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_ts_metrics.py

@@ -0,0 +1,109 @@
+"""Tests for eval/ts_metrics.py (T5.2)."""
+import numpy as np
+import pytest
+
+from tsmm.eval.ts_metrics import (
+    affiliation_f1,
+    auc_pr,
+    point_f1,
+    point_f1_with_pa,
+    vus_pr,
+)
+
+
+def labels(segs, T=100):
+    y = np.zeros(T, dtype=int)
+    for a, b in segs:
+        y[a:b + 1] = 1
+    return y
+
+
+class TestPointF1:
+    def test_perfect(self):
+        y = labels([(20, 40)], T=100)
+        s = np.zeros(100); s[20:41] = 1.0
+        f1, prec, rec = point_f1(s, y)
+        assert f1 == pytest.approx(1.0, abs=1e-6)
+
+    def test_no_overlap(self):
+        y = labels([(20, 40)])
+        s = np.zeros(100); s[60:70] = 1.0
+        f1, _, _ = point_f1(s, y)
+        assert f1 == pytest.approx(0.0, abs=1e-6)
+
+    def test_partial(self):
+        y = labels([(20, 40)])
+        s = np.zeros(100); s[30:41] = 0.9
+        f1, prec, rec = point_f1(s, y, threshold=0.5)
+        # predicted 11 anomalous all in true region: precision 1, recall 11/21
+        assert prec == pytest.approx(1.0, abs=1e-6)
+        assert rec == pytest.approx(11 / 21, abs=1e-3)
+
+
+class TestAUCPR:
+    def test_perfect_ranking(self):
+        y = labels([(10, 20)])
+        s = np.zeros(100); s[10:21] = 1.0
+        assert auc_pr(s, y) == pytest.approx(1.0, abs=1e-6)
+
+    def test_inverse_ranking_low(self):
+        y = labels([(10, 20)])
+        s = np.ones(100); s[10:21] = 0.0  # anomalies score LOW
+        assert auc_pr(s, y) < 0.5
+
+
+class TestPAF1:
+    def test_pa_inflates(self):
+        # PA: if ANY predicted point is in the true anomaly, the whole segment
+        # counts as caught → much higher F1 than point-wise
+        y = labels([(20, 40)])
+        s = np.zeros(100); s[40] = 1.0  # single overlap point
+        f1_pa, _, _ = point_f1_with_pa(s, y)
+        f1_pt, _, _ = point_f1(s, y)
+        assert f1_pa > f1_pt
+
+
+class TestAffiliationF1:
+    def test_perfect(self):
+        y = labels([(20, 40)])
+        s = np.zeros(100); s[20:41] = 1.0
+        f1, _, _ = affiliation_f1(s, y)
+        assert f1 == pytest.approx(1.0, abs=1e-6)
+
+    def test_far_predictions_lower(self):
+        y = labels([(20, 40)])
+        s_near = np.zeros(100); s_near[41:45] = 1.0
+        s_far = np.zeros(100); s_far[90:95] = 1.0
+        f1_near, _, _ = affiliation_f1(s_near, y)
+        f1_far, _, _ = affiliation_f1(s_far, y)
+        assert f1_near > f1_far
+
+
+class TestVUSPR:
+    def test_perfect_high(self):
+        y = labels([(20, 40)])
+        s = np.zeros(100); s[20:41] = 1.0
+        v = vus_pr(s, y)
+        assert v == pytest.approx(1.0, abs=1e-3)
+
+    def test_random_scores_moderate(self):
+        rng = np.random.default_rng(0)
+        y = labels([(20, 40)])
+        s = rng.random(100)
+        v = vus_pr(s, y)
+        # random ranking → VUS-PR around the anomaly prevalence (~0.21)
+        assert 0.0 < v < 0.6
+
+    def test_all_report_not_inflated(self):
+        # spec REQUIREMENT: "全报异常" trivial baseline must NOT have inflated VUS-PR
+        y = labels([(20, 40)], T=100)
+        s = np.ones(100)  # report everything as anomalous
+        v = vus_pr(s, y)
+        # prevalence = 21/100; all-ones gives AUC-PR == prevalence everywhere
+        assert v == pytest.approx(21 / 100, abs=1e-3)
+
+    def test_returns_scalar(self):
+        y = labels([(5, 10)])
+        s = np.random.default_rng(1).random(100)
+        v = vus_pr(s, y)
+        assert np.isscalar(v) or v.shape == ()