Promote focused small-building detector

backend/tests/test_docker_runtime_config.py

@@ -58,14 +58,33 @@ def test_all_in_one_dockerfile_can_opt_into_ai_dependencies_without_base_install
 def test_all_in_one_dockerfile_copies_operator_scripts_for_runtime_use() -> None:
     dockerfile = (ROOT / "deploy" / "unraid" / "Dockerfile.all-in-one").read_text(encoding="utf-8")
 
-    assert "COPY scripts/prepare_operator_real_data_samples.py /app/scripts/prepare_operator_real_data_samples.py" in dockerfile
-    assert "COPY scripts/export_operator_yolo_tile_dataset.py /app/scripts/export_operator_yolo_tile_dataset.py" in dockerfile
-    assert "COPY scripts/audit_operator_yolo_dataset_quality.py /app/scripts/audit_operator_yolo_dataset_quality.py" in dockerfile
-    assert (
-        "COPY scripts/render_operator_yolo_label_qa_contact_sheets.py "
-        "/app/scripts/render_operator_yolo_label_qa_contact_sheets.py"
-    ) in dockerfile
-    assert "COPY scripts/train_operator_yolo_detector.sh /app/scripts/train_operator_yolo_detector.sh" in dockerfile
+    for line in dockerfile.splitlines():
+        if line.startswith("COPY scripts/"):
+            source_path = line.split()[1]
+            assert (ROOT / source_path).is_file()
+
+    required_runtime_scripts = {
+        "prepare_operator_real_data_samples.py",
+        "export_operator_yolo_tile_dataset.py",
+        "audit_operator_yolo_dataset_quality.py",
+        "render_operator_yolo_label_qa_contact_sheets.py",
+        "train_operator_yolo_detector.sh",
+        "verify_real_data_detection_qa_workflow.sh",
+        "run_detection_quality_matrix.sh",
+        "run_multi_sample_detection_quality_matrix.sh",
+        "export_detection_calibration_evidence.sh",
+        "assemble_detection_calibration_evidence_portfolio.sh",
+        "build_fixed_threshold_evidence_portfolio_inputs.py",
+        "audit_detection_false_negative_evidence.py",
+        "run_operator_hard_negative_detection_matrix.sh",
+        "run_background_corpus_split_matrix.sh",
+        "build_background_corpus_split_report.py",
+        "build_detection_model_promotion_report.py",
+        "run_split_background_promotion_workflow.sh",
+        "activate_promoted_yolo_candidate.py",
+    }
+    for script_name in required_runtime_scripts:
+        assert f"COPY scripts/{script_name} /app/scripts/{script_name}" in dockerfile
 
 
 def test_all_in_one_dockerfile_copies_operator_scripts_after_dependency_install() -> None:

backend/tests/test_schema_model_field_warnings.py

@@ -0,0 +1,17 @@
+from pydantic import BaseModel
+
+from app.schemas import detection, segmentation
+
+
+def test_model_prefixed_api_fields_are_explicitly_supported() -> None:
+    schemas = [
+        value
+        for module in (detection, segmentation)
+        for value in vars(module).values()
+        if isinstance(value, type)
+        and issubclass(value, BaseModel)
+        and any(field_name.startswith("model_") for field_name in value.model_fields)
+    ]
+
+    assert schemas
+    assert all(schema.model_config.get("protected_namespaces") == () for schema in schemas)

backend/tests/test_sprint130_operator_yolo_tile_dataset.py

@@ -69,6 +69,7 @@ def test_operator_yolo_tile_dataset_export_help_does_not_require_gis_dependencie
     assert "Export operator real-data samples to a tile-level YOLO detection dataset" in result.stdout
     assert "--tile-size" in result.stdout
     assert "--stride" in result.stdout
+    assert "--samples" in result.stdout
     assert "--negative-keep-ratio" in result.stdout
     assert "--min-label-visible-ratio" in result.stdout
     assert "--background-negative-repeat" in result.stdout
@@ -84,10 +85,19 @@ def test_default_validation_split_is_explicit_and_rejects_holdout_leakage() -> N
         {"sample_slug": "retie", "recommended_split": "val"},
         {"sample_slug": "westerlo", "recommended_split": "val"},
         {"sample_slug": "arendonk_heide", "recommended_split": "val"},
+        {"sample_slug": "vosselaar_center", "recommended_split": "val"},
+        {"sample_slug": "grobbendonk_center", "recommended_split": "val"},
     ]
 
     assert module.DEFAULT_VALIDATION_SAMPLE_SLUGS == frozenset(
-        {"turnhout", "retie", "westerlo", "arendonk_heide"}
+        {
+            "turnhout",
+            "retie",
+            "westerlo",
+            "arendonk_heide",
+            "vosselaar_center",
+            "grobbendonk_center",
+        }
     )
     assert module.validate_validation_split(
         samples,
@@ -100,6 +110,35 @@ def test_default_validation_split_is_explicit_and_rejects_holdout_leakage() -> N
         module.validate_validation_split(samples, {"turnhout", "missing"})
 
 
+def test_manifest_sample_selection_keeps_external_holdouts_out_of_targeted_dataset() -> None:
+    module = load_tile_exporter()
+    samples = [
+        {"sample_slug": "geel", "recommended_split": "train"},
+        {"sample_slug": "beerse_center", "recommended_split": "train"},
+        {"sample_slug": "vosselaar_center", "recommended_split": "val"},
+        {"sample_slug": "turnhout", "recommended_split": "val"},
+        {"sample_slug": "retie", "recommended_split": "val"},
+        {"sample_slug": "westerlo", "recommended_split": "val"},
+    ]
+
+    selected, excluded = module.select_manifest_samples(
+        samples,
+        {"geel", "beerse_center", "vosselaar_center"},
+    )
+
+    assert [sample["sample_slug"] for sample in selected] == [
+        "geel",
+        "beerse_center",
+        "vosselaar_center",
+    ]
+    assert excluded == ["retie", "turnhout", "westerlo"]
+    assert module.validate_validation_split(selected, {"vosselaar_center"}) == {
+        "vosselaar_center"
+    }
+    with pytest.raises(SystemExit, match="unknown samples"):
+        module.select_manifest_samples(samples, {"geel", "missing"})
+
+
 def test_validation_coverage_reports_holdouts_without_retained_tiles() -> None:
     module = load_tile_exporter()
     coverage = module.validation_sample_coverage(

backend/tests/test_sprint131_operator_sample_expansion.py

@@ -51,7 +51,7 @@ def test_operator_training_expansion_preserves_geographically_separate_holdouts(
     expected_holdouts = {"turnhout", "retie", "westerlo", "arendonk_heide"}
 
     assert module.TRAINING_EXPANSION_SAMPLE_SLUGS == frozenset(expected_expansion)
-    assert module.DEFAULT_VALIDATION_SAMPLE_SLUGS == frozenset(expected_holdouts)
+    assert expected_holdouts.issubset(module.DEFAULT_VALIDATION_SAMPLE_SLUGS)
     assert all(module.SAMPLES[slug].sample_role == "reference" for slug in expected_expansion)
     assert all(not module.SAMPLES[slug].allow_empty_reference for slug in expected_expansion)
     assert all(module.recommended_split_for_sample(module.SAMPLES[slug]) == "train" for slug in expected_expansion)
@@ -78,6 +78,51 @@ def test_operator_training_expansion_preserves_geographically_separate_holdouts(
         ) >= 2_000
 
 
+def test_small_building_expansion_has_separate_training_and_validation_centers() -> None:
+    module = load_sample_preparer()
+
+    expected_training = {
+        "beerse_center",
+        "rijkevorsel_center",
+        "hoogstraten_center",
+        "vorselaar_center",
+    }
+    expected_validation = {"vosselaar_center", "grobbendonk_center"}
+
+    assert module.SMALL_BUILDING_TRAINING_SAMPLE_SLUGS == frozenset(expected_training)
+    assert module.SMALL_BUILDING_VALIDATION_SAMPLE_SLUGS == frozenset(expected_validation)
+    assert expected_validation.issubset(module.DEFAULT_VALIDATION_SAMPLE_SLUGS)
+    assert all(module.SAMPLES[slug].sample_role == "reference" for slug in expected_training | expected_validation)
+    assert all(
+        module.recommended_split_for_sample(module.SAMPLES[slug]) == "train"
+        for slug in expected_training
+    )
+    assert all(
+        module.recommended_split_for_sample(module.SAMPLES[slug]) == "val"
+        for slug in expected_validation
+    )
+
+    def distance_m(left, right) -> float:
+        radius_m = 6_371_008.8
+        left_lat = math.radians(left.center_lat)
+        right_lat = math.radians(right.center_lat)
+        delta_lat = right_lat - left_lat
+        delta_lon = math.radians(right.center_lon - left.center_lon)
+        haversine = (
+            math.sin(delta_lat / 2) ** 2
+            + math.cos(left_lat) * math.cos(right_lat) * math.sin(delta_lon / 2) ** 2
+        )
+        return 2 * radius_m * math.asin(math.sqrt(haversine))
+
+    protected_holdouts = expected_validation | {"turnhout", "retie", "westerlo"}
+    for training_slug in expected_training:
+        training_sample = module.SAMPLES[training_slug]
+        assert min(
+            distance_m(training_sample, module.SAMPLES[holdout_slug])
+            for holdout_slug in protected_holdouts
+        ) >= 2_000
+
+
 def test_operator_background_candidates_are_unique_enough_for_hard_negative_training() -> None:
     module = load_sample_preparer()
 

backend/tests/test_sprint155_detection_operator_profiles.py

@@ -9,8 +9,10 @@ def test_detection_operator_profiles_define_explicit_yolo_candidates_and_promote
     source = profiles.read_text(encoding="utf-8")
 
     assert "DETECTION_OPERATOR_PROFILES" in source
+    assert "geointel-building-yolov8s-smallbld-minpx3-img640-ft30-pt" in source
     assert "geointel-building-yolov8s-aoi1024expandedminpx4vis035e50-pt" in source
     assert "geointel-building-yolov8s-aoi1024bg512r3e50-pt" in source
+    assert "small-building-balanced-review" in source
     assert "expanded-balanced-review" in source
     assert "conservative-review" in source
     assert "confidenceThreshold: 0.15" in source
@@ -18,10 +20,12 @@ def test_detection_operator_profiles_define_explicit_yolo_candidates_and_promote
     assert "defaultApproved: true" in source
     assert "promotionRecommendation: 'promote_candidate'" in source
     assert "positiveSampleCount: 7" in source
+    assert "f1: 0.5824578631584316" in source
     assert "f1: 0.5432865390636915" in source
     assert "maxBackgroundDetections: 0" in source
     assert "pure-empty gate passed" in source
-    assert "persistent small-building misses" in source
+    assert "1,571 fewer false negatives" in source
+    assert "higher false-positive review load" in source
 
 
 def test_detection_lab_surfaces_profiles_as_deliberate_operator_actions() -> None:

backend/tests/test_sprint170_detection_false_negative_audit.py

@@ -199,6 +199,28 @@ def test_false_negative_audit_finds_persistent_reference_misses(tmp_path: Path)
     assert candidate["false_negative_count"] == 1
     assert candidate["false_negative_rate"] == 1 / 3
     assert active["false_negative_area_m2"]["median"] > 0
+    assert sample["persistent_false_negative_area_m2"]["count"] == 1
+    assert sample["persistent_false_negative_area_m2"]["median"] > 0
+    assert sum(
+        bucket["count"] for bucket in sample["persistent_area_buckets"].values()
+    ) == 1
+    assert sum(
+        bucket["share"] for bucket in sample["persistent_area_buckets"].values()
+    ) == 1.0
+    persistent_evidence = json.loads(
+        (output_dir / "persistent_false_negatives.geojson").read_text(encoding="utf-8")
+    )
+    assert persistent_evidence["type"] == "FeatureCollection"
+    assert len(persistent_evidence["features"]) == 1
+    persistent_feature = persistent_evidence["features"][0]
+    assert persistent_feature["properties"]["qa_evidence_role"] == "persistent_false_negative"
+    assert persistent_feature["properties"]["sample_slug"] == "geel"
+    assert persistent_feature["properties"]["persistent_reference_id"] == "source:persistent-small"
+    assert persistent_feature["properties"]["area_m2"] > 0
+    assert persistent_feature["properties"]["area_bucket"] in sample["persistent_area_buckets"]
+    assert report["persistent_evidence_geojson_path"] == str(
+        output_dir / "persistent_false_negatives.geojson"
+    )
     assert report["recommendations"]
     assert (output_dir / "detection_false_negative_audit.md").is_file()