This repository has been archived on 2026-05-31. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
imagerepo/app/celery_app.py
T
bvandeusen 5b7e033d0c feat(suggestions): auto-accept threshold + retroactive blocklist sweep
Two capabilities that work together to turn the suggestion system from
a 'review every noisy chip' UX into a 'curated tags only, configurable
auto-apply' UX for a solo-user library.

Auto-accept threshold
  Service (tag_suggestions.py):
    - New default auto_accept_general_threshold = 0.95 in _DEFAULTS
    - get_suggestions splits general-category hits at/above the threshold
      into a separate auto_accept_candidates list; the core 'character'/
      'copyright'/'general' keys stay the same shape for existing callers
    - get_bulk_suggestions ignores the new key (no side effects in bulk)
  Route (main.py GET /image/<id>/suggestions):
    - For each candidate: find-or-create Tag(kind='user', name=name), attach
      to image, log SuggestionFeedback(source='wd14'|etc, decision='accepted')
    - Response adds 'auto_accepted: [{id, name, display_name, kind,
      confidence, source}, ...]' so the modal can review + undo
  Config endpoints (main.py):
    GET  /api/suggestions/config/auto-accept-threshold
    POST /api/suggestions/config/auto-accept-threshold {threshold}
    Values > 1.0 effectively disable the feature
  UI (view-modal.js):
    - New renderAutoAccepted block at top of suggestions section with
      green-tinted chips carrying ✕ (undo for this image, logs rejection)
      and ⊘ (blocklist + remove from all images)
    - loadSuggestions refreshes the tag pill list when auto_accepted has
      items so the user sees them in the Tags section too
  Settings:
    - Maintenance tab gains a number input + save button backed by
      /api/suggestions/config/auto-accept-threshold

Retroactive blocklist sweep
  New Celery task app.tasks.maintenance.sweep_blocklisted_tag_from_images
  on the maintenance queue. Enqueued automatically when a name is added
  via POST /api/suggestions/blocklist or appears new in the bulk replace.
  Task body: finds kind='user' Tag matching the name, deletes its
  image_tags rows, deletes the Tag itself. Scope limited to kind='user'
  so deliberate character/fandom/artist tags sharing a blocklisted name
  aren't silently destroyed.

Verification (local dev):
  - Threshold GET/POST round-trip correct (default 0.95, persisted in
    tag_suggestion_config)
  - Image 633 at threshold=0.9: 4 general tags auto-applied, each with
    a SuggestionFeedback row, returned in auto_accepted
  - Blocklist add of 'sweeptestonly' with an attached test tag: Redis
    maintenance queue depth = 1, task body removes 1 image_tags row +
    the Tag row
  - get_bulk_suggestions still works (auto_accept_candidates key skipped)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-23 17:23:25 -04:00

151 lines
5.2 KiB
Python

# app/celery_app.py
"""
Celery application factory and configuration.
Provides task queue functionality for the ImageRepo import pipeline.
"""
import os
from celery import Celery
# Default broker/backend URLs
DEFAULT_BROKER = 'redis://redis:6379/0'
DEFAULT_BACKEND = 'redis://redis:6379/0'
def make_celery(app=None):
"""
Create Celery instance with Flask app context support.
Args:
app: Flask application instance (optional)
Returns:
Configured Celery instance
"""
# Get broker/backend from app config or environment
if app:
broker = app.config.get('CELERY_BROKER_URL', DEFAULT_BROKER)
backend = app.config.get('CELERY_RESULT_BACKEND', DEFAULT_BACKEND)
else:
broker = os.environ.get('CELERY_BROKER_URL', DEFAULT_BROKER)
backend = os.environ.get('CELERY_RESULT_BACKEND', DEFAULT_BACKEND)
celery = Celery(
'imagerepo',
broker=broker,
backend=backend,
include=[
'app.tasks.scan',
'app.tasks.import_file',
'app.tasks.thumbnail',
'app.tasks.sidecar',
'app.tasks.ml',
'app.tasks.maintenance',
]
)
# Worker concurrency from environment
concurrency = int(os.environ.get('CELERY_WORKER_CONCURRENCY', '2'))
celery.conf.update(
# Serialization
task_serializer='json',
accept_content=['json'],
result_serializer='json',
timezone='UTC',
enable_utc=True,
# Concurrency - intentionally low for steady background processing
worker_concurrency=concurrency,
worker_prefetch_multiplier=1, # One task at a time per worker process
# Task routing - separate queues for different task types
# Scheduler handles: maintenance (periodic tasks) + scan (directory scans)
# Worker handles: import, thumbnail, sidecar, default
task_routes={
# Scan tasks - handled by scheduler
'app.tasks.scan.scan_directory': {'queue': 'scan'},
'app.tasks.scan.deep_scan_directory': {'queue': 'scan'},
# Maintenance tasks - handled by scheduler (periodic/lightweight)
'app.tasks.scan.recover_interrupted_tasks': {'queue': 'maintenance'},
'app.tasks.scan.cleanup_old_tasks': {'queue': 'maintenance'},
'app.tasks.scan.update_system_stats': {'queue': 'maintenance'},
'app.tasks.scan.update_batch_stats': {'queue': 'maintenance'},
'app.tasks.maintenance.sweep_blocklisted_tag_from_images': {'queue': 'maintenance'},
# Import tasks - handled by worker (heavy processing)
'app.tasks.import_file.*': {'queue': 'import'},
'app.tasks.thumbnail.*': {'queue': 'thumbnail'},
'app.tasks.sidecar.*': {'queue': 'sidecar'},
# ML inference tasks - handled by ml-worker
'app.tasks.ml.*': {'queue': 'ml'},
},
# Task default queue for unrouted tasks
task_default_queue='default',
# Result backend settings
result_expires=86400, # 24 hours
# Task execution settings for resume capability
task_acks_late=True, # Acknowledge after task completes
task_reject_on_worker_lost=True, # Requeue if worker dies
# Time limits (video transcoding may need longer)
task_soft_time_limit=600, # 10 minutes soft limit
task_time_limit=900, # 15 minutes hard limit
# Periodic task schedule (Celery Beat)
beat_schedule={
'periodic-import-scan': {
'task': 'app.tasks.scan.scan_directory',
'schedule': int(os.environ.get('IMPORT_EVERY_SECONDS', '28800')), # 8 hours default
'args': ('/import', '/images'),
},
'recover-interrupted-tasks': {
'task': 'app.tasks.scan.recover_interrupted_tasks',
'schedule': 300, # Every 5 minutes
},
'cleanup-old-tasks': {
'task': 'app.tasks.scan.cleanup_old_tasks',
'schedule': 86400, # Once per day
'args': (7,), # Keep tasks for 7 days
},
'update-system-stats': {
'task': 'app.tasks.scan.update_system_stats',
'schedule': 21600, # Every 6 hours
},
},
)
if app:
# Don't pass Flask config directly to Celery - it contains old-style keys
# that conflict with Celery's new lowercase format.
# The broker/backend are already set above from app.config.
# Create a task base class that runs within Flask app context
class ContextTask(celery.Task):
def __call__(self, *args, **kwargs):
with app.app_context():
return self.run(*args, **kwargs)
celery.Task = ContextTask
return celery
def create_celery_with_app():
"""
Create Celery instance with Flask app context for standalone workers.
This is used when running `celery -A app.celery_app:celery worker`.
"""
from app import create_app
flask_app = create_app()
return make_celery(flask_app)
# Create celery instance with Flask app context
# This ensures workers have access to the database and Flask extensions
celery = create_celery_with_app()