fix: isolate gate baseline-arm INFRA errors from BaselineCache (algo #6)

2026-07-16 05:33:21 -04:00
parent 87908b23eb
commit d1516bf56b
2 changed files with 141 additions and 18 deletions
@@ -505,6 +505,76 @@ async def test_baseline_cache_hit(tmp_path: Path) -> None:
        log.close()


+@pytest.mark.asyncio
+async def test_baseline_infra_error_not_cached(tmp_path: Path) -> None:
+    """基线臂 INFRA error 的 unit 不写入 BaselineCache（不永久污染），且从有效单元排除。"""
+    from app.harness.gate_ladder import skill_hash
+    from app.harness.question_units import build_units
+    from app.harness.validate import _resolve_baseline_block
+
+    workspace = _setup_workspace(tmp_path)
+    log = _make_log(workspace)
+    questions = _make_questions(2)  # q0 干净, q1 INFRA error
+    units = build_units(questions)
+    cache = BaselineCache(workspace / "baseline_cache.json")
+    s_hash = skill_hash("baseline skill content")
+
+    async def mock_fn(qs, *, run_id, skills_dir):
+        for q in qs:
+            is_err = q.question_id == "q1"
+            log.insert(
+                "predictions",
+                {
+                    "run_id": run_id,
+                    "video_id": "v0",
+                    "question_id": q.question_id,
+                    "task_type": "temporal",
+                    "prediction": "" if is_err else "A",
+                    "answer": "A",
+                    "evidence": "",
+                    "reasoning": "",
+                    "steps_used": 1,
+                    "prompt_tokens": 10,
+                    "completion_tokens": 10,
+                    "stop_reason": "error" if is_err else "completed",
+                    "steps_json": "[]",
+                },
+            )
+        return InferenceResult(
+            run_id=run_id,
+            accuracy=0.5,
+            total=2,
+            correct=1,
+            per_task_type={},
+            steps_mean=1.0,
+            token_usage={"prompt_tokens": 10, "completion_tokens": 10},
+            stop_reason_counts={"completed": 1, "error": 1},
+        )
+
+    try:
+        b_units, valid_units, _errors_inc, _denom_inc = await _resolve_baseline_block(
+            units=units,
+            task_type="temporal",
+            s_hash=s_hash,
+            prompts_version="p1",
+            baseline_cache=cache,
+            base_skills_dir=workspace / "skills" / "v1",
+            run_inference=mock_fn,
+            log=log,
+            run_id="step1_gate_b0_base",
+        )
+        # q1 是 INFRA：不写缓存、不入 b_units、不在有效单元里
+        assert cache.get("temporal", s_hash, "p1", "q1") is None
+        assert "q1" not in b_units
+        assert all(u.unit_id != "q1" for u in valid_units)
+        # q0 干净：正常缓存并入 b_units/valid_units
+        assert cache.get("temporal", s_hash, "p1", "q0") is True
+        assert b_units["q0"] is True
+        assert any(u.unit_id == "q0" for u in valid_units)
+    finally:
+        log.close()
+
+
@pytest.mark.asyncio
 async def test_last_block_terminal(tmp_path: Path) -> None:
    """单块 + n_remaining=0 → 终态判定（provisional 或 inertia），非 continue。"""