feat(provenance): govern source snapshots and data inputs

backend/app/services/demo_workflow_service.py

@@ -12,6 +12,7 @@ from sqlalchemy.orm import Session
 
 from app.models import Area, Dataset, DatasetVersion, Metric, Project, QualityCheck
 from app.schemas.demo import DemoWorkflowResponse
+from app.services.derived_dataset_governance_service import DerivedDatasetGovernanceService
 from app.services.geojson_service import parse_geojson_payload
 from app.services.qa_service import QaService
 from app.services.quality_service import QualityService
@@ -30,17 +31,17 @@ class DemoWorkflowService:
     EXPECTED_METRICS_FILENAME = "expected_qa_metrics.json"
 
     @staticmethod
-    def _add_initial_version(db: Session, dataset: Dataset) -> None:
-        db.add(
-            DatasetVersion(
-                dataset_id=dataset.id,
-                version=1,
-                storage_path=dataset.storage_path,
-                checksum_sha256=dataset.checksum_sha256,
-                source_metadata=dataset.source_metadata,
-                provenance_metadata=dataset.provenance_metadata,
-            )
+    def _add_initial_version(db: Session, dataset: Dataset) -> DatasetVersion:
+        version = DatasetVersion(
+            dataset_id=dataset.id,
+            version=1,
+            storage_path=dataset.storage_path,
+            checksum_sha256=dataset.checksum_sha256,
+            source_metadata=dataset.source_metadata,
+            provenance_metadata=dataset.provenance_metadata,
         )
+        db.add(version)
+        return version
 
     @staticmethod
     def _repo_root() -> Path:
@@ -233,24 +234,34 @@ class DemoWorkflowService:
             crs=metadata.get("crs"),
             bounds_json=metadata.get("bounds_json"),
             metadata_json=metadata,
-            status="ready",
+            status="validating",
         )
         db.add(dataset)
-        DemoWorkflowService._add_initial_version(db, dataset)
+        version = DemoWorkflowService._add_initial_version(db, dataset)
+        is_ready = DerivedDatasetGovernanceService.govern_vector(
+            db,
+            dataset=dataset,
+            dataset_version=version,
+            feature_collection=payload,
+            source_key="fixture",
+            operation="demo.fixture_vector",
+            operation_parameters={"fixture_name": filename, "role": role},
+        )
+        if is_ready:
+            VectorFeatureService.persist_geojson_features(
+                db=db,
+                dataset_id=dataset.id,
+                payload=payload,
+                feature_class=reference_layer_name or "building",
+                commit=False,
+            )
         db.commit()
         db.refresh(dataset)
-        VectorFeatureService.persist_geojson_features(
-            db=db,
-            dataset_id=dataset.id,
-            payload=payload,
-            feature_class=reference_layer_name or "building",
-        )
         return dataset
 
     @staticmethod
     def _create_demo_raster_bytes() -> bytes:
         numpy = importlib.import_module("numpy")
-        rasterio = importlib.import_module("rasterio")
         rasterio_io = importlib.import_module("rasterio.io")
         rasterio_transform = importlib.import_module("rasterio.transform")
 
@@ -318,10 +329,19 @@ class DemoWorkflowService:
             crs=metadata.get("crs"),
             bounds_json=bounds_json,
             metadata_json=metadata,
-            status="ready",
+            status="validating",
         )
         db.add(dataset)
-        DemoWorkflowService._add_initial_version(db, dataset)
+        version = DemoWorkflowService._add_initial_version(db, dataset)
+        DerivedDatasetGovernanceService.govern_raster(
+            db,
+            dataset=dataset,
+            dataset_version=version,
+            raster_metadata=metadata,
+            source_key="fixture",
+            operation="demo.fixture_raster",
+            operation_parameters={"fixture_name": DemoWorkflowService.RASTER_FILENAME},
+        )
         db.commit()
         db.refresh(dataset)
         return dataset