fix: make vector ingestion canonical and atomic

backend/app/services/dataset_service.py

@@ -376,32 +376,37 @@ class DatasetService:
             metadata_json=metadata,
             status=status,
         )
-        db.add(dataset)
-        db.add(
-            DatasetVersion(
-                dataset_id=dataset.id,
-                version=1,
-                storage_path=dataset.storage_path,
-                source_version=dataset.source_version,
-                observed_at=dataset.observed_at,
-                valid_from=dataset.valid_from,
-                valid_to=dataset.valid_to,
-                checksum_sha256=dataset.checksum_sha256,
-                source_metadata=dataset.source_metadata,
-                provenance_metadata=dataset.provenance_metadata,
-            )
-        )
-        db.commit()
-        db.refresh(dataset)
-
-        if canonical_type == "vector" and vector_payload is not None and status == "ready":
-            feature_class = reference_layer_name if normalized_role == "reference" else None
-            VectorFeatureService.persist_geojson_features(
-                db=db,
-                dataset_id=dataset.id,
-                payload=vector_payload,
-                feature_class=feature_class,
+        try:
+            db.add(dataset)
+            db.add(
+                DatasetVersion(
+                    dataset_id=dataset.id,
+                    version=1,
+                    storage_path=dataset.storage_path,
+                    source_version=dataset.source_version,
+                    observed_at=dataset.observed_at,
+                    valid_from=dataset.valid_from,
+                    valid_to=dataset.valid_to,
+                    checksum_sha256=dataset.checksum_sha256,
+                    source_metadata=dataset.source_metadata,
+                    provenance_metadata=dataset.provenance_metadata,
+                )
             )
+            if canonical_type == "vector" and vector_payload is not None and status == "ready":
+                feature_class = reference_layer_name if normalized_role == "reference" else None
+                VectorFeatureService.persist_geojson_features(
+                    db=db,
+                    dataset_id=dataset.id,
+                    payload=vector_payload,
+                    feature_class=feature_class,
+                    commit=False,
+                )
+            db.commit()
+            db.refresh(dataset)
+        except Exception:
+            db.rollback()
+            StorageService.remove_dataset_file(storage_info["storage_path"])
+            raise
 
         return DatasetService._to_response(dataset)
 

backend/app/services/geojson_service.py

@@ -32,6 +32,7 @@ def parse_geojson_payload(raw_text: str | dict[str, Any]) -> dict[str, Any]:
     geometry_types: set[str] = set()
     geometries = []
     invalid_features = 0
+    z_dimension_features = 0
     polygon_area_m2: float | None = None
     crs_assumed = None
     for feature in features:
@@ -49,6 +50,8 @@ def parse_geojson_payload(raw_text: str | dict[str, Any]) -> dict[str, Any]:
             if not geom.is_valid:
                 invalid_features += 1
                 raise ValueError("Invalid geometry remains after repair")
+        if geom.has_z:
+            z_dimension_features += 1
         geometry_types.add(str(geom.geom_type))
         geometries.append(geom)
 
@@ -85,6 +88,8 @@ def parse_geojson_payload(raw_text: str | dict[str, Any]) -> dict[str, Any]:
         "bounds_json": bounds_json,
         "approximate_area_m2": polygon_area_m2,
         "invalid_features": invalid_features,
+        "z_dimension_feature_count": z_dimension_features,
+        "canonical_storage_dimension": "2D",
         "crs": crs,
         "crs_assumed": crs_assumed,
         "extracted_at": datetime.now(timezone.utc).isoformat(),

backend/app/services/vector_feature_service.py

@@ -8,6 +8,7 @@ from geoalchemy2.shape import from_shape
 from geoalchemy2.shape import to_shape
 from shapely.geometry import mapping
 from shapely.geometry import shape
+from shapely.ops import transform as transform_geometry
 from shapely.validation import make_valid
 from sqlalchemy import Float, cast, func
 
@@ -265,6 +266,8 @@ class VectorFeatureService:
                 geometry = make_valid(geometry)
             if geometry.is_empty or not geometry.is_valid:
                 raise AppError(code="INVALID_GEOMETRY", message=f"Invalid feature geometry at index {index}", status_code=400)
+            if geometry.has_z:
+                geometry = transform_geometry(lambda x, y, z=None: (x, y), geometry)
 
             properties = feature.get("properties") if isinstance(feature.get("properties"), dict) else {}
             source_feature_id = feature.get("id")