V4.3 revision to Document Types

tests/test_db.py

@@ -1,5 +1,7 @@
 """Tests for the database runtime and V2 schema bootstrap behavior."""
 
+from uuid import uuid4
+
 import pytest
 from sqlalchemy import inspect
 from sqlalchemy import text
@@ -97,10 +99,10 @@ async def test_create_all_seeds_default_registry_rows(tmp_path):
         await create_all(engine=runtime.engine)
         async with AsyncSession(runtime.engine, expire_on_commit=False) as session:
             role_codes = set((await session.exec(select(PersonRole.code))).all())
-            type_codes = set((await session.exec(select(DocumentType.code))).all())
+            type_labels = set((await session.exec(select(DocumentType.label))).all())
 
         assert {"author", "recipient", "mentioned"}.issubset(role_codes)
-        assert {"letter", "record", "memo"}.issubset(type_codes)
+        assert {"Letter", "Record", "Memo"}.issubset(type_labels)
     finally:
         await dispose_database_runtime()
 
@@ -130,9 +132,94 @@ async def test_create_all_upgrades_existing_person_table_for_family_search(tmp_p
             )
 
         assert "family_search_id" in columns
-        assert any(
-            index["column_names"] == ["family_search_id"] and index["unique"] for index in indexes
-        )
+        assert any(index["column_names"] == ["family_search_id"] and index["unique"] for index in indexes)
+    finally:
+        await dispose_database_runtime()
+
+
+@pytest.mark.asyncio
+async def test_upgrade_migrates_document_types_to_uuid_only_identity(tmp_path):
+    settings = Settings(
+        openrouter_api_key="test-key",
+        database=SqliteSettings(path=str(tmp_path / "type-upgrade.db")),
+        environment="test",
+    )
+    runtime = initialize_database_runtime(settings=settings)
+    type_id = uuid4().hex
+    document_id = uuid4().hex
+
+    try:
+        async with runtime.engine.begin() as connection:
+            await connection.execute(
+                text(
+                    "CREATE TABLE document_type ("
+                    "id CHAR(32) PRIMARY KEY NOT NULL, "
+                    "code VARCHAR NOT NULL, "
+                    "label VARCHAR NOT NULL, "
+                    "is_active BOOLEAN NOT NULL, "
+                    "sort_order INTEGER NOT NULL, "
+                    "created_at DATETIME NOT NULL, "
+                    "updated_at DATETIME NOT NULL"
+                    ")"
+                )
+            )
+            await connection.execute(text("CREATE UNIQUE INDEX ix_document_type_code ON document_type (code)"))
+            await connection.execute(
+                text(
+                    "CREATE TABLE document ("
+                    "id CHAR(32) PRIMARY KEY NOT NULL, "
+                    "name VARCHAR NOT NULL, "
+                    "document_type_id CHAR(32), "
+                    "document_type VARCHAR, "
+                    "document_date DATE, "
+                    "document_date_raw VARCHAR, "
+                    "location_created VARCHAR, "
+                    "notes VARCHAR, "
+                    "archive_identifier VARCHAR, "
+                    "created_at DATETIME NOT NULL, "
+                    "updated_at DATETIME NOT NULL"
+                    ")"
+                )
+            )
+            await connection.execute(
+                text(
+                    "INSERT INTO document_type "
+                    "(id, code, label, is_active, sort_order, created_at, updated_at) "
+                    "VALUES (:id, 'letter', 'Letter', 1, 0, CURRENT_TIMESTAMP, CURRENT_TIMESTAMP)"
+                ),
+                {"id": type_id},
+            )
+            await connection.execute(
+                text(
+                    "INSERT INTO document "
+                    "(id, name, document_type_id, document_type, created_at, updated_at) "
+                    "VALUES (:id, 'Legacy Letter', NULL, 'letter', CURRENT_TIMESTAMP, CURRENT_TIMESTAMP)"
+                ),
+                {"id": document_id},
+            )
+
+        await upgrade_schema(engine=runtime.engine)
+
+        async with runtime.engine.connect() as connection:
+            type_columns, document_columns, migrated_type_id, normalized_label = await connection.run_sync(
+                lambda sync_connection: (
+                    {column["name"] for column in inspect(sync_connection).get_columns("document_type")},
+                    {column["name"] for column in inspect(sync_connection).get_columns("document")},
+                    sync_connection.execute(
+                        text("SELECT document_type_id FROM document WHERE id = :id"),
+                        {"id": document_id},
+                    ).scalar_one(),
+                    sync_connection.execute(
+                        text("SELECT normalized_label FROM document_type WHERE id = :id"),
+                        {"id": type_id},
+                    ).scalar_one(),
+                )
+            )
+
+        assert {"code", "sort_order"}.isdisjoint(type_columns)
+        assert "document_type" not in document_columns
+        assert migrated_type_id == type_id
+        assert normalized_label == "letter"
     finally:
         await dispose_database_runtime()
 
@@ -175,9 +262,7 @@ async def test_v42_upgrade_adds_evidence_tables_without_rewriting_legacy_snapsho
         async with runtime.engine.connect() as connection:
             table_names = set(await connection.run_sync(lambda c: inspect(c).get_table_names()))
             legacy_snapshot = (
-                await connection.execute(
-                    text("SELECT raw_api_response FROM job_source WHERE id = 'link-1'")
-                )
+                await connection.execute(text("SELECT raw_api_response FROM job_source WHERE id = 'link-1'"))
             ).scalar_one()
 
         assert {"execution_attempt", "processing_artifact"}.issubset(table_names)