harden model registry persistence and evaluation

tests/ml/test_evaluation.py

@@ -21,13 +21,35 @@ def evaluator_factory() -> Evaluator:
 
 def test_evaluate_returns_report_with_metrics() -> None:
     evaluator = evaluator_factory()
-    report = evaluator.evaluate("artifact_v1", ["artifact_v1:sensor.kitchen:{'temperature': 21.0}", "artifact_v1:sensor.bedroom:{'temperature': 18.5}"])
+    report = evaluator.evaluate(
+        "artifact_v1",
+        [
+            "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
+            "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+        ],
+    )
     assert report.artifact_id == "artifact_v1"
     assert report.sample_size == 2
     assert {metric.name for metric in report.metrics} == {"coverage", "unknown_rate"}
+    assert next(metric.value for metric in report.metrics if metric.name == "coverage") == 1.0
 
 
 def test_evaluate_without_training_raises_value_error() -> None:
     evaluator = Evaluator(TrainingPipeline(FeatureStore()))
     with pytest.raises(ValueError):
-        evaluator.evaluate("artifact_v1", [])
+        evaluator.evaluate("artifact_v1", [])
+
+
+def test_coverage_is_bounded_and_requires_exact_sensor_match() -> None:
+    evaluator = evaluator_factory()
+    report = evaluator.evaluate(
+        "artifact_v1",
+        [
+            "artifact_v1:sensor.kitchen:{'note': 'sensor.bedroom'}",
+            "artifact_v1:sensor.kitchen_extra:{}",
+            "malformed",
+        ],
+    )
+
+    metrics = {metric.name: metric.value for metric in report.metrics}
+    assert metrics == {"coverage": pytest.approx(1 / 3), "unknown_rate": pytest.approx(2 / 3)}

tests/ml/test_model_registry.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+import json
+
+import pytest
+
+from app.ml.registry.model_registry import ModelRegistry
+from app.ml.training import TrainedArtifact
+
+
+def test_registry_loads_persisted_artifacts_after_restart(tmp_path) -> None:
+    registry = ModelRegistry(tmp_path)
+    artifact = TrainedArtifact("model-v1", ("sensor.kitchen", "sensor.bedroom"))
+    registry.register(artifact)
+
+    restarted = ModelRegistry(tmp_path)
+
+    assert restarted.load_artifact("model-v1") == artifact
+
+
+@pytest.mark.parametrize("artifact_id", ["../escape", "nested/model", "..", ""])
+def test_registry_rejects_unsafe_artifact_ids(tmp_path, artifact_id: str) -> None:
+    registry = ModelRegistry(tmp_path)
+
+    with pytest.raises(ValueError):
+        registry.register(TrainedArtifact(artifact_id, ("sensor.kitchen",)))
+
+    assert list(tmp_path.parent.glob("escape.json")) == []
+
+
+def test_registry_rejects_corrupt_persisted_artifact(tmp_path) -> None:
+    (tmp_path / "broken.json").write_text(
+        json.dumps({"artifact_id": "../broken", "supported_sensors": []}),
+        encoding="utf-8",
+    )
+
+    with pytest.raises(ValueError, match="broken.json"):
+        ModelRegistry(tmp_path)