Files
FabledCurator/backend/app/celery_app.py
T
bvandeusen 96e984cded
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 20s
CI / backend-lint-and-test (push) Successful in 28s
CI / integration (push) Failing after 3m14s
feat(external): download worker for file-host links (Phase 4b)
tasks/external.py drives the external_link ledger:
- fetch_external_link(link_id): atomic claim (pending/failed→downloading, so a
  duplicate enqueue no-ops), per-host Redis serialize lock (#720 pattern;
  requeue-with-countdown if busy), fetch via external_fetch into the artist
  library tree, then route each file through importer.attach_in_place via a
  synthesized sidecar so it links to the SAME post (archive→ImageRecords,
  else→PostAttachment; on-disk original removed for captured files, art stays);
  thumbnail+ML enqueue for new images; status downloaded | failed | dead with
  attempts/last_error/completed_at/duration.
- sweep_external_links(): enqueue a bounded batch of actionable links.
- recover_external_links() + prune_external_links(): recovery + retention (#89).
- per-host enable read via getattr (forward-compatible; Settings UI adds the
  columns in 4d — defaults on, rule #26).

Wiring: celery include + route (download lane) + beat (sweep 10m, recover +
prune daily); download_service phase 3 enqueues a sweep after recording links.
Integration tests: download+attach, failure, dead-letter, non-claimable, sweep.

mega still needs the MEGAcmd binary in the runtime image (Phase 4c). Refs #830.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-14 13:44:07 -04:00

182 lines
8.1 KiB
Python

"""Celery configuration with separate queue lanes.
Queues:
import — filesystem import path (FC-2)
ml — WD14 + SigLIP inference (FC-2; runs in the ml-worker image)
thumbnail — image and video thumbnail generation (FC-2)
download — gallery-dl tasks (FC-3)
scan — periodic source checks (FC-3) — kept separate so long imports
don't starve the scheduler
maintenance — pHash recomputation, centroid rebuild, etc. (FC-2/FC-3)
default — anything not explicitly routed
"""
from celery import Celery
from .config import get_config
def make_celery() -> Celery:
cfg = get_config()
app = Celery(
"fabledcurator",
broker=cfg.celery_broker_url,
backend=cfg.celery_result_backend,
include=[
"backend.app.tasks.smoke",
"backend.app.tasks.scan",
"backend.app.tasks.import_file",
"backend.app.tasks.thumbnail",
"backend.app.tasks.maintenance",
"backend.app.tasks.ml",
"backend.app.tasks.download",
"backend.app.tasks.external",
"backend.app.tasks.backup",
"backend.app.tasks.admin",
"backend.app.tasks.library_audit",
],
)
app.conf.update(
task_default_queue="default",
task_routes={
"backend.app.tasks.import_file.*": {"queue": "import"},
"backend.app.tasks.ml.*": {"queue": "ml"},
"backend.app.tasks.thumbnail.*": {"queue": "thumbnail"},
"backend.app.tasks.download.*": {"queue": "download"},
# External file-host fetches are downloads — same lane (they can run
# long, but the download worker already tolerates long backfills).
"backend.app.tasks.external.*": {"queue": "download"},
"backend.app.tasks.scan.*": {"queue": "scan"},
# `maintenance` is the QUICK lane — recovery sweeps, vacuum, cleanup
# (concurrency-1 on the scheduler). The long one-shots (DB backups,
# library audits, admin maintenance: normalize/re-extract/cascade-
# delete) run on a SEPARATE `maintenance_long` lane + worker so they
# can never starve the quick self-healing sweeps (operator-flagged
# 2026-06-07: a 2h audit blocked vacuum/backup/normalize for hours).
"backend.app.tasks.maintenance.*": {"queue": "maintenance"},
"backend.app.tasks.backup.*": {"queue": "maintenance_long"},
"backend.app.tasks.admin.*": {"queue": "maintenance_long"},
"backend.app.tasks.library_audit.*": {"queue": "maintenance_long"},
},
# Heavy ML tasks need fair dispatch — see ImageRepo's precedent.
task_acks_late=True,
worker_prefetch_multiplier=1,
broker_connection_retry_on_startup=True,
beat_schedule={
"recover-interrupted-tasks": {
"task": "backend.app.tasks.maintenance.recover_interrupted_tasks",
"schedule": 300.0, # every 5 minutes
},
"cleanup-old-tasks": {
"task": "backend.app.tasks.maintenance.cleanup_old_tasks",
"schedule": 86400.0, # daily
},
"ml-backfill-daily": {
"task": "backend.app.tasks.ml.backfill",
"schedule": 86400.0,
},
"recompute-centroids-daily": {
"task": "backend.app.tasks.ml.recompute_centroids",
"schedule": 86400.0,
},
"apply-allowlist-sweep-daily": {
"task": "backend.app.tasks.ml.apply_allowlist_tags",
"schedule": 86400.0,
},
"integrity-verify-weekly": {
"task": "backend.app.tasks.maintenance.verify_integrity",
"schedule": 604800.0, # weekly
},
"fc3d-tick-due-sources": {
"task": "backend.app.tasks.scan.tick_due_sources",
"schedule": 60.0, # every minute
},
"fc3d-cleanup-download-events": {
"task": "backend.app.tasks.maintenance.cleanup_old_download_events",
"schedule": 86400.0, # daily
},
"recover-stalled-download-events": {
"task": "backend.app.tasks.maintenance.recover_stalled_download_events",
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
},
"recover-stalled-task-runs": {
"task": "backend.app.tasks.maintenance.recover_stalled_task_runs",
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
},
"prune-task-runs": {
"task": "backend.app.tasks.maintenance.prune_task_runs",
"schedule": 86400.0, # daily
},
"vacuum-analyze": {
"task": "backend.app.tasks.maintenance.vacuum_analyze",
"schedule": 604800.0, # weekly — reclaim dead-tuple bloat + refresh stats
},
"fc3h-backup-db-nightly": {
"task": "backend.app.tasks.backup.backup_db_nightly",
"schedule": 3600.0, # hourly tick; task self-gates on configured UTC hour
},
"fc3h-prune-backups": {
"task": "backend.app.tasks.backup.prune_backups",
"schedule": 86400.0, # daily
},
# Audit 2026-06-02 — three new per-entity recovery sweeps.
# Each runs every 5 min like the other recover_stalled_*
# sweeps; each is a no-op when nothing is stuck.
"recover-stalled-backup-runs": {
"task": "backend.app.tasks.maintenance.recover_stalled_backup_runs",
"schedule": 300.0,
},
"recover-stalled-library-audit-runs": {
"task": "backend.app.tasks.maintenance.recover_stalled_library_audit_runs",
"schedule": 300.0,
},
"recover-stalled-import-batches": {
"task": "backend.app.tasks.maintenance.recover_stalled_import_batches",
"schedule": 300.0,
},
# Audit 2026-06-02 — daily retention for two entities
# whose terminal rows otherwise accumulate forever.
"prune-library-audit-runs": {
"task": "backend.app.tasks.maintenance.prune_library_audit_runs",
"schedule": 86400.0,
},
"prune-import-batches": {
"task": "backend.app.tasks.maintenance.prune_import_batches",
"schedule": 86400.0,
},
# Audit 2026-06-02 — backfill_thumbnails's docstring claimed
# "periodic Beat" but the entry was never registered, so the
# library got no self-healing thumbnail repair; only the
# manual admin-UI button fired it. Daily cadence is gentle
# (the task is idempotent and only enqueues regen for rows
# whose stored thumbnails are missing or corrupt).
"backfill-thumbnails-daily": {
"task": "backend.app.tasks.thumbnail.backfill_thumbnails",
"schedule": 86400.0,
},
# External file-host downloads (#830): a steady sweep catches links
# the post-download hook missed (worker down, etc.); recovery re-tries
# dead links daily; retention prunes long-dead rows.
"extdl-sweep": {
"task": "backend.app.tasks.external.sweep_external_links",
"schedule": 600.0, # every 10 min
},
"extdl-recover-daily": {
"task": "backend.app.tasks.external.recover_external_links",
"schedule": 86400.0,
},
"extdl-prune-daily": {
"task": "backend.app.tasks.external.prune_external_links",
"schedule": 86400.0,
},
},
timezone="UTC",
)
# FC-3i: register task_run signal handlers (side-effect import).
from . import celery_signals # noqa: F401
return app
celery = make_celery()