feat: complete catalog-driven preprocessing

harness/tests/test_qdrant_cli_commands.py

@@ -32,6 +32,9 @@ class _FakeVectorStore:
     def existing_hashes(self, collection, kinds):
         return {}
 
+    def delete_kinds(self, collection, kinds):
+        return 0
+
     def upsert(self, collection, records):
         self.upserts.append((collection, records))
         return len(records)
@@ -58,6 +61,7 @@ roots:
   sessions: {tmp_path / 'sessions'}
   artifacts: {tmp_path / 'artifacts'}
   indexes: {tmp_path / 'indexes'}
+  catalog_metadata_snapshot: {tmp_path / 'catalog-metadata.json'}
 embeddings:
   provider: ollama_internal
   base_url: http://embedding:11434
@@ -68,22 +72,34 @@ embeddings:
     return cfg
 
 
-def _write_schema_artifacts(tmp_path: Path) -> None:
-    (tmp_path / "artifacts" / "mschema").mkdir(parents=True, exist_ok=True)
-    (tmp_path / "artifacts" / "mschema" / "physical.yaml").write_text(
-        """
-database: analytics
-schema: mart
-introspected_at: 2026-01-01T00:00:00+00:00
-tables:
-  fact_patient:
-    comment: Patients
-    columns:
-      id:
-        type: bigint
-"""
-    )
-    (tmp_path / "artifacts" / "mschema" / "annotations.yaml").write_text("tables: {}\n")
+def _write_catalog_snapshot(tmp_path: Path) -> None:
+    (tmp_path / "catalog-metadata.json").write_text(json.dumps({
+        "schemaVersion": 1,
+        "workspaceId": "psd-clinical",
+        "databaseId": "db-1",
+        "databaseName": "analytics",
+        "schemaName": "mart",
+        "metadataContentRevision": 1,
+        "tables": [{
+            "id": "table-1",
+            "name": "fact_patient",
+            "description": "Patients",
+            "descriptionSource": "curated",
+            "columns": [{
+                "id": "column-1",
+                "name": "id",
+                "ordinalPosition": 1,
+                "dataType": "bigint",
+                "isNullable": False,
+                "defaultExpression": None,
+                "primaryKeyPosition": 1,
+                "sensitive": False,
+                "description": None,
+                "descriptionSource": None,
+            }],
+        }],
+        "relationships": [],
+    }))
 
 
 def _memory_record() -> MemoryRecord:
@@ -104,7 +120,7 @@ def _memory_record() -> MemoryRecord:
 
 def test_vector_index_schema_accepts_qdrant_only_runtime_config(tmp_path, monkeypatch):
     cfg = _qdrant_runtime_config(tmp_path)
-    _write_schema_artifacts(tmp_path)
+    _write_catalog_snapshot(tmp_path)
     store = _FakeVectorStore()
 
     monkeypatch.setattr("tht.adapters.factory.build_vector_store", lambda cfg, require_write: store)
@@ -118,7 +134,7 @@ def test_vector_index_schema_accepts_qdrant_only_runtime_config(tmp_path, monkey
 
 def test_vector_index_schema_json_is_pristine_and_reports_artifacts(tmp_path, monkeypatch):
     cfg = _qdrant_runtime_config(tmp_path)
-    _write_schema_artifacts(tmp_path)
+    _write_catalog_snapshot(tmp_path)
     store = _FakeVectorStore()
 
     monkeypatch.setattr("tht.adapters.factory.build_vector_store", lambda cfg, require_write: store)
@@ -131,12 +147,8 @@ def test_vector_index_schema_json_is_pristine_and_reports_artifacts(tmp_path, mo
     assert json.loads(response.stdout) == {
         "artifactIdentities": [
             {
-                "digest": _sha_file(tmp_path / "artifacts" / "mschema" / "annotations.yaml"),
-                "kind": "schema_annotations",
-            },
-            {
-                "digest": _sha_file(tmp_path / "artifacts" / "mschema" / "physical.yaml"),
-                "kind": "physical_schema",
+                "digest": _sha_file(tmp_path / "catalog-metadata.json"),
+                "kind": "catalog_metadata_snapshot",
             },
         ],
         "code": "ok",
@@ -146,6 +158,7 @@ def test_vector_index_schema_json_is_pristine_and_reports_artifacts(tmp_path, mo
             "columns": 1,
             "deleted": 0,
             "records": 2,
+            "relationships": 0,
             "tables": 1,
             "unchanged": 0,
             "updated": 0,
@@ -160,7 +173,7 @@ def test_vector_index_schema_json_is_pristine_and_reports_artifacts(tmp_path, mo
 
 def test_vector_index_schema_json_failure_is_pristine(tmp_path, monkeypatch):
     cfg = _qdrant_runtime_config(tmp_path)
-    _write_schema_artifacts(tmp_path)
+    _write_catalog_snapshot(tmp_path)
 
     def boom(cfg, require_write):
         raise VectorStoreError("semantic_index_incompatible")