Files
FabledCurator/backend/app/celery_app.py
T
bvandeusen 98673d4dca
CI / lint (push) Failing after 3s
CI / backend-lint-and-test (push) Successful in 17s
CI / frontend-build (push) Successful in 31s
CI / intimp (push) Successful in 3m45s
CI / intapi (push) Successful in 7m46s
CI / intcore (push) Successful in 8m23s
fix(audit-g5a): small architectural cleanups bundle
Five small G5 findings from the 2026-06-02 audit. Each is local and
follows an established FC pattern.

- download_service: replace hardcoded ('discord','pixiv') tuple with
  auth_type_for(platform) == 'token'. A 7th token-platform now picks
  up the right credential path without touching this site.

- /api/tags/<source_id>/merge enqueues recompute_centroid.delay after
  merge so the target's centroid reflects its new image set
  immediately. Daily list_drifted catches it within 24h, but eager
  recompute closes the suggestion-quality dip in the meantime.

- backfill_thumbnails added to beat_schedule (daily). The task
  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.

- modal.createAndAdd pushes a kind='fandom' tag into
  tagsStore.fandomCache so FandomPicker sees the new fandom on next
  open. Was: cache-gated load (length===0) skipped refetch, new
  fandom invisible until full page reload.

- cleanup cluster:
  - Drop .webp from cleanup_service.unlink — thumbnailer only writes
    .jpg/.png; the third tuple member was dead code.
  - Drop effective_date from /api/gallery/scroll response — no FE
    consumer reads it. Service still computes the attribute for
    timeline ordering; this just trims the JSON.
  - Rename store.recentMinute → store.recentRuns across the
    systemActivity store + three consumers (SystemActivitySummary,
    QueuesTable, SystemActivityTab). The data is the last 200 runs
    (not actually "last minute"), so the name lied.

NOT in this bundle: the duplicate tag-merge endpoint
(/api/tags vs /api/admin/tags) is harder — has 1 FE caller and 3 tests
on the admin variant; consolidation is its own change.
2026-06-02 16:46:46 -04:00

153 lines
6.4 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.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"},
"backend.app.tasks.scan.*": {"queue": "scan"},
"backend.app.tasks.maintenance.*": {"queue": "maintenance"},
"backend.app.tasks.backup.*": {"queue": "maintenance"},
"backend.app.tasks.admin.*": {"queue": "maintenance"},
"backend.app.tasks.library_audit.*": {"queue": "maintenance"},
},
# 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
},
"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,
},
},
timezone="UTC",
)
# FC-3i: register task_run signal handlers (side-effect import).
from . import celery_signals # noqa: F401
return app
celery = make_celery()