refactor(dry-B4): extract shared async_session_factory for Celery tasks

download/migration/scan each defined an identical _async_session_factory()
(fresh per-invocation async engine — async connections are event-loop-bound
so each asyncio.run() task needs its own engine, unlike the process-wide
_sync_engine). Moved it to tasks/_async_session.py; the 3 files import it
and drop their now-orphaned sqlalchemy.ext.asyncio / get_config imports
(migration keeps AsyncSession for a type hint). Call-site try/finally
dispose left as-is to avoid re-indenting the critical task bodies.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-28 13:15:04 -04:00
parent 597c6d48d3
commit 21c1b0a81c
4 changed files with 28 additions and 27 deletions
+21
View File
@@ -0,0 +1,21 @@
"""Per-invocation async session factory for Celery task modules.
Async engine connections are bound to the event loop. Each Celery task
runs its async body under a fresh ``asyncio.run()`` loop, so it needs its
own engine created (and disposed) within that loop — a process-wide async
engine would reuse loop-bound connections across tasks and raise "attached
to a different loop". So unlike the process-wide sync engine in
``_sync_engine.py``, this returns a fresh engine per call; the caller
disposes it (``await engine.dispose()``) when its loop ends.
"""
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from ..config import get_config
def async_session_factory():
"""Return ``(sessionmaker, engine)`` bound to a fresh async engine."""
cfg = get_config()
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
+2 -9
View File
@@ -5,10 +5,8 @@ from pathlib import Path
from sqlalchemy import select
from sqlalchemy.exc import DBAPIError, OperationalError
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from ..celery_app import celery
from ..config import get_config
from ..models import ImportSettings
from ..services.credential_crypto import CredentialCrypto
from ..services.credential_service import CredentialService
@@ -16,18 +14,13 @@ from ..services.download_service import DownloadService
from ..services.gallery_dl import GalleryDLService
from ..services.importer import Importer
from ..services.thumbnailer import Thumbnailer
from ._async_session import async_session_factory
from .import_file import _sync_session_factory
IMAGES_ROOT = Path("/images")
_KEY_PATH = IMAGES_ROOT / "secrets" / "credential_key.b64"
def _async_session_factory():
cfg = get_config()
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
@celery.task(
name="backend.app.tasks.download.download_source",
bind=True,
@@ -44,7 +37,7 @@ def download_source(self, source_id: int) -> int:
"""Returns the DownloadEvent.id."""
async def _run():
async_factory, async_engine = _async_session_factory()
async_factory, async_engine = async_session_factory()
SyncFactory = _sync_session_factory()
try:
with SyncFactory() as sync_session:
+3 -9
View File
@@ -15,14 +15,14 @@ from datetime import UTC, datetime
from pathlib import Path
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from sqlalchemy.ext.asyncio import AsyncSession
from ..celery_app import celery
from ..config import get_config
from ..models import MigrationRun
from ..services.credential_crypto import CredentialCrypto
from ..services.migrators import cleanup as cleanup_mod
from ..services.migrators import gs_ingest, ir_ingest, ml_queue, tag_apply, verify
from ._async_session import async_session_factory
log = logging.getLogger(__name__)
@@ -30,12 +30,6 @@ IMAGES_ROOT = Path("/images")
_KEY_PATH = IMAGES_ROOT / "secrets" / "credential_key.b64"
def _async_session_factory():
cfg = get_config()
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
async def _update_run(
db: AsyncSession, run_id: int, *,
status: str | None = None, counts: dict | None = None,
@@ -59,7 +53,7 @@ async def _update_run(
async def _run_async(run_id: int, kind: str, params: dict) -> dict:
factory, engine = _async_session_factory()
factory, engine = async_session_factory()
try:
async with factory() as db:
await _update_run(db, run_id, status="running")
+2 -9
View File
@@ -12,13 +12,12 @@ from datetime import UTC, datetime
from pathlib import Path
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from ..celery_app import celery
from ..config import get_config
from ..models import DownloadEvent, ImportBatch, ImportSettings, ImportTask
from ..services.archive_extractor import is_archive
from ..services.scheduler_service import record_tick, select_due_sources
from ._async_session import async_session_factory
from ._sync_engine import sync_session_factory as _sync_session_factory
@@ -141,14 +140,8 @@ def scan_directory(self, triggered_by: str = "manual",
# --- FC-3d: periodic source-check tick ------------------------------------
def _async_session_factory():
cfg = get_config()
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
async def _tick_due_sources_async() -> dict:
factory, engine = _async_session_factory()
factory, engine = async_session_factory()
try:
async with factory() as session:
# Prove the scheduler is alive even on empty ticks (UI reads this).