feat(m5): full eval pipeline — parse/metrics/judge/baselines/report (T5.1-T5.5)

- src/tsmm/eval/parse_answer.py: text→JSON segments→point scores (JSON-first,
  regex fallback, all-zero on fail).
- src/tsmm/eval/ts_metrics.py: VUS-PR (main, threshold-free; constant-score →
  prevalence, NOT inflated), AUC-PR, Point-F1 (no PA), PA-F1 (control only),
  self-contained Affiliation-F1.
- src/tsmm/eval/qa_judge.py: RuleJudge (anomaly IoU / describe+forecast numeric
  tolerance) + LLMJudge (stub backend = deterministic offline heuristic for the
  no-network host; openai backend = GPT-4o 0-5; pluggable callable).
- src/tsmm/eval/baselines.py: trivial (Random/Constant/AllReport) + ts_to_text
  + pure_llm_answer glue; Time-LLM/ChatTS marked not-reproduced (honest).
- src/tsmm/eval/report.py + scripts/run_eval.sh: trained model + all baselines
  through the SAME pipeline → reports/eval-YYYYMMDD.md (VUS-PR main, PA-F1
  explicitly labelled control, trivial baselines included).
- tests: 45 new (parse 13, metrics 12, judge 12, baselines 8). 145 passing.
- Smoke: run_eval on 40 samples produces valid markdown; PA-F1≈1.0 vs
  VUS-PR≈0.35 for all_report demonstrates why PA must not be the headline.

tests/test_qa_judge.py

@@ -0,0 +1,105 @@
+"""Tests for eval/qa_judge.py (T5.3)."""
+import json
+
+import pytest
+
+from tsmm.eval.qa_judge import (
+    RuleJudge,
+    rule_score_describe,
+    rule_score_anomaly,
+    rule_score_forecast,
+)
+
+
+class TestDescribeRule:
+    def test_numerical_within_tolerance(self):
+        # predicted mean within 5% of reference → 1.0
+        out = rule_score_describe(
+            pred='{"mean": 50.0, "std": 2.0}',
+            ref={"mean": 50.5, "std": 2.1},
+            rtol=0.05,
+        )
+        assert out["score"] == 1.0
+        assert out["parsed"] is True
+
+    def test_outside_tolerance(self):
+        out = rule_score_describe(
+            pred='{"mean": 80.0}',
+            ref={"mean": 50.0},
+            rtol=0.05,
+        )
+        assert out["score"] == 0.0
+        assert out["parsed"] is True
+
+    def test_unparseable(self):
+        out = rule_score_describe(pred="the mean is around 50", ref={"mean": 50.0})
+        assert out["parsed"] is False
+        assert out["score"] == 0.0
+
+
+class TestAnomalyRule:
+    def test_exact_match(self):
+        pred = '{"segments": [[10, 20]]}'
+        ref_segs = [(10, 20)]
+        out = rule_score_anomaly(pred, ref_segs, T=50)
+        assert out["score"] == 1.0
+        assert out["parsed"] is True
+
+    def test_iou_partial(self):
+        pred = '{"segments": [[10, 30]]}'
+        ref_segs = [(20, 40)]
+        out = rule_score_anomaly(pred, ref_segs, T=50)
+        assert 0.0 < out["score"] < 1.0
+
+    def test_no_overlap(self):
+        pred = '{"segments": [[0, 5]]}'
+        ref_segs = [(20, 40)]
+        out = rule_score_anomaly(pred, ref_segs, T=50)
+        assert out["score"] == 0.0
+
+
+class TestForecastRule:
+    def test_within_tolerance(self):
+        pred = '{"forecast": [1.0, 2.0, 3.0]}'
+        ref = [1.05, 1.95, 3.1]
+        out = rule_score_forecast(pred, ref, rtol=0.1)
+        assert out["score"] == 1.0
+        assert out["parsed"] is True
+
+    def test_one_off(self):
+        pred = '{"forecast": [1.0, 2.0, 9.0]}'
+        ref = [1.0, 2.0, 3.0]
+        out = rule_score_forecast(pred, ref, rtol=0.1)
+        assert out["score"] < 1.0
+
+
+class TestRuleJudgeDispatch:
+    def test_judge_anomaly(self):
+        judge = RuleJudge()
+        out = judge.judge("anomaly", '{"segments": [[5, 8]]}', ref_segs=[(5, 8)], T=20)
+        assert out["score"] == 1.0
+        assert out["track"] == "rule"
+
+    def test_judge_unknown_category_skips(self):
+        judge = RuleJudge()
+        out = judge.judge("root_cause", "some text answer", ref_answer="some text answer")
+        assert out["track"] == "skip"
+        assert out["score"] is None
+
+
+class TestLLMJudgeStub:
+    def test_stub_returns_deterministic(self):
+        from tsmm.eval.qa_judge import LLMJudge
+        judge = LLMJudge(backend="stub")
+        s1 = judge.score("Q?", "ref", "pred")
+        s2 = judge.score("Q?", "ref", "pred")
+        assert isinstance(s1, dict)
+        assert "score" in s1 and 0 <= s1["score"] <= 5
+        assert s1 == s2  # deterministic stub
+
+    def test_stub_rewards_exact_match(self):
+        from tsmm.eval.qa_judge import LLMJudge
+        judge = LLMJudge(backend="stub")
+        same = judge.score("Q?", "正常", "正常")["score"]
+        diff = judge.score("Q?", "正常", "完全不同的乱码回答xyz")["score"]
+        assert same >= diff