Phase 1 - minor fix to Sources page

src/transcription/app.py

@@ -24,6 +24,7 @@ from .config import get_settings
 from .db import create_all
 from .db import dispose_database_runtime
 from .db import initialize_database_runtime
+from .db import normalize_legacy_status_spellings
 from .services import ServiceBundle
 from .ui import register_pages
 from .worker import worker_consumer_lifespan
@@ -42,6 +43,7 @@ async def _lifespan(app: FastAPI):
 
     if settings.should_bootstrap_schema:
         await create_all(engine=app.state.runtime.engine)
+    await normalize_legacy_status_spellings(engine=app.state.runtime.engine)
 
     settings.upload_dir.mkdir(parents=True, exist_ok=True)
     settings.prompt_dir.mkdir(parents=True, exist_ok=True)

src/transcription/db/__init__.py

@@ -1,4 +1,5 @@
 from .operations import create_all
+from .operations import normalize_legacy_status_spellings
 from .runtime import dispose_database_runtime
 from .runtime import initialize_database_runtime
 from .session import session_scope
@@ -8,6 +9,7 @@ __all__ = [
     "create_all",
     "dispose_database_runtime",
     "initialize_database_runtime",
+    "normalize_legacy_status_spellings",
     "session_scope",
     "transaction_scope",
 ]

src/transcription/db/operations.py

@@ -2,6 +2,8 @@ from __future__ import annotations
 
 import logging
 
+from sqlalchemy import inspect as sqlalchemy_inspect
+from sqlalchemy import text
 from sqlalchemy.ext.asyncio import AsyncEngine
 from sqlalchemy.ext.asyncio import async_sessionmaker
 from sqlmodel import SQLModel
@@ -10,6 +12,7 @@ from sqlmodel.ext.asyncio.session import AsyncSession
 
 from .engine import resolve_engine
 from .models import DocumentType
+from .models import JobSourceStatus
 from .models import PersonRole
 from .registries import BUILT_IN_DOCUMENT_TYPES
 from .registries import BUILT_IN_PERSON_ROLES
@@ -29,6 +32,47 @@ async def create_all(*, engine: AsyncEngine | None = None) -> None:
     logger.debug("Database schema bootstrap complete for database_url=%s", active_engine.url)
 
 
+async def normalize_legacy_status_spellings(*, engine: AsyncEngine | None = None) -> int:
+    """Normalize legacy enum-name spellings to canonical enum values.
+
+    Historical databases may carry ``TRANSCRIBED``/``FAILED``-style enum *names*
+    in ``job_source.status`` or ``execution_attempt.status``. Runtime models
+    expect canonical lowercase values, so stale rows must be normalized before
+    ORM reads.
+    """
+    active_engine = engine or resolve_engine()
+    if not hasattr(active_engine, "begin"):
+        return 0
+    replacements = {
+        status.name: status.value
+        for status in JobSourceStatus
+        if status.name != status.value
+    }
+
+    def _normalize(sync_connection) -> int:
+        inspector = sqlalchemy_inspect(sync_connection)
+        table_names = set(inspector.get_table_names())
+        if not table_names:
+            return 0
+        fixed = 0
+        for table_name in ("job_source", "execution_attempt"):
+            if table_name not in table_names:
+                continue
+            for legacy, canonical in replacements.items():
+                result = sync_connection.execute(
+                    text(f'update "{table_name}" set status = :canonical where status = :legacy'),
+                    {"canonical": canonical, "legacy": legacy},
+                )
+                fixed += result.rowcount or 0
+        return fixed
+
+    async with active_engine.begin() as connection:
+        fixed_rows = await connection.run_sync(_normalize)
+    if fixed_rows:
+        logger.warning("Normalized %s legacy status row(s) to canonical spellings", fixed_rows)
+    return fixed_rows
+
+
 async def seed_registry_defaults(*, engine: AsyncEngine | None = None) -> None:
     """Seed default registry rows for role and document type taxonomies."""
     active_engine = engine or resolve_engine()