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_baselines.py

@@ -0,0 +1,62 @@
+"""Tests for eval/baselines.py (T5.4)."""
+import numpy as np
+import pytest
+
+from tsmm.eval.baselines import (
+    RandomBaseline,
+    ConstantBaseline,
+    AllReportBaseline,
+    ts_to_text,
+)
+
+
+class TestTrivial:
+    def test_random_in_range_and_shape(self):
+        bl = RandomBaseline(seed=0)
+        scores = bl.score(T=100)
+        assert scores.shape == (100,)
+        assert scores.min() >= 0.0 and scores.max() <= 1.0
+
+    def test_random_reproducible(self):
+        a = RandomBaseline(seed=42).score(T=50)
+        b = RandomBaseline(seed=42).score(T=50)
+        assert np.allclose(a, b)
+
+    def test_constant_value(self):
+        bl = ConstantBaseline(value=0.3)
+        s = bl.score(T=10)
+        assert s.shape == (10,)
+        assert np.allclose(s, 0.3)
+
+    def test_all_report_is_all_ones(self):
+        bl = AllReportBaseline()
+        s = bl.score(T=8)
+        assert s.shape == (8,)
+        assert np.allclose(s, 1.0)
+
+    def test_all_report_vus_pr_not_inflated(self):
+        from tsmm.eval.ts_metrics import vus_pr
+        y = np.zeros(100, dtype=int); y[20:40] = 1
+        s = AllReportBaseline().score(T=100)
+        v = vus_pr(s, y)
+        assert v == pytest.approx(20 / 100, abs=1e-3)
+
+
+class TestTsToText:
+    def test_shape_and_content(self):
+        series = np.arange(12).reshape(4, 3).tolist()  # T=4, C=3
+        text = ts_to_text(series, max_points=12)
+        assert isinstance(text, str)
+        assert "0" in text
+
+    def test_truncates_long_series(self):
+        series = [[float(i)] for i in range(1000)]
+        text = ts_to_text(series, max_points=50)
+        # roughly bounded length
+        assert len(text) < 5000
+
+    def test_handles_nan(self):
+        import math
+        series = [[1.0], [float("nan")], [3.0]]
+        text = ts_to_text(series, max_points=10)
+        assert "nan" in text.lower() or "missing" in text.lower()