feat(provenance): govern source snapshots and data inputs

backend/tests/test_sprint9_segmentation_foundation.py

@@ -10,7 +10,18 @@ from shapely.geometry import MultiPolygon, box, mapping
 
 from app.db.session import get_db
 from app.main import app
-from app.models import AnalysisRun, Dataset, Job, Metric, Project, QualityCheck, Segmentation, VectorFeature
+from app.models import (
+    AnalysisRun,
+    Dataset,
+    Job,
+    Metric,
+    Project,
+    QualityCheck,
+    Segmentation,
+    SourceRegistry,
+    SourceSnapshot,
+    VectorFeature,
+)
 from app.services.model_registry_service import ModelRegistryService
 from app.services.segmentation_service import SegmentationService
 
@@ -75,7 +86,7 @@ def _project_and_dataset(dataset_type: str = "raster"):
         project_id=project_id,
         name="source.tif",
         dataset_type=dataset_type,
-        source="user_upload",
+        source="test",
         storage_path="storage/uploads/source.tif",
     )
     db = FakeSession(objects={(Project, project_id): project, (Dataset, dataset_id): dataset})
@@ -105,6 +116,47 @@ def _segmentation(project_id, dataset_id, analysis_run_id, class_name="vegetatio
     )
 
 
+def _authoritative_reference(dataset: Dataset) -> Dataset:
+    """Model segmentation QA references as governed authoritative GRB evidence."""
+
+    source_id = uuid4()
+    snapshot_id = uuid4()
+    checksum = "a" * 64
+    source = SourceRegistry(
+        id=source_id,
+        source_key="grb",
+        display_name="GRB segmentation QA fixture",
+        classification="authoritative",
+        authority_name="Digitaal Vlaanderen",
+        authority_scope_json={"zone": "Flanders"},
+        usage_policy_json={"ground_truth_allowed": True, "validation_authority": {"building_validation": "primary"}},
+    )
+    snapshot = SourceSnapshot(
+        id=snapshot_id,
+        source_registry_id=source_id,
+        snapshot_key=f"segmentation-qa-{dataset.id}",
+        checksum_sha256=checksum,
+        ingest_status="ingested",
+        freshness_status="current",
+    )
+    dataset.source = "grb"
+    dataset.source_name = "grb"
+    dataset.dataset_role = "reference"
+    dataset.status = "ready"
+    dataset.checksum_sha256 = checksum
+    dataset.source_registry_id = source_id
+    dataset.source_snapshot_id = snapshot_id
+    dataset.data_contract_key = "geointel.vector.geojson"
+    dataset.data_contract_version = "1.0.0"
+    dataset.validation_status = "passed"
+    dataset.provenance_status = "complete"
+    dataset.lineage_status = "complete"
+    dataset.quarantine_status = "not_quarantined"
+    dataset.source_registry = source
+    dataset.source_snapshot = snapshot
+    return dataset
+
+
 def test_model_registry_returns_segmentation_states() -> None:
     models = {model.model_id: model for model in ModelRegistryService.list_model_capabilities(task_type="segmentation")}
 
@@ -265,14 +317,14 @@ def test_segmentation_qa_persists_quality_check_and_metrics() -> None:
     reference_dataset_id = uuid4()
     analysis_run_id = uuid4()
     segmentation = _segmentation(project_id, dataset_id, analysis_run_id, geom=box(0, 0, 1, 1))
-    reference_dataset = Dataset(
+    reference_dataset = _authoritative_reference(Dataset(
         id=reference_dataset_id,
         project_id=project_id,
         name="reference.geojson",
         dataset_type="vector",
-        source="manual",
+        source="test",
         dataset_role="reference",
-    )
+    ))
     reference_feature = VectorFeature(
         id=uuid4(),
         dataset_id=reference_dataset_id,
@@ -282,6 +334,7 @@ def test_segmentation_qa_persists_quality_check_and_metrics() -> None:
     db = FakeSession(
         objects={
             (AnalysisRun, analysis_run_id): AnalysisRun(id=analysis_run_id, project_id=project_id, dataset_id=dataset_id, analysis_type="segmentation", status="success", parameters_json={}),
+            (Dataset, dataset_id): Dataset(id=dataset_id, project_id=project_id, name="fixture.tif", dataset_type="raster", source="test"),
             (Dataset, reference_dataset_id): reference_dataset,
         },
         query_rows={Segmentation: [segmentation], VectorFeature: [reference_feature]},
@@ -318,14 +371,14 @@ def test_segmentation_qa_no_match_case_persists_zero_scores() -> None:
     reference_dataset_id = uuid4()
     analysis_run_id = uuid4()
     segmentation = _segmentation(project_id, dataset_id, analysis_run_id, geom=box(0, 0, 1, 1))
-    reference_dataset = Dataset(
+    reference_dataset = _authoritative_reference(Dataset(
         id=reference_dataset_id,
         project_id=project_id,
         name="reference.geojson",
         dataset_type="vector",
-        source="manual",
+        source="test",
         dataset_role="reference",
-    )
+    ))
     reference_feature = VectorFeature(
         id=uuid4(),
         dataset_id=reference_dataset_id,
@@ -335,6 +388,7 @@ def test_segmentation_qa_no_match_case_persists_zero_scores() -> None:
     db = FakeSession(
         objects={
             (AnalysisRun, analysis_run_id): AnalysisRun(id=analysis_run_id, project_id=project_id, dataset_id=dataset_id, analysis_type="segmentation", status="success", parameters_json={}),
+            (Dataset, dataset_id): Dataset(id=dataset_id, project_id=project_id, name="fixture.tif", dataset_type="raster", source="test"),
             (Dataset, reference_dataset_id): reference_dataset,
         },
         query_rows={Segmentation: [segmentation], VectorFeature: [reference_feature]},