V4.2 Updated what ai_raw_response data is being captured. The changes were more extensive than I expected.

tests/test_db.py

@@ -12,6 +12,7 @@ from transcription.db import create_all
 from transcription.db import dispose_database_runtime
 from transcription.db import initialize_database_runtime
 from transcription.db import session_scope
+from transcription.db import upgrade_schema
 from transcription.db.models import DocumentType
 from transcription.db.models import PersonRole
 
@@ -38,6 +39,8 @@ async def test_create_all_creates_expected_tables(tmp_path):
         assert "job" in table_names
         assert "source" in table_names
         assert "job_source" in table_names
+        assert "execution_attempt" in table_names
+        assert "processing_artifact" in table_names
         assert "revision" not in table_names
     finally:
         await dispose_database_runtime()
@@ -112,6 +115,55 @@ async def test_create_all_upgrades_existing_person_table_for_family_search(tmp_p
         await dispose_database_runtime()
 
 
+@pytest.mark.asyncio
+async def test_v42_upgrade_adds_evidence_tables_without_rewriting_legacy_snapshot(tmp_path):
+    settings = Settings(
+        openrouter_api_key="test-key",
+        database=SqliteSettings(path=str(tmp_path / "v42-upgrade.db")),
+        environment="test",
+    )
+    runtime = initialize_database_runtime(settings=settings)
+
+    try:
+        async with runtime.engine.begin() as connection:
+            await connection.execute(text("CREATE TABLE job (id CHAR(32) PRIMARY KEY NOT NULL)"))
+            await connection.execute(text("CREATE TABLE source (id CHAR(32) PRIMARY KEY NOT NULL)"))
+            await connection.execute(
+                text(
+                    "CREATE TABLE job_source ("
+                    "id CHAR(32) PRIMARY KEY NOT NULL, "
+                    "job_id CHAR(32) NOT NULL, "
+                    "source_id CHAR(32) NOT NULL, "
+                    "raw_api_response JSON"
+                    ")"
+                )
+            )
+            await connection.execute(text("INSERT INTO job (id) VALUES ('job-1')"))
+            await connection.execute(text("INSERT INTO source (id) VALUES ('source-1')"))
+            await connection.execute(
+                text(
+                    "INSERT INTO job_source (id, job_id, source_id, raw_api_response) "
+                    "VALUES ('link-1', 'job-1', 'source-1', :snapshot)"
+                ),
+                {"snapshot": '{"legacy":true}'},
+            )
+
+        await upgrade_schema(engine=runtime.engine)
+        await upgrade_schema(engine=runtime.engine)
+        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'")
+                )
+            ).scalar_one()
+
+        assert {"execution_attempt", "processing_artifact"}.issubset(table_names)
+        assert "legacy" in legacy_snapshot
+    finally:
+        await dispose_database_runtime()
+
+
 def test_bootstrap_policy_production_defaults_false():
     settings = Settings(openrouter_api_key="test-key", environment="production")
     assert settings.should_bootstrap_schema is False