fix(critical): disable thinking for tool_call requests — fixes d03_tool_call FAIL

Root cause: When tool_choice=auto + tools present, the model enters
<think>...</think> mode by default. On BI-V100 hardware, decode is slow
enough that thinking consumes the entire max_tokens budget, and the model
finishes (finish=stop) before ever emitting <tool_call> XML.

Sub168 reference: d03 in 2.12s with tools=1, finish=tool_calls
Our sub509: d03 in 49.04s with tools=0, finish=stop — FAIL

Fix: Two-layer defense:
1. protocol.py normalize_messages: when tools active + tool_choice=auto
   and thinking not explicitly set, auto-set enable_thinking=False
2. qwen3coder_tool_parser.py adjust_request: same logic as defense-in-depth
3. baseline.muh synced with actual computility-run.yaml
This commit is contained in:
Claude
2026-08-07 07:45:28 +00:00
parent 812c374f7a
commit e0344b1730
3 changed files with 40 additions and 4 deletions

View File

@@ -19,13 +19,10 @@ vllm:
max_model_len: 100000
gpu_memory_utilization: 0.90
tensor_parallel: 4
max_num_seqs: 2
max_num_batched_tokens: 4096
max_seq_len_to_capture: 32768
max_num_seqs: 1
trust_remote_code: true
disable_log_requests: true
disable_frontend_multiprocessing: true
enable_chunked_prefill: true
enable_auto_tool_choice: true
tool_call_parser: qwen3_coder
reasoning_parser: qwen3