feat: reserve queue capacity for recent models

tests/test_concurrency.py

@@ -17,8 +17,13 @@ if str(PACKAGE_DIR) in sys.path:
 sys.path.insert(0, str(PACKAGE_DIR))
 
 from common import read_json, read_jsonl  # noqa: E402
-from main import build_parser, make_run_dir, run_submission, submit_candidate  # noqa: E402
-from modelhub_client import ModelHubAPIError, ModelHubClientPool, is_duplicate_submission_error  # noqa: E402
+from main import build_adaptive_scan_stages, build_parser, make_run_dir, run_submission, submit_candidate  # noqa: E402
+from modelhub_client import (  # noqa: E402
+    ModelHubAPIError,
+    ModelHubClientPool,
+    OldModelQueuePolicyError,
+    is_duplicate_submission_error,
+)
 from models import HFModelSummary, ModelInspection  # noqa: E402
 from outcome_tracker import OutcomeTracker  # noqa: E402
 from submission_claims import SubmissionClaimStore, candidate_key  # noqa: E402
@@ -210,6 +215,109 @@ def make_candidate(index: int) -> dict:
 
 
 class ClientPoolConcurrencyTests(unittest.TestCase):
+    def test_old_models_use_only_each_accounts_first_eighty_queue_positions(self) -> None:
+        below_threshold = FakeClient(active_count=79)
+        at_threshold = FakeClient(active_count=80)
+        pool = ModelHubClientPool(
+            [below_threshold, at_threshold],  # type: ignore[list-item]
+            active_task_cap=100,
+            active_counts_ttl=60,
+            old_model_queue_threshold=80,
+            recent_model_days=7,
+            instance_id="old-model-threshold-test",
+        )
+        submitted_at = datetime(2026, 8, 11, tzinfo=timezone.utc)
+
+        pool.add_task_for_model(
+            {"model": "old-allowed-as-position-80"},
+            model_last_modified=datetime(2026, 7, 1, tzinfo=timezone.utc),
+            submitted_at=submitted_at,
+        )
+
+        self.assertEqual(1, len(below_threshold.submitted))
+        self.assertEqual(0, len(at_threshold.submitted))
+        self.assertEqual(0, pool.old_model_submit_slots())
+        with self.assertRaises(OldModelQueuePolicyError):
+            pool.add_task_for_model(
+                {"model": "old-rejected"},
+                model_last_modified=datetime(2026, 7, 1, tzinfo=timezone.utc),
+                submitted_at=submitted_at,
+            )
+
+        pool.add_task_for_model(
+            {"model": "recent-allowed"},
+            model_last_modified=datetime(2026, 8, 10, tzinfo=timezone.utc),
+            submitted_at=submitted_at,
+        )
+        self.assertEqual(2, len(below_threshold.submitted) + len(at_threshold.submitted))
+
+    def test_concurrent_old_model_submissions_cannot_cross_eighty(self) -> None:
+        client = FakeClient(active_count=78)
+        pool = ModelHubClientPool(
+            [client],  # type: ignore[list-item]
+            active_task_cap=100,
+            active_counts_ttl=60,
+            old_model_queue_threshold=80,
+            recent_model_days=7,
+        )
+        submitted_at = datetime(2026, 8, 11, tzinfo=timezone.utc)
+
+        def submit(index: int) -> str:
+            try:
+                pool.add_task_for_model(
+                    {"model": f"old-{index}"},
+                    model_last_modified=datetime(2026, 7, 1, tzinfo=timezone.utc),
+                    submitted_at=submitted_at,
+                )
+                return "submitted"
+            except OldModelQueuePolicyError:
+                return "policy_skipped"
+
+        with ThreadPoolExecutor(max_workers=8) as executor:
+            outcomes = list(executor.map(submit, range(8)))
+
+        self.assertEqual(2, outcomes.count("submitted"))
+        self.assertEqual(6, outcomes.count("policy_skipped"))
+        self.assertEqual(2, len(client.submitted))
+        self.assertEqual(0, pool.old_model_submit_slots())
+
+    def test_scan_does_not_expand_beyond_recent_window_when_old_slots_are_full(self) -> None:
+        now = datetime(2026, 8, 11, tzinfo=timezone.utc)
+        stages = build_adaptive_scan_stages(
+            now=now,
+            initial_updated_after=now - timedelta(hours=48),
+            initial_limit=100,
+            allow_older_than_recent_window=False,
+            recent_model_days=7,
+        )
+
+        self.assertEqual(["configured_window", "last_7_days"], [stage["name"] for stage in stages])
+        self.assertTrue(all(stage["updatedAfter"] >= now - timedelta(days=7) for stage in stages))
+
+    def test_submit_candidate_reports_old_model_policy_skip_at_eighty(self) -> None:
+        client = FakeClient(active_count=80)
+        pool = ModelHubClientPool(
+            [client],  # type: ignore[list-item]
+            active_task_cap=100,
+            old_model_queue_threshold=80,
+            recent_model_days=7,
+        )
+        result = submit_candidate(
+            {
+                "repoId": "owner/old",
+                "modelAddress": "https://modelscope.cn/models/owner/old",
+                "targetGpu": "Iluvatar_bi-150",
+                "taskType": "text-generation",
+                "framework": "vllm",
+                "configParams": "framework: vllm",
+                "lastModified": "2025-01-01T00:00:00+00:00",
+            },
+            pool,  # type: ignore[arg-type]
+        )
+
+        self.assertEqual("old_model_policy_skipped", result["outcome"])
+        self.assertEqual([], client.submitted)
+
     def test_online_submission_does_not_construct_llm_even_when_key_is_present(self) -> None:
         with tempfile.TemporaryDirectory() as temporary_dir:
             root = Path(temporary_dir)