10,700] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8d68e8ae14e4e7f649a5ceaf38a1121f attempt=1 -[2026-08-13 12:12:11,157] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8d68e8ae14e4e7f649a5ceaf38a1121f status=200 post_dur=0.456s -[2026-08-13 12:12:44,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8d68e8ae14e4e7f649a5ceaf38a1121f total=33891.9ms bytes=62855 finished=True finish=tool_calls stop=None out_tok=339 prompt_tok=15606 tps=10.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:12:44,607] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e88374f12de83b910d09e3f23434f8c8 attempt=1 -[2026-08-13 12:12:45,199] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e88374f12de83b910d09e3f23434f8c8 status=200 post_dur=0.592s -[2026-08-13 12:14:14,508] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e88374f12de83b910d09e3f23434f8c8 total=89900.7ms bytes=160537 finished=True finish=stop stop=None out_tok=556 prompt_tok=85506 tps=6.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:14:14,529] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c97a290f6e6a445f8a3eb02b49dc072 attempt=1 -[2026-08-13 12:14:15,129] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c97a290f6e6a445f8a3eb02b49dc072 status=200 post_dur=0.600s -[2026-08-13 12:14:38,049] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c97a290f6e6a445f8a3eb02b49dc072 total=23520.2ms bytes=17164 finished=True finish=tool_calls stop=None out_tok=112 prompt_tok=85386 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:14:38,058] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fea48fb5a69f25359c593d21f564dc88 attempt=1 -[2026-08-13 12:14:38,468] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fea48fb5a69f25359c593d21f564dc88 status=200 post_dur=0.410s -[2026-08-13 12:15:06,132] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fea48fb5a69f25359c593d21f564dc88 total=28073.7ms bytes=34603 finished=True finish=tool_calls stop=None out_tok=271 prompt_tok=1406 tps=9.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:15:06,135] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=093710e89a5c239545e99191909bf3a2 attempt=1 -[2026-08-13 12:15:06,600] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=093710e89a5c239545e99191909bf3a2 status=200 post_dur=0.464s -[2026-08-13 12:15:22,771] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=093710e89a5c239545e99191909bf3a2 total=16636.1ms bytes=17209 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=20704 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:15:22,774] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c26b7eb2a458da319e74275ea639f38c attempt=1 -[2026-08-13 12:15:23,047] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c26b7eb2a458da319e74275ea639f38c status=200 post_dur=0.274s -[2026-08-13 12:20:03,957] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c26b7eb2a458da319e74275ea639f38c total=281183.0ms bytes=969318 finished=True finish=stop stop=None out_tok=3329 prompt_tok=131 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:20:03,962] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d8de85a26ea050ffb37fa41c065476a5 attempt=1 -[2026-08-13 12:20:04,434] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d8de85a26ea050ffb37fa41c065476a5 status=200 post_dur=0.471s -[2026-08-13 12:20:47,614] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d8de85a26ea050ffb37fa41c065476a5 total=43652.2ms bytes=55837 finished=True finish=tool_calls stop=None out_tok=351 prompt_tok=16328 tps=8.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:20:47,617] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7f06b1abf52730de2eb1f656654f536 attempt=1 -[2026-08-13 12:20:47,917] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7f06b1abf52730de2eb1f656654f536 status=200 post_dur=0.300s -[2026-08-13 12:25:21,770] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7f06b1abf52730de2eb1f656654f536 total=274153.0ms bytes=930379 finished=True finish=stop stop=None out_tok=3195 prompt_tok=972 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:25:21,782] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=312d8b0505f0cb7179134bc400d13a6e attempt=1 -[2026-08-13 12:25:22,335] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=312d8b0505f0cb7179134bc400d13a6e status=200 post_dur=0.553s -[2026-08-13 12:27:05,149] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=312d8b0505f0cb7179134bc400d13a6e total=103366.4ms bytes=38222 finished=True finish=stop stop=None out_tok=133 prompt_tok=59214 tps=1.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:27:05,155] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45938b0cc831c0d3c80f1d1277b5f3ad attempt=1 -[2026-08-13 12:27:05,155] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 58% (528/881) has_cb=True -[2026-08-13 12:27:05,595] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45938b0cc831c0d3c80f1d1277b5f3ad status=200 post_dur=0.440s -[2026-08-13 12:27:41,572] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45938b0cc831c0d3c80f1d1277b5f3ad total=36416.6ms bytes=43802 finished=True finish=tool_calls stop=None out_tok=417 prompt_tok=7433 tps=11.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:27:41,576] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=081fe3a74bd43801f12c645e2a3ae7b7 attempt=1 -[2026-08-13 12:27:42,039] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=081fe3a74bd43801f12c645e2a3ae7b7 status=200 post_dur=0.463s -[2026-08-13 12:28:12,836] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=081fe3a74bd43801f12c645e2a3ae7b7 total=31260.1ms bytes=56985 finished=True finish=stop stop=None out_tok=199 prompt_tok=25271 tps=6.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:28:12,841] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b58038c4737a45f09fc0b1118bdf4141 attempt=1 -[2026-08-13 12:28:13,301] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b58038c4737a45f09fc0b1118bdf4141 status=200 post_dur=0.459s -[2026-08-13 12:28:48,051] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b58038c4737a45f09fc0b1118bdf4141 total=35209.6ms bytes=22402 finished=True finish=tool_calls stop=None out_tok=332 prompt_tok=16885 tps=9.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:28:48,056] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f38aca645e01b5450c80787a8e086615 attempt=1 -[2026-08-13 12:28:48,522] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f38aca645e01b5450c80787a8e086615 status=200 post_dur=0.466s -[2026-08-13 12:29:02,501] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f38aca645e01b5450c80787a8e086615 total=14445.4ms bytes=11812 finished=True finish=tool_calls stop=None out_tok=73 prompt_tok=21175 tps=5.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:29:02,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6723649fcfe66b870267a36cc1480224 attempt=1 -[2026-08-13 12:29:03,103] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6723649fcfe66b870267a36cc1480224 status=200 post_dur=0.591s -[2026-08-13 12:32:07,612] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6723649fcfe66b870267a36cc1480224 total=185099.8ms bytes=47988 finished=True finish=stop stop=None out_tok=166 prompt_tok=97666 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:32:07,632] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ed7b0f268e7473e470ecde2677ad894c attempt=1 -[2026-08-13 12:32:08,280] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ed7b0f268e7473e470ecde2677ad894c status=200 post_dur=0.648s -[2026-08-13 12:37:22,496] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ed7b0f268e7473e470ecde2677ad894c total=314863.2ms bytes=127618 finished=True finish=tool_calls stop=None out_tok=858 prompt_tok=105278 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:37:22,517] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 attempt=1 -[2026-08-13 12:37:23,143] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 status=200 post_dur=0.624s -[2026-08-13 12:44:39,060] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 total=436542.7ms bytes=23869 finished=True finish=tool_calls stop=None out_tok=117 prompt_tok=97854 tps=0.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:44:39,073] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 attempt=1 -[2026-08-13 12:44:39,538] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 status=200 post_dur=0.465s -[2026-08-13 12:45:14,699] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 total=35626.7ms bytes=8950 finished=True finish=tool_calls stop=None out_tok=105 prompt_tok=18613 tps=2.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:45:14,705] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bc17ec878bf859b2f969d6ca5ef0220a attempt=1 -[2026-08-13 12:45:15,163] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bc17ec878bf859b2f969d6ca5ef0220a status=200 post_dur=0.458s -[2026-08-13 12:48:03,019] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bc17ec878bf859b2f969d6ca5ef0220a total=168313.7ms bytes=459344 finished=True finish=stop stop=None out_tok=1606 prompt_tok=23226 tps=9.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:48:03,032] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=22c90534cda8c06901fc6b40a0f1d343 attempt=1 -[2026-08-13 12:48:03,416] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=22c90534cda8c06901fc6b40a0f1d343 status=400 post_dur=0.383s -[2026-08-13 12:48:03,416] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=22c90534cda8c06901fc6b40a0f1d343 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 164562 tokens (99026 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 12:48:03,423] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b02b3eb4794572cbc8049f7978e4755c attempt=1 -[2026-08-13 12:48:03,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b02b3eb4794572cbc8049f7978e4755c status=200 post_dur=0.411s -[2026-08-13 12:48:25,789] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b02b3eb4794572cbc8049f7978e4755c total=22365.3ms bytes=15863 finished=True finish=tool_calls stop=None out_tok=156 prompt_tok=9191 tps=7.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:48:25,793] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=924070facc5daa8a8ca16a926c529564 attempt=1 -[2026-08-13 12:48:26,268] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=924070facc5daa8a8ca16a926c529564 status=200 post_dur=0.475s -[2026-08-13 12:49:13,712] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=924070facc5daa8a8ca16a926c529564 total=47919.4ms bytes=34575 finished=True finish=tool_calls stop=None out_tok=175 prompt_tok=32804 tps=3.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:49:13,716] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a65336acb86bcebdfbd2b8c6bca1d061 attempt=1 -[2026-08-13 12:49:14,166] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a65336acb86bcebdfbd2b8c6bca1d061 status=200 post_dur=0.450s -[2026-08-13 12:49:38,133] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a65336acb86bcebdfbd2b8c6bca1d061 total=24416.9ms bytes=10117 finished=True finish=tool_calls stop=None out_tok=154 prompt_tok=9473 tps=6.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:49:38,136] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=edcf2f49985d064360ea6398600a8b12 attempt=1 -[2026-08-13 12:49:38,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=edcf2f49985d064360ea6398600a8b12 status=200 post_dur=0.450s -[2026-08-13 12:50:00,734] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=edcf2f49985d064360ea6398600a8b12 total=22597.8ms bytes=51230 finished=True finish=stop stop=None out_tok=180 prompt_tok=9815 tps=8.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:50:00,737] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3c2b7880184eb54fd9c7e0351370ed0c attempt=1 -[2026-08-13 12:50:01,171] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3c2b7880184eb54fd9c7e0351370ed0c status=200 post_dur=0.434s -[2026-08-13 12:50:14,734] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3c2b7880184eb54fd9c7e0351370ed0c total=13997.7ms bytes=11728 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=9635 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:50:14,736] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3158e44658122080759ed2c7aff28211 attempt=1 -[2026-08-13 12:50:15,162] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3158e44658122080759ed2c7aff28211 status=200 post_dur=0.426s -[2026-08-13 12:50:29,762] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3158e44658122080759ed2c7aff28211 total=15025.5ms bytes=11353 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=7294 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:50:29,771] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 attempt=1 -[2026-08-13 12:50:30,066] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 status=400 post_dur=0.294s -[2026-08-13 12:50:30,066] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 132798 tokens (67262 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 12:50:30,074] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7fbaa37cf7f1e96e4795b9d17055a38 attempt=1 -[2026-08-13 12:50:30,492] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7fbaa37cf7f1e96e4795b9d17055a38 status=200 post_dur=0.416s -[2026-08-13 12:50:54,873] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7fbaa37cf7f1e96e4795b9d17055a38 total=24798.8ms bytes=27533 finished=True finish=tool_calls stop=None out_tok=203 prompt_tok=10201 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:50:54,875] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2b12cf202b49219e657a8b2e81f9dfc1 attempt=1 -[2026-08-13 12:50:55,304] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2b12cf202b49219e657a8b2e81f9dfc1 status=200 post_dur=0.428s -[2026-08-13 12:51:10,626] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2b12cf202b49219e657a8b2e81f9dfc1 total=15751.1ms bytes=11052 finished=True finish=stop stop=None out_tok=37 prompt_tok=7776 tps=2.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:51:10,629] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f5d25e952ef8d660cd7497a38cf0270c attempt=1 -[2026-08-13 12:51:11,066] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f5d25e952ef8d660cd7497a38cf0270c status=200 post_dur=0.437s -[2026-08-13 12:51:20,209] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f5d25e952ef8d660cd7497a38cf0270c total=9580.4ms bytes=9922 finished=True finish=stop stop=None out_tok=33 prompt_tok=7938 tps=3.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:51:20,214] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e427beb44dc125b8bd82d43e4c32e97 attempt=1 -[2026-08-13 12:51:20,691] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e427beb44dc125b8bd82d43e4c32e97 status=200 post_dur=0.478s -[2026-08-13 12:52:16,825] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e427beb44dc125b8bd82d43e4c32e97 total=56611.1ms bytes=17921 finished=True finish=tool_calls stop=None out_tok=254 prompt_tok=35023 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:52:16,843] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7250fe183fffe987aec6d4b89b9965a8 attempt=1 -[2026-08-13 12:52:17,496] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7250fe183fffe987aec6d4b89b9965a8 status=200 post_dur=0.653s -[2026-08-13 12:52:50,287] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7250fe183fffe987aec6d4b89b9965a8 total=33444.2ms bytes=16464 finished=True finish=tool_calls stop=None out_tok=119 prompt_tok=105641 tps=3.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:52:50,296] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db53b560bbed67ab1e2158598060e88d attempt=1 -[2026-08-13 12:52:50,739] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db53b560bbed67ab1e2158598060e88d status=200 post_dur=0.443s -[2026-08-13 12:53:06,833] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db53b560bbed67ab1e2158598060e88d total=16537.2ms bytes=9254 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=10737 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:53:06,836] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=029e041b4912d1ebd63c7f0fa1351aa5 attempt=1 -[2026-08-13 12:53:07,277] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=029e041b4912d1ebd63c7f0fa1351aa5 status=200 post_dur=0.441s -[2026-08-13 12:53:25,458] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=029e041b4912d1ebd63c7f0fa1351aa5 total=18621.9ms bytes=14302 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=11113 tps=6.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:53:25,463] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74b0d5d0879c7f51f492013e43205593 attempt=1 -[2026-08-13 12:53:26,013] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74b0d5d0879c7f51f492013e43205593 status=200 post_dur=0.550s -[2026-08-13 12:55:29,148] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74b0d5d0879c7f51f492013e43205593 total=123685.1ms bytes=16698 finished=True finish=tool_calls stop=None out_tok=234 prompt_tok=65135 tps=1.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:55:29,153] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e74ce8663959187db4fe091ec5f1c42f attempt=1 -[2026-08-13 12:55:29,452] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e74ce8663959187db4fe091ec5f1c42f status=200 post_dur=0.299s -[2026-08-13 12:59:04,465] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e74ce8663959187db4fe091ec5f1c42f total=215311.7ms bytes=706819 finished=True finish=stop stop=None out_tok=2425 prompt_tok=362 tps=11.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 12:59:04,468] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d5d420ae0d25ad0437d519c768fd0e47 attempt=1 -[2026-08-13 12:59:04,769] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d5d420ae0d25ad0437d519c768fd0e47 status=200 post_dur=0.301s -[2026-08-13 13:02:51,029] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d5d420ae0d25ad0437d519c768fd0e47 total=226561.1ms bytes=771423 finished=True finish=stop stop=None out_tok=2647 prompt_tok=358 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:02:51,046] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=28abb489d809527e4bcc2c8752fa09b8 attempt=1 -[2026-08-13 13:02:51,660] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=28abb489d809527e4bcc2c8752fa09b8 status=200 post_dur=0.614s -[2026-08-13 13:04:54,844] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=28abb489d809527e4bcc2c8752fa09b8 total=123798.3ms bytes=28066 finished=True finish=tool_calls stop=None out_tok=153 prompt_tok=85425 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:04:54,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7f25dab6cfca855b9458f5c1669794e attempt=1 -[2026-08-13 13:04:55,296] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7f25dab6cfca855b9458f5c1669794e status=200 post_dur=0.443s -[2026-08-13 13:05:33,971] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7f25dab6cfca855b9458f5c1669794e total=39118.9ms bytes=30298 finished=True finish=tool_calls stop=None out_tok=357 prompt_tok=7229 tps=9.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:05:33,987] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c04babac846d016602c36a4d167ecdd5 attempt=1 -[2026-08-13 13:05:33,999] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c04babac846d016602c36a4d167ecdd5 status=400 post_dur=0.009s -[2026-08-13 13:05:33,999] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c04babac846d016602c36a4d167ecdd5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 13:05:34,009] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21ee0199b59266591733f3a31e6398c6 attempt=1 -[2026-08-13 13:05:34,469] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21ee0199b59266591733f3a31e6398c6 status=200 post_dur=0.458s -[2026-08-13 13:06:27,828] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=21ee0199b59266591733f3a31e6398c6 total=53819.2ms bytes=25870 finished=True finish=tool_calls stop=None out_tok=535 prompt_tok=12285 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:06:27,832] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=063bd0d56ee7c36da2edce892b9a9a01 attempt=1 -[2026-08-13 13:06:28,287] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=063bd0d56ee7c36da2edce892b9a9a01 status=200 post_dur=0.455s -[2026-08-13 13:06:42,039] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=063bd0d56ee7c36da2edce892b9a9a01 total=14207.3ms bytes=3013 finished=True finish=tool_calls stop=None out_tok=66 prompt_tok=12382 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:06:42,044] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80742d6579e019f5a55e92a87e6d3799 attempt=1 -[2026-08-13 13:06:42,630] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80742d6579e019f5a55e92a87e6d3799 status=200 post_dur=0.585s -[2026-08-13 13:10:12,089] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80742d6579e019f5a55e92a87e6d3799 total=210045.0ms bytes=115537 finished=True finish=tool_calls stop=None out_tok=448 prompt_tok=86747 tps=2.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:10:12,097] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1751d2a2d72071e3e1e23a141dd1dcee attempt=1 -[2026-08-13 13:10:12,621] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1751d2a2d72071e3e1e23a141dd1dcee status=200 post_dur=0.525s -[2026-08-13 13:11:33,710] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1751d2a2d72071e3e1e23a141dd1dcee total=81613.5ms bytes=56610 finished=True finish=tool_calls stop=None out_tok=221 prompt_tok=43817 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:11:33,729] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b034d8815c633b7b3142f73b4d6665f attempt=1 -[2026-08-13 13:11:33,746] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b034d8815c633b7b3142f73b4d6665f status=400 post_dur=0.009s -[2026-08-13 13:11:33,746] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0b034d8815c633b7b3142f73b4d6665f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 13:11:33,758] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2b4629c705e03c7baa507defa4060a62 attempt=1 -[2026-08-13 13:11:34,240] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2b4629c705e03c7baa507defa4060a62 status=200 post_dur=0.482s -[2026-08-13 13:12:18,960] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2b4629c705e03c7baa507defa4060a62 total=45202.1ms bytes=20323 finished=True finish=tool_calls stop=None out_tok=381 prompt_tok=25958 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:12:18,964] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a41c299f953102b14a53c164f6d20ce8 attempt=1 -[2026-08-13 13:12:19,408] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a41c299f953102b14a53c164f6d20ce8 status=200 post_dur=0.443s -[2026-08-13 13:12:43,278] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a41c299f953102b14a53c164f6d20ce8 total=24314.2ms bytes=57512 finished=True finish=stop stop=None out_tok=198 prompt_tok=12893 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:12:43,294] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=995096ab6f8f43b956cf2e4732ae7851 attempt=1 -[2026-08-13 13:12:43,884] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=995096ab6f8f43b956cf2e4732ae7851 status=200 post_dur=0.591s -[2026-08-13 13:14:23,912] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=995096ab6f8f43b956cf2e4732ae7851 total=100618.5ms bytes=29503 finished=True finish=tool_calls stop=None out_tok=493 prompt_tok=87160 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:14:23,930] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f attempt=1 -[2026-08-13 13:14:24,535] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f status=200 post_dur=0.605s -[2026-08-13 13:14:50,531] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f total=26601.0ms bytes=18622 finished=True finish=tool_calls stop=None out_tok=128 prompt_tok=86229 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:14:50,539] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45aeec5a434a049349b4acdd7f856e7e attempt=1 -[2026-08-13 13:14:50,993] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45aeec5a434a049349b4acdd7f856e7e status=200 post_dur=0.453s -[2026-08-13 13:15:22,803] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45aeec5a434a049349b4acdd7f856e7e total=32263.8ms bytes=84575 finished=True finish=stop stop=None out_tok=291 prompt_tok=13205 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:15:22,808] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb18e1593776a3836355a914f5aa0c53 attempt=1 -[2026-08-13 13:15:23,321] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb18e1593776a3836355a914f5aa0c53 status=200 post_dur=0.512s -[2026-08-13 13:16:37,449] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fb18e1593776a3836355a914f5aa0c53 total=74640.9ms bytes=6451 finished=True finish=tool_calls stop=None out_tok=46 prompt_tok=52221 tps=0.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:16:37,453] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=898794d56a74b0e64a50b428304105a8 attempt=1 -[2026-08-13 13:16:37,902] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=898794d56a74b0e64a50b428304105a8 status=200 post_dur=0.450s -[2026-08-13 13:17:16,630] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=898794d56a74b0e64a50b428304105a8 total=39177.1ms bytes=25423 finished=True finish=tool_calls stop=None out_tok=304 prompt_tok=8916 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:17:16,644] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a16b10f455c3304c2fb9fd68d1512d69 attempt=1 -[2026-08-13 13:17:17,248] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a16b10f455c3304c2fb9fd68d1512d69 status=200 post_dur=0.599s -[2026-08-13 13:18:39,701] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a16b10f455c3304c2fb9fd68d1512d69 total=83056.9ms bytes=16682 finished=True finish=tool_calls stop=None out_tok=492 prompt_tok=86880 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:18:39,713] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce attempt=1 -[2026-08-13 13:18:40,265] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce status=200 post_dur=0.553s -[2026-08-13 13:21:31,430] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce total=171716.9ms bytes=142263 finished=True finish=tool_calls stop=None out_tok=768 prompt_tok=55905 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:21:31,436] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0eb49188844d458d207604c17e5a3929 attempt=1 -[2026-08-13 13:21:31,436] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 62% (572/881) has_cb=True -[2026-08-13 13:21:31,969] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0eb49188844d458d207604c17e5a3929 status=200 post_dur=0.533s -[2026-08-13 13:22:50,054] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0eb49188844d458d207604c17e5a3929 total=78618.3ms bytes=8875 finished=True finish=tool_calls stop=None out_tok=73 prompt_tok=52353 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:22:50,070] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 attempt=1 -[2026-08-13 13:22:50,679] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 status=200 post_dur=0.608s -[2026-08-13 13:25:07,229] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 total=137159.4ms bytes=22086 finished=True finish=tool_calls stop=None out_tok=812 prompt_tok=87797 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:25:07,240] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=581edde74167a3c45573de2f1676b021 attempt=1 -[2026-08-13 13:25:07,787] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=581edde74167a3c45573de2f1676b021 status=200 post_dur=0.547s -[2026-08-13 13:26:27,648] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=581edde74167a3c45573de2f1676b021 total=80408.6ms bytes=8583 finished=True finish=tool_calls stop=None out_tok=78 prompt_tok=52497 tps=1.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:26:27,652] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=541237f01550b2cf13fe768369f702a5 attempt=1 -[2026-08-13 13:26:28,120] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=541237f01550b2cf13fe768369f702a5 status=200 post_dur=0.468s -[2026-08-13 13:27:00,847] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=541237f01550b2cf13fe768369f702a5 total=33195.1ms bytes=18081 finished=True finish=tool_calls stop=None out_tok=252 prompt_tok=9237 tps=7.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:27:00,850] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dadf47f2924a71aeebdf4def0a247a24 attempt=1 -[2026-08-13 13:27:01,301] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dadf47f2924a71aeebdf4def0a247a24 status=200 post_dur=0.450s -[2026-08-13 13:27:27,106] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dadf47f2924a71aeebdf4def0a247a24 total=26255.6ms bytes=65642 finished=True finish=stop stop=None out_tok=223 prompt_tok=9651 tps=8.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:27:27,109] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=232ea832a39433597fde4f14a674806e attempt=1 -[2026-08-13 13:27:27,544] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=232ea832a39433597fde4f14a674806e status=200 post_dur=0.435s -[2026-08-13 13:27:52,188] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=232ea832a39433597fde4f14a674806e total=25079.0ms bytes=26090 finished=True finish=tool_calls stop=None out_tok=187 prompt_tok=7197 tps=7.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:27:52,203] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd attempt=1 -[2026-08-13 13:27:52,807] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd status=200 post_dur=0.604s -[2026-08-13 13:29:58,569] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd total=126366.2ms bytes=34258 finished=True finish=tool_calls stop=None out_tok=743 prompt_tok=88698 tps=5.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:29:58,578] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 attempt=1 -[2026-08-13 13:29:59,025] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 status=200 post_dur=0.448s -[2026-08-13 13:30:14,592] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 total=16014.8ms bytes=15166 finished=True finish=stop stop=None out_tok=51 prompt_tok=7426 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:30:14,595] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d04bfff957574fc3cadb25e318f640eb attempt=1 -[2026-08-13 13:30:15,035] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d04bfff957574fc3cadb25e318f640eb status=200 post_dur=0.440s -[2026-08-13 13:31:13,513] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d04bfff957574fc3cadb25e318f640eb total=58917.6ms bytes=167580 finished=True finish=stop stop=None out_tok=580 prompt_tok=12431 tps=9.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:31:13,516] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e68ab759ebb81c0cdc4016ea50387e52 attempt=1 -[2026-08-13 13:31:13,961] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e68ab759ebb81c0cdc4016ea50387e52 status=200 post_dur=0.445s -[2026-08-13 13:31:24,396] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e68ab759ebb81c0cdc4016ea50387e52 total=10879.4ms bytes=14935 finished=True finish=tool_calls stop=None out_tok=86 prompt_tok=7530 tps=7.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:31:24,399] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4cea7c08234860fb460738dc8912a84b attempt=1 -[2026-08-13 13:31:24,837] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4cea7c08234860fb460738dc8912a84b status=200 post_dur=0.438s -[2026-08-13 13:32:30,118] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4cea7c08234860fb460738dc8912a84b total=65719.4ms bytes=203999 finished=True finish=stop stop=None out_tok=700 prompt_tok=15698 tps=10.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:32:30,123] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 attempt=1 -[2026-08-13 13:32:30,584] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 status=200 post_dur=0.461s -[2026-08-13 13:32:52,456] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 total=22333.7ms bytes=32797 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=13212 tps=9.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:32:52,461] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 attempt=1 -[2026-08-13 13:32:52,935] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 status=200 post_dur=0.473s -[2026-08-13 13:36:54,303] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 total=241841.8ms bytes=23161 finished=True finish=tool_calls stop=None out_tok=2625 prompt_tok=28318 tps=10.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:36:54,308] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=682bb781d4ef1bc29015ffe458c427ad attempt=1 -[2026-08-13 13:36:54,755] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=682bb781d4ef1bc29015ffe458c427ad status=200 post_dur=0.447s -[2026-08-13 13:37:03,571] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=682bb781d4ef1bc29015ffe458c427ad total=9262.7ms bytes=11102 finished=True finish=stop stop=None out_tok=37 prompt_tok=7843 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:37:03,572] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b6f364eaa495b697314b68be83d4a4bb attempt=1 -[2026-08-13 13:37:03,852] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b6f364eaa495b697314b68be83d4a4bb status=200 post_dur=0.280s -[2026-08-13 13:43:36,826] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b6f364eaa495b697314b68be83d4a4bb total=393253.9ms bytes=1352126 finished=True finish=stop stop=None out_tok=4640 prompt_tok=548 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:43:36,843] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d6a4a4fac1b9838447064f7b6daa52dc attempt=1 -[2026-08-13 13:43:37,473] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d6a4a4fac1b9838447064f7b6daa52dc status=200 post_dur=0.630s -[2026-08-13 13:45:27,928] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d6a4a4fac1b9838447064f7b6daa52dc total=111085.2ms bytes=16607 finished=True finish=tool_calls stop=None out_tok=683 prompt_tok=88483 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:45:27,941] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87a3cea97cf01e35c2ec790689c0c801 attempt=1 -[2026-08-13 13:45:28,486] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87a3cea97cf01e35c2ec790689c0c801 status=200 post_dur=0.541s -[2026-08-13 13:47:09,222] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=87a3cea97cf01e35c2ec790689c0c801 total=101281.1ms bytes=56343 finished=True finish=stop stop=None out_tok=195 prompt_tok=50704 tps=1.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:47:09,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c55ac9fc0bf64311641d91826a3a777a attempt=1 -[2026-08-13 13:47:09,672] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c55ac9fc0bf64311641d91826a3a777a status=200 post_dur=0.444s -[2026-08-13 13:47:58,860] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c55ac9fc0bf64311641d91826a3a777a total=49632.6ms bytes=28954 finished=True finish=tool_calls stop=None out_tok=416 prompt_tok=9201 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:47:58,879] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2d0551f547503ca534746ae888c882c8 attempt=1 -[2026-08-13 13:47:59,235] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2d0551f547503ca534746ae888c882c8 status=400 post_dur=0.357s -[2026-08-13 13:47:59,236] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2d0551f547503ca534746ae888c882c8 status=400 class=ctx_overflow error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=This model's maximum context length is 131072 tokens. However, you requested 142213 tokens (76677 in the messages, 65536 in the completion). Please reduce the length of the messages or completion. (retryable=False, attempt=1) -[2026-08-13 13:47:59,251] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=10c3f6626f09481a6a8bed57bda0c6a3 attempt=1 -[2026-08-13 13:47:59,753] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=10c3f6626f09481a6a8bed57bda0c6a3 status=200 post_dur=0.500s -[2026-08-13 13:48:12,429] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=10c3f6626f09481a6a8bed57bda0c6a3 total=13178.0ms bytes=7393 finished=True finish=tool_calls stop=None out_tok=61 prompt_tok=51158 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:48:12,433] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7f8fb51b56ed2258e2acc9e519541db2 attempt=1 -[2026-08-13 13:48:12,706] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7f8fb51b56ed2258e2acc9e519541db2 status=200 post_dur=0.273s -[2026-08-13 13:52:15,901] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7f8fb51b56ed2258e2acc9e519541db2 total=243468.7ms bytes=820803 finished=True finish=stop stop=None out_tok=2823 prompt_tok=593 tps=11.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:52:15,906] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea57d6b26dd9827842bc67ac8939ba8e attempt=1 -[2026-08-13 13:52:16,401] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea57d6b26dd9827842bc67ac8939ba8e status=200 post_dur=0.495s -[2026-08-13 13:53:14,024] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea57d6b26dd9827842bc67ac8939ba8e total=58117.8ms bytes=39676 finished=True finish=tool_calls stop=None out_tok=324 prompt_tok=25460 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 13:53:14,035] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5744fc796d14ca1c2f1a3a4fc368ff03 attempt=1 -[2026-08-13 13:53:14,681] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5744fc796d14ca1c2f1a3a4fc368ff03 status=200 post_dur=0.645s -[2026-08-13 14:09:22,000] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5744fc796d14ca1c2f1a3a4fc368ff03 total=967965.4ms bytes=42355 finished=True finish=tool_calls stop=None out_tok=4698 prompt_tok=110794 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:09:22,012] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74801d2b6e1344413d70868d48e27945 attempt=1 -[2026-08-13 14:09:22,588] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74801d2b6e1344413d70868d48e27945 status=200 post_dur=0.577s -[2026-08-13 14:10:41,737] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74801d2b6e1344413d70868d48e27945 total=79725.2ms bytes=26368 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=43310 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:10:41,740] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4ea211f22f784a62a9112c940048e76 attempt=1 -[2026-08-13 14:10:42,200] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4ea211f22f784a62a9112c940048e76 status=200 post_dur=0.460s -[2026-08-13 14:11:13,110] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4ea211f22f784a62a9112c940048e76 total=31369.2ms bytes=16547 finished=True finish=tool_calls stop=None out_tok=218 prompt_tok=10801 tps=6.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:11:13,112] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1c4b6526fdbbb273358af3f3ee24bc50 attempt=1 -[2026-08-13 14:11:13,565] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1c4b6526fdbbb273358af3f3ee24bc50 status=200 post_dur=0.453s -[2026-08-13 14:11:48,221] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1c4b6526fdbbb273358af3f3ee24bc50 total=35108.3ms bytes=16994 finished=True finish=tool_calls stop=None out_tok=354 prompt_tok=10482 tps=10.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:11:48,225] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b58587e2f2156097cc30c1fd9d06884 attempt=1 -[2026-08-13 14:11:48,773] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b58587e2f2156097cc30c1fd9d06884 status=200 post_dur=0.548s -[2026-08-13 14:13:23,276] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b58587e2f2156097cc30c1fd9d06884 total=95051.6ms bytes=16143 finished=True finish=tool_calls stop=None out_tok=111 prompt_tok=58375 tps=1.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:13:23,292] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e0e4ea9b2a019481d574c690a973542 attempt=1 -[2026-08-13 14:13:23,957] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e0e4ea9b2a019481d574c690a973542 status=200 post_dur=0.665s -[2026-08-13 14:21:29,432] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e0e4ea9b2a019481d574c690a973542 total=486139.2ms bytes=43126 finished=True finish=tool_calls stop=None out_tok=1532 prompt_tok=121309 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:21:29,452] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb6a3235bd8dde22d3dea0b3551a4003 attempt=1 -[2026-08-13 14:21:30,069] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb6a3235bd8dde22d3dea0b3551a4003 status=200 post_dur=0.617s -[2026-08-13 14:23:13,022] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fb6a3235bd8dde22d3dea0b3551a4003 total=103570.2ms bytes=124644 finished=True finish=tool_calls stop=None out_tok=478 prompt_tok=90038 tps=4.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:23:13,045] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d88101aaa3c2f1d392f4680a468b9268 attempt=1 -[2026-08-13 14:23:13,666] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d88101aaa3c2f1d392f4680a468b9268 status=200 post_dur=0.621s -[2026-08-13 14:23:46,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d88101aaa3c2f1d392f4680a468b9268 total=33806.4ms bytes=7440 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=90964 tps=2.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:23:46,859] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1c3d9ac233797d670c5d5201d895c14f attempt=1 -[2026-08-13 14:23:47,145] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1c3d9ac233797d670c5d5201d895c14f status=200 post_dur=0.286s -[2026-08-13 14:27:51,774] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1c3d9ac233797d670c5d5201d895c14f total=244915.0ms bytes=840406 finished=True finish=stop stop=None out_tok=2889 prompt_tok=542 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:27:51,779] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=06102f503fba4228f1a0711c6f168417 attempt=1 -[2026-08-13 14:27:52,251] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=06102f503fba4228f1a0711c6f168417 status=200 post_dur=0.472s -[2026-08-13 14:28:12,553] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=06102f503fba4228f1a0711c6f168417 total=20774.6ms bytes=10796 finished=True finish=tool_calls stop=None out_tok=113 prompt_tok=13038 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:28:12,562] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=128e3606dca3dd4d012e6069bb8272df attempt=1 -[2026-08-13 14:28:13,103] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=128e3606dca3dd4d012e6069bb8272df status=200 post_dur=0.540s -[2026-08-13 14:28:46,596] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=128e3606dca3dd4d012e6069bb8272df total=34034.0ms bytes=53514 finished=True finish=stop stop=None out_tok=184 prompt_tok=52294 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:28:46,600] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a78bfd66ce177b70452a35a38a5e5b75 attempt=1 -[2026-08-13 14:28:46,898] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a78bfd66ce177b70452a35a38a5e5b75 status=200 post_dur=0.297s -[2026-08-13 14:32:55,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a78bfd66ce177b70452a35a38a5e5b75 total=249250.8ms bytes=854634 finished=True finish=stop stop=None out_tok=2938 prompt_tok=569 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:32:55,856] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4112c97a2451f207899535c7eee5243b attempt=1 -[2026-08-13 14:32:56,327] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4112c97a2451f207899535c7eee5243b status=200 post_dur=0.471s -[2026-08-13 14:33:19,105] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4112c97a2451f207899535c7eee5243b total=23248.8ms bytes=17656 finished=True finish=tool_calls stop=None out_tok=157 prompt_tok=13403 tps=6.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:33:19,106] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe attempt=1 -[2026-08-13 14:33:19,392] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe status=200 post_dur=0.286s -[2026-08-13 14:39:01,622] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe total=342515.5ms bytes=1180630 finished=True finish=stop stop=None out_tok=4055 prompt_tok=537 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:39:01,627] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e0af977fdbf7c3b9f22a4e951d542a2 attempt=1 -[2026-08-13 14:39:02,085] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e0af977fdbf7c3b9f22a4e951d542a2 status=200 post_dur=0.458s -[2026-08-13 14:39:23,061] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6e0af977fdbf7c3b9f22a4e951d542a2 total=21433.3ms bytes=27596 finished=True finish=tool_calls stop=None out_tok=239 prompt_tok=7197 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:39:23,064] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=104241ef58ecfe337063e40a26b59742 attempt=1 -[2026-08-13 14:39:23,516] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=104241ef58ecfe337063e40a26b59742 status=200 post_dur=0.452s -[2026-08-13 14:39:49,072] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=104241ef58ecfe337063e40a26b59742 total=26008.1ms bytes=63756 finished=True finish=stop stop=None out_tok=215 prompt_tok=13641 tps=8.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:39:49,087] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03fa37d92159c07903a344809bb94c96 attempt=1 -[2026-08-13 14:39:49,700] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03fa37d92159c07903a344809bb94c96 status=200 post_dur=0.612s -[2026-08-13 14:41:40,269] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03fa37d92159c07903a344809bb94c96 total=111181.8ms bytes=55904 finished=True finish=tool_calls stop=None out_tok=597 prompt_tok=92399 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:41:40,277] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3419c407e5d404b8c562134084916a53 attempt=1 -[2026-08-13 14:41:40,587] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3419c407e5d404b8c562134084916a53 status=200 post_dur=0.310s -[2026-08-13 14:46:27,275] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3419c407e5d404b8c562134084916a53 total=286997.6ms bytes=987468 finished=True finish=stop stop=None out_tok=3394 prompt_tok=537 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:46:27,280] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=de2869d6bbf3ad41415bcae19a593267 attempt=1 -[2026-08-13 14:46:27,740] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=de2869d6bbf3ad41415bcae19a593267 status=200 post_dur=0.460s -[2026-08-13 14:46:35,821] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=de2869d6bbf3ad41415bcae19a593267 total=8541.2ms bytes=8766 finished=True finish=stop stop=None out_tok=29 prompt_tok=7666 tps=3.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:46:35,827] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f2290a1ebe57afe84b95d9e141b2b13d attempt=1 -[2026-08-13 14:46:36,269] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f2290a1ebe57afe84b95d9e141b2b13d status=200 post_dur=0.442s -[2026-08-13 14:46:57,729] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f2290a1ebe57afe84b95d9e141b2b13d total=21902.5ms bytes=61901 finished=True finish=stop stop=None out_tok=213 prompt_tok=13859 tps=9.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:46:57,747] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=faa096786ea7a27aea086ff1e5f0709f attempt=1 -[2026-08-13 14:46:58,361] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=faa096786ea7a27aea086ff1e5f0709f status=200 post_dur=0.615s -[2026-08-13 14:47:24,891] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=faa096786ea7a27aea086ff1e5f0709f total=27144.5ms bytes=7743 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=92992 tps=3.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:47:24,912] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=84995c7233752a30efd17762e7c12e6f attempt=1 -[2026-08-13 14:47:25,502] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=84995c7233752a30efd17762e7c12e6f status=200 post_dur=0.590s -[2026-08-13 14:47:46,720] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=84995c7233752a30efd17762e7c12e6f total=21808.2ms bytes=3307 finished=True finish=tool_calls stop=None out_tok=69 prompt_tok=93076 tps=3.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:47:46,730] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=37a9e3e4762efd2f5c0c47f2353ee105 attempt=1 -[2026-08-13 14:47:46,730] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 66% (616/881) has_cb=True -[2026-08-13 14:47:47,304] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=37a9e3e4762efd2f5c0c47f2353ee105 status=200 post_dur=0.574s -[2026-08-13 14:58:32,200] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=37a9e3e4762efd2f5c0c47f2353ee105 total=645469.9ms bytes=28649 finished=True finish=tool_calls stop=None out_tok=4440 prompt_tok=70311 tps=6.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:58:32,206] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=859b88bc3806f09b6a18faf10805b7e4 attempt=1 -[2026-08-13 14:58:32,681] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=859b88bc3806f09b6a18faf10805b7e4 status=200 post_dur=0.475s -[2026-08-13 14:59:06,347] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=859b88bc3806f09b6a18faf10805b7e4 total=34140.7ms bytes=9155 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=18593 tps=2.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 14:59:06,349] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 attempt=1 -[2026-08-13 14:59:06,642] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 status=200 post_dur=0.292s -[2026-08-13 15:02:42,811] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 total=216462.1ms bytes=746433 finished=True finish=stop stop=None out_tok=2566 prompt_tok=540 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:02:42,829] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bdeb4435351b882c8ae811933fbecadf attempt=1 -[2026-08-13 15:02:43,500] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bdeb4435351b882c8ae811933fbecadf status=200 post_dur=0.665s -[2026-08-13 15:06:51,794] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bdeb4435351b882c8ae811933fbecadf total=248964.6ms bytes=181395 finished=True finish=stop stop=None out_tok=617 prompt_tok=105825 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:06:51,803] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ef2055b1f042d938040df3eab9df8100 attempt=1 -[2026-08-13 15:06:52,103] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ef2055b1f042d938040df3eab9df8100 status=200 post_dur=0.300s -[2026-08-13 15:10:43,989] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ef2055b1f042d938040df3eab9df8100 total=232186.0ms bytes=795630 finished=True finish=stop stop=None out_tok=2734 prompt_tok=540 tps=11.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:10:43,993] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5db79e2b12ac689acdc11655a124ff5a attempt=1 -[2026-08-13 15:10:44,446] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5db79e2b12ac689acdc11655a124ff5a status=200 post_dur=0.453s -[2026-08-13 15:11:19,517] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5db79e2b12ac689acdc11655a124ff5a total=35523.9ms bytes=32892 finished=True finish=tool_calls stop=None out_tok=314 prompt_tok=7229 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:11:19,531] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cf45bd083c178f22f6465ede0bbe788f attempt=1 -[2026-08-13 15:11:20,158] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cf45bd083c178f22f6465ede0bbe788f status=200 post_dur=0.627s -[2026-08-13 15:12:00,344] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cf45bd083c178f22f6465ede0bbe788f total=40812.5ms bytes=31361 finished=True finish=tool_calls stop=None out_tok=177 prompt_tok=94811 tps=4.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:12:00,355] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9d97d66cceb27563585016c986a3af1b attempt=1 -[2026-08-13 15:12:00,934] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9d97d66cceb27563585016c986a3af1b status=200 post_dur=0.580s -[2026-08-13 15:12:40,079] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9d97d66cceb27563585016c986a3af1b total=39724.2ms bytes=8674 finished=True finish=tool_calls stop=None out_tok=99 prompt_tok=74146 tps=2.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:12:40,084] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=81c7bee1d0f4161bccadb5541ca5c1a6 attempt=1 -[2026-08-13 15:12:40,528] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=81c7bee1d0f4161bccadb5541ca5c1a6 status=200 post_dur=0.444s -[2026-08-13 15:13:09,509] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=81c7bee1d0f4161bccadb5541ca5c1a6 total=29425.0ms bytes=15313 finished=True finish=tool_calls stop=None out_tok=204 prompt_tok=7772 tps=6.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:13:09,511] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=816d7b5428ed1be410b7287bc61ad073 attempt=1 -[2026-08-13 15:13:09,941] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=816d7b5428ed1be410b7287bc61ad073 status=200 post_dur=0.430s -[2026-08-13 15:13:35,772] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=816d7b5428ed1be410b7287bc61ad073 total=26261.6ms bytes=16887 finished=True finish=tool_calls stop=None out_tok=231 prompt_tok=7898 tps=8.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:13:35,775] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9ccd7782d74bafaada51d2dfd0a820b6 attempt=1 -[2026-08-13 15:13:36,216] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9ccd7782d74bafaada51d2dfd0a820b6 status=200 post_dur=0.442s -[2026-08-13 15:14:32,115] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9ccd7782d74bafaada51d2dfd0a820b6 total=56339.9ms bytes=86122 finished=True finish=tool_calls stop=None out_tok=501 prompt_tok=9390 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:14:32,118] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f88ae55b820822ca0d6d284ed99c68a attempt=1 -[2026-08-13 15:14:32,568] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f88ae55b820822ca0d6d284ed99c68a status=200 post_dur=0.450s -[2026-08-13 15:14:57,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f88ae55b820822ca0d6d284ed99c68a total=25716.7ms bytes=15792 finished=True finish=tool_calls stop=None out_tok=140 prompt_tok=8844 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:14:57,837] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 attempt=1 -[2026-08-13 15:14:58,273] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 status=200 post_dur=0.436s -[2026-08-13 15:15:15,105] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 total=17268.1ms bytes=44147 finished=True finish=stop stop=None out_tok=154 prompt_tok=9055 tps=8.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:15:15,108] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ae7129dc7825ca4b4922f47ef4b6b817 attempt=1 -[2026-08-13 15:15:15,542] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ae7129dc7825ca4b4922f47ef4b6b817 status=200 post_dur=0.434s -[2026-08-13 15:16:02,576] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ae7129dc7825ca4b4922f47ef4b6b817 total=47468.4ms bytes=34747 finished=True finish=tool_calls stop=None out_tok=469 prompt_tok=8828 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:16:02,579] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0037cbe5fb38bb35563eb68ffd63f2dc attempt=1 -[2026-08-13 15:16:03,034] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0037cbe5fb38bb35563eb68ffd63f2dc status=200 post_dur=0.455s -[2026-08-13 15:16:19,489] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0037cbe5fb38bb35563eb68ffd63f2dc total=16910.1ms bytes=2932 finished=True finish=tool_calls stop=None out_tok=45 prompt_tok=10064 tps=2.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:16:19,492] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=748ccb810c5ee26afe5271127bcd71be attempt=1 -[2026-08-13 15:16:19,927] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=748ccb810c5ee26afe5271127bcd71be status=200 post_dur=0.435s -[2026-08-13 15:16:42,429] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=748ccb810c5ee26afe5271127bcd71be total=22936.8ms bytes=12183 finished=True finish=tool_calls stop=None out_tok=222 prompt_tok=9859 tps=9.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:16:42,435] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4ef25e1646a61801f96022b22237e75d attempt=1 -[2026-08-13 15:16:42,934] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4ef25e1646a61801f96022b22237e75d status=200 post_dur=0.499s -[2026-08-13 15:17:58,017] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4ef25e1646a61801f96022b22237e75d total=75581.9ms bytes=15384 finished=True finish=tool_calls stop=None out_tok=163 prompt_tok=40076 tps=2.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:17:58,022] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3176bc8dfe399f543afd31ce14aff7d0 attempt=1 -[2026-08-13 15:17:58,500] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3176bc8dfe399f543afd31ce14aff7d0 status=200 post_dur=0.478s -[2026-08-13 15:18:29,697] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3176bc8dfe399f543afd31ce14aff7d0 total=31675.6ms bytes=15060 finished=True finish=tool_calls stop=None out_tok=267 prompt_tok=13364 tps=8.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:18:29,703] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=175ca9cdfba5a980a3e77b3bb270f3e7 attempt=1 -[2026-08-13 15:18:30,515] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=175ca9cdfba5a980a3e77b3bb270f3e7 status=200 post_dur=0.811s -[2026-08-13 15:19:02,062] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=175ca9cdfba5a980a3e77b3bb270f3e7 total=32358.3ms bytes=17144 finished=True finish=tool_calls stop=None out_tok=147 prompt_tok=44704 tps=4.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:19:02,067] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7410174a4a76efde6b06949906f79bc6 attempt=1 -[2026-08-13 15:19:02,525] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7410174a4a76efde6b06949906f79bc6 status=200 post_dur=0.458s -[2026-08-13 15:19:35,065] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7410174a4a76efde6b06949906f79bc6 total=32997.8ms bytes=27655 finished=True finish=tool_calls stop=None out_tok=326 prompt_tok=11594 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:19:35,071] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0ed5d84769f7c4d9b682d80ea4f85b80 attempt=1 -[2026-08-13 15:19:35,585] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0ed5d84769f7c4d9b682d80ea4f85b80 status=200 post_dur=0.514s -[2026-08-13 15:19:57,049] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0ed5d84769f7c4d9b682d80ea4f85b80 total=21978.3ms bytes=10437 finished=True finish=tool_calls stop=None out_tok=142 prompt_tok=40570 tps=6.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:19:57,057] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=820cbdd56093ff0b360fbc48bc80b984 attempt=1 -[2026-08-13 15:19:57,511] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=820cbdd56093ff0b360fbc48bc80b984 status=200 post_dur=0.454s -[2026-08-13 15:20:23,797] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=820cbdd56093ff0b360fbc48bc80b984 total=26739.5ms bytes=24351 finished=True finish=tool_calls stop=None out_tok=256 prompt_tok=12381 tps=9.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:20:23,809] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9df64eb29d4f0a19dac69304dfc74345 attempt=1 -[2026-08-13 15:20:24,334] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9df64eb29d4f0a19dac69304dfc74345 status=200 post_dur=0.516s -[2026-08-13 15:21:37,616] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9df64eb29d4f0a19dac69304dfc74345 total=73806.8ms bytes=19322 finished=True finish=stop stop=None out_tok=66 prompt_tok=46520 tps=0.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:21:37,634] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=263af4cb7bf009461ee438fc2761358c attempt=1 -[2026-08-13 15:21:38,303] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=263af4cb7bf009461ee438fc2761358c status=200 post_dur=0.663s -[2026-08-13 15:28:02,537] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=263af4cb7bf009461ee438fc2761358c total=384903.2ms bytes=9512 finished=True finish=tool_calls stop=None out_tok=1186 prompt_tok=114005 tps=3.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:28:02,547] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5edeed4a34fa4c38655a08215a3b343b attempt=1 -[2026-08-13 15:28:02,997] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5edeed4a34fa4c38655a08215a3b343b status=200 post_dur=0.450s -[2026-08-13 15:28:10,724] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5edeed4a34fa4c38655a08215a3b343b total=8177.1ms bytes=3528 finished=True finish=tool_calls stop=None out_tok=57 prompt_tok=7307 tps=7.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:28:10,739] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=69fba56c09d963a5c1c96bd939c2d2bb attempt=1 -[2026-08-13 15:28:11,344] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=69fba56c09d963a5c1c96bd939c2d2bb status=200 post_dur=0.601s -[2026-08-13 15:31:47,959] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=69fba56c09d963a5c1c96bd939c2d2bb total=217220.1ms bytes=114775 finished=True finish=stop stop=None out_tok=393 prompt_tok=96266 tps=1.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:31:47,975] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=af68150f83e67dbc37f04cccc839b789 attempt=1 -[2026-08-13 15:31:48,504] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=af68150f83e67dbc37f04cccc839b789 status=200 post_dur=0.529s -[2026-08-13 15:32:55,151] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=af68150f83e67dbc37f04cccc839b789 total=67176.6ms bytes=75313 finished=True finish=stop stop=None out_tok=262 prompt_tok=46672 tps=3.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:32:55,156] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=788904c22957b5bf226fcde26ad387d0 attempt=1 -[2026-08-13 15:32:55,460] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=788904c22957b5bf226fcde26ad387d0 status=200 post_dur=0.303s -[2026-08-13 15:37:37,438] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=788904c22957b5bf226fcde26ad387d0 total=282282.0ms bytes=961297 finished=True finish=stop stop=None out_tok=3316 prompt_tok=540 tps=11.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:37:37,450] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db attempt=1 -[2026-08-13 15:37:37,995] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db status=200 post_dur=0.545s -[2026-08-13 15:39:05,310] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db total=87860.1ms bytes=50853 finished=True finish=stop stop=None out_tok=172 prompt_tok=46672 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:39:05,316] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4bff32787c3a952325ebdb8621331ac9 attempt=1 -[2026-08-13 15:39:05,766] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4bff32787c3a952325ebdb8621331ac9 status=200 post_dur=0.450s -[2026-08-13 15:39:12,231] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4bff32787c3a952325ebdb8621331ac9 total=6914.8ms bytes=8462 finished=True finish=stop stop=None out_tok=28 prompt_tok=7755 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:39:12,247] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f5f79bc1ceaf96da2cf7d93a45d905d attempt=1 -[2026-08-13 15:39:12,850] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f5f79bc1ceaf96da2cf7d93a45d905d status=200 post_dur=0.604s -[2026-08-13 15:43:16,911] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f5f79bc1ceaf96da2cf7d93a45d905d total=244663.9ms bytes=93503 finished=True finish=stop stop=None out_tok=323 prompt_tok=107649 tps=1.3 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:43:16,934] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=440568bcab80772c65a1a19b6c4a2e4b attempt=1 -[2026-08-13 15:43:17,597] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=440568bcab80772c65a1a19b6c4a2e4b status=200 post_dur=0.663s -[2026-08-13 15:48:24,008] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=440568bcab80772c65a1a19b6c4a2e4b total=307074.3ms bytes=195634 finished=True finish=stop stop=None out_tok=680 prompt_tok=122904 tps=2.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:48:24,026] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e2bb5eb73878fe0447ffa145451449c attempt=1 -[2026-08-13 15:48:24,551] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e2bb5eb73878fe0447ffa145451449c status=200 post_dur=0.523s -[2026-08-13 15:48:34,131] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e2bb5eb73878fe0447ffa145451449c total=10104.3ms bytes=7921 finished=True finish=stop stop=None out_tok=26 prompt_tok=47569 tps=2.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:48:34,140] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ccba346fe9fd8c8963c2eb8cc9192609 attempt=1 -[2026-08-13 15:48:34,630] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ccba346fe9fd8c8963c2eb8cc9192609 status=200 post_dur=0.490s -[2026-08-13 15:50:07,041] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ccba346fe9fd8c8963c2eb8cc9192609 total=92901.3ms bytes=50892 finished=True finish=tool_calls stop=None out_tok=355 prompt_tok=44724 tps=3.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:50:07,055] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49fdd29c1e750cc0095af7a7d202779b attempt=1 -[2026-08-13 15:50:07,622] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49fdd29c1e750cc0095af7a7d202779b status=200 post_dur=0.565s -[2026-08-13 15:51:50,633] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=49fdd29c1e750cc0095af7a7d202779b total=103577.4ms bytes=171151 finished=True finish=stop stop=None out_tok=595 prompt_tok=52365 tps=5.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:51:50,640] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b5934204c5ba11ac7bd0cde16fc8302 attempt=1 -[2026-08-13 15:51:51,102] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b5934204c5ba11ac7bd0cde16fc8302 status=200 post_dur=0.463s -[2026-08-13 15:53:35,772] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b5934204c5ba11ac7bd0cde16fc8302 total=105132.0ms bytes=303115 finished=True finish=stop stop=None out_tok=1044 prompt_tok=13359 tps=9.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:53:35,776] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4f5fada8238654bc3501c846608f7957 attempt=1 -[2026-08-13 15:53:36,242] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4f5fada8238654bc3501c846608f7957 status=200 post_dur=0.466s -[2026-08-13 15:54:08,237] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4f5fada8238654bc3501c846608f7957 total=32460.3ms bytes=10617 finished=True finish=tool_calls stop=None out_tok=194 prompt_tok=13902 tps=6.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:54:08,240] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=41b2156ad49ca72ea2116ebae8befd04 attempt=1 -[2026-08-13 15:54:08,701] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=41b2156ad49ca72ea2116ebae8befd04 status=200 post_dur=0.461s -[2026-08-13 15:54:46,567] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=41b2156ad49ca72ea2116ebae8befd04 total=38327.4ms bytes=25904 finished=True finish=tool_calls stop=None out_tok=283 prompt_tok=13273 tps=7.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 15:54:46,569] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fad751a2f24c9becb63bdcd8b4602b0 attempt=1 -[2026-08-13 15:54:46,864] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fad751a2f24c9becb63bdcd8b4602b0 status=200 post_dur=0.296s -[2026-08-13 16:00:46,730] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fad751a2f24c9becb63bdcd8b4602b0 total=360161.4ms bytes=1248541 finished=True finish=stop stop=None out_tok=4295 prompt_tok=540 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:00:46,751] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=52d47c0440fe8244cd59e99870eaff80 attempt=1 -[2026-08-13 16:00:47,420] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=52d47c0440fe8244cd59e99870eaff80 status=200 post_dur=0.669s -[2026-08-13 16:03:20,769] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=52d47c0440fe8244cd59e99870eaff80 total=154018.8ms bytes=229499 finished=True finish=stop stop=None out_tok=799 prompt_tok=115151 tps=5.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:03:20,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=35a9a8671ea3aac267092deeb15b1ff9 attempt=1 -[2026-08-13 16:03:21,235] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=35a9a8671ea3aac267092deeb15b1ff9 status=200 post_dur=0.454s -[2026-08-13 16:03:52,362] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=35a9a8671ea3aac267092deeb15b1ff9 total=31580.6ms bytes=21320 finished=True finish=tool_calls stop=None out_tok=193 prompt_tok=8031 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:03:52,363] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6efce744b4d2681b3918d6dfce942922 attempt=1 -[2026-08-13 16:03:52,746] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6efce744b4d2681b3918d6dfce942922 status=200 post_dur=0.382s -[2026-08-13 16:06:32,788] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6efce744b4d2681b3918d6dfce942922 total=160424.7ms bytes=524839 finished=True finish=stop stop=None out_tok=1791 prompt_tok=1559 tps=11.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:06:32,792] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5efed514ae2a145d3506fb048b6241de attempt=1 -[2026-08-13 16:06:33,258] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5efed514ae2a145d3506fb048b6241de status=200 post_dur=0.466s -[2026-08-13 16:07:07,108] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5efed514ae2a145d3506fb048b6241de total=34316.2ms bytes=33496 finished=True finish=tool_calls stop=None out_tok=297 prompt_tok=9330 tps=8.7 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:07:07,113] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9dc63684b6d5f28c198da1c92ef36976 attempt=1 -[2026-08-13 16:07:07,590] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9dc63684b6d5f28c198da1c92ef36976 status=200 post_dur=0.477s -[2026-08-13 16:08:38,233] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9dc63684b6d5f28c198da1c92ef36976 total=91120.1ms bytes=205664 finished=True finish=stop stop=None out_tok=707 prompt_tok=27546 tps=7.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:08:38,238] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3a845e29c3f5d2fd4d7586880d69c2c3 attempt=1 -[2026-08-13 16:08:38,238] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 70% (660/881) has_cb=True -[2026-08-13 16:08:38,693] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3a845e29c3f5d2fd4d7586880d69c2c3 status=200 post_dur=0.454s -[2026-08-13 16:08:59,877] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3a845e29c3f5d2fd4d7586880d69c2c3 total=21638.9ms bytes=8828 finished=True finish=tool_calls stop=None out_tok=121 prompt_tok=9612 tps=5.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:08:59,880] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b1a08a1ae782b81c2138c65515224b2 attempt=1 -[2026-08-13 16:09:00,309] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b1a08a1ae782b81c2138c65515224b2 status=200 post_dur=0.430s -[2026-08-13 16:09:22,929] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b1a08a1ae782b81c2138c65515224b2 total=23049.6ms bytes=9966 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=7787 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:09:22,943] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8d805fc340e553746465349bcc736c4a attempt=1 -[2026-08-13 16:09:23,545] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8d805fc340e553746465349bcc736c4a status=200 post_dur=0.601s -[2026-08-13 16:11:26,484] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8d805fc340e553746465349bcc736c4a total=123540.6ms bytes=35020 finished=True finish=tool_calls stop=None out_tok=611 prompt_tok=96148 tps=4.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:11:26,493] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b793c03effdd47955bbe35351fb81ebf attempt=1 -[2026-08-13 16:11:26,958] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b793c03effdd47955bbe35351fb81ebf status=200 post_dur=0.466s -[2026-08-13 16:12:37,779] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b793c03effdd47955bbe35351fb81ebf total=71286.2ms bytes=194264 finished=True finish=stop stop=None out_tok=677 prompt_tok=15999 tps=9.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:12:37,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e549cb549b08e6f7d377f52f85509ed5 attempt=1 -[2026-08-13 16:12:38,080] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e549cb549b08e6f7d377f52f85509ed5 status=200 post_dur=0.298s -[2026-08-13 16:18:01,706] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e549cb549b08e6f7d377f52f85509ed5 total=323924.6ms bytes=1119743 finished=True finish=stop stop=None out_tok=3854 prompt_tok=540 tps=11.9 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:18:01,711] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c48208521c9d36be53831b7dbc0549b3 attempt=1 -[2026-08-13 16:18:02,172] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c48208521c9d36be53831b7dbc0549b3 status=200 post_dur=0.461s -[2026-08-13 16:18:12,671] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c48208521c9d36be53831b7dbc0549b3 total=10960.0ms bytes=9949 finished=True finish=stop stop=None out_tok=33 prompt_tok=8191 tps=3.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:18:12,673] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7adce66ea6f56253cc33c8d74330235 attempt=1 -[2026-08-13 16:18:13,098] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7adce66ea6f56253cc33c8d74330235 status=200 post_dur=0.425s -[2026-08-13 16:18:35,851] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7adce66ea6f56253cc33c8d74330235 total=23177.6ms bytes=33057 finished=True finish=stop stop=None out_tok=112 prompt_tok=8320 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:18:35,853] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4f5d7c11192057e3feb3c46857e2a9d attempt=1 -[2026-08-13 16:18:36,287] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4f5d7c11192057e3feb3c46857e2a9d status=200 post_dur=0.433s -[2026-08-13 16:18:48,770] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4f5d7c11192057e3feb3c46857e2a9d total=12916.9ms bytes=18423 finished=True finish=stop stop=None out_tok=62 prompt_tok=8301 tps=4.8 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:18:48,773] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7e91035da05743523fd6837ca145fcf6 attempt=1 -[2026-08-13 16:18:49,204] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7e91035da05743523fd6837ca145fcf6 status=200 post_dur=0.431s -[2026-08-13 16:19:01,776] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7e91035da05743523fd6837ca145fcf6 total=13003.4ms bytes=15798 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=10519 tps=7.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:19:01,781] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9616ac2056cd5ca2cba64bad90dd24f8 attempt=1 -[2026-08-13 16:19:02,348] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9616ac2056cd5ca2cba64bad90dd24f8 status=200 post_dur=0.566s -[2026-08-13 16:32:46,607] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9616ac2056cd5ca2cba64bad90dd24f8 total=824825.3ms bytes=1462841 finished=True finish=tool_calls stop=None out_tok=4991 prompt_tok=74000 tps=6.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:32:46,623] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ed5227a774ede3c260f6e79accb678f9 attempt=1 -[2026-08-13 16:32:46,630] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ed5227a774ede3c260f6e79accb678f9 status=400 post_dur=0.007s -[2026-08-13 16:32:46,631] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ed5227a774ede3c260f6e79accb678f9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:43325/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) -[2026-08-13 16:32:46,636] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=139ffb2666d8dd0ac24d34f3257b90ca attempt=1 -[2026-08-13 16:32:47,078] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=139ffb2666d8dd0ac24d34f3257b90ca status=200 post_dur=0.440s -[2026-08-13 16:33:16,486] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=139ffb2666d8dd0ac24d34f3257b90ca total=29849.4ms bytes=15845 finished=True finish=tool_calls stop=None out_tok=245 prompt_tok=11405 tps=8.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:33:16,489] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6437b0bbe06fdc147e24d034c65ac025 attempt=1 -[2026-08-13 16:33:16,932] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6437b0bbe06fdc147e24d034c65ac025 status=200 post_dur=0.443s -[2026-08-13 16:33:55,772] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6437b0bbe06fdc147e24d034c65ac025 total=39283.0ms bytes=44379 finished=True finish=tool_calls stop=None out_tok=399 prompt_tok=12577 tps=10.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:33:55,775] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c5deaf60300d84afbce55d2d1043ecb8 attempt=1 -[2026-08-13 16:33:56,216] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c5deaf60300d84afbce55d2d1043ecb8 status=200 post_dur=0.441s -[2026-08-13 16:34:17,414] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c5deaf60300d84afbce55d2d1043ecb8 total=21639.1ms bytes=21980 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=12028 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:34:17,417] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6c623f2bc44ed880a3cc333f6585bd3 attempt=1 -[2026-08-13 16:34:17,834] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6c623f2bc44ed880a3cc333f6585bd3 status=200 post_dur=0.418s -[2026-08-13 16:34:40,454] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6c623f2bc44ed880a3cc333f6585bd3 total=23037.7ms bytes=13708 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=7891 tps=8.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:34:40,463] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7a8000c7a656ab74224e177fb985e988 attempt=1 -[2026-08-13 16:34:40,976] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7a8000c7a656ab74224e177fb985e988 status=200 post_dur=0.511s -[2026-08-13 16:35:39,505] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7a8000c7a656ab74224e177fb985e988 total=59042.2ms bytes=14176 finished=True finish=tool_calls stop=None out_tok=204 prompt_tok=45526 tps=3.5 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:35:39,515] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1077b34d114c5fd3705bcec999d85d17 attempt=1 -[2026-08-13 16:35:40,039] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1077b34d114c5fd3705bcec999d85d17 status=200 post_dur=0.524s -[2026-08-13 16:36:22,208] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1077b34d114c5fd3705bcec999d85d17 total=42693.4ms bytes=13332 finished=True finish=tool_calls stop=None out_tok=87 prompt_tok=53368 tps=2.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:36:22,222] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c42e43e0575fc20a868511f953c0ff86 attempt=1 -[2026-08-13 16:36:22,800] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c42e43e0575fc20a868511f953c0ff86 status=200 post_dur=0.578s -[2026-08-13 16:39:03,445] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c42e43e0575fc20a868511f953c0ff86 total=161223.7ms bytes=12365 finished=True finish=tool_calls stop=None out_tok=218 prompt_tok=83646 tps=1.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:39:03,453] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a402e775c8dbc194998438ebe3430375 attempt=1 -[2026-08-13 16:39:03,910] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a402e775c8dbc194998438ebe3430375 status=200 post_dur=0.458s -[2026-08-13 16:39:34,673] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a402e775c8dbc194998438ebe3430375 total=31220.1ms bytes=73497 finished=True finish=stop stop=None out_tok=253 prompt_tok=13505 tps=8.1 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:39:34,677] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=500a26f22e1662f9550c0eb0b6a8f007 attempt=1 -[2026-08-13 16:39:35,112] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=500a26f22e1662f9550c0eb0b6a8f007 status=200 post_dur=0.435s -[2026-08-13 16:40:11,137] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=500a26f22e1662f9550c0eb0b6a8f007 total=36459.6ms bytes=96484 finished=True finish=stop stop=None out_tok=335 prompt_tok=13670 tps=9.2 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:40:11,140] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6655d6d29896f86bb52031124195b96b attempt=1 -[2026-08-13 16:40:11,599] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6655d6d29896f86bb52031124195b96b status=200 post_dur=0.459s -[2026-08-13 16:40:46,642] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6655d6d29896f86bb52031124195b96b total=35501.9ms bytes=18922 finished=True finish=tool_calls stop=None out_tok=271 prompt_tok=13245 tps=7.6 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:40:46,660] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23e518df272b2a3db9aee2cf2479da5b attempt=1 -[2026-08-13 16:40:47,313] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23e518df272b2a3db9aee2cf2479da5b status=200 post_dur=0.653s -[2026-08-13 16:46:11,205] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=23e518df272b2a3db9aee2cf2479da5b total=324544.7ms bytes=503455 finished=True finish=stop stop=None out_tok=1743 prompt_tok=124552 tps=5.4 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:46:11,228] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be9fcfc652f67e5bbae60f96b9ef78af attempt=1 -[2026-08-13 16:46:11,898] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be9fcfc652f67e5bbae60f96b9ef78af status=200 post_dur=0.670s -[2026-08-13 16:49:25,252] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] Time budget reached (46800s) — stopping batch with 4 in flight, 686/881 dispatched -[2026-08-13 16:49:25,252] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] END batch total=881 dispatched=686 completed=682 elapsed=46800.0s throughput=0.01 req/s -[2026-08-13 16:49:25,252] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] wall_time_s=46800.040 records=881 -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] Failure breakdown (of 682 attempted): {'ctx_overflow': 21, 'http_400': 13, 'request_validation': 6} -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] ctx_overflow ×21 — e.g. request_id=0095eee8517acdd4d3777bb0dad225d0: This model's maximum context length is 131072 tokens. However, you requested 185059 tokens in the messages, Please reduce the length of the messages. -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] http_400 ×13 — e.g. request_id=1e8a1d182746d47cd271f17406d129a5: At most 1 image(s) may be provided in one request. -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] request_validation ×6 — e.g. request_id=57832f49558fd182b94b8e85dacaec5a: 1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] 21 requests exceeded the target's context window (prompt alone, or prompt + max_tokens / the server's default completion budget). Not a service outage — pre-filter the dataset (convert_bodylog_dataset.py --clean --max-model-len ) or set max_generation_tokens. -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] 6 requests failed the server's request validation (malformed roles / content types the capture's gateway tolerated). convert --clean coerces the known shapes; see the example above for what the server objected to. -[2026-08-13 16:49:25,253] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] 199/881 requests never started (batch was canceled or budget ran out before they were dispatched) -[2026-08-13 16:49:25,255] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] PASSED. metrics={'total_requests': 881, 'attempted_requests': 682, 'not_started_requests': 199, 'successful_requests': 642, 'error_requests': 40, 'error_rate': 0.05865102639296188, 'unfinished_requests': 0, 'unfinished_rate': 0.0, 'uptime': 0.9413489736070382, 'http_200_count': 642, 'tool_requests_total': 548, 'tool_call_4xx_errors': 36, 'image_requests_total': 24, 'image_4xx_errors': 19, 'multi_system_requests': 34, 'multi_system_4xx_errors': 15, 'system_normalized_count': 34, 'error_class_counts': {'ctx_overflow': 21, 'http_400': 13, 'request_validation': 6}, 'ttft_p50_ms': 9299.582526087761, 'ttft_p90_ms': 56121.13758586347, 'ttft_p99_ms': 187644.995908402, 'ttft_mean_ms': 22857.75699448479, 'ttft_input_unknown_count': 0, 'ttft_lt_6k_p90_ms': 6190.393481403592, 'ttft_lt_6k_p50_ms': 4085.1966366171837, 'ttft_lt_6k_avg_ms': 7456.025787348312, 'ttft_lt_6k_count': 63, 'ttft_6k_16k_p90_ms': 12745.279929041862, 'ttft_6k_16k_p50_ms': 8333.302970975637, 'ttft_6k_16k_avg_ms': 8397.925453046795, 'ttft_6k_16k_count': 305, 'ttft_16k_32k_p90_ms': 37355.44242784381, 'ttft_16k_32k_p50_ms': 25844.000635668635, 'ttft_16k_32k_avg_ms': 22381.870580910174, 'ttft_16k_32k_count': 102, 'ttft_32k_64k_p90_ms': 71544.49126310647, 'ttft_32k_64k_p50_ms': 35154.12933379412, 'ttft_32k_64k_avg_ms': 37780.680700530145, 'ttft_32k_64k_count': 86, 'ttft_64k_128k_p90_ms': 179731.03193938732, 'ttft_64k_128k_p50_ms': 24592.828322201967, 'ttft_64k_128k_avg_ms': 71063.88096719288, 'ttft_64k_128k_count': 86, 'ttft_128k_256k_p90_ms': None, 'ttft_128k_256k_p50_ms': None, 'ttft_128k_256k_avg_ms': None, 'ttft_128k_256k_count': 0, 'ttft_ge_256k_p90_ms': None, 'ttft_ge_256k_p50_ms': None, 'ttft_ge_256k_avg_ms': None, 'ttft_ge_256k_count': 0, 'total_time_p50_ms': 33807.13538452983, 'total_time_p99_ms': 557955.6459960374, 'avg_prompt_tokens': 27062.7492211838, 'avg_completion_tokens': 510.2461059190031, 'output_tps_avg': 6.319760205433673, 'output_tps_mean': 6.319760205433673, 'output_tps_p10': 1.958467786818834, 'output_tps_p50': 6.129895664847464, 'output_tps_p90': 10.846020579884797, 'input_tps_mean': 1997.809605806273, 'input_tps_p10': 550.6529332764267, 'input_tps_p50': 1098.0396160472553, 'input_tps_p90': 5105.125383182228, 'total_input_tokens': 17374285, 'total_output_tokens': 327578, 'total_cached_tokens': 10076176, 'total_uncached_input_tokens': 7298109, 'cache_hit_rate': 0.5799476640333688, 'wall_time_s': 46800.03986830264, 'input_tpm': 22274.70538344668, 'output_tpm': 419.9714371036676, 'cached_tpm': 12918.163354161406, 'uncached_input_tpm': 9356.54202928527, 'tokens_after_finish_count': 0, 'repetitive_token_count': 0, 'generation_capped_count': 0, 'finish_reason_length_count': 7, 'finish_reason_stop_count': 226, 'finish_marker_counts': {'openai_finish_reason_tool_calls': 409, 'openai_finish_reason_length': 7, 'openai_finish_reason_stop': 226}, 'judge_sampled_count': None, 'judge_answered_count': None, 'judge_toolcall_count': None, 'judge_length_count': None, 'judge_disconnect_count': None, 'judge_error_count': None, 'judge_kept_count': None, 'judge_good_acc_rate': None, 'judge_poor_rate': None, 'judge_halluc_clear_rate': None, 'judge_halluc_suspected_count': None, 'judge_failures': None} -[2026-08-13 16:49:25,255] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Response capture written to /tmp/perfbench_submission_694_4hv5__9n/replay_tencent_104/replay_responses.jsonl -[2026-08-13 16:49:25,256] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [replay_tencent] uptime=0.9413489736070382 ttft_p99=187644.995908402 total_time_p99=557955.6459960374 -[2026-08-13 16:49:25,257] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module replay_tencent: card-normalized TPM (baseline=8, cards=8 assumed): input_tpm_card_norm=22275, output_tpm_card_norm=420, cached_tpm_card_norm=12918, total_tpm_card_norm=22695 -[2026-08-13 16:49:25,257] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module replay_tencent: dataset identity dataset_id=gpu-41-42-2026-06-29-1400-bystart.replay.jsonl, dataset_sha256=- -[2026-08-13 16:49:30,981] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module replay_tencent done — passed=False score=26028.0060 -[2026-08-13 16:49:34,142] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 starting module opencompass (bm_id=105 order=3) -[2026-08-13 16:49:47,197] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module opencompass: CONCURRENCY OVERRIDE max_workers=4 -> 1. -[2026-08-13 16:49:53,285] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass] received params: {'dataset_dir': '/app/dataset/opencompass/data', 'selected_benchmarks': ['aime2025', 'gpqa_diamond', 'simpleqa', 'longbench_v2', 'hle'], 'max_workers': 1, 'request_timeout': 3600.0, 'max_seconds': 57600.0, 'max_tokens': 131072, 'sample_cap_aime': 0, 'sample_cap_gpqa': 0, 'sample_cap_ifeval': 0, 'sample_cap_mmlu': 0, 'sample_cap_hle': 100, 'sample_cap_lcb': 0, 'sample_cap_simpleqa': 200, 'sample_cap_longbench': 0, 'avg_k_aime': 8, 'avg_k_gpqa': 1, 'avg_k_ifeval': 1, 'avg_k_mmlu': 1, 'avg_k_hle': 1, 'avg_k_lcb': 1, 'avg_k_simpleqa': 1, 'avg_k_longbench': 1, 'pass_k_aime': 1, 'pass_k_gpqa': 1, 'pass_k_ifeval': 1, 'pass_k_mmlu': 1, 'pass_k_hle': 1, 'pass_k_lcb': 1, 'pass_k_simpleqa': 1, 'pass_k_longbench': 1, 'sample_temperature': 1.0, 'sample_top_p': 0.95, 'force_temperature': True, 'stream': True, 'judge_api_url': 'http://172.21.112.11/phanrouter', 'judge_model': 'Kimi-K2.5', 'judge_api_key': '***', 'judge_max_tokens': 16384, 'hle_use_judge': True, 'hle_judge_max_tokens': 2048, 'longbench_max_input_tokens': 190000, 'longbench_max_output_tokens': 16384} -[2026-08-13 16:49:53,310] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] Starting academic evaluation - endpoint : api_url=http://172.28.22.18:43325 model=llm api_key=*** - data_dir : /app/dataset/opencompass/data - max_workers : 1 - request_timeout : 3600.0s - max_tokens : 131072 - sample_caps : {'aime2025': 0, 'gpqa_diamond': 0, 'ifeval': 0, 'mmlu_pro': 0, 'hle': 100, 'livecodebench_v6': 0, 'simpleqa': 200, 'longbench_v2': 0} - skip_flags : {'aime2025': False, 'gpqa_diamond': False, 'ifeval': True, 'mmlu_pro': True, 'hle': False, 'livecodebench_v6': True, 'simpleqa': False, 'longbench_v2': False} - avg_k : {'aime2025': 8, 'gpqa_diamond': 1, 'ifeval': 1, 'mmlu_pro': 1, 'hle': 1, 'livecodebench_v6': 1, 'simpleqa': 1, 'longbench_v2': 1} - pass_k : {'aime2025': 1, 'gpqa_diamond': 1, 'ifeval': 1, 'mmlu_pro': 1, 'hle': 1, 'livecodebench_v6': 1, 'simpleqa': 1, 'longbench_v2': 1} sample_temperature=1.00 sample_top_p=0.95 force_temperature=True - active runners : ['aime2025', 'gpqa_diamond', 'hle', 'simpleqa', 'longbench_v2'] - baseline_file : (none) max_regression=0.0200 -[2026-08-13 16:49:53,310] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] module time cap: 57600s -[2026-08-13 16:49:53,310] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 1/5: aime2025 (sample_cap=all, avg@8, pass@1, temp=1.00, top_p=0.95, max_tokens=131072, suite_elapsed=0s) -[2026-08-13 16:49:53,312] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: BEGIN items=30 n_samples=8 (avg@8/pass@1) temp=1.00 top_p=0.95 requests=240 workers=1 max_tokens=131072 timeout=3600.0s stream=True -[2026-08-13 16:49:53,638] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 2/240 reqs (0.8%) sample_acc=0.000 fails=2 elapsed=0s rate=6.15/s eta=39s -[2026-08-13 16:49:53,917] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 4/240 reqs (1.7%) sample_acc=0.000 fails=4 elapsed=1s rate=6.62/s eta=36s -[2026-08-13 16:49:54,188] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 6/240 reqs (2.5%) sample_acc=0.000 fails=6 elapsed=1s rate=6.86/s eta=34s -[2026-08-13 16:49:54,463] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 8/240 reqs (3.3%) sample_acc=0.000 fails=8 elapsed=1s rate=6.95/s eta=33s -[2026-08-13 16:49:54,731] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 10/240 reqs (4.2%) sample_acc=0.000 fails=10 elapsed=1s rate=7.05/s eta=33s -[2026-08-13 16:49:55,008] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 12/240 reqs (5.0%) sample_acc=0.000 fails=12 elapsed=2s rate=7.08/s eta=32s -[2026-08-13 16:49:55,277] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 14/240 reqs (5.8%) sample_acc=0.000 fails=14 elapsed=2s rate=7.13/s eta=32s -[2026-08-13 16:49:55,545] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 16/240 reqs (6.7%) sample_acc=0.000 fails=16 elapsed=2s rate=7.17/s eta=31s -[2026-08-13 16:49:55,822] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 18/240 reqs (7.5%) sample_acc=0.000 fails=18 elapsed=3s rate=7.17/s eta=31s -[2026-08-13 16:49:56,102] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 20/240 reqs (8.3%) sample_acc=0.000 fails=20 elapsed=3s rate=7.17/s eta=31s -[2026-08-13 16:49:56,370] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 22/240 reqs (9.2%) sample_acc=0.000 fails=22 elapsed=3s rate=7.20/s eta=30s -[2026-08-13 16:49:56,647] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 24/240 reqs (10.0%) sample_acc=0.000 fails=24 elapsed=3s rate=7.20/s eta=30s -[2026-08-13 16:49:56,914] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 26/240 reqs (10.8%) sample_acc=0.000 fails=26 elapsed=4s rate=7.22/s eta=30s -[2026-08-13 16:49:57,190] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 28/240 reqs (11.7%) sample_acc=0.000 fails=28 elapsed=4s rate=7.22/s eta=29s -[2026-08-13 16:49:57,461] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 30/240 reqs (12.5%) sample_acc=0.000 fails=30 elapsed=4s rate=7.23/s eta=29s -[2026-08-13 16:49:57,729] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 32/240 reqs (13.3%) sample_acc=0.000 fails=32 elapsed=4s rate=7.25/s eta=29s -[2026-08-13 16:49:58,005] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 34/240 reqs (14.2%) sample_acc=0.000 fails=34 elapsed=5s rate=7.25/s eta=28s -[2026-08-13 16:49:58,272] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 36/240 reqs (15.0%) sample_acc=0.000 fails=36 elapsed=5s rate=7.26/s eta=28s -[2026-08-13 16:49:58,548] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 38/240 reqs (15.8%) sample_acc=0.000 fails=38 elapsed=5s rate=7.26/s eta=28s -[2026-08-13 16:49:58,826] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 40/240 reqs (16.7%) sample_acc=0.000 fails=40 elapsed=6s rate=7.26/s eta=28s -[2026-08-13 16:49:59,094] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 42/240 reqs (17.5%) sample_acc=0.000 fails=42 elapsed=6s rate=7.27/s eta=27s -[2026-08-13 16:49:59,371] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 44/240 reqs (18.3%) sample_acc=0.000 fails=44 elapsed=6s rate=7.26/s eta=27s -[2026-08-13 16:49:59,647] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 46/240 reqs (19.2%) sample_acc=0.000 fails=46 elapsed=6s rate=7.26/s eta=27s -[2026-08-13 16:49:59,916] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 48/240 reqs (20.0%) sample_acc=0.000 fails=48 elapsed=7s rate=7.27/s eta=26s -[2026-08-13 16:50:00,185] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 50/240 reqs (20.8%) sample_acc=0.000 fails=50 elapsed=7s rate=7.28/s eta=26s -[2026-08-13 16:50:00,453] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 52/240 reqs (21.7%) sample_acc=0.000 fails=52 elapsed=7s rate=7.28/s eta=26s -[2026-08-13 16:50:00,729] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 54/240 reqs (22.5%) sample_acc=0.000 fails=54 elapsed=7s rate=7.28/s eta=26s -[2026-08-13 16:50:01,007] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 56/240 reqs (23.3%) sample_acc=0.000 fails=56 elapsed=8s rate=7.28/s eta=25s -[2026-08-13 16:50:01,279] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 58/240 reqs (24.2%) sample_acc=0.000 fails=58 elapsed=8s rate=7.28/s eta=25s -[2026-08-13 16:50:01,557] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 60/240 reqs (25.0%) sample_acc=0.000 fails=60 elapsed=8s rate=7.28/s eta=25s -[2026-08-13 16:50:01,824] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 62/240 reqs (25.8%) sample_acc=0.000 fails=62 elapsed=9s rate=7.28/s eta=24s -[2026-08-13 16:50:02,101] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 64/240 reqs (26.7%) sample_acc=0.000 fails=64 elapsed=9s rate=7.28/s eta=24s -[2026-08-13 16:50:02,388] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 66/240 reqs (27.5%) sample_acc=0.000 fails=66 elapsed=9s rate=7.27/s eta=24s -[2026-08-13 16:50:02,656] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 68/240 reqs (28.3%) sample_acc=0.000 fails=68 elapsed=9s rate=7.28/s eta=24s -[2026-08-13 16:50:02,923] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 70/240 reqs (29.2%) sample_acc=0.000 fails=70 elapsed=10s rate=7.28/s eta=23s -[2026-08-13 16:50:03,199] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 72/240 reqs (30.0%) sample_acc=0.000 fails=72 elapsed=10s rate=7.28/s eta=23s -[2026-08-13 16:50:03,468] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 74/240 reqs (30.8%) sample_acc=0.000 fails=74 elapsed=10s rate=7.29/s eta=23s -[2026-08-13 16:50:03,746] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 76/240 reqs (31.7%) sample_acc=0.000 fails=76 elapsed=10s rate=7.28/s eta=23s -[2026-08-13 16:50:04,025] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 78/240 reqs (32.5%) sample_acc=0.000 fails=78 elapsed=11s rate=7.28/s eta=22s -[2026-08-13 16:50:04,293] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 80/240 reqs (33.3%) sample_acc=0.000 fails=80 elapsed=11s rate=7.29/s eta=22s -[2026-08-13 16:50:04,573] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 82/240 reqs (34.2%) sample_acc=0.000 fails=82 elapsed=11s rate=7.28/s eta=22s -[2026-08-13 16:50:04,852] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 84/240 reqs (35.0%) sample_acc=0.000 fails=84 elapsed=12s rate=7.28/s eta=21s -[2026-08-13 16:50:05,123] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 86/240 reqs (35.8%) sample_acc=0.000 fails=86 elapsed=12s rate=7.28/s eta=21s -[2026-08-13 16:50:05,392] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 88/240 reqs (36.7%) sample_acc=0.000 fails=88 elapsed=12s rate=7.28/s eta=21s -[2026-08-13 16:50:05,670] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 90/240 reqs (37.5%) sample_acc=0.000 fails=90 elapsed=12s rate=7.28/s eta=21s -[2026-08-13 16:50:05,939] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 92/240 reqs (38.3%) sample_acc=0.000 fails=92 elapsed=13s rate=7.29/s eta=20s -[2026-08-13 16:50:06,215] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 94/240 reqs (39.2%) sample_acc=0.000 fails=94 elapsed=13s rate=7.29/s eta=20s -[2026-08-13 16:50:06,493] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 96/240 reqs (40.0%) sample_acc=0.000 fails=96 elapsed=13s rate=7.28/s eta=20s -[2026-08-13 16:50:06,761] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 98/240 reqs (40.8%) sample_acc=0.000 fails=98 elapsed=13s rate=7.29/s eta=19s -[2026-08-13 16:50:07,039] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 100/240 reqs (41.7%) sample_acc=0.000 fails=100 elapsed=14s rate=7.29/s eta=19s -[2026-08-13 16:50:07,318] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 102/240 reqs (42.5%) sample_acc=0.000 fails=102 elapsed=14s rate=7.28/s eta=19s -[2026-08-13 16:50:07,587] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 104/240 reqs (43.3%) sample_acc=0.000 fails=104 elapsed=14s rate=7.29/s eta=19s -[2026-08-13 16:50:07,865] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 106/240 reqs (44.2%) sample_acc=0.000 fails=106 elapsed=15s rate=7.28/s eta=18s -[2026-08-13 16:50:08,143] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 108/240 reqs (45.0%) sample_acc=0.000 fails=108 elapsed=15s rate=7.28/s eta=18s -[2026-08-13 16:50:08,410] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 110/240 reqs (45.8%) sample_acc=0.000 fails=110 elapsed=15s rate=7.29/s eta=18s -[2026-08-13 16:50:08,688] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 112/240 reqs (46.7%) sample_acc=0.000 fails=112 elapsed=15s rate=7.28/s eta=18s -[2026-08-13 16:50:08,956] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 114/240 reqs (47.5%) sample_acc=0.000 fails=114 elapsed=16s rate=7.29/s eta=17s -[2026-08-13 16:50:09,224] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 116/240 reqs (48.3%) sample_acc=0.000 fails=116 elapsed=16s rate=7.29/s eta=17s -[2026-08-13 16:50:09,503] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 118/240 reqs (49.2%) sample_acc=0.000 fails=118 elapsed=16s rate=7.29/s eta=17s -[2026-08-13 16:50:09,771] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 120/240 reqs (50.0%) sample_acc=0.000 fails=120 elapsed=16s rate=7.29/s eta=16s -[2026-08-13 16:50:10,039] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 122/240 reqs (50.8%) sample_acc=0.000 fails=122 elapsed=17s rate=7.29/s eta=16s -[2026-08-13 16:50:10,306] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 124/240 reqs (51.7%) sample_acc=0.000 fails=124 elapsed=17s rate=7.30/s eta=16s -[2026-08-13 16:50:10,583] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 126/240 reqs (52.5%) sample_acc=0.000 fails=126 elapsed=17s rate=7.30/s eta=16s -[2026-08-13 16:50:10,859] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 128/240 reqs (53.3%) sample_acc=0.000 fails=128 elapsed=18s rate=7.30/s eta=15s -[2026-08-13 16:50:11,126] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 130/240 reqs (54.2%) sample_acc=0.000 fails=130 elapsed=18s rate=7.30/s eta=15s -[2026-08-13 16:50:11,401] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 132/240 reqs (55.0%) sample_acc=0.000 fails=132 elapsed=18s rate=7.30/s eta=15s -[2026-08-13 16:50:11,671] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 134/240 reqs (55.8%) sample_acc=0.000 fails=134 elapsed=18s rate=7.30/s eta=15s -[2026-08-13 16:50:11,951] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 136/240 reqs (56.7%) sample_acc=0.000 fails=136 elapsed=19s rate=7.30/s eta=14s -[2026-08-13 16:50:12,228] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 138/240 reqs (57.5%) sample_acc=0.000 fails=138 elapsed=19s rate=7.30/s eta=14s -[2026-08-13 16:50:12,498] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 140/240 reqs (58.3%) sample_acc=0.000 fails=140 elapsed=19s rate=7.30/s eta=14s -[2026-08-13 16:50:12,776] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 142/240 reqs (59.2%) sample_acc=0.000 fails=142 elapsed=19s rate=7.30/s eta=13s -[2026-08-13 16:50:13,044] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 144/240 reqs (60.0%) sample_acc=0.000 fails=144 elapsed=20s rate=7.30/s eta=13s -[2026-08-13 16:50:13,324] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 146/240 reqs (60.8%) sample_acc=0.000 fails=146 elapsed=20s rate=7.30/s eta=13s -[2026-08-13 16:50:13,593] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 148/240 reqs (61.7%) sample_acc=0.000 fails=148 elapsed=20s rate=7.30/s eta=13s -[2026-08-13 16:50:13,869] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 150/240 reqs (62.5%) sample_acc=0.000 fails=150 elapsed=21s rate=7.30/s eta=12s -[2026-08-13 16:50:14,143] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 152/240 reqs (63.3%) sample_acc=0.000 fails=152 elapsed=21s rate=7.30/s eta=12s -[2026-08-13 16:50:14,419] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 154/240 reqs (64.2%) sample_acc=0.000 fails=154 elapsed=21s rate=7.30/s eta=12s -[2026-08-13 16:50:14,698] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 156/240 reqs (65.0%) sample_acc=0.000 fails=156 elapsed=21s rate=7.29/s eta=12s -[2026-08-13 16:50:14,965] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 158/240 reqs (65.8%) sample_acc=0.000 fails=158 elapsed=22s rate=7.30/s eta=11s -[2026-08-13 16:50:15,236] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 160/240 reqs (66.7%) sample_acc=0.000 fails=160 elapsed=22s rate=7.30/s eta=11s -[2026-08-13 16:50:15,513] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 162/240 reqs (67.5%) sample_acc=0.000 fails=162 elapsed=22s rate=7.30/s eta=11s -[2026-08-13 16:50:15,784] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 164/240 reqs (68.3%) sample_acc=0.000 fails=164 elapsed=22s rate=7.30/s eta=10s -[2026-08-13 16:50:16,061] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 166/240 reqs (69.2%) sample_acc=0.000 fails=166 elapsed=23s rate=7.30/s eta=10s -[2026-08-13 16:50:16,338] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 168/240 reqs (70.0%) sample_acc=0.000 fails=168 elapsed=23s rate=7.30/s eta=10s -[2026-08-13 16:50:16,606] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 170/240 reqs (70.8%) sample_acc=0.000 fails=170 elapsed=23s rate=7.30/s eta=10s -[2026-08-13 16:50:16,883] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 172/240 reqs (71.7%) sample_acc=0.000 fails=172 elapsed=24s rate=7.30/s eta=9s -[2026-08-13 16:50:17,151] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 174/240 reqs (72.5%) sample_acc=0.000 fails=174 elapsed=24s rate=7.30/s eta=9s -[2026-08-13 16:50:17,428] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 176/240 reqs (73.3%) sample_acc=0.000 fails=176 elapsed=24s rate=7.30/s eta=9s -[2026-08-13 16:50:17,699] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 178/240 reqs (74.2%) sample_acc=0.000 fails=178 elapsed=24s rate=7.30/s eta=8s -[2026-08-13 16:50:17,977] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 180/240 reqs (75.0%) sample_acc=0.000 fails=180 elapsed=25s rate=7.30/s eta=8s -[2026-08-13 16:50:18,256] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 182/240 reqs (75.8%) sample_acc=0.000 fails=182 elapsed=25s rate=7.30/s eta=8s -[2026-08-13 16:50:18,524] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 184/240 reqs (76.7%) sample_acc=0.000 fails=184 elapsed=25s rate=7.30/s eta=8s -[2026-08-13 16:50:18,803] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 186/240 reqs (77.5%) sample_acc=0.000 fails=186 elapsed=25s rate=7.30/s eta=7s -[2026-08-13 16:50:19,076] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 188/240 reqs (78.3%) sample_acc=0.000 fails=188 elapsed=26s rate=7.30/s eta=7s -[2026-08-13 16:50:19,353] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 190/240 reqs (79.2%) sample_acc=0.000 fails=190 elapsed=26s rate=7.30/s eta=7s -[2026-08-13 16:50:19,630] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 192/240 reqs (80.0%) sample_acc=0.000 fails=192 elapsed=26s rate=7.30/s eta=7s -[2026-08-13 16:50:19,900] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 194/240 reqs (80.8%) sample_acc=0.000 fails=194 elapsed=27s rate=7.30/s eta=6s -[2026-08-13 16:50:20,168] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 196/240 reqs (81.7%) sample_acc=0.000 fails=196 elapsed=27s rate=7.30/s eta=6s -[2026-08-13 16:50:20,435] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 198/240 reqs (82.5%) sample_acc=0.000 fails=198 elapsed=27s rate=7.30/s eta=6s -[2026-08-13 16:50:20,711] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 200/240 reqs (83.3%) sample_acc=0.000 fails=200 elapsed=27s rate=7.30/s eta=5s -[2026-08-13 16:50:20,988] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 202/240 reqs (84.2%) sample_acc=0.000 fails=202 elapsed=28s rate=7.30/s eta=5s -[2026-08-13 16:50:21,256] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 204/240 reqs (85.0%) sample_acc=0.000 fails=204 elapsed=28s rate=7.30/s eta=5s -[2026-08-13 16:50:21,534] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 206/240 reqs (85.8%) sample_acc=0.000 fails=206 elapsed=28s rate=7.30/s eta=5s -[2026-08-13 16:50:21,812] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 208/240 reqs (86.7%) sample_acc=0.000 fails=208 elapsed=28s rate=7.30/s eta=4s -[2026-08-13 16:50:22,080] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 210/240 reqs (87.5%) sample_acc=0.000 fails=210 elapsed=29s rate=7.30/s eta=4s -[2026-08-13 16:50:22,358] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 212/240 reqs (88.3%) sample_acc=0.000 fails=212 elapsed=29s rate=7.30/s eta=4s -[2026-08-13 16:50:22,635] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 214/240 reqs (89.2%) sample_acc=0.000 fails=214 elapsed=29s rate=7.30/s eta=4s -[2026-08-13 16:50:22,904] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 216/240 reqs (90.0%) sample_acc=0.000 fails=216 elapsed=30s rate=7.30/s eta=3s -[2026-08-13 16:50:23,172] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 218/240 reqs (90.8%) sample_acc=0.000 fails=218 elapsed=30s rate=7.30/s eta=3s -[2026-08-13 16:50:23,448] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 220/240 reqs (91.7%) sample_acc=0.000 fails=220 elapsed=30s rate=7.30/s eta=3s -[2026-08-13 16:50:23,717] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 222/240 reqs (92.5%) sample_acc=0.000 fails=222 elapsed=30s rate=7.30/s eta=2s -[2026-08-13 16:50:23,994] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 224/240 reqs (93.3%) sample_acc=0.000 fails=224 elapsed=31s rate=7.30/s eta=2s -[2026-08-13 16:50:24,262] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 226/240 reqs (94.2%) sample_acc=0.000 fails=226 elapsed=31s rate=7.30/s eta=2s -[2026-08-13 16:50:24,540] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 228/240 reqs (95.0%) sample_acc=0.000 fails=228 elapsed=31s rate=7.30/s eta=2s -[2026-08-13 16:50:24,810] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 230/240 reqs (95.8%) sample_acc=0.000 fails=230 elapsed=31s rate=7.30/s eta=1s -[2026-08-13 16:50:25,079] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 232/240 reqs (96.7%) sample_acc=0.000 fails=232 elapsed=32s rate=7.30/s eta=1s -[2026-08-13 16:50:25,355] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 234/240 reqs (97.5%) sample_acc=0.000 fails=234 elapsed=32s rate=7.30/s eta=1s -[2026-08-13 16:50:25,622] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 236/240 reqs (98.3%) sample_acc=0.000 fails=236 elapsed=32s rate=7.30/s eta=1s -[2026-08-13 16:50:25,891] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 238/240 reqs (99.2%) sample_acc=0.000 fails=238 elapsed=33s rate=7.31/s eta=0s -[2026-08-13 16:50:26,162] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 240/240 reqs (100.0%) sample_acc=0.000 fails=240 elapsed=33s rate=7.31/s eta=0s -[2026-08-13 16:50:26,162] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [academic] aime2025: 240 requests failed during inference (sample: ['HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131138 tokens (66 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131138 tokens (66 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131138 tokens (66 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}']) -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: avg@8=0.0000 pass@1=0.0000 (items=30, samples=240, correct_samples=0) in 32.9s -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025 sample item=0 correct=False response='' -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025 sample item=0 correct=False response='' -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025 sample item=0 correct=False response='' -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] <<< benchmark 1/5: aime2025 done score=0.0000 took=33s -[2026-08-13 16:50:26,163] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 2/5: gpqa_diamond (sample_cap=all, avg@1, pass@1, temp=1.00, top_p=0.95, max_tokens=131072, suite_elapsed=33s) -[2026-08-13 16:50:26,186] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: BEGIN items=198 n_samples=1 (avg@1/pass@1) temp=1.00 top_p=0.95 requests=198 workers=1 max_tokens=131072 timeout=3600.0s stream=True -[2026-08-13 16:50:26,324] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 1/198 reqs (0.5%) sample_acc=0.000 fails=1 elapsed=0s rate=7.30/s eta=27s -[2026-08-13 16:50:26,458] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 2/198 reqs (1.0%) sample_acc=0.000 fails=2 elapsed=0s rate=7.36/s eta=27s -[2026-08-13 16:50:26,592] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 3/198 reqs (1.5%) sample_acc=0.000 fails=3 elapsed=0s rate=7.40/s eta=26s -[2026-08-13 16:50:26,742] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 4/198 reqs (2.0%) sample_acc=0.000 fails=4 elapsed=1s rate=7.20/s eta=27s -[2026-08-13 16:50:26,877] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 5/198 reqs (2.5%) sample_acc=0.000 fails=5 elapsed=1s rate=7.24/s eta=27s -[2026-08-13 16:50:27,012] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 6/198 reqs (3.0%) sample_acc=0.000 fails=6 elapsed=1s rate=7.27/s eta=26s -[2026-08-13 16:50:27,155] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 7/198 reqs (3.5%) sample_acc=0.000 fails=7 elapsed=1s rate=7.23/s eta=26s -[2026-08-13 16:50:27,290] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 8/198 reqs (4.0%) sample_acc=0.000 fails=8 elapsed=1s rate=7.25/s eta=26s -[2026-08-13 16:50:27,424] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 9/198 reqs (4.5%) sample_acc=0.000 fails=9 elapsed=1s rate=7.27/s eta=26s -[2026-08-13 16:50:27,567] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 10/198 reqs (5.1%) sample_acc=0.000 fails=10 elapsed=1s rate=7.24/s eta=26s -[2026-08-13 16:50:27,704] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 11/198 reqs (5.6%) sample_acc=0.000 fails=11 elapsed=2s rate=7.25/s eta=26s -[2026-08-13 16:50:27,847] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 12/198 reqs (6.1%) sample_acc=0.000 fails=12 elapsed=2s rate=7.23/s eta=26s -[2026-08-13 16:50:27,981] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 13/198 reqs (6.6%) sample_acc=0.000 fails=13 elapsed=2s rate=7.24/s eta=26s -[2026-08-13 16:50:28,116] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 14/198 reqs (7.1%) sample_acc=0.000 fails=14 elapsed=2s rate=7.26/s eta=25s -[2026-08-13 16:50:28,260] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 15/198 reqs (7.6%) sample_acc=0.000 fails=15 elapsed=2s rate=7.23/s eta=25s -[2026-08-13 16:50:28,395] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 16/198 reqs (8.1%) sample_acc=0.000 fails=16 elapsed=2s rate=7.25/s eta=25s -[2026-08-13 16:50:28,530] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 17/198 reqs (8.6%) sample_acc=0.000 fails=17 elapsed=2s rate=7.25/s eta=25s -[2026-08-13 16:50:28,673] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 18/198 reqs (9.1%) sample_acc=0.000 fails=18 elapsed=2s rate=7.24/s eta=25s -[2026-08-13 16:50:28,809] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 19/198 reqs (9.6%) sample_acc=0.000 fails=19 elapsed=3s rate=7.25/s eta=25s -[2026-08-13 16:50:28,944] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 20/198 reqs (10.1%) sample_acc=0.000 fails=20 elapsed=3s rate=7.25/s eta=25s -[2026-08-13 16:50:29,079] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 21/198 reqs (10.6%) sample_acc=0.000 fails=21 elapsed=3s rate=7.26/s eta=24s -[2026-08-13 16:50:29,213] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 22/198 reqs (11.1%) sample_acc=0.000 fails=22 elapsed=3s rate=7.27/s eta=24s -[2026-08-13 16:50:29,348] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 23/198 reqs (11.6%) sample_acc=0.000 fails=23 elapsed=3s rate=7.28/s eta=24s -[2026-08-13 16:50:29,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 24/198 reqs (12.1%) sample_acc=0.000 fails=24 elapsed=3s rate=7.28/s eta=24s -[2026-08-13 16:50:29,625] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 25/198 reqs (12.6%) sample_acc=0.000 fails=25 elapsed=3s rate=7.27/s eta=24s -[2026-08-13 16:50:29,760] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 26/198 reqs (13.1%) sample_acc=0.000 fails=26 elapsed=4s rate=7.28/s eta=24s -[2026-08-13 16:50:29,895] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 27/198 reqs (13.6%) sample_acc=0.000 fails=27 elapsed=4s rate=7.28/s eta=23s -[2026-08-13 16:50:30,039] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 28/198 reqs (14.1%) sample_acc=0.000 fails=28 elapsed=4s rate=7.27/s eta=23s -[2026-08-13 16:50:30,174] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 29/198 reqs (14.6%) sample_acc=0.000 fails=29 elapsed=4s rate=7.27/s eta=23s -[2026-08-13 16:50:30,310] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 30/198 reqs (15.2%) sample_acc=0.000 fails=30 elapsed=4s rate=7.28/s eta=23s -[2026-08-13 16:50:30,443] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 31/198 reqs (15.7%) sample_acc=0.000 fails=31 elapsed=4s rate=7.28/s eta=23s -[2026-08-13 16:50:30,586] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 32/198 reqs (16.2%) sample_acc=0.000 fails=32 elapsed=4s rate=7.27/s eta=23s -[2026-08-13 16:50:30,721] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 33/198 reqs (16.7%) sample_acc=0.000 fails=33 elapsed=5s rate=7.28/s eta=23s -[2026-08-13 16:50:30,855] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 34/198 reqs (17.2%) sample_acc=0.000 fails=34 elapsed=5s rate=7.28/s eta=23s -[2026-08-13 16:50:30,999] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 35/198 reqs (17.7%) sample_acc=0.000 fails=35 elapsed=5s rate=7.27/s eta=22s -[2026-08-13 16:50:31,132] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 36/198 reqs (18.2%) sample_acc=0.000 fails=36 elapsed=5s rate=7.28/s eta=22s -[2026-08-13 16:50:31,266] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 37/198 reqs (18.7%) sample_acc=0.000 fails=37 elapsed=5s rate=7.28/s eta=22s -[2026-08-13 16:50:31,403] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 38/198 reqs (19.2%) sample_acc=0.000 fails=38 elapsed=5s rate=7.28/s eta=22s -[2026-08-13 16:50:31,546] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 39/198 reqs (19.7%) sample_acc=0.000 fails=39 elapsed=5s rate=7.28/s eta=22s -[2026-08-13 16:50:31,679] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 40/198 reqs (20.2%) sample_acc=0.000 fails=40 elapsed=5s rate=7.28/s eta=22s -[2026-08-13 16:50:31,813] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 41/198 reqs (20.7%) sample_acc=0.000 fails=41 elapsed=6s rate=7.29/s eta=22s -[2026-08-13 16:50:31,956] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 42/198 reqs (21.2%) sample_acc=0.000 fails=42 elapsed=6s rate=7.28/s eta=21s -[2026-08-13 16:50:32,092] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 43/198 reqs (21.7%) sample_acc=0.000 fails=43 elapsed=6s rate=7.28/s eta=21s -[2026-08-13 16:50:32,226] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 44/198 reqs (22.2%) sample_acc=0.000 fails=44 elapsed=6s rate=7.29/s eta=21s -[2026-08-13 16:50:32,369] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 45/198 reqs (22.7%) sample_acc=0.000 fails=45 elapsed=6s rate=7.28/s eta=21s -[2026-08-13 16:50:32,503] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 46/198 reqs (23.2%) sample_acc=0.000 fails=46 elapsed=6s rate=7.28/s eta=21s -[2026-08-13 16:50:32,638] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 47/198 reqs (23.7%) sample_acc=0.000 fails=47 elapsed=6s rate=7.29/s eta=21s -[2026-08-13 16:50:32,780] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 48/198 reqs (24.2%) sample_acc=0.000 fails=48 elapsed=7s rate=7.28/s eta=21s -[2026-08-13 16:50:32,915] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 49/198 reqs (24.7%) sample_acc=0.000 fails=49 elapsed=7s rate=7.28/s eta=20s -[2026-08-13 16:50:33,049] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 50/198 reqs (25.3%) sample_acc=0.000 fails=50 elapsed=7s rate=7.29/s eta=20s -[2026-08-13 16:50:33,192] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 51/198 reqs (25.8%) sample_acc=0.000 fails=51 elapsed=7s rate=7.28/s eta=20s -[2026-08-13 16:50:33,326] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 52/198 reqs (26.3%) sample_acc=0.000 fails=52 elapsed=7s rate=7.28/s eta=20s -[2026-08-13 16:50:33,460] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 53/198 reqs (26.8%) sample_acc=0.000 fails=53 elapsed=7s rate=7.29/s eta=20s -[2026-08-13 16:50:33,603] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 54/198 reqs (27.3%) sample_acc=0.000 fails=54 elapsed=7s rate=7.28/s eta=20s -[2026-08-13 16:50:33,738] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 55/198 reqs (27.8%) sample_acc=0.000 fails=55 elapsed=8s rate=7.28/s eta=20s -[2026-08-13 16:50:33,873] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 56/198 reqs (28.3%) sample_acc=0.000 fails=56 elapsed=8s rate=7.29/s eta=19s -[2026-08-13 16:50:34,007] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 57/198 reqs (28.8%) sample_acc=0.000 fails=57 elapsed=8s rate=7.29/s eta=19s -[2026-08-13 16:50:34,142] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 58/198 reqs (29.3%) sample_acc=0.000 fails=58 elapsed=8s rate=7.29/s eta=19s -[2026-08-13 16:50:34,276] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 59/198 reqs (29.8%) sample_acc=0.000 fails=59 elapsed=8s rate=7.29/s eta=19s -[2026-08-13 16:50:34,411] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 60/198 reqs (30.3%) sample_acc=0.000 fails=60 elapsed=8s rate=7.30/s eta=19s -[2026-08-13 16:50:34,554] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 61/198 reqs (30.8%) sample_acc=0.000 fails=61 elapsed=8s rate=7.29/s eta=19s -[2026-08-13 16:50:34,690] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 62/198 reqs (31.3%) sample_acc=0.000 fails=62 elapsed=9s rate=7.29/s eta=19s -[2026-08-13 16:50:34,823] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 63/198 reqs (31.8%) sample_acc=0.000 fails=63 elapsed=9s rate=7.29/s eta=19s -[2026-08-13 16:50:34,965] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 64/198 reqs (32.3%) sample_acc=0.000 fails=64 elapsed=9s rate=7.29/s eta=18s -[2026-08-13 16:50:35,099] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 65/198 reqs (32.8%) sample_acc=0.000 fails=65 elapsed=9s rate=7.29/s eta=18s -[2026-08-13 16:50:35,233] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 66/198 reqs (33.3%) sample_acc=0.000 fails=66 elapsed=9s rate=7.30/s eta=18s -[2026-08-13 16:50:35,377] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 67/198 reqs (33.8%) sample_acc=0.000 fails=67 elapsed=9s rate=7.29/s eta=18s -[2026-08-13 16:50:35,512] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 68/198 reqs (34.3%) sample_acc=0.000 fails=68 elapsed=9s rate=7.29/s eta=18s -[2026-08-13 16:50:35,656] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 69/198 reqs (34.8%) sample_acc=0.000 fails=69 elapsed=9s rate=7.29/s eta=18s -[2026-08-13 16:50:35,790] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 70/198 reqs (35.4%) sample_acc=0.000 fails=70 elapsed=10s rate=7.29/s eta=18s -[2026-08-13 16:50:35,925] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 71/198 reqs (35.9%) sample_acc=0.000 fails=71 elapsed=10s rate=7.29/s eta=17s -[2026-08-13 16:50:36,067] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 72/198 reqs (36.4%) sample_acc=0.000 fails=72 elapsed=10s rate=7.29/s eta=17s -[2026-08-13 16:50:36,202] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 73/198 reqs (36.9%) sample_acc=0.000 fails=73 elapsed=10s rate=7.29/s eta=17s -[2026-08-13 16:50:36,337] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 74/198 reqs (37.4%) sample_acc=0.000 fails=74 elapsed=10s rate=7.29/s eta=17s -[2026-08-13 16:50:36,482] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 75/198 reqs (37.9%) sample_acc=0.000 fails=75 elapsed=10s rate=7.28/s eta=17s -[2026-08-13 16:50:36,617] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 76/198 reqs (38.4%) sample_acc=0.000 fails=76 elapsed=10s rate=7.29/s eta=17s -[2026-08-13 16:50:36,762] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 77/198 reqs (38.9%) sample_acc=0.000 fails=77 elapsed=11s rate=7.28/s eta=17s -[2026-08-13 16:50:36,897] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 78/198 reqs (39.4%) sample_acc=0.000 fails=78 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,032] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 79/198 reqs (39.9%) sample_acc=0.000 fails=79 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,176] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 80/198 reqs (40.4%) sample_acc=0.000 fails=80 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,310] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 81/198 reqs (40.9%) sample_acc=0.000 fails=81 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,454] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 82/198 reqs (41.4%) sample_acc=0.000 fails=82 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,588] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 83/198 reqs (41.9%) sample_acc=0.000 fails=83 elapsed=11s rate=7.28/s eta=16s -[2026-08-13 16:50:37,723] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 84/198 reqs (42.4%) sample_acc=0.000 fails=84 elapsed=12s rate=7.28/s eta=16s -[2026-08-13 16:50:37,872] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 85/198 reqs (42.9%) sample_acc=0.000 fails=85 elapsed=12s rate=7.27/s eta=16s -[2026-08-13 16:50:38,007] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 86/198 reqs (43.4%) sample_acc=0.000 fails=86 elapsed=12s rate=7.28/s eta=15s -[2026-08-13 16:50:38,143] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 87/198 reqs (43.9%) sample_acc=0.000 fails=87 elapsed=12s rate=7.28/s eta=15s -[2026-08-13 16:50:38,279] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 88/198 reqs (44.4%) sample_acc=0.000 fails=88 elapsed=12s rate=7.28/s eta=15s -[2026-08-13 16:50:38,415] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 89/198 reqs (44.9%) sample_acc=0.000 fails=89 elapsed=12s rate=7.28/s eta=15s -[2026-08-13 16:50:38,558] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 90/198 reqs (45.5%) sample_acc=0.000 fails=90 elapsed=12s rate=7.27/s eta=15s -[2026-08-13 16:50:38,693] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 91/198 reqs (46.0%) sample_acc=0.000 fails=91 elapsed=13s rate=7.28/s eta=15s -[2026-08-13 16:50:38,827] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 92/198 reqs (46.5%) sample_acc=0.000 fails=92 elapsed=13s rate=7.28/s eta=15s -[2026-08-13 16:50:38,970] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 93/198 reqs (47.0%) sample_acc=0.000 fails=93 elapsed=13s rate=7.27/s eta=14s -[2026-08-13 16:50:39,105] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 94/198 reqs (47.5%) sample_acc=0.000 fails=94 elapsed=13s rate=7.28/s eta=14s -[2026-08-13 16:50:39,239] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 95/198 reqs (48.0%) sample_acc=0.000 fails=95 elapsed=13s rate=7.28/s eta=14s -[2026-08-13 16:50:39,382] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 96/198 reqs (48.5%) sample_acc=0.000 fails=96 elapsed=13s rate=7.28/s eta=14s -[2026-08-13 16:50:39,518] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 97/198 reqs (49.0%) sample_acc=0.000 fails=97 elapsed=13s rate=7.28/s eta=14s -[2026-08-13 16:50:39,662] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 98/198 reqs (49.5%) sample_acc=0.000 fails=98 elapsed=13s rate=7.27/s eta=14s -[2026-08-13 16:50:39,798] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 99/198 reqs (50.0%) sample_acc=0.000 fails=99 elapsed=14s rate=7.27/s eta=14s -[2026-08-13 16:50:39,932] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 100/198 reqs (50.5%) sample_acc=0.000 fails=100 elapsed=14s rate=7.28/s eta=13s -[2026-08-13 16:50:40,074] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 101/198 reqs (51.0%) sample_acc=0.000 fails=101 elapsed=14s rate=7.27/s eta=13s -[2026-08-13 16:50:40,209] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 102/198 reqs (51.5%) sample_acc=0.000 fails=102 elapsed=14s rate=7.27/s eta=13s -[2026-08-13 16:50:40,343] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 103/198 reqs (52.0%) sample_acc=0.000 fails=103 elapsed=14s rate=7.28/s eta=13s -[2026-08-13 16:50:40,485] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 104/198 reqs (52.5%) sample_acc=0.000 fails=104 elapsed=14s rate=7.27/s eta=13s -[2026-08-13 16:50:40,620] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 105/198 reqs (53.0%) sample_acc=0.000 fails=105 elapsed=14s rate=7.27/s eta=13s -[2026-08-13 16:50:40,755] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 106/198 reqs (53.5%) sample_acc=0.000 fails=106 elapsed=15s rate=7.28/s eta=13s -[2026-08-13 16:50:40,901] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 107/198 reqs (54.0%) sample_acc=0.000 fails=107 elapsed=15s rate=7.27/s eta=13s -[2026-08-13 16:50:41,041] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 108/198 reqs (54.5%) sample_acc=0.000 fails=108 elapsed=15s rate=7.27/s eta=12s -[2026-08-13 16:50:41,176] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 109/198 reqs (55.1%) sample_acc=0.000 fails=109 elapsed=15s rate=7.27/s eta=12s -[2026-08-13 16:50:41,321] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 110/198 reqs (55.6%) sample_acc=0.000 fails=110 elapsed=15s rate=7.27/s eta=12s -[2026-08-13 16:50:41,456] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 111/198 reqs (56.1%) sample_acc=0.000 fails=111 elapsed=15s rate=7.27/s eta=12s -[2026-08-13 16:50:41,601] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 112/198 reqs (56.6%) sample_acc=0.000 fails=112 elapsed=15s rate=7.27/s eta=12s -[2026-08-13 16:50:41,736] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 113/198 reqs (57.1%) sample_acc=0.000 fails=113 elapsed=16s rate=7.27/s eta=12s -[2026-08-13 16:50:41,870] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 114/198 reqs (57.6%) sample_acc=0.000 fails=114 elapsed=16s rate=7.27/s eta=12s -[2026-08-13 16:50:42,014] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 115/198 reqs (58.1%) sample_acc=0.000 fails=115 elapsed=16s rate=7.27/s eta=11s -[2026-08-13 16:50:42,149] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 116/198 reqs (58.6%) sample_acc=0.000 fails=116 elapsed=16s rate=7.27/s eta=11s -[2026-08-13 16:50:42,283] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 117/198 reqs (59.1%) sample_acc=0.000 fails=117 elapsed=16s rate=7.27/s eta=11s -[2026-08-13 16:50:42,417] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 118/198 reqs (59.6%) sample_acc=0.000 fails=118 elapsed=16s rate=7.27/s eta=11s -[2026-08-13 16:50:42,552] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 119/198 reqs (60.1%) sample_acc=0.000 fails=119 elapsed=16s rate=7.27/s eta=11s -[2026-08-13 16:50:42,687] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 120/198 reqs (60.6%) sample_acc=0.000 fails=120 elapsed=17s rate=7.27/s eta=11s -[2026-08-13 16:50:42,820] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 121/198 reqs (61.1%) sample_acc=0.000 fails=121 elapsed=17s rate=7.27/s eta=11s -[2026-08-13 16:50:42,964] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 122/198 reqs (61.6%) sample_acc=0.000 fails=122 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,098] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 123/198 reqs (62.1%) sample_acc=0.000 fails=123 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,233] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 124/198 reqs (62.6%) sample_acc=0.000 fails=124 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,376] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 125/198 reqs (63.1%) sample_acc=0.000 fails=125 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,511] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 126/198 reqs (63.6%) sample_acc=0.000 fails=126 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,646] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 127/198 reqs (64.1%) sample_acc=0.000 fails=127 elapsed=17s rate=7.27/s eta=10s -[2026-08-13 16:50:43,793] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 128/198 reqs (64.6%) sample_acc=0.000 fails=128 elapsed=18s rate=7.27/s eta=10s -[2026-08-13 16:50:43,928] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 129/198 reqs (65.2%) sample_acc=0.000 fails=129 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,072] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 130/198 reqs (65.7%) sample_acc=0.000 fails=130 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,206] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 131/198 reqs (66.2%) sample_acc=0.000 fails=131 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,340] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 132/198 reqs (66.7%) sample_acc=0.000 fails=132 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,484] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 133/198 reqs (67.2%) sample_acc=0.000 fails=133 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,618] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 134/198 reqs (67.7%) sample_acc=0.000 fails=134 elapsed=18s rate=7.27/s eta=9s -[2026-08-13 16:50:44,753] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 135/198 reqs (68.2%) sample_acc=0.000 fails=135 elapsed=19s rate=7.27/s eta=9s -[2026-08-13 16:50:44,898] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 136/198 reqs (68.7%) sample_acc=0.000 fails=136 elapsed=19s rate=7.27/s eta=9s -[2026-08-13 16:50:45,032] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 137/198 reqs (69.2%) sample_acc=0.000 fails=137 elapsed=19s rate=7.27/s eta=8s -[2026-08-13 16:50:45,168] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 138/198 reqs (69.7%) sample_acc=0.000 fails=138 elapsed=19s rate=7.27/s eta=8s -[2026-08-13 16:50:45,313] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 139/198 reqs (70.2%) sample_acc=0.000 fails=139 elapsed=19s rate=7.27/s eta=8s -[2026-08-13 16:50:45,448] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 140/198 reqs (70.7%) sample_acc=0.000 fails=140 elapsed=19s rate=7.27/s eta=8s -[2026-08-13 16:50:45,582] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 141/198 reqs (71.2%) sample_acc=0.000 fails=141 elapsed=19s rate=7.27/s eta=8s -[2026-08-13 16:50:45,725] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 142/198 reqs (71.7%) sample_acc=0.000 fails=142 elapsed=20s rate=7.27/s eta=8s -[2026-08-13 16:50:45,860] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 143/198 reqs (72.2%) sample_acc=0.000 fails=143 elapsed=20s rate=7.27/s eta=8s -[2026-08-13 16:50:45,994] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 144/198 reqs (72.7%) sample_acc=0.000 fails=144 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,137] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 145/198 reqs (73.2%) sample_acc=0.000 fails=145 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,271] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 146/198 reqs (73.7%) sample_acc=0.000 fails=146 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,405] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 147/198 reqs (74.2%) sample_acc=0.000 fails=147 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,549] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 148/198 reqs (74.7%) sample_acc=0.000 fails=148 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,684] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 149/198 reqs (75.3%) sample_acc=0.000 fails=149 elapsed=20s rate=7.27/s eta=7s -[2026-08-13 16:50:46,818] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 150/198 reqs (75.8%) sample_acc=0.000 fails=150 elapsed=21s rate=7.27/s eta=7s -[2026-08-13 16:50:46,953] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 151/198 reqs (76.3%) sample_acc=0.000 fails=151 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,087] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 152/198 reqs (76.8%) sample_acc=0.000 fails=152 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,221] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 153/198 reqs (77.3%) sample_acc=0.000 fails=153 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,357] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 154/198 reqs (77.8%) sample_acc=0.000 fails=154 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,501] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 155/198 reqs (78.3%) sample_acc=0.000 fails=155 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,635] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 156/198 reqs (78.8%) sample_acc=0.000 fails=156 elapsed=21s rate=7.27/s eta=6s -[2026-08-13 16:50:47,770] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 157/198 reqs (79.3%) sample_acc=0.000 fails=157 elapsed=22s rate=7.27/s eta=6s -[2026-08-13 16:50:47,913] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 158/198 reqs (79.8%) sample_acc=0.000 fails=158 elapsed=22s rate=7.27/s eta=6s -[2026-08-13 16:50:48,047] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 159/198 reqs (80.3%) sample_acc=0.000 fails=159 elapsed=22s rate=7.27/s eta=5s -[2026-08-13 16:50:48,182] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 160/198 reqs (80.8%) sample_acc=0.000 fails=160 elapsed=22s rate=7.27/s eta=5s -[2026-08-13 16:50:48,325] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 161/198 reqs (81.3%) sample_acc=0.000 fails=161 elapsed=22s rate=7.27/s eta=5s -[2026-08-13 16:50:48,459] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 162/198 reqs (81.8%) sample_acc=0.000 fails=162 elapsed=22s rate=7.27/s eta=5s -[2026-08-13 16:50:48,593] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 163/198 reqs (82.3%) sample_acc=0.000 fails=163 elapsed=22s rate=7.27/s eta=5s -[2026-08-13 16:50:48,738] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 164/198 reqs (82.8%) sample_acc=0.000 fails=164 elapsed=23s rate=7.27/s eta=5s -[2026-08-13 16:50:48,873] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 165/198 reqs (83.3%) sample_acc=0.000 fails=165 elapsed=23s rate=7.27/s eta=5s -[2026-08-13 16:50:49,008] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 166/198 reqs (83.8%) sample_acc=0.000 fails=166 elapsed=23s rate=7.27/s eta=4s -[2026-08-13 16:50:49,151] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 167/198 reqs (84.3%) sample_acc=0.000 fails=167 elapsed=23s rate=7.27/s eta=4s -[2026-08-13 16:50:49,285] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 168/198 reqs (84.8%) sample_acc=0.000 fails=168 elapsed=23s rate=7.27/s eta=4s -[2026-08-13 16:50:49,420] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 169/198 reqs (85.4%) sample_acc=0.000 fails=169 elapsed=23s rate=7.27/s eta=4s -[2026-08-13 16:50:49,562] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 170/198 reqs (85.9%) sample_acc=0.000 fails=170 elapsed=23s rate=7.27/s eta=4s -[2026-08-13 16:50:49,696] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 171/198 reqs (86.4%) sample_acc=0.000 fails=171 elapsed=24s rate=7.27/s eta=4s -[2026-08-13 16:50:49,831] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 172/198 reqs (86.9%) sample_acc=0.000 fails=172 elapsed=24s rate=7.27/s eta=4s -[2026-08-13 16:50:49,974] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 173/198 reqs (87.4%) sample_acc=0.000 fails=173 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,108] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 174/198 reqs (87.9%) sample_acc=0.000 fails=174 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,257] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 175/198 reqs (88.4%) sample_acc=0.000 fails=175 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,392] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 176/198 reqs (88.9%) sample_acc=0.000 fails=176 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,527] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 177/198 reqs (89.4%) sample_acc=0.000 fails=177 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,670] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 178/198 reqs (89.9%) sample_acc=0.000 fails=178 elapsed=24s rate=7.27/s eta=3s -[2026-08-13 16:50:50,805] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 179/198 reqs (90.4%) sample_acc=0.000 fails=179 elapsed=25s rate=7.27/s eta=3s -[2026-08-13 16:50:50,949] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 180/198 reqs (90.9%) sample_acc=0.000 fails=180 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,085] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 181/198 reqs (91.4%) sample_acc=0.000 fails=181 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,219] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 182/198 reqs (91.9%) sample_acc=0.000 fails=182 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,353] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 183/198 reqs (92.4%) sample_acc=0.000 fails=183 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,488] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 184/198 reqs (92.9%) sample_acc=0.000 fails=184 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,622] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 185/198 reqs (93.4%) sample_acc=0.000 fails=185 elapsed=25s rate=7.27/s eta=2s -[2026-08-13 16:50:51,756] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 186/198 reqs (93.9%) sample_acc=0.000 fails=186 elapsed=26s rate=7.27/s eta=2s -[2026-08-13 16:50:51,900] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 187/198 reqs (94.4%) sample_acc=0.000 fails=187 elapsed=26s rate=7.27/s eta=2s -[2026-08-13 16:50:52,033] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 188/198 reqs (94.9%) sample_acc=0.000 fails=188 elapsed=26s rate=7.27/s eta=1s -[2026-08-13 16:50:52,167] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 189/198 reqs (95.5%) sample_acc=0.000 fails=189 elapsed=26s rate=7.27/s eta=1s -[2026-08-13 16:50:52,301] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 190/198 reqs (96.0%) sample_acc=0.000 fails=190 elapsed=26s rate=7.28/s eta=1s -[2026-08-13 16:50:52,446] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 191/198 reqs (96.5%) sample_acc=0.000 fails=191 elapsed=26s rate=7.27/s eta=1s -[2026-08-13 16:50:52,580] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 192/198 reqs (97.0%) sample_acc=0.000 fails=192 elapsed=26s rate=7.27/s eta=1s -[2026-08-13 16:50:52,715] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 193/198 reqs (97.5%) sample_acc=0.000 fails=193 elapsed=27s rate=7.28/s eta=1s -[2026-08-13 16:50:52,857] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 194/198 reqs (98.0%) sample_acc=0.000 fails=194 elapsed=27s rate=7.27/s eta=1s -[2026-08-13 16:50:52,992] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 195/198 reqs (98.5%) sample_acc=0.000 fails=195 elapsed=27s rate=7.27/s eta=0s -[2026-08-13 16:50:53,136] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 196/198 reqs (99.0%) sample_acc=0.000 fails=196 elapsed=27s rate=7.27/s eta=0s -[2026-08-13 16:50:53,270] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 197/198 reqs (99.5%) sample_acc=0.000 fails=197 elapsed=27s rate=7.27/s eta=0s -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: 198/198 reqs (100.0%) sample_acc=0.000 fails=198 elapsed=27s rate=7.27/s eta=0s -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [academic] gpqa_diamond: 198 requests failed during inference (sample: ['HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131229 tokens (157 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131238 tokens (166 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131259 tokens (187 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}']) -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond: avg@1=0.0000 pass@1=0.0000 (items=198, samples=198, correct_samples=0) in 27.2s -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond sample item=0 correct=False response='' -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond sample item=1 correct=False response='' -[2026-08-13 16:50:53,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] gpqa_diamond sample item=2 correct=False response='' -[2026-08-13 16:50:53,410] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] <<< benchmark 2/5: gpqa_diamond done score=0.0000 took=27s -[2026-08-13 16:50:53,410] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 3/5: hle (sample_cap=100, avg@1, pass@1, temp=1.00, top_p=0.95, max_tokens=131072, suite_elapsed=60s) -[2026-08-13 16:50:55,346] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [hle] grader=llm_judge (model=Kimi-K2.5 endpoint=http://172.21.112.11/phanrouter max_tokens=2048) -[2026-08-13 16:51:16,897] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [hle] judge preflight OK (Kimi-K2.5 at http://172.21.112.11/phanrouter) -[2026-08-13 16:51:16,898] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: BEGIN items=100 n_samples=1 (avg@1/pass@1) temp=1.00 top_p=0.95 requests=100 workers=1 max_tokens=131072 timeout=3600.0s stream=True -[2026-08-13 16:51:17,068] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 1/100 reqs (1.0%) sample_acc=0.000 fails=1 elapsed=0s rate=5.87/s eta=17s -[2026-08-13 16:51:17,205] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 2/100 reqs (2.0%) sample_acc=0.000 fails=2 elapsed=0s rate=6.52/s eta=15s -[2026-08-13 16:51:17,349] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 3/100 reqs (3.0%) sample_acc=0.000 fails=3 elapsed=0s rate=6.64/s eta=15s -[2026-08-13 16:51:17,485] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 4/100 reqs (4.0%) sample_acc=0.000 fails=4 elapsed=1s rate=6.81/s eta=14s -[2026-08-13 16:51:17,622] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 5/100 reqs (5.0%) sample_acc=0.000 fails=5 elapsed=1s rate=6.91/s eta=14s -[2026-08-13 16:51:17,766] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 6/100 reqs (6.0%) sample_acc=0.000 fails=6 elapsed=1s rate=6.91/s eta=14s -[2026-08-13 16:51:17,902] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 7/100 reqs (7.0%) sample_acc=0.000 fails=7 elapsed=1s rate=6.97/s eta=13s -[2026-08-13 16:51:18,037] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 8/100 reqs (8.0%) sample_acc=0.000 fails=8 elapsed=1s rate=7.02/s eta=13s -[2026-08-13 16:51:18,180] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 9/100 reqs (9.0%) sample_acc=0.000 fails=9 elapsed=1s rate=7.02/s eta=13s -[2026-08-13 16:51:18,314] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 10/100 reqs (10.0%) sample_acc=0.000 fails=10 elapsed=1s rate=7.06/s eta=13s -[2026-08-13 16:51:18,448] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 11/100 reqs (11.0%) sample_acc=0.000 fails=11 elapsed=2s rate=7.10/s eta=13s -[2026-08-13 16:51:18,582] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 12/100 reqs (12.0%) sample_acc=0.000 fails=12 elapsed=2s rate=7.12/s eta=12s -[2026-08-13 16:51:18,725] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 13/100 reqs (13.0%) sample_acc=0.000 fails=13 elapsed=2s rate=7.12/s eta=12s -[2026-08-13 16:51:18,860] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 14/100 reqs (14.0%) sample_acc=0.000 fails=14 elapsed=2s rate=7.13/s eta=12s -[2026-08-13 16:51:18,994] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 15/100 reqs (15.0%) sample_acc=0.000 fails=15 elapsed=2s rate=7.16/s eta=12s -[2026-08-13 16:51:19,129] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 16/100 reqs (16.0%) sample_acc=0.000 fails=16 elapsed=2s rate=7.17/s eta=12s -[2026-08-13 16:51:19,263] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 17/100 reqs (17.0%) sample_acc=0.000 fails=17 elapsed=2s rate=7.19/s eta=12s -[2026-08-13 16:51:19,398] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 18/100 reqs (18.0%) sample_acc=0.000 fails=18 elapsed=3s rate=7.20/s eta=11s -[2026-08-13 16:51:19,533] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 19/100 reqs (19.0%) sample_acc=0.000 fails=19 elapsed=3s rate=7.21/s eta=11s -[2026-08-13 16:51:19,676] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 20/100 reqs (20.0%) sample_acc=0.000 fails=20 elapsed=3s rate=7.20/s eta=11s -[2026-08-13 16:51:19,811] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 21/100 reqs (21.0%) sample_acc=0.000 fails=21 elapsed=3s rate=7.21/s eta=11s -[2026-08-13 16:51:19,945] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 22/100 reqs (22.0%) sample_acc=0.000 fails=22 elapsed=3s rate=7.22/s eta=11s -[2026-08-13 16:51:20,088] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 23/100 reqs (23.0%) sample_acc=0.000 fails=23 elapsed=3s rate=7.21/s eta=11s -[2026-08-13 16:51:20,222] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 24/100 reqs (24.0%) sample_acc=0.000 fails=24 elapsed=3s rate=7.22/s eta=11s -[2026-08-13 16:51:20,356] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 25/100 reqs (25.0%) sample_acc=0.000 fails=25 elapsed=3s rate=7.23/s eta=10s -[2026-08-13 16:51:20,500] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 26/100 reqs (26.0%) sample_acc=0.000 fails=26 elapsed=4s rate=7.22/s eta=10s -[2026-08-13 16:51:20,634] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 27/100 reqs (27.0%) sample_acc=0.000 fails=27 elapsed=4s rate=7.23/s eta=10s -[2026-08-13 16:51:20,769] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 28/100 reqs (28.0%) sample_acc=0.000 fails=28 elapsed=4s rate=7.23/s eta=10s -[2026-08-13 16:51:20,902] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 29/100 reqs (29.0%) sample_acc=0.000 fails=29 elapsed=4s rate=7.24/s eta=10s -[2026-08-13 16:51:21,047] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 30/100 reqs (30.0%) sample_acc=0.000 fails=30 elapsed=4s rate=7.23/s eta=10s -[2026-08-13 16:51:21,182] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 31/100 reqs (31.0%) sample_acc=0.000 fails=31 elapsed=4s rate=7.24/s eta=10s -[2026-08-13 16:51:21,320] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 32/100 reqs (32.0%) sample_acc=0.000 fails=32 elapsed=4s rate=7.24/s eta=9s -[2026-08-13 16:51:21,473] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 33/100 reqs (33.0%) sample_acc=0.000 fails=33 elapsed=5s rate=7.21/s eta=9s -[2026-08-13 16:51:21,608] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 34/100 reqs (34.0%) sample_acc=0.000 fails=34 elapsed=5s rate=7.22/s eta=9s -[2026-08-13 16:51:21,743] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 35/100 reqs (35.0%) sample_acc=0.000 fails=35 elapsed=5s rate=7.22/s eta=9s -[2026-08-13 16:51:21,885] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 36/100 reqs (36.0%) sample_acc=0.000 fails=36 elapsed=5s rate=7.22/s eta=9s -[2026-08-13 16:51:22,019] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 37/100 reqs (37.0%) sample_acc=0.000 fails=37 elapsed=5s rate=7.22/s eta=9s -[2026-08-13 16:51:22,165] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 38/100 reqs (38.0%) sample_acc=0.000 fails=38 elapsed=5s rate=7.22/s eta=9s -[2026-08-13 16:51:22,299] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 39/100 reqs (39.0%) sample_acc=0.000 fails=39 elapsed=5s rate=7.22/s eta=8s -[2026-08-13 16:51:22,434] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 40/100 reqs (40.0%) sample_acc=0.000 fails=40 elapsed=6s rate=7.23/s eta=8s -[2026-08-13 16:51:22,578] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 41/100 reqs (41.0%) sample_acc=0.000 fails=41 elapsed=6s rate=7.22/s eta=8s -[2026-08-13 16:51:22,714] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 42/100 reqs (42.0%) sample_acc=0.000 fails=42 elapsed=6s rate=7.22/s eta=8s -[2026-08-13 16:51:22,849] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 43/100 reqs (43.0%) sample_acc=0.000 fails=43 elapsed=6s rate=7.23/s eta=8s -[2026-08-13 16:51:22,997] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 44/100 reqs (44.0%) sample_acc=0.000 fails=44 elapsed=6s rate=7.21/s eta=8s -[2026-08-13 16:51:23,142] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 45/100 reqs (45.0%) sample_acc=0.000 fails=45 elapsed=6s rate=7.21/s eta=8s -[2026-08-13 16:51:23,279] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 46/100 reqs (46.0%) sample_acc=0.000 fails=46 elapsed=6s rate=7.21/s eta=7s -[2026-08-13 16:51:23,413] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 47/100 reqs (47.0%) sample_acc=0.000 fails=47 elapsed=7s rate=7.21/s eta=7s -[2026-08-13 16:51:23,547] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 48/100 reqs (48.0%) sample_acc=0.000 fails=48 elapsed=7s rate=7.22/s eta=7s -[2026-08-13 16:51:23,683] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 49/100 reqs (49.0%) sample_acc=0.000 fails=49 elapsed=7s rate=7.22/s eta=7s -[2026-08-13 16:51:23,818] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 50/100 reqs (50.0%) sample_acc=0.000 fails=50 elapsed=7s rate=7.23/s eta=7s -[2026-08-13 16:51:23,963] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 51/100 reqs (51.0%) sample_acc=0.000 fails=51 elapsed=7s rate=7.22/s eta=7s -[2026-08-13 16:51:24,097] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 52/100 reqs (52.0%) sample_acc=0.000 fails=52 elapsed=7s rate=7.22/s eta=7s -[2026-08-13 16:51:24,231] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 53/100 reqs (53.0%) sample_acc=0.000 fails=53 elapsed=7s rate=7.23/s eta=7s -[2026-08-13 16:51:24,364] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 54/100 reqs (54.0%) sample_acc=0.000 fails=54 elapsed=7s rate=7.23/s eta=6s -[2026-08-13 16:51:24,507] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 55/100 reqs (55.0%) sample_acc=0.000 fails=55 elapsed=8s rate=7.23/s eta=6s -[2026-08-13 16:51:24,641] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 56/100 reqs (56.0%) sample_acc=0.000 fails=56 elapsed=8s rate=7.23/s eta=6s -[2026-08-13 16:51:24,776] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 57/100 reqs (57.0%) sample_acc=0.000 fails=57 elapsed=8s rate=7.24/s eta=6s -[2026-08-13 16:51:24,921] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 58/100 reqs (58.0%) sample_acc=0.000 fails=58 elapsed=8s rate=7.23/s eta=6s -[2026-08-13 16:51:25,056] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 59/100 reqs (59.0%) sample_acc=0.000 fails=59 elapsed=8s rate=7.23/s eta=6s -[2026-08-13 16:51:25,190] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 60/100 reqs (60.0%) sample_acc=0.000 fails=60 elapsed=8s rate=7.24/s eta=6s -[2026-08-13 16:51:25,333] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 61/100 reqs (61.0%) sample_acc=0.000 fails=61 elapsed=8s rate=7.23/s eta=5s -[2026-08-13 16:51:25,467] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 62/100 reqs (62.0%) sample_acc=0.000 fails=62 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:25,602] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 63/100 reqs (63.0%) sample_acc=0.000 fails=63 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:25,736] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 64/100 reqs (64.0%) sample_acc=0.000 fails=64 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:25,879] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 65/100 reqs (65.0%) sample_acc=0.000 fails=65 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:26,016] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 66/100 reqs (66.0%) sample_acc=0.000 fails=66 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:26,151] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 67/100 reqs (67.0%) sample_acc=0.000 fails=67 elapsed=9s rate=7.24/s eta=5s -[2026-08-13 16:51:26,297] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 68/100 reqs (68.0%) sample_acc=0.000 fails=68 elapsed=9s rate=7.23/s eta=4s -[2026-08-13 16:51:26,432] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 69/100 reqs (69.0%) sample_acc=0.000 fails=69 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:26,567] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 70/100 reqs (70.0%) sample_acc=0.000 fails=70 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:26,710] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 71/100 reqs (71.0%) sample_acc=0.000 fails=71 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:26,845] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 72/100 reqs (72.0%) sample_acc=0.000 fails=72 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:26,979] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 73/100 reqs (73.0%) sample_acc=0.000 fails=73 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:27,122] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 74/100 reqs (74.0%) sample_acc=0.000 fails=74 elapsed=10s rate=7.24/s eta=4s -[2026-08-13 16:51:27,256] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 75/100 reqs (75.0%) sample_acc=0.000 fails=75 elapsed=10s rate=7.24/s eta=3s -[2026-08-13 16:51:27,390] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 76/100 reqs (76.0%) sample_acc=0.000 fails=76 elapsed=10s rate=7.24/s eta=3s -[2026-08-13 16:51:27,533] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 77/100 reqs (77.0%) sample_acc=0.000 fails=77 elapsed=11s rate=7.24/s eta=3s -[2026-08-13 16:51:27,668] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 78/100 reqs (78.0%) sample_acc=0.000 fails=78 elapsed=11s rate=7.24/s eta=3s -[2026-08-13 16:51:27,817] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 79/100 reqs (79.0%) sample_acc=0.000 fails=79 elapsed=11s rate=7.24/s eta=3s -[2026-08-13 16:51:27,954] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 80/100 reqs (80.0%) sample_acc=0.000 fails=80 elapsed=11s rate=7.24/s eta=3s -[2026-08-13 16:51:28,088] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 81/100 reqs (81.0%) sample_acc=0.000 fails=81 elapsed=11s rate=7.24/s eta=3s -[2026-08-13 16:51:28,224] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 82/100 reqs (82.0%) sample_acc=0.000 fails=82 elapsed=11s rate=7.24/s eta=2s -[2026-08-13 16:51:28,360] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 83/100 reqs (83.0%) sample_acc=0.000 fails=83 elapsed=11s rate=7.24/s eta=2s -[2026-08-13 16:51:28,494] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 84/100 reqs (84.0%) sample_acc=0.000 fails=84 elapsed=12s rate=7.24/s eta=2s -[2026-08-13 16:51:28,637] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 85/100 reqs (85.0%) sample_acc=0.000 fails=85 elapsed=12s rate=7.24/s eta=2s -[2026-08-13 16:51:28,771] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 86/100 reqs (86.0%) sample_acc=0.000 fails=86 elapsed=12s rate=7.24/s eta=2s -[2026-08-13 16:51:28,904] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 87/100 reqs (87.0%) sample_acc=0.000 fails=87 elapsed=12s rate=7.25/s eta=2s -[2026-08-13 16:51:29,048] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 88/100 reqs (88.0%) sample_acc=0.000 fails=88 elapsed=12s rate=7.24/s eta=2s -[2026-08-13 16:51:29,183] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 89/100 reqs (89.0%) sample_acc=0.000 fails=89 elapsed=12s rate=7.24/s eta=2s -[2026-08-13 16:51:29,317] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 90/100 reqs (90.0%) sample_acc=0.000 fails=90 elapsed=12s rate=7.25/s eta=1s -[2026-08-13 16:51:29,462] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 91/100 reqs (91.0%) sample_acc=0.000 fails=91 elapsed=13s rate=7.24/s eta=1s -[2026-08-13 16:51:29,595] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 92/100 reqs (92.0%) sample_acc=0.000 fails=92 elapsed=13s rate=7.25/s eta=1s -[2026-08-13 16:51:29,729] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 93/100 reqs (93.0%) sample_acc=0.000 fails=93 elapsed=13s rate=7.25/s eta=1s -[2026-08-13 16:51:29,873] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 94/100 reqs (94.0%) sample_acc=0.000 fails=94 elapsed=13s rate=7.24/s eta=1s -[2026-08-13 16:51:30,007] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 95/100 reqs (95.0%) sample_acc=0.000 fails=95 elapsed=13s rate=7.25/s eta=1s -[2026-08-13 16:51:30,141] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 96/100 reqs (96.0%) sample_acc=0.000 fails=96 elapsed=13s rate=7.25/s eta=1s -[2026-08-13 16:51:30,275] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 97/100 reqs (97.0%) sample_acc=0.000 fails=97 elapsed=13s rate=7.25/s eta=0s -[2026-08-13 16:51:30,418] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 98/100 reqs (98.0%) sample_acc=0.000 fails=98 elapsed=14s rate=7.25/s eta=0s -[2026-08-13 16:51:30,552] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 99/100 reqs (99.0%) sample_acc=0.000 fails=99 elapsed=14s rate=7.25/s eta=0s -[2026-08-13 16:51:30,688] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: 100/100 reqs (100.0%) sample_acc=0.000 fails=100 elapsed=14s rate=7.25/s eta=0s -[2026-08-13 16:51:30,688] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [academic] hle: 100 requests failed during inference (sample: ['HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131195 tokens (123 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131331 tokens (259 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131187 tokens (115 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}']) -[2026-08-13 16:51:30,688] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle: avg@1=0.0000 pass@1=0.0000 (items=100, samples=100, correct_samples=0) in 13.8s -[2026-08-13 16:51:30,689] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle sample item=0 correct=False response='' -[2026-08-13 16:51:30,689] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle sample item=1 correct=False response='' -[2026-08-13 16:51:30,689] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] hle sample item=2 correct=False response='' -[2026-08-13 16:51:30,689] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] <<< benchmark 3/5: hle done score=0.0000 took=37s -[2026-08-13 16:51:30,689] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 4/5: simpleqa (sample_cap=200, avg@1, pass@1, temp=1.00, top_p=0.95, max_tokens=131072, suite_elapsed=97s) -[2026-08-13 16:51:30,695] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [simpleqa] grader model=Kimi-K2.5 endpoint=http://172.21.112.11/phanrouter (external) judge_max_tokens=16384 -[2026-08-13 16:51:36,249] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [simpleqa] judge preflight OK (Kimi-K2.5 at http://172.21.112.11/phanrouter) -[2026-08-13 16:51:36,249] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: BEGIN items=200 n_samples=1 (avg@1/pass@1) temp=1.00 top_p=0.95 requests=200 workers=1 max_tokens=131072 timeout=3600.0s stream=True -[2026-08-13 16:51:36,536] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 2/200 reqs (1.0%) sample_acc=0.000 fails=2 elapsed=0s rate=6.98/s eta=28s -[2026-08-13 16:51:36,803] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 4/200 reqs (2.0%) sample_acc=0.000 fails=4 elapsed=1s rate=7.22/s eta=27s -[2026-08-13 16:51:37,079] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 6/200 reqs (3.0%) sample_acc=0.000 fails=6 elapsed=1s rate=7.24/s eta=27s -[2026-08-13 16:51:37,345] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 8/200 reqs (4.0%) sample_acc=0.000 fails=8 elapsed=1s rate=7.30/s eta=26s -[2026-08-13 16:51:37,612] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 10/200 reqs (5.0%) sample_acc=0.000 fails=10 elapsed=1s rate=7.34/s eta=26s -[2026-08-13 16:51:37,890] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 12/200 reqs (6.0%) sample_acc=0.000 fails=12 elapsed=2s rate=7.31/s eta=26s -[2026-08-13 16:51:38,157] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 14/200 reqs (7.0%) sample_acc=0.000 fails=14 elapsed=2s rate=7.34/s eta=25s -[2026-08-13 16:51:38,433] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 16/200 reqs (8.0%) sample_acc=0.000 fails=16 elapsed=2s rate=7.33/s eta=25s -[2026-08-13 16:51:38,699] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 18/200 reqs (9.0%) sample_acc=0.000 fails=18 elapsed=2s rate=7.35/s eta=25s -[2026-08-13 16:51:38,975] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 20/200 reqs (10.0%) sample_acc=0.000 fails=20 elapsed=3s rate=7.34/s eta=25s -[2026-08-13 16:51:39,254] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 22/200 reqs (11.0%) sample_acc=0.000 fails=22 elapsed=3s rate=7.32/s eta=24s -[2026-08-13 16:51:39,528] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 24/200 reqs (12.0%) sample_acc=0.000 fails=24 elapsed=3s rate=7.32/s eta=24s -[2026-08-13 16:51:39,795] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 26/200 reqs (13.0%) sample_acc=0.000 fails=26 elapsed=4s rate=7.33/s eta=24s -[2026-08-13 16:51:40,062] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 28/200 reqs (14.0%) sample_acc=0.000 fails=28 elapsed=4s rate=7.34/s eta=23s -[2026-08-13 16:51:40,338] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 30/200 reqs (15.0%) sample_acc=0.000 fails=30 elapsed=4s rate=7.34/s eta=23s -[2026-08-13 16:51:40,607] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 32/200 reqs (16.0%) sample_acc=0.000 fails=32 elapsed=4s rate=7.34/s eta=23s -[2026-08-13 16:51:40,882] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 34/200 reqs (17.0%) sample_acc=0.000 fails=34 elapsed=5s rate=7.34/s eta=23s -[2026-08-13 16:51:41,149] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 36/200 reqs (18.0%) sample_acc=0.000 fails=36 elapsed=5s rate=7.35/s eta=22s -[2026-08-13 16:51:41,424] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 38/200 reqs (19.0%) sample_acc=0.000 fails=38 elapsed=5s rate=7.34/s eta=22s -[2026-08-13 16:51:41,692] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 40/200 reqs (20.0%) sample_acc=0.000 fails=40 elapsed=5s rate=7.35/s eta=22s -[2026-08-13 16:51:41,968] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 42/200 reqs (21.0%) sample_acc=0.000 fails=42 elapsed=6s rate=7.34/s eta=22s -[2026-08-13 16:51:42,234] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 44/200 reqs (22.0%) sample_acc=0.000 fails=44 elapsed=6s rate=7.35/s eta=21s -[2026-08-13 16:51:42,510] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 46/200 reqs (23.0%) sample_acc=0.000 fails=46 elapsed=6s rate=7.35/s eta=21s -[2026-08-13 16:51:42,776] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 48/200 reqs (24.0%) sample_acc=0.000 fails=48 elapsed=7s rate=7.35/s eta=21s -[2026-08-13 16:51:43,051] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 50/200 reqs (25.0%) sample_acc=0.000 fails=50 elapsed=7s rate=7.35/s eta=20s -[2026-08-13 16:51:43,329] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 52/200 reqs (26.0%) sample_acc=0.000 fails=52 elapsed=7s rate=7.35/s eta=20s -[2026-08-13 16:51:43,596] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 54/200 reqs (27.0%) sample_acc=0.000 fails=54 elapsed=7s rate=7.35/s eta=20s -[2026-08-13 16:51:43,875] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 56/200 reqs (28.0%) sample_acc=0.000 fails=56 elapsed=8s rate=7.34/s eta=20s -[2026-08-13 16:51:44,143] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 58/200 reqs (29.0%) sample_acc=0.000 fails=58 elapsed=8s rate=7.35/s eta=19s -[2026-08-13 16:51:44,420] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 60/200 reqs (30.0%) sample_acc=0.000 fails=60 elapsed=8s rate=7.34/s eta=19s -[2026-08-13 16:51:44,696] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 62/200 reqs (31.0%) sample_acc=0.000 fails=62 elapsed=8s rate=7.34/s eta=19s -[2026-08-13 16:51:44,965] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 64/200 reqs (32.0%) sample_acc=0.000 fails=64 elapsed=9s rate=7.34/s eta=19s -[2026-08-13 16:51:45,232] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 66/200 reqs (33.0%) sample_acc=0.000 fails=66 elapsed=9s rate=7.35/s eta=18s -[2026-08-13 16:51:45,506] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 68/200 reqs (34.0%) sample_acc=0.000 fails=68 elapsed=9s rate=7.35/s eta=18s -[2026-08-13 16:51:45,782] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 70/200 reqs (35.0%) sample_acc=0.000 fails=70 elapsed=10s rate=7.34/s eta=18s -[2026-08-13 16:51:46,050] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 72/200 reqs (36.0%) sample_acc=0.000 fails=72 elapsed=10s rate=7.35/s eta=17s -[2026-08-13 16:51:46,327] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 74/200 reqs (37.0%) sample_acc=0.000 fails=74 elapsed=10s rate=7.34/s eta=17s -[2026-08-13 16:51:46,596] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 76/200 reqs (38.0%) sample_acc=0.000 fails=76 elapsed=10s rate=7.35/s eta=17s -[2026-08-13 16:51:46,872] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 78/200 reqs (39.0%) sample_acc=0.000 fails=78 elapsed=11s rate=7.34/s eta=17s -[2026-08-13 16:51:47,140] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 80/200 reqs (40.0%) sample_acc=0.000 fails=80 elapsed=11s rate=7.35/s eta=16s -[2026-08-13 16:51:47,415] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 82/200 reqs (41.0%) sample_acc=0.000 fails=82 elapsed=11s rate=7.34/s eta=16s -[2026-08-13 16:51:47,685] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 84/200 reqs (42.0%) sample_acc=0.000 fails=84 elapsed=11s rate=7.35/s eta=16s -[2026-08-13 16:51:47,961] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 86/200 reqs (43.0%) sample_acc=0.000 fails=86 elapsed=12s rate=7.34/s eta=16s -[2026-08-13 16:51:48,227] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 88/200 reqs (44.0%) sample_acc=0.000 fails=88 elapsed=12s rate=7.35/s eta=15s -[2026-08-13 16:51:48,505] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 90/200 reqs (45.0%) sample_acc=0.000 fails=90 elapsed=12s rate=7.34/s eta=15s -[2026-08-13 16:51:48,782] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 92/200 reqs (46.0%) sample_acc=0.000 fails=92 elapsed=13s rate=7.34/s eta=15s -[2026-08-13 16:51:49,049] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 94/200 reqs (47.0%) sample_acc=0.000 fails=94 elapsed=13s rate=7.34/s eta=14s -[2026-08-13 16:51:49,316] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 96/200 reqs (48.0%) sample_acc=0.000 fails=96 elapsed=13s rate=7.35/s eta=14s -[2026-08-13 16:51:49,584] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 98/200 reqs (49.0%) sample_acc=0.000 fails=98 elapsed=13s rate=7.35/s eta=14s -[2026-08-13 16:51:49,864] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 100/200 reqs (50.0%) sample_acc=0.000 fails=100 elapsed=14s rate=7.35/s eta=14s -[2026-08-13 16:51:50,141] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 102/200 reqs (51.0%) sample_acc=0.000 fails=102 elapsed=14s rate=7.34/s eta=13s -[2026-08-13 16:51:50,410] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 104/200 reqs (52.0%) sample_acc=0.000 fails=104 elapsed=14s rate=7.34/s eta=13s -[2026-08-13 16:51:50,678] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 106/200 reqs (53.0%) sample_acc=0.000 fails=106 elapsed=14s rate=7.35/s eta=13s -[2026-08-13 16:51:50,946] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 108/200 reqs (54.0%) sample_acc=0.000 fails=108 elapsed=15s rate=7.35/s eta=13s -[2026-08-13 16:51:51,222] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 110/200 reqs (55.0%) sample_acc=0.000 fails=110 elapsed=15s rate=7.35/s eta=12s -[2026-08-13 16:51:51,490] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 112/200 reqs (56.0%) sample_acc=0.000 fails=112 elapsed=15s rate=7.35/s eta=12s -[2026-08-13 16:51:51,767] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 114/200 reqs (57.0%) sample_acc=0.000 fails=114 elapsed=16s rate=7.35/s eta=12s -[2026-08-13 16:51:52,045] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 116/200 reqs (58.0%) sample_acc=0.000 fails=116 elapsed=16s rate=7.34/s eta=11s -[2026-08-13 16:51:52,311] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 118/200 reqs (59.0%) sample_acc=0.000 fails=118 elapsed=16s rate=7.35/s eta=11s -[2026-08-13 16:51:52,589] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 120/200 reqs (60.0%) sample_acc=0.000 fails=120 elapsed=16s rate=7.34/s eta=11s -[2026-08-13 16:51:52,855] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 122/200 reqs (61.0%) sample_acc=0.000 fails=122 elapsed=17s rate=7.35/s eta=11s -[2026-08-13 16:51:53,131] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 124/200 reqs (62.0%) sample_acc=0.000 fails=124 elapsed=17s rate=7.35/s eta=10s -[2026-08-13 16:51:53,398] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 126/200 reqs (63.0%) sample_acc=0.000 fails=126 elapsed=17s rate=7.35/s eta=10s -[2026-08-13 16:51:53,675] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 128/200 reqs (64.0%) sample_acc=0.000 fails=128 elapsed=17s rate=7.35/s eta=10s -[2026-08-13 16:51:53,945] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 130/200 reqs (65.0%) sample_acc=0.000 fails=130 elapsed=18s rate=7.35/s eta=10s -[2026-08-13 16:51:54,225] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 132/200 reqs (66.0%) sample_acc=0.000 fails=132 elapsed=18s rate=7.34/s eta=9s -[2026-08-13 16:51:54,491] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 134/200 reqs (67.0%) sample_acc=0.000 fails=134 elapsed=18s rate=7.35/s eta=9s -[2026-08-13 16:51:54,768] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 136/200 reqs (68.0%) sample_acc=0.000 fails=136 elapsed=19s rate=7.34/s eta=9s -[2026-08-13 16:51:55,046] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 138/200 reqs (69.0%) sample_acc=0.000 fails=138 elapsed=19s rate=7.34/s eta=8s -[2026-08-13 16:51:55,314] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 140/200 reqs (70.0%) sample_acc=0.000 fails=140 elapsed=19s rate=7.34/s eta=8s -[2026-08-13 16:51:55,590] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 142/200 reqs (71.0%) sample_acc=0.000 fails=142 elapsed=19s rate=7.34/s eta=8s -[2026-08-13 16:51:55,858] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 144/200 reqs (72.0%) sample_acc=0.000 fails=144 elapsed=20s rate=7.34/s eta=8s -[2026-08-13 16:51:56,126] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 146/200 reqs (73.0%) sample_acc=0.000 fails=146 elapsed=20s rate=7.35/s eta=7s -[2026-08-13 16:51:56,405] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 148/200 reqs (74.0%) sample_acc=0.000 fails=148 elapsed=20s rate=7.34/s eta=7s -[2026-08-13 16:51:56,672] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 150/200 reqs (75.0%) sample_acc=0.000 fails=150 elapsed=20s rate=7.34/s eta=7s -[2026-08-13 16:51:56,950] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 152/200 reqs (76.0%) sample_acc=0.000 fails=152 elapsed=21s rate=7.34/s eta=7s -[2026-08-13 16:51:57,217] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 154/200 reqs (77.0%) sample_acc=0.000 fails=154 elapsed=21s rate=7.34/s eta=6s -[2026-08-13 16:51:57,494] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 156/200 reqs (78.0%) sample_acc=0.000 fails=156 elapsed=21s rate=7.34/s eta=6s -[2026-08-13 16:51:57,762] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 158/200 reqs (79.0%) sample_acc=0.000 fails=158 elapsed=22s rate=7.34/s eta=6s -[2026-08-13 16:51:58,038] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 160/200 reqs (80.0%) sample_acc=0.000 fails=160 elapsed=22s rate=7.34/s eta=5s -[2026-08-13 16:51:58,308] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 162/200 reqs (81.0%) sample_acc=0.000 fails=162 elapsed=22s rate=7.34/s eta=5s -[2026-08-13 16:51:58,575] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 164/200 reqs (82.0%) sample_acc=0.000 fails=164 elapsed=22s rate=7.35/s eta=5s -[2026-08-13 16:51:58,851] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 166/200 reqs (83.0%) sample_acc=0.000 fails=166 elapsed=23s rate=7.34/s eta=5s -[2026-08-13 16:51:59,118] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 168/200 reqs (84.0%) sample_acc=0.000 fails=168 elapsed=23s rate=7.35/s eta=4s -[2026-08-13 16:51:59,394] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 170/200 reqs (85.0%) sample_acc=0.000 fails=170 elapsed=23s rate=7.35/s eta=4s -[2026-08-13 16:51:59,661] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 172/200 reqs (86.0%) sample_acc=0.000 fails=172 elapsed=23s rate=7.35/s eta=4s -[2026-08-13 16:51:59,936] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 174/200 reqs (87.0%) sample_acc=0.000 fails=174 elapsed=24s rate=7.35/s eta=4s -[2026-08-13 16:52:00,203] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 176/200 reqs (88.0%) sample_acc=0.000 fails=176 elapsed=24s rate=7.35/s eta=3s -[2026-08-13 16:52:00,479] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 178/200 reqs (89.0%) sample_acc=0.000 fails=178 elapsed=24s rate=7.35/s eta=3s -[2026-08-13 16:52:00,754] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 180/200 reqs (90.0%) sample_acc=0.000 fails=180 elapsed=25s rate=7.35/s eta=3s -[2026-08-13 16:52:01,036] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 182/200 reqs (91.0%) sample_acc=0.000 fails=182 elapsed=25s rate=7.34/s eta=2s -[2026-08-13 16:52:01,305] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 184/200 reqs (92.0%) sample_acc=0.000 fails=184 elapsed=25s rate=7.34/s eta=2s -[2026-08-13 16:52:01,571] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 186/200 reqs (93.0%) sample_acc=0.000 fails=186 elapsed=25s rate=7.35/s eta=2s -[2026-08-13 16:52:01,847] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 188/200 reqs (94.0%) sample_acc=0.000 fails=188 elapsed=26s rate=7.34/s eta=2s -[2026-08-13 16:52:02,114] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 190/200 reqs (95.0%) sample_acc=0.000 fails=190 elapsed=26s rate=7.35/s eta=1s -[2026-08-13 16:52:02,392] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 192/200 reqs (96.0%) sample_acc=0.000 fails=192 elapsed=26s rate=7.34/s eta=1s -[2026-08-13 16:52:02,670] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 194/200 reqs (97.0%) sample_acc=0.000 fails=194 elapsed=26s rate=7.34/s eta=1s -[2026-08-13 16:52:02,937] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 196/200 reqs (98.0%) sample_acc=0.000 fails=196 elapsed=27s rate=7.34/s eta=1s -[2026-08-13 16:52:03,213] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 198/200 reqs (99.0%) sample_acc=0.000 fails=198 elapsed=27s rate=7.34/s eta=0s -[2026-08-13 16:52:03,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: 200/200 reqs (100.0%) sample_acc=0.000 fails=200 elapsed=27s rate=7.34/s eta=0s -[2026-08-13 16:52:03,481] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [academic] simpleqa: 200 requests failed during inference (sample: ['HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131097 tokens (25 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131100 tokens (28 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 131098 tokens (26 in the messages, 131072 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}']) -[2026-08-13 16:52:03,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa: avg@1=0.0000 pass@1=0.0000 (items=200, samples=200, correct_samples=0) in 27.2s -[2026-08-13 16:52:03,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa sample item=0 correct=False response='' -[2026-08-13 16:52:03,481] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa sample item=1 correct=False response='' -[2026-08-13 16:52:03,482] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] simpleqa sample item=2 correct=False response='' -[2026-08-13 16:52:03,482] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] <<< benchmark 4/5: simpleqa done score=0.0000 took=33s -[2026-08-13 16:52:03,482] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 5/5: longbench_v2 (sample_cap=all, avg@1, pass@1, temp=1.00, top_p=0.95, max_tokens=16384, suite_elapsed=130s) -[2026-08-13 16:52:06,252] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [longbench_v2] clamping input budget 190000 -> 108135 tokens (max_model_len=131072, output=16384, margin=6553) -[2026-08-13 16:52:06,253] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: BEGIN items=503 n_samples=1 (avg@1/pass@1) temp=1.00 top_p=0.95 requests=503 workers=1 max_tokens=16384 timeout=3600.0s stream=True -[2026-08-13 16:52:40,576] [PID 12] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=be9fcfc652f67e5bbae60f96b9ef78af total=389348.2ms bytes=453861 finished=True finish=stop stop=None out_tok=1575 prompt_tok=123598 tps=4.0 tok_after_finish=0 repetitive=False capped=False -[2026-08-13 16:58:36,288] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 2/503 reqs (0.4%) sample_acc=0.500 fails=1 elapsed=390s rate=0.01/s eta=97704s ttft=82153ms tpot=115.4ms svc_tps=7 -[2026-08-13 17:01:44,991] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 5/503 reqs (1.0%) sample_acc=0.200 fails=3 elapsed=579s rate=0.01/s eta=57642s ttft=55648ms tpot=100.1ms svc_tps=8 -[2026-08-13 17:18:23,561] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 6/503 reqs (1.2%) sample_acc=0.167 fails=3 elapsed=1577s rate=0.00/s eta=130654s ttft=97630ms tpot=121.8ms svc_tps=6 -[2026-08-13 17:25:51,698] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 7/503 reqs (1.4%) sample_acc=0.286 fails=3 elapsed=2025s rate=0.00/s eta=143517s ttft=88729ms tpot=121.9ms svc_tps=6 -[2026-08-13 17:35:39,495] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 9/503 reqs (1.8%) sample_acc=0.222 fails=4 elapsed=2613s rate=0.00/s eta=143438s ttft=91191ms tpot=125.2ms svc_tps=6 -[2026-08-13 17:40:14,116] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 10/503 reqs (2.0%) sample_acc=0.300 fails=4 elapsed=2888s rate=0.00/s eta=142372s ttft=98143ms tpot=129.3ms svc_tps=6 -[2026-08-13 17:47:05,229] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 11/503 reqs (2.2%) sample_acc=0.364 fails=4 elapsed=3299s rate=0.00/s eta=147554s ttft=107663ms tpot=133.3ms svc_tps=6 -[2026-08-13 17:53:13,738] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 12/503 reqs (2.4%) sample_acc=0.417 fails=4 elapsed=3667s rate=0.00/s eta=150061s ttft=114759ms tpot=136.2ms svc_tps=5 -[2026-08-13 17:59:57,264] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 13/503 reqs (2.6%) sample_acc=0.385 fails=4 elapsed=4071s rate=0.00/s eta=153446s ttft=122499ms tpot=139.4ms svc_tps=5 -[2026-08-13 18:15:47,263] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 14/503 reqs (2.8%) sample_acc=0.357 fails=4 elapsed=5021s rate=0.00/s eta=175377s ttft=125138ms tpot=141.2ms svc_tps=5 -[2026-08-13 18:15:47,819] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 15/503 reqs (3.0%) sample_acc=0.333 fails=5 elapsed=5022s rate=0.00/s eta=163368s ttft=125138ms tpot=141.2ms svc_tps=5 -[2026-08-13 18:20:53,621] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 16/503 reqs (3.2%) sample_acc=0.312 fails=5 elapsed=5327s rate=0.00/s eta=162152s ttft=121754ms tpot=140.4ms svc_tps=5 -[2026-08-13 18:33:07,406] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 17/503 reqs (3.4%) sample_acc=0.353 fails=5 elapsed=6061s rate=0.00/s eta=173278s ttft=127337ms tpot=142.6ms svc_tps=5 -[2026-08-13 18:43:56,284] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 20/503 reqs (4.0%) sample_acc=0.300 fails=7 elapsed=6710s rate=0.00/s eta=162047s ttft=132308ms tpot=144.5ms svc_tps=5 -[2026-08-13 18:49:26,769] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 21/503 reqs (4.2%) sample_acc=0.286 fails=7 elapsed=7041s rate=0.00/s eta=161597s ttft=127761ms tpot=143.0ms svc_tps=5 -[2026-08-13 18:53:45,048] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 22/503 reqs (4.4%) sample_acc=0.318 fails=7 elapsed=7299s rate=0.00/s eta=159578s ttft=120694ms tpot=139.1ms svc_tps=5 -[2026-08-13 18:57:28,457] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 25/503 reqs (5.0%) sample_acc=0.320 fails=9 elapsed=7522s rate=0.00/s eta=143825s ttft=115300ms tpot=135.8ms svc_tps=5 -[2026-08-13 19:02:29,078] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 26/503 reqs (5.2%) sample_acc=0.346 fails=9 elapsed=7823s rate=0.00/s eta=143519s ttft=112351ms tpot=135.0ms svc_tps=6 -[2026-08-13 19:06:05,841] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 27/503 reqs (5.4%) sample_acc=0.333 fails=9 elapsed=8040s rate=0.00/s eta=141735s ttft=107520ms tpot=132.2ms svc_tps=6 -[2026-08-13 19:10:20,112] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 28/503 reqs (5.6%) sample_acc=0.357 fails=9 elapsed=8294s rate=0.00/s eta=140699s ttft=103320ms tpot=129.7ms svc_tps=6 -[2026-08-13 19:10:21,200] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 30/503 reqs (6.0%) sample_acc=0.333 fails=11 elapsed=8295s rate=0.00/s eta=130784s ttft=103320ms tpot=129.7ms svc_tps=6 -[2026-08-13 19:21:35,501] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 31/503 reqs (6.2%) sample_acc=0.323 fails=11 elapsed=8969s rate=0.00/s eta=136564s ttft=105123ms tpot=131.0ms svc_tps=6 -[2026-08-13 19:28:59,738] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 34/503 reqs (6.8%) sample_acc=0.294 fails=13 elapsed=9413s rate=0.00/s eta=129851s ttft=109412ms tpot=132.8ms svc_tps=6 -[2026-08-13 19:29:00,289] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 35/503 reqs (7.0%) sample_acc=0.286 fails=14 elapsed=9414s rate=0.00/s eta=125879s ttft=109412ms tpot=132.8ms svc_tps=6 -[2026-08-13 19:38:00,639] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 36/503 reqs (7.2%) sample_acc=0.306 fails=14 elapsed=9954s rate=0.00/s eta=129131s ttft=113306ms tpot=134.4ms svc_tps=6 -[2026-08-13 19:47:21,551] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 37/503 reqs (7.4%) sample_acc=0.297 fails=14 elapsed=10515s rate=0.00/s eta=132436s ttft=113523ms tpot=134.8ms svc_tps=6 -[2026-08-13 20:00:33,942] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 39/503 reqs (7.8%) sample_acc=0.282 fails=15 elapsed=11308s rate=0.00/s eta=134533s ttft=113144ms tpot=135.1ms svc_tps=6 -[2026-08-13 20:03:57,345] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 40/503 reqs (8.0%) sample_acc=0.300 fails=15 elapsed=11511s rate=0.00/s eta=133241s ttft=110174ms tpot=133.2ms svc_tps=6 -[2026-08-13 20:08:25,140] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 41/503 reqs (8.2%) sample_acc=0.293 fails=15 elapsed=11779s rate=0.00/s eta=132728s ttft=106673ms tpot=131.3ms svc_tps=6 -[2026-08-13 20:24:20,265] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 42/503 reqs (8.3%) sample_acc=0.286 fails=15 elapsed=12734s rate=0.00/s eta=139771s ttft=106992ms tpot=131.8ms svc_tps=6 -[2026-08-13 20:28:37,622] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 44/503 reqs (8.7%) sample_acc=0.273 fails=16 elapsed=12991s rate=0.00/s eta=135524s ttft=104197ms tpot=130.1ms svc_tps=6 -[2026-08-13 20:28:38,080] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 45/503 reqs (8.9%) sample_acc=0.267 fails=17 elapsed=12992s rate=0.00/s eta=132228s ttft=104197ms tpot=130.1ms svc_tps=6 -[2026-08-13 20:33:05,415] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 48/503 reqs (9.5%) sample_acc=0.250 fails=19 elapsed=13259s rate=0.00/s eta=125686s ttft=101823ms tpot=128.6ms svc_tps=6 -[2026-08-13 20:38:49,248] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 49/503 reqs (9.7%) sample_acc=0.265 fails=19 elapsed=13603s rate=0.00/s eta=126036s ttft=100565ms tpot=128.4ms svc_tps=6 -[2026-08-13 20:43:02,182] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 50/503 reqs (9.9%) sample_acc=0.260 fails=19 elapsed=13856s rate=0.00/s eta=125535s ttft=97929ms tpot=126.9ms svc_tps=6 -[2026-08-13 20:48:01,846] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 51/503 reqs (10.1%) sample_acc=0.275 fails=19 elapsed=14156s rate=0.00/s eta=125457s ttft=98639ms tpot=127.5ms svc_tps=6 -[2026-08-13 20:50:57,094] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 52/503 reqs (10.3%) sample_acc=0.288 fails=19 elapsed=14331s rate=0.00/s eta=124292s ttft=96432ms tpot=126.3ms svc_tps=6 -[2026-08-13 20:53:50,997] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 53/503 reqs (10.5%) sample_acc=0.302 fails=19 elapsed=14505s rate=0.00/s eta=123153s ttft=94688ms tpot=125.1ms svc_tps=6 -[2026-08-13 20:56:32,746] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 55/503 reqs (10.9%) sample_acc=0.291 fails=20 elapsed=14666s rate=0.00/s eta=119465s ttft=92655ms tpot=123.9ms svc_tps=6 -[2026-08-13 21:04:45,248] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 56/503 reqs (11.1%) sample_acc=0.304 fails=20 elapsed=15159s rate=0.00/s eta=121001s ttft=93266ms tpot=124.4ms svc_tps=6 -[2026-08-13 21:11:46,250] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 57/503 reqs (11.3%) sample_acc=0.316 fails=20 elapsed=15580s rate=0.00/s eta=121907s ttft=92966ms tpot=124.6ms svc_tps=6 -[2026-08-13 21:15:56,564] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 60/503 reqs (11.9%) sample_acc=0.317 fails=22 elapsed=15830s rate=0.00/s eta=116880s ttft=90923ms tpot=123.5ms svc_tps=6 -[2026-08-13 21:19:49,761] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 61/503 reqs (12.1%) sample_acc=0.328 fails=22 elapsed=16064s rate=0.00/s eta=116395s ttft=89805ms tpot=123.3ms svc_tps=6 -[2026-08-13 21:27:32,209] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 62/503 reqs (12.3%) sample_acc=0.339 fails=22 elapsed=16526s rate=0.00/s eta=117548s ttft=90889ms tpot=124.0ms svc_tps=6 -[2026-08-13 21:33:52,497] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 63/503 reqs (12.5%) sample_acc=0.333 fails=22 elapsed=16906s rate=0.00/s eta=118075s ttft=93258ms tpot=125.0ms svc_tps=6 -[2026-08-13 21:46:03,641] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 64/503 reqs (12.7%) sample_acc=0.328 fails=22 elapsed=17637s rate=0.00/s eta=120981s ttft=95121ms tpot=125.8ms svc_tps=6 -[2026-08-13 21:46:04,159] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 65/503 reqs (12.9%) sample_acc=0.323 fails=23 elapsed=17638s rate=0.00/s eta=118852s ttft=95121ms tpot=125.8ms svc_tps=6 -[2026-08-13 22:01:45,035] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 66/503 reqs (13.1%) sample_acc=0.333 fails=23 elapsed=18579s rate=0.00/s eta=123014s ttft=96757ms tpot=126.6ms svc_tps=6 -[2026-08-13 22:04:48,770] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 67/503 reqs (13.3%) sample_acc=0.343 fails=23 elapsed=18763s rate=0.00/s eta=122096s ttft=94981ms tpot=125.6ms svc_tps=6 -[2026-08-13 22:08:15,116] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 68/503 reqs (13.5%) sample_acc=0.353 fails=23 elapsed=18969s rate=0.00/s eta=121345s ttft=93431ms tpot=124.8ms svc_tps=6 -[2026-08-13 22:08:16,082] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 70/503 reqs (13.9%) sample_acc=0.343 fails=25 elapsed=18970s rate=0.00/s eta=117342s ttft=93431ms tpot=124.8ms svc_tps=6 -[2026-08-13 22:20:04,226] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 71/503 reqs (14.1%) sample_acc=0.352 fails=25 elapsed=19678s rate=0.00/s eta=119731s ttft=95379ms tpot=125.6ms svc_tps=6 -[2026-08-13 22:27:10,386] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 73/503 reqs (14.5%) sample_acc=0.356 fails=26 elapsed=20104s rate=0.00/s eta=118422s ttft=96089ms tpot=126.1ms svc_tps=6 -[2026-08-13 22:32:22,702] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 74/503 reqs (14.7%) sample_acc=0.351 fails=26 elapsed=20416s rate=0.00/s eta=118360s ttft=98020ms tpot=126.9ms svc_tps=6 -[2026-08-13 22:46:13,675] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 75/503 reqs (14.9%) sample_acc=0.347 fails=26 elapsed=21247s rate=0.00/s eta=121252s ttft=99438ms tpot=127.6ms svc_tps=6 -[2026-08-13 22:49:13,920] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 76/503 reqs (15.1%) sample_acc=0.355 fails=26 elapsed=21428s rate=0.00/s eta=120390s ttft=97941ms tpot=126.7ms svc_tps=6 -[2026-08-13 22:59:32,237] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 77/503 reqs (15.3%) sample_acc=0.351 fails=26 elapsed=22046s rate=0.00/s eta=121969s ttft=99807ms tpot=127.5ms svc_tps=6 -[2026-08-13 23:04:12,501] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 78/503 reqs (15.5%) sample_acc=0.346 fails=26 elapsed=22326s rate=0.00/s eta=121649s ttft=98242ms tpot=126.7ms svc_tps=6 -[2026-08-13 23:12:43,229] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 79/503 reqs (15.7%) sample_acc=0.342 fails=26 elapsed=22837s rate=0.00/s eta=122568s ttft=99470ms tpot=127.3ms svc_tps=6 -[2026-08-13 23:16:07,326] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 80/503 reqs (15.9%) sample_acc=0.350 fails=26 elapsed=23041s rate=0.00/s eta=121830s ttft=97948ms tpot=126.5ms svc_tps=6 -[2026-08-13 23:20:33,966] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 81/503 reqs (16.1%) sample_acc=0.358 fails=26 elapsed=23308s rate=0.00/s eta=121430s ttft=96801ms tpot=125.7ms svc_tps=6 -[2026-08-13 23:24:39,684] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 82/503 reqs (16.3%) sample_acc=0.366 fails=26 elapsed=23553s rate=0.00/s eta=120927s ttft=95786ms tpot=125.4ms svc_tps=6 -[2026-08-13 23:36:10,033] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 84/503 reqs (16.7%) sample_acc=0.357 fails=27 elapsed=24244s rate=0.00/s eta=120930s ttft=96997ms tpot=126.0ms svc_tps=6 -[2026-08-13 23:44:40,079] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 85/503 reqs (16.9%) sample_acc=0.365 fails=27 elapsed=24754s rate=0.00/s eta=121731s ttft=98643ms tpot=126.7ms svc_tps=6 -[2026-08-14 00:01:19,982] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 86/503 reqs (17.1%) sample_acc=0.360 fails=27 elapsed=25754s rate=0.00/s eta=124876s ttft=99869ms tpot=127.3ms svc_tps=6 -[2026-08-14 00:07:14,569] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 87/503 reqs (17.3%) sample_acc=0.368 fails=27 elapsed=26108s rate=0.00/s eta=124840s ttft=98835ms tpot=126.6ms svc_tps=6 -[2026-08-14 00:10:25,874] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 88/503 reqs (17.5%) sample_acc=0.364 fails=27 elapsed=26300s rate=0.00/s eta=124027s ttft=97762ms tpot=125.9ms svc_tps=6 -[2026-08-14 00:14:54,878] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 89/503 reqs (17.7%) sample_acc=0.360 fails=27 elapsed=26569s rate=0.00/s eta=123589s ttft=97155ms tpot=125.8ms svc_tps=6 -[2026-08-14 00:29:56,962] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 90/503 reqs (17.9%) sample_acc=0.367 fails=27 elapsed=27471s rate=0.00/s eta=126060s ttft=98352ms tpot=126.4ms svc_tps=6 -[2026-08-14 00:33:38,547] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 91/503 reqs (18.1%) sample_acc=0.363 fails=27 elapsed=27692s rate=0.00/s eta=125376s ttft=97418ms tpot=125.8ms svc_tps=6 -[2026-08-14 00:37:02,753] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 92/503 reqs (18.3%) sample_acc=0.370 fails=27 elapsed=27897s rate=0.00/s eta=124625s ttft=96284ms tpot=125.1ms svc_tps=6 -[2026-08-14 00:40:43,166] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 93/503 reqs (18.5%) sample_acc=0.376 fails=27 elapsed=28117s rate=0.00/s eta=123956s ttft=95336ms tpot=124.5ms svc_tps=6 -[2026-08-14 00:40:44,129] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 95/503 reqs (18.9%) sample_acc=0.368 fails=29 elapsed=28118s rate=0.00/s eta=120759s ttft=95336ms tpot=124.5ms svc_tps=6 -[2026-08-14 00:43:31,565] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 96/503 reqs (19.1%) sample_acc=0.375 fails=29 elapsed=28285s rate=0.00/s eta=119918s ttft=94193ms tpot=123.9ms svc_tps=6 -[2026-08-14 00:52:12,233] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 98/503 reqs (19.5%) sample_acc=0.378 fails=30 elapsed=28806s rate=0.00/s eta=119045s ttft=93492ms tpot=123.8ms svc_tps=6 -[2026-08-14 01:02:08,126] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 99/503 reqs (19.7%) sample_acc=0.384 fails=30 elapsed=29402s rate=0.00/s eta=119983s ttft=94967ms tpot=124.4ms svc_tps=6 -[2026-08-14 01:16:21,549] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 100/503 reqs (19.9%) sample_acc=0.390 fails=30 elapsed=30255s rate=0.00/s eta=121929s ttft=96380ms tpot=125.1ms svc_tps=6 -[2026-08-14 01:23:12,304] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 101/503 reqs (20.1%) sample_acc=0.386 fails=30 elapsed=30666s rate=0.00/s eta=122057s ttft=96099ms tpot=125.1ms svc_tps=6 -[2026-08-14 01:34:04,886] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 102/503 reqs (20.3%) sample_acc=0.382 fails=30 elapsed=31319s rate=0.00/s eta=123125s ttft=97394ms tpot=125.7ms svc_tps=6 -[2026-08-14 01:42:58,231] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 103/503 reqs (20.5%) sample_acc=0.379 fails=30 elapsed=31852s rate=0.00/s eta=123697s ttft=98327ms tpot=126.2ms svc_tps=6 -[2026-08-14 01:56:29,298] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 104/503 reqs (20.7%) sample_acc=0.375 fails=30 elapsed=32663s rate=0.00/s eta=125313s ttft=98208ms tpot=126.3ms svc_tps=6 -[2026-08-14 01:56:29,845] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 105/503 reqs (20.9%) sample_acc=0.371 fails=31 elapsed=32664s rate=0.00/s eta=123811s ttft=98208ms tpot=126.3ms svc_tps=6 -[2026-08-14 02:01:39,021] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 106/503 reqs (21.1%) sample_acc=0.368 fails=31 elapsed=32973s rate=0.00/s eta=123492s ttft=97505ms tpot=126.1ms svc_tps=6 -[2026-08-14 02:11:07,533] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 107/503 reqs (21.3%) sample_acc=0.364 fails=31 elapsed=33541s rate=0.00/s eta=124134s ttft=98076ms tpot=126.4ms svc_tps=6 -[2026-08-14 02:18:12,581] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 109/503 reqs (21.7%) sample_acc=0.367 fails=32 elapsed=33966s rate=0.00/s eta=122777s ttft=99215ms tpot=126.9ms svc_tps=6 -[2026-08-14 02:28:48,920] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 110/503 reqs (21.9%) sample_acc=0.364 fails=32 elapsed=34603s rate=0.00/s eta=123626s ttft=100097ms tpot=127.4ms svc_tps=6 -[2026-08-14 02:35:30,842] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 111/503 reqs (22.1%) sample_acc=0.369 fails=32 elapsed=35005s rate=0.00/s eta=123620s ttft=99606ms tpot=127.3ms svc_tps=6 -[2026-08-14 02:48:16,564] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 112/503 reqs (22.3%) sample_acc=0.366 fails=32 elapsed=35770s rate=0.00/s eta=124877s ttft=100716ms tpot=127.8ms svc_tps=6 -[2026-08-14 02:52:09,330] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 113/503 reqs (22.5%) sample_acc=0.372 fails=32 elapsed=36003s rate=0.00/s eta=124258s ttft=99658ms tpot=127.2ms svc_tps=6 -[2026-08-14 03:02:22,102] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 115/503 reqs (22.9%) sample_acc=0.374 fails=33 elapsed=36616s rate=0.00/s eta=123539s ttft=100777ms tpot=127.7ms svc_tps=6 -[2026-08-14 03:11:48,383] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 116/503 reqs (23.1%) sample_acc=0.379 fails=33 elapsed=37182s rate=0.00/s eta=124047s ttft=101832ms tpot=128.1ms svc_tps=6 -[2026-08-14 03:15:37,931] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 118/503 reqs (23.5%) sample_acc=0.381 fails=34 elapsed=37412s rate=0.00/s eta=122064s ttft=101283ms tpot=128.0ms svc_tps=6 -[2026-08-14 03:24:00,963] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 119/503 reqs (23.7%) sample_acc=0.378 fails=34 elapsed=37915s rate=0.00/s eta=122347s ttft=101769ms tpot=128.3ms svc_tps=6 -[2026-08-14 03:30:37,995] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 120/503 reqs (23.9%) sample_acc=0.383 fails=34 elapsed=38312s rate=0.00/s eta=122278s ttft=100873ms tpot=127.8ms svc_tps=6 -[2026-08-14 03:40:03,986] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 121/503 reqs (24.1%) sample_acc=0.388 fails=34 elapsed=38878s rate=0.00/s eta=122738s ttft=101830ms tpot=128.2ms svc_tps=6 -[2026-08-14 03:42:43,178] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 123/503 reqs (24.5%) sample_acc=0.390 fails=35 elapsed=39037s rate=0.00/s eta=120602s ttft=100948ms tpot=127.7ms svc_tps=6 -[2026-08-14 03:42:44,275] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 125/503 reqs (24.9%) sample_acc=0.384 fails=37 elapsed=39038s rate=0.00/s eta=118051s ttft=100948ms tpot=127.7ms svc_tps=6 -[2026-08-14 03:49:52,516] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 126/503 reqs (25.0%) sample_acc=0.381 fails=37 elapsed=39466s rate=0.00/s eta=118086s ttft=101007ms tpot=127.9ms svc_tps=6 -[2026-08-14 03:55:05,561] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 127/503 reqs (25.2%) sample_acc=0.386 fails=37 elapsed=39779s rate=0.00/s eta=117772s ttft=102002ms tpot=128.3ms svc_tps=6 -[2026-08-14 04:01:26,562] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 129/503 reqs (25.6%) sample_acc=0.380 fails=38 elapsed=40160s rate=0.00/s eta=116434s ttft=102563ms tpot=128.6ms svc_tps=6 -[2026-08-14 04:01:27,112] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 130/503 reqs (25.8%) sample_acc=0.377 fails=39 elapsed=40161s rate=0.00/s eta=115231s ttft=102563ms tpot=128.6ms svc_tps=6 -[2026-08-14 04:08:31,705] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 131/503 reqs (26.0%) sample_acc=0.382 fails=39 elapsed=40585s rate=0.00/s eta=115250s ttft=103492ms tpot=129.0ms svc_tps=6 -[2026-08-14 04:14:59,080] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 132/503 reqs (26.2%) sample_acc=0.386 fails=39 elapsed=40973s rate=0.00/s eta=115158s ttft=104166ms tpot=129.3ms svc_tps=6 -[2026-08-14 04:19:06,306] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 134/503 reqs (26.6%) sample_acc=0.388 fails=40 elapsed=41220s rate=0.00/s eta=113509s ttft=103686ms tpot=129.2ms svc_tps=6 -[2026-08-14 04:25:45,218] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 135/503 reqs (26.8%) sample_acc=0.385 fails=40 elapsed=41619s rate=0.00/s eta=113450s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:40,924] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 137/503 reqs (27.2%) sample_acc=0.380 fails=42 elapsed=41855s rate=0.00/s eta=111816s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:41,257] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 140/503 reqs (27.8%) sample_acc=0.371 fails=45 elapsed=41855s rate=0.00/s eta=108524s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:43,789] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 145/503 reqs (28.8%) sample_acc=0.359 fails=50 elapsed=41858s rate=0.00/s eta=103345s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:44,397] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 150/503 reqs (29.8%) sample_acc=0.347 fails=55 elapsed=41858s rate=0.00/s eta=98506s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:44,730] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 155/503 reqs (30.8%) sample_acc=0.335 fails=60 elapsed=41858s rate=0.00/s eta=93979s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:45,536] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 160/503 reqs (31.8%) sample_acc=0.325 fails=65 elapsed=41859s rate=0.00/s eta=89736s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:45,709] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 165/503 reqs (32.8%) sample_acc=0.315 fails=70 elapsed=41859s rate=0.00/s eta=85748s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:45,995] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 170/503 reqs (33.8%) sample_acc=0.306 fails=75 elapsed=41860s rate=0.00/s eta=81996s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:46,273] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 175/503 reqs (34.8%) sample_acc=0.297 fails=80 elapsed=41860s rate=0.00/s eta=78458s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:46,566] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 180/503 reqs (35.8%) sample_acc=0.289 fails=85 elapsed=41860s rate=0.00/s eta=75116s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:46,868] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 185/503 reqs (36.8%) sample_acc=0.281 fails=90 elapsed=41861s rate=0.00/s eta=71955s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:47,087] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 190/503 reqs (37.8%) sample_acc=0.274 fails=95 elapsed=41861s rate=0.00/s eta=68960s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:47,844] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 195/503 reqs (38.8%) sample_acc=0.267 fails=100 elapsed=41862s rate=0.00/s eta=66120s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:48,216] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 200/503 reqs (39.8%) sample_acc=0.260 fails=105 elapsed=41862s rate=0.00/s eta=63421s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:48,409] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 205/503 reqs (40.8%) sample_acc=0.254 fails=110 elapsed=41862s rate=0.00/s eta=60853s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:48,665] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 210/503 reqs (41.7%) sample_acc=0.248 fails=115 elapsed=41862s rate=0.01/s eta=58408s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:49,042] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 215/503 reqs (42.7%) sample_acc=0.242 fails=120 elapsed=41863s rate=0.01/s eta=56077s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:49,445] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 220/503 reqs (43.7%) sample_acc=0.236 fails=125 elapsed=41863s rate=0.01/s eta=53851s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:50,447] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 225/503 reqs (44.7%) sample_acc=0.231 fails=130 elapsed=41864s rate=0.01/s eta=51726s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:50,738] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 230/503 reqs (45.7%) sample_acc=0.226 fails=135 elapsed=41864s rate=0.01/s eta=49691s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:51,060] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 235/503 reqs (46.7%) sample_acc=0.221 fails=140 elapsed=41865s rate=0.01/s eta=47744s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:51,147] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 240/503 reqs (47.7%) sample_acc=0.217 fails=145 elapsed=41865s rate=0.01/s eta=45877s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:51,343] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 245/503 reqs (48.7%) sample_acc=0.212 fails=150 elapsed=41865s rate=0.01/s eta=44087s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:51,525] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 250/503 reqs (49.7%) sample_acc=0.208 fails=155 elapsed=41865s rate=0.01/s eta=42368s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:52,197] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 255/503 reqs (50.7%) sample_acc=0.204 fails=160 elapsed=41866s rate=0.01/s eta=40717s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:52,347] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 260/503 reqs (51.7%) sample_acc=0.200 fails=165 elapsed=41866s rate=0.01/s eta=39129s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:55,395] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 265/503 reqs (52.7%) sample_acc=0.196 fails=170 elapsed=41869s rate=0.01/s eta=37603s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:55,564] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 270/503 reqs (53.7%) sample_acc=0.193 fails=175 elapsed=41869s rate=0.01/s eta=36132s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:55,885] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 275/503 reqs (54.7%) sample_acc=0.189 fails=180 elapsed=41870s rate=0.01/s eta=34714s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:56,158] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 280/503 reqs (55.7%) sample_acc=0.186 fails=185 elapsed=41870s rate=0.01/s eta=33346s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:56,575] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 285/503 reqs (56.7%) sample_acc=0.182 fails=190 elapsed=41870s rate=0.01/s eta=32027s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:56,711] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 290/503 reqs (57.7%) sample_acc=0.179 fails=195 elapsed=41870s rate=0.01/s eta=30753s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:56,821] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 295/503 reqs (58.6%) sample_acc=0.176 fails=200 elapsed=41871s rate=0.01/s eta=29522s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:57,096] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 300/503 reqs (59.6%) sample_acc=0.173 fails=205 elapsed=41871s rate=0.01/s eta=28333s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:57,324] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 305/503 reqs (60.6%) sample_acc=0.170 fails=210 elapsed=41871s rate=0.01/s eta=27182s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:57,748] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 310/503 reqs (61.6%) sample_acc=0.168 fails=215 elapsed=41871s rate=0.01/s eta=26068s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:57,917] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 315/503 reqs (62.6%) sample_acc=0.165 fails=220 elapsed=41872s rate=0.01/s eta=24990s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:58,718] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 320/503 reqs (63.6%) sample_acc=0.163 fails=225 elapsed=41872s rate=0.01/s eta=23946s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:58,930] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 325/503 reqs (64.6%) sample_acc=0.160 fails=230 elapsed=41873s rate=0.01/s eta=22933s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:59,431] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 330/503 reqs (65.6%) sample_acc=0.158 fails=235 elapsed=41873s rate=0.01/s eta=21952s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:29:59,680] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 335/503 reqs (66.6%) sample_acc=0.155 fails=240 elapsed=41873s rate=0.01/s eta=20999s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:00,643] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 340/503 reqs (67.6%) sample_acc=0.153 fails=245 elapsed=41874s rate=0.01/s eta=20075s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:00,874] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 345/503 reqs (68.6%) sample_acc=0.151 fails=250 elapsed=41875s rate=0.01/s eta=19177s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:01,485] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 350/503 reqs (69.6%) sample_acc=0.149 fails=255 elapsed=41875s rate=0.01/s eta=18305s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:01,924] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 355/503 reqs (70.6%) sample_acc=0.146 fails=260 elapsed=41876s rate=0.01/s eta=17458s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:02,936] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 360/503 reqs (71.6%) sample_acc=0.144 fails=265 elapsed=41877s rate=0.01/s eta=16634s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:03,245] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 365/503 reqs (72.6%) sample_acc=0.142 fails=270 elapsed=41877s rate=0.01/s eta=15833s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:06,002] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 370/503 reqs (73.6%) sample_acc=0.141 fails=275 elapsed=41880s rate=0.01/s eta=15054s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:08,439] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 375/503 reqs (74.6%) sample_acc=0.139 fails=280 elapsed=41882s rate=0.01/s eta=14296s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:08,603] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 380/503 reqs (75.5%) sample_acc=0.137 fails=285 elapsed=41882s rate=0.01/s eta=13557s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:08,877] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 385/503 reqs (76.5%) sample_acc=0.135 fails=290 elapsed=41883s rate=0.01/s eta=12837s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:09,145] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 390/503 reqs (77.5%) sample_acc=0.133 fails=295 elapsed=41883s rate=0.01/s eta=12135s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:09,879] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 395/503 reqs (78.5%) sample_acc=0.132 fails=300 elapsed=41884s rate=0.01/s eta=11452s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:10,404] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 400/503 reqs (79.5%) sample_acc=0.130 fails=305 elapsed=41884s rate=0.01/s eta=10785s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:10,545] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 405/503 reqs (80.5%) sample_acc=0.128 fails=310 elapsed=41884s rate=0.01/s eta=10135s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:11,612] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 410/503 reqs (81.5%) sample_acc=0.127 fails=315 elapsed=41885s rate=0.01/s eta=9501s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:11,925] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 415/503 reqs (82.5%) sample_acc=0.125 fails=320 elapsed=41886s rate=0.01/s eta=8882s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:13,144] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 420/503 reqs (83.5%) sample_acc=0.124 fails=325 elapsed=41887s rate=0.01/s eta=8278s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:13,521] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 425/503 reqs (84.5%) sample_acc=0.122 fails=330 elapsed=41887s rate=0.01/s eta=7688s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:14,613] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 430/503 reqs (85.5%) sample_acc=0.121 fails=335 elapsed=41888s rate=0.01/s eta=7111s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:14,845] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 435/503 reqs (86.5%) sample_acc=0.120 fails=340 elapsed=41889s rate=0.01/s eta=6548s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:15,586] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 440/503 reqs (87.5%) sample_acc=0.118 fails=345 elapsed=41889s rate=0.01/s eta=5998s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:15,806] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 445/503 reqs (88.5%) sample_acc=0.117 fails=350 elapsed=41890s rate=0.01/s eta=5460s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:17,509] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 450/503 reqs (89.5%) sample_acc=0.116 fails=355 elapsed=41891s rate=0.01/s eta=4934s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:19,215] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 455/503 reqs (90.5%) sample_acc=0.114 fails=360 elapsed=41893s rate=0.01/s eta=4419s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:19,537] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 460/503 reqs (91.5%) sample_acc=0.113 fails=365 elapsed=41893s rate=0.01/s eta=3916s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:19,873] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 465/503 reqs (92.4%) sample_acc=0.112 fails=370 elapsed=41894s rate=0.01/s eta=3424s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:20,172] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 470/503 reqs (93.4%) sample_acc=0.111 fails=375 elapsed=41894s rate=0.01/s eta=2941s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:21,351] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 475/503 reqs (94.4%) sample_acc=0.109 fails=380 elapsed=41895s rate=0.01/s eta=2470s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:21,522] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 480/503 reqs (95.4%) sample_acc=0.108 fails=385 elapsed=41895s rate=0.01/s eta=2007s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:21,711] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 485/503 reqs (96.4%) sample_acc=0.107 fails=390 elapsed=41895s rate=0.01/s eta=1555s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:22,642] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 490/503 reqs (97.4%) sample_acc=0.106 fails=395 elapsed=41896s rate=0.01/s eta=1112s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:22,907] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 495/503 reqs (98.4%) sample_acc=0.105 fails=400 elapsed=41897s rate=0.01/s eta=677s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:23,234] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 500/503 reqs (99.4%) sample_acc=0.104 fails=405 elapsed=41897s rate=0.01/s eta=251s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:23,400] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: 503/503 reqs (100.0%) sample_acc=0.103 fails=408 elapsed=41897s rate=0.01/s eta=0s ttft=104617ms tpot=129.6ms svc_tps=6 -[2026-08-14 04:30:23,400] [PID 12] [Thread-4] [/app/utils/logger.py] [WARNING] [academic] longbench_v2: 408 requests failed during inference (sample: ['HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 134082 tokens (117698 in the messages, 16384 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 133027 tokens (116643 in the messages, 16384 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}', 'HTTPError: 400 Bad Request for http://172.28.22.18:43325/v1/chat/completions: {"object":"error","message":"This model\'s maximum context length is 131072 tokens. However, you requested 135713 tokens (119329 in the messages, 16384 in the completion). Please reduce the length of the messages or completion.","type":"BadRequestError","param":null,"code":400}']) -[2026-08-14 04:30:23,401] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2: avg@1=0.1034 pass@1=0.1034 (items=503, samples=503, correct_samples=52) in 41897.1s -[2026-08-14 04:30:23,401] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2 sample item=0 correct=False response='' -[2026-08-14 04:30:23,401] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2 sample item=1 correct=True response=' The correct answer is (D)' -[2026-08-14 04:30:23,401] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [academic] longbench_v2 sample item=2 correct=False response='' -[2026-08-14 04:30:23,402] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [longbench_v2] by_difficulty={'easy': 0.6785714285714286, 'hard': 0.4925373134328358} by_length={'short': 0.6739130434782609, 'medium': 0.3333333333333333, 'long': 0.625} -[2026-08-14 04:30:23,402] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] <<< benchmark 5/5: longbench_v2 done score=0.1034 took=41900s -[2026-08-14 04:30:23,402] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] generation perf — ttft_mean=104617ms tpot_mean=130ms service_tps=6 gen_tokens=241534 -[2026-08-14 04:30:23,402] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] PASSED — scores: {'aime2025': 0.0, 'gpqa_diamond': 0.0, 'hle': 0.0, 'simpleqa': 0.0, 'longbench_v2': 0.10337972166998012} -[2026-08-14 04:30:23,403] [PID 12] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass] scores={'aime2025': 0.0, 'gpqa_diamond': 0.0, 'hle': 0.0, 'simpleqa': 0.0, 'longbench_v2': 0.10337972166998012} avg=0.021 -[2026-08-14 04:30:35,291] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 module opencompass done — passed=False score=0.0000 -[2026-08-14 04:30:35,734] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Submission 694 finished — passed=False score=26028.00598 modules_run=4 -[2026-08-14 04:30:46,365] [PID 12] [Thread-4] [app.queue.jobs] [INFO] Keeping output dir for submission 694 (run had failures): /tmp/perfbench_submission_694_4hv5__9n - diff --git a/sub791rizhi.txt b/sub791rizhi.txt new file mode 100644 index 00000000..924b91bf --- /dev/null +++ b/sub791rizhi.txt @@ -0,0 +1,2548 @@ +===== submission 791 attempt 1/3 ===== +[2026-08-21 09:14:15,860] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 started — model=llm endpoint=http://172.28.22.18:38879 benchmark_id=44 module=None +[2026-08-21 09:14:15,870] [PID 14] [Thread-4] [root] [INFO] guidellm report Path: /app/ui/index.html +[2026-08-21 09:14:15,889] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 starting module functional_acceptance (bm_id=102 order=0) +[2026-08-21 09:14:28,078] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module functional_acceptance: concurrency_override=1 requested but this module has no concurrency-equivalent param — not applied. +[2026-08-21 09:14:28,079] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] skip_tests: 4 check(s) will be skipped (recorded SKIP): d08_image_url_blocked, t11a_no_auth, t11b_wrong_auth, t16b_missing_content +[2026-08-21 09:14:28,086] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] backend_style=auto → resolved=direct (native endpoint /version → 200 (vLLM)) +[2026-08-21 09:14:58,599] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] thinking probe: chat_template_kwargs.enable_thinking zeroes reasoning on llm — using it for all thinking conversions +[2026-08-21 09:14:58,599] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] multimodal=on → resolved=on (explicit override) +[2026-08-21 09:15:11,399] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d01_basic_nostream — content[11] reasoning[420] tok=139 (12.80s) +[2026-08-21 09:15:16,533] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d02_stream_usage — chunks=53 done=1 usage=52 (5.13s) +[2026-08-21 09:15:22,812] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d03_tool_call — tool=get_weather args="{'city': 'Beijing'}" finish=tool_calls (tool_choice=auto) (6.28s) +[2026-08-21 09:15:57,873] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d04_reasoning — content[213] reasoning[957] (35.06s) +[2026-08-21 09:16:34,676] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d05_multimodal — content[37]='\n\nThe image is a solid **red** color.' (36.80s) +[2026-08-21 09:16:49,598] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d06_cache_hit — 1st(pt=2576,cached=0) 2nd(pt=2576,cached=2560) (9.92s) +[2026-08-21 09:18:40,511] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d07_reasoning_plus_content — reasoning[3143] content[1076] (110.91s) +[2026-08-21 09:18:45,792] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] d08_image_url_blocked skipped by config (skip_tests); computed PASS discarded +[2026-08-21 09:18:45,792] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP d08_image_url_blocked — skipped by config (skip_tests) (5.28s) +[2026-08-21 09:18:47,917] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d09_thinking_disable_top — reasoning[0] content='4' finish=stop (converted to chat_template_kwargs for direct backend) (2.12s) +[2026-08-21 09:18:49,007] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS d10_thinking_disable_ctk — reasoning[0] content='4' finish=stop (chat_template_kwargs) (1.09s) +[2026-08-21 09:19:06,460] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1a_thinking_true — HTTP 200 reasoning[635] (expect >0) (17.45s) +[2026-08-21 09:19:08,354] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1b_thinking_false — HTTP 200 reasoning[0] (expect =0) (1.89s) +[2026-08-21 09:19:23,418] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t1c_thinking_default — HTTP 200 reasoning[516] (expect >0, default on) (15.06s) +[2026-08-21 09:19:26,153] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_0_0 — HTTP 200 (2.74s) +[2026-08-21 09:19:28,882] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_1_0 — HTTP 200 (2.73s) +[2026-08-21 09:19:31,611] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_1_1 — HTTP 200 (2.73s) +[2026-08-21 09:19:34,338] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_temperature_2_0 — HTTP 200 (2.73s) +[2026-08-21 09:19:34,468] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_0 — HTTP 400 (direct: accept 2xx or 4xx) (0.13s) +[2026-08-21 09:19:37,195] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_01 — HTTP 200 (2.73s) +[2026-08-21 09:19:39,950] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_0_95 — HTTP 200 (2.75s) +[2026-08-21 09:19:42,677] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_1_0 — HTTP 200 (2.73s) +[2026-08-21 09:19:42,810] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_top_p_1_1 — HTTP 400 (expect 4xx) (0.13s) +[2026-08-21 09:19:45,536] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_neg2 — HTTP 200 (2.73s) +[2026-08-21 09:19:48,263] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_0 — HTTP 200 (2.73s) +[2026-08-21 09:19:50,995] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_frequency_penalty_2 — HTTP 200 (2.73s) +[2026-08-21 09:19:53,730] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_neg2 — HTTP 200 (2.73s) +[2026-08-21 09:19:56,461] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_0 — HTTP 200 (2.73s) +[2026-08-21 09:19:59,188] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_presence_penalty_2 — HTTP 200 (2.73s) +[2026-08-21 09:20:01,922] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t2_n_1 — HTTP 200 (2.73s) +[2026-08-21 09:20:01,925] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t2_n_2 — HTTP 400 (0.00s) +[2026-08-21 09:25:02,023] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t3_max_tokens_none — HTTP -1 finish= (300.10s) +[2026-08-21 09:25:03,418] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_1 — HTTP 200 finish=length (1.39s) +[2026-08-21 09:25:09,919] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_64 — HTTP 200 finish=length (6.50s) +[2026-08-21 09:28:37,721] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_mid — HTTP 200 finish=stop (207.80s) +[2026-08-21 09:31:39,804] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_max — HTTP 200 finish=stop (182.08s) +[2026-08-21 09:31:39,938] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_neg1 — HTTP 400 (expect 4xx) (0.13s) +[2026-08-21 09:31:40,067] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t3_max_tokens_over — HTTP 400 (expect 4xx) (0.13s) +[2026-08-21 09:31:42,231] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t4a_no_system — HTTP 200 content='_NO_SYSTEM' reasoning[0] (2.16s) +[2026-08-21 09:31:44,539] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t4b_system_control — HTTP 200 content='_SYSTEM_CONTROL' reasoning[0] (2.31s) +[2026-08-21 09:31:47,770] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t5_function_calling — tool=get_weather args="{'city': 'Beijing'}" finish=tool_calls (tool_choice=auto) (3.23s) +[2026-08-21 09:31:50,775] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t6_multi_turn — HTTP 200 reply='BLUE_42' reasoning[0] (3.00s) +[2026-08-21 09:31:59,034] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t7_streaming_sse — HTTP 200 chunks=83 done=1 usage=82 (8.26s) +[2026-08-21 09:32:48,720] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t8_json_object — parsed={'name': 'Alice', 'age': 30} (49.69s) +[2026-08-21 09:32:55,052] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t9_json_schema — parsed={'name': 'Alice', 'age': 30} (6.33s) +[2026-08-21 09:33:00,108] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t10_stop_word — HTTP 200 content='1 2 3 4 5 6 7 8 9 10 11 12 13 14 ' finish=stop (5.06s) +[2026-08-21 09:33:01,614] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t11a_no_auth — skipped by config (skip_tests) (0.00s) +[2026-08-21 09:33:01,614] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t11b_wrong_auth — skipped by config (skip_tests) (0.00s) +[2026-08-21 09:33:04,140] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_chinese — HTTP 200 content="'中文测试：你好世界'" reasoning[0] (2.53s) +[2026-08-21 09:33:06,410] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_japanese — HTTP 200 content="'日本語: こんにちは'" reasoning[0] (2.27s) +[2026-08-21 09:33:09,917] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t12_emoji — HTTP 200 content='Emoji: 🎉🚀✨🇨🇳' reasoning[0] (3.51s) +[2026-08-21 09:38:10,267] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] t13 quadrant image: HTTP -1 missing=['red', 'green', 'blue', 'yellow'] content='' reasoning='' +[2026-08-21 09:38:10,267] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✗ FAIL t13_multimodal_base64 — HTTP -1 missing=['red', 'green', 'blue', 'yellow'] content='' (300.09s) +[2026-08-21 09:38:10,270] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t14_empty_body — HTTP 400 (expect 4xx) (0.00s) +[2026-08-21 09:39:20,231] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t15_idempotency_seed — call1='Hello' call2='Hello' (69.96s) +[2026-08-21 09:39:20,234] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t16a_missing_role — HTTP 400 (expect 4xx) (0.00s) +[2026-08-21 09:39:20,237] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [functional] t16b_missing_content skipped by config (skip_tests); computed PASS discarded +[2026-08-21 09:39:20,237] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] - SKIP t16b_missing_content — skipped by config (skip_tests) (0.00s) +[2026-08-21 09:39:20,239] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional] ✓ PASS t16c_empty_messages — HTTP 400 (expect 4xx) (0.00s) +[2026-08-21 09:39:20,240] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [functional_acceptance] pass_rate=0.942 passed=49 failed=3 skipped=4 failed_keys=['t2_n_2', 't3_max_tokens_none', 't13_multimodal_base64'] +[2026-08-21 09:39:23,100] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module functional_acceptance done — passed=False score=0.9423 +[2026-08-21 09:39:23,137] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 starting module case_truncation (bm_id=103 order=1) +[2026-08-21 09:39:23,249] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module case_truncation: CONCURRENCY OVERRIDE concurrency=4 -> 1. +[2026-08-21 09:39:24,906] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [long_output_truncation] Starting 1 concurrent requests (max_tokens=8192) +[2026-08-21 09:50:52,800] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [long_output_truncation] PASSED — avg_output_tokens=8192, elapsed=687.9s +[2026-08-21 09:50:52,801] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [case_truncation] truncation_rate=0.0 completion_ratio=1.0 +[2026-08-21 09:50:53,896] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module case_truncation done — passed=True score=1.0000 +[2026-08-21 09:51:03,608] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 starting module replay_tencent (bm_id=104 order=2) +[2026-08-21 09:51:09,210] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module replay_tencent: CONCURRENCY OVERRIDE concurrency=8 -> 1. +[2026-08-21 09:51:14,080] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Replaying 881 requests, concurrency=1 +[2026-08-21 09:51:14,080] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] SAVING per-request request/response capture to /tmp/perfbench_submission_791_v_1ac8s4/replay_tencent_104/replay_responses.jsonl (<=65536 raw bytes each; REPLAY_SAVE_RESPONSES_MAX_BYTES=0 for full). Inspect with: kubectl exec -- cat /tmp/perfbench_submission_791_v_1ac8s4/replay_tencent_104/replay_responses.jsonl +[2026-08-21 09:51:18,959] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] tool-support preflight OK (HTTP 200); 690/881 scanned records carry tool messages. +[2026-08-21 09:51:18,959] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] BEGIN batch total=881 concurrency=1 window=4 url=http://172.28.22.18:38879/v1/chat/completions +[2026-08-21 09:51:18,967] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a58f13fba3a7932488e00d79515e12dd attempt=1 +[2026-08-21 09:51:18,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a58f13fba3a7932488e00d79515e12dd status=400 post_dur=0.003s +[2026-08-21 09:51:18,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a58f13fba3a7932488e00d79515e12dd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 09:51:18,982] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6a84efa4064631019cccbcc326d46012 attempt=1 +[2026-08-21 09:51:18,985] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6a84efa4064631019cccbcc326d46012 status=400 post_dur=0.003s +[2026-08-21 09:51:18,985] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6a84efa4064631019cccbcc326d46012 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 65536}] (retryable=False, attempt=1) +[2026-08-21 09:51:18,990] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d8da3191f5f8fb3583bb9f63573df16f attempt=1 +[2026-08-21 09:51:18,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d8da3191f5f8fb3583bb9f63573df16f status=400 post_dur=0.003s +[2026-08-21 09:51:18,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d8da3191f5f8fb3583bb9f63573df16f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 09:51:18,996] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a68af618dd7b34c86b59fdcb52d5c6a5 attempt=1 +[2026-08-21 09:51:19,400] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a68af618dd7b34c86b59fdcb52d5c6a5 status=200 post_dur=0.404s +[2026-08-21 09:51:47,198] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a68af618dd7b34c86b59fdcb52d5c6a5 total=28202.2ms bytes=32021 finished=True finish=tool_calls stop=None out_tok=225 prompt_tok=7438 tps=8.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:51:47,203] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fd7d52d45bac317c237f5af46800d51d attempt=1 +[2026-08-21 09:51:47,208] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fd7d52d45bac317c237f5af46800d51d status=400 post_dur=0.004s +[2026-08-21 09:51:47,208] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=fd7d52d45bac317c237f5af46800d51d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:51:47,210] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=70823b5ac845bd1f8774ee42d21bafee attempt=1 +[2026-08-21 09:51:47,500] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=70823b5ac845bd1f8774ee42d21bafee status=200 post_dur=0.290s +[2026-08-21 09:55:09,804] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=70823b5ac845bd1f8774ee42d21bafee total=202594.1ms bytes=690434 finished=True finish=stop stop=None out_tok=2372 prompt_tok=918 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:55:09,814] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2682fb6fd37b4f24e968d764437a25e1 attempt=1 +[2026-08-21 09:55:10,337] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2682fb6fd37b4f24e968d764437a25e1 status=200 post_dur=0.523s +[2026-08-21 09:56:30,669] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2682fb6fd37b4f24e968d764437a25e1 total=80855.3ms bytes=31461 finished=True finish=tool_calls stop=None out_tok=166 prompt_tok=45454 tps=2.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:56:30,677] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=585c250747371801b7e793d8b4c0f1c2 attempt=1 +[2026-08-21 09:56:30,682] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=585c250747371801b7e793d8b4c0f1c2 status=400 post_dur=0.004s +[2026-08-21 09:56:30,682] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=585c250747371801b7e793d8b4c0f1c2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 09:56:30,684] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7db3dd955c38e4306ae474ec656cb93d attempt=1 +[2026-08-21 09:56:31,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7db3dd955c38e4306ae474ec656cb93d status=200 post_dur=0.428s +[2026-08-21 09:56:49,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7db3dd955c38e4306ae474ec656cb93d total=19192.1ms bytes=20648 finished=True finish=tool_calls stop=None out_tok=151 prompt_tok=3334 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:56:49,884] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03fe467d3f55594f27596be0c817de64 attempt=1 +[2026-08-21 09:56:49,889] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03fe467d3f55594f27596be0c817de64 status=400 post_dur=0.005s +[2026-08-21 09:56:49,889] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=03fe467d3f55594f27596be0c817de64 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:56:49,895] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd attempt=1 +[2026-08-21 09:56:49,899] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd status=400 post_dur=0.004s +[2026-08-21 09:56:49,899] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bb5cc83729c4fceaab14ebb7d0dd4bfd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:56:49,903] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4da63363793b798959b852923d0b1a75 attempt=1 +[2026-08-21 09:56:49,906] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4da63363793b798959b852923d0b1a75 status=400 post_dur=0.003s +[2026-08-21 09:56:49,907] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4da63363793b798959b852923d0b1a75 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:56:49,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1009845b9f7199b5af1dcc9732c85401 attempt=1 +[2026-08-21 09:56:49,913] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1009845b9f7199b5af1dcc9732c85401 status=400 post_dur=0.003s +[2026-08-21 09:56:49,913] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1009845b9f7199b5af1dcc9732c85401 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:56:49,916] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21ce0a97bf87bbe568bf685f1a6489e6 attempt=1 +[2026-08-21 09:56:50,349] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21ce0a97bf87bbe568bf685f1a6489e6 status=200 post_dur=0.432s +[2026-08-21 09:57:17,643] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=21ce0a97bf87bbe568bf685f1a6489e6 total=27726.4ms bytes=23937 finished=True finish=tool_calls stop=None out_tok=139 prompt_tok=11310 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:57:17,646] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18124d640da68a1ca39ea1da607626bc attempt=1 +[2026-08-21 09:57:17,651] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18124d640da68a1ca39ea1da607626bc status=400 post_dur=0.005s +[2026-08-21 09:57:17,651] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=18124d640da68a1ca39ea1da607626bc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:57:17,654] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2f4bd5b73828650b91e3203f36a89b96 attempt=1 +[2026-08-21 09:57:18,120] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2f4bd5b73828650b91e3203f36a89b96 status=200 post_dur=0.465s +[2026-08-21 09:58:01,607] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2f4bd5b73828650b91e3203f36a89b96 total=43952.8ms bytes=57421 finished=True finish=stop stop=None out_tok=201 prompt_tok=21577 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:58:01,611] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 attempt=1 +[2026-08-21 09:58:02,055] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 status=200 post_dur=0.443s +[2026-08-21 09:58:30,252] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e3b1ad0d4b0ae9a0af796ee04ebb0dc7 total=28641.1ms bytes=20410 finished=True finish=tool_calls stop=None out_tok=169 prompt_tok=11631 tps=5.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:58:30,262] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7cbdab7b46e95ec6366386836cba94c5 attempt=1 +[2026-08-21 09:58:30,769] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7cbdab7b46e95ec6366386836cba94c5 status=200 post_dur=0.507s +[2026-08-21 09:58:52,822] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7cbdab7b46e95ec6366386836cba94c5 total=22560.9ms bytes=12657 finished=True finish=tool_calls stop=None out_tok=107 prompt_tok=49084 tps=4.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:58:52,830] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=376a3e1437ef36f81003e0637ea935a3 attempt=1 +[2026-08-21 09:58:52,834] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=376a3e1437ef36f81003e0637ea935a3 status=400 post_dur=0.004s +[2026-08-21 09:58:52,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=376a3e1437ef36f81003e0637ea935a3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:58:52,838] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=339ca333c681e7919cb517c87404dd63 attempt=1 +[2026-08-21 09:58:53,287] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=339ca333c681e7919cb517c87404dd63 status=200 post_dur=0.449s +[2026-08-21 09:59:22,007] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=339ca333c681e7919cb517c87404dd63 total=29169.3ms bytes=28644 finished=True finish=tool_calls stop=None out_tok=143 prompt_tok=13787 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:59:22,012] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ec64948e84e3de297ff24346fcaf6c2 attempt=1 +[2026-08-21 09:59:22,021] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ec64948e84e3de297ff24346fcaf6c2 status=400 post_dur=0.009s +[2026-08-21 09:59:22,021] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5ec64948e84e3de297ff24346fcaf6c2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:59:22,026] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0bcc15254f1e81443ea18c89ec99619b attempt=1 +[2026-08-21 09:59:22,030] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0bcc15254f1e81443ea18c89ec99619b status=400 post_dur=0.004s +[2026-08-21 09:59:22,030] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0bcc15254f1e81443ea18c89ec99619b status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:59:22,034] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5f5e5cb5b40f1964a4da622bb0ff39d attempt=1 +[2026-08-21 09:59:22,482] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5f5e5cb5b40f1964a4da622bb0ff39d status=200 post_dur=0.449s +[2026-08-21 09:59:46,189] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e5f5e5cb5b40f1964a4da622bb0ff39d total=24155.5ms bytes=11209 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=13625 tps=3.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 09:59:46,203] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3de56e7ddccd49d37365f311c73b68ee attempt=1 +[2026-08-21 09:59:46,212] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3de56e7ddccd49d37365f311c73b68ee status=400 post_dur=0.009s +[2026-08-21 09:59:46,212] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3de56e7ddccd49d37365f311c73b68ee status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:59:46,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f7b93cf7bf0ac456356481ba0a3c0869 attempt=1 +[2026-08-21 09:59:46,226] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f7b93cf7bf0ac456356481ba0a3c0869 status=400 post_dur=0.003s +[2026-08-21 09:59:46,226] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f7b93cf7bf0ac456356481ba0a3c0869 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:59:46,231] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=813a4c2ed840077d3e58e7ef7d0ba1fc attempt=1 +[2026-08-21 09:59:46,235] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=813a4c2ed840077d3e58e7ef7d0ba1fc status=400 post_dur=0.004s +[2026-08-21 09:59:46,235] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=813a4c2ed840077d3e58e7ef7d0ba1fc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 09:59:46,247] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=00f17c302646afed467a87ea313afde5 attempt=1 +[2026-08-21 09:59:46,748] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=00f17c302646afed467a87ea313afde5 status=200 post_dur=0.501s +[2026-08-21 10:00:13,127] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=00f17c302646afed467a87ea313afde5 total=26880.5ms bytes=17681 finished=True finish=tool_calls stop=None out_tok=109 prompt_tok=49263 tps=4.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:00:13,133] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9059eb022c6e80edfecc26f6afd3af84 attempt=1 +[2026-08-21 10:00:13,568] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9059eb022c6e80edfecc26f6afd3af84 status=200 post_dur=0.435s +[2026-08-21 10:00:34,509] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9059eb022c6e80edfecc26f6afd3af84 total=21375.9ms bytes=18969 finished=True finish=tool_calls stop=None out_tok=202 prompt_tok=7940 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:00:34,515] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e89e3e63625e700c56b71773c4c7eab4 attempt=1 +[2026-08-21 10:00:34,519] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e89e3e63625e700c56b71773c4c7eab4 status=400 post_dur=0.005s +[2026-08-21 10:00:34,520] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e89e3e63625e700c56b71773c4c7eab4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 10:00:34,524] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=360c6b0cfb2a4dd1100d416a70e7e657 attempt=1 +[2026-08-21 10:00:34,963] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=360c6b0cfb2a4dd1100d416a70e7e657 status=200 post_dur=0.439s +[2026-08-21 10:01:18,470] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=360c6b0cfb2a4dd1100d416a70e7e657 total=43946.6ms bytes=30954 finished=True finish=tool_calls stop=None out_tok=472 prompt_tok=7229 tps=10.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:01:18,473] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 attempt=1 +[2026-08-21 10:01:18,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 status=200 post_dur=0.437s +[2026-08-21 10:01:45,340] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0783ee21a4aab7e23c8fbdb0a2b5a817 total=26867.1ms bytes=23127 finished=True finish=tool_calls stop=None out_tok=274 prompt_tok=8044 tps=10.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:01:45,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=89f6e2c636fdff89a84f43f2da82dcd2 attempt=1 +[2026-08-21 10:01:45,776] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=89f6e2c636fdff89a84f43f2da82dcd2 status=200 post_dur=0.434s +[2026-08-21 10:01:59,761] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=89f6e2c636fdff89a84f43f2da82dcd2 total=14419.2ms bytes=24352 finished=True finish=tool_calls stop=None out_tok=127 prompt_tok=7197 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:01:59,769] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80270320a8dff29e764f3e51f2457048 attempt=1 +[2026-08-21 10:02:00,252] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80270320a8dff29e764f3e51f2457048 status=200 post_dur=0.483s +[2026-08-21 10:03:09,571] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80270320a8dff29e764f3e51f2457048 total=69801.4ms bytes=10898 finished=True finish=tool_calls stop=None out_tok=121 prompt_tok=40506 tps=1.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:03:09,576] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5d339eab458d8528d67a43e72e6fb280 attempt=1 +[2026-08-21 10:03:10,012] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5d339eab458d8528d67a43e72e6fb280 status=200 post_dur=0.436s +[2026-08-21 10:03:34,646] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5d339eab458d8528d67a43e72e6fb280 total=25069.9ms bytes=25381 finished=True finish=tool_calls stop=None out_tok=203 prompt_tok=9054 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:03:34,648] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d attempt=1 +[2026-08-21 10:03:35,085] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d status=200 post_dur=0.436s +[2026-08-21 10:04:05,057] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6b4cd6b8ca48cc1e1b9bf19492373d1d total=30409.1ms bytes=15813 finished=True finish=tool_calls stop=None out_tok=266 prompt_tok=8499 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:04:05,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f3d7ddfa95b6d6451c33fb084bbca83 attempt=1 +[2026-08-21 10:04:05,356] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f3d7ddfa95b6d6451c33fb084bbca83 status=200 post_dur=0.297s +[2026-08-21 10:07:01,172] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f3d7ddfa95b6d6451c33fb084bbca83 total=176113.5ms bytes=596545 finished=True finish=length stop=None out_tok=2048 prompt_tok=722 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:07:01,176] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=712fd074b7d4ea4b83bfcea317b58ce1 attempt=1 +[2026-08-21 10:07:01,620] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=712fd074b7d4ea4b83bfcea317b58ce1 status=200 post_dur=0.444s +[2026-08-21 10:07:13,706] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=712fd074b7d4ea4b83bfcea317b58ce1 total=12530.0ms bytes=10051 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=7322 tps=6.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:07:13,710] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a395f30cab08fc845d5d9611fa68f99e attempt=1 +[2026-08-21 10:07:13,715] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a395f30cab08fc845d5d9611fa68f99e status=400 post_dur=0.005s +[2026-08-21 10:07:13,716] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a395f30cab08fc845d5d9611fa68f99e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:07:13,718] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad2442913856511942e1b75e3e16026f attempt=1 +[2026-08-21 10:07:14,153] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad2442913856511942e1b75e3e16026f status=200 post_dur=0.434s +[2026-08-21 10:07:32,949] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ad2442913856511942e1b75e3e16026f total=19231.0ms bytes=15879 finished=True finish=tool_calls stop=None out_tok=144 prompt_tok=7664 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:07:32,954] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be69437c717502c0a63e8a525b38648c attempt=1 +[2026-08-21 10:07:32,957] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be69437c717502c0a63e8a525b38648c status=400 post_dur=0.003s +[2026-08-21 10:07:32,957] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=be69437c717502c0a63e8a525b38648c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:07:32,962] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b3ee41175527902f6fbcd82eb8223f16 attempt=1 +[2026-08-21 10:07:33,391] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b3ee41175527902f6fbcd82eb8223f16 status=200 post_dur=0.428s +[2026-08-21 10:08:00,808] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b3ee41175527902f6fbcd82eb8223f16 total=27845.6ms bytes=33225 finished=True finish=tool_calls stop=None out_tok=191 prompt_tok=9643 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:08:00,811] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23562599c4adb3e90d36122c9fb0f170 attempt=1 +[2026-08-21 10:08:01,247] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23562599c4adb3e90d36122c9fb0f170 status=200 post_dur=0.436s +[2026-08-21 10:08:12,062] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=23562599c4adb3e90d36122c9fb0f170 total=11251.4ms bytes=12852 finished=True finish=stop stop=None out_tok=43 prompt_tok=7873 tps=3.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:08:12,064] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07a68b8da39a6f982e88d0cd82940b3f attempt=1 +[2026-08-21 10:08:12,487] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07a68b8da39a6f982e88d0cd82940b3f status=200 post_dur=0.423s +[2026-08-21 10:08:24,475] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=07a68b8da39a6f982e88d0cd82940b3f total=12410.4ms bytes=9955 finished=True finish=tool_calls stop=None out_tok=70 prompt_tok=7975 tps=5.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:08:24,478] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=219b40a8c965d11add7bd2c508c7791d attempt=1 +[2026-08-21 10:08:24,819] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=219b40a8c965d11add7bd2c508c7791d status=200 post_dur=0.341s +[2026-08-21 10:08:59,721] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=219b40a8c965d11add7bd2c508c7791d total=35242.8ms bytes=3672 finished=True finish=stop stop= out_tok=7 prompt_tok=27241 tps=0.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:08:59,724] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0d42f70c177f45adc313f51314e9f310 attempt=1 +[2026-08-21 10:08:59,725] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 14% (44/881) has_cb=True +[2026-08-21 10:09:00,170] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0d42f70c177f45adc313f51314e9f310 status=200 post_dur=0.445s +[2026-08-21 10:09:31,343] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0d42f70c177f45adc313f51314e9f310 total=31618.6ms bytes=26116 finished=True finish=tool_calls stop=None out_tok=277 prompt_tok=9964 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:09:31,348] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f699dd3ebdf7c24caa4d8288ae6306c9 attempt=1 +[2026-08-21 10:09:31,353] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f699dd3ebdf7c24caa4d8288ae6306c9 status=400 post_dur=0.005s +[2026-08-21 10:09:31,353] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f699dd3ebdf7c24caa4d8288ae6306c9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:09:31,356] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a56c2293beb6e091c063773919a7b85a attempt=1 +[2026-08-21 10:09:31,797] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a56c2293beb6e091c063773919a7b85a status=200 post_dur=0.441s +[2026-08-21 10:09:43,146] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a56c2293beb6e091c063773919a7b85a total=11789.4ms bytes=20052 finished=True finish=stop stop=None out_tok=68 prompt_tok=8163 tps=5.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:09:43,150] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5a0840884edeb8f37a79e2a99b091fff attempt=1 +[2026-08-21 10:09:43,153] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5a0840884edeb8f37a79e2a99b091fff status=400 post_dur=0.003s +[2026-08-21 10:09:43,153] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5a0840884edeb8f37a79e2a99b091fff status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:09:43,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=54a7844586d857514e3829e8ef560825 attempt=1 +[2026-08-21 10:09:43,650] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=54a7844586d857514e3829e8ef560825 status=200 post_dur=0.486s +[2026-08-21 10:10:03,719] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=54a7844586d857514e3829e8ef560825 total=20554.6ms bytes=8306 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=49698 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:10:03,724] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 attempt=1 +[2026-08-21 10:10:04,021] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 status=200 post_dur=0.297s +[2026-08-21 10:16:51,186] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=85db3caec6b582aaafd3dbfe9bd5e7d8 total=407461.9ms bytes=1385763 finished=True finish=stop stop=None out_tok=4774 prompt_tok=543 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:16:51,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8e95ef4c8df8d98f53d1f3578d275be attempt=1 +[2026-08-21 10:16:51,643] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8e95ef4c8df8d98f53d1f3578d275be status=200 post_dur=0.450s +[2026-08-21 10:17:32,691] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a8e95ef4c8df8d98f53d1f3578d275be total=41499.2ms bytes=30152 finished=True finish=tool_calls stop=None out_tok=347 prompt_tok=9644 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:17:32,695] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 attempt=1 +[2026-08-21 10:17:33,142] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 status=200 post_dur=0.448s +[2026-08-21 10:18:06,513] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d2fbdb145e8ba1fb9b156a2e526d32c2 total=33818.0ms bytes=6980 finished=True finish=tool_calls stop=None out_tok=289 prompt_tok=13629 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:18:06,514] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39102a614c8ccec8e7ca9bcfb647d006 attempt=1 +[2026-08-21 10:18:06,812] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39102a614c8ccec8e7ca9bcfb647d006 status=200 post_dur=0.298s +[2026-08-21 10:21:14,278] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=39102a614c8ccec8e7ca9bcfb647d006 total=187764.3ms bytes=635629 finished=True finish=stop stop=None out_tok=2185 prompt_tok=340 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:21:14,283] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ce01f9017d9d711130b41c2ddbae17c attempt=1 +[2026-08-21 10:21:14,739] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ce01f9017d9d711130b41c2ddbae17c status=200 post_dur=0.456s +[2026-08-21 10:21:50,292] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ce01f9017d9d711130b41c2ddbae17c total=36008.8ms bytes=35217 finished=True finish=tool_calls stop=None out_tok=330 prompt_tok=10478 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:21:50,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=efd73b6b2b7ff74dd1c2c06494d7075d attempt=1 +[2026-08-21 10:21:50,301] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=efd73b6b2b7ff74dd1c2c06494d7075d status=400 post_dur=0.005s +[2026-08-21 10:21:50,302] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=efd73b6b2b7ff74dd1c2c06494d7075d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:21:50,305] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a2b735acf3a16ed3e21d3f5098df2ba7 attempt=1 +[2026-08-21 10:21:50,749] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a2b735acf3a16ed3e21d3f5098df2ba7 status=200 post_dur=0.443s +[2026-08-21 10:22:30,277] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a2b735acf3a16ed3e21d3f5098df2ba7 total=39971.4ms bytes=29812 finished=True finish=tool_calls stop=None out_tok=382 prompt_tok=10715 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:22:30,279] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=75640a175567399b71ba112bebff92dc attempt=1 +[2026-08-21 10:22:30,719] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=75640a175567399b71ba112bebff92dc status=200 post_dur=0.439s +[2026-08-21 10:22:47,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=75640a175567399b71ba112bebff92dc total=17037.4ms bytes=33781 finished=True finish=stop stop=None out_tok=116 prompt_tok=8287 tps=6.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:22:47,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c0c3e503a9bb2dffb86498602abab0f8 attempt=1 +[2026-08-21 10:22:47,751] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c0c3e503a9bb2dffb86498602abab0f8 status=200 post_dur=0.431s +[2026-08-21 10:23:02,535] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c0c3e503a9bb2dffb86498602abab0f8 total=15215.5ms bytes=24142 finished=True finish=stop stop=None out_tok=82 prompt_tok=8410 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:23:02,539] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac347710b223a90a91abea5cc1a4953a attempt=1 +[2026-08-21 10:23:02,544] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac347710b223a90a91abea5cc1a4953a status=400 post_dur=0.005s +[2026-08-21 10:23:02,544] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ac347710b223a90a91abea5cc1a4953a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:23:02,550] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8463c2c502f1f0534d61b5ca2d393ebe attempt=1 +[2026-08-21 10:23:02,553] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8463c2c502f1f0534d61b5ca2d393ebe status=400 post_dur=0.004s +[2026-08-21 10:23:02,553] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=8463c2c502f1f0534d61b5ca2d393ebe status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:23:02,566] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b0e4b0f5b0ca97ed4d751c75618548c attempt=1 +[2026-08-21 10:23:03,061] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b0e4b0f5b0ca97ed4d751c75618548c status=200 post_dur=0.496s +[2026-08-21 10:23:50,699] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b0e4b0f5b0ca97ed4d751c75618548c total=48132.9ms bytes=44121 finished=True finish=tool_calls stop=None out_tok=316 prompt_tok=50019 tps=6.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:23:50,706] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a391bb70b9e2ba5c7e520aab15e3def1 attempt=1 +[2026-08-21 10:23:51,149] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a391bb70b9e2ba5c7e520aab15e3def1 status=200 post_dur=0.443s +[2026-08-21 10:24:03,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a391bb70b9e2ba5c7e520aab15e3def1 total=12613.2ms bytes=21102 finished=True finish=stop stop=None out_tok=72 prompt_tok=8534 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:24:03,322] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f37ea383d6ec06c307d5f3744b934942 attempt=1 +[2026-08-21 10:24:03,748] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f37ea383d6ec06c307d5f3744b934942 status=200 post_dur=0.426s +[2026-08-21 10:24:17,732] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f37ea383d6ec06c307d5f3744b934942 total=14410.7ms bytes=27242 finished=True finish=stop stop=None out_tok=92 prompt_tok=8664 tps=6.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:24:17,738] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=311152e5f6fe095f516df19d0f9295a3 attempt=1 +[2026-08-21 10:24:17,742] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=311152e5f6fe095f516df19d0f9295a3 status=400 post_dur=0.005s +[2026-08-21 10:24:17,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=311152e5f6fe095f516df19d0f9295a3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:24:17,750] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6b0d07d4e32c236ad057a1909c20b94c attempt=1 +[2026-08-21 10:24:17,755] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6b0d07d4e32c236ad057a1909c20b94c status=400 post_dur=0.005s +[2026-08-21 10:24:17,755] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6b0d07d4e32c236ad057a1909c20b94c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:24:17,761] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1553e713a265e3e047100572f79b3970 attempt=1 +[2026-08-21 10:24:17,765] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1553e713a265e3e047100572f79b3970 status=400 post_dur=0.003s +[2026-08-21 10:24:17,765] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1553e713a265e3e047100572f79b3970 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:24:17,768] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7f48075c85514d36f9123d4d520ad38 attempt=1 +[2026-08-21 10:24:18,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7f48075c85514d36f9123d4d520ad38 status=200 post_dur=0.424s +[2026-08-21 10:24:30,502] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7f48075c85514d36f9123d4d520ad38 total=12734.1ms bytes=20485 finished=True finish=stop stop=None out_tok=69 prompt_tok=8783 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:24:30,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5834b503b1451d5964dff9ea1d95cdfd attempt=1 +[2026-08-21 10:24:30,512] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5834b503b1451d5964dff9ea1d95cdfd status=400 post_dur=0.005s +[2026-08-21 10:24:30,512] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5834b503b1451d5964dff9ea1d95cdfd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:24:30,516] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c99a9bde00a04b8817a94ee39e4d79b5 attempt=1 +[2026-08-21 10:24:30,950] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c99a9bde00a04b8817a94ee39e4d79b5 status=200 post_dur=0.434s +[2026-08-21 10:25:03,676] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c99a9bde00a04b8817a94ee39e4d79b5 total=33159.9ms bytes=40259 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=14545 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:25:03,682] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=074a482ddedc3555e604c834ff66c671 attempt=1 +[2026-08-21 10:25:03,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=074a482ddedc3555e604c834ff66c671 status=400 post_dur=0.005s +[2026-08-21 10:25:03,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=074a482ddedc3555e604c834ff66c671 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:25:03,693] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bf9397c366a1037bdd145249dee8b6cd attempt=1 +[2026-08-21 10:25:04,075] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bf9397c366a1037bdd145249dee8b6cd status=200 post_dur=0.383s +[2026-08-21 10:25:43,083] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bf9397c366a1037bdd145249dee8b6cd total=39390.5ms bytes=3953 finished=True finish=stop stop= out_tok=7 prompt_tok=27569 tps=0.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:25:43,087] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a0ee8f7cc01879cf295f23c02c4d1655 attempt=1 +[2026-08-21 10:25:43,536] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a0ee8f7cc01879cf295f23c02c4d1655 status=200 post_dur=0.450s +[2026-08-21 10:26:24,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a0ee8f7cc01879cf295f23c02c4d1655 total=41646.8ms bytes=22433 finished=True finish=tool_calls stop=None out_tok=389 prompt_tok=12033 tps=9.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:26:24,737] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=784782f027a97cabd3ecf7d581aaf95f attempt=1 +[2026-08-21 10:26:25,191] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=784782f027a97cabd3ecf7d581aaf95f status=200 post_dur=0.454s +[2026-08-21 10:26:57,907] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=784782f027a97cabd3ecf7d581aaf95f total=33170.2ms bytes=18556 finished=True finish=tool_calls stop=None out_tok=336 prompt_tok=14122 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:26:57,930] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0095eee8517acdd4d3777bb0dad225d0 attempt=1 +[2026-08-21 10:26:57,941] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0095eee8517acdd4d3777bb0dad225d0 status=400 post_dur=0.011s +[2026-08-21 10:26:57,941] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0095eee8517acdd4d3777bb0dad225d0 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:26:57,956] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a05d3a420be46da851a6bd2697078069 attempt=1 +[2026-08-21 10:26:57,962] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a05d3a420be46da851a6bd2697078069 status=400 post_dur=0.003s +[2026-08-21 10:26:57,962] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a05d3a420be46da851a6bd2697078069 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:26:57,972] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e35b4624c19687e1ea219c3ac378c64 attempt=1 +[2026-08-21 10:26:58,479] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e35b4624c19687e1ea219c3ac378c64 status=200 post_dur=0.505s +[2026-08-21 10:27:40,203] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e35b4624c19687e1ea219c3ac378c64 total=42231.1ms bytes=8373 finished=True finish=tool_calls stop=None out_tok=99 prompt_tok=43882 tps=2.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:27:40,211] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f4bf992edfbf1935605b2c80b414d03 attempt=1 +[2026-08-21 10:27:40,216] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f4bf992edfbf1935605b2c80b414d03 status=400 post_dur=0.005s +[2026-08-21 10:27:40,217] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5f4bf992edfbf1935605b2c80b414d03 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'reasoning_effort'), 'msg': 'Extra inputs are not permitted', 'input': 'low'}] (retryable=False, attempt=1) +[2026-08-21 10:27:40,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40959c2050879969f36ed4f3b444dacd attempt=1 +[2026-08-21 10:27:40,227] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40959c2050879969f36ed4f3b444dacd status=400 post_dur=0.003s +[2026-08-21 10:27:40,228] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=40959c2050879969f36ed4f3b444dacd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:40,234] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aeabdeb121230304d17740b28591d176 attempt=1 +[2026-08-21 10:27:40,239] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aeabdeb121230304d17740b28591d176 status=400 post_dur=0.003s +[2026-08-21 10:27:40,239] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=aeabdeb121230304d17740b28591d176 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:40,243] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f8d05205e676b25e02ee83b3f6ed2502 attempt=1 +[2026-08-21 10:27:40,692] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f8d05205e676b25e02ee83b3f6ed2502 status=200 post_dur=0.449s +[2026-08-21 10:27:52,626] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f8d05205e676b25e02ee83b3f6ed2502 total=12382.9ms bytes=13295 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=11658 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:27:52,631] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a21ccfb1e67b5d347d1c44d30403b795 attempt=1 +[2026-08-21 10:27:52,638] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a21ccfb1e67b5d347d1c44d30403b795 status=400 post_dur=0.006s +[2026-08-21 10:27:52,638] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a21ccfb1e67b5d347d1c44d30403b795 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:52,642] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2f83fc5e61ae17754909b5b0d66e6ca5 attempt=1 +[2026-08-21 10:27:52,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2f83fc5e61ae17754909b5b0d66e6ca5 status=400 post_dur=0.002s +[2026-08-21 10:27:52,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2f83fc5e61ae17754909b5b0d66e6ca5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:52,657] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bbff126da08af9ca0d698e918bd39573 attempt=1 +[2026-08-21 10:27:52,663] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bbff126da08af9ca0d698e918bd39573 status=400 post_dur=0.005s +[2026-08-21 10:27:52,663] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bbff126da08af9ca0d698e918bd39573 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:52,672] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b65fcd82491c19e8d7d0d34518546e5a attempt=1 +[2026-08-21 10:27:52,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b65fcd82491c19e8d7d0d34518546e5a status=400 post_dur=0.003s +[2026-08-21 10:27:52,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b65fcd82491c19e8d7d0d34518546e5a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:27:52,678] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77b618402ff95dd4ff23bd2310cb8318 attempt=1 +[2026-08-21 10:27:52,965] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77b618402ff95dd4ff23bd2310cb8318 status=200 post_dur=0.287s +[2026-08-21 10:34:10,141] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=77b618402ff95dd4ff23bd2310cb8318 total=377462.9ms bytes=1304082 finished=True finish=stop stop=None out_tok=4469 prompt_tok=122 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:34:10,149] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d32f68c92aef9a9648a699a77ef05b26 attempt=1 +[2026-08-21 10:34:10,156] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d32f68c92aef9a9648a699a77ef05b26 status=400 post_dur=0.007s +[2026-08-21 10:34:10,157] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d32f68c92aef9a9648a699a77ef05b26 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:34:10,159] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=918aec365fd6259a7e6b60476f6088a4 attempt=1 +[2026-08-21 10:34:10,457] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=918aec365fd6259a7e6b60476f6088a4 status=200 post_dur=0.298s +[2026-08-21 10:41:32,509] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=918aec365fd6259a7e6b60476f6088a4 total=442350.1ms bytes=1521102 finished=True finish=stop stop=None out_tok=5234 prompt_tok=543 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:41:32,523] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a64b40ed62a4f1699c75f575d5608d10 attempt=1 +[2026-08-21 10:41:32,531] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a64b40ed62a4f1699c75f575d5608d10 status=400 post_dur=0.006s +[2026-08-21 10:41:32,531] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a64b40ed62a4f1699c75f575d5608d10 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:41:32,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ca31eadeeaf52359665b0d1944272c8 attempt=1 +[2026-08-21 10:41:32,540] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 18% (88/881) has_cb=True +[2026-08-21 10:41:32,548] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ca31eadeeaf52359665b0d1944272c8 status=400 post_dur=0.008s +[2026-08-21 10:41:32,549] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=8ca31eadeeaf52359665b0d1944272c8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:41:32,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=78ea5bb2fab0a10263af727c1c9c09b5 attempt=1 +[2026-08-21 10:41:33,011] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=78ea5bb2fab0a10263af727c1c9c09b5 status=200 post_dur=0.457s +[2026-08-21 10:42:03,259] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=78ea5bb2fab0a10263af727c1c9c09b5 total=30705.1ms bytes=18801 finished=True finish=tool_calls stop=None out_tok=259 prompt_tok=13068 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:42:03,262] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a96ee2366817370eea1cef47ad091443 attempt=1 +[2026-08-21 10:42:03,691] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a96ee2366817370eea1cef47ad091443 status=200 post_dur=0.430s +[2026-08-21 10:42:16,635] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a96ee2366817370eea1cef47ad091443 total=13373.7ms bytes=12251 finished=True finish=tool_calls stop=None out_tok=108 prompt_tok=7510 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:42:16,641] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0bea91b5ded418d8d4a581db599a3427 attempt=1 +[2026-08-21 10:42:16,646] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0bea91b5ded418d8d4a581db599a3427 status=400 post_dur=0.005s +[2026-08-21 10:42:16,646] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0bea91b5ded418d8d4a581db599a3427 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:42:16,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1a96f880493d5949c2df7e1cf3b2a6ef attempt=1 +[2026-08-21 10:42:16,659] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1a96f880493d5949c2df7e1cf3b2a6ef status=400 post_dur=0.006s +[2026-08-21 10:42:16,659] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1a96f880493d5949c2df7e1cf3b2a6ef status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:42:16,663] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=06537fb205ebfa74b468388f0205c0b6 attempt=1 +[2026-08-21 10:42:17,100] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=06537fb205ebfa74b468388f0205c0b6 status=200 post_dur=0.436s +[2026-08-21 10:42:47,023] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=06537fb205ebfa74b468388f0205c0b6 total=30359.5ms bytes=25347 finished=True finish=tool_calls stop=None out_tok=303 prompt_tok=13375 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:42:47,026] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6cd5c62d32dcdbcbbb415bd7854e91ca attempt=1 +[2026-08-21 10:42:47,458] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6cd5c62d32dcdbcbbb415bd7854e91ca status=200 post_dur=0.432s +[2026-08-21 10:42:56,648] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6cd5c62d32dcdbcbbb415bd7854e91ca total=9622.4ms bytes=8757 finished=True finish=stop stop=None out_tok=29 prompt_tok=7694 tps=3.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:42:56,654] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ec1d220a384aea3297a253a297cf1a9 attempt=1 +[2026-08-21 10:42:56,660] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ec1d220a384aea3297a253a297cf1a9 status=400 post_dur=0.006s +[2026-08-21 10:42:56,660] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3ec1d220a384aea3297a253a297cf1a9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:42:56,667] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e88b521cf3df9fb0cbc8d992a2449aee attempt=1 +[2026-08-21 10:42:56,671] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e88b521cf3df9fb0cbc8d992a2449aee status=400 post_dur=0.003s +[2026-08-21 10:42:56,671] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e88b521cf3df9fb0cbc8d992a2449aee status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:42:56,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=359993faafbbf5e1f8c854e67edd7b28 attempt=1 +[2026-08-21 10:42:57,104] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=359993faafbbf5e1f8c854e67edd7b28 status=200 post_dur=0.429s +[2026-08-21 10:43:32,815] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=359993faafbbf5e1f8c854e67edd7b28 total=36139.4ms bytes=34524 finished=True finish=tool_calls stop=None out_tok=321 prompt_tok=14631 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:43:32,819] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5287e77e7d3f01ce0ec64229252926f1 attempt=1 +[2026-08-21 10:43:32,823] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5287e77e7d3f01ce0ec64229252926f1 status=400 post_dur=0.004s +[2026-08-21 10:43:32,823] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5287e77e7d3f01ce0ec64229252926f1 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:43:32,825] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4074aa7dc7eeae406e1611ba25d09f4 attempt=1 +[2026-08-21 10:43:33,124] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4074aa7dc7eeae406e1611ba25d09f4 status=200 post_dur=0.297s +[2026-08-21 10:47:32,616] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4074aa7dc7eeae406e1611ba25d09f4 total=239791.1ms bytes=814762 finished=True finish=stop stop=None out_tok=2796 prompt_tok=329 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:47:32,625] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=72ac37b8e14256ef5f1f6b17c95816e3 attempt=1 +[2026-08-21 10:47:32,633] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=72ac37b8e14256ef5f1f6b17c95816e3 status=400 post_dur=0.006s +[2026-08-21 10:47:32,633] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=72ac37b8e14256ef5f1f6b17c95816e3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:47:32,636] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6c94c67fba670cdb7e87d0346aaa846d attempt=1 +[2026-08-21 10:47:32,934] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6c94c67fba670cdb7e87d0346aaa846d status=200 post_dur=0.297s +[2026-08-21 10:51:57,865] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6c94c67fba670cdb7e87d0346aaa846d total=265229.0ms bytes=908444 finished=True finish=stop stop=None out_tok=3100 prompt_tok=1147 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:51:57,872] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d90b76d18c2aa143a4aa12ca4b73a91f attempt=1 +[2026-08-21 10:51:57,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d90b76d18c2aa143a4aa12ca4b73a91f status=400 post_dur=0.004s +[2026-08-21 10:51:57,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d90b76d18c2aa143a4aa12ca4b73a91f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:51:57,879] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ee3b59eca4ff424eeeeb06f0f9807899 attempt=1 +[2026-08-21 10:51:57,883] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ee3b59eca4ff424eeeeb06f0f9807899 status=400 post_dur=0.002s +[2026-08-21 10:51:57,883] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ee3b59eca4ff424eeeeb06f0f9807899 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:51:57,886] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b08d07aa190488d2ee3424334d75e8ba attempt=1 +[2026-08-21 10:51:58,348] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b08d07aa190488d2ee3424334d75e8ba status=200 post_dur=0.462s +[2026-08-21 10:52:33,580] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b08d07aa190488d2ee3424334d75e8ba total=35694.5ms bytes=54115 finished=True finish=tool_calls stop=None out_tok=205 prompt_tok=15084 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:52:33,588] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8da9e2d6b6813eaddab9b4575a1a83f attempt=1 +[2026-08-21 10:52:33,595] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8da9e2d6b6813eaddab9b4575a1a83f status=400 post_dur=0.007s +[2026-08-21 10:52:33,595] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a8da9e2d6b6813eaddab9b4575a1a83f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:52:33,601] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad67a766c04ea6887f061628a3a3d818 attempt=1 +[2026-08-21 10:52:33,605] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad67a766c04ea6887f061628a3a3d818 status=400 post_dur=0.004s +[2026-08-21 10:52:33,605] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ad67a766c04ea6887f061628a3a3d818 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:52:33,608] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 attempt=1 +[2026-08-21 10:52:34,045] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 status=200 post_dur=0.437s +[2026-08-21 10:53:13,180] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=93e83c7cfef9b6adb4fc1e50d0e222d8 total=39572.3ms bytes=31978 finished=True finish=tool_calls stop=None out_tok=362 prompt_tok=7433 tps=9.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:53:13,187] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b316df0c85c0582bbe29e8ec225bc084 attempt=1 +[2026-08-21 10:53:13,193] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b316df0c85c0582bbe29e8ec225bc084 status=400 post_dur=0.006s +[2026-08-21 10:53:13,193] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b316df0c85c0582bbe29e8ec225bc084 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:53:13,201] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 attempt=1 +[2026-08-21 10:53:13,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 status=400 post_dur=0.006s +[2026-08-21 10:53:13,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3cfc1c5b9409ee8f8d1a75361cfeb229 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:53:13,212] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=644f50cec5c5a17c7ed68cd3d209a327 attempt=1 +[2026-08-21 10:53:13,668] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=644f50cec5c5a17c7ed68cd3d209a327 status=200 post_dur=0.456s +[2026-08-21 10:54:49,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=644f50cec5c5a17c7ed68cd3d209a327 total=96057.9ms bytes=289726 finished=True finish=stop stop=None out_tok=1010 prompt_tok=16293 tps=10.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:54:49,276] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea32e9659a5417289b1ca305dae84ea7 attempt=1 +[2026-08-21 10:54:49,739] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea32e9659a5417289b1ca305dae84ea7 status=200 post_dur=0.462s +[2026-08-21 10:55:18,536] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea32e9659a5417289b1ca305dae84ea7 total=29259.7ms bytes=25262 finished=True finish=tool_calls stop=None out_tok=209 prompt_tok=18482 tps=7.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 10:55:18,547] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 attempt=1 +[2026-08-21 10:55:18,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 status=400 post_dur=0.006s +[2026-08-21 10:55:18,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e7aa9783dccc6a9dbbe1f5e03e98fa06 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 10:55:18,578] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fe7722e1ac0ce6b82619d5486a7d745f attempt=1 +[2026-08-21 10:55:19,327] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fe7722e1ac0ce6b82619d5486a7d745f status=200 post_dur=0.749s +[2026-08-21 11:24:40,397] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fe7722e1ac0ce6b82619d5486a7d745f total=1761818.8ms bytes=1183816 finished=True finish=length stop=None out_tok=4096 prompt_tok=254336 tps=2.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:24:40,423] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea0d61904cec5ffd9962be89b52a5533 attempt=1 +[2026-08-21 11:24:40,432] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea0d61904cec5ffd9962be89b52a5533 status=400 post_dur=0.008s +[2026-08-21 11:24:40,432] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ea0d61904cec5ffd9962be89b52a5533 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:24:40,436] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17ed153b31dbaf712162b2e8efcf5f83 attempt=1 +[2026-08-21 11:24:40,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17ed153b31dbaf712162b2e8efcf5f83 status=200 post_dur=0.440s +[2026-08-21 11:25:01,945] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17ed153b31dbaf712162b2e8efcf5f83 total=21508.7ms bytes=10367 finished=True finish=tool_calls stop=None out_tok=198 prompt_tok=7670 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:25:01,947] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8594181c733137b3501cbdef6c8ca480 attempt=1 +[2026-08-21 11:25:02,391] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8594181c733137b3501cbdef6c8ca480 status=200 post_dur=0.443s +[2026-08-21 11:25:34,213] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8594181c733137b3501cbdef6c8ca480 total=32266.1ms bytes=16123 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=8974 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:25:34,218] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab3a26a3b1baafac01deca1e9c297be3 attempt=1 +[2026-08-21 11:25:34,223] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab3a26a3b1baafac01deca1e9c297be3 status=400 post_dur=0.005s +[2026-08-21 11:25:34,223] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ab3a26a3b1baafac01deca1e9c297be3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:25:34,226] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bd7ef39fe969b9fc6d359b5c1627bbbc attempt=1 +[2026-08-21 11:25:34,669] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bd7ef39fe969b9fc6d359b5c1627bbbc status=200 post_dur=0.442s +[2026-08-21 11:25:57,504] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bd7ef39fe969b9fc6d359b5c1627bbbc total=23277.8ms bytes=14788 finished=True finish=tool_calls stop=None out_tok=225 prompt_tok=7955 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:25:57,509] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=70bdd90760d1a4809ceb24b904b635f7 attempt=1 +[2026-08-21 11:25:57,516] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=70bdd90760d1a4809ceb24b904b635f7 status=400 post_dur=0.007s +[2026-08-21 11:25:57,516] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=70bdd90760d1a4809ceb24b904b635f7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:25:57,519] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b115b076b436975dd0bdc04a97b0250d attempt=1 +[2026-08-21 11:25:57,949] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b115b076b436975dd0bdc04a97b0250d status=200 post_dur=0.430s +[2026-08-21 11:26:14,353] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b115b076b436975dd0bdc04a97b0250d total=16834.3ms bytes=18103 finished=True finish=tool_calls stop=None out_tok=139 prompt_tok=8108 tps=8.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:26:14,355] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=05c88893744ef06a571e677dea1d4b35 attempt=1 +[2026-08-21 11:26:14,635] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=05c88893744ef06a571e677dea1d4b35 status=200 post_dur=0.280s +[2026-08-21 11:28:57,905] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=05c88893744ef06a571e677dea1d4b35 total=163549.8ms bytes=551100 finished=True finish=stop stop=None out_tok=1894 prompt_tok=665 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:28:57,913] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 attempt=1 +[2026-08-21 11:28:57,920] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 status=400 post_dur=0.007s +[2026-08-21 11:28:57,920] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=8e3efa7469d462db26a0bbb0c1b8b2b7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:28:57,925] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=98ccba13269d9b590af730b62743e33b attempt=1 +[2026-08-21 11:28:58,371] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=98ccba13269d9b590af730b62743e33b status=200 post_dur=0.443s +[2026-08-21 11:29:14,249] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=98ccba13269d9b590af730b62743e33b total=16324.8ms bytes=11151 finished=True finish=tool_calls stop=None out_tok=82 prompt_tok=8897 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:29:14,253] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b621098765131843ffeab6dfd48accd attempt=1 +[2026-08-21 11:29:14,700] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b621098765131843ffeab6dfd48accd status=200 post_dur=0.447s +[2026-08-21 11:29:58,929] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b621098765131843ffeab6dfd48accd total=44676.2ms bytes=19189 finished=True finish=tool_calls stop=None out_tok=424 prompt_tok=18180 tps=9.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:29:58,935] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c2c871af3ea2bfd0969ab05edf0d3656 attempt=1 +[2026-08-21 11:29:58,940] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c2c871af3ea2bfd0969ab05edf0d3656 status=400 post_dur=0.005s +[2026-08-21 11:29:58,940] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c2c871af3ea2bfd0969ab05edf0d3656 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:29:58,948] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=99cf6f20ee57cda5eb49ae34d8d3e834 attempt=1 +[2026-08-21 11:29:58,955] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=99cf6f20ee57cda5eb49ae34d8d3e834 status=400 post_dur=0.004s +[2026-08-21 11:29:58,955] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=99cf6f20ee57cda5eb49ae34d8d3e834 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:29:58,963] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7967bc80bba6d05abe4d2ab9846fd01d attempt=1 +[2026-08-21 11:29:58,967] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7967bc80bba6d05abe4d2ab9846fd01d status=400 post_dur=0.004s +[2026-08-21 11:29:58,968] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7967bc80bba6d05abe4d2ab9846fd01d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:29:58,972] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e82a541b8876c7ce47306d2d774519ff attempt=1 +[2026-08-21 11:29:59,411] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e82a541b8876c7ce47306d2d774519ff status=200 post_dur=0.440s +[2026-08-21 11:30:22,777] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e82a541b8876c7ce47306d2d774519ff total=23805.8ms bytes=20236 finished=True finish=tool_calls stop=None out_tok=202 prompt_tok=8582 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:30:22,784] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9714fabdd0f00bbb50c5ac49930bf1e4 attempt=1 +[2026-08-21 11:30:22,791] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9714fabdd0f00bbb50c5ac49930bf1e4 status=400 post_dur=0.007s +[2026-08-21 11:30:22,792] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=9714fabdd0f00bbb50c5ac49930bf1e4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:30:22,795] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3e56365379b717c910e903207fc67f9 attempt=1 +[2026-08-21 11:30:23,089] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3e56365379b717c910e903207fc67f9 status=200 post_dur=0.293s +[2026-08-21 11:30:26,843] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3e56365379b717c910e903207fc67f9 total=4048.2ms bytes=1392 finished=True finish=length stop=None out_tok=1 prompt_tok=100 tps=0.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:30:26,849] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f41046205744415148dca979685e81eb attempt=1 +[2026-08-21 11:30:26,856] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f41046205744415148dca979685e81eb status=400 post_dur=0.007s +[2026-08-21 11:30:26,857] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f41046205744415148dca979685e81eb status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:30:26,863] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b3452ce4a8b51cc2663f5a17101f4c12 attempt=1 +[2026-08-21 11:30:26,863] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 22% (132/881) has_cb=True +[2026-08-21 11:30:26,867] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b3452ce4a8b51cc2663f5a17101f4c12 status=400 post_dur=0.004s +[2026-08-21 11:30:26,867] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b3452ce4a8b51cc2663f5a17101f4c12 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:30:26,871] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f5732edcfa094a4f5437d9960ecb1cf5 attempt=1 +[2026-08-21 11:30:27,286] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f5732edcfa094a4f5437d9960ecb1cf5 status=200 post_dur=0.416s +[2026-08-21 11:30:42,006] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f5732edcfa094a4f5437d9960ecb1cf5 total=15135.3ms bytes=23107 finished=True finish=tool_calls stop=None out_tok=153 prompt_tok=7197 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:30:42,013] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7d534d19ae66525152a691c5fb1453b2 attempt=1 +[2026-08-21 11:30:42,018] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7d534d19ae66525152a691c5fb1453b2 status=400 post_dur=0.005s +[2026-08-21 11:30:42,018] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7d534d19ae66525152a691c5fb1453b2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:30:42,027] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6cf82700ecbf1dcdddc9a112b28a8fcc attempt=1 +[2026-08-21 11:30:42,031] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6cf82700ecbf1dcdddc9a112b28a8fcc status=400 post_dur=0.004s +[2026-08-21 11:30:42,031] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6cf82700ecbf1dcdddc9a112b28a8fcc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:30:42,035] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e919424545dba016f1344168295d939 attempt=1 +[2026-08-21 11:30:42,462] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e919424545dba016f1344168295d939 status=200 post_dur=0.426s +[2026-08-21 11:30:50,704] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e919424545dba016f1344168295d939 total=8668.7ms bytes=8457 finished=True finish=stop stop=None out_tok=28 prompt_tok=7656 tps=3.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:30:50,706] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff32a774226d5c886a88aa72901e86f2 attempt=1 +[2026-08-21 11:30:51,133] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff32a774226d5c886a88aa72901e86f2 status=200 post_dur=0.427s +[2026-08-21 11:31:00,296] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff32a774226d5c886a88aa72901e86f2 total=9589.6ms bytes=9356 finished=True finish=stop stop=None out_tok=31 prompt_tok=7767 tps=3.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:31:00,303] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3137024ca0b158f7fbce02895f3b8b8a attempt=1 +[2026-08-21 11:31:00,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3137024ca0b158f7fbce02895f3b8b8a status=400 post_dur=0.005s +[2026-08-21 11:31:00,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3137024ca0b158f7fbce02895f3b8b8a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:31:00,326] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dd2b4e9f218fe5b238ad972d25e4ce9c attempt=1 +[2026-08-21 11:31:00,945] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dd2b4e9f218fe5b238ad972d25e4ce9c status=200 post_dur=0.619s +[2026-08-21 11:51:32,211] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dd2b4e9f218fe5b238ad972d25e4ce9c total=1231885.5ms bytes=33281 finished=True finish=tool_calls stop=None out_tok=6132 prompt_tok=113398 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:51:32,221] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=826f76de33da93cb52b68dd1e522fce0 attempt=1 +[2026-08-21 11:51:32,663] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=826f76de33da93cb52b68dd1e522fce0 status=200 post_dur=0.442s +[2026-08-21 11:51:55,929] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=826f76de33da93cb52b68dd1e522fce0 total=23707.7ms bytes=34514 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=9003 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:51:55,936] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c6619b3df2f17997a2d9a003a5c4e4a4 attempt=1 +[2026-08-21 11:51:55,942] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c6619b3df2f17997a2d9a003a5c4e4a4 status=400 post_dur=0.006s +[2026-08-21 11:51:55,942] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c6619b3df2f17997a2d9a003a5c4e4a4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:51:55,965] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=667576259d250af5b1b7f7d5fa6cc434 attempt=1 +[2026-08-21 11:51:55,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=667576259d250af5b1b7f7d5fa6cc434 status=400 post_dur=0.004s +[2026-08-21 11:51:55,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=667576259d250af5b1b7f7d5fa6cc434 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:51:55,974] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8f202a6a1eeeb4687c0f209503e5d7bc attempt=1 +[2026-08-21 11:51:56,414] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8f202a6a1eeeb4687c0f209503e5d7bc status=200 post_dur=0.439s +[2026-08-21 11:52:23,917] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8f202a6a1eeeb4687c0f209503e5d7bc total=27942.3ms bytes=19750 finished=True finish=tool_calls stop=None out_tok=246 prompt_tok=9686 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:52:23,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=653bed13cc029a74eaccc52263ef6f80 attempt=1 +[2026-08-21 11:52:24,364] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=653bed13cc029a74eaccc52263ef6f80 status=200 post_dur=0.445s +[2026-08-21 11:52:36,290] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=653bed13cc029a74eaccc52263ef6f80 total=12370.4ms bytes=14338 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=9216 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:52:36,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f3ce331e0f79fbdcce0ad93e2af6686f attempt=1 +[2026-08-21 11:52:36,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f3ce331e0f79fbdcce0ad93e2af6686f status=400 post_dur=0.010s +[2026-08-21 11:52:36,318] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f3ce331e0f79fbdcce0ad93e2af6686f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:52:36,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77ffdf78bc0eae6e20df04d7ebf53e40 attempt=1 +[2026-08-21 11:52:36,800] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77ffdf78bc0eae6e20df04d7ebf53e40 status=200 post_dur=0.470s +[2026-08-21 11:53:46,672] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=77ffdf78bc0eae6e20df04d7ebf53e40 total=70342.4ms bytes=80966 finished=True finish=tool_calls stop=None out_tok=343 prompt_tok=27697 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:53:46,678] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=16a2123e386b959af0777eb22067ee15 attempt=1 +[2026-08-21 11:53:47,157] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=16a2123e386b959af0777eb22067ee15 status=200 post_dur=0.479s +[2026-08-21 11:54:35,269] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=16a2123e386b959af0777eb22067ee15 total=48591.0ms bytes=14186 finished=True finish=tool_calls stop=None out_tok=243 prompt_tok=23974 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:54:35,272] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b678cc3606725f288a48f46eb1c7c835 attempt=1 +[2026-08-21 11:54:35,710] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b678cc3606725f288a48f46eb1c7c835 status=200 post_dur=0.438s +[2026-08-21 11:55:10,851] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b678cc3606725f288a48f46eb1c7c835 total=35578.7ms bytes=29392 finished=True finish=tool_calls stop=None out_tok=386 prompt_tok=7229 tps=10.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:55:10,854] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9958a4cb4e36707148f90bb3f0622f40 attempt=1 +[2026-08-21 11:55:11,307] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9958a4cb4e36707148f90bb3f0622f40 status=200 post_dur=0.452s +[2026-08-21 11:55:47,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9958a4cb4e36707148f90bb3f0622f40 total=36672.0ms bytes=12083 finished=True finish=tool_calls stop=None out_tok=317 prompt_tok=11236 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:55:47,531] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=494364739f0e59882dd28de5f5fde603 attempt=1 +[2026-08-21 11:55:48,013] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=494364739f0e59882dd28de5f5fde603 status=200 post_dur=0.481s +[2026-08-21 11:56:28,300] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=494364739f0e59882dd28de5f5fde603 total=40768.7ms bytes=22176 finished=True finish=tool_calls stop=None out_tok=114 prompt_tok=24275 tps=2.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:56:28,306] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40ae7ef2c5585416574d7b9e4ed73887 attempt=1 +[2026-08-21 11:56:28,796] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40ae7ef2c5585416574d7b9e4ed73887 status=200 post_dur=0.490s +[2026-08-21 11:57:41,980] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40ae7ef2c5585416574d7b9e4ed73887 total=73673.5ms bytes=25145 finished=True finish=tool_calls stop=None out_tok=396 prompt_tok=29279 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:57:41,984] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=eef03a856669cef40ea937442e7b272e attempt=1 +[2026-08-21 11:57:42,442] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=eef03a856669cef40ea937442e7b272e status=200 post_dur=0.458s +[2026-08-21 11:58:05,002] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=eef03a856669cef40ea937442e7b272e total=23018.5ms bytes=21071 finished=True finish=tool_calls stop=None out_tok=159 prompt_tok=11866 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:58:05,005] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17cd2d1094cc3755b606aea1e0b43293 attempt=1 +[2026-08-21 11:58:05,443] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17cd2d1094cc3755b606aea1e0b43293 status=200 post_dur=0.438s +[2026-08-21 11:58:29,843] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17cd2d1094cc3755b606aea1e0b43293 total=24838.1ms bytes=18327 finished=True finish=tool_calls stop=None out_tok=240 prompt_tok=7689 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 11:58:29,850] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=51f93e4fe99fc13f642b02b7625e12e9 attempt=1 +[2026-08-21 11:58:29,861] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=51f93e4fe99fc13f642b02b7625e12e9 status=400 post_dur=0.006s +[2026-08-21 11:58:29,861] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=51f93e4fe99fc13f642b02b7625e12e9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 11:58:29,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9fb1a641cbd4ac84202fa6d111341dd9 attempt=1 +[2026-08-21 11:58:30,465] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9fb1a641cbd4ac84202fa6d111341dd9 status=200 post_dur=0.589s +[2026-08-21 12:01:08,719] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9fb1a641cbd4ac84202fa6d111341dd9 total=158844.8ms bytes=121387 finished=True finish=tool_calls stop=None out_tok=550 prompt_tok=73323 tps=3.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:01:08,727] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=079d189247c2005954c0ffafbc90f546 attempt=1 +[2026-08-21 12:01:09,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=079d189247c2005954c0ffafbc90f546 status=200 post_dur=0.495s +[2026-08-21 12:01:54,404] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=079d189247c2005954c0ffafbc90f546 total=45677.4ms bytes=11846 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=28542 tps=2.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:01:54,414] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ccb525ec15458844aa875194b2936b8 attempt=1 +[2026-08-21 12:01:55,039] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ccb525ec15458844aa875194b2936b8 status=200 post_dur=0.621s +[2026-08-21 12:05:47,859] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8ccb525ec15458844aa875194b2936b8 total=233444.5ms bytes=167472 finished=True finish=tool_calls stop=None out_tok=776 prompt_tok=89252 tps=3.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:05:47,867] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f4a0366dc8299d3f5ac66271db2df9a attempt=1 +[2026-08-21 12:05:48,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f4a0366dc8299d3f5ac66271db2df9a status=200 post_dur=0.449s +[2026-08-21 12:06:16,443] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f4a0366dc8299d3f5ac66271db2df9a total=28575.9ms bytes=16689 finished=True finish=tool_calls stop=None out_tok=242 prompt_tok=11967 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:06:16,463] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cebd4d9abe71d1d144a78ed61dd6c4dc attempt=1 +[2026-08-21 12:06:16,473] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cebd4d9abe71d1d144a78ed61dd6c4dc status=400 post_dur=0.010s +[2026-08-21 12:06:16,474] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=cebd4d9abe71d1d144a78ed61dd6c4dc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:06:16,487] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b91db1e602c6992d29502b3359891b9c attempt=1 +[2026-08-21 12:06:17,014] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b91db1e602c6992d29502b3359891b9c status=200 post_dur=0.527s +[2026-08-21 12:10:24,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b91db1e602c6992d29502b3359891b9c total=248483.1ms bytes=435697 finished=True finish=tool_calls stop=None out_tok=1583 prompt_tok=44013 tps=6.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:10:24,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=88449d7c1e901f5dc7b8950e03ee286a attempt=1 +[2026-08-21 12:10:25,004] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=88449d7c1e901f5dc7b8950e03ee286a status=400 post_dur=0.010s +[2026-08-21 12:10:25,004] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=88449d7c1e901f5dc7b8950e03ee286a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:10:25,014] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a52e198bc3b053b9794f62a54f694d58 attempt=1 +[2026-08-21 12:10:25,503] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a52e198bc3b053b9794f62a54f694d58 status=200 post_dur=0.488s +[2026-08-21 12:10:58,777] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a52e198bc3b053b9794f62a54f694d58 total=33763.0ms bytes=22728 finished=True finish=tool_calls stop=None out_tok=214 prompt_tok=27642 tps=6.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:10:58,792] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1e8a1d182746d47cd271f17406d129a5 attempt=1 +[2026-08-21 12:10:58,800] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1e8a1d182746d47cd271f17406d129a5 status=400 post_dur=0.007s +[2026-08-21 12:10:58,800] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1e8a1d182746d47cd271f17406d129a5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 12:10:58,811] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff264c049c849d4f5084847624476a1e attempt=1 +[2026-08-21 12:10:59,346] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff264c049c849d4f5084847624476a1e status=200 post_dur=0.532s +[2026-08-21 12:17:39,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff264c049c849d4f5084847624476a1e total=400715.6ms bytes=835980 finished=True finish=stop stop=None out_tok=2882 prompt_tok=47563 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:17:39,537] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74e4c061b27775a11f5fcde024f01279 attempt=1 +[2026-08-21 12:17:40,031] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74e4c061b27775a11f5fcde024f01279 status=200 post_dur=0.494s +[2026-08-21 12:18:10,495] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74e4c061b27775a11f5fcde024f01279 total=30958.7ms bytes=5597 finished=True finish=tool_calls stop=None out_tok=52 prompt_tok=29042 tps=1.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:18:10,500] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=15ae6478087342edb4fccc7ff69d87ac attempt=1 +[2026-08-21 12:18:10,963] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=15ae6478087342edb4fccc7ff69d87ac status=200 post_dur=0.463s +[2026-08-21 12:19:03,421] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=15ae6478087342edb4fccc7ff69d87ac total=52921.5ms bytes=27879 finished=True finish=tool_calls stop=None out_tok=520 prompt_tok=15058 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:19:03,426] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=058c90071a1209165674024c2bed02ab attempt=1 +[2026-08-21 12:19:03,920] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=058c90071a1209165674024c2bed02ab status=200 post_dur=0.493s +[2026-08-21 12:19:17,656] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=058c90071a1209165674024c2bed02ab total=14230.0ms bytes=9437 finished=True finish=tool_calls stop=None out_tok=65 prompt_tok=29199 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:19:17,661] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=afa1d00e3635cde58cca667f6ee50fef attempt=1 +[2026-08-21 12:19:18,109] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=afa1d00e3635cde58cca667f6ee50fef status=200 post_dur=0.447s +[2026-08-21 12:19:53,821] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=afa1d00e3635cde58cca667f6ee50fef total=36159.5ms bytes=26477 finished=True finish=tool_calls stop=None out_tok=294 prompt_tok=15965 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:19:53,834] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bfecd14065d52362c7d2fac1bfc696f2 attempt=1 +[2026-08-21 12:19:54,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bfecd14065d52362c7d2fac1bfc696f2 status=200 post_dur=0.643s +[2026-08-21 12:29:47,465] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bfecd14065d52362c7d2fac1bfc696f2 total=593631.9ms bytes=50933 finished=True finish=tool_calls stop=None out_tok=2594 prompt_tok=110846 tps=4.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:29:47,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cb98ecfe0b976a41aa206ff09cf1a59a attempt=1 +[2026-08-21 12:29:47,942] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cb98ecfe0b976a41aa206ff09cf1a59a status=200 post_dur=0.465s +[2026-08-21 12:30:27,276] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cb98ecfe0b976a41aa206ff09cf1a59a total=39799.1ms bytes=66167 finished=True finish=tool_calls stop=None out_tok=335 prompt_tok=18014 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:30:27,278] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9b50b9d920eefddcc46c2bdbe4efe955 attempt=1 +[2026-08-21 12:30:27,586] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9b50b9d920eefddcc46c2bdbe4efe955 status=200 post_dur=0.307s +[2026-08-21 12:37:01,552] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9b50b9d920eefddcc46c2bdbe4efe955 total=394273.2ms bytes=1343072 finished=True finish=stop stop=None out_tok=4617 prompt_tok=536 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:37:01,559] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8ad06619f68dc319f128ab083bc9035e attempt=1 +[2026-08-21 12:37:02,041] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8ad06619f68dc319f128ab083bc9035e status=200 post_dur=0.481s +[2026-08-21 12:37:56,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8ad06619f68dc319f128ab083bc9035e total=55275.9ms bytes=33583 finished=True finish=tool_calls stop=None out_tok=488 prompt_tok=19077 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:37:56,854] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5b8abb39b4e491d993523c0eca33a733 attempt=1 +[2026-08-21 12:37:56,878] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5b8abb39b4e491d993523c0eca33a733 status=400 post_dur=0.012s +[2026-08-21 12:37:56,879] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5b8abb39b4e491d993523c0eca33a733 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:37:56,909] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=38fa4bbb7e77481d6d22ca00a573bd1d attempt=1 +[2026-08-21 12:37:56,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=38fa4bbb7e77481d6d22ca00a573bd1d status=400 post_dur=0.009s +[2026-08-21 12:37:56,920] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=38fa4bbb7e77481d6d22ca00a573bd1d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:37:56,930] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6370cfdf8af78056bb4f79167cc689e1 attempt=1 +[2026-08-21 12:37:57,397] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6370cfdf8af78056bb4f79167cc689e1 status=200 post_dur=0.466s +[2026-08-21 12:38:32,784] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6370cfdf8af78056bb4f79167cc689e1 total=35853.6ms bytes=69828 finished=True finish=tool_calls stop=None out_tok=360 prompt_tok=19748 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:38:32,793] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 26% (176/881) has_cb=True +[2026-08-21 12:38:32,802] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e83d730f4005cd76724ac91454d8f354 attempt=1 +[2026-08-21 12:38:32,813] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e83d730f4005cd76724ac91454d8f354 status=400 post_dur=0.010s +[2026-08-21 12:38:32,813] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e83d730f4005cd76724ac91454d8f354 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:38:32,822] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1f87d33fb2f2650b0513a62f57a7f997 attempt=1 +[2026-08-21 12:38:33,260] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1f87d33fb2f2650b0513a62f57a7f997 status=200 post_dur=0.437s +[2026-08-21 12:38:58,218] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1f87d33fb2f2650b0513a62f57a7f997 total=25395.4ms bytes=11549 finished=True finish=tool_calls stop=None out_tok=200 prompt_tok=8693 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:38:58,223] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=777c59452201b179009a4078f2a02391 attempt=1 +[2026-08-21 12:38:58,687] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=777c59452201b179009a4078f2a02391 status=200 post_dur=0.465s +[2026-08-21 12:39:43,612] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=777c59452201b179009a4078f2a02391 total=45389.1ms bytes=122098 finished=True finish=stop stop=None out_tok=424 prompt_tok=20156 tps=9.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:39:43,617] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=13ef3fc060013bd95196da61a1bf3df1 attempt=1 +[2026-08-21 12:39:44,086] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=13ef3fc060013bd95196da61a1bf3df1 status=200 post_dur=0.468s +[2026-08-21 12:40:07,063] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=13ef3fc060013bd95196da61a1bf3df1 total=23445.1ms bytes=19580 finished=True finish=tool_calls stop=None out_tok=221 prompt_tok=20034 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:40:07,066] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d0073c44f216fc29f0a510fc3fb6f88f attempt=1 +[2026-08-21 12:40:07,496] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d0073c44f216fc29f0a510fc3fb6f88f status=200 post_dur=0.430s +[2026-08-21 12:41:05,190] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d0073c44f216fc29f0a510fc3fb6f88f total=58124.1ms bytes=89493 finished=True finish=tool_calls stop=None out_tok=547 prompt_tok=9626 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:41:05,195] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1e11e493ec17ec803d1b586f3fc4b8ee attempt=1 +[2026-08-21 12:41:05,662] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1e11e493ec17ec803d1b586f3fc4b8ee status=200 post_dur=0.467s +[2026-08-21 12:41:25,873] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1e11e493ec17ec803d1b586f3fc4b8ee total=20677.9ms bytes=26030 finished=True finish=tool_calls stop=None out_tok=144 prompt_tok=21261 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:41:25,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ee033f311208961f19432ec0d1c43f74 attempt=1 +[2026-08-21 12:41:26,171] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ee033f311208961f19432ec0d1c43f74 status=200 post_dur=0.294s +[2026-08-21 12:43:50,344] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ee033f311208961f19432ec0d1c43f74 total=144467.2ms bytes=478707 finished=True finish=stop stop=None out_tok=1646 prompt_tok=370 tps=11.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:43:50,366] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d18c2e5de51873f089bfbe539048656e attempt=1 +[2026-08-21 12:43:50,378] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d18c2e5de51873f089bfbe539048656e status=400 post_dur=0.011s +[2026-08-21 12:43:50,378] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d18c2e5de51873f089bfbe539048656e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:43:50,387] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03b5d62aa68619706ebb2d1ea390d59e attempt=1 +[2026-08-21 12:43:50,684] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03b5d62aa68619706ebb2d1ea390d59e status=200 post_dur=0.295s +[2026-08-21 12:51:21,647] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03b5d62aa68619706ebb2d1ea390d59e total=451260.4ms bytes=1558295 finished=True finish=stop stop=None out_tok=5362 prompt_tok=536 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:51:21,722] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=966d726aa90dd5d5b683f08f61b54b3d attempt=1 +[2026-08-21 12:51:21,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=966d726aa90dd5d5b683f08f61b54b3d status=400 post_dur=0.021s +[2026-08-21 12:51:21,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=966d726aa90dd5d5b683f08f61b54b3d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:51:21,754] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45573e6a72fff1a858f00441c401c4c4 attempt=1 +[2026-08-21 12:51:22,230] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45573e6a72fff1a858f00441c401c4c4 status=200 post_dur=0.476s +[2026-08-21 12:51:46,363] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45573e6a72fff1a858f00441c401c4c4 total=24609.1ms bytes=66201 finished=True finish=stop stop=None out_tok=230 prompt_tok=21583 tps=9.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:51:46,369] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=76c94ffa10f26e0703a5abb6aa70e111 attempt=1 +[2026-08-21 12:51:46,832] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=76c94ffa10f26e0703a5abb6aa70e111 status=200 post_dur=0.463s +[2026-08-21 12:52:10,068] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=76c94ffa10f26e0703a5abb6aa70e111 total=23699.3ms bytes=65081 finished=True finish=stop stop=None out_tok=224 prompt_tok=21832 tps=9.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:52:10,092] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=71d4542befba35217656f1d77ae23ee3 attempt=1 +[2026-08-21 12:52:10,105] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=71d4542befba35217656f1d77ae23ee3 status=400 post_dur=0.012s +[2026-08-21 12:52:10,105] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=71d4542befba35217656f1d77ae23ee3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:52:10,117] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a374aadb665f75a3226b2641582b9df0 attempt=1 +[2026-08-21 12:52:10,541] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a374aadb665f75a3226b2641582b9df0 status=200 post_dur=0.424s +[2026-08-21 12:52:24,391] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a374aadb665f75a3226b2641582b9df0 total=14274.6ms bytes=8731 finished=True finish=stop stop=None out_tok=29 prompt_tok=7390 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:52:24,394] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f69182640ddc1ee2d8fb9e0354826a6c attempt=1 +[2026-08-21 12:52:24,814] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f69182640ddc1ee2d8fb9e0354826a6c status=200 post_dur=0.420s +[2026-08-21 12:52:32,724] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f69182640ddc1ee2d8fb9e0354826a6c total=8329.9ms bytes=8155 finished=True finish=stop stop=None out_tok=27 prompt_tok=7479 tps=3.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:52:32,736] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=98fef617f4f3b71afa4ed7f95fd3e8cf attempt=1 +[2026-08-21 12:52:32,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=98fef617f4f3b71afa4ed7f95fd3e8cf status=400 post_dur=0.006s +[2026-08-21 12:52:32,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=98fef617f4f3b71afa4ed7f95fd3e8cf status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 12:52:32,752] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e0931547ccd69d58ff457e4e8a232a2e attempt=1 +[2026-08-21 12:52:33,171] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e0931547ccd69d58ff457e4e8a232a2e status=200 post_dur=0.419s +[2026-08-21 12:53:00,175] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e0931547ccd69d58ff457e4e8a232a2e total=27423.7ms bytes=34791 finished=True finish=tool_calls stop=None out_tok=310 prompt_tok=7229 tps=11.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:53:00,177] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=59c442b5a51cadb423c6b60f147cb1d6 attempt=1 +[2026-08-21 12:53:00,473] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=59c442b5a51cadb423c6b60f147cb1d6 status=200 post_dur=0.296s +[2026-08-21 12:55:57,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=59c442b5a51cadb423c6b60f147cb1d6 total=177532.2ms bytes=596875 finished=True finish=length stop=None out_tok=2048 prompt_tok=674 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:55:57,713] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ad97d90fb5b28a960b1c03c66639d428 attempt=1 +[2026-08-21 12:55:58,161] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ad97d90fb5b28a960b1c03c66639d428 status=200 post_dur=0.448s +[2026-08-21 12:56:27,603] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ad97d90fb5b28a960b1c03c66639d428 total=29889.7ms bytes=15037 finished=True finish=tool_calls stop=None out_tok=210 prompt_tok=7646 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:56:27,605] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5de2573e7ffdf925143010f6e6d9c571 attempt=1 +[2026-08-21 12:56:28,044] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5de2573e7ffdf925143010f6e6d9c571 status=200 post_dur=0.439s +[2026-08-21 12:56:56,597] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5de2573e7ffdf925143010f6e6d9c571 total=28991.5ms bytes=24644 finished=True finish=tool_calls stop=None out_tok=254 prompt_tok=8402 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:56:56,600] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b68737ce69afc08685d35bf935d2eb2 attempt=1 +[2026-08-21 12:56:57,045] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b68737ce69afc08685d35bf935d2eb2 status=200 post_dur=0.445s +[2026-08-21 12:57:35,487] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b68737ce69afc08685d35bf935d2eb2 total=38887.0ms bytes=102654 finished=True finish=stop stop=None out_tok=347 prompt_tok=11385 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:57:35,491] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bb6de925ae6246f4b54248dbf225fb8b attempt=1 +[2026-08-21 12:57:35,931] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bb6de925ae6246f4b54248dbf225fb8b status=200 post_dur=0.440s +[2026-08-21 12:58:01,530] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bb6de925ae6246f4b54248dbf225fb8b total=26039.1ms bytes=19805 finished=True finish=tool_calls stop=None out_tok=203 prompt_tok=9348 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:58:01,532] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7c0c1024bfb5552c607eb33016de858 attempt=1 +[2026-08-21 12:58:01,976] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7c0c1024bfb5552c607eb33016de858 status=200 post_dur=0.443s +[2026-08-21 12:58:24,414] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7c0c1024bfb5552c607eb33016de858 total=22881.5ms bytes=62705 finished=True finish=stop stop=None out_tok=213 prompt_tok=9998 tps=9.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:58:24,434] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=009dde816fc3acb4cc10671f347bbd03 attempt=1 +[2026-08-21 12:58:24,444] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=009dde816fc3acb4cc10671f347bbd03 status=400 post_dur=0.011s +[2026-08-21 12:58:24,445] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=009dde816fc3acb4cc10671f347bbd03 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 12:58:24,456] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=458a7fd31d1b277ba75cc38c2eb73c1d attempt=1 +[2026-08-21 12:58:24,886] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=458a7fd31d1b277ba75cc38c2eb73c1d status=200 post_dur=0.430s +[2026-08-21 12:58:54,400] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=458a7fd31d1b277ba75cc38c2eb73c1d total=29943.4ms bytes=23407 finished=True finish=tool_calls stop=None out_tok=182 prompt_tok=9805 tps=6.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:58:54,402] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=17b6876da090ee233e27a16837a4388d attempt=1 +[2026-08-21 12:58:54,846] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=17b6876da090ee233e27a16837a4388d status=200 post_dur=0.444s +[2026-08-21 12:59:08,367] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=17b6876da090ee233e27a16837a4388d total=13964.2ms bytes=15927 finished=True finish=tool_calls stop=None out_tok=95 prompt_tok=11629 tps=6.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:59:08,370] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44ee2e606690216969520a15bba4e844 attempt=1 +[2026-08-21 12:59:08,792] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44ee2e606690216969520a15bba4e844 status=200 post_dur=0.422s +[2026-08-21 12:59:45,191] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44ee2e606690216969520a15bba4e844 total=36821.3ms bytes=30074 finished=True finish=tool_calls stop=None out_tok=297 prompt_tok=10021 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 12:59:45,193] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48f34154f82351bd849d658039fa2da1 attempt=1 +[2026-08-21 12:59:45,631] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48f34154f82351bd849d658039fa2da1 status=200 post_dur=0.437s +[2026-08-21 13:00:05,398] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48f34154f82351bd849d658039fa2da1 total=20204.2ms bytes=25774 finished=True finish=tool_calls stop=None out_tok=132 prompt_tok=7197 tps=6.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:00:05,411] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=554c0cc7053b81d2ac40541165710ef5 attempt=1 +[2026-08-21 13:00:05,419] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=554c0cc7053b81d2ac40541165710ef5 status=400 post_dur=0.007s +[2026-08-21 13:00:05,419] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=554c0cc7053b81d2ac40541165710ef5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 13:00:05,428] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c4908254d2033142cf448b88583d10a0 attempt=1 +[2026-08-21 13:00:05,873] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c4908254d2033142cf448b88583d10a0 status=200 post_dur=0.445s +[2026-08-21 13:00:29,751] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c4908254d2033142cf448b88583d10a0 total=24322.8ms bytes=16248 finished=True finish=tool_calls stop=None out_tok=185 prompt_tok=11879 tps=7.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:00:29,753] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6c12607de0607a2542939b0805f7e16f attempt=1 +[2026-08-21 13:00:30,183] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6c12607de0607a2542939b0805f7e16f status=200 post_dur=0.430s +[2026-08-21 13:00:41,887] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6c12607de0607a2542939b0805f7e16f total=12133.5ms bytes=9685 finished=True finish=tool_calls stop=None out_tok=74 prompt_tok=7419 tps=6.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:00:41,889] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=eab9e55d270895fac52faab687b358d6 attempt=1 +[2026-08-21 13:00:42,313] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=eab9e55d270895fac52faab687b358d6 status=200 post_dur=0.424s +[2026-08-21 13:01:06,085] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=eab9e55d270895fac52faab687b358d6 total=24195.4ms bytes=13352 finished=True finish=tool_calls stop=None out_tok=197 prompt_tok=12157 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:01:06,087] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d5066b7438d6fab3349d202019b3d923 attempt=1 +[2026-08-21 13:01:06,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d5066b7438d6fab3349d202019b3d923 status=200 post_dur=0.440s +[2026-08-21 13:01:22,051] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d5066b7438d6fab3349d202019b3d923 total=15963.8ms bytes=8097 finished=True finish=tool_calls stop=None out_tok=115 prompt_tok=7703 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:01:22,069] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f6ba3a16a963f964c09513ef3f2ecdf4 attempt=1 +[2026-08-21 13:01:22,078] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f6ba3a16a963f964c09513ef3f2ecdf4 status=400 post_dur=0.008s +[2026-08-21 13:01:22,078] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f6ba3a16a963f964c09513ef3f2ecdf4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 13:01:22,103] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=77a2c20c0bf4bd84bd95d71569134530 attempt=1 +[2026-08-21 13:01:22,111] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=77a2c20c0bf4bd84bd95d71569134530 status=400 post_dur=0.009s +[2026-08-21 13:01:22,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=77a2c20c0bf4bd84bd95d71569134530 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 13:01:22,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f525460d67a79e7c9785eeca7c9c368b attempt=1 +[2026-08-21 13:01:22,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f525460d67a79e7c9785eeca7c9c368b status=200 post_dur=0.410s +[2026-08-21 13:01:39,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f525460d67a79e7c9785eeca7c9c368b total=17849.1ms bytes=11051 finished=True finish=tool_calls stop=None out_tok=132 prompt_tok=7814 tps=7.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:01:39,972] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f565b7fa99ac804074f2c75449643828 attempt=1 +[2026-08-21 13:01:40,413] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f565b7fa99ac804074f2c75449643828 status=200 post_dur=0.441s +[2026-08-21 13:01:46,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f565b7fa99ac804074f2c75449643828 total=6337.9ms bytes=7580 finished=True finish=stop stop=None out_tok=25 prompt_tok=8074 tps=3.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:01:46,312] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9133cdea736e26b36553213ed50256df attempt=1 +[2026-08-21 13:01:46,728] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9133cdea736e26b36553213ed50256df status=200 post_dur=0.416s +[2026-08-21 13:01:52,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9133cdea736e26b36553213ed50256df total=5997.8ms bytes=7868 finished=True finish=stop stop=None out_tok=26 prompt_tok=7944 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:01:52,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ae7a4ff3045ad8b088a55a71be801710 attempt=1 +[2026-08-21 13:01:52,337] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ae7a4ff3045ad8b088a55a71be801710 status=400 post_dur=0.009s +[2026-08-21 13:01:52,338] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ae7a4ff3045ad8b088a55a71be801710 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 13:01:52,348] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b645cf1d05ada3289f87b46397f9efc attempt=1 +[2026-08-21 13:01:52,767] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b645cf1d05ada3289f87b46397f9efc status=200 post_dur=0.419s +[2026-08-21 13:02:26,812] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b645cf1d05ada3289f87b46397f9efc total=34463.9ms bytes=23415 finished=True finish=tool_calls stop=None out_tok=313 prompt_tok=12841 tps=9.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:02:26,815] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0659326491f8067412c4f1c8f9ae6c01 attempt=1 +[2026-08-21 13:02:27,260] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0659326491f8067412c4f1c8f9ae6c01 status=200 post_dur=0.445s +[2026-08-21 13:02:53,933] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0659326491f8067412c4f1c8f9ae6c01 total=27118.1ms bytes=14167 finished=True finish=tool_calls stop=None out_tok=219 prompt_tok=13182 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:02:53,935] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=37986f79399dfb3e4b1b70aa905c22e6 attempt=1 +[2026-08-21 13:02:54,227] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=37986f79399dfb3e4b1b70aa905c22e6 status=200 post_dur=0.292s +[2026-08-21 13:05:25,893] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=37986f79399dfb3e4b1b70aa905c22e6 total=151958.0ms bytes=510332 finished=True finish=stop stop=None out_tok=1753 prompt_tok=571 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:05:25,896] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48458299fcceb2bf195b62b03f2590a7 attempt=1 +[2026-08-21 13:05:26,362] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48458299fcceb2bf195b62b03f2590a7 status=200 post_dur=0.465s +[2026-08-21 13:05:50,815] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48458299fcceb2bf195b62b03f2590a7 total=24918.9ms bytes=21890 finished=True finish=tool_calls stop=None out_tok=204 prompt_tok=13381 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:05:50,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cf84a1354f68d39cea0201b556ad5c96 attempt=1 +[2026-08-21 13:05:50,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cf84a1354f68d39cea0201b556ad5c96 status=400 post_dur=0.010s +[2026-08-21 13:05:50,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=cf84a1354f68d39cea0201b556ad5c96 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 13:05:50,854] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e1bb149f25198dfd6e3cabea2fc78fb attempt=1 +[2026-08-21 13:05:50,854] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 30% (220/881) has_cb=True +[2026-08-21 13:05:51,147] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e1bb149f25198dfd6e3cabea2fc78fb status=200 post_dur=0.293s +[2026-08-21 13:17:05,182] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e1bb149f25198dfd6e3cabea2fc78fb total=674328.2ms bytes=2302248 finished=True finish=stop stop=None out_tok=7900 prompt_tok=4570 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:17:05,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d566dbf5f98af5b5e4a14afb454bcd4a attempt=1 +[2026-08-21 13:17:05,220] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d566dbf5f98af5b5e4a14afb454bcd4a status=400 post_dur=0.011s +[2026-08-21 13:17:05,220] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d566dbf5f98af5b5e4a14afb454bcd4a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 13:17:05,230] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1bffc6d6fac1750d40cc0e93a6ef3758 attempt=1 +[2026-08-21 13:17:05,545] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1bffc6d6fac1750d40cc0e93a6ef3758 status=200 post_dur=0.308s +[2026-08-21 13:32:44,659] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1bffc6d6fac1750d40cc0e93a6ef3758 total=939428.1ms bytes=3171334 finished=True finish=stop stop=None out_tok=10947 prompt_tok=7026 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:32:44,672] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23682db8af25c58464b1efba92034f89 attempt=1 +[2026-08-21 13:32:45,243] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23682db8af25c58464b1efba92034f89 status=200 post_dur=0.571s +[2026-08-21 13:33:28,456] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=23682db8af25c58464b1efba92034f89 total=43783.7ms bytes=46121 finished=True finish=tool_calls stop=None out_tok=443 prompt_tok=14926 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:33:28,460] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40cd8d8aed528adbf0c19beeb7f32ea0 attempt=1 +[2026-08-21 13:33:28,927] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40cd8d8aed528adbf0c19beeb7f32ea0 status=200 post_dur=0.467s +[2026-08-21 13:33:55,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40cd8d8aed528adbf0c19beeb7f32ea0 total=27514.8ms bytes=16863 finished=True finish=tool_calls stop=None out_tok=265 prompt_tok=15858 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 13:33:55,985] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=efcd74850ca1e15747878498ed0d6a3a attempt=1 +[2026-08-21 13:33:56,602] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=efcd74850ca1e15747878498ed0d6a3a status=200 post_dur=0.615s +[2026-08-21 14:06:14,981] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=efcd74850ca1e15747878498ed0d6a3a total=1938996.3ms bytes=262459 finished=True finish=tool_calls stop=None out_tok=12160 prompt_tok=78545 tps=6.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:06:14,991] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c4f19bd7d83f90e15736800abb3d9c11 attempt=1 +[2026-08-21 14:06:15,292] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c4f19bd7d83f90e15736800abb3d9c11 status=200 post_dur=0.301s +[2026-08-21 14:08:30,992] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c4f19bd7d83f90e15736800abb3d9c11 total=136000.7ms bytes=453418 finished=True finish=stop stop=None out_tok=1571 prompt_tok=620 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:08:30,996] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=315ef0cd61b2a648f9a133900198f1cf attempt=1 +[2026-08-21 14:08:31,467] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=315ef0cd61b2a648f9a133900198f1cf status=200 post_dur=0.471s +[2026-08-21 14:08:59,034] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=315ef0cd61b2a648f9a133900198f1cf total=28037.5ms bytes=27313 finished=True finish=tool_calls stop=None out_tok=222 prompt_tok=16471 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:08:59,038] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=48155b6bee74a3bae6e9b0e741b22729 attempt=1 +[2026-08-21 14:08:59,523] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=48155b6bee74a3bae6e9b0e741b22729 status=200 post_dur=0.484s +[2026-08-21 14:09:35,505] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=48155b6bee74a3bae6e9b0e741b22729 total=36466.4ms bytes=53227 finished=True finish=tool_calls stop=None out_tok=308 prompt_tok=16668 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:09:35,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e0911ecde78482595ec62539993f1a51 attempt=1 +[2026-08-21 14:09:35,815] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e0911ecde78482595ec62539993f1a51 status=200 post_dur=0.307s +[2026-08-21 14:13:19,433] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e0911ecde78482595ec62539993f1a51 total=223925.6ms bytes=765334 finished=True finish=stop stop=None out_tok=2633 prompt_tok=365 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:13:19,436] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f1b45eab94135ecedbd73838841b83dd attempt=1 +[2026-08-21 14:13:19,737] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f1b45eab94135ecedbd73838841b83dd status=200 post_dur=0.301s +[2026-08-21 14:16:14,434] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f1b45eab94135ecedbd73838841b83dd total=174997.9ms bytes=596497 finished=True finish=length stop=None out_tok=2048 prompt_tok=347 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:16:14,438] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=25c94e38181bd1e5ae0bfc0937fd46f3 attempt=1 +[2026-08-21 14:16:14,900] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=25c94e38181bd1e5ae0bfc0937fd46f3 status=200 post_dur=0.463s +[2026-08-21 14:16:53,739] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=25c94e38181bd1e5ae0bfc0937fd46f3 total=39300.9ms bytes=37132 finished=True finish=tool_calls stop=None out_tok=453 prompt_tok=7229 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:16:53,742] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea138743339a5ff7727e824177ddc131 attempt=1 +[2026-08-21 14:16:54,181] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea138743339a5ff7727e824177ddc131 status=200 post_dur=0.439s +[2026-08-21 14:17:02,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea138743339a5ff7727e824177ddc131 total=8933.6ms bytes=13802 finished=True finish=tool_calls stop=None out_tok=91 prompt_tok=7197 tps=10.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:17:02,678] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4974db681bd93f2c8b2352385fdd97c3 attempt=1 +[2026-08-21 14:17:03,079] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4974db681bd93f2c8b2352385fdd97c3 status=200 post_dur=0.402s +[2026-08-21 14:17:20,751] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4974db681bd93f2c8b2352385fdd97c3 total=18073.5ms bytes=14167 finished=True finish=tool_calls stop=None out_tok=78 prompt_tok=7307 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:17:20,754] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49b88cd23e172cd2b84ae1c44804a9ea attempt=1 +[2026-08-21 14:17:21,183] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49b88cd23e172cd2b84ae1c44804a9ea status=200 post_dur=0.430s +[2026-08-21 14:17:32,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=49b88cd23e172cd2b84ae1c44804a9ea total=11723.7ms bytes=6086 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=7759 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:17:32,496] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e0d5a0196fbbbe5a3bf287e9d26718a attempt=1 +[2026-08-21 14:17:32,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e0d5a0196fbbbe5a3bf287e9d26718a status=400 post_dur=0.010s +[2026-08-21 14:17:32,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3e0d5a0196fbbbe5a3bf287e9d26718a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 14:17:32,517] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f4ba4ddb09108e29c6acde545ccf2ce2 attempt=1 +[2026-08-21 14:17:32,935] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f4ba4ddb09108e29c6acde545ccf2ce2 status=200 post_dur=0.417s +[2026-08-21 14:17:43,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f4ba4ddb09108e29c6acde545ccf2ce2 total=11327.6ms bytes=12155 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=8029 tps=7.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:17:43,847] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9f749b36e5f09b5dadad96cbc136ca65 attempt=1 +[2026-08-21 14:17:44,277] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9f749b36e5f09b5dadad96cbc136ca65 status=200 post_dur=0.429s +[2026-08-21 14:18:16,508] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9f749b36e5f09b5dadad96cbc136ca65 total=32660.3ms bytes=11780 finished=True finish=tool_calls stop=None out_tok=280 prompt_tok=9450 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:18:16,513] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7171fc3bc036a7e3f7f8483edd20c795 attempt=1 +[2026-08-21 14:18:16,976] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7171fc3bc036a7e3f7f8483edd20c795 status=200 post_dur=0.463s +[2026-08-21 14:18:46,379] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7171fc3bc036a7e3f7f8483edd20c795 total=29865.7ms bytes=60700 finished=True finish=stop stop=None out_tok=206 prompt_tok=9787 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:18:46,383] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6ebcfc88241a7349a60a9b64addf2725 attempt=1 +[2026-08-21 14:18:46,824] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6ebcfc88241a7349a60a9b64addf2725 status=200 post_dur=0.441s +[2026-08-21 14:18:59,850] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6ebcfc88241a7349a60a9b64addf2725 total=13466.7ms bytes=21014 finished=True finish=stop stop=None out_tok=72 prompt_tok=8386 tps=5.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:18:59,853] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ff73752fbb7433419099a8511754f987 attempt=1 +[2026-08-21 14:19:00,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ff73752fbb7433419099a8511754f987 status=200 post_dur=0.432s +[2026-08-21 14:19:08,665] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ff73752fbb7433419099a8511754f987 total=8812.5ms bytes=15569 finished=True finish=stop stop=None out_tok=53 prompt_tok=8608 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:19:08,686] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=90d12d82d9614d497c44f712d66d057d attempt=1 +[2026-08-21 14:19:08,696] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=90d12d82d9614d497c44f712d66d057d status=400 post_dur=0.009s +[2026-08-21 14:19:08,696] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=90d12d82d9614d497c44f712d66d057d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 14:19:08,707] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=78a85b9994fd97dcbc014c08a24db6d0 attempt=1 +[2026-08-21 14:19:09,116] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=78a85b9994fd97dcbc014c08a24db6d0 status=200 post_dur=0.409s +[2026-08-21 14:19:37,885] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=78a85b9994fd97dcbc014c08a24db6d0 total=29178.1ms bytes=71901 finished=True finish=stop stop=None out_tok=248 prompt_tok=8615 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:19:37,888] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5662b2bbd9e414513008b4bceb92f818 attempt=1 +[2026-08-21 14:19:38,331] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5662b2bbd9e414513008b4bceb92f818 status=200 post_dur=0.443s +[2026-08-21 14:19:52,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5662b2bbd9e414513008b4bceb92f818 total=14409.0ms bytes=10318 finished=True finish=tool_calls stop=None out_tok=71 prompt_tok=10916 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:19:52,300] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ddb6a8dffccee8b7bfbd59c50410c50 attempt=1 +[2026-08-21 14:19:52,740] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ddb6a8dffccee8b7bfbd59c50410c50 status=200 post_dur=0.440s +[2026-08-21 14:20:11,552] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ddb6a8dffccee8b7bfbd59c50410c50 total=19252.4ms bytes=26195 finished=True finish=stop stop=None out_tok=90 prompt_tok=8831 tps=4.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:20:11,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dc73696f73b0fe3f59a59ffe53007225 attempt=1 +[2026-08-21 14:20:11,843] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dc73696f73b0fe3f59a59ffe53007225 status=200 post_dur=0.289s +[2026-08-21 14:22:57,006] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dc73696f73b0fe3f59a59ffe53007225 total=165452.2ms bytes=563317 finished=True finish=stop stop=None out_tok=1937 prompt_tok=392 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:22:57,009] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6375e08fbebeb80f77edcc00d59b289 attempt=1 +[2026-08-21 14:22:57,315] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6375e08fbebeb80f77edcc00d59b289 status=200 post_dur=0.306s +[2026-08-21 14:25:49,175] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6375e08fbebeb80f77edcc00d59b289 total=172165.8ms bytes=596360 finished=True finish=length stop=None out_tok=2048 prompt_tok=392 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:25:49,195] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d427f650b2405bc6faf0259ec53fa73 attempt=1 +[2026-08-21 14:25:49,878] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d427f650b2405bc6faf0259ec53fa73 status=200 post_dur=0.683s +[2026-08-21 14:37:00,705] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3d427f650b2405bc6faf0259ec53fa73 total=671509.9ms bytes=19692 finished=True finish=tool_calls stop=None out_tok=2529 prompt_tok=125231 tps=3.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:37:00,716] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=50b915b9dfb222d7395005cef54051a5 attempt=1 +[2026-08-21 14:37:01,226] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=50b915b9dfb222d7395005cef54051a5 status=200 post_dur=0.511s +[2026-08-21 14:37:49,098] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=50b915b9dfb222d7395005cef54051a5 total=48382.0ms bytes=21587 finished=True finish=tool_calls stop=None out_tok=112 prompt_tok=31595 tps=2.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:37:49,102] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c6b7b47ee76b8533b7a98cc16c313084 attempt=1 +[2026-08-21 14:37:49,535] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c6b7b47ee76b8533b7a98cc16c313084 status=200 post_dur=0.433s +[2026-08-21 14:38:20,496] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c6b7b47ee76b8533b7a98cc16c313084 total=31393.8ms bytes=16752 finished=True finish=tool_calls stop=None out_tok=219 prompt_tok=8030 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:38:20,501] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ec2ff62b72bbcd3995e27d992648334 attempt=1 +[2026-08-21 14:38:21,007] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ec2ff62b72bbcd3995e27d992648334 status=200 post_dur=0.505s +[2026-08-21 14:39:54,932] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ec2ff62b72bbcd3995e27d992648334 total=94430.6ms bytes=43739 finished=True finish=tool_calls stop=None out_tok=452 prompt_tok=34100 tps=4.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:39:54,937] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3cefef050a3ee8ca33860c658f11845c attempt=1 +[2026-08-21 14:39:55,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3cefef050a3ee8ca33860c658f11845c status=200 post_dur=0.455s +[2026-08-21 14:40:19,715] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3cefef050a3ee8ca33860c658f11845c total=24778.5ms bytes=10948 finished=True finish=tool_calls stop=None out_tok=174 prompt_tok=10219 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:40:19,718] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6be2b53962c07f34e880a823f1851772 attempt=1 +[2026-08-21 14:40:20,167] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6be2b53962c07f34e880a823f1851772 status=200 post_dur=0.449s +[2026-08-21 14:40:41,681] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6be2b53962c07f34e880a823f1851772 total=21963.2ms bytes=15009 finished=True finish=tool_calls stop=None out_tok=161 prompt_tok=10116 tps=7.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:40:41,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea089eece066038a01e1b9b1e6364808 attempt=1 +[2026-08-21 14:40:42,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea089eece066038a01e1b9b1e6364808 status=200 post_dur=0.533s +[2026-08-21 14:43:23,352] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea089eece066038a01e1b9b1e6364808 total=161663.5ms bytes=88947 finished=True finish=tool_calls stop=None out_tok=550 prompt_tok=62737 tps=3.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:43:23,363] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=de6c6ace906958e9ff36c812a170106f attempt=1 +[2026-08-21 14:43:23,923] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=de6c6ace906958e9ff36c812a170106f status=200 post_dur=0.560s +[2026-08-21 14:45:35,894] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=de6c6ace906958e9ff36c812a170106f total=132531.2ms bytes=88820 finished=True finish=tool_calls stop=None out_tok=889 prompt_tok=65629 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:45:35,901] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aa52e474fe7d8b89a4059e7a699515ad attempt=1 +[2026-08-21 14:45:36,358] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aa52e474fe7d8b89a4059e7a699515ad status=200 post_dur=0.458s +[2026-08-21 14:46:04,409] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=aa52e474fe7d8b89a4059e7a699515ad total=28508.3ms bytes=23315 finished=True finish=tool_calls stop=None out_tok=255 prompt_tok=10728 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:46:04,411] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1758f90e7869e81ba0a715fe723dcce5 attempt=1 +[2026-08-21 14:46:04,836] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1758f90e7869e81ba0a715fe723dcce5 status=200 post_dur=0.425s +[2026-08-21 14:46:39,620] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1758f90e7869e81ba0a715fe723dcce5 total=35208.6ms bytes=29836 finished=True finish=tool_calls stop=None out_tok=308 prompt_tok=7438 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:46:39,622] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e56c04311574c6d317528df03e22ff8d attempt=1 +[2026-08-21 14:46:40,066] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e56c04311574c6d317528df03e22ff8d status=200 post_dur=0.444s +[2026-08-21 14:47:09,885] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e56c04311574c6d317528df03e22ff8d total=30262.9ms bytes=29294 finished=True finish=tool_calls stop=None out_tok=345 prompt_tok=7229 tps=11.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:47:09,894] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44c3fc821cbb980be109c776553f457f attempt=1 +[2026-08-21 14:47:09,909] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44c3fc821cbb980be109c776553f457f status=400 post_dur=0.015s +[2026-08-21 14:47:09,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=44c3fc821cbb980be109c776553f457f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 14:47:09,915] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=da2858b1e39d4081b580f847d3e3f155 attempt=1 +[2026-08-21 14:47:10,360] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=da2858b1e39d4081b580f847d3e3f155 status=200 post_dur=0.445s +[2026-08-21 14:47:36,118] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=da2858b1e39d4081b580f847d3e3f155 total=26203.1ms bytes=58794 finished=True finish=stop stop=None out_tok=204 prompt_tok=11769 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:47:36,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=69cdc6f065632f2d1d96158896d8c6a7 attempt=1 +[2026-08-21 14:47:36,553] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=69cdc6f065632f2d1d96158896d8c6a7 status=200 post_dur=0.431s +[2026-08-21 14:48:03,662] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=69cdc6f065632f2d1d96158896d8c6a7 total=27540.5ms bytes=23553 finished=True finish=tool_calls stop=None out_tok=242 prompt_tok=8405 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 14:48:03,676] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4cf272cf5d7e74a687b41f792ebb351e attempt=1 +[2026-08-21 14:48:04,347] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4cf272cf5d7e74a687b41f792ebb351e status=200 post_dur=0.670s +[2026-08-21 15:06:22,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4cf272cf5d7e74a687b41f792ebb351e total=1099158.9ms bytes=26445 finished=True finish=tool_calls stop=None out_tok=4829 prompt_tok=127840 tps=4.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:06:22,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b7d8d571e00650e7f699591ac8f87918 attempt=1 +[2026-08-21 15:06:23,296] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b7d8d571e00650e7f699591ac8f87918 status=200 post_dur=0.450s +[2026-08-21 15:06:35,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b7d8d571e00650e7f699591ac8f87918 total=12807.2ms bytes=23234 finished=True finish=stop stop=None out_tok=79 prompt_tok=7530 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:06:35,655] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=127c1094b08c47e9a10959202bef52a2 attempt=1 +[2026-08-21 15:06:36,063] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=127c1094b08c47e9a10959202bef52a2 status=200 post_dur=0.408s +[2026-08-21 15:06:46,434] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=127c1094b08c47e9a10959202bef52a2 total=10779.0ms bytes=13512 finished=True finish=stop stop=None out_tok=46 prompt_tok=7706 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:06:46,437] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0932353bade1e13b7847c64c1ecfd729 attempt=1 +[2026-08-21 15:06:46,437] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 34% (264/881) has_cb=True +[2026-08-21 15:06:46,855] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0932353bade1e13b7847c64c1ecfd729 status=200 post_dur=0.418s +[2026-08-21 15:07:31,744] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0932353bade1e13b7847c64c1ecfd729 total=45307.1ms bytes=76181 finished=True finish=tool_calls stop=None out_tok=386 prompt_tok=10844 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:07:31,747] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f401ee7d8921bc0e3fa2e05e5ceee02b attempt=1 +[2026-08-21 15:07:32,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f401ee7d8921bc0e3fa2e05e5ceee02b status=200 post_dur=0.445s +[2026-08-21 15:08:13,650] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f401ee7d8921bc0e3fa2e05e5ceee02b total=41903.3ms bytes=32701 finished=True finish=tool_calls stop=None out_tok=392 prompt_tok=9718 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:08:13,653] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bba8acbaa74a3dc870febf0bfdbcf32e attempt=1 +[2026-08-21 15:08:14,104] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bba8acbaa74a3dc870febf0bfdbcf32e status=200 post_dur=0.450s +[2026-08-21 15:08:34,860] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bba8acbaa74a3dc870febf0bfdbcf32e total=21207.1ms bytes=40172 finished=True finish=stop stop=None out_tok=139 prompt_tok=12369 tps=6.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:08:34,869] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c7dc349c3ee6663fc23399a22b9654f attempt=1 +[2026-08-21 15:08:34,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c7dc349c3ee6663fc23399a22b9654f status=400 post_dur=0.006s +[2026-08-21 15:08:34,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=9c7dc349c3ee6663fc23399a22b9654f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 15:08:34,894] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=305b7df9874d7557abe9b73388420205 attempt=1 +[2026-08-21 15:08:34,901] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=305b7df9874d7557abe9b73388420205 status=400 post_dur=0.006s +[2026-08-21 15:08:34,901] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=305b7df9874d7557abe9b73388420205 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 15:08:34,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b4c7ff25b9f196398801d56e1e9179a attempt=1 +[2026-08-21 15:08:35,354] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b4c7ff25b9f196398801d56e1e9179a status=200 post_dur=0.442s +[2026-08-21 15:09:12,601] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b4c7ff25b9f196398801d56e1e9179a total=37691.1ms bytes=21560 finished=True finish=tool_calls stop=None out_tok=286 prompt_tok=11114 tps=7.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:09:12,605] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e attempt=1 +[2026-08-21 15:09:13,070] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e status=200 post_dur=0.466s +[2026-08-21 15:09:35,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0fc06d2ddaa6259fcaef9c312c7a5e2e total=22787.2ms bytes=18862 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=14186 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:09:35,400] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 attempt=1 +[2026-08-21 15:09:35,981] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 status=200 post_dur=0.580s +[2026-08-21 15:11:22,963] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e2fcb2ca0e8da88f059d96a8894b3e9 total=107562.5ms bytes=113730 finished=True finish=tool_calls stop=None out_tok=638 prompt_tok=69897 tps=5.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:11:22,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c3db67d9e27ff560abfb31e5a355ea4 attempt=1 +[2026-08-21 15:11:23,432] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c3db67d9e27ff560abfb31e5a355ea4 status=200 post_dur=0.462s +[2026-08-21 15:11:54,446] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c3db67d9e27ff560abfb31e5a355ea4 total=31476.5ms bytes=12434 finished=True finish=tool_calls stop=None out_tok=247 prompt_tok=15755 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:11:54,450] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a22e26e27968bee0c2aca034a1400e1a attempt=1 +[2026-08-21 15:11:54,916] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a22e26e27968bee0c2aca034a1400e1a status=200 post_dur=0.466s +[2026-08-21 15:12:08,242] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a22e26e27968bee0c2aca034a1400e1a total=13791.6ms bytes=12240 finished=True finish=tool_calls stop=None out_tok=116 prompt_tok=15885 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:12:08,246] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d3c81ea36a70eb17df97031eb88e3a93 attempt=1 +[2026-08-21 15:12:08,680] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d3c81ea36a70eb17df97031eb88e3a93 status=200 post_dur=0.434s +[2026-08-21 15:12:42,695] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d3c81ea36a70eb17df97031eb88e3a93 total=34449.3ms bytes=19454 finished=True finish=tool_calls stop=None out_tok=303 prompt_tok=11557 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:12:42,703] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=761173bbfd9c45a4a912f7e8a06bfd21 attempt=1 +[2026-08-21 15:12:43,256] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=761173bbfd9c45a4a912f7e8a06bfd21 status=200 post_dur=0.553s +[2026-08-21 15:13:08,127] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=761173bbfd9c45a4a912f7e8a06bfd21 total=25423.4ms bytes=16961 finished=True finish=tool_calls stop=None out_tok=139 prompt_tok=70311 tps=5.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:13:08,133] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff attempt=1 +[2026-08-21 15:13:08,590] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff status=200 post_dur=0.457s +[2026-08-21 15:13:31,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f50c6dbe4cffe5c1c5aa83ea5e466ff total=22987.6ms bytes=59895 finished=True finish=stop stop=None out_tok=202 prompt_tok=16409 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:13:31,125] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7cc9a754c24107848331586e88d4b52 attempt=1 +[2026-08-21 15:13:31,581] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7cc9a754c24107848331586e88d4b52 status=200 post_dur=0.456s +[2026-08-21 15:13:48,007] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7cc9a754c24107848331586e88d4b52 total=16881.2ms bytes=18014 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=16259 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:13:48,011] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2bc0097e24faffcef96c571f2c6fa0b2 attempt=1 +[2026-08-21 15:13:48,448] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2bc0097e24faffcef96c571f2c6fa0b2 status=200 post_dur=0.437s +[2026-08-21 15:14:27,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2bc0097e24faffcef96c571f2c6fa0b2 total=39258.8ms bytes=98161 finished=True finish=tool_calls stop=None out_tok=379 prompt_tok=16899 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:14:27,274] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=208c93456a81bd6e6eb789edcbaad815 attempt=1 +[2026-08-21 15:14:27,719] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=208c93456a81bd6e6eb789edcbaad815 status=200 post_dur=0.445s +[2026-08-21 15:14:55,917] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=208c93456a81bd6e6eb789edcbaad815 total=28643.0ms bytes=19111 finished=True finish=tool_calls stop=None out_tok=250 prompt_tok=11829 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:14:55,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=489e3bf4f1669a09c4d84b22d29c76fa attempt=1 +[2026-08-21 15:14:56,369] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=489e3bf4f1669a09c4d84b22d29c76fa status=200 post_dur=0.450s +[2026-08-21 15:15:23,945] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=489e3bf4f1669a09c4d84b22d29c76fa total=28025.3ms bytes=21105 finished=True finish=tool_calls stop=None out_tok=244 prompt_tok=12338 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:15:23,948] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 attempt=1 +[2026-08-21 15:15:24,384] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 status=200 post_dur=0.436s +[2026-08-21 15:15:55,792] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cfd251d10ffc02d35a3dd6f5ef48ef27 total=31843.6ms bytes=15042 finished=True finish=tool_calls stop=None out_tok=271 prompt_tok=13434 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:15:55,796] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=897720c5f0ce3aa6b53435be41b4854d attempt=1 +[2026-08-21 15:15:56,237] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=897720c5f0ce3aa6b53435be41b4854d status=200 post_dur=0.442s +[2026-08-21 15:16:29,519] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=897720c5f0ce3aa6b53435be41b4854d total=33723.6ms bytes=28003 finished=True finish=tool_calls stop=None out_tok=280 prompt_tok=14844 tps=8.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:16:29,522] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=030f9998f1b00aacffc6a63891bbd937 attempt=1 +[2026-08-21 15:16:29,962] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=030f9998f1b00aacffc6a63891bbd937 status=200 post_dur=0.439s +[2026-08-21 15:16:41,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=030f9998f1b00aacffc6a63891bbd937 total=12129.2ms bytes=14621 finished=True finish=stop stop=None out_tok=49 prompt_tok=8563 tps=4.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:16:41,654] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b6eef4c55d5057023dfae4e40cb45ca7 attempt=1 +[2026-08-21 15:16:42,058] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b6eef4c55d5057023dfae4e40cb45ca7 status=200 post_dur=0.403s +[2026-08-21 15:17:03,752] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b6eef4c55d5057023dfae4e40cb45ca7 total=22097.7ms bytes=13869 finished=True finish=tool_calls stop=None out_tok=189 prompt_tok=8220 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:17:03,760] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2320f9838fc0fa37eb8c4d4e50dbc091 attempt=1 +[2026-08-21 15:17:03,766] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2320f9838fc0fa37eb8c4d4e50dbc091 status=400 post_dur=0.005s +[2026-08-21 15:17:03,766] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2320f9838fc0fa37eb8c4d4e50dbc091 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 15:17:03,772] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=781df8a628086f0bbb1a8d47df29c678 attempt=1 +[2026-08-21 15:17:04,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=781df8a628086f0bbb1a8d47df29c678 status=200 post_dur=0.449s +[2026-08-21 15:17:32,538] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=781df8a628086f0bbb1a8d47df29c678 total=28766.0ms bytes=12031 finished=True finish=tool_calls stop=None out_tok=223 prompt_tok=15361 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:17:32,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca38125c983fc73af3bd211a8d7b63eb attempt=1 +[2026-08-21 15:17:32,968] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca38125c983fc73af3bd211a8d7b63eb status=200 post_dur=0.427s +[2026-08-21 15:17:53,067] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca38125c983fc73af3bd211a8d7b63eb total=20526.8ms bytes=21504 finished=True finish=tool_calls stop=None out_tok=137 prompt_tok=8705 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:17:53,070] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7e67de6f8dee2746ed569e299f51c644 attempt=1 +[2026-08-21 15:17:53,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7e67de6f8dee2746ed569e299f51c644 status=200 post_dur=0.436s +[2026-08-21 15:18:06,727] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7e67de6f8dee2746ed569e299f51c644 total=13656.9ms bytes=9334 finished=True finish=stop stop=None out_tok=31 prompt_tok=8770 tps=2.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:18:06,729] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dab19ab6560dab4f147969a4e86d9585 attempt=1 +[2026-08-21 15:18:07,147] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dab19ab6560dab4f147969a4e86d9585 status=200 post_dur=0.417s +[2026-08-21 15:18:25,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dab19ab6560dab4f147969a4e86d9585 total=18810.9ms bytes=12923 finished=True finish=tool_calls stop=None out_tok=85 prompt_tok=9005 tps=4.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:18:25,543] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18969f5ebf290953286b44f51e87c15e attempt=1 +[2026-08-21 15:18:25,970] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18969f5ebf290953286b44f51e87c15e status=200 post_dur=0.428s +[2026-08-21 15:18:38,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=18969f5ebf290953286b44f51e87c15e total=12774.3ms bytes=7926 finished=True finish=tool_calls stop=None out_tok=66 prompt_tok=9181 tps=5.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:18:38,320] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bd58eef4ec4a56d53f985821361907f2 attempt=1 +[2026-08-21 15:18:38,750] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bd58eef4ec4a56d53f985821361907f2 status=200 post_dur=0.430s +[2026-08-21 15:18:47,578] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bd58eef4ec4a56d53f985821361907f2 total=9258.3ms bytes=7040 finished=True finish=tool_calls stop=None out_tok=60 prompt_tok=9032 tps=6.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:18:47,586] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dcdddd3cfd29ed17e082111c49ce2fe6 attempt=1 +[2026-08-21 15:18:47,592] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dcdddd3cfd29ed17e082111c49ce2fe6 status=400 post_dur=0.006s +[2026-08-21 15:18:47,592] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=dcdddd3cfd29ed17e082111c49ce2fe6 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 15:18:47,596] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a78369072b9c53f0d464d0c5199cdc6d attempt=1 +[2026-08-21 15:18:48,011] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a78369072b9c53f0d464d0c5199cdc6d status=200 post_dur=0.415s +[2026-08-21 15:19:04,421] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a78369072b9c53f0d464d0c5199cdc6d total=16824.7ms bytes=16772 finished=True finish=tool_calls stop=None out_tok=105 prompt_tok=9840 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:19:04,424] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=da150dbed66672f1597e924c9b8bfd17 attempt=1 +[2026-08-21 15:19:04,839] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=da150dbed66672f1597e924c9b8bfd17 status=200 post_dur=0.415s +[2026-08-21 15:19:12,077] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=da150dbed66672f1597e924c9b8bfd17 total=7652.2ms bytes=10505 finished=True finish=stop stop=None out_tok=35 prompt_tok=9699 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:19:12,079] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=81dc399d3b76594fed6c228e74aa9177 attempt=1 +[2026-08-21 15:19:12,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=81dc399d3b76594fed6c228e74aa9177 status=200 post_dur=0.428s +[2026-08-21 15:19:23,034] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=81dc399d3b76594fed6c228e74aa9177 total=10954.3ms bytes=11979 finished=True finish=stop stop=None out_tok=40 prompt_tok=9801 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:19:23,036] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=67679b9ac717784d43dba75b443d00d5 attempt=1 +[2026-08-21 15:19:23,474] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=67679b9ac717784d43dba75b443d00d5 status=200 post_dur=0.437s +[2026-08-21 15:19:30,184] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=67679b9ac717784d43dba75b443d00d5 total=7147.1ms bytes=11390 finished=True finish=stop stop=None out_tok=38 prompt_tok=9902 tps=5.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:19:30,186] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fde534bf37958b32c69dd33dea05e6d attempt=1 +[2026-08-21 15:19:30,605] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fde534bf37958b32c69dd33dea05e6d status=200 post_dur=0.419s +[2026-08-21 15:19:52,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fde534bf37958b32c69dd33dea05e6d total=22272.9ms bytes=29724 finished=True finish=tool_calls stop=None out_tok=249 prompt_tok=7229 tps=11.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:19:52,462] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39d36ff3385f88aef025fd09d38417d2 attempt=1 +[2026-08-21 15:19:52,880] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39d36ff3385f88aef025fd09d38417d2 status=200 post_dur=0.418s +[2026-08-21 15:20:10,198] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=39d36ff3385f88aef025fd09d38417d2 total=17736.5ms bytes=19501 finished=True finish=tool_calls stop=None out_tok=107 prompt_tok=10399 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:20:10,202] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3be58ea636a67e6431609e2bbfde0c8e attempt=1 +[2026-08-21 15:20:10,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3be58ea636a67e6431609e2bbfde0c8e status=200 post_dur=0.443s +[2026-08-21 15:20:25,199] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3be58ea636a67e6431609e2bbfde0c8e total=14997.7ms bytes=13278 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=10762 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:20:25,201] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=739d74764d68eac2906cc142d1c4dc0a attempt=1 +[2026-08-21 15:20:25,205] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=739d74764d68eac2906cc142d1c4dc0a status=400 post_dur=0.003s +[2026-08-21 15:20:25,205] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=739d74764d68eac2906cc142d1c4dc0a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 15:20:25,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=534861acba13709ce90e3532fec86ba0 attempt=1 +[2026-08-21 15:20:25,627] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=534861acba13709ce90e3532fec86ba0 status=200 post_dur=0.420s +[2026-08-21 15:20:53,383] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=534861acba13709ce90e3532fec86ba0 total=28176.1ms bytes=14316 finished=True finish=tool_calls stop=None out_tok=190 prompt_tok=7626 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:20:53,387] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a85cdbec78c97f2960cda954365e3b15 attempt=1 +[2026-08-21 15:20:53,857] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a85cdbec78c97f2960cda954365e3b15 status=200 post_dur=0.470s +[2026-08-21 15:21:29,781] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a85cdbec78c97f2960cda954365e3b15 total=36393.7ms bytes=9343 finished=True finish=stop stop=None out_tok=31 prompt_tok=24820 tps=0.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:21:29,784] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=591d6bcdfc7fa47d9c8d0923dba82161 attempt=1 +[2026-08-21 15:21:30,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=591d6bcdfc7fa47d9c8d0923dba82161 status=200 post_dur=0.438s +[2026-08-21 15:22:17,489] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=591d6bcdfc7fa47d9c8d0923dba82161 total=47704.7ms bytes=62785 finished=True finish=tool_calls stop=None out_tok=460 prompt_tok=10073 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:22:17,491] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7a94fb833580b70db22b2c6646da818e attempt=1 +[2026-08-21 15:22:17,791] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7a94fb833580b70db22b2c6646da818e status=200 post_dur=0.300s +[2026-08-21 15:24:25,073] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7a94fb833580b70db22b2c6646da818e total=127581.5ms bytes=433002 finished=True finish=stop stop=None out_tok=1487 prompt_tok=126 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:24:25,075] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=543eb2ee52a87501fabacd48dd360270 attempt=1 +[2026-08-21 15:24:25,375] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=543eb2ee52a87501fabacd48dd360270 status=200 post_dur=0.300s +[2026-08-21 15:27:52,469] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=543eb2ee52a87501fabacd48dd360270 total=207394.0ms bytes=711471 finished=True finish=stop stop=None out_tok=2446 prompt_tok=122 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:27:52,482] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=30f411698380613107fd553990855b29 attempt=1 +[2026-08-21 15:27:53,122] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=30f411698380613107fd553990855b29 status=200 post_dur=0.639s +[2026-08-21 15:35:43,265] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=30f411698380613107fd553990855b29 total=470782.7ms bytes=90133 finished=True finish=tool_calls stop=None out_tok=2651 prompt_tok=93943 tps=5.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:35:43,274] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d359c33479ab1219a4b91fb3192ff84f attempt=1 +[2026-08-21 15:35:43,735] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d359c33479ab1219a4b91fb3192ff84f status=200 post_dur=0.461s +[2026-08-21 15:36:12,777] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d359c33479ab1219a4b91fb3192ff84f total=29503.3ms bytes=17348 finished=True finish=tool_calls stop=None out_tok=292 prompt_tok=11589 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:36:12,779] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e6e3b089f22fe8c96166bd8684b699b attempt=1 +[2026-08-21 15:36:12,779] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 38% (308/881) has_cb=True +[2026-08-21 15:36:13,069] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e6e3b089f22fe8c96166bd8684b699b status=200 post_dur=0.290s +[2026-08-21 15:40:08,375] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e6e3b089f22fe8c96166bd8684b699b total=235596.0ms bytes=807507 finished=True finish=stop stop=None out_tok=2774 prompt_tok=310 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:40:08,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bee17ca5762fa519f395a394d63c923e attempt=1 +[2026-08-21 15:40:09,098] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bee17ca5762fa519f395a394d63c923e status=200 post_dur=0.706s +[2026-08-21 15:52:13,848] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bee17ca5762fa519f395a394d63c923e total=725456.3ms bytes=19665 finished=True finish=tool_calls stop=None out_tok=2671 prompt_tok=134404 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:52:13,859] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=42d7ff74e68564a4c55eab4bbf0e5455 attempt=1 +[2026-08-21 15:52:14,322] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=42d7ff74e68564a4c55eab4bbf0e5455 status=200 post_dur=0.462s +[2026-08-21 15:52:36,109] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=42d7ff74e68564a4c55eab4bbf0e5455 total=22250.0ms bytes=41023 finished=True finish=stop stop=None out_tok=138 prompt_tok=11572 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:52:36,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b2b836d03a813f24d41f6852aa59ec0d attempt=1 +[2026-08-21 15:52:36,533] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b2b836d03a813f24d41f6852aa59ec0d status=200 post_dur=0.421s +[2026-08-21 15:52:45,849] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b2b836d03a813f24d41f6852aa59ec0d total=9736.8ms bytes=9119 finished=True finish=tool_calls stop=None out_tok=72 prompt_tok=7319 tps=7.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:52:45,853] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=20381136fd4119d82879fa066f8a4da3 attempt=1 +[2026-08-21 15:52:46,269] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=20381136fd4119d82879fa066f8a4da3 status=200 post_dur=0.416s +[2026-08-21 15:53:06,476] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=20381136fd4119d82879fa066f8a4da3 total=20622.9ms bytes=12113 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=11674 tps=4.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:53:06,479] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44e6047d34f4018aa8ad7dee8d50d616 attempt=1 +[2026-08-21 15:53:06,896] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44e6047d34f4018aa8ad7dee8d50d616 status=200 post_dur=0.416s +[2026-08-21 15:53:34,427] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44e6047d34f4018aa8ad7dee8d50d616 total=27947.5ms bytes=82669 finished=True finish=stop stop=None out_tok=285 prompt_tok=11705 tps=10.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:53:34,430] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1fb23507e631016b81cf5d1cf81d126e attempt=1 +[2026-08-21 15:53:34,866] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1fb23507e631016b81cf5d1cf81d126e status=200 post_dur=0.436s +[2026-08-21 15:53:45,545] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1fb23507e631016b81cf5d1cf81d126e total=11115.4ms bytes=12568 finished=True finish=stop stop=None out_tok=42 prompt_tok=8093 tps=3.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:53:45,549] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b8525370526bef040d70756d7f0ee140 attempt=1 +[2026-08-21 15:53:45,552] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b8525370526bef040d70756d7f0ee140 status=400 post_dur=0.003s +[2026-08-21 15:53:45,552] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b8525370526bef040d70756d7f0ee140 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 15:53:45,555] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3a44fcf5b4a683a78a5648a97793dd1 attempt=1 +[2026-08-21 15:53:45,966] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3a44fcf5b4a683a78a5648a97793dd1 status=200 post_dur=0.411s +[2026-08-21 15:54:15,442] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3a44fcf5b4a683a78a5648a97793dd1 total=29886.8ms bytes=76016 finished=True finish=stop stop=None out_tok=260 prompt_tok=8382 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 15:54:15,457] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=429e2ec8a4bb7e555738313a9f787546 attempt=1 +[2026-08-21 15:54:16,131] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=429e2ec8a4bb7e555738313a9f787546 status=200 post_dur=0.673s +[2026-08-21 16:10:41,817] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=429e2ec8a4bb7e555738313a9f787546 total=986359.9ms bytes=25218 finished=True finish=tool_calls stop=None out_tok=4898 prompt_tok=137134 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:10:41,828] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=472fa9b9163a07a78ee1e76d69b4034d attempt=1 +[2026-08-21 16:10:42,276] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=472fa9b9163a07a78ee1e76d69b4034d status=200 post_dur=0.448s +[2026-08-21 16:10:55,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=472fa9b9163a07a78ee1e76d69b4034d total=13480.2ms bytes=17840 finished=True finish=stop stop=None out_tok=60 prompt_tok=8363 tps=4.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:10:55,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e8b63715a54029132096ddb713de5080 attempt=1 +[2026-08-21 16:10:55,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e8b63715a54029132096ddb713de5080 status=400 post_dur=0.007s +[2026-08-21 16:10:55,318] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e8b63715a54029132096ddb713de5080 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] (retryable=False, attempt=1) +[2026-08-21 16:10:55,320] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=279ef80c5ca400b7a2a8e9d9709257db attempt=1 +[2026-08-21 16:10:55,650] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=279ef80c5ca400b7a2a8e9d9709257db status=200 post_dur=0.330s +[2026-08-21 16:11:20,679] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=279ef80c5ca400b7a2a8e9d9709257db total=25359.0ms bytes=3391 finished=True finish=stop stop= out_tok=7 prompt_tok=19541 tps=0.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:11:20,683] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=609555a434d06a6739b49a1a6e188512 attempt=1 +[2026-08-21 16:11:21,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=609555a434d06a6739b49a1a6e188512 status=200 post_dur=0.461s +[2026-08-21 16:12:26,708] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=609555a434d06a6739b49a1a6e188512 total=66024.5ms bytes=25803 finished=True finish=tool_calls stop=None out_tok=363 prompt_tok=27365 tps=5.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:12:26,718] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f162e5772523b77f1fd6f11119aba52e attempt=1 +[2026-08-21 16:12:26,726] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f162e5772523b77f1fd6f11119aba52e status=400 post_dur=0.006s +[2026-08-21 16:12:26,726] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f162e5772523b77f1fd6f11119aba52e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:12:26,731] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7dfdc826123166286f9350e95ba9dd74 attempt=1 +[2026-08-21 16:12:27,176] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7dfdc826123166286f9350e95ba9dd74 status=200 post_dur=0.444s +[2026-08-21 16:12:40,727] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7dfdc826123166286f9350e95ba9dd74 total=13996.0ms bytes=10230 finished=True finish=stop stop=None out_tok=34 prompt_tok=8747 tps=2.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:12:40,731] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07245351d69936bcf5160d35c7986d38 attempt=1 +[2026-08-21 16:12:40,735] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07245351d69936bcf5160d35c7986d38 status=400 post_dur=0.004s +[2026-08-21 16:12:40,735] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=07245351d69936bcf5160d35c7986d38 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:12:40,739] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2c279398e5811a0668d2c99bba40f0f1 attempt=1 +[2026-08-21 16:12:41,181] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2c279398e5811a0668d2c99bba40f0f1 status=200 post_dur=0.442s +[2026-08-21 16:13:17,032] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2c279398e5811a0668d2c99bba40f0f1 total=36292.4ms bytes=15229 finished=True finish=tool_calls stop=None out_tok=125 prompt_tok=20282 tps=3.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:13:17,037] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ecce35417f652721e8b3d83ebdbe97b8 attempt=1 +[2026-08-21 16:13:17,503] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ecce35417f652721e8b3d83ebdbe97b8 status=200 post_dur=0.466s +[2026-08-21 16:14:02,097] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ecce35417f652721e8b3d83ebdbe97b8 total=45059.4ms bytes=20657 finished=True finish=tool_calls stop=None out_tok=117 prompt_tok=27038 tps=2.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:14:02,101] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=274a2ea60d0d6699ae57042b9df59a9c attempt=1 +[2026-08-21 16:14:02,530] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=274a2ea60d0d6699ae57042b9df59a9c status=200 post_dur=0.430s +[2026-08-21 16:14:37,450] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=274a2ea60d0d6699ae57042b9df59a9c total=35348.9ms bytes=33906 finished=True finish=tool_calls stop=None out_tok=311 prompt_tok=7438 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:14:37,455] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=92bc65caec466c196c5c29641b61fab3 attempt=1 +[2026-08-21 16:14:37,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=92bc65caec466c196c5c29641b61fab3 status=400 post_dur=0.004s +[2026-08-21 16:14:37,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=92bc65caec466c196c5c29641b61fab3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'reasoning_effort'), 'msg': 'Extra inputs are not permitted', 'input': 'low'}] (retryable=False, attempt=1) +[2026-08-21 16:14:37,464] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f638e6d289e6c0155b99340453e7f6cd attempt=1 +[2026-08-21 16:14:37,468] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f638e6d289e6c0155b99340453e7f6cd status=400 post_dur=0.004s +[2026-08-21 16:14:37,468] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f638e6d289e6c0155b99340453e7f6cd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:14:37,484] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=18402a4e7df20b9b0a2378d8d829f2da attempt=1 +[2026-08-21 16:14:38,151] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=18402a4e7df20b9b0a2378d8d829f2da status=200 post_dur=0.668s +[2026-08-21 16:19:07,665] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=18402a4e7df20b9b0a2378d8d829f2da total=270181.4ms bytes=8128 finished=True finish=tool_calls stop=None out_tok=185 prompt_tok=134170 tps=0.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:19:07,674] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=861831dca52df0c5fa277aa51ba52f02 attempt=1 +[2026-08-21 16:19:08,117] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=861831dca52df0c5fa277aa51ba52f02 status=200 post_dur=0.443s +[2026-08-21 16:19:30,653] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=861831dca52df0c5fa277aa51ba52f02 total=22979.1ms bytes=12725 finished=True finish=tool_calls stop=None out_tok=222 prompt_tok=7865 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:19:30,656] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca2a5777ff1428d41f12b0b0e98f650a attempt=1 +[2026-08-21 16:19:31,077] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca2a5777ff1428d41f12b0b0e98f650a status=200 post_dur=0.421s +[2026-08-21 16:20:03,266] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca2a5777ff1428d41f12b0b0e98f650a total=32610.0ms bytes=19993 finished=True finish=tool_calls stop=None out_tok=281 prompt_tok=9570 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:20:03,268] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=19a5b1d36a0575436b7d58259b731048 attempt=1 +[2026-08-21 16:20:03,705] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=19a5b1d36a0575436b7d58259b731048 status=200 post_dur=0.437s +[2026-08-21 16:20:24,407] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=19a5b1d36a0575436b7d58259b731048 total=21138.6ms bytes=24682 finished=True finish=tool_calls stop=None out_tok=140 prompt_tok=9201 tps=6.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:20:24,409] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2cae3880668cf3586211138d03ca36dc attempt=1 +[2026-08-21 16:20:24,829] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2cae3880668cf3586211138d03ca36dc status=200 post_dur=0.420s +[2026-08-21 16:20:57,714] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2cae3880668cf3586211138d03ca36dc total=33304.0ms bytes=26910 finished=True finish=tool_calls stop=None out_tok=252 prompt_tok=9937 tps=7.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:20:57,727] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=12c6c48470de526ecb2c2b7c0aa856de attempt=1 +[2026-08-21 16:20:57,734] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=12c6c48470de526ecb2c2b7c0aa856de status=400 post_dur=0.006s +[2026-08-21 16:20:57,734] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=12c6c48470de526ecb2c2b7c0aa856de status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 16:20:57,742] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e1491602678c1921e5fb02c410f76d3 attempt=1 +[2026-08-21 16:20:58,149] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e1491602678c1921e5fb02c410f76d3 status=200 post_dur=0.407s +[2026-08-21 16:21:26,169] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e1491602678c1921e5fb02c410f76d3 total=28426.9ms bytes=30046 finished=True finish=tool_calls stop=None out_tok=323 prompt_tok=7229 tps=11.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:21:26,174] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0479e081fd710787d7263de415b808ce attempt=1 +[2026-08-21 16:21:26,639] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0479e081fd710787d7263de415b808ce status=200 post_dur=0.464s +[2026-08-21 16:24:26,840] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0479e081fd710787d7263de415b808ce total=180665.8ms bytes=21354 finished=True finish=tool_calls stop=None out_tok=1641 prompt_tok=29749 tps=9.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:24:26,844] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca6258bbd7739ea06692f037e73af14c attempt=1 +[2026-08-21 16:24:27,287] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca6258bbd7739ea06692f037e73af14c status=200 post_dur=0.443s +[2026-08-21 16:24:46,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca6258bbd7739ea06692f037e73af14c total=19475.4ms bytes=31424 finished=True finish=tool_calls stop=None out_tok=205 prompt_tok=7197 tps=10.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:24:46,322] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb259d9b4105065222a81d4ee0ba25d1 attempt=1 +[2026-08-21 16:24:46,649] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb259d9b4105065222a81d4ee0ba25d1 status=200 post_dur=0.327s +[2026-08-21 16:25:01,344] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fb259d9b4105065222a81d4ee0ba25d1 total=15022.3ms bytes=3439 finished=True finish=stop stop= out_tok=7 prompt_tok=19894 tps=0.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:25:01,347] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7529578e135854befe7cb7538706fd49 attempt=1 +[2026-08-21 16:25:01,761] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7529578e135854befe7cb7538706fd49 status=200 post_dur=0.415s +[2026-08-21 16:25:12,625] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7529578e135854befe7cb7538706fd49 total=11278.6ms bytes=11714 finished=True finish=tool_calls stop=None out_tok=72 prompt_tok=7294 tps=6.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:25:12,628] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db8031b46e0d570d6672546b905d59da attempt=1 +[2026-08-21 16:25:13,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db8031b46e0d570d6672546b905d59da status=200 post_dur=0.432s +[2026-08-21 16:25:53,100] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db8031b46e0d570d6672546b905d59da total=40472.5ms bytes=11820 finished=True finish=tool_calls stop=None out_tok=321 prompt_tok=8599 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:25:53,104] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2e431b6fccc5248fd9864f7ccce4ecf4 attempt=1 +[2026-08-21 16:25:53,543] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2e431b6fccc5248fd9864f7ccce4ecf4 status=200 post_dur=0.439s +[2026-08-21 16:26:05,872] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2e431b6fccc5248fd9864f7ccce4ecf4 total=12768.1ms bytes=10357 finished=True finish=tool_calls stop=None out_tok=86 prompt_tok=10928 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:26:05,875] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=43b55004efbaf0f8acfcbf32ac94aef1 attempt=1 +[2026-08-21 16:26:06,201] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=43b55004efbaf0f8acfcbf32ac94aef1 status=200 post_dur=0.326s +[2026-08-21 16:26:13,832] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=43b55004efbaf0f8acfcbf32ac94aef1 total=7956.4ms bytes=3158 finished=True finish=stop stop= out_tok=7 prompt_tok=20050 tps=0.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:26:13,846] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b20030ac5b5832f877f2b30f9f5e01a8 attempt=1 +[2026-08-21 16:26:13,853] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b20030ac5b5832f877f2b30f9f5e01a8 status=400 post_dur=0.006s +[2026-08-21 16:26:13,854] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b20030ac5b5832f877f2b30f9f5e01a8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 16:26:13,863] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d06150a2df906c2e476c45b973b43bee attempt=1 +[2026-08-21 16:26:14,280] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d06150a2df906c2e476c45b973b43bee status=200 post_dur=0.417s +[2026-08-21 16:26:36,189] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d06150a2df906c2e476c45b973b43bee total=22325.6ms bytes=47783 finished=True finish=stop stop=None out_tok=165 prompt_tok=11163 tps=7.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:26:36,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7f2d3841e1eeef072d0c35f7e26f1f8d attempt=1 +[2026-08-21 16:26:36,626] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7f2d3841e1eeef072d0c35f7e26f1f8d status=200 post_dur=0.434s +[2026-08-21 16:27:08,792] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7f2d3841e1eeef072d0c35f7e26f1f8d total=32599.3ms bytes=15640 finished=True finish=tool_calls stop=None out_tok=301 prompt_tok=11354 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:27:08,794] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3de25793ade30c457cac9eb6599596c0 attempt=1 +[2026-08-21 16:27:09,230] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3de25793ade30c457cac9eb6599596c0 status=200 post_dur=0.436s +[2026-08-21 16:27:35,091] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3de25793ade30c457cac9eb6599596c0 total=26296.8ms bytes=14869 finished=True finish=tool_calls stop=None out_tok=164 prompt_tok=10488 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:27:35,094] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=635214b9e34c72c0130f432a0cef31b0 attempt=1 +[2026-08-21 16:27:35,515] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=635214b9e34c72c0130f432a0cef31b0 status=200 post_dur=0.421s +[2026-08-21 16:28:10,552] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=635214b9e34c72c0130f432a0cef31b0 total=35457.7ms bytes=16349 finished=True finish=tool_calls stop=None out_tok=265 prompt_tok=10895 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:28:10,555] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=85f151be1e5f546e001316abfc2f790d attempt=1 +[2026-08-21 16:28:10,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=85f151be1e5f546e001316abfc2f790d status=200 post_dur=0.438s +[2026-08-21 16:28:38,904] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=85f151be1e5f546e001316abfc2f790d total=28349.3ms bytes=20261 finished=True finish=tool_calls stop=None out_tok=249 prompt_tok=11738 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:28:38,907] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b2e77e30bc470141455b116c301d01c7 attempt=1 +[2026-08-21 16:28:39,341] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b2e77e30bc470141455b116c301d01c7 status=200 post_dur=0.434s +[2026-08-21 16:29:13,136] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b2e77e30bc470141455b116c301d01c7 total=34228.7ms bytes=25839 finished=True finish=tool_calls stop=None out_tok=307 prompt_tok=10885 tps=9.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:29:13,139] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a8cbebc1418321449b8337a4b6a8a419 attempt=1 +[2026-08-21 16:29:13,568] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a8cbebc1418321449b8337a4b6a8a419 status=200 post_dur=0.428s +[2026-08-21 16:29:32,074] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a8cbebc1418321449b8337a4b6a8a419 total=18934.2ms bytes=18975 finished=True finish=tool_calls stop=None out_tok=174 prompt_tok=11236 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:29:32,081] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 42% (352/881) has_cb=True +[2026-08-21 16:29:32,087] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2c9a026e503ef8037293cb832698e683 attempt=1 +[2026-08-21 16:29:32,093] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2c9a026e503ef8037293cb832698e683 status=400 post_dur=0.006s +[2026-08-21 16:29:32,093] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2c9a026e503ef8037293cb832698e683 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 16:29:32,109] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=df387d4c577f944c69a77089501c6af5 attempt=1 +[2026-08-21 16:29:32,114] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=df387d4c577f944c69a77089501c6af5 status=400 post_dur=0.005s +[2026-08-21 16:29:32,114] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=df387d4c577f944c69a77089501c6af5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:29:32,120] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac8d56b6daae31f8e66ac545d6ddcb6d attempt=1 +[2026-08-21 16:29:32,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac8d56b6daae31f8e66ac545d6ddcb6d status=200 post_dur=0.418s +[2026-08-21 16:29:58,861] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ac8d56b6daae31f8e66ac545d6ddcb6d total=26741.0ms bytes=19879 finished=True finish=tool_calls stop=None out_tok=224 prompt_tok=11582 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:29:58,870] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fb7f8200244661a9e24b010c5b57fa8 attempt=1 +[2026-08-21 16:29:58,877] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fb7f8200244661a9e24b010c5b57fa8 status=400 post_dur=0.005s +[2026-08-21 16:29:58,877] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7fb7f8200244661a9e24b010c5b57fa8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:29:58,882] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14ff5b55b889e97c1a7e80193796aa58 attempt=1 +[2026-08-21 16:29:59,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14ff5b55b889e97c1a7e80193796aa58 status=200 post_dur=0.434s +[2026-08-21 16:30:33,245] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14ff5b55b889e97c1a7e80193796aa58 total=34362.9ms bytes=18436 finished=True finish=tool_calls stop=None out_tok=305 prompt_tok=13139 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:30:33,250] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 attempt=1 +[2026-08-21 16:30:33,726] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 status=200 post_dur=0.476s +[2026-08-21 16:30:51,063] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=01160a3a9c0fac4db0e5ec03e0acb2f5 total=17813.2ms bytes=7674 finished=True finish=tool_calls stop=None out_tok=65 prompt_tok=30912 tps=3.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:30:51,068] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=60ede395352414a38079a484eaf198de attempt=1 +[2026-08-21 16:30:51,497] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=60ede395352414a38079a484eaf198de status=200 post_dur=0.429s +[2026-08-21 16:31:22,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=60ede395352414a38079a484eaf198de total=31842.0ms bytes=27946 finished=True finish=tool_calls stop=None out_tok=268 prompt_tok=13720 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:31:22,913] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0144b8b9927afe3007c1368bb0ccda39 attempt=1 +[2026-08-21 16:31:23,197] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0144b8b9927afe3007c1368bb0ccda39 status=200 post_dur=0.284s +[2026-08-21 16:35:54,550] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0144b8b9927afe3007c1368bb0ccda39 total=271636.5ms bytes=181397 finished=True finish=stop stop=None out_tok=642 prompt_tok=790 tps=2.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:35:54,553] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e416fbe4d56d069fc7e605809cfba44d attempt=1 +[2026-08-21 16:35:54,843] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e416fbe4d56d069fc7e605809cfba44d status=200 post_dur=0.290s +[2026-08-21 16:38:33,905] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e416fbe4d56d069fc7e605809cfba44d total=159352.2ms bytes=535685 finished=True finish=stop stop=None out_tok=1843 prompt_tok=251 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:38:33,908] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cc81042dc54416c8768e82fee13770b3 attempt=1 +[2026-08-21 16:38:34,361] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cc81042dc54416c8768e82fee13770b3 status=200 post_dur=0.452s +[2026-08-21 16:39:11,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cc81042dc54416c8768e82fee13770b3 total=37420.6ms bytes=24402 finished=True finish=tool_calls stop=None out_tok=336 prompt_tok=7433 tps=9.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:39:11,334] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b21c998e2c72a301cbf8c9a5abdb4068 attempt=1 +[2026-08-21 16:39:11,807] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b21c998e2c72a301cbf8c9a5abdb4068 status=200 post_dur=0.473s +[2026-08-21 16:39:27,479] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b21c998e2c72a301cbf8c9a5abdb4068 total=16144.8ms bytes=5607 finished=True finish=tool_calls stop=None out_tok=59 prompt_tok=32060 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:39:27,489] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b31287524a5bdde3d489b19723abeb8d attempt=1 +[2026-08-21 16:39:27,495] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b31287524a5bdde3d489b19723abeb8d status=400 post_dur=0.005s +[2026-08-21 16:39:27,495] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b31287524a5bdde3d489b19723abeb8d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:39:27,500] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e3ed7dd1515cb0be028e2775fe5a4600 attempt=1 +[2026-08-21 16:39:27,910] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e3ed7dd1515cb0be028e2775fe5a4600 status=200 post_dur=0.410s +[2026-08-21 16:39:39,945] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e3ed7dd1515cb0be028e2775fe5a4600 total=12444.4ms bytes=10979 finished=True finish=tool_calls stop=None out_tok=109 prompt_tok=7307 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:39:39,947] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4848e81852f3718e4afa6f6db26720e6 attempt=1 +[2026-08-21 16:39:40,368] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4848e81852f3718e4afa6f6db26720e6 status=200 post_dur=0.421s +[2026-08-21 16:39:46,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4848e81852f3718e4afa6f6db26720e6 total=6174.5ms bytes=9331 finished=True finish=stop stop=None out_tok=31 prompt_tok=7414 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:39:46,123] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9571bb4868f83194065d93aefe25be3f attempt=1 +[2026-08-21 16:39:46,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9571bb4868f83194065d93aefe25be3f status=200 post_dur=0.404s +[2026-08-21 16:39:55,863] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9571bb4868f83194065d93aefe25be3f total=9739.3ms bytes=13727 finished=True finish=stop stop=None out_tok=46 prompt_tok=7515 tps=4.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:39:55,865] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d77d4756eca9a5bfb7c18e94cd149cf2 attempt=1 +[2026-08-21 16:39:56,137] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d77d4756eca9a5bfb7c18e94cd149cf2 status=200 post_dur=0.272s +[2026-08-21 16:44:01,960] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d77d4756eca9a5bfb7c18e94cd149cf2 total=246094.7ms bytes=842389 finished=True finish=stop stop=None out_tok=2892 prompt_tok=388 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:44:01,965] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0254959a6925f264971a93e914090cbc attempt=1 +[2026-08-21 16:44:02,422] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0254959a6925f264971a93e914090cbc status=200 post_dur=0.456s +[2026-08-21 16:44:27,972] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0254959a6925f264971a93e914090cbc total=26006.9ms bytes=18838 finished=True finish=tool_calls stop=None out_tok=213 prompt_tok=8705 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:44:27,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3fe50daa51b851305e691f1bb7c0057c attempt=1 +[2026-08-21 16:44:28,408] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3fe50daa51b851305e691f1bb7c0057c status=200 post_dur=0.432s +[2026-08-21 16:44:37,575] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3fe50daa51b851305e691f1bb7c0057c total=9599.4ms bytes=8456 finished=True finish=stop stop=None out_tok=28 prompt_tok=8055 tps=2.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:44:37,577] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e9f02c35f7a9f4f68a6a144193fac24 attempt=1 +[2026-08-21 16:44:37,994] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e9f02c35f7a9f4f68a6a144193fac24 status=200 post_dur=0.416s +[2026-08-21 16:44:48,245] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e9f02c35f7a9f4f68a6a144193fac24 total=10667.4ms bytes=7873 finished=True finish=stop stop=None out_tok=26 prompt_tok=8507 tps=2.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:44:48,247] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=66a411a3713d8ad4fd1d1790a0d2c5ac attempt=1 +[2026-08-21 16:44:48,662] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=66a411a3713d8ad4fd1d1790a0d2c5ac status=200 post_dur=0.415s +[2026-08-21 16:45:04,563] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=66a411a3713d8ad4fd1d1790a0d2c5ac total=16315.5ms bytes=18152 finished=True finish=stop stop=None out_tok=61 prompt_tok=9334 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:45:04,565] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ce4171917f54dcc759f9601e14f5215 attempt=1 +[2026-08-21 16:45:04,977] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ce4171917f54dcc759f9601e14f5215 status=200 post_dur=0.412s +[2026-08-21 16:45:15,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3ce4171917f54dcc759f9601e14f5215 total=10731.9ms bytes=9391 finished=True finish=tool_calls stop=None out_tok=74 prompt_tok=9221 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:45:15,302] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=727f330a2980b24d2bab5ccecfbe5d55 attempt=1 +[2026-08-21 16:45:15,774] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=727f330a2980b24d2bab5ccecfbe5d55 status=200 post_dur=0.471s +[2026-08-21 16:45:34,362] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=727f330a2980b24d2bab5ccecfbe5d55 total=19059.5ms bytes=7101 finished=True finish=tool_calls stop=None out_tok=67 prompt_tok=33492 tps=3.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:45:34,368] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c321c704b52eb67b2ca92cf66d9e016 attempt=1 +[2026-08-21 16:45:34,841] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c321c704b52eb67b2ca92cf66d9e016 status=200 post_dur=0.473s +[2026-08-21 16:45:55,273] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9c321c704b52eb67b2ca92cf66d9e016 total=20905.2ms bytes=6240 finished=True finish=tool_calls stop=None out_tok=68 prompt_tok=33606 tps=3.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:45:55,280] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=405548cab3cb18d726be17fc7c373ecd attempt=1 +[2026-08-21 16:45:55,747] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=405548cab3cb18d726be17fc7c373ecd status=200 post_dur=0.467s +[2026-08-21 16:46:06,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=405548cab3cb18d726be17fc7c373ecd total=10926.9ms bytes=9403 finished=True finish=tool_calls stop=None out_tok=54 prompt_tok=33834 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:46:06,211] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b0fe3c8521896490e23da8dfe4e63b38 attempt=1 +[2026-08-21 16:46:06,623] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b0fe3c8521896490e23da8dfe4e63b38 status=200 post_dur=0.412s +[2026-08-21 16:46:34,560] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b0fe3c8521896490e23da8dfe4e63b38 total=28349.3ms bytes=11322 finished=True finish=tool_calls stop=None out_tok=226 prompt_tok=9252 tps=8.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:46:34,566] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 attempt=1 +[2026-08-21 16:46:35,058] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 status=200 post_dur=0.492s +[2026-08-21 16:49:16,337] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ecf6c3f9f9c9a1cd83befed2b66e0b22 total=161770.6ms bytes=11576 finished=True finish=tool_calls stop=None out_tok=335 prompt_tok=34716 tps=2.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:49:16,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 attempt=1 +[2026-08-21 16:49:16,782] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 status=200 post_dur=0.441s +[2026-08-21 16:49:30,360] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=233e1cd6dacd5449ac3d8a4b3d4ddc66 total=14018.6ms bytes=13826 finished=True finish=tool_calls stop=None out_tok=150 prompt_tok=8017 tps=10.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:49:30,362] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7383fb22c93f6890d7647632036c16bb attempt=1 +[2026-08-21 16:49:30,776] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7383fb22c93f6890d7647632036c16bb status=200 post_dur=0.413s +[2026-08-21 16:50:03,436] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7383fb22c93f6890d7647632036c16bb total=33073.4ms bytes=12851 finished=True finish=tool_calls stop=None out_tok=304 prompt_tok=8435 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:50:03,437] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80a75b9fec157ea6e81ad68cf15a50c3 attempt=1 +[2026-08-21 16:50:03,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80a75b9fec157ea6e81ad68cf15a50c3 status=200 post_dur=0.272s +[2026-08-21 16:51:21,128] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80a75b9fec157ea6e81ad68cf15a50c3 total=77690.6ms bytes=247103 finished=True finish=stop stop=None out_tok=871 prompt_tok=1471 tps=11.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:51:21,135] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=edb89c582b082458dd3e33b1761b8d78 attempt=1 +[2026-08-21 16:51:21,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=edb89c582b082458dd3e33b1761b8d78 status=400 post_dur=0.009s +[2026-08-21 16:51:21,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=edb89c582b082458dd3e33b1761b8d78 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:51:21,153] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=82ff65cddafe6fb19c5b0f6e6c95f64f attempt=1 +[2026-08-21 16:51:21,686] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=82ff65cddafe6fb19c5b0f6e6c95f64f status=200 post_dur=0.527s +[2026-08-21 16:54:05,719] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=82ff65cddafe6fb19c5b0f6e6c95f64f total=164566.4ms bytes=16321 finished=True finish=tool_calls stop=None out_tok=359 prompt_tok=35317 tps=2.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:54:05,728] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 attempt=1 +[2026-08-21 16:54:06,233] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 status=200 post_dur=0.505s +[2026-08-21 16:54:18,289] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=29e8ec2f1bdd0b51e6a0df3f5b489d00 total=12561.1ms bytes=6487 finished=True finish=tool_calls stop=None out_tok=60 prompt_tok=35129 tps=4.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:54:18,298] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5602bdaf443488e897d8b901f4f001a5 attempt=1 +[2026-08-21 16:54:18,302] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5602bdaf443488e897d8b901f4f001a5 status=400 post_dur=0.004s +[2026-08-21 16:54:18,302] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5602bdaf443488e897d8b901f4f001a5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:54:18,318] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=50b3dd5c165a5799ea46b1a4bf5196e1 attempt=1 +[2026-08-21 16:54:18,323] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=50b3dd5c165a5799ea46b1a4bf5196e1 status=400 post_dur=0.004s +[2026-08-21 16:54:18,323] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=50b3dd5c165a5799ea46b1a4bf5196e1 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:54:18,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab2963e3325789542c112702c80b5fbe attempt=1 +[2026-08-21 16:54:18,740] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab2963e3325789542c112702c80b5fbe status=200 post_dur=0.412s +[2026-08-21 16:54:30,584] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ab2963e3325789542c112702c80b5fbe total=12255.4ms bytes=6695 finished=True finish=stop stop=None out_tok=22 prompt_tok=7823 tps=1.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:54:30,585] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8b8e1a9e1c4915fded776b3a404e5900 attempt=1 +[2026-08-21 16:54:30,987] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8b8e1a9e1c4915fded776b3a404e5900 status=200 post_dur=0.402s +[2026-08-21 16:54:43,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8b8e1a9e1c4915fded776b3a404e5900 total=12685.2ms bytes=13907 finished=True finish=stop stop=None out_tok=47 prompt_tok=1893 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:54:43,278] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c3380e499ef38094b85d8b9cbb72383e attempt=1 +[2026-08-21 16:54:43,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c3380e499ef38094b85d8b9cbb72383e status=400 post_dur=0.006s +[2026-08-21 16:54:43,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c3380e499ef38094b85d8b9cbb72383e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:54:43,293] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ee3baaad3fa44bbe74cc7e9858accee attempt=1 +[2026-08-21 16:54:43,301] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ee3baaad3fa44bbe74cc7e9858accee status=400 post_dur=0.003s +[2026-08-21 16:54:43,301] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3ee3baaad3fa44bbe74cc7e9858accee status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 16:54:43,305] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=28710330b7557818f6edad22899b9bf9 attempt=1 +[2026-08-21 16:54:43,722] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=28710330b7557818f6edad22899b9bf9 status=200 post_dur=0.417s +[2026-08-21 16:55:18,235] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=28710330b7557818f6edad22899b9bf9 total=34930.3ms bytes=22191 finished=True finish=tool_calls stop=None out_tok=308 prompt_tok=10773 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:55:18,238] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=542cc693537603e442f286c26145e05d attempt=1 +[2026-08-21 16:55:18,657] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=542cc693537603e442f286c26145e05d status=200 post_dur=0.419s +[2026-08-21 16:55:52,881] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=542cc693537603e442f286c26145e05d total=34643.2ms bytes=30112 finished=True finish=tool_calls stop=None out_tok=302 prompt_tok=7438 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:55:52,891] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e9cade087de6458ef3ed3970deba4b8 attempt=1 +[2026-08-21 16:55:53,432] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e9cade087de6458ef3ed3970deba4b8 status=200 post_dur=0.541s +[2026-08-21 16:58:17,036] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e9cade087de6458ef3ed3970deba4b8 total=144145.4ms bytes=75129 finished=True finish=tool_calls stop=None out_tok=291 prompt_tok=67263 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 16:58:17,050] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 attempt=1 +[2026-08-21 16:58:17,634] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 status=200 post_dur=0.584s +[2026-08-21 17:00:26,237] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b337160cf1dcbb2543b24fdcfb0c0eb3 total=129187.2ms bytes=5934 finished=True finish=tool_calls stop=None out_tok=133 prompt_tok=73075 tps=1.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:00:26,242] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=df0a36329f95a99cf3f2b09499f56721 attempt=1 +[2026-08-21 17:00:26,684] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=df0a36329f95a99cf3f2b09499f56721 status=200 post_dur=0.442s +[2026-08-21 17:01:00,545] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=df0a36329f95a99cf3f2b09499f56721 total=34302.4ms bytes=16209 finished=True finish=tool_calls stop=None out_tok=359 prompt_tok=7752 tps=10.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:01:00,547] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14de2d899fc8516106395c4d9b78336b attempt=1 +[2026-08-21 17:01:00,974] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14de2d899fc8516106395c4d9b78336b status=200 post_dur=0.427s +[2026-08-21 17:01:20,212] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14de2d899fc8516106395c4d9b78336b total=19665.0ms bytes=15986 finished=True finish=tool_calls stop=None out_tok=99 prompt_tok=7319 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:01:20,214] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7854323f23998fa50f3c845880c2ecb1 attempt=1 +[2026-08-21 17:01:20,215] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 46% (396/881) has_cb=True +[2026-08-21 17:01:20,640] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7854323f23998fa50f3c845880c2ecb1 status=200 post_dur=0.426s +[2026-08-21 17:01:45,813] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7854323f23998fa50f3c845880c2ecb1 total=25598.7ms bytes=17180 finished=True finish=tool_calls stop=None out_tok=153 prompt_tok=11555 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:01:45,816] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9f2bbd7143b34ed94b65a7193a898be9 attempt=1 +[2026-08-21 17:01:46,230] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9f2bbd7143b34ed94b65a7193a898be9 status=200 post_dur=0.414s +[2026-08-21 17:02:03,582] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9f2bbd7143b34ed94b65a7193a898be9 total=17766.2ms bytes=16518 finished=True finish=tool_calls stop=None out_tok=162 prompt_tok=7646 tps=9.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:02:03,590] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e840166adea29bc2e6f86c559ff8e93f attempt=1 +[2026-08-21 17:02:04,159] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e840166adea29bc2e6f86c559ff8e93f status=200 post_dur=0.568s +[2026-08-21 17:04:43,085] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e840166adea29bc2e6f86c559ff8e93f total=159495.0ms bytes=16311 finished=True finish=tool_calls stop=None out_tok=313 prompt_tok=74107 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:04:43,100] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0f28b08a0330b59170b78e9c386a68ab attempt=1 +[2026-08-21 17:04:43,108] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0f28b08a0330b59170b78e9c386a68ab status=400 post_dur=0.007s +[2026-08-21 17:04:43,108] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0f28b08a0330b59170b78e9c386a68ab status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:04:43,128] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c2d8fbfc292584bf8cb1f080e8b57140 attempt=1 +[2026-08-21 17:04:43,136] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c2d8fbfc292584bf8cb1f080e8b57140 status=400 post_dur=0.008s +[2026-08-21 17:04:43,137] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c2d8fbfc292584bf8cb1f080e8b57140 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:04:43,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=12c40991cbb4006666b23ef1bb6db526 attempt=1 +[2026-08-21 17:04:43,593] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=12c40991cbb4006666b23ef1bb6db526 status=200 post_dur=0.449s +[2026-08-21 17:04:54,200] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=12c40991cbb4006666b23ef1bb6db526 total=11055.6ms bytes=15198 finished=True finish=stop stop=None out_tok=51 prompt_tok=7865 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:04:54,202] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ba1621bc6e605ee9a62e281355307441 attempt=1 +[2026-08-21 17:04:54,638] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ba1621bc6e605ee9a62e281355307441 status=200 post_dur=0.435s +[2026-08-21 17:05:42,807] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ba1621bc6e605ee9a62e281355307441 total=48605.1ms bytes=137657 finished=True finish=stop stop=None out_tok=483 prompt_tok=8979 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:05:42,811] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fa88e748c5c989d4bf7b78d539747aba attempt=1 +[2026-08-21 17:05:43,237] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fa88e748c5c989d4bf7b78d539747aba status=200 post_dur=0.426s +[2026-08-21 17:06:07,679] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fa88e748c5c989d4bf7b78d539747aba total=24867.8ms bytes=12924 finished=True finish=tool_calls stop=None out_tok=248 prompt_tok=8024 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:06:07,687] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 attempt=1 +[2026-08-21 17:06:08,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 status=200 post_dur=0.582s +[2026-08-21 17:09:08,708] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b4f1721f9e9ad86e96ecc09eacdc06a3 total=181020.5ms bytes=27131 finished=True finish=tool_calls stop=None out_tok=607 prompt_tok=74884 tps=3.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:09:08,726] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9fa1231b3de4a2ea9f5c284274cd70e3 attempt=1 +[2026-08-21 17:09:08,737] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9fa1231b3de4a2ea9f5c284274cd70e3 status=400 post_dur=0.010s +[2026-08-21 17:09:08,737] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=9fa1231b3de4a2ea9f5c284274cd70e3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:09:08,745] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=665356988c08c18ac7adebe5d1ab25d1 attempt=1 +[2026-08-21 17:09:09,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=665356988c08c18ac7adebe5d1ab25d1 status=200 post_dur=0.446s +[2026-08-21 17:09:48,157] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=665356988c08c18ac7adebe5d1ab25d1 total=39411.0ms bytes=32309 finished=True finish=tool_calls stop=None out_tok=364 prompt_tok=8990 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:09:48,158] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab attempt=1 +[2026-08-21 17:09:48,573] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab status=200 post_dur=0.414s +[2026-08-21 17:10:00,495] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f5c0d5f64d63b4e97ffc8a2264b27ab total=12336.6ms bytes=7933 finished=True finish=tool_calls stop=None out_tok=74 prompt_tok=1791 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:10:00,510] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9ba23d4edca7c884690c522163db9e69 attempt=1 +[2026-08-21 17:10:00,518] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9ba23d4edca7c884690c522163db9e69 status=400 post_dur=0.008s +[2026-08-21 17:10:00,519] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=9ba23d4edca7c884690c522163db9e69 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:10:00,526] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ec6541c7e7d698b8550e27e7eb95dd5e attempt=1 +[2026-08-21 17:10:00,807] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ec6541c7e7d698b8550e27e7eb95dd5e status=200 post_dur=0.281s +[2026-08-21 17:10:51,576] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ec6541c7e7d698b8550e27e7eb95dd5e total=51050.6ms bytes=148782 finished=True finish=stop stop=None out_tok=522 prompt_tok=1344 tps=10.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:10:51,591] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5eba948b1bd4c4fb79495e2a81f56a7 attempt=1 +[2026-08-21 17:10:51,602] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5eba948b1bd4c4fb79495e2a81f56a7 status=400 post_dur=0.011s +[2026-08-21 17:10:51,602] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e5eba948b1bd4c4fb79495e2a81f56a7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:10:51,610] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d3fed72e042e604e764c644de6d2aceb attempt=1 +[2026-08-21 17:10:51,913] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d3fed72e042e604e764c644de6d2aceb status=200 post_dur=0.302s +[2026-08-21 17:13:46,720] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d3fed72e042e604e764c644de6d2aceb total=175110.0ms bytes=596323 finished=True finish=length stop=None out_tok=2048 prompt_tok=349 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:13:46,730] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9216bd6b4a6d971042b413ba0da531cb attempt=1 +[2026-08-21 17:13:47,341] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9216bd6b4a6d971042b413ba0da531cb status=200 post_dur=0.610s +[2026-08-21 17:15:47,228] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9216bd6b4a6d971042b413ba0da531cb total=120497.2ms bytes=49827 finished=True finish=stop stop=None out_tok=173 prompt_tok=75657 tps=1.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:15:47,243] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d6b8abbcc880d4e08cd5bee4a446b26 attempt=1 +[2026-08-21 17:15:47,264] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d6b8abbcc880d4e08cd5bee4a446b26 status=400 post_dur=0.007s +[2026-08-21 17:15:47,264] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3d6b8abbcc880d4e08cd5bee4a446b26 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:15:47,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e695214d50c8e016a8d2a6f6739cc5a attempt=1 +[2026-08-21 17:15:47,717] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e695214d50c8e016a8d2a6f6739cc5a status=200 post_dur=0.447s +[2026-08-21 17:16:09,909] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6e695214d50c8e016a8d2a6f6739cc5a total=22639.3ms bytes=11027 finished=True finish=tool_calls stop=None out_tok=131 prompt_tok=7331 tps=5.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:16:09,911] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ba126c1bdb15e40c22f9a58d1791b733 attempt=1 +[2026-08-21 17:16:10,337] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ba126c1bdb15e40c22f9a58d1791b733 status=200 post_dur=0.426s +[2026-08-21 17:16:32,486] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ba126c1bdb15e40c22f9a58d1791b733 total=22574.8ms bytes=14786 finished=True finish=tool_calls stop=None out_tok=184 prompt_tok=8006 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:16:32,502] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=57832f49558fd182b94b8e85dacaec5a attempt=1 +[2026-08-21 17:16:32,510] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=57832f49558fd182b94b8e85dacaec5a status=400 post_dur=0.008s +[2026-08-21 17:16:32,510] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=57832f49558fd182b94b8e85dacaec5a status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:16:32,521] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fcbb0eefee83b04e30d08fc49880dfc5 attempt=1 +[2026-08-21 17:16:32,960] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fcbb0eefee83b04e30d08fc49880dfc5 status=200 post_dur=0.438s +[2026-08-21 17:16:56,278] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fcbb0eefee83b04e30d08fc49880dfc5 total=23756.5ms bytes=13099 finished=True finish=tool_calls stop=None out_tok=193 prompt_tok=8465 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:16:56,298] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6b03c10d014a17217b95d102b07ca8a attempt=1 +[2026-08-21 17:16:56,306] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6b03c10d014a17217b95d102b07ca8a status=400 post_dur=0.007s +[2026-08-21 17:16:56,306] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e6b03c10d014a17217b95d102b07ca8a status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:16:56,316] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=294958e82a507ea8e7ff8b02009ab9e7 attempt=1 +[2026-08-21 17:16:56,740] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=294958e82a507ea8e7ff8b02009ab9e7 status=200 post_dur=0.424s +[2026-08-21 17:17:12,609] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=294958e82a507ea8e7ff8b02009ab9e7 total=16293.5ms bytes=15559 finished=True finish=tool_calls stop=None out_tok=139 prompt_tok=8983 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:17:12,612] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b8af517857e40649f6620ab38d8fa42 attempt=1 +[2026-08-21 17:17:13,029] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b8af517857e40649f6620ab38d8fa42 status=200 post_dur=0.417s +[2026-08-21 17:17:25,209] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b8af517857e40649f6620ab38d8fa42 total=12597.3ms bytes=19005 finished=True finish=stop stop=None out_tok=64 prompt_tok=9096 tps=5.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:17:25,221] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=04da7c9b034138a392ec3af7a144cf3a attempt=1 +[2026-08-21 17:17:25,227] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=04da7c9b034138a392ec3af7a144cf3a status=400 post_dur=0.006s +[2026-08-21 17:17:25,227] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=04da7c9b034138a392ec3af7a144cf3a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:17:25,244] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7bbff6735d1705bc9b1049a1a56a3e54 attempt=1 +[2026-08-21 17:17:25,249] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7bbff6735d1705bc9b1049a1a56a3e54 status=400 post_dur=0.005s +[2026-08-21 17:17:25,249] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7bbff6735d1705bc9b1049a1a56a3e54 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:17:25,254] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87fdd72f02bf9189b4ee2f90e8d96b02 attempt=1 +[2026-08-21 17:17:25,533] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87fdd72f02bf9189b4ee2f90e8d96b02 status=200 post_dur=0.278s +[2026-08-21 17:19:31,481] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=87fdd72f02bf9189b4ee2f90e8d96b02 total=126227.0ms bytes=414370 finished=True finish=stop stop=None out_tok=1426 prompt_tok=265 tps=11.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:19:31,483] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=40260b037528a86dc15250ad42f50767 attempt=1 +[2026-08-21 17:19:31,786] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=40260b037528a86dc15250ad42f50767 status=200 post_dur=0.303s +[2026-08-21 17:21:44,006] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=40260b037528a86dc15250ad42f50767 total=132523.0ms bytes=446596 finished=True finish=stop stop=None out_tok=1536 prompt_tok=262 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:21:44,010] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0e89471cb9498a6c5ff350a3461b6dff attempt=1 +[2026-08-21 17:21:44,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0e89471cb9498a6c5ff350a3461b6dff status=200 post_dur=0.467s +[2026-08-21 17:22:03,217] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0e89471cb9498a6c5ff350a3461b6dff total=19207.3ms bytes=9113 finished=True finish=tool_calls stop=None out_tok=167 prompt_tok=9895 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:22:03,232] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab8099c4a0532cc5d8d25a833bae242e attempt=1 +[2026-08-21 17:22:03,240] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab8099c4a0532cc5d8d25a833bae242e status=400 post_dur=0.007s +[2026-08-21 17:22:03,240] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ab8099c4a0532cc5d8d25a833bae242e status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:22:03,250] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be5a6db40cdfc03ac81ff32cb810a7d1 attempt=1 +[2026-08-21 17:22:03,685] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be5a6db40cdfc03ac81ff32cb810a7d1 status=200 post_dur=0.435s +[2026-08-21 17:22:20,544] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=be5a6db40cdfc03ac81ff32cb810a7d1 total=17294.4ms bytes=30119 finished=True finish=stop stop=None out_tok=104 prompt_tok=10277 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:22:20,547] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=04524a5823cf67123c6a01475b370390 attempt=1 +[2026-08-21 17:22:20,979] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=04524a5823cf67123c6a01475b370390 status=200 post_dur=0.432s +[2026-08-21 17:23:01,590] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=04524a5823cf67123c6a01475b370390 total=41042.7ms bytes=32253 finished=True finish=tool_calls stop=None out_tok=376 prompt_tok=7229 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:23:01,591] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=007f176bf501898e1efca138dc288c0c attempt=1 +[2026-08-21 17:23:01,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=007f176bf501898e1efca138dc288c0c status=200 post_dur=0.283s +[2026-08-21 17:25:48,871] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=007f176bf501898e1efca138dc288c0c total=167279.6ms bytes=562956 finished=True finish=stop stop=None out_tok=1935 prompt_tok=766 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:25:48,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d6e4320c6266d9ba375d9869e784508d attempt=1 +[2026-08-21 17:25:49,180] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d6e4320c6266d9ba375d9869e784508d status=200 post_dur=0.306s +[2026-08-21 17:28:41,436] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d6e4320c6266d9ba375d9869e784508d total=172561.7ms bytes=596995 finished=True finish=length stop=None out_tok=2048 prompt_tok=766 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:28:41,440] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3546faf14839049a620c533440ef2728 attempt=1 +[2026-08-21 17:28:41,893] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3546faf14839049a620c533440ef2728 status=200 post_dur=0.453s +[2026-08-21 17:29:12,008] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3546faf14839049a620c533440ef2728 total=30568.5ms bytes=32259 finished=True finish=tool_calls stop=None out_tok=255 prompt_tok=7197 tps=8.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:29:12,025] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5c59f84adacc104b26d222ffc941feb9 attempt=1 +[2026-08-21 17:29:12,038] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5c59f84adacc104b26d222ffc941feb9 status=400 post_dur=0.013s +[2026-08-21 17:29:12,038] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5c59f84adacc104b26d222ffc941feb9 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:29:12,048] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bf5edec2786bc068979f6c1af9534bcb attempt=1 +[2026-08-21 17:29:12,493] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bf5edec2786bc068979f6c1af9534bcb status=200 post_dur=0.445s +[2026-08-21 17:29:47,962] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bf5edec2786bc068979f6c1af9534bcb total=35914.2ms bytes=11702 finished=True finish=tool_calls stop=None out_tok=263 prompt_tok=8745 tps=7.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:29:47,964] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db72c2d754aa0d17bdb0cc491861ead4 attempt=1 +[2026-08-21 17:29:48,401] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db72c2d754aa0d17bdb0cc491861ead4 status=200 post_dur=0.437s +[2026-08-21 17:30:02,467] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db72c2d754aa0d17bdb0cc491861ead4 total=14503.0ms bytes=11048 finished=True finish=stop stop=None out_tok=37 prompt_tok=7346 tps=2.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:30:02,479] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=feaafb10695ae5754022c5c4960adf18 attempt=1 +[2026-08-21 17:30:02,485] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=feaafb10695ae5754022c5c4960adf18 status=400 post_dur=0.006s +[2026-08-21 17:30:02,485] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=feaafb10695ae5754022c5c4960adf18 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:30:02,491] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a226a9108affcc69382a56d80100595d attempt=1 +[2026-08-21 17:30:02,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a226a9108affcc69382a56d80100595d status=200 post_dur=0.426s +[2026-08-21 17:30:14,196] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a226a9108affcc69382a56d80100595d total=11704.9ms bytes=9352 finished=True finish=tool_calls stop=None out_tok=62 prompt_tok=7573 tps=5.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:30:14,198] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a6092c183888b28b15f5c45bbb0fadf2 attempt=1 +[2026-08-21 17:30:14,476] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a6092c183888b28b15f5c45bbb0fadf2 status=200 post_dur=0.278s +[2026-08-21 17:32:33,014] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a6092c183888b28b15f5c45bbb0fadf2 total=138816.2ms bytes=470832 finished=True finish=stop stop=None out_tok=1620 prompt_tok=370 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:32:33,017] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0565df1a12f2ca6e37273d15f3d14b4d attempt=1 +[2026-08-21 17:32:33,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0565df1a12f2ca6e37273d15f3d14b4d status=200 post_dur=0.302s +[2026-08-21 17:34:23,891] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0565df1a12f2ca6e37273d15f3d14b4d total=110873.7ms bytes=372566 finished=True finish=stop stop=None out_tok=1283 prompt_tok=249 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:34:23,895] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b900e4d7a184b278ed832645f55ab2b8 attempt=1 +[2026-08-21 17:34:24,364] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b900e4d7a184b278ed832645f55ab2b8 status=200 post_dur=0.469s +[2026-08-21 17:34:35,790] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b900e4d7a184b278ed832645f55ab2b8 total=11895.2ms bytes=10209 finished=True finish=stop stop=None out_tok=34 prompt_tok=9083 tps=2.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:34:35,793] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=022d2b2b8c7d13cbff0c1b9628f84a6c attempt=1 +[2026-08-21 17:34:35,793] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 50% (440/881) has_cb=True +[2026-08-21 17:34:36,214] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=022d2b2b8c7d13cbff0c1b9628f84a6c status=200 post_dur=0.421s +[2026-08-21 17:35:01,840] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=022d2b2b8c7d13cbff0c1b9628f84a6c total=26046.9ms bytes=11512 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=9567 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:35:01,869] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7581d09638f73e2b378c66ff03b96dd8 attempt=1 +[2026-08-21 17:35:01,877] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7581d09638f73e2b378c66ff03b96dd8 status=400 post_dur=0.008s +[2026-08-21 17:35:01,878] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7581d09638f73e2b378c66ff03b96dd8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:35:01,909] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7e4f846bbcd425fc5db38309beee377 attempt=1 +[2026-08-21 17:35:01,916] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7e4f846bbcd425fc5db38309beee377 status=400 post_dur=0.007s +[2026-08-21 17:35:01,916] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d7e4f846bbcd425fc5db38309beee377 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:35:01,925] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=32b82933b54025b46106559643673cf8 attempt=1 +[2026-08-21 17:35:02,203] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=32b82933b54025b46106559643673cf8 status=200 post_dur=0.276s +[2026-08-21 17:37:57,660] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=32b82933b54025b46106559643673cf8 total=175735.0ms bytes=596508 finished=True finish=length stop=None out_tok=2048 prompt_tok=355 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:37:57,662] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f8c1bca56172e3337fbea71b510b6ea9 attempt=1 +[2026-08-21 17:37:57,964] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f8c1bca56172e3337fbea71b510b6ea9 status=200 post_dur=0.302s +[2026-08-21 17:40:40,968] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f8c1bca56172e3337fbea71b510b6ea9 total=163305.8ms bytes=552737 finished=True finish=stop stop=None out_tok=1901 prompt_tok=319 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:40:40,971] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 attempt=1 +[2026-08-21 17:40:41,278] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 status=200 post_dur=0.306s +[2026-08-21 17:43:11,704] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f1398ce62e3bbb27ec0e1a78a09a1f30 total=150732.9ms bytes=519578 finished=True finish=stop stop=None out_tok=1787 prompt_tok=355 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:43:11,711] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bea2801c53f38667fdbb545d12a6c42d attempt=1 +[2026-08-21 17:43:11,715] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bea2801c53f38667fdbb545d12a6c42d status=400 post_dur=0.004s +[2026-08-21 17:43:11,715] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bea2801c53f38667fdbb545d12a6c42d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:43:11,717] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ebb27d04a82dc701ceff0fc7cf634ca4 attempt=1 +[2026-08-21 17:43:12,020] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ebb27d04a82dc701ceff0fc7cf634ca4 status=200 post_dur=0.303s +[2026-08-21 17:46:04,309] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ebb27d04a82dc701ceff0fc7cf634ca4 total=172591.9ms bytes=596462 finished=True finish=length stop=None out_tok=2048 prompt_tok=355 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:46:04,315] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b31f436e5f5e703425729a09d9384f7f attempt=1 +[2026-08-21 17:46:04,320] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b31f436e5f5e703425729a09d9384f7f status=400 post_dur=0.005s +[2026-08-21 17:46:04,320] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b31f436e5f5e703425729a09d9384f7f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 16384}] (retryable=False, attempt=1) +[2026-08-21 17:46:04,326] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1a6522cc010c520c4373d69e9a17ac82 attempt=1 +[2026-08-21 17:46:04,331] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1a6522cc010c520c4373d69e9a17ac82 status=400 post_dur=0.005s +[2026-08-21 17:46:04,332] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1a6522cc010c520c4373d69e9a17ac82 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 16384}] (retryable=False, attempt=1) +[2026-08-21 17:46:04,337] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5c3932b77a057da7caec4c8336852f26 attempt=1 +[2026-08-21 17:46:04,341] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5c3932b77a057da7caec4c8336852f26 status=400 post_dur=0.004s +[2026-08-21 17:46:04,341] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5c3932b77a057da7caec4c8336852f26 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:46:04,346] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ef445c15cceed8edec782bd8c1dd7481 attempt=1 +[2026-08-21 17:46:04,351] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ef445c15cceed8edec782bd8c1dd7481 status=400 post_dur=0.005s +[2026-08-21 17:46:04,351] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ef445c15cceed8edec782bd8c1dd7481 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 16384}] (retryable=False, attempt=1) +[2026-08-21 17:46:04,357] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7951297b80918735c3976ec42dd1bc3a attempt=1 +[2026-08-21 17:46:04,368] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7951297b80918735c3976ec42dd1bc3a status=400 post_dur=0.011s +[2026-08-21 17:46:04,377] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7951297b80918735c3976ec42dd1bc3a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 16384}] (retryable=False, attempt=1) +[2026-08-21 17:46:04,381] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=72357751f6256ba81c96cf1c75bf20de attempt=1 +[2026-08-21 17:46:04,840] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=72357751f6256ba81c96cf1c75bf20de status=200 post_dur=0.459s +[2026-08-21 17:46:52,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=72357751f6256ba81c96cf1c75bf20de total=47889.8ms bytes=32175 finished=True finish=tool_calls stop=None out_tok=472 prompt_tok=9513 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:46:52,276] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c3bc9ee2e12489608e0a6a7632bfac67 attempt=1 +[2026-08-21 17:46:52,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c3bc9ee2e12489608e0a6a7632bfac67 status=400 post_dur=0.009s +[2026-08-21 17:46:52,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c3bc9ee2e12489608e0a6a7632bfac67 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 16384}] (retryable=False, attempt=1) +[2026-08-21 17:46:52,314] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a9acfcad7d4f81bdf956b49c8c9237d2 attempt=1 +[2026-08-21 17:46:52,323] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a9acfcad7d4f81bdf956b49c8c9237d2 status=400 post_dur=0.009s +[2026-08-21 17:46:52,323] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a9acfcad7d4f81bdf956b49c8c9237d2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:46:52,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=af727512758092d747ce2d61d07ef790 attempt=1 +[2026-08-21 17:46:52,345] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=af727512758092d747ce2d61d07ef790 status=400 post_dur=0.003s +[2026-08-21 17:46:52,345] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=af727512758092d747ce2d61d07ef790 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:46:52,360] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7bd2b82352eb49f5bd56ff3259de2476 attempt=1 +[2026-08-21 17:46:52,368] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7bd2b82352eb49f5bd56ff3259de2476 status=400 post_dur=0.008s +[2026-08-21 17:46:52,369] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7bd2b82352eb49f5bd56ff3259de2476 status=400 class=request_validation error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden (retryable=False, attempt=1) +[2026-08-21 17:46:52,378] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac0b6fa67eeb91675b178489e49d32c3 attempt=1 +[2026-08-21 17:46:52,830] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac0b6fa67eeb91675b178489e49d32c3 status=200 post_dur=0.452s +[2026-08-21 17:47:09,692] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ac0b6fa67eeb91675b178489e49d32c3 total=17314.0ms bytes=6491 finished=True finish=tool_calls stop=None out_tok=60 prompt_tok=10017 tps=3.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:47:09,695] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03592b84d37aac489062c3649a7a54da attempt=1 +[2026-08-21 17:47:10,129] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03592b84d37aac489062c3649a7a54da status=200 post_dur=0.433s +[2026-08-21 17:47:24,452] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=03592b84d37aac489062c3649a7a54da total=14756.9ms bytes=10900 finished=True finish=tool_calls stop=None out_tok=75 prompt_tok=10337 tps=5.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:47:24,454] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b97f3d051c2822653eed010996e8984 attempt=1 +[2026-08-21 17:47:24,881] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b97f3d051c2822653eed010996e8984 status=200 post_dur=0.427s +[2026-08-21 17:47:38,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b97f3d051c2822653eed010996e8984 total=13709.7ms bytes=12086 finished=True finish=tool_calls stop=None out_tok=77 prompt_tok=10441 tps=5.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:47:38,167] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07b3a87bce0f474baa82b6ea7fb90697 attempt=1 +[2026-08-21 17:47:38,589] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07b3a87bce0f474baa82b6ea7fb90697 status=200 post_dur=0.422s +[2026-08-21 17:48:05,989] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=07b3a87bce0f474baa82b6ea7fb90697 total=27822.3ms bytes=80047 finished=True finish=stop stop=None out_tok=277 prompt_tok=10705 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:48:06,016] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a65800f42cc9ccda52bc1ca4aa090ef9 attempt=1 +[2026-08-21 17:48:06,027] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a65800f42cc9ccda52bc1ca4aa090ef9 status=400 post_dur=0.011s +[2026-08-21 17:48:06,027] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a65800f42cc9ccda52bc1ca4aa090ef9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:48:06,053] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=788d64d04c24ba7f49b287783b7df63d attempt=1 +[2026-08-21 17:48:06,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=788d64d04c24ba7f49b287783b7df63d status=400 post_dur=0.006s +[2026-08-21 17:48:06,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=788d64d04c24ba7f49b287783b7df63d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:48:06,066] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=56672c2a06386f9216084b205d91a299 attempt=1 +[2026-08-21 17:48:06,509] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=56672c2a06386f9216084b205d91a299 status=200 post_dur=0.443s +[2026-08-21 17:48:46,138] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=56672c2a06386f9216084b205d91a299 total=40072.6ms bytes=36888 finished=True finish=tool_calls stop=None out_tok=461 prompt_tok=7229 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:48:46,141] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=90fdbd989225f791f22a8d7c6713b8c8 attempt=1 +[2026-08-21 17:48:46,564] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=90fdbd989225f791f22a8d7c6713b8c8 status=200 post_dur=0.423s +[2026-08-21 17:49:04,498] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=90fdbd989225f791f22a8d7c6713b8c8 total=18356.7ms bytes=30834 finished=True finish=tool_calls stop=None out_tok=203 prompt_tok=7197 tps=11.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:49:04,510] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b16c5379cbe4ac359fe045f1b251d1fd attempt=1 +[2026-08-21 17:49:04,518] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b16c5379cbe4ac359fe045f1b251d1fd status=400 post_dur=0.007s +[2026-08-21 17:49:04,518] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=b16c5379cbe4ac359fe045f1b251d1fd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:49:04,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9408271375a3c55f61a62d7d54438f65 attempt=1 +[2026-08-21 17:49:04,952] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9408271375a3c55f61a62d7d54438f65 status=200 post_dur=0.424s +[2026-08-21 17:49:15,831] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9408271375a3c55f61a62d7d54438f65 total=11304.1ms bytes=10607 finished=True finish=tool_calls stop=None out_tok=90 prompt_tok=7294 tps=8.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:49:15,833] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=91cde38354627ab0586a9bb7228a330f attempt=1 +[2026-08-21 17:49:16,250] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=91cde38354627ab0586a9bb7228a330f status=200 post_dur=0.417s +[2026-08-21 17:49:31,146] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=91cde38354627ab0586a9bb7228a330f total=15313.3ms bytes=21397 finished=True finish=tool_calls stop=None out_tok=110 prompt_tok=7526 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:49:31,149] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a79e369cb5dfffe7d98a4253cf78c0f7 attempt=1 +[2026-08-21 17:49:31,575] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a79e369cb5dfffe7d98a4253cf78c0f7 status=200 post_dur=0.426s +[2026-08-21 17:49:44,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a79e369cb5dfffe7d98a4253cf78c0f7 total=13825.5ms bytes=12580 finished=True finish=tool_calls stop=None out_tok=75 prompt_tok=7841 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:49:44,977] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=767d433df35a797c831a6b269551a636 attempt=1 +[2026-08-21 17:49:45,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=767d433df35a797c831a6b269551a636 status=200 post_dur=0.415s +[2026-08-21 17:50:25,145] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=767d433df35a797c831a6b269551a636 total=40168.3ms bytes=19654 finished=True finish=tool_calls stop=None out_tok=303 prompt_tok=9886 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:50:25,148] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=559a25c823109c7916b634842e21d19b attempt=1 +[2026-08-21 17:50:25,610] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=559a25c823109c7916b634842e21d19b status=200 post_dur=0.462s +[2026-08-21 17:51:10,261] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=559a25c823109c7916b634842e21d19b total=45112.4ms bytes=70080 finished=True finish=tool_calls stop=None out_tok=354 prompt_tok=13070 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:51:10,264] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=91d117794014a96bf3b9ac1a4934dd78 attempt=1 +[2026-08-21 17:51:10,701] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=91d117794014a96bf3b9ac1a4934dd78 status=200 post_dur=0.437s +[2026-08-21 17:51:43,956] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=91d117794014a96bf3b9ac1a4934dd78 total=33692.6ms bytes=19522 finished=True finish=tool_calls stop=None out_tok=341 prompt_tok=10465 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:51:43,967] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=520d3bd3fc64de70453268e5baa2ea62 attempt=1 +[2026-08-21 17:51:43,979] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=520d3bd3fc64de70453268e5baa2ea62 status=400 post_dur=0.006s +[2026-08-21 17:51:43,979] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=520d3bd3fc64de70453268e5baa2ea62 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:51:43,987] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2a8de1821196671dc704bbcafe61dde0 attempt=1 +[2026-08-21 17:51:43,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2a8de1821196671dc704bbcafe61dde0 status=400 post_dur=0.006s +[2026-08-21 17:51:43,993] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2a8de1821196671dc704bbcafe61dde0 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:51:43,997] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7b4a18254d28c23095f6b4b7e35069a0 attempt=1 +[2026-08-21 17:51:44,446] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7b4a18254d28c23095f6b4b7e35069a0 status=200 post_dur=0.450s +[2026-08-21 17:52:21,773] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7b4a18254d28c23095f6b4b7e35069a0 total=37775.9ms bytes=16670 finished=True finish=tool_calls stop=None out_tok=365 prompt_tok=14200 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:52:21,785] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e5337acd0606cabf3bc95ef01ec4094 attempt=1 +[2026-08-21 17:52:21,793] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e5337acd0606cabf3bc95ef01ec4094 status=400 post_dur=0.008s +[2026-08-21 17:52:21,793] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6e5337acd0606cabf3bc95ef01ec4094 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:52:21,809] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=88c78115aced7a36e2a38629c6a9a3d0 attempt=1 +[2026-08-21 17:52:21,814] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=88c78115aced7a36e2a38629c6a9a3d0 status=400 post_dur=0.004s +[2026-08-21 17:52:21,814] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=88c78115aced7a36e2a38629c6a9a3d0 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:52:21,818] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2cf15ec1aeb8db5364671bff24998087 attempt=1 +[2026-08-21 17:52:22,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2cf15ec1aeb8db5364671bff24998087 status=200 post_dur=0.294s +[2026-08-21 17:54:29,444] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2cf15ec1aeb8db5364671bff24998087 total=127626.8ms bytes=432906 finished=True finish=stop stop=None out_tok=1475 prompt_tok=1133 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:54:29,448] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b attempt=1 +[2026-08-21 17:54:29,926] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b status=200 post_dur=0.478s +[2026-08-21 17:55:14,905] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9aa8f39ce1d03b5f1ffaac6a5b16c88b total=45456.7ms bytes=25331 finished=True finish=tool_calls stop=None out_tok=409 prompt_tok=14789 tps=9.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:55:14,914] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=82c6bb52d3c3ce2441c194cc6392b9c9 attempt=1 +[2026-08-21 17:55:14,921] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=82c6bb52d3c3ce2441c194cc6392b9c9 status=400 post_dur=0.005s +[2026-08-21 17:55:14,921] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=82c6bb52d3c3ce2441c194cc6392b9c9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:14,926] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6a9a7675f53ca7c151831eb61229b018 attempt=1 +[2026-08-21 17:55:14,929] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6a9a7675f53ca7c151831eb61229b018 status=400 post_dur=0.002s +[2026-08-21 17:55:14,929] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6a9a7675f53ca7c151831eb61229b018 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:14,936] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a attempt=1 +[2026-08-21 17:55:15,408] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a status=200 post_dur=0.472s +[2026-08-21 17:55:52,078] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=05bcd6d62c0c2a14dfd1949eaaa7a78a total=37141.7ms bytes=22593 finished=True finish=tool_calls stop=None out_tok=373 prompt_tok=16388 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:55:52,081] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f51294fa1775431852330ac7c37db7e6 attempt=1 +[2026-08-21 17:55:52,089] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f51294fa1775431852330ac7c37db7e6 status=400 post_dur=0.007s +[2026-08-21 17:55:52,089] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f51294fa1775431852330ac7c37db7e6 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:52,097] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 54% (484/881) has_cb=True +[2026-08-21 17:55:52,101] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=baeb99b5aa23fd7430855568b3879abe attempt=1 +[2026-08-21 17:55:52,108] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=baeb99b5aa23fd7430855568b3879abe status=400 post_dur=0.007s +[2026-08-21 17:55:52,108] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=baeb99b5aa23fd7430855568b3879abe status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:52,116] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b688f7b1b297cd106f543711cae9a4f attempt=1 +[2026-08-21 17:55:52,123] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b688f7b1b297cd106f543711cae9a4f status=400 post_dur=0.007s +[2026-08-21 17:55:52,123] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1b688f7b1b297cd106f543711cae9a4f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:52,135] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=94370a3b621376ee8fb9653c0a249680 attempt=1 +[2026-08-21 17:55:52,143] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=94370a3b621376ee8fb9653c0a249680 status=400 post_dur=0.006s +[2026-08-21 17:55:52,143] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=94370a3b621376ee8fb9653c0a249680 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:52,159] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49c00854c28f996edc5e6ad0f28a6956 attempt=1 +[2026-08-21 17:55:52,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49c00854c28f996edc5e6ad0f28a6956 status=400 post_dur=0.005s +[2026-08-21 17:55:52,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=49c00854c28f996edc5e6ad0f28a6956 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 17:55:52,177] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0ab5af499b282cf1341f1a64bf036563 attempt=1 +[2026-08-21 17:55:52,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0ab5af499b282cf1341f1a64bf036563 status=200 post_dur=0.556s +[2026-08-21 17:58:12,446] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0ab5af499b282cf1341f1a64bf036563 total=140268.4ms bytes=81307 finished=True finish=stop stop=None out_tok=276 prompt_tok=67262 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:58:12,456] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ffee06953f66beac62e984c64cd4921f attempt=1 +[2026-08-21 17:58:12,974] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ffee06953f66beac62e984c64cd4921f status=200 post_dur=0.518s +[2026-08-21 17:59:47,437] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ffee06953f66beac62e984c64cd4921f total=94981.1ms bytes=175607 finished=True finish=stop stop=None out_tok=612 prompt_tok=30128 tps=6.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 17:59:47,442] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c8407aa57c901822bd4a7f1a4824282e attempt=1 +[2026-08-21 17:59:47,896] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c8407aa57c901822bd4a7f1a4824282e status=200 post_dur=0.454s +[2026-08-21 18:00:36,659] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c8407aa57c901822bd4a7f1a4824282e total=49217.3ms bytes=31783 finished=True finish=tool_calls stop=None out_tok=436 prompt_tok=8054 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:00:36,661] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87666946e7ef49235aaaad7bba67d7aa attempt=1 +[2026-08-21 18:00:36,964] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87666946e7ef49235aaaad7bba67d7aa status=200 post_dur=0.303s +[2026-08-21 18:04:43,581] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=87666946e7ef49235aaaad7bba67d7aa total=246919.6ms bytes=839074 finished=True finish=stop stop=None out_tok=2909 prompt_tok=986 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:04:43,595] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e146957b208859356a77b2cdf7a8b5f7 attempt=1 +[2026-08-21 18:04:43,608] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e146957b208859356a77b2cdf7a8b5f7 status=400 post_dur=0.007s +[2026-08-21 18:04:43,608] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e146957b208859356a77b2cdf7a8b5f7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:04:43,616] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b4c1b81c547fe11edcb629e03e4c76d5 attempt=1 +[2026-08-21 18:04:44,106] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b4c1b81c547fe11edcb629e03e4c76d5 status=200 post_dur=0.490s +[2026-08-21 18:05:09,581] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b4c1b81c547fe11edcb629e03e4c76d5 total=25965.2ms bytes=68641 finished=True finish=stop stop=None out_tok=239 prompt_tok=17360 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:05:09,588] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aea1d259d89a2eb16856934b75f0d484 attempt=1 +[2026-08-21 18:05:09,593] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aea1d259d89a2eb16856934b75f0d484 status=400 post_dur=0.004s +[2026-08-21 18:05:09,593] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=aea1d259d89a2eb16856934b75f0d484 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:05:09,607] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2184f21cdc712067bbc06b55f9b93333 attempt=1 +[2026-08-21 18:05:09,613] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2184f21cdc712067bbc06b55f9b93333 status=400 post_dur=0.006s +[2026-08-21 18:05:09,614] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2184f21cdc712067bbc06b55f9b93333 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:05:09,624] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6d2e1495524d98b499229d18fb2719f4 attempt=1 +[2026-08-21 18:05:09,628] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6d2e1495524d98b499229d18fb2719f4 status=400 post_dur=0.002s +[2026-08-21 18:05:09,628] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6d2e1495524d98b499229d18fb2719f4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:05:09,632] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f3d7b0a4eef9318758a46bef9644daaf attempt=1 +[2026-08-21 18:05:09,640] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f3d7b0a4eef9318758a46bef9644daaf status=400 post_dur=0.008s +[2026-08-21 18:05:09,640] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f3d7b0a4eef9318758a46bef9644daaf status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:05:09,643] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c132e981015feb774a6b40404413fe48 attempt=1 +[2026-08-21 18:05:10,079] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c132e981015feb774a6b40404413fe48 status=200 post_dur=0.436s +[2026-08-21 18:05:18,475] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c132e981015feb774a6b40404413fe48 total=8832.4ms bytes=11386 finished=True finish=stop stop=None out_tok=38 prompt_tok=7388 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:05:18,478] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6056fb65ba8b11e1671ac10b9b26c05d attempt=1 +[2026-08-21 18:05:18,896] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6056fb65ba8b11e1671ac10b9b26c05d status=200 post_dur=0.419s +[2026-08-21 18:05:33,232] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6056fb65ba8b11e1671ac10b9b26c05d total=14754.2ms bytes=9616 finished=True finish=tool_calls stop=None out_tok=99 prompt_tok=7615 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:05:33,244] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=39933fc2a7732142be84b5021b6bc226 attempt=1 +[2026-08-21 18:05:33,257] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=39933fc2a7732142be84b5021b6bc226 status=400 post_dur=0.006s +[2026-08-21 18:05:33,257] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=39933fc2a7732142be84b5021b6bc226 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:05:33,264] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c432ceec50900a040871794ff14c8428 attempt=1 +[2026-08-21 18:05:33,725] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c432ceec50900a040871794ff14c8428 status=200 post_dur=0.460s +[2026-08-21 18:08:26,315] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c432ceec50900a040871794ff14c8428 total=173051.0ms bytes=506896 finished=True finish=stop stop=None out_tok=1736 prompt_tok=21151 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:08:26,333] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d1c10cd2b23d301652b17f5d21203516 attempt=1 +[2026-08-21 18:08:26,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d1c10cd2b23d301652b17f5d21203516 status=400 post_dur=0.008s +[2026-08-21 18:08:26,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d1c10cd2b23d301652b17f5d21203516 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:08:26,361] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4836e6b5c8ea8ec79be47dfcfee4d22d attempt=1 +[2026-08-21 18:08:26,367] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4836e6b5c8ea8ec79be47dfcfee4d22d status=400 post_dur=0.005s +[2026-08-21 18:08:26,367] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4836e6b5c8ea8ec79be47dfcfee4d22d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:08:26,373] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3f2ec22ac04405739c4822521d9783d attempt=1 +[2026-08-21 18:08:26,821] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3f2ec22ac04405739c4822521d9783d status=200 post_dur=0.446s +[2026-08-21 18:08:48,994] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3f2ec22ac04405739c4822521d9783d total=22620.4ms bytes=29217 finished=True finish=tool_calls stop=None out_tok=254 prompt_tok=7229 tps=11.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:08:48,998] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d76c7b7e31583f037d3fc46a28a67e2 attempt=1 +[2026-08-21 18:08:49,003] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d76c7b7e31583f037d3fc46a28a67e2 status=400 post_dur=0.004s +[2026-08-21 18:08:49,003] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3d76c7b7e31583f037d3fc46a28a67e2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:08:49,006] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e25283e725bb1320f8ffb894b685a76 attempt=1 +[2026-08-21 18:08:49,432] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e25283e725bb1320f8ffb894b685a76 status=200 post_dur=0.426s +[2026-08-21 18:09:14,213] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3e25283e725bb1320f8ffb894b685a76 total=25207.2ms bytes=10724 finished=True finish=tool_calls stop=None out_tok=144 prompt_tok=7969 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:09:14,217] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ab42192d9e63327faa6d9d6bd7232041 attempt=1 +[2026-08-21 18:09:14,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ab42192d9e63327faa6d9d6bd7232041 status=200 post_dur=0.427s +[2026-08-21 18:09:46,561] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ab42192d9e63327faa6d9d6bd7232041 total=32344.1ms bytes=26039 finished=True finish=tool_calls stop=None out_tok=266 prompt_tok=9998 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:09:46,567] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=248cac21ae65186381de6e8118230699 attempt=1 +[2026-08-21 18:09:46,571] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=248cac21ae65186381de6e8118230699 status=400 post_dur=0.004s +[2026-08-21 18:09:46,571] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=248cac21ae65186381de6e8118230699 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:09:46,577] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3e972aa3942f148deda44f4aa7cd39dc attempt=1 +[2026-08-21 18:09:46,579] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3e972aa3942f148deda44f4aa7cd39dc status=400 post_dur=0.002s +[2026-08-21 18:09:46,580] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3e972aa3942f148deda44f4aa7cd39dc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:09:46,582] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6cbde6783a8c4561e1b19c6a34c73fe attempt=1 +[2026-08-21 18:09:47,020] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6cbde6783a8c4561e1b19c6a34c73fe status=200 post_dur=0.437s +[2026-08-21 18:10:00,118] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6cbde6783a8c4561e1b19c6a34c73fe total=13535.3ms bytes=7284 finished=True finish=tool_calls stop=None out_tok=55 prompt_tok=8760 tps=4.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:10:00,120] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=10c0375f972ee141fef6d820741d7b67 attempt=1 +[2026-08-21 18:10:00,547] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=10c0375f972ee141fef6d820741d7b67 status=200 post_dur=0.427s +[2026-08-21 18:10:17,933] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=10c0375f972ee141fef6d820741d7b67 total=17812.4ms bytes=9151 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=9001 tps=4.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:10:17,934] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 attempt=1 +[2026-08-21 18:10:18,207] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 status=200 post_dur=0.273s +[2026-08-21 18:14:17,358] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dd4c8419fccac3b2f39251bdcbbaf4a9 total=239424.4ms bytes=821553 finished=True finish=stop stop=None out_tok=2829 prompt_tok=124 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:14:17,363] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=92d54e76e1e8c369e8d915b943330332 attempt=1 +[2026-08-21 18:14:17,836] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=92d54e76e1e8c369e8d915b943330332 status=200 post_dur=0.473s +[2026-08-21 18:14:55,099] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=92d54e76e1e8c369e8d915b943330332 total=37735.7ms bytes=41599 finished=True finish=tool_calls stop=None out_tok=356 prompt_tok=14403 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:14:55,105] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=faec012895ed44b46198171888c58f68 attempt=1 +[2026-08-21 18:14:55,622] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=faec012895ed44b46198171888c58f68 status=200 post_dur=0.517s +[2026-08-21 18:17:33,634] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=faec012895ed44b46198171888c58f68 total=158529.2ms bytes=10334 finished=True finish=tool_calls stop=None out_tok=926 prompt_tok=38041 tps=5.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:17:33,661] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4afe8af206a3e5fb423fcf90962c2a82 attempt=1 +[2026-08-21 18:17:33,678] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4afe8af206a3e5fb423fcf90962c2a82 status=400 post_dur=0.016s +[2026-08-21 18:17:33,678] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4afe8af206a3e5fb423fcf90962c2a82 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:17:33,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f43101c82dd79fd6bc3f8bb7001b13cb attempt=1 +[2026-08-21 18:17:34,134] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f43101c82dd79fd6bc3f8bb7001b13cb status=200 post_dur=0.446s +[2026-08-21 18:17:46,901] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f43101c82dd79fd6bc3f8bb7001b13cb total=13213.8ms bytes=28757 finished=True finish=tool_calls stop=None out_tok=142 prompt_tok=7197 tps=10.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:17:46,921] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=afd019506d9c67fb54a1f7cb6b1512bc attempt=1 +[2026-08-21 18:17:46,928] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=afd019506d9c67fb54a1f7cb6b1512bc status=400 post_dur=0.007s +[2026-08-21 18:17:46,928] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=afd019506d9c67fb54a1f7cb6b1512bc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:17:46,954] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f0fc3c03f50f31f76829a71a499d92e attempt=1 +[2026-08-21 18:17:46,966] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f0fc3c03f50f31f76829a71a499d92e status=400 post_dur=0.012s +[2026-08-21 18:17:46,966] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5f0fc3c03f50f31f76829a71a499d92e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:17:46,975] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8d68e8ae14e4e7f649a5ceaf38a1121f attempt=1 +[2026-08-21 18:17:47,419] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8d68e8ae14e4e7f649a5ceaf38a1121f status=200 post_dur=0.443s +[2026-08-21 18:18:22,904] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8d68e8ae14e4e7f649a5ceaf38a1121f total=35928.0ms bytes=38050 finished=True finish=tool_calls stop=None out_tok=363 prompt_tok=15606 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:18:22,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e88374f12de83b910d09e3f23434f8c8 attempt=1 +[2026-08-21 18:18:22,926] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e88374f12de83b910d09e3f23434f8c8 status=400 post_dur=0.007s +[2026-08-21 18:18:22,926] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e88374f12de83b910d09e3f23434f8c8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:18:22,943] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9c97a290f6e6a445f8a3eb02b49dc072 attempt=1 +[2026-08-21 18:18:22,949] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9c97a290f6e6a445f8a3eb02b49dc072 status=400 post_dur=0.006s +[2026-08-21 18:18:22,949] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=9c97a290f6e6a445f8a3eb02b49dc072 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:18:22,954] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fea48fb5a69f25359c593d21f564dc88 attempt=1 +[2026-08-21 18:18:23,376] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fea48fb5a69f25359c593d21f564dc88 status=200 post_dur=0.421s +[2026-08-21 18:18:53,638] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fea48fb5a69f25359c593d21f564dc88 total=30683.6ms bytes=31804 finished=True finish=tool_calls stop=None out_tok=302 prompt_tok=1406 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:18:53,642] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=093710e89a5c239545e99191909bf3a2 attempt=1 +[2026-08-21 18:18:53,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=093710e89a5c239545e99191909bf3a2 status=400 post_dur=0.003s +[2026-08-21 18:18:53,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=093710e89a5c239545e99191909bf3a2 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:18:53,647] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c26b7eb2a458da319e74275ea639f38c attempt=1 +[2026-08-21 18:18:53,930] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c26b7eb2a458da319e74275ea639f38c status=200 post_dur=0.283s +[2026-08-21 18:22:30,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c26b7eb2a458da319e74275ea639f38c total=216464.9ms bytes=745869 finished=True finish=stop stop=None out_tok=2565 prompt_tok=131 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:22:30,117] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d8de85a26ea050ffb37fa41c065476a5 attempt=1 +[2026-08-21 18:22:30,591] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d8de85a26ea050ffb37fa41c065476a5 status=200 post_dur=0.474s +[2026-08-21 18:23:16,619] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d8de85a26ea050ffb37fa41c065476a5 total=46501.9ms bytes=37678 finished=True finish=tool_calls stop=None out_tok=383 prompt_tok=16328 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:23:16,621] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7f06b1abf52730de2eb1f656654f536 attempt=1 +[2026-08-21 18:23:16,908] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7f06b1abf52730de2eb1f656654f536 status=200 post_dur=0.287s +[2026-08-21 18:27:30,592] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7f06b1abf52730de2eb1f656654f536 total=253970.4ms bytes=870309 finished=True finish=stop stop=None out_tok=2989 prompt_tok=972 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:27:30,604] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=312d8b0505f0cb7179134bc400d13a6e attempt=1 +[2026-08-21 18:27:30,614] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=312d8b0505f0cb7179134bc400d13a6e status=400 post_dur=0.007s +[2026-08-21 18:27:30,614] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=312d8b0505f0cb7179134bc400d13a6e status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:27:30,620] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45938b0cc831c0d3c80f1d1277b5f3ad attempt=1 +[2026-08-21 18:27:30,620] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 58% (528/881) has_cb=True +[2026-08-21 18:27:31,072] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45938b0cc831c0d3c80f1d1277b5f3ad status=200 post_dur=0.452s +[2026-08-21 18:27:58,585] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45938b0cc831c0d3c80f1d1277b5f3ad total=27964.8ms bytes=20049 finished=True finish=tool_calls stop=None out_tok=321 prompt_tok=7433 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:27:58,589] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=081fe3a74bd43801f12c645e2a3ae7b7 attempt=1 +[2026-08-21 18:27:58,598] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=081fe3a74bd43801f12c645e2a3ae7b7 status=400 post_dur=0.009s +[2026-08-21 18:27:58,598] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=081fe3a74bd43801f12c645e2a3ae7b7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:27:58,602] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b58038c4737a45f09fc0b1118bdf4141 attempt=1 +[2026-08-21 18:27:59,055] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b58038c4737a45f09fc0b1118bdf4141 status=200 post_dur=0.452s +[2026-08-21 18:28:33,857] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b58038c4737a45f09fc0b1118bdf4141 total=35254.4ms bytes=30067 finished=True finish=tool_calls stop=None out_tok=336 prompt_tok=16885 tps=9.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:28:33,862] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f38aca645e01b5450c80787a8e086615 attempt=1 +[2026-08-21 18:28:33,868] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f38aca645e01b5450c80787a8e086615 status=400 post_dur=0.006s +[2026-08-21 18:28:33,869] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=f38aca645e01b5450c80787a8e086615 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:28:33,885] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6723649fcfe66b870267a36cc1480224 attempt=1 +[2026-08-21 18:28:33,904] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6723649fcfe66b870267a36cc1480224 status=400 post_dur=0.020s +[2026-08-21 18:28:33,907] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=6723649fcfe66b870267a36cc1480224 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:28:33,930] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ed7b0f268e7473e470ecde2677ad894c attempt=1 +[2026-08-21 18:28:33,938] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ed7b0f268e7473e470ecde2677ad894c status=400 post_dur=0.008s +[2026-08-21 18:28:33,938] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ed7b0f268e7473e470ecde2677ad894c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:28:33,968] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 attempt=1 +[2026-08-21 18:28:33,976] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 status=400 post_dur=0.007s +[2026-08-21 18:28:33,976] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3ebbe4eff88e7ce8268fb099eb7c6a32 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:28:33,988] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 attempt=1 +[2026-08-21 18:28:34,449] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 status=200 post_dur=0.461s +[2026-08-21 18:29:10,292] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e84ee19eb8a6fa4ce077fa8a8ffa9682 total=36304.0ms bytes=8947 finished=True finish=tool_calls stop=None out_tok=105 prompt_tok=18613 tps=2.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:29:10,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bc17ec878bf859b2f969d6ca5ef0220a attempt=1 +[2026-08-21 18:29:10,763] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bc17ec878bf859b2f969d6ca5ef0220a status=200 post_dur=0.466s +[2026-08-21 18:31:42,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=bc17ec878bf859b2f969d6ca5ef0220a total=151924.1ms bytes=407432 finished=True finish=stop stop=None out_tok=1415 prompt_tok=23226 tps=9.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:31:42,237] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=22c90534cda8c06901fc6b40a0f1d343 attempt=1 +[2026-08-21 18:31:42,890] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=22c90534cda8c06901fc6b40a0f1d343 status=200 post_dur=0.650s +[2026-08-21 18:40:02,429] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=22c90534cda8c06901fc6b40a0f1d343 total=500191.2ms bytes=610834 finished=True finish=stop stop=None out_tok=2142 prompt_tok=99026 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:40:02,440] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b02b3eb4794572cbc8049f7978e4755c attempt=1 +[2026-08-21 18:40:02,889] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b02b3eb4794572cbc8049f7978e4755c status=200 post_dur=0.449s +[2026-08-21 18:40:26,997] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b02b3eb4794572cbc8049f7978e4755c total=24557.7ms bytes=24975 finished=True finish=tool_calls stop=None out_tok=199 prompt_tok=9191 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:40:27,002] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=924070facc5daa8a8ca16a926c529564 attempt=1 +[2026-08-21 18:40:27,483] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=924070facc5daa8a8ca16a926c529564 status=200 post_dur=0.481s +[2026-08-21 18:41:10,295] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=924070facc5daa8a8ca16a926c529564 total=43293.2ms bytes=24838 finished=True finish=tool_calls stop=None out_tok=136 prompt_tok=32804 tps=3.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:41:10,299] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a65336acb86bcebdfbd2b8c6bca1d061 attempt=1 +[2026-08-21 18:41:10,747] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a65336acb86bcebdfbd2b8c6bca1d061 status=200 post_dur=0.448s +[2026-08-21 18:41:33,051] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a65336acb86bcebdfbd2b8c6bca1d061 total=22751.9ms bytes=14090 finished=True finish=tool_calls stop=None out_tok=134 prompt_tok=9473 tps=5.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:41:33,054] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=edcf2f49985d064360ea6398600a8b12 attempt=1 +[2026-08-21 18:41:33,497] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=edcf2f49985d064360ea6398600a8b12 status=200 post_dur=0.443s +[2026-08-21 18:41:54,537] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=edcf2f49985d064360ea6398600a8b12 total=21483.0ms bytes=47736 finished=True finish=stop stop=None out_tok=167 prompt_tok=9815 tps=7.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:41:54,540] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3c2b7880184eb54fd9c7e0351370ed0c attempt=1 +[2026-08-21 18:41:54,963] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3c2b7880184eb54fd9c7e0351370ed0c status=200 post_dur=0.423s +[2026-08-21 18:42:08,217] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3c2b7880184eb54fd9c7e0351370ed0c total=13676.5ms bytes=9978 finished=True finish=tool_calls stop=None out_tok=121 prompt_tok=9635 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:42:08,219] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3158e44658122080759ed2c7aff28211 attempt=1 +[2026-08-21 18:42:08,638] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3158e44658122080759ed2c7aff28211 status=200 post_dur=0.419s +[2026-08-21 18:42:16,391] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3158e44658122080759ed2c7aff28211 total=8172.6ms bytes=7912 finished=True finish=tool_calls stop=None out_tok=59 prompt_tok=7294 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:42:16,401] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 attempt=1 +[2026-08-21 18:42:16,948] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 status=200 post_dur=0.547s +[2026-08-21 18:42:36,877] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b9a77f8b07e7af8eb0d28f0d55877f2 total=20475.5ms bytes=30759 finished=True finish=stop stop=None out_tok=109 prompt_tok=67262 tps=5.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:42:36,884] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7fbaa37cf7f1e96e4795b9d17055a38 attempt=1 +[2026-08-21 18:42:37,325] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7fbaa37cf7f1e96e4795b9d17055a38 status=200 post_dur=0.441s +[2026-08-21 18:43:04,541] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7fbaa37cf7f1e96e4795b9d17055a38 total=27656.9ms bytes=57637 finished=True finish=tool_calls stop=None out_tok=239 prompt_tok=10201 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:43:04,545] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2b12cf202b49219e657a8b2e81f9dfc1 attempt=1 +[2026-08-21 18:43:04,971] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2b12cf202b49219e657a8b2e81f9dfc1 status=200 post_dur=0.426s +[2026-08-21 18:43:18,069] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2b12cf202b49219e657a8b2e81f9dfc1 total=13523.3ms bytes=31649 finished=True finish=stop stop=None out_tok=107 prompt_tok=7776 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:43:18,071] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f5d25e952ef8d660cd7497a38cf0270c attempt=1 +[2026-08-21 18:43:18,503] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f5d25e952ef8d660cd7497a38cf0270c status=200 post_dur=0.431s +[2026-08-21 18:43:27,848] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f5d25e952ef8d660cd7497a38cf0270c total=9776.4ms bytes=10817 finished=True finish=stop stop=None out_tok=36 prompt_tok=7938 tps=3.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:43:27,852] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5e427beb44dc125b8bd82d43e4c32e97 attempt=1 +[2026-08-21 18:43:28,320] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5e427beb44dc125b8bd82d43e4c32e97 status=200 post_dur=0.467s +[2026-08-21 18:44:22,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5e427beb44dc125b8bd82d43e4c32e97 total=54702.0ms bytes=29683 finished=True finish=tool_calls stop=None out_tok=239 prompt_tok=35023 tps=4.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:44:22,570] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7250fe183fffe987aec6d4b89b9965a8 attempt=1 +[2026-08-21 18:44:22,582] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7250fe183fffe987aec6d4b89b9965a8 status=400 post_dur=0.011s +[2026-08-21 18:44:22,582] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7250fe183fffe987aec6d4b89b9965a8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:44:22,591] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=db53b560bbed67ab1e2158598060e88d attempt=1 +[2026-08-21 18:44:23,028] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=db53b560bbed67ab1e2158598060e88d status=200 post_dur=0.437s +[2026-08-21 18:44:42,060] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=db53b560bbed67ab1e2158598060e88d total=19469.1ms bytes=37410 finished=True finish=stop stop=None out_tok=130 prompt_tok=10737 tps=6.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:44:42,063] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=029e041b4912d1ebd63c7f0fa1351aa5 attempt=1 +[2026-08-21 18:44:42,482] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=029e041b4912d1ebd63c7f0fa1351aa5 status=200 post_dur=0.419s +[2026-08-21 18:44:59,147] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=029e041b4912d1ebd63c7f0fa1351aa5 total=17083.3ms bytes=12464 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=11113 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:44:59,152] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74b0d5d0879c7f51f492013e43205593 attempt=1 +[2026-08-21 18:44:59,710] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74b0d5d0879c7f51f492013e43205593 status=200 post_dur=0.558s +[2026-08-21 18:47:01,903] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74b0d5d0879c7f51f492013e43205593 total=122751.2ms bytes=23083 finished=True finish=tool_calls stop=None out_tok=215 prompt_tok=65135 tps=1.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:47:01,907] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e74ce8663959187db4fe091ec5f1c42f attempt=1 +[2026-08-21 18:47:02,206] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e74ce8663959187db4fe091ec5f1c42f status=200 post_dur=0.299s +[2026-08-21 18:51:41,922] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e74ce8663959187db4fe091ec5f1c42f total=280015.0ms bytes=951422 finished=True finish=stop stop=None out_tok=3273 prompt_tok=362 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:51:41,926] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d5d420ae0d25ad0437d519c768fd0e47 attempt=1 +[2026-08-21 18:51:42,230] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d5d420ae0d25ad0437d519c768fd0e47 status=200 post_dur=0.304s +[2026-08-21 18:55:31,969] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d5d420ae0d25ad0437d519c768fd0e47 total=230043.3ms bytes=787850 finished=True finish=stop stop=None out_tok=2705 prompt_tok=358 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:55:31,987] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=28abb489d809527e4bcc2c8752fa09b8 attempt=1 +[2026-08-21 18:55:31,995] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=28abb489d809527e4bcc2c8752fa09b8 status=400 post_dur=0.008s +[2026-08-21 18:55:31,995] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=28abb489d809527e4bcc2c8752fa09b8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 18:55:32,002] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e7f25dab6cfca855b9458f5c1669794e attempt=1 +[2026-08-21 18:55:32,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e7f25dab6cfca855b9458f5c1669794e status=200 post_dur=0.456s +[2026-08-21 18:56:07,082] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e7f25dab6cfca855b9458f5c1669794e total=35080.4ms bytes=32348 finished=True finish=tool_calls stop=None out_tok=402 prompt_tok=7229 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:56:07,098] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c04babac846d016602c36a4d167ecdd5 attempt=1 +[2026-08-21 18:56:07,110] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c04babac846d016602c36a4d167ecdd5 status=400 post_dur=0.012s +[2026-08-21 18:56:07,111] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c04babac846d016602c36a4d167ecdd5 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 18:56:07,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21ee0199b59266591733f3a31e6398c6 attempt=1 +[2026-08-21 18:56:07,568] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21ee0199b59266591733f3a31e6398c6 status=200 post_dur=0.448s +[2026-08-21 18:56:33,077] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=21ee0199b59266591733f3a31e6398c6 total=25956.7ms bytes=58634 finished=True finish=stop stop=None out_tok=201 prompt_tok=12285 tps=7.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:56:33,081] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=063bd0d56ee7c36da2edce892b9a9a01 attempt=1 +[2026-08-21 18:56:33,511] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=063bd0d56ee7c36da2edce892b9a9a01 status=200 post_dur=0.429s +[2026-08-21 18:56:47,312] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=063bd0d56ee7c36da2edce892b9a9a01 total=14231.1ms bytes=3013 finished=True finish=tool_calls stop=None out_tok=66 prompt_tok=12382 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:56:47,321] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80742d6579e019f5a55e92a87e6d3799 attempt=1 +[2026-08-21 18:56:47,894] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80742d6579e019f5a55e92a87e6d3799 status=200 post_dur=0.572s +[2026-08-21 18:59:54,509] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=80742d6579e019f5a55e92a87e6d3799 total=187187.5ms bytes=72892 finished=True finish=tool_calls stop=None out_tok=297 prompt_tok=86747 tps=1.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 18:59:54,517] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1751d2a2d72071e3e1e23a141dd1dcee attempt=1 +[2026-08-21 18:59:55,051] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1751d2a2d72071e3e1e23a141dd1dcee status=200 post_dur=0.534s +[2026-08-21 19:01:07,703] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1751d2a2d72071e3e1e23a141dd1dcee total=73186.0ms bytes=28311 finished=True finish=tool_calls stop=None out_tok=145 prompt_tok=43817 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:01:07,722] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b034d8815c633b7b3142f73b4d6665f attempt=1 +[2026-08-21 19:01:07,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b034d8815c633b7b3142f73b4d6665f status=400 post_dur=0.010s +[2026-08-21 19:01:07,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0b034d8815c633b7b3142f73b4d6665f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=At most 1 image(s) may be provided in one request. (retryable=False, attempt=1) +[2026-08-21 19:01:07,746] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2b4629c705e03c7baa507defa4060a62 attempt=1 +[2026-08-21 19:01:07,755] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2b4629c705e03c7baa507defa4060a62 status=400 post_dur=0.008s +[2026-08-21 19:01:07,755] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2b4629c705e03c7baa507defa4060a62 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:01:07,759] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a41c299f953102b14a53c164f6d20ce8 attempt=1 +[2026-08-21 19:01:08,217] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a41c299f953102b14a53c164f6d20ce8 status=200 post_dur=0.458s +[2026-08-21 19:01:23,327] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a41c299f953102b14a53c164f6d20ce8 total=15568.5ms bytes=16217 finished=True finish=tool_calls stop=None out_tok=93 prompt_tok=12893 tps=6.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:01:23,348] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=995096ab6f8f43b956cf2e4732ae7851 attempt=1 +[2026-08-21 19:01:23,359] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=995096ab6f8f43b956cf2e4732ae7851 status=400 post_dur=0.008s +[2026-08-21 19:01:23,360] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=995096ab6f8f43b956cf2e4732ae7851 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:01:23,381] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f attempt=1 +[2026-08-21 19:01:23,388] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f status=400 post_dur=0.007s +[2026-08-21 19:01:23,388] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=371ac8a4cd11d6f2f662cc7ae2e6eb9f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:01:23,399] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=45aeec5a434a049349b4acdd7f856e7e attempt=1 +[2026-08-21 19:01:23,829] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=45aeec5a434a049349b4acdd7f856e7e status=200 post_dur=0.430s +[2026-08-21 19:02:12,244] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=45aeec5a434a049349b4acdd7f856e7e total=48844.4ms bytes=142243 finished=True finish=stop stop=None out_tok=487 prompt_tok=13205 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:02:12,249] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb18e1593776a3836355a914f5aa0c53 attempt=1 +[2026-08-21 19:02:12,764] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb18e1593776a3836355a914f5aa0c53 status=200 post_dur=0.515s +[2026-08-21 19:03:27,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=fb18e1593776a3836355a914f5aa0c53 total=75426.5ms bytes=6154 finished=True finish=tool_calls stop=None out_tok=46 prompt_tok=52221 tps=0.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:03:27,679] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=898794d56a74b0e64a50b428304105a8 attempt=1 +[2026-08-21 19:03:28,124] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=898794d56a74b0e64a50b428304105a8 status=200 post_dur=0.445s +[2026-08-21 19:03:56,903] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=898794d56a74b0e64a50b428304105a8 total=29224.1ms bytes=19398 finished=True finish=tool_calls stop=None out_tok=181 prompt_tok=8916 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:03:56,917] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a16b10f455c3304c2fb9fd68d1512d69 attempt=1 +[2026-08-21 19:03:56,924] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a16b10f455c3304c2fb9fd68d1512d69 status=400 post_dur=0.008s +[2026-08-21 19:03:56,925] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=a16b10f455c3304c2fb9fd68d1512d69 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:03:56,933] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce attempt=1 +[2026-08-21 19:03:57,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce status=200 post_dur=0.526s +[2026-08-21 19:05:47,943] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5ae2cbf1de765ffa68b45efaf5f1d6ce total=111009.6ms bytes=46538 finished=True finish=tool_calls stop=None out_tok=285 prompt_tok=55905 tps=2.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:05:47,949] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0eb49188844d458d207604c17e5a3929 attempt=1 +[2026-08-21 19:05:47,950] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 62% (572/881) has_cb=True +[2026-08-21 19:05:48,481] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0eb49188844d458d207604c17e5a3929 status=200 post_dur=0.533s +[2026-08-21 19:07:08,439] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0eb49188844d458d207604c17e5a3929 total=80490.5ms bytes=7726 finished=True finish=tool_calls stop=None out_tok=80 prompt_tok=52353 tps=1.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:07:08,455] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 attempt=1 +[2026-08-21 19:07:08,463] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 status=400 post_dur=0.008s +[2026-08-21 19:07:08,463] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d0f7382406c6d8c54c0295ad6c3c0bf6 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:07:08,471] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=581edde74167a3c45573de2f1676b021 attempt=1 +[2026-08-21 19:07:09,004] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=581edde74167a3c45573de2f1676b021 status=200 post_dur=0.532s +[2026-08-21 19:08:29,266] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=581edde74167a3c45573de2f1676b021 total=80794.8ms bytes=9177 finished=True finish=tool_calls stop=None out_tok=80 prompt_tok=52497 tps=1.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:08:29,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=541237f01550b2cf13fe768369f702a5 attempt=1 +[2026-08-21 19:08:29,723] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=541237f01550b2cf13fe768369f702a5 status=200 post_dur=0.453s +[2026-08-21 19:08:59,820] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=541237f01550b2cf13fe768369f702a5 total=30550.1ms bytes=12134 finished=True finish=tool_calls stop=None out_tok=216 prompt_tok=9237 tps=7.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:08:59,822] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=dadf47f2924a71aeebdf4def0a247a24 attempt=1 +[2026-08-21 19:09:00,256] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=dadf47f2924a71aeebdf4def0a247a24 status=200 post_dur=0.433s +[2026-08-21 19:09:12,624] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=dadf47f2924a71aeebdf4def0a247a24 total=12801.8ms bytes=7600 finished=True finish=tool_calls stop=None out_tok=61 prompt_tok=9651 tps=4.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:09:12,626] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=232ea832a39433597fde4f14a674806e attempt=1 +[2026-08-21 19:09:13,051] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=232ea832a39433597fde4f14a674806e status=200 post_dur=0.425s +[2026-08-21 19:09:36,819] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=232ea832a39433597fde4f14a674806e total=24193.1ms bytes=25201 finished=True finish=tool_calls stop=None out_tok=176 prompt_tok=7197 tps=7.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:09:36,833] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd attempt=1 +[2026-08-21 19:09:36,841] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd status=400 post_dur=0.007s +[2026-08-21 19:09:36,841] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4b0d630a9eb4a7b9dd72410d9f09e2dd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:09:36,848] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 attempt=1 +[2026-08-21 19:09:37,271] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 status=200 post_dur=0.422s +[2026-08-21 19:09:54,062] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e9d3b3d5c9b2c4eab1b3e051ce0a346 total=17214.6ms bytes=19371 finished=True finish=stop stop=None out_tok=66 prompt_tok=7426 tps=3.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:09:54,065] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d04bfff957574fc3cadb25e318f640eb attempt=1 +[2026-08-21 19:09:54,499] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d04bfff957574fc3cadb25e318f640eb status=200 post_dur=0.434s +[2026-08-21 19:10:29,505] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d04bfff957574fc3cadb25e318f640eb total=35439.6ms bytes=32954 finished=True finish=tool_calls stop=None out_tok=296 prompt_tok=12431 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:10:29,508] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e68ab759ebb81c0cdc4016ea50387e52 attempt=1 +[2026-08-21 19:10:29,950] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e68ab759ebb81c0cdc4016ea50387e52 status=200 post_dur=0.441s +[2026-08-21 19:10:36,530] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e68ab759ebb81c0cdc4016ea50387e52 total=7022.1ms bytes=11682 finished=True finish=stop stop=None out_tok=39 prompt_tok=7530 tps=5.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:10:36,534] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4cea7c08234860fb460738dc8912a84b attempt=1 +[2026-08-21 19:10:36,965] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4cea7c08234860fb460738dc8912a84b status=200 post_dur=0.431s +[2026-08-21 19:11:03,997] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4cea7c08234860fb460738dc8912a84b total=27463.2ms bytes=70467 finished=True finish=stop stop=None out_tok=240 prompt_tok=15698 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:11:04,001] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 attempt=1 +[2026-08-21 19:11:04,435] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 status=200 post_dur=0.434s +[2026-08-21 19:12:03,818] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9bfb17e9038c9db35d1a6e81fbdf7df7 total=59817.0ms bytes=141566 finished=True finish=tool_calls stop=None out_tok=641 prompt_tok=13212 tps=10.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:12:03,824] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 attempt=1 +[2026-08-21 19:12:03,831] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 status=400 post_dur=0.007s +[2026-08-21 19:12:03,832] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ca91c5e1164a958e0cb24ecd4b5bfbe8 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:12:03,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=682bb781d4ef1bc29015ffe458c427ad attempt=1 +[2026-08-21 19:12:04,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=682bb781d4ef1bc29015ffe458c427ad status=200 post_dur=0.451s +[2026-08-21 19:12:12,664] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=682bb781d4ef1bc29015ffe458c427ad total=8829.2ms bytes=9066 finished=True finish=stop stop=None out_tok=30 prompt_tok=7843 tps=3.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:12:12,665] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b6f364eaa495b697314b68be83d4a4bb attempt=1 +[2026-08-21 19:12:12,937] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b6f364eaa495b697314b68be83d4a4bb status=200 post_dur=0.272s +[2026-08-21 19:18:17,397] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b6f364eaa495b697314b68be83d4a4bb total=364731.7ms bytes=1250621 finished=True finish=stop stop=None out_tok=4293 prompt_tok=548 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:18:17,417] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d6a4a4fac1b9838447064f7b6daa52dc attempt=1 +[2026-08-21 19:18:17,437] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d6a4a4fac1b9838447064f7b6daa52dc status=400 post_dur=0.009s +[2026-08-21 19:18:17,437] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d6a4a4fac1b9838447064f7b6daa52dc status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:18:17,449] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=87a3cea97cf01e35c2ec790689c0c801 attempt=1 +[2026-08-21 19:18:17,458] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=87a3cea97cf01e35c2ec790689c0c801 status=400 post_dur=0.008s +[2026-08-21 19:18:17,458] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=87a3cea97cf01e35c2ec790689c0c801 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:18:17,463] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c55ac9fc0bf64311641d91826a3a777a attempt=1 +[2026-08-21 19:18:17,921] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c55ac9fc0bf64311641d91826a3a777a status=200 post_dur=0.459s +[2026-08-21 19:18:38,862] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c55ac9fc0bf64311641d91826a3a777a total=21399.1ms bytes=26419 finished=True finish=tool_calls stop=None out_tok=149 prompt_tok=9201 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:18:38,880] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2d0551f547503ca534746ae888c882c8 attempt=1 +[2026-08-21 19:18:39,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2d0551f547503ca534746ae888c882c8 status=200 post_dur=0.579s +[2026-08-21 19:20:53,072] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2d0551f547503ca534746ae888c882c8 total=134192.6ms bytes=22005 finished=True finish=stop stop=None out_tok=75 prompt_tok=76677 tps=0.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:20:53,089] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=10c3f6626f09481a6a8bed57bda0c6a3 attempt=1 +[2026-08-21 19:20:53,101] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=10c3f6626f09481a6a8bed57bda0c6a3 status=400 post_dur=0.012s +[2026-08-21 19:20:53,101] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=10c3f6626f09481a6a8bed57bda0c6a3 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:20:53,105] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7f8fb51b56ed2258e2acc9e519541db2 attempt=1 +[2026-08-21 19:20:53,406] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7f8fb51b56ed2258e2acc9e519541db2 status=200 post_dur=0.301s +[2026-08-21 19:25:31,662] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7f8fb51b56ed2258e2acc9e519541db2 total=278557.7ms bytes=947589 finished=True finish=stop stop=None out_tok=3256 prompt_tok=593 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:25:31,669] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ea57d6b26dd9827842bc67ac8939ba8e attempt=1 +[2026-08-21 19:25:32,169] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ea57d6b26dd9827842bc67ac8939ba8e status=200 post_dur=0.500s +[2026-08-21 19:26:45,514] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ea57d6b26dd9827842bc67ac8939ba8e total=73845.9ms bytes=54998 finished=True finish=tool_calls stop=None out_tok=512 prompt_tok=25460 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:26:45,534] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5744fc796d14ca1c2f1a3a4fc368ff03 attempt=1 +[2026-08-21 19:26:45,543] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5744fc796d14ca1c2f1a3a4fc368ff03 status=400 post_dur=0.009s +[2026-08-21 19:26:45,544] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=5744fc796d14ca1c2f1a3a4fc368ff03 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:26:45,553] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=74801d2b6e1344413d70868d48e27945 attempt=1 +[2026-08-21 19:26:46,079] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=74801d2b6e1344413d70868d48e27945 status=200 post_dur=0.526s +[2026-08-21 19:28:09,919] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=74801d2b6e1344413d70868d48e27945 total=84365.9ms bytes=20518 finished=True finish=tool_calls stop=None out_tok=245 prompt_tok=43310 tps=2.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:28:09,923] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4ea211f22f784a62a9112c940048e76 attempt=1 +[2026-08-21 19:28:10,379] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4ea211f22f784a62a9112c940048e76 status=200 post_dur=0.456s +[2026-08-21 19:28:33,384] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4ea211f22f784a62a9112c940048e76 total=23460.7ms bytes=11735 finished=True finish=tool_calls stop=None out_tok=133 prompt_tok=10801 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:28:33,386] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1c4b6526fdbbb273358af3f3ee24bc50 attempt=1 +[2026-08-21 19:28:33,819] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1c4b6526fdbbb273358af3f3ee24bc50 status=200 post_dur=0.432s +[2026-08-21 19:28:51,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1c4b6526fdbbb273358af3f3ee24bc50 total=18288.6ms bytes=10169 finished=True finish=tool_calls stop=None out_tok=153 prompt_tok=10482 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:28:51,679] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b58587e2f2156097cc30c1fd9d06884 attempt=1 +[2026-08-21 19:28:52,197] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b58587e2f2156097cc30c1fd9d06884 status=200 post_dur=0.517s +[2026-08-21 19:30:40,057] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b58587e2f2156097cc30c1fd9d06884 total=108377.2ms bytes=17186 finished=True finish=tool_calls stop=None out_tok=213 prompt_tok=58375 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:30:40,076] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e0e4ea9b2a019481d574c690a973542 attempt=1 +[2026-08-21 19:30:40,087] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e0e4ea9b2a019481d574c690a973542 status=400 post_dur=0.011s +[2026-08-21 19:30:40,088] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=8e0e4ea9b2a019481d574c690a973542 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:30:40,107] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fb6a3235bd8dde22d3dea0b3551a4003 attempt=1 +[2026-08-21 19:30:40,116] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fb6a3235bd8dde22d3dea0b3551a4003 status=400 post_dur=0.007s +[2026-08-21 19:30:40,116] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=fb6a3235bd8dde22d3dea0b3551a4003 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:30:40,135] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d88101aaa3c2f1d392f4680a468b9268 attempt=1 +[2026-08-21 19:30:40,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d88101aaa3c2f1d392f4680a468b9268 status=400 post_dur=0.006s +[2026-08-21 19:30:40,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d88101aaa3c2f1d392f4680a468b9268 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:30:40,150] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1c3d9ac233797d670c5d5201d895c14f attempt=1 +[2026-08-21 19:30:40,452] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1c3d9ac233797d670c5d5201d895c14f status=200 post_dur=0.301s +[2026-08-21 19:36:39,468] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1c3d9ac233797d670c5d5201d895c14f total=359317.7ms bytes=1237041 finished=True finish=stop stop=None out_tok=4247 prompt_tok=542 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:36:39,474] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=06102f503fba4228f1a0711c6f168417 attempt=1 +[2026-08-21 19:36:39,940] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=06102f503fba4228f1a0711c6f168417 status=200 post_dur=0.465s +[2026-08-21 19:37:01,048] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=06102f503fba4228f1a0711c6f168417 total=21574.3ms bytes=14868 finished=True finish=tool_calls stop=None out_tok=121 prompt_tok=13038 tps=5.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:37:01,057] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=128e3606dca3dd4d012e6069bb8272df attempt=1 +[2026-08-21 19:37:01,064] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=128e3606dca3dd4d012e6069bb8272df status=400 post_dur=0.007s +[2026-08-21 19:37:01,064] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=128e3606dca3dd4d012e6069bb8272df status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:37:01,068] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a78bfd66ce177b70452a35a38a5e5b75 attempt=1 +[2026-08-21 19:37:01,362] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a78bfd66ce177b70452a35a38a5e5b75 status=200 post_dur=0.293s +[2026-08-21 19:41:37,669] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a78bfd66ce177b70452a35a38a5e5b75 total=276601.3ms bytes=951675 finished=True finish=stop stop=None out_tok=3270 prompt_tok=569 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:41:37,676] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4112c97a2451f207899535c7eee5243b attempt=1 +[2026-08-21 19:41:38,145] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4112c97a2451f207899535c7eee5243b status=200 post_dur=0.469s +[2026-08-21 19:42:03,418] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4112c97a2451f207899535c7eee5243b total=25742.1ms bytes=54141 finished=True finish=stop stop=None out_tok=187 prompt_tok=13403 tps=7.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:42:03,421] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe attempt=1 +[2026-08-21 19:42:03,708] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe status=200 post_dur=0.287s +[2026-08-21 19:46:56,831] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=26b5e4e4f2ef71c9df0ecb9bf32c96fe total=293409.6ms bytes=999743 finished=True finish=stop stop=None out_tok=3435 prompt_tok=537 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:46:56,842] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6e0af977fdbf7c3b9f22a4e951d542a2 attempt=1 +[2026-08-21 19:46:57,299] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6e0af977fdbf7c3b9f22a4e951d542a2 status=200 post_dur=0.456s +[2026-08-21 19:47:09,159] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6e0af977fdbf7c3b9f22a4e951d542a2 total=12316.6ms bytes=24356 finished=True finish=tool_calls stop=None out_tok=131 prompt_tok=7197 tps=10.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:47:09,162] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=104241ef58ecfe337063e40a26b59742 attempt=1 +[2026-08-21 19:47:09,594] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=104241ef58ecfe337063e40a26b59742 status=200 post_dur=0.431s +[2026-08-21 19:47:22,484] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=104241ef58ecfe337063e40a26b59742 total=13321.3ms bytes=19338 finished=True finish=stop stop=None out_tok=65 prompt_tok=13641 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:47:22,500] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=03fa37d92159c07903a344809bb94c96 attempt=1 +[2026-08-21 19:47:22,508] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=03fa37d92159c07903a344809bb94c96 status=400 post_dur=0.008s +[2026-08-21 19:47:22,508] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=03fa37d92159c07903a344809bb94c96 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:47:22,515] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3419c407e5d404b8c562134084916a53 attempt=1 +[2026-08-21 19:47:22,790] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3419c407e5d404b8c562134084916a53 status=200 post_dur=0.275s +[2026-08-21 19:52:24,935] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3419c407e5d404b8c562134084916a53 total=302420.9ms bytes=1043936 finished=True finish=stop stop=None out_tok=3587 prompt_tok=537 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:52:24,942] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=de2869d6bbf3ad41415bcae19a593267 attempt=1 +[2026-08-21 19:52:25,399] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=de2869d6bbf3ad41415bcae19a593267 status=200 post_dur=0.457s +[2026-08-21 19:52:39,543] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=de2869d6bbf3ad41415bcae19a593267 total=14601.5ms bytes=8727 finished=True finish=stop stop=None out_tok=29 prompt_tok=7666 tps=2.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:52:39,546] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f2290a1ebe57afe84b95d9e141b2b13d attempt=1 +[2026-08-21 19:52:39,981] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f2290a1ebe57afe84b95d9e141b2b13d status=200 post_dur=0.435s +[2026-08-21 19:52:56,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f2290a1ebe57afe84b95d9e141b2b13d total=16723.4ms bytes=13558 finished=True finish=tool_calls stop=None out_tok=151 prompt_tok=13859 tps=9.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 19:52:56,284] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=faa096786ea7a27aea086ff1e5f0709f attempt=1 +[2026-08-21 19:52:56,293] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=faa096786ea7a27aea086ff1e5f0709f status=400 post_dur=0.008s +[2026-08-21 19:52:56,294] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=faa096786ea7a27aea086ff1e5f0709f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:52:56,313] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=84995c7233752a30efd17762e7c12e6f attempt=1 +[2026-08-21 19:52:56,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=84995c7233752a30efd17762e7c12e6f status=400 post_dur=0.006s +[2026-08-21 19:52:56,319] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=84995c7233752a30efd17762e7c12e6f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 19:52:56,328] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=37a9e3e4762efd2f5c0c47f2353ee105 attempt=1 +[2026-08-21 19:52:56,328] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 66% (616/881) has_cb=True +[2026-08-21 19:52:56,883] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=37a9e3e4762efd2f5c0c47f2353ee105 status=200 post_dur=0.555s +[2026-08-21 20:12:36,480] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=37a9e3e4762efd2f5c0c47f2353ee105 total=1180151.5ms bytes=6509 finished=True finish=tool_calls stop=None out_tok=8192 prompt_tok=70311 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:12:36,487] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=859b88bc3806f09b6a18faf10805b7e4 attempt=1 +[2026-08-21 20:12:36,960] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=859b88bc3806f09b6a18faf10805b7e4 status=200 post_dur=0.473s +[2026-08-21 20:13:06,891] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=859b88bc3806f09b6a18faf10805b7e4 total=30403.5ms bytes=9199 finished=True finish=tool_calls stop=None out_tok=81 prompt_tok=18593 tps=2.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:13:06,893] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 attempt=1 +[2026-08-21 20:13:07,186] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 status=200 post_dur=0.293s +[2026-08-21 20:17:46,747] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9bb7121bcf6e5a6a8b8efd59a77e2812 total=279854.0ms bytes=963228 finished=True finish=stop stop=None out_tok=3310 prompt_tok=540 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:17:46,765] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bdeb4435351b882c8ae811933fbecadf attempt=1 +[2026-08-21 20:17:46,776] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bdeb4435351b882c8ae811933fbecadf status=400 post_dur=0.011s +[2026-08-21 20:17:46,777] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bdeb4435351b882c8ae811933fbecadf status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:17:46,784] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ef2055b1f042d938040df3eab9df8100 attempt=1 +[2026-08-21 20:17:47,080] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ef2055b1f042d938040df3eab9df8100 status=200 post_dur=0.296s +[2026-08-21 20:22:36,284] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ef2055b1f042d938040df3eab9df8100 total=289500.6ms bytes=995630 finished=True finish=stop stop=None out_tok=3419 prompt_tok=540 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:22:36,289] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5db79e2b12ac689acdc11655a124ff5a attempt=1 +[2026-08-21 20:22:36,743] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5db79e2b12ac689acdc11655a124ff5a status=200 post_dur=0.454s +[2026-08-21 20:23:11,554] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5db79e2b12ac689acdc11655a124ff5a total=35264.7ms bytes=29419 finished=True finish=tool_calls stop=None out_tok=383 prompt_tok=7229 tps=10.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:23:11,569] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cf45bd083c178f22f6465ede0bbe788f attempt=1 +[2026-08-21 20:23:11,576] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cf45bd083c178f22f6465ede0bbe788f status=400 post_dur=0.007s +[2026-08-21 20:23:11,577] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=cf45bd083c178f22f6465ede0bbe788f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:23:11,587] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9d97d66cceb27563585016c986a3af1b attempt=1 +[2026-08-21 20:23:12,156] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9d97d66cceb27563585016c986a3af1b status=200 post_dur=0.567s +[2026-08-21 20:23:56,707] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9d97d66cceb27563585016c986a3af1b total=45119.4ms bytes=11452 finished=True finish=tool_calls stop=None out_tok=137 prompt_tok=74146 tps=3.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:23:56,714] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=81c7bee1d0f4161bccadb5541ca5c1a6 attempt=1 +[2026-08-21 20:23:57,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=81c7bee1d0f4161bccadb5541ca5c1a6 status=200 post_dur=0.449s +[2026-08-21 20:24:28,081] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=81c7bee1d0f4161bccadb5541ca5c1a6 total=31367.1ms bytes=14210 finished=True finish=tool_calls stop=None out_tok=225 prompt_tok=7772 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:24:28,084] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=816d7b5428ed1be410b7287bc61ad073 attempt=1 +[2026-08-21 20:24:28,512] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=816d7b5428ed1be410b7287bc61ad073 status=200 post_dur=0.428s +[2026-08-21 20:24:41,446] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=816d7b5428ed1be410b7287bc61ad073 total=13362.6ms bytes=10262 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=7898 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:24:41,449] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9ccd7782d74bafaada51d2dfd0a820b6 attempt=1 +[2026-08-21 20:24:41,880] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9ccd7782d74bafaada51d2dfd0a820b6 status=200 post_dur=0.431s +[2026-08-21 20:25:12,407] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9ccd7782d74bafaada51d2dfd0a820b6 total=30958.1ms bytes=17464 finished=True finish=tool_calls stop=None out_tok=270 prompt_tok=9390 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:25:12,410] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f88ae55b820822ca0d6d284ed99c68a attempt=1 +[2026-08-21 20:25:12,849] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f88ae55b820822ca0d6d284ed99c68a status=200 post_dur=0.439s +[2026-08-21 20:25:46,010] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3f88ae55b820822ca0d6d284ed99c68a total=33600.4ms bytes=16984 finished=True finish=tool_calls stop=None out_tok=234 prompt_tok=8844 tps=7.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:25:46,013] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 attempt=1 +[2026-08-21 20:25:46,460] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 status=200 post_dur=0.447s +[2026-08-21 20:26:12,885] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d43cbd1f43d89142cd77e0c7dcc97ed8 total=26872.4ms bytes=77086 finished=True finish=stop stop=None out_tok=266 prompt_tok=9055 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:26:12,888] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ae7129dc7825ca4b4922f47ef4b6b817 attempt=1 +[2026-08-21 20:26:13,314] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ae7129dc7825ca4b4922f47ef4b6b817 status=200 post_dur=0.426s +[2026-08-21 20:26:53,265] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ae7129dc7825ca4b4922f47ef4b6b817 total=40376.7ms bytes=26884 finished=True finish=tool_calls stop=None out_tok=380 prompt_tok=8828 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:26:53,268] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0037cbe5fb38bb35563eb68ffd63f2dc attempt=1 +[2026-08-21 20:26:53,712] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0037cbe5fb38bb35563eb68ffd63f2dc status=200 post_dur=0.444s +[2026-08-21 20:27:10,210] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0037cbe5fb38bb35563eb68ffd63f2dc total=16942.1ms bytes=2932 finished=True finish=tool_calls stop=None out_tok=45 prompt_tok=10064 tps=2.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:27:10,213] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=748ccb810c5ee26afe5271127bcd71be attempt=1 +[2026-08-21 20:27:10,637] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=748ccb810c5ee26afe5271127bcd71be status=200 post_dur=0.424s +[2026-08-21 20:27:35,822] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=748ccb810c5ee26afe5271127bcd71be total=25609.6ms bytes=13775 finished=True finish=tool_calls stop=None out_tok=251 prompt_tok=9859 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:27:35,829] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4ef25e1646a61801f96022b22237e75d attempt=1 +[2026-08-21 20:27:35,834] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4ef25e1646a61801f96022b22237e75d status=400 post_dur=0.004s +[2026-08-21 20:27:35,834] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=4ef25e1646a61801f96022b22237e75d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:27:35,838] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3176bc8dfe399f543afd31ce14aff7d0 attempt=1 +[2026-08-21 20:27:36,265] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3176bc8dfe399f543afd31ce14aff7d0 status=200 post_dur=0.427s +[2026-08-21 20:27:59,783] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3176bc8dfe399f543afd31ce14aff7d0 total=23944.3ms bytes=13515 finished=True finish=tool_calls stop=None out_tok=202 prompt_tok=13364 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:27:59,789] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=175ca9cdfba5a980a3e77b3bb270f3e7 attempt=1 +[2026-08-21 20:27:59,794] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=175ca9cdfba5a980a3e77b3bb270f3e7 status=400 post_dur=0.005s +[2026-08-21 20:27:59,794] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=175ca9cdfba5a980a3e77b3bb270f3e7 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:27:59,799] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7410174a4a76efde6b06949906f79bc6 attempt=1 +[2026-08-21 20:28:00,242] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7410174a4a76efde6b06949906f79bc6 status=200 post_dur=0.443s +[2026-08-21 20:28:53,507] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7410174a4a76efde6b06949906f79bc6 total=53708.5ms bytes=116925 finished=True finish=tool_calls stop=None out_tok=568 prompt_tok=11594 tps=10.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:28:53,515] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0ed5d84769f7c4d9b682d80ea4f85b80 attempt=1 +[2026-08-21 20:28:53,521] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0ed5d84769f7c4d9b682d80ea4f85b80 status=400 post_dur=0.005s +[2026-08-21 20:28:53,521] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=0ed5d84769f7c4d9b682d80ea4f85b80 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:28:53,532] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=820cbdd56093ff0b360fbc48bc80b984 attempt=1 +[2026-08-21 20:28:53,977] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=820cbdd56093ff0b360fbc48bc80b984 status=200 post_dur=0.445s +[2026-08-21 20:29:28,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=820cbdd56093ff0b360fbc48bc80b984 total=35120.4ms bytes=102964 finished=True finish=stop stop=None out_tok=352 prompt_tok=12381 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:29:28,661] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9df64eb29d4f0a19dac69304dfc74345 attempt=1 +[2026-08-21 20:29:29,182] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9df64eb29d4f0a19dac69304dfc74345 status=200 post_dur=0.520s +[2026-08-21 20:30:42,293] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9df64eb29d4f0a19dac69304dfc74345 total=73631.6ms bytes=18105 finished=True finish=stop stop=None out_tok=61 prompt_tok=46520 tps=0.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:30:42,307] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=263af4cb7bf009461ee438fc2761358c attempt=1 +[2026-08-21 20:30:42,315] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=263af4cb7bf009461ee438fc2761358c status=400 post_dur=0.008s +[2026-08-21 20:30:42,315] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=263af4cb7bf009461ee438fc2761358c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:30:42,322] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5edeed4a34fa4c38655a08215a3b343b attempt=1 +[2026-08-21 20:30:42,768] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5edeed4a34fa4c38655a08215a3b343b status=200 post_dur=0.446s +[2026-08-21 20:30:52,383] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5edeed4a34fa4c38655a08215a3b343b total=10060.6ms bytes=10291 finished=True finish=tool_calls stop=None out_tok=79 prompt_tok=7307 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:30:52,397] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=69fba56c09d963a5c1c96bd939c2d2bb attempt=1 +[2026-08-21 20:30:52,407] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=69fba56c09d963a5c1c96bd939c2d2bb status=400 post_dur=0.007s +[2026-08-21 20:30:52,407] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=69fba56c09d963a5c1c96bd939c2d2bb status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:30:52,421] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=af68150f83e67dbc37f04cccc839b789 attempt=1 +[2026-08-21 20:30:52,925] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=af68150f83e67dbc37f04cccc839b789 status=200 post_dur=0.503s +[2026-08-21 20:31:42,018] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=af68150f83e67dbc37f04cccc839b789 total=49597.5ms bytes=35012 finished=True finish=stop stop=None out_tok=119 prompt_tok=46672 tps=2.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:31:42,023] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=788904c22957b5bf226fcde26ad387d0 attempt=1 +[2026-08-21 20:31:42,325] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=788904c22957b5bf226fcde26ad387d0 status=200 post_dur=0.302s +[2026-08-21 20:37:16,270] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=788904c22957b5bf226fcde26ad387d0 total=334246.9ms bytes=1149086 finished=True finish=stop stop=None out_tok=3955 prompt_tok=540 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:37:16,282] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db attempt=1 +[2026-08-21 20:37:16,818] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db status=200 post_dur=0.536s +[2026-08-21 20:38:42,521] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fcbe5b3dedfa6567c9f9a7ef2e636db total=86239.7ms bytes=48492 finished=True finish=stop stop=None out_tok=165 prompt_tok=46672 tps=1.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:38:42,528] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4bff32787c3a952325ebdb8621331ac9 attempt=1 +[2026-08-21 20:38:42,979] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4bff32787c3a952325ebdb8621331ac9 status=200 post_dur=0.452s +[2026-08-21 20:38:50,338] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4bff32787c3a952325ebdb8621331ac9 total=7810.7ms bytes=11682 finished=True finish=stop stop=None out_tok=39 prompt_tok=7755 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:38:50,352] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3f5f79bc1ceaf96da2cf7d93a45d905d attempt=1 +[2026-08-21 20:38:50,364] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3f5f79bc1ceaf96da2cf7d93a45d905d status=400 post_dur=0.010s +[2026-08-21 20:38:50,364] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3f5f79bc1ceaf96da2cf7d93a45d905d status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:38:50,386] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=440568bcab80772c65a1a19b6c4a2e4b attempt=1 +[2026-08-21 20:38:50,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=440568bcab80772c65a1a19b6c4a2e4b status=400 post_dur=0.006s +[2026-08-21 20:38:50,392] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=440568bcab80772c65a1a19b6c4a2e4b status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:38:50,406] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9e2bb5eb73878fe0447ffa145451449c attempt=1 +[2026-08-21 20:38:50,899] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9e2bb5eb73878fe0447ffa145451449c status=200 post_dur=0.492s +[2026-08-21 20:39:09,102] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9e2bb5eb73878fe0447ffa145451449c total=18695.7ms bytes=29145 finished=True finish=stop stop=None out_tok=98 prompt_tok=47569 tps=5.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:39:09,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ccba346fe9fd8c8963c2eb8cc9192609 attempt=1 +[2026-08-21 20:39:09,117] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ccba346fe9fd8c8963c2eb8cc9192609 status=400 post_dur=0.005s +[2026-08-21 20:39:09,117] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ccba346fe9fd8c8963c2eb8cc9192609 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:39:09,127] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=49fdd29c1e750cc0095af7a7d202779b attempt=1 +[2026-08-21 20:39:09,131] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=49fdd29c1e750cc0095af7a7d202779b status=400 post_dur=0.004s +[2026-08-21 20:39:09,131] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=49fdd29c1e750cc0095af7a7d202779b status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:39:09,136] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b5934204c5ba11ac7bd0cde16fc8302 attempt=1 +[2026-08-21 20:39:09,583] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b5934204c5ba11ac7bd0cde16fc8302 status=200 post_dur=0.447s +[2026-08-21 20:40:01,189] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1b5934204c5ba11ac7bd0cde16fc8302 total=52052.6ms bytes=139138 finished=True finish=stop stop=None out_tok=471 prompt_tok=13359 tps=9.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:40:01,193] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4f5fada8238654bc3501c846608f7957 attempt=1 +[2026-08-21 20:40:01,644] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4f5fada8238654bc3501c846608f7957 status=200 post_dur=0.451s +[2026-08-21 20:40:39,226] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4f5fada8238654bc3501c846608f7957 total=38032.9ms bytes=15870 finished=True finish=tool_calls stop=None out_tok=261 prompt_tok=13902 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:40:39,229] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=41b2156ad49ca72ea2116ebae8befd04 attempt=1 +[2026-08-21 20:40:39,677] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=41b2156ad49ca72ea2116ebae8befd04 status=200 post_dur=0.448s +[2026-08-21 20:41:15,472] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=41b2156ad49ca72ea2116ebae8befd04 total=36242.7ms bytes=24043 finished=True finish=tool_calls stop=None out_tok=261 prompt_tok=13273 tps=7.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:41:15,473] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7fad751a2f24c9becb63bdcd8b4602b0 attempt=1 +[2026-08-21 20:41:15,766] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7fad751a2f24c9becb63bdcd8b4602b0 status=200 post_dur=0.293s +[2026-08-21 20:47:21,992] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7fad751a2f24c9becb63bdcd8b4602b0 total=366519.0ms bytes=1268944 finished=True finish=stop stop=None out_tok=4381 prompt_tok=540 tps=12.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:47:22,006] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=52d47c0440fe8244cd59e99870eaff80 attempt=1 +[2026-08-21 20:47:22,015] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=52d47c0440fe8244cd59e99870eaff80 status=400 post_dur=0.007s +[2026-08-21 20:47:22,015] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=52d47c0440fe8244cd59e99870eaff80 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:47:22,022] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=35a9a8671ea3aac267092deeb15b1ff9 attempt=1 +[2026-08-21 20:47:22,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=35a9a8671ea3aac267092deeb15b1ff9 status=200 post_dur=0.455s +[2026-08-21 20:47:48,608] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=35a9a8671ea3aac267092deeb15b1ff9 total=26586.0ms bytes=13115 finished=True finish=tool_calls stop=None out_tok=161 prompt_tok=8031 tps=6.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:47:48,609] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6efce744b4d2681b3918d6dfce942922 attempt=1 +[2026-08-21 20:47:48,887] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6efce744b4d2681b3918d6dfce942922 status=200 post_dur=0.278s +[2026-08-21 20:52:02,110] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6efce744b4d2681b3918d6dfce942922 total=253500.6ms bytes=875099 finished=True finish=stop stop=None out_tok=2986 prompt_tok=1559 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:52:02,115] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5efed514ae2a145d3506fb048b6241de attempt=1 +[2026-08-21 20:52:02,576] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5efed514ae2a145d3506fb048b6241de status=200 post_dur=0.460s +[2026-08-21 20:52:47,472] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5efed514ae2a145d3506fb048b6241de total=45357.1ms bytes=47230 finished=True finish=tool_calls stop=None out_tok=427 prompt_tok=9330 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:52:47,478] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9dc63684b6d5f28c198da1c92ef36976 attempt=1 +[2026-08-21 20:52:47,966] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9dc63684b6d5f28c198da1c92ef36976 status=200 post_dur=0.488s +[2026-08-21 20:54:00,827] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9dc63684b6d5f28c198da1c92ef36976 total=73349.0ms bytes=124259 finished=True finish=stop stop=None out_tok=428 prompt_tok=27546 tps=5.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:54:00,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3a845e29c3f5d2fd4d7586880d69c2c3 attempt=1 +[2026-08-21 20:54:00,836] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 70% (660/881) has_cb=True +[2026-08-21 20:54:01,291] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3a845e29c3f5d2fd4d7586880d69c2c3 status=200 post_dur=0.455s +[2026-08-21 20:54:22,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3a845e29c3f5d2fd4d7586880d69c2c3 total=21472.5ms bytes=9684 finished=True finish=tool_calls stop=None out_tok=119 prompt_tok=9612 tps=5.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:54:22,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0b1a08a1ae782b81c2138c65515224b2 attempt=1 +[2026-08-21 20:54:22,734] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0b1a08a1ae782b81c2138c65515224b2 status=200 post_dur=0.423s +[2026-08-21 20:54:45,154] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0b1a08a1ae782b81c2138c65515224b2 total=22844.1ms bytes=9955 finished=True finish=tool_calls stop=None out_tok=123 prompt_tok=7787 tps=5.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:54:45,170] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8d805fc340e553746465349bcc736c4a attempt=1 +[2026-08-21 20:54:45,178] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8d805fc340e553746465349bcc736c4a status=400 post_dur=0.007s +[2026-08-21 20:54:45,178] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=8d805fc340e553746465349bcc736c4a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 20:54:45,186] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b793c03effdd47955bbe35351fb81ebf attempt=1 +[2026-08-21 20:54:45,615] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b793c03effdd47955bbe35351fb81ebf status=200 post_dur=0.427s +[2026-08-21 20:55:40,012] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b793c03effdd47955bbe35351fb81ebf total=54825.9ms bytes=66048 finished=True finish=tool_calls stop=None out_tok=486 prompt_tok=15999 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 20:55:40,015] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e549cb549b08e6f7d377f52f85509ed5 attempt=1 +[2026-08-21 20:55:40,314] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e549cb549b08e6f7d377f52f85509ed5 status=200 post_dur=0.299s +[2026-08-21 21:02:40,982] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e549cb549b08e6f7d377f52f85509ed5 total=420967.5ms bytes=1464124 finished=True finish=stop stop=None out_tok=5037 prompt_tok=540 tps=12.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:02:40,989] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c48208521c9d36be53831b7dbc0549b3 attempt=1 +[2026-08-21 21:02:41,453] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c48208521c9d36be53831b7dbc0549b3 status=200 post_dur=0.464s +[2026-08-21 21:02:53,707] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c48208521c9d36be53831b7dbc0549b3 total=12717.5ms bytes=16399 finished=True finish=stop stop=None out_tok=56 prompt_tok=8191 tps=4.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:02:53,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d7adce66ea6f56253cc33c8d74330235 attempt=1 +[2026-08-21 21:02:54,125] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d7adce66ea6f56253cc33c8d74330235 status=200 post_dur=0.415s +[2026-08-21 21:03:30,161] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d7adce66ea6f56253cc33c8d74330235 total=36451.6ms bytes=79854 finished=True finish=stop stop=None out_tok=273 prompt_tok=8320 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:03:30,164] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e4f5d7c11192057e3feb3c46857e2a9d attempt=1 +[2026-08-21 21:03:30,601] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e4f5d7c11192057e3feb3c46857e2a9d status=200 post_dur=0.437s +[2026-08-21 21:03:39,710] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e4f5d7c11192057e3feb3c46857e2a9d total=9545.2ms bytes=6992 finished=True finish=stop stop=None out_tok=23 prompt_tok=8301 tps=2.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:03:39,712] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7e91035da05743523fd6837ca145fcf6 attempt=1 +[2026-08-21 21:03:40,130] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7e91035da05743523fd6837ca145fcf6 status=200 post_dur=0.417s +[2026-08-21 21:04:15,780] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7e91035da05743523fd6837ca145fcf6 total=36068.0ms bytes=108440 finished=True finish=stop stop=None out_tok=371 prompt_tok=10519 tps=10.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:04:15,787] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=9616ac2056cd5ca2cba64bad90dd24f8 attempt=1 +[2026-08-21 21:04:16,336] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=9616ac2056cd5ca2cba64bad90dd24f8 status=200 post_dur=0.549s +[2026-08-21 21:12:29,434] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=9616ac2056cd5ca2cba64bad90dd24f8 total=493647.0ms bytes=20634 finished=True finish=tool_calls stop=None out_tok=3370 prompt_tok=74000 tps=6.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:12:29,444] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ed5227a774ede3c260f6e79accb678f9 attempt=1 +[2026-08-21 21:12:29,452] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ed5227a774ede3c260f6e79accb678f9 status=400 post_dur=0.007s +[2026-08-21 21:12:29,452] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ed5227a774ede3c260f6e79accb678f9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:12:29,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=139ffb2666d8dd0ac24d34f3257b90ca attempt=1 +[2026-08-21 21:12:29,916] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=139ffb2666d8dd0ac24d34f3257b90ca status=200 post_dur=0.456s +[2026-08-21 21:12:50,939] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=139ffb2666d8dd0ac24d34f3257b90ca total=21480.6ms bytes=13614 finished=True finish=tool_calls stop=None out_tok=146 prompt_tok=11405 tps=6.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:12:50,942] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6437b0bbe06fdc147e24d034c65ac025 attempt=1 +[2026-08-21 21:12:51,384] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6437b0bbe06fdc147e24d034c65ac025 status=200 post_dur=0.442s +[2026-08-21 21:13:29,682] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6437b0bbe06fdc147e24d034c65ac025 total=38739.7ms bytes=42102 finished=True finish=tool_calls stop=None out_tok=395 prompt_tok=12577 tps=10.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:13:29,686] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c5deaf60300d84afbce55d2d1043ecb8 attempt=1 +[2026-08-21 21:13:30,120] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c5deaf60300d84afbce55d2d1043ecb8 status=200 post_dur=0.434s +[2026-08-21 21:13:52,101] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c5deaf60300d84afbce55d2d1043ecb8 total=22415.6ms bytes=22276 finished=True finish=tool_calls stop=None out_tok=205 prompt_tok=12028 tps=9.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:13:52,104] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6c623f2bc44ed880a3cc333f6585bd3 attempt=1 +[2026-08-21 21:13:52,535] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6c623f2bc44ed880a3cc333f6585bd3 status=200 post_dur=0.431s +[2026-08-21 21:14:18,745] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6c623f2bc44ed880a3cc333f6585bd3 total=26641.0ms bytes=21342 finished=True finish=tool_calls stop=None out_tok=262 prompt_tok=7891 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:14:18,753] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7a8000c7a656ab74224e177fb985e988 attempt=1 +[2026-08-21 21:14:18,760] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7a8000c7a656ab74224e177fb985e988 status=400 post_dur=0.005s +[2026-08-21 21:14:18,760] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=7a8000c7a656ab74224e177fb985e988 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:14:18,770] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1077b34d114c5fd3705bcec999d85d17 attempt=1 +[2026-08-21 21:14:18,774] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1077b34d114c5fd3705bcec999d85d17 status=400 post_dur=0.004s +[2026-08-21 21:14:18,774] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1077b34d114c5fd3705bcec999d85d17 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:14:18,787] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c42e43e0575fc20a868511f953c0ff86 attempt=1 +[2026-08-21 21:14:18,795] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c42e43e0575fc20a868511f953c0ff86 status=400 post_dur=0.007s +[2026-08-21 21:14:18,795] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=c42e43e0575fc20a868511f953c0ff86 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:14:18,804] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a402e775c8dbc194998438ebe3430375 attempt=1 +[2026-08-21 21:14:19,252] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a402e775c8dbc194998438ebe3430375 status=200 post_dur=0.448s +[2026-08-21 21:14:35,824] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a402e775c8dbc194998438ebe3430375 total=17019.4ms bytes=6864 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=13505 tps=4.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:14:35,827] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=500a26f22e1662f9550c0eb0b6a8f007 attempt=1 +[2026-08-21 21:14:36,249] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=500a26f22e1662f9550c0eb0b6a8f007 status=200 post_dur=0.422s +[2026-08-21 21:14:57,734] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=500a26f22e1662f9550c0eb0b6a8f007 total=21907.2ms bytes=24814 finished=True finish=tool_calls stop=None out_tok=161 prompt_tok=13670 tps=7.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:14:57,738] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6655d6d29896f86bb52031124195b96b attempt=1 +[2026-08-21 21:14:58,177] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6655d6d29896f86bb52031124195b96b status=200 post_dur=0.439s +[2026-08-21 21:15:33,625] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6655d6d29896f86bb52031124195b96b total=35887.0ms bytes=19271 finished=True finish=tool_calls stop=None out_tok=278 prompt_tok=13245 tps=7.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:15:33,643] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=23e518df272b2a3db9aee2cf2479da5b attempt=1 +[2026-08-21 21:15:33,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=23e518df272b2a3db9aee2cf2479da5b status=400 post_dur=0.008s +[2026-08-21 21:15:33,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=23e518df272b2a3db9aee2cf2479da5b status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:15:33,673] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be9fcfc652f67e5bbae60f96b9ef78af attempt=1 +[2026-08-21 21:15:33,681] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be9fcfc652f67e5bbae60f96b9ef78af status=400 post_dur=0.008s +[2026-08-21 21:15:33,681] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=be9fcfc652f67e5bbae60f96b9ef78af status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:15:33,689] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c9e2f56eea2e6158bc8de323d9237a7b attempt=1 +[2026-08-21 21:15:34,125] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c9e2f56eea2e6158bc8de323d9237a7b status=200 post_dur=0.436s +[2026-08-21 21:16:13,691] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c9e2f56eea2e6158bc8de323d9237a7b total=40002.7ms bytes=40593 finished=True finish=tool_calls stop=None out_tok=368 prompt_tok=7438 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:16:13,702] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=be3bc80cae0f314e77160fc68dd5cc38 attempt=1 +[2026-08-21 21:16:13,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=be3bc80cae0f314e77160fc68dd5cc38 status=400 post_dur=0.007s +[2026-08-21 21:16:13,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=be3bc80cae0f314e77160fc68dd5cc38 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:16:13,714] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14ce510766d3d65789f568a00aa485fe attempt=1 +[2026-08-21 21:16:14,146] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14ce510766d3d65789f568a00aa485fe status=200 post_dur=0.431s +[2026-08-21 21:16:33,304] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14ce510766d3d65789f568a00aa485fe total=19589.8ms bytes=32007 finished=True finish=tool_calls stop=None out_tok=207 prompt_tok=7197 tps=10.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:16:33,312] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3ae820d3d8b2f04593e46ef6f892169c attempt=1 +[2026-08-21 21:16:33,316] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3ae820d3d8b2f04593e46ef6f892169c status=400 post_dur=0.004s +[2026-08-21 21:16:33,316] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3ae820d3d8b2f04593e46ef6f892169c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:16:33,321] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=112f6774c1239a3bd7724e4eff7075ef attempt=1 +[2026-08-21 21:16:33,746] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=112f6774c1239a3bd7724e4eff7075ef status=200 post_dur=0.425s +[2026-08-21 21:16:50,546] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=112f6774c1239a3bd7724e4eff7075ef total=17225.6ms bytes=10637 finished=True finish=tool_calls stop=None out_tok=106 prompt_tok=6327 tps=6.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:16:50,549] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e9ba44e82e68bf31022ee8b3a43a9824 attempt=1 +[2026-08-21 21:16:50,987] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e9ba44e82e68bf31022ee8b3a43a9824 status=200 post_dur=0.438s +[2026-08-21 21:17:24,112] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e9ba44e82e68bf31022ee8b3a43a9824 total=33562.7ms bytes=18996 finished=True finish=tool_calls stop=None out_tok=212 prompt_tok=14662 tps=6.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:17:24,114] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5dc2d723b6412f12f293609228c22fae attempt=1 +[2026-08-21 21:17:24,533] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5dc2d723b6412f12f293609228c22fae status=200 post_dur=0.418s +[2026-08-21 21:17:42,089] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5dc2d723b6412f12f293609228c22fae total=17974.4ms bytes=7073 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=6439 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:17:42,092] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d14bfff61dc219783a32c809d17f7728 attempt=1 +[2026-08-21 21:17:42,528] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d14bfff61dc219783a32c809d17f7728 status=200 post_dur=0.436s +[2026-08-21 21:18:11,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d14bfff61dc219783a32c809d17f7728 total=29641.7ms bytes=17892 finished=True finish=tool_calls stop=None out_tok=287 prompt_tok=14299 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:18:11,737] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ed431b804143b9d0cce3d162e17cad4b attempt=1 +[2026-08-21 21:18:12,188] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ed431b804143b9d0cce3d162e17cad4b status=200 post_dur=0.451s +[2026-08-21 21:18:41,802] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ed431b804143b9d0cce3d162e17cad4b total=30064.7ms bytes=13904 finished=True finish=tool_calls stop=None out_tok=285 prompt_tok=16287 tps=9.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:18:41,807] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=14e1b57e0291a52cf73a394c7386be6e attempt=1 +[2026-08-21 21:18:42,372] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=14e1b57e0291a52cf73a394c7386be6e status=200 post_dur=0.565s +[2026-08-21 21:19:58,626] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=14e1b57e0291a52cf73a394c7386be6e total=76819.1ms bytes=10823 finished=True finish=tool_calls stop=None out_tok=381 prompt_tok=82072 tps=5.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:19:58,636] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=671a043468b95c95f13768a92ddd0bbe attempt=1 +[2026-08-21 21:19:58,641] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=671a043468b95c95f13768a92ddd0bbe status=400 post_dur=0.006s +[2026-08-21 21:19:58,642] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=671a043468b95c95f13768a92ddd0bbe status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:19:58,652] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1b49feb867746a975cf58deeeb395535 attempt=1 +[2026-08-21 21:19:58,657] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1b49feb867746a975cf58deeeb395535 status=400 post_dur=0.005s +[2026-08-21 21:19:58,657] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=1b49feb867746a975cf58deeeb395535 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:19:58,667] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=bcc2e8ba220bd3e4bd9890cd8c971843 attempt=1 +[2026-08-21 21:19:58,673] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=bcc2e8ba220bd3e4bd9890cd8c971843 status=400 post_dur=0.006s +[2026-08-21 21:19:58,673] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=bcc2e8ba220bd3e4bd9890cd8c971843 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:19:58,760] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=882970b4c57ae23190b4c20818bba5ef attempt=1 +[2026-08-21 21:19:59,214] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=882970b4c57ae23190b4c20818bba5ef status=200 post_dur=0.454s +[2026-08-21 21:20:48,500] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=882970b4c57ae23190b4c20818bba5ef total=49739.1ms bytes=29832 finished=True finish=tool_calls stop=None out_tok=485 prompt_tok=9928 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:20:48,510] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=73a3bd5d3ff167b67dbd423e716be328 attempt=1 +[2026-08-21 21:20:49,903] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=73a3bd5d3ff167b67dbd423e716be328 status=200 post_dur=1.391s +[2026-08-21 21:22:25,128] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=73a3bd5d3ff167b67dbd423e716be328 total=96618.3ms bytes=51172 finished=True finish=stop stop=None out_tok=176 prompt_tok=67260 tps=1.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:22:25,144] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b0af71c7e45d74babce202b4a360bf91 attempt=1 +[2026-08-21 21:22:25,715] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b0af71c7e45d74babce202b4a360bf91 status=200 post_dur=0.570s +[2026-08-21 21:22:54,340] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b0af71c7e45d74babce202b4a360bf91 total=29196.5ms bytes=59123 finished=True finish=stop stop=None out_tok=202 prompt_tok=67260 tps=6.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:22:54,347] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f415e58ad74ca97370764c3a39334257 attempt=1 +[2026-08-21 21:22:54,780] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f415e58ad74ca97370764c3a39334257 status=200 post_dur=0.433s +[2026-08-21 21:23:04,582] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f415e58ad74ca97370764c3a39334257 total=10234.5ms bytes=14022 finished=True finish=stop stop=None out_tok=47 prompt_tok=7518 tps=4.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:23:04,585] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=22de4742f212925edbb78a19e315776a attempt=1 +[2026-08-21 21:23:05,026] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=22de4742f212925edbb78a19e315776a status=200 post_dur=0.441s +[2026-08-21 21:23:47,040] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=22de4742f212925edbb78a19e315776a total=42454.8ms bytes=92817 finished=True finish=tool_calls stop=None out_tok=360 prompt_tok=19522 tps=8.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:23:47,045] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=286ef0cf7acf16b5c6169f837a4a2c77 attempt=1 +[2026-08-21 21:23:47,468] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=286ef0cf7acf16b5c6169f837a4a2c77 status=200 post_dur=0.423s +[2026-08-21 21:24:18,526] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=286ef0cf7acf16b5c6169f837a4a2c77 total=31481.0ms bytes=21062 finished=True finish=tool_calls stop=None out_tok=310 prompt_tok=11338 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:24:18,527] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7109532b9b260c52de9b5df9ce765e77 attempt=1 +[2026-08-21 21:24:18,818] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7109532b9b260c52de9b5df9ce765e77 status=200 post_dur=0.290s +[2026-08-21 21:28:26,265] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7109532b9b260c52de9b5df9ce765e77 total=247737.2ms bytes=845905 finished=True finish=stop stop=None out_tok=2913 prompt_tok=506 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:28:26,275] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e298b617246e0a136230757680e61332 attempt=1 +[2026-08-21 21:28:26,281] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e298b617246e0a136230757680e61332 status=400 post_dur=0.006s +[2026-08-21 21:28:26,281] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e298b617246e0a136230757680e61332 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:28:26,291] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 74% (704/881) has_cb=True +[2026-08-21 21:28:26,298] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=73fec74078f5787892b7df7d3e7328d4 attempt=1 +[2026-08-21 21:28:26,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=73fec74078f5787892b7df7d3e7328d4 status=400 post_dur=0.009s +[2026-08-21 21:28:26,308] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=73fec74078f5787892b7df7d3e7328d4 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:28:26,317] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=6f2d5741c5dd68c9390b0ba5f46f2da5 attempt=1 +[2026-08-21 21:28:26,782] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=6f2d5741c5dd68c9390b0ba5f46f2da5 status=200 post_dur=0.465s +[2026-08-21 21:28:52,749] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=6f2d5741c5dd68c9390b0ba5f46f2da5 total=26431.5ms bytes=13847 finished=True finish=tool_calls stop=None out_tok=254 prompt_tok=12263 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:28:52,750] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5f3f556423e78c442aee9f86ee59e733 attempt=1 +[2026-08-21 21:28:53,023] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5f3f556423e78c442aee9f86ee59e733 status=200 post_dur=0.273s +[2026-08-21 21:34:08,420] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5f3f556423e78c442aee9f86ee59e733 total=315670.0ms bytes=1089461 finished=True finish=stop stop=None out_tok=3746 prompt_tok=519 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:34:08,438] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5f37d8513efd204ad426f617040fe3b attempt=1 +[2026-08-21 21:34:08,447] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5f37d8513efd204ad426f617040fe3b status=400 post_dur=0.009s +[2026-08-21 21:34:08,447] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e5f37d8513efd204ad426f617040fe3b status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:34:08,456] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e6e6a4c831c8d2f2b012cac2203b562f attempt=1 +[2026-08-21 21:34:08,944] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e6e6a4c831c8d2f2b012cac2203b562f status=200 post_dur=0.488s +[2026-08-21 21:34:57,005] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e6e6a4c831c8d2f2b012cac2203b562f total=48548.6ms bytes=90380 finished=True finish=tool_calls stop=None out_tok=502 prompt_tok=20987 tps=10.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:34:57,009] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=622ddad28d04e4ed284d6dc10dd381b8 attempt=1 +[2026-08-21 21:34:57,454] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=622ddad28d04e4ed284d6dc10dd381b8 status=200 post_dur=0.445s +[2026-08-21 21:35:28,140] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=622ddad28d04e4ed284d6dc10dd381b8 total=31131.1ms bytes=20618 finished=True finish=tool_calls stop=None out_tok=262 prompt_tok=12863 tps=8.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:35:28,143] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f7ad86e522d208ae4de329d02f219826 attempt=1 +[2026-08-21 21:35:28,597] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f7ad86e522d208ae4de329d02f219826 status=200 post_dur=0.453s +[2026-08-21 21:36:01,016] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f7ad86e522d208ae4de329d02f219826 total=32873.0ms bytes=46811 finished=True finish=tool_calls stop=None out_tok=302 prompt_tok=12994 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:36:01,020] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0eec05bdc18aeb9a0a3145f40f51ee46 attempt=1 +[2026-08-21 21:36:01,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0eec05bdc18aeb9a0a3145f40f51ee46 status=200 post_dur=0.440s +[2026-08-21 21:36:26,312] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0eec05bdc18aeb9a0a3145f40f51ee46 total=25291.9ms bytes=16468 finished=True finish=tool_calls stop=None out_tok=253 prompt_tok=13209 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:36:26,314] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f44b1737342fd2a4bafb3ef88b5da090 attempt=1 +[2026-08-21 21:36:26,752] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f44b1737342fd2a4bafb3ef88b5da090 status=200 post_dur=0.437s +[2026-08-21 21:36:50,045] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f44b1737342fd2a4bafb3ef88b5da090 total=23730.7ms bytes=16797 finished=True finish=tool_calls stop=None out_tok=224 prompt_tok=8031 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:36:50,048] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=cf5613fba4ffe54b92c60dc92576c101 attempt=1 +[2026-08-21 21:36:50,502] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=cf5613fba4ffe54b92c60dc92576c101 status=200 post_dur=0.454s +[2026-08-21 21:39:02,549] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=cf5613fba4ffe54b92c60dc92576c101 total=132500.7ms bytes=61072 finished=True finish=tool_calls stop=None out_tok=1445 prompt_tok=22247 tps=10.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:39:02,565] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3d6a27c894ea4811422d22776303b4fd attempt=1 +[2026-08-21 21:39:02,574] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3d6a27c894ea4811422d22776303b4fd status=400 post_dur=0.009s +[2026-08-21 21:39:02,575] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3d6a27c894ea4811422d22776303b4fd status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 21:39:02,583] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3139704c09490c9774447526c1df3cf0 attempt=1 +[2026-08-21 21:39:03,044] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3139704c09490c9774447526c1df3cf0 status=200 post_dur=0.461s +[2026-08-21 21:39:28,457] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3139704c09490c9774447526c1df3cf0 total=25873.9ms bytes=18437 finished=True finish=tool_calls stop=None out_tok=208 prompt_tok=14346 tps=8.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:39:28,460] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a37407f9934c26c75ef6da8537ab9f2f attempt=1 +[2026-08-21 21:39:28,897] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a37407f9934c26c75ef6da8537ab9f2f status=200 post_dur=0.437s +[2026-08-21 21:40:05,448] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a37407f9934c26c75ef6da8537ab9f2f total=36988.9ms bytes=32454 finished=True finish=tool_calls stop=None out_tok=329 prompt_tok=9165 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:40:05,450] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=391ec2e1889e48bc0084be45e3056695 attempt=1 +[2026-08-21 21:40:05,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=391ec2e1889e48bc0084be45e3056695 status=200 post_dur=0.283s +[2026-08-21 21:49:37,636] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=391ec2e1889e48bc0084be45e3056695 total=572186.2ms bytes=1999021 finished=True finish=stop stop=None out_tok=6850 prompt_tok=519 tps=12.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:49:37,645] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8352bcdb1468e2519a185464d4000846 attempt=1 +[2026-08-21 21:49:38,106] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8352bcdb1468e2519a185464d4000846 status=200 post_dur=0.461s +[2026-08-21 21:50:03,663] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8352bcdb1468e2519a185464d4000846 total=26018.1ms bytes=19687 finished=True finish=tool_calls stop=None out_tok=249 prompt_tok=9792 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:50:03,664] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3aeae62c68dd2d6e1377869b283e9a40 attempt=1 +[2026-08-21 21:50:03,954] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3aeae62c68dd2d6e1377869b283e9a40 status=200 post_dur=0.290s +[2026-08-21 21:57:22,405] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3aeae62c68dd2d6e1377869b283e9a40 total=438741.0ms bytes=1528329 finished=True finish=stop stop=None out_tok=5246 prompt_tok=506 tps=12.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:57:22,413] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=08546a840cec05c064a409824955bbba attempt=1 +[2026-08-21 21:57:22,876] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=08546a840cec05c064a409824955bbba status=200 post_dur=0.463s +[2026-08-21 21:57:44,937] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=08546a840cec05c064a409824955bbba total=22523.7ms bytes=15455 finished=True finish=tool_calls stop=None out_tok=169 prompt_tok=10122 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:57:44,940] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d17426d11e64747aa2600d725f57d460 attempt=1 +[2026-08-21 21:57:45,396] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d17426d11e64747aa2600d725f57d460 status=200 post_dur=0.455s +[2026-08-21 21:58:51,152] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d17426d11e64747aa2600d725f57d460 total=66212.1ms bytes=135443 finished=True finish=tool_calls stop=None out_tok=538 prompt_tok=14085 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:58:51,156] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=02d4feae9634cf32e7e6b61e553463ad attempt=1 +[2026-08-21 21:58:51,608] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=02d4feae9634cf32e7e6b61e553463ad status=200 post_dur=0.451s +[2026-08-21 21:59:07,937] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=02d4feae9634cf32e7e6b61e553463ad total=16781.2ms bytes=12783 finished=True finish=tool_calls stop=None out_tok=159 prompt_tok=10227 tps=9.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:59:07,940] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4f707873f2d3877c215d558cb24fc4e2 attempt=1 +[2026-08-21 21:59:08,367] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4f707873f2d3877c215d558cb24fc4e2 status=200 post_dur=0.427s +[2026-08-21 21:59:18,192] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4f707873f2d3877c215d558cb24fc4e2 total=10251.9ms bytes=11468 finished=True finish=tool_calls stop=None out_tok=83 prompt_tok=7307 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 21:59:18,193] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e5ace36360b819da18742ba885cd175d attempt=1 +[2026-08-21 21:59:18,477] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e5ace36360b819da18742ba885cd175d status=200 post_dur=0.285s +[2026-08-21 22:04:00,149] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e5ace36360b819da18742ba885cd175d total=281956.3ms bytes=975580 finished=True finish=stop stop=None out_tok=3359 prompt_tok=519 tps=11.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:04:00,155] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2ba4da781561dfe88c63fd4bd87fea31 attempt=1 +[2026-08-21 22:04:00,616] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2ba4da781561dfe88c63fd4bd87fea31 status=200 post_dur=0.462s +[2026-08-21 22:04:20,742] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2ba4da781561dfe88c63fd4bd87fea31 total=20587.3ms bytes=15481 finished=True finish=tool_calls stop=None out_tok=84 prompt_tok=8239 tps=4.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:04:20,745] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1dc0a3a3a22b8b9e4df4a02b9e282a6c attempt=1 +[2026-08-21 22:04:21,183] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1dc0a3a3a22b8b9e4df4a02b9e282a6c status=200 post_dur=0.438s +[2026-08-21 22:04:59,389] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1dc0a3a3a22b8b9e4df4a02b9e282a6c total=38644.8ms bytes=23908 finished=True finish=tool_calls stop=None out_tok=379 prompt_tok=10761 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:04:59,393] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e0d7e7b9b926f1de5f73ee7971ac5840 attempt=1 +[2026-08-21 22:04:59,828] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e0d7e7b9b926f1de5f73ee7971ac5840 status=200 post_dur=0.435s +[2026-08-21 22:05:19,905] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e0d7e7b9b926f1de5f73ee7971ac5840 total=20512.4ms bytes=12645 finished=True finish=tool_calls stop=None out_tok=193 prompt_tok=11170 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:05:19,908] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b3bccacd301c72e7ad3c834148f4d29f attempt=1 +[2026-08-21 22:05:20,344] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b3bccacd301c72e7ad3c834148f4d29f status=200 post_dur=0.436s +[2026-08-21 22:05:41,282] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b3bccacd301c72e7ad3c834148f4d29f total=21373.6ms bytes=14293 finished=True finish=tool_calls stop=None out_tok=164 prompt_tok=11415 tps=7.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:05:41,296] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a3a5e39903407d2a971e3a5838593359 attempt=1 +[2026-08-21 22:05:41,896] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a3a5e39903407d2a971e3a5838593359 status=200 post_dur=0.599s +[2026-08-21 22:10:44,247] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a3a5e39903407d2a971e3a5838593359 total=302950.9ms bytes=274231 finished=True finish=stop stop=None out_tok=927 prompt_tok=106344 tps=3.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:10:44,271] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=27ac50f444d86cb5da3b29541e69ce9f attempt=1 +[2026-08-21 22:10:44,280] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=27ac50f444d86cb5da3b29541e69ce9f status=400 post_dur=0.009s +[2026-08-21 22:10:44,280] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=27ac50f444d86cb5da3b29541e69ce9f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:10:44,289] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=097921426c942809b61658d1f77a2d55 attempt=1 +[2026-08-21 22:10:44,732] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=097921426c942809b61658d1f77a2d55 status=200 post_dur=0.442s +[2026-08-21 22:11:14,136] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=097921426c942809b61658d1f77a2d55 total=29847.2ms bytes=28794 finished=True finish=tool_calls stop=None out_tok=246 prompt_tok=7229 tps=8.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:11:14,138] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=54b324762f54160a8e635d0c5080eff4 attempt=1 +[2026-08-21 22:11:14,551] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=54b324762f54160a8e635d0c5080eff4 status=200 post_dur=0.413s +[2026-08-21 22:11:21,777] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=54b324762f54160a8e635d0c5080eff4 total=7638.7ms bytes=10580 finished=True finish=tool_calls stop=None out_tok=77 prompt_tok=7307 tps=10.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:11:21,780] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8dd4dfd064b0fec73276248cb2f830a5 attempt=1 +[2026-08-21 22:11:22,211] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8dd4dfd064b0fec73276248cb2f830a5 status=200 post_dur=0.431s +[2026-08-21 22:11:45,016] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8dd4dfd064b0fec73276248cb2f830a5 total=23236.1ms bytes=23175 finished=True finish=tool_calls stop=None out_tok=152 prompt_tok=15016 tps=6.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:11:45,019] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c7c195332bf640009374052aaef769ab attempt=1 +[2026-08-21 22:11:45,440] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c7c195332bf640009374052aaef769ab status=200 post_dur=0.421s +[2026-08-21 22:11:58,978] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c7c195332bf640009374052aaef769ab total=13958.6ms bytes=12326 finished=True finish=tool_calls stop=None out_tok=124 prompt_tok=7414 tps=8.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:11:58,980] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=06e737ed262cdd26d6ea3a0c561ef8fb attempt=1 +[2026-08-21 22:11:59,406] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=06e737ed262cdd26d6ea3a0c561ef8fb status=200 post_dur=0.426s +[2026-08-21 22:12:07,648] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=06e737ed262cdd26d6ea3a0c561ef8fb total=8668.5ms bytes=7893 finished=True finish=stop stop=None out_tok=26 prompt_tok=7648 tps=3.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:12:07,651] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=a979db6a2f456224fd82a74c3d94c67c attempt=1 +[2026-08-21 22:12:08,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=a979db6a2f456224fd82a74c3d94c67c status=200 post_dur=0.408s +[2026-08-21 22:12:21,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=a979db6a2f456224fd82a74c3d94c67c total=13645.9ms bytes=31933 finished=True finish=stop stop=None out_tok=108 prompt_tok=7768 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:12:21,314] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=95967cff704af8221a9dc8601183be1f attempt=1 +[2026-08-21 22:12:21,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=95967cff704af8221a9dc8601183be1f status=400 post_dur=0.014s +[2026-08-21 22:12:21,329] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=95967cff704af8221a9dc8601183be1f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:12:21,338] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=95218bbd3152ffe40dcca3eed11cb7f4 attempt=1 +[2026-08-21 22:12:21,764] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=95218bbd3152ffe40dcca3eed11cb7f4 status=200 post_dur=0.418s +[2026-08-21 22:12:31,720] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=95218bbd3152ffe40dcca3eed11cb7f4 total=10382.3ms bytes=13430 finished=True finish=stop stop=None out_tok=45 prompt_tok=7749 tps=4.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:12:31,722] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b2ffb8750cab6cb3f517bb328adbb2d9 attempt=1 +[2026-08-21 22:12:32,133] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b2ffb8750cab6cb3f517bb328adbb2d9 status=200 post_dur=0.411s +[2026-08-21 22:12:58,820] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b2ffb8750cab6cb3f517bb328adbb2d9 total=27097.8ms bytes=23646 finished=True finish=tool_calls stop=None out_tok=139 prompt_tok=10784 tps=5.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:12:58,837] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ac5b28578454d9c4950ccbb3d8fe9144 attempt=1 +[2026-08-21 22:12:58,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ac5b28578454d9c4950ccbb3d8fe9144 status=400 post_dur=0.008s +[2026-08-21 22:12:58,845] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=ac5b28578454d9c4950ccbb3d8fe9144 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:12:58,865] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2ecbc7ce213f2e5ab8e47dd792072d88 attempt=1 +[2026-08-21 22:12:58,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2ecbc7ce213f2e5ab8e47dd792072d88 status=400 post_dur=0.009s +[2026-08-21 22:12:58,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=2ecbc7ce213f2e5ab8e47dd792072d88 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:12:58,895] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3a7ac50236e5e5c790c2a66a29ce8ea0 attempt=1 +[2026-08-21 22:12:58,904] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3a7ac50236e5e5c790c2a66a29ce8ea0 status=400 post_dur=0.008s +[2026-08-21 22:12:58,904] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=3a7ac50236e5e5c790c2a66a29ce8ea0 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:12:58,912] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=601141329ab7026beee31c7e2606ccb5 attempt=1 +[2026-08-21 22:12:59,340] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=601141329ab7026beee31c7e2606ccb5 status=200 post_dur=0.427s +[2026-08-21 22:13:28,664] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=601141329ab7026beee31c7e2606ccb5 total=29751.5ms bytes=26200 finished=True finish=tool_calls stop=None out_tok=342 prompt_tok=7433 tps=11.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:13:28,679] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=80e2160d9f40a0fed3c36843147e788f attempt=1 +[2026-08-21 22:13:28,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=80e2160d9f40a0fed3c36843147e788f status=400 post_dur=0.009s +[2026-08-21 22:13:28,688] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=80e2160d9f40a0fed3c36843147e788f status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:13:28,709] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d8d72af25438344ba15724944f481d96 attempt=1 +[2026-08-21 22:13:28,716] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d8d72af25438344ba15724944f481d96 status=400 post_dur=0.007s +[2026-08-21 22:13:28,717] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d8d72af25438344ba15724944f481d96 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:13:28,731] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=0bef92b56cd88a5ed7852457758e842c attempt=1 +[2026-08-21 22:13:29,275] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=0bef92b56cd88a5ed7852457758e842c status=200 post_dur=0.543s +[2026-08-21 22:14:09,585] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=0bef92b56cd88a5ed7852457758e842c total=40853.7ms bytes=74734 finished=True finish=stop stop=None out_tok=259 prompt_tok=67263 tps=6.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:14:09,596] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8911a74fcea14576f24edd254af7fce4 attempt=1 +[2026-08-21 22:14:09,881] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8911a74fcea14576f24edd254af7fce4 status=200 post_dur=0.284s +[2026-08-21 22:17:05,849] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8911a74fcea14576f24edd254af7fce4 total=176253.3ms bytes=596192 finished=True finish=length stop=None out_tok=2048 prompt_tok=348 tps=11.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:17:05,854] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21e3e8abe11c6a1dfdfccfb3f61dafdf attempt=1 +[2026-08-21 22:17:05,854] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Progress: 78% (748/881) has_cb=True +[2026-08-21 22:17:06,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21e3e8abe11c6a1dfdfccfb3f61dafdf status=200 post_dur=0.456s +[2026-08-21 22:17:40,443] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=21e3e8abe11c6a1dfdfccfb3f61dafdf total=34588.5ms bytes=25732 finished=True finish=tool_calls stop=None out_tok=324 prompt_tok=8467 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:17:40,453] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=830a8aebda787e7c6981ee8639998451 attempt=1 +[2026-08-21 22:17:41,001] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=830a8aebda787e7c6981ee8639998451 status=200 post_dur=0.547s +[2026-08-21 22:17:57,336] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=830a8aebda787e7c6981ee8639998451 total=16882.3ms bytes=32904 finished=True finish=stop stop=None out_tok=111 prompt_tok=67263 tps=6.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:17:57,342] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=8e6580f441eee0083337dbc210859258 attempt=1 +[2026-08-21 22:17:57,623] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=8e6580f441eee0083337dbc210859258 status=200 post_dur=0.281s +[2026-08-21 22:21:23,442] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=8e6580f441eee0083337dbc210859258 total=206100.5ms bytes=710127 finished=True finish=stop stop=None out_tok=2437 prompt_tok=133 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:21:23,447] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=2e1058bed8cefe678ef431fcd1d2328d attempt=1 +[2026-08-21 22:21:23,903] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=2e1058bed8cefe678ef431fcd1d2328d status=200 post_dur=0.456s +[2026-08-21 22:21:48,664] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=2e1058bed8cefe678ef431fcd1d2328d total=25216.9ms bytes=19075 finished=True finish=tool_calls stop=None out_tok=200 prompt_tok=9261 tps=7.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:21:48,666] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ca08fb72cf9509755ef655b72b6e0fb3 attempt=1 +[2026-08-21 22:21:49,081] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ca08fb72cf9509755ef655b72b6e0fb3 status=200 post_dur=0.415s +[2026-08-21 22:22:16,403] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ca08fb72cf9509755ef655b72b6e0fb3 total=27737.6ms bytes=27747 finished=True finish=tool_calls stop=None out_tok=312 prompt_tok=7229 tps=11.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:22:16,406] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d9d27317e6fc16335e7f2f73bd6d0685 attempt=1 +[2026-08-21 22:22:16,838] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d9d27317e6fc16335e7f2f73bd6d0685 status=200 post_dur=0.432s +[2026-08-21 22:22:34,648] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=d9d27317e6fc16335e7f2f73bd6d0685 total=18241.9ms bytes=10278 finished=True finish=tool_calls stop=None out_tok=76 prompt_tok=9446 tps=4.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:22:34,650] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44d0e4bbf30781359d72543f85d3bd02 attempt=1 +[2026-08-21 22:22:35,079] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44d0e4bbf30781359d72543f85d3bd02 status=200 post_dur=0.429s +[2026-08-21 22:22:49,285] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=44d0e4bbf30781359d72543f85d3bd02 total=14634.5ms bytes=20755 finished=True finish=tool_calls stop=None out_tok=145 prompt_tok=7197 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:22:49,287] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=44463a5d5adffc8a22206b34e51546c9 attempt=1 +[2026-08-21 22:22:49,290] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=44463a5d5adffc8a22206b34e51546c9 status=400 post_dur=0.003s +[2026-08-21 22:22:49,291] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=44463a5d5adffc8a22206b34e51546c9 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32000}] (retryable=False, attempt=1) +[2026-08-21 22:22:49,293] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=00a2a1293afc30148c742ae51fd1d687 attempt=1 +[2026-08-21 22:22:49,713] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=00a2a1293afc30148c742ae51fd1d687 status=200 post_dur=0.419s +[2026-08-21 22:23:17,172] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=00a2a1293afc30148c742ae51fd1d687 total=27879.2ms bytes=68907 finished=True finish=stop stop=None out_tok=241 prompt_tok=9916 tps=8.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:23:17,177] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=aa4794221115a6434b1f860d6babdb60 attempt=1 +[2026-08-21 22:23:17,604] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=aa4794221115a6434b1f860d6babdb60 status=200 post_dur=0.427s +[2026-08-21 22:23:31,024] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=aa4794221115a6434b1f860d6babdb60 total=13847.0ms bytes=25518 finished=True finish=stop stop=None out_tok=87 prompt_tok=7527 tps=6.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:23:31,026] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c202f7e0e152fa0ff5326c116d791191 attempt=1 +[2026-08-21 22:23:31,459] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c202f7e0e152fa0ff5326c116d791191 status=200 post_dur=0.433s +[2026-08-21 22:24:22,480] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c202f7e0e152fa0ff5326c116d791191 total=51453.5ms bytes=43018 finished=True finish=tool_calls stop=None out_tok=450 prompt_tok=11393 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:24:22,483] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=60bd0696cb4b8ff32e9c282b85346c39 attempt=1 +[2026-08-21 22:24:22,921] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=60bd0696cb4b8ff32e9c282b85346c39 status=200 post_dur=0.438s +[2026-08-21 22:24:44,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=60bd0696cb4b8ff32e9c282b85346c39 total=21826.8ms bytes=24983 finished=True finish=tool_calls stop=None out_tok=168 prompt_tok=10294 tps=7.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:24:44,312] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=543cc04bcc3f9a7e318568886ee8633f attempt=1 +[2026-08-21 22:24:44,740] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=543cc04bcc3f9a7e318568886ee8633f status=200 post_dur=0.428s +[2026-08-21 22:24:53,871] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=543cc04bcc3f9a7e318568886ee8633f total=9558.4ms bytes=10212 finished=True finish=stop stop=None out_tok=34 prompt_tok=7735 tps=3.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:24:53,874] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b344ad8e596833f35a8103990982604d attempt=1 +[2026-08-21 22:24:54,293] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b344ad8e596833f35a8103990982604d status=200 post_dur=0.419s +[2026-08-21 22:25:39,773] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b344ad8e596833f35a8103990982604d total=45899.5ms bytes=92403 finished=True finish=tool_calls stop=None out_tok=423 prompt_tok=12612 tps=9.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:25:39,775] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=ee889e467065d0df16323594bb84712e attempt=1 +[2026-08-21 22:25:40,073] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=ee889e467065d0df16323594bb84712e status=200 post_dur=0.297s +[2026-08-21 22:29:18,427] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=ee889e467065d0df16323594bb84712e total=218652.2ms bytes=746709 finished=True finish=stop stop=None out_tok=2567 prompt_tok=128 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:29:18,431] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c308df7464f629c6690e5873e925b1f5 attempt=1 +[2026-08-21 22:29:18,733] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c308df7464f629c6690e5873e925b1f5 status=200 post_dur=0.302s +[2026-08-21 22:31:49,153] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c308df7464f629c6690e5873e925b1f5 total=150721.9ms bytes=207017 finished=True finish=stop stop=None out_tok=712 prompt_tok=556 tps=4.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:31:49,158] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c219767d23cbf4f04a61b340e19df5c6 attempt=1 +[2026-08-21 22:31:49,616] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c219767d23cbf4f04a61b340e19df5c6 status=200 post_dur=0.458s +[2026-08-21 22:32:17,797] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c219767d23cbf4f04a61b340e19df5c6 total=28638.3ms bytes=72299 finished=True finish=stop stop=None out_tok=249 prompt_tok=10521 tps=8.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:32:17,800] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=4e55b86aabfde6b0a66c5ceebc7dcd57 attempt=1 +[2026-08-21 22:32:18,235] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=4e55b86aabfde6b0a66c5ceebc7dcd57 status=200 post_dur=0.434s +[2026-08-21 22:32:51,444] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=4e55b86aabfde6b0a66c5ceebc7dcd57 total=33643.6ms bytes=31533 finished=True finish=tool_calls stop=None out_tok=279 prompt_tok=10790 tps=8.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:32:51,447] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7002fe78c3e08251cc4309f416481570 attempt=1 +[2026-08-21 22:32:51,869] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7002fe78c3e08251cc4309f416481570 status=200 post_dur=0.422s +[2026-08-21 22:33:10,808] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7002fe78c3e08251cc4309f416481570 total=19360.7ms bytes=9630 finished=True finish=tool_calls stop=None out_tok=125 prompt_tok=12359 tps=6.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:33:10,811] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e9409b7bfc71a4daa16fa8581d9e91dc attempt=1 +[2026-08-21 22:33:11,247] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e9409b7bfc71a4daa16fa8581d9e91dc status=200 post_dur=0.436s +[2026-08-21 22:33:38,977] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=e9409b7bfc71a4daa16fa8581d9e91dc total=28166.0ms bytes=22119 finished=True finish=tool_calls stop=None out_tok=201 prompt_tok=13131 tps=7.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:33:38,980] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c4e2ffecd88bbc1ee550f9e7549bafce attempt=1 +[2026-08-21 22:33:39,416] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c4e2ffecd88bbc1ee550f9e7549bafce status=200 post_dur=0.436s +[2026-08-21 22:34:11,880] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c4e2ffecd88bbc1ee550f9e7549bafce total=32900.4ms bytes=57221 finished=True finish=tool_calls stop=None out_tok=266 prompt_tok=11334 tps=8.1 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:34:11,884] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5609993a4f4848e4fc2244b7184340f2 attempt=1 +[2026-08-21 22:34:12,310] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5609993a4f4848e4fc2244b7184340f2 status=200 post_dur=0.426s +[2026-08-21 22:34:34,221] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5609993a4f4848e4fc2244b7184340f2 total=22337.2ms bytes=15897 finished=True finish=tool_calls stop=None out_tok=221 prompt_tok=11526 tps=9.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:34:34,224] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=3da0d1a231638e8ac5bdd34db8391e7a attempt=1 +[2026-08-21 22:34:34,656] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=3da0d1a231638e8ac5bdd34db8391e7a status=200 post_dur=0.432s +[2026-08-21 22:34:58,041] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=3da0d1a231638e8ac5bdd34db8391e7a total=23816.3ms bytes=25727 finished=True finish=tool_calls stop=None out_tok=225 prompt_tok=13394 tps=9.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:34:58,054] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=793161e7f7404449ca7eaaa9f92c10cd attempt=1 +[2026-08-21 22:34:58,665] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=793161e7f7404449ca7eaaa9f92c10cd status=200 post_dur=0.610s +[2026-08-21 22:38:32,517] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=793161e7f7404449ca7eaaa9f92c10cd total=214463.2ms bytes=115447 finished=True finish=stop stop=None out_tok=398 prompt_tok=106809 tps=1.9 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:38:32,529] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7390681af47ba80e01e90106fa0de554 attempt=1 +[2026-08-21 22:38:32,981] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7390681af47ba80e01e90106fa0de554 status=200 post_dur=0.452s +[2026-08-21 22:38:56,297] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7390681af47ba80e01e90106fa0de554 total=23768.4ms bytes=25091 finished=True finish=tool_calls stop=None out_tok=231 prompt_tok=11851 tps=9.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:38:56,316] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=21082f9133a92ea01ddfd1b968fde9bb attempt=1 +[2026-08-21 22:38:56,334] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=21082f9133a92ea01ddfd1b968fde9bb status=400 post_dur=0.016s +[2026-08-21 22:38:56,334] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=21082f9133a92ea01ddfd1b968fde9bb status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:38:56,343] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7381933996e2d13ef34fd433758431a3 attempt=1 +[2026-08-21 22:38:56,780] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7381933996e2d13ef34fd433758431a3 status=200 post_dur=0.436s +[2026-08-21 22:39:14,211] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7381933996e2d13ef34fd433758431a3 total=17867.8ms bytes=3142 finished=True finish=tool_calls stop=None out_tok=101 prompt_tok=14206 tps=5.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:39:14,214] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=7c759d2d9b3d9e9e460dea23d385c8e5 attempt=1 +[2026-08-21 22:39:14,644] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=7c759d2d9b3d9e9e460dea23d385c8e5 status=200 post_dur=0.430s +[2026-08-21 22:39:46,109] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=7c759d2d9b3d9e9e460dea23d385c8e5 total=31895.1ms bytes=28210 finished=True finish=tool_calls stop=None out_tok=312 prompt_tok=14350 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:39:46,126] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=d1e5989d3695098a6dd9a6c4ca01b08c attempt=1 +[2026-08-21 22:39:46,138] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=d1e5989d3695098a6dd9a6c4ca01b08c status=400 post_dur=0.012s +[2026-08-21 22:39:46,138] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=d1e5989d3695098a6dd9a6c4ca01b08c status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:39:46,148] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=64662c7efa9424921f237ce3a400bf2a attempt=1 +[2026-08-21 22:39:46,588] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=64662c7efa9424921f237ce3a400bf2a status=200 post_dur=0.439s +[2026-08-21 22:40:23,610] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=64662c7efa9424921f237ce3a400bf2a total=37462.8ms bytes=25112 finished=True finish=tool_calls stop=None out_tok=387 prompt_tok=14721 tps=10.3 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:40:23,614] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c26dfc374dc8c68e6df139f63bb11205 attempt=1 +[2026-08-21 22:40:24,059] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c26dfc374dc8c68e6df139f63bb11205 status=200 post_dur=0.445s +[2026-08-21 22:40:39,098] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c26dfc374dc8c68e6df139f63bb11205 total=15483.8ms bytes=7135 finished=True finish=tool_calls stop=None out_tok=80 prompt_tok=14666 tps=5.2 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:40:39,121] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=07c2676f3c4591a9d1ca0ab485f2a55a attempt=1 +[2026-08-21 22:40:39,131] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=07c2676f3c4591a9d1ca0ab485f2a55a status=400 post_dur=0.010s +[2026-08-21 22:40:39,131] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=07c2676f3c4591a9d1ca0ab485f2a55a status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:40:39,157] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=fa5e17661777d2529388743aac10ab34 attempt=1 +[2026-08-21 22:40:39,165] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=fa5e17661777d2529388743aac10ab34 status=400 post_dur=0.008s +[2026-08-21 22:40:39,166] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=fa5e17661777d2529388743aac10ab34 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:40:39,175] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=01b2941acd9079431550509a1422924a attempt=1 +[2026-08-21 22:40:39,602] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=01b2941acd9079431550509a1422924a status=200 post_dur=0.427s +[2026-08-21 22:40:53,832] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=01b2941acd9079431550509a1422924a total=14657.1ms bytes=15133 finished=True finish=tool_calls stop=None out_tok=110 prompt_tok=15406 tps=7.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:40:53,835] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=b6eba20607e2d1a036a02a861e894b8f attempt=1 +[2026-08-21 22:40:54,262] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=b6eba20607e2d1a036a02a861e894b8f status=200 post_dur=0.427s +[2026-08-21 22:41:12,861] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=b6eba20607e2d1a036a02a861e894b8f total=19025.5ms bytes=11381 finished=True finish=tool_calls stop=None out_tok=168 prompt_tok=15239 tps=8.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:41:12,864] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=052dba3442456a480754f3eb83a464bd attempt=1 +[2026-08-21 22:41:13,303] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=052dba3442456a480754f3eb83a464bd status=200 post_dur=0.439s +[2026-08-21 22:41:57,416] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=052dba3442456a480754f3eb83a464bd total=44552.3ms bytes=29758 finished=True finish=tool_calls stop=None out_tok=426 prompt_tok=15812 tps=9.6 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:41:57,420] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=1cfad1ad5848c8e08773fad350c77179 attempt=1 +[2026-08-21 22:41:57,871] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=1cfad1ad5848c8e08773fad350c77179 status=200 post_dur=0.451s +[2026-08-21 22:42:34,222] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=1cfad1ad5848c8e08773fad350c77179 total=36801.4ms bytes=36391 finished=True finish=tool_calls stop=None out_tok=387 prompt_tok=15090 tps=10.5 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:42:34,225] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=89e97ed329c80d17df1eff8bd4f7d61a attempt=1 +[2026-08-21 22:42:34,675] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=89e97ed329c80d17df1eff8bd4f7d61a status=200 post_dur=0.449s +[2026-08-21 22:42:52,181] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=89e97ed329c80d17df1eff8bd4f7d61a total=17955.3ms bytes=8132 finished=True finish=tool_calls stop=None out_tok=115 prompt_tok=16333 tps=6.4 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:42:52,183] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=5eeb15e34409174ac39272ce458a6d89 attempt=1 +[2026-08-21 22:42:52,470] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=5eeb15e34409174ac39272ce458a6d89 status=200 post_dur=0.287s +[2026-08-21 22:45:46,899] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=5eeb15e34409174ac39272ce458a6d89 total=174716.1ms bytes=596525 finished=True finish=length stop=None out_tok=2048 prompt_tok=330 tps=11.7 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:45:46,906] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=c35e8fc6259d255e63fc9962a13b3056 attempt=1 +[2026-08-21 22:45:47,391] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=c35e8fc6259d255e63fc9962a13b3056 status=200 post_dur=0.485s +[2026-08-21 22:46:28,668] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=c35e8fc6259d255e63fc9962a13b3056 total=41761.9ms bytes=30316 finished=True finish=tool_calls stop=None out_tok=409 prompt_tok=16928 tps=9.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:46:28,683] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=e37b63740964d431a04a79abf8d71eb1 attempt=1 +[2026-08-21 22:46:28,696] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=e37b63740964d431a04a79abf8d71eb1 status=400 post_dur=0.011s +[2026-08-21 22:46:28,696] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [WARNING] [replay] FAIL request_id=e37b63740964d431a04a79abf8d71eb1 status=400 class=http_400 error=HTTPError: 400 Client Error: Bad Request for url: http://172.28.22.18:38879/v1/chat/completions server_msg=[{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 8192}] (retryable=False, attempt=1) +[2026-08-21 22:46:28,704] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=f7e514a7e86dcba850ea1fc45a9c2f98 attempt=1 +[2026-08-21 22:46:28,999] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=f7e514a7e86dcba850ea1fc45a9c2f98 status=200 post_dur=0.295s +[2026-08-21 22:50:40,708] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=f7e514a7e86dcba850ea1fc45a9c2f98 total=252003.7ms bytes=866201 finished=True finish=stop stop=None out_tok=2979 prompt_tok=1078 tps=11.8 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 22:50:40,713] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] START request_id=392d8a6b3a97a67457adeb772551b8af attempt=1 +[2026-08-21 22:50:41,197] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] POST request_id=392d8a6b3a97a67457adeb772551b8af status=200 post_dur=0.484s +[2026-08-21 22:51:19,720] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] Time budget reached (46800s) — stopping batch with 4 in flight, 794/881 dispatched +[2026-08-21 22:51:19,721] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] END batch total=881 dispatched=794 completed=790 elapsed=46800.8s throughput=0.02 req/s +[2026-08-21 22:51:19,721] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] wall_time_s=46800.762 records=881 +[2026-08-21 22:51:19,722] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] Failure breakdown (of 790 attempted): {'http_400': 232, 'request_validation': 6} +[2026-08-21 22:51:19,723] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] http_400 ×232 — e.g. request_id=a58f13fba3a7932488e00d79515e12dd: [{'type': 'extra_forbidden', 'loc': ('body', 'max_completion_tokens'), 'msg': 'Extra inputs are not permitted', 'input': 32768}] +[2026-08-21 22:51:19,723] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] request_validation ×6 — e.g. request_id=57832f49558fd182b94b8e85dacaec5a: 1 validation error for ValidatorIterator 0.index Extra inputs are not permitted [type=extra_forbidden, input_value=0, input_type=int] For further information visit https://errors.pydantic.dev/2.11/v/extra_forbidden +[2026-08-21 22:51:19,723] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] 6 requests failed the server's request validation (malformed roles / content types the capture's gateway tolerated). convert --clean coerces the known shapes; see the example above for what the server objected to. +[2026-08-21 22:51:19,723] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [replay] 91/881 requests never started (batch was canceled or budget ran out before they were dispatched) +[2026-08-21 22:51:19,725] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] PASSED. metrics={'total_requests': 881, 'attempted_requests': 790, 'not_started_requests': 91, 'successful_requests': 552, 'error_requests': 238, 'error_rate': 0.3012658227848101, 'unfinished_requests': 0, 'unfinished_rate': 0.0, 'uptime': 0.6987341772151898, 'http_200_count': 552, 'tool_requests_total': 634, 'tool_call_4xx_errors': 218, 'image_requests_total': 27, 'image_4xx_errors': 22, 'multi_system_requests': 34, 'multi_system_4xx_errors': 7, 'system_normalized_count': 34, 'error_class_counts': {'http_400': 232, 'request_validation': 6}, 'ttft_p50_ms': 8026.477517560124, 'ttft_p90_ms': 35175.84916204215, 'ttft_p99_ms': 204674.42504394823, 'ttft_mean_ms': 18109.350033192153, 'ttft_input_unknown_count': 0, 'ttft_lt_6k_p90_ms': 6142.49766841531, 'ttft_lt_6k_p50_ms': 4037.4590642750263, 'ttft_lt_6k_avg_ms': 7941.284985860458, 'ttft_lt_6k_count': 74, 'ttft_6k_16k_p90_ms': 12554.19871583581, 'ttft_6k_16k_p50_ms': 7909.27005186677, 'ttft_6k_16k_avg_ms': 7970.6060968112415, 'ttft_6k_16k_count': 361, 'ttft_16k_32k_p90_ms': 38859.58320386708, 'ttft_16k_32k_p50_ms': 14271.574016660452, 'ttft_16k_32k_avg_ms': 19994.37927260995, 'ttft_16k_32k_count': 50, 'ttft_32k_64k_p90_ms': 88069.90002654494, 'ttft_32k_64k_p50_ms': 54282.86877274513, 'ttft_32k_64k_avg_ms': 49116.96075554937, 'ttft_32k_64k_count': 32, 'ttft_64k_128k_p90_ms': 165133.84408131242, 'ttft_64k_128k_p50_ms': 96002.26914510131, 'ttft_64k_128k_avg_ms': 89086.57433429072, 'ttft_64k_128k_count': 31, 'ttft_128k_256k_p90_ms': 524881.0651980342, 'ttft_128k_256k_p50_ms': 236742.4282375723, 'ttft_128k_256k_avg_ms': 299542.9540621117, 'ttft_128k_256k_count': 4, 'ttft_ge_256k_p90_ms': None, 'ttft_ge_256k_p50_ms': None, 'ttft_ge_256k_avg_ms': None, 'ttft_ge_256k_count': 0, 'total_time_p50_ms': 29856.456445530057, 'total_time_p99_ms': 962424.7151445975, 'avg_prompt_tokens': 17172.108695652172, 'avg_completion_tokens': 672.2047101449275, 'output_tps_avg': 7.422580787798189, 'output_tps_mean': 7.422580787798189, 'output_tps_p10': 3.0387401626464814, 'output_tps_p50': 7.924574711816534, 'output_tps_p90': 11.589456054097667, 'input_tps_mean': 1604.1964746080528, 'input_tps_p10': 234.44183658701695, 'input_tps_p50': 1146.3573810774499, 'input_tps_p90': 2868.566990994874, 'total_input_tokens': 9479004, 'total_output_tokens': 371057, 'total_cached_tokens': 5032112, 'total_uncached_input_tokens': 4446892, 'cache_hit_rate': 0.5308692769831092, 'wall_time_s': 46800.76168292761, 'input_tpm': 12152.37144756706, 'output_tpm': 475.7063603116837, 'cached_tpm': 6451.320644000105, 'uncached_input_tpm': 5701.0508035669545, 'tokens_after_finish_count': 0, 'repetitive_token_count': 0, 'generation_capped_count': 0, 'finish_reason_length_count': 12, 'finish_reason_stop_count': 174, 'finish_marker_counts': {'openai_finish_reason_tool_calls': 366, 'openai_finish_reason_length': 12, 'openai_finish_reason_stop': 174}, 'judge_sampled_count': None, 'judge_answered_count': None, 'judge_toolcall_count': None, 'judge_length_count': None, 'judge_disconnect_count': None, 'judge_error_count': None, 'judge_kept_count': None, 'judge_good_acc_rate': None, 'judge_poor_rate': None, 'judge_halluc_clear_rate': None, 'judge_halluc_suspected_count': None, 'judge_failures': None} +[2026-08-21 22:51:19,725] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay] Response capture written to /tmp/perfbench_submission_791_v_1ac8s4/replay_tencent_104/replay_responses.jsonl +[2026-08-21 22:51:19,725] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [replay_tencent] uptime=0.6987341772151898 ttft_p99=204674.42504394823 total_time_p99=962424.7151445975 +[2026-08-21 22:51:19,729] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module replay_tencent: card-normalized TPM (baseline=8, cards=8 assumed): input_tpm_card_norm=12152, output_tpm_card_norm=476, cached_tpm_card_norm=6451, total_tpm_card_norm=12628 +[2026-08-21 22:51:19,730] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module replay_tencent: dataset identity dataset_id=gpu-41-42-2026-06-29-1400-bystart.replay.jsonl, dataset_sha256=- +[2026-08-21 22:51:34,390] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module replay_tencent done — passed=False score=17721.9956 +[2026-08-21 22:51:34,575] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 starting module opencompass (bm_id=105 order=3) +[2026-08-21 22:51:37,468] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module opencompass: CONCURRENCY OVERRIDE max_workers=4 -> 1. +[2026-08-21 22:51:45,847] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass] received params: {'dataset_dir': '/app/dataset/opencompass/data', 'selected_benchmarks': ['aime2025', 'gpqa_diamond', 'simpleqa', 'longbench_v2', 'hle'], 'max_workers': 1, 'request_timeout': 3600.0, 'max_seconds': 57600.0, 'max_tokens': 131072, 'sample_cap_aime': 0, 'sample_cap_gpqa': 0, 'sample_cap_ifeval': 0, 'sample_cap_mmlu': 0, 'sample_cap_hle': 100, 'sample_cap_lcb': 0, 'sample_cap_simpleqa': 200, 'sample_cap_longbench': 0, 'avg_k_aime': 8, 'avg_k_gpqa': 1, 'avg_k_ifeval': 1, 'avg_k_mmlu': 1, 'avg_k_hle': 1, 'avg_k_lcb': 1, 'avg_k_simpleqa': 1, 'avg_k_longbench': 1, 'pass_k_aime': 1, 'pass_k_gpqa': 1, 'pass_k_ifeval': 1, 'pass_k_mmlu': 1, 'pass_k_hle': 1, 'pass_k_lcb': 1, 'pass_k_simpleqa': 1, 'pass_k_longbench': 1, 'sample_temperature': 1.0, 'sample_top_p': 0.95, 'force_temperature': True, 'stream': True, 'judge_api_url': 'http://172.21.112.11/phanrouter', 'judge_model': 'Kimi-K2.5', 'judge_api_key': '***', 'judge_max_tokens': 16384, 'hle_use_judge': True, 'hle_judge_max_tokens': 2048, 'longbench_max_input_tokens': 190000, 'longbench_max_output_tokens': 16384} +[2026-08-21 22:51:45,877] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] Starting academic evaluation + endpoint : api_url=http://172.28.22.18:38879 model=llm api_key=*** + data_dir : /app/dataset/opencompass/data + max_workers : 1 + request_timeout : 3600.0s + max_tokens : 131072 + sample_caps : {'aime2025': 0, 'gpqa_diamond': 0, 'ifeval': 0, 'mmlu_pro': 0, 'hle': 100, 'livecodebench_v6': 0, 'simpleqa': 200, 'longbench_v2': 0} + skip_flags : {'aime2025': False, 'gpqa_diamond': False, 'ifeval': True, 'mmlu_pro': True, 'hle': False, 'livecodebench_v6': True, 'simpleqa': False, 'longbench_v2': False} + avg_k : {'aime2025': 8, 'gpqa_diamond': 1, 'ifeval': 1, 'mmlu_pro': 1, 'hle': 1, 'livecodebench_v6': 1, 'simpleqa': 1, 'longbench_v2': 1} + pass_k : {'aime2025': 1, 'gpqa_diamond': 1, 'ifeval': 1, 'mmlu_pro': 1, 'hle': 1, 'livecodebench_v6': 1, 'simpleqa': 1, 'longbench_v2': 1} sample_temperature=1.00 sample_top_p=0.95 force_temperature=True + active runners : ['aime2025', 'gpqa_diamond', 'hle', 'simpleqa', 'longbench_v2'] + baseline_file : (none) max_regression=0.0200 +[2026-08-21 22:51:45,877] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] module time cap: 57600s +[2026-08-21 22:51:45,877] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] >>> benchmark 1/5: aime2025 (sample_cap=all, avg@8, pass@1, temp=1.00, top_p=0.95, max_tokens=131072, suite_elapsed=0s) +[2026-08-21 22:51:45,881] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: BEGIN items=30 n_samples=8 (avg@8/pass@1) temp=1.00 top_p=0.95 requests=240 workers=1 max_tokens=131072 timeout=3600.0s stream=True +[2026-08-21 22:51:49,257] [PID 14] [ThreadPoolExecutor-0_0] [/app/utils/logger.py] [INFO] [replay] DONE request_id=392d8a6b3a97a67457adeb772551b8af total=68544.2ms bytes=74385 finished=True finish=tool_calls stop=None out_tok=684 prompt_tok=18904 tps=10.0 tok_after_finish=0 repetitive=False capped=False +[2026-08-21 23:13:08,116] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 1/240 reqs (0.4%) sample_acc=1.000 fails=0 elapsed=1282s rate=0.00/s eta=306454s ttft=5629ms tpot=83.5ms svc_tps=12 +[2026-08-21 23:35:51,270] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 2/240 reqs (0.8%) sample_acc=1.000 fails=0 elapsed=2645s rate=0.00/s eta=314801s ttft=3188ms tpot=83.5ms svc_tps=12 +[2026-08-21 23:51:34,843] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 3/240 reqs (1.2%) sample_acc=1.000 fails=0 elapsed=3589s rate=0.00/s eta=283528s ttft=2375ms tpot=83.7ms svc_tps=12 +[2026-08-22 00:13:44,333] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 4/240 reqs (1.7%) sample_acc=1.000 fails=0 elapsed=4918s rate=0.00/s eta=290189s ttft=1968ms tpot=83.7ms svc_tps=12 +[2026-08-22 00:34:27,657] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 5/240 reqs (2.1%) sample_acc=1.000 fails=0 elapsed=6162s rate=0.00/s eta=289603s ttft=1724ms tpot=83.7ms svc_tps=12 +[2026-08-22 00:54:30,718] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 6/240 reqs (2.5%) sample_acc=1.000 fails=0 elapsed=7365s rate=0.00/s eta=287229s ttft=1562ms tpot=83.8ms svc_tps=12 +[2026-08-22 01:13:08,996] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 7/240 reqs (2.9%) sample_acc=1.000 fails=0 elapsed=8483s rate=0.00/s eta=282367s ttft=1446ms tpot=83.7ms svc_tps=12 +[2026-08-22 01:37:25,258] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 8/240 reqs (3.3%) sample_acc=1.000 fails=0 elapsed=9939s rate=0.00/s eta=288242s ttft=1358ms tpot=83.8ms svc_tps=12 +[2026-08-22 03:27:23,853] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 9/240 reqs (3.8%) sample_acc=1.000 fails=0 elapsed=16538s rate=0.00/s eta=424475s ttft=1606ms tpot=85.9ms svc_tps=11 +[2026-08-22 04:28:20,441] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 10/240 reqs (4.2%) sample_acc=1.000 fails=0 elapsed=20195s rate=0.00/s eta=464475s ttft=1573ms tpot=86.3ms svc_tps=11 +[2026-08-22 05:27:52,067] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 11/240 reqs (4.6%) sample_acc=1.000 fails=0 elapsed=23766s rate=0.00/s eta=494769s ttft=1545ms tpot=86.6ms svc_tps=11 +[2026-08-22 06:30:09,470] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 12/240 reqs (5.0%) sample_acc=1.000 fails=0 elapsed=27504s rate=0.00/s eta=522568s ttft=1522ms tpot=87.0ms svc_tps=11 +[2026-08-22 07:48:06,741] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 13/240 reqs (5.4%) sample_acc=1.000 fails=0 elapsed=32181s rate=0.00/s eta=561927s ttft=1502ms tpot=87.6ms svc_tps=11 +[2026-08-22 08:47:49,464] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 14/240 reqs (5.8%) sample_acc=1.000 fails=0 elapsed=35764s rate=0.00/s eta=577326s ttft=1486ms tpot=87.8ms svc_tps=11 +[2026-08-22 10:20:53,787] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 15/240 reqs (6.2%) sample_acc=1.000 fails=0 elapsed=41348s rate=0.00/s eta=620219s ttft=1470ms tpot=88.5ms svc_tps=11 +[2026-08-22 11:18:23,890] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 16/240 reqs (6.7%) sample_acc=1.000 fails=0 elapsed=44798s rate=0.00/s eta=627172s ttft=1458ms tpot=88.6ms svc_tps=11 +[2026-08-22 11:52:07,448] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 17/240 reqs (7.1%) sample_acc=1.000 fails=0 elapsed=46822s rate=0.00/s eta=614189s ttft=1583ms tpot=88.3ms svc_tps=11 +[2026-08-22 12:21:55,406] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 18/240 reqs (7.5%) sample_acc=1.000 fails=0 elapsed=48610s rate=0.00/s eta=599517s ttft=1567ms tpot=88.0ms svc_tps=11 +[2026-08-22 12:46:16,078] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 19/240 reqs (7.9%) sample_acc=1.000 fails=0 elapsed=50070s rate=0.00/s eta=582395s ttft=1553ms tpot=87.8ms svc_tps=11 +[2026-08-22 13:10:53,724] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 20/240 reqs (8.3%) sample_acc=1.000 fails=0 elapsed=51548s rate=0.00/s eta=567026s ttft=1541ms tpot=87.6ms svc_tps=11 +[2026-08-22 13:33:31,324] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 21/240 reqs (8.8%) sample_acc=1.000 fails=0 elapsed=52905s rate=0.00/s eta=551728s ttft=1530ms tpot=87.5ms svc_tps=11 +[2026-08-22 13:57:48,414] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 22/240 reqs (9.2%) sample_acc=1.000 fails=0 elapsed=54363s rate=0.00/s eta=538683s ttft=1520ms tpot=87.3ms svc_tps=11 +[2026-08-22 14:30:32,303] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: 23/240 reqs (9.6%) sample_acc=1.000 fails=0 elapsed=56326s rate=0.00/s eta=531428s ttft=1510ms tpot=87.1ms svc_tps=11 +[2026-08-22 14:57:39,912] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: cancel requested — aborting at 23/240 (in-flight requests will drain up to request_timeout) +[2026-08-22 14:57:39,914] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [academic] aime2025: CANCELED partial=23/240 reqs correct_samples=23 in 57954.0s +[2026-08-22 14:57:39,915] [PID 14] [Thread-4] [/app/utils/logger.py] [WARNING] [opencompass_benchmark] aime2025 stopped by module time cap (57600s) at 23/30 items — stopping suite +[2026-08-22 14:57:39,915] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] generation perf — ttft_mean=1510ms tpot_mean=87ms service_tps=11 gen_tokens=625255 +[2026-08-22 14:57:39,915] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass_benchmark] PASSED — scores: {} +[2026-08-22 14:57:39,916] [PID 14] [Thread-4] [/app/utils/logger.py] [INFO] [opencompass] scores={} avg=0.000 +[2026-08-22 14:57:49,320] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 module opencompass done — passed=True score=0.0000 +[2026-08-22 14:57:59,003] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Submission 791 finished — passed=False score=17721.99557 modules_run=4 +[2026-08-22 14:58:14,610] [PID 14] [Thread-4] [app.queue.jobs] [INFO] Keeping output dir for submission 791 (run had failures): /tmp/perfbench_submission_791_v_1ac8s4 + + + + + + + + + + + +