feat(eval): Markdown report builder with matplotlib plots

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/test_eval_metrics.py

@@ -111,3 +111,45 @@ class TestKlDivergence:
         y = np.array([10.0, 10.1, 10.2, 10.3, 10.4])
         kl = kl_divergence_histograms(x, y, bins=10)
         assert np.isfinite(kl)
+
+
+class TestReportGeneration:
+    def test_generates_report_md(self, tmp_path):
+        """Smoke test: build_report writes an MD file with all expected sections."""
+        from ai_mouse.eval.report import build_report
+
+        # Synthetic generated traces (3 traces, 50 points each)
+        rng = np.random.default_rng(0)
+        gen_traces = []
+        for _ in range(3):
+            xs = np.cumsum(rng.uniform(0, 5, 50))
+            ys = np.cumsum(rng.uniform(-1, 1, 50))
+            ts = np.cumsum(rng.uniform(5, 20, 50))
+            gen_traces.append({"xs": xs, "ys": ys, "ts": ts})
+
+        # Synthetic reference
+        ref_traces = []
+        for _ in range(5):
+            xs = np.cumsum(rng.uniform(0, 5, 50))
+            ys = np.cumsum(rng.uniform(-1, 1, 50))
+            ts = np.cumsum(rng.uniform(5, 20, 50))
+            ref_traces.append({"xs": xs, "ys": ys, "ts": ts})
+
+        out_md = tmp_path / "report.md"
+        build_report(
+            generated_traces=gen_traces,
+            reference_traces=ref_traces,
+            output_md=out_md,
+            tag="smoke-test",
+            model_dir="/fake/model/dir",
+        )
+        assert out_md.exists()
+        content = out_md.read_text(encoding="utf-8")
+        assert "# Eval Report" in content
+        assert "smoke-test" in content
+        assert "速度" in content or "speed" in content.lower()
+        assert "FFT" in content.upper()
+        # PNG plots should exist next to MD
+        plot_dir = tmp_path / "plots"
+        assert plot_dir.exists()
+        assert any(plot_dir.iterdir())