fc3d: cleanup_old_download_events daily task (terminal-only, configurable retention)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-21 16:02:36 -04:00
parent 9d5793f0ce
commit ec004933a5
2 changed files with 135 additions and 1 deletions
+27 -1
View File
@@ -11,7 +11,7 @@ from sqlalchemy.orm import sessionmaker
from ..celery_app import celery
from ..config import get_config
from ..models import ImageRecord, ImportTask
from ..models import DownloadEvent, ImageRecord, ImportSettings, ImportTask
from ..utils.phash import compute_phash
log = logging.getLogger(__name__)
@@ -196,3 +196,29 @@ def verify_integrity() -> int:
last_id = rows[-1].id
log.info("verify_integrity verdicts: %s (total %d)", counts, total)
return total
@celery.task(name="backend.app.tasks.maintenance.cleanup_old_download_events")
def cleanup_old_download_events() -> int:
"""FC-3d: delete terminal DownloadEvent rows older than the configured
retention window. Never touches pending/running rows.
Why terminal-only: pending/running rows represent in-flight work whose
owning task may still be alive; deleting them would orphan the task.
Retention days comes from ImportSettings.download_event_retention_days
so the operator can tune without a code change.
"""
SessionLocal = _sync_session_factory()
with SessionLocal() as session:
settings = session.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
retention_days = settings.download_event_retention_days
cutoff = datetime.now(UTC) - timedelta(days=retention_days)
result = session.execute(
delete(DownloadEvent)
.where(DownloadEvent.status.in_(["ok", "error", "skipped"]))
.where(DownloadEvent.started_at < cutoff)
)
session.commit()
return result.rowcount or 0