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)}