Files
reflector/server/reflector/worker/app.py
Mathieu Virbel 6f0c7c1a5e feat(cleanup): add automatic data retention for public instances (#574)
* feat(cleanup): add automatic data retention for public instances

- Add Celery task to clean up anonymous data after configurable retention period
- Delete transcripts, meetings, and orphaned recordings older than retention days
- Only runs when PUBLIC_MODE is enabled to prevent accidental data loss
- Properly removes all associated files (local and S3 storage)
- Add manual cleanup tool for testing and intervention
- Configure retention via PUBLIC_DATA_RETENTION_DAYS setting (default: 7 days)

Fixes #571

* fix: apply pre-commit formatting fixes

* fix: properly delete recording files from storage during cleanup

- Add storage deletion for orphaned recordings in both cleanup task and manual tool
- Delete from storage before removing database records
- Log warnings if storage deletion fails but continue with database cleanup

* Apply suggestion from @pr-agent-monadical[bot]

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>

* Apply suggestion from @pr-agent-monadical[bot]

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>

* refactor: cleanup_old_data for better logging

* fix: linting

* test: fix meeting cleanup test to not require room controller

- Simplify test by directly inserting meetings into database
- Remove dependency on non-existent rooms_controller.create method
- Tests now pass successfully

* fix: linting

* refactor: simplify cleanup tool to use worker implementation

- Remove duplicate cleanup logic from manual tool
- Use the same _cleanup_old_public_data function from worker
- Remove dry-run feature as requested
- Prevent code duplication and ensure consistency
- Update documentation to reflect changes

* refactor: split cleanup worker into smaller functions

- Move all imports to the top of the file
- Extract cleanup logic into separate functions:
  - cleanup_old_transcripts()
  - cleanup_old_meetings()
  - cleanup_orphaned_recordings()
  - log_cleanup_results()
- Make code more maintainable and testable
- Add days parameter support to Celery task
- Update manual tool to work with refactored code

* feat: add TypedDict typing for cleanup stats

- Add CleanupStats TypedDict for better type safety
- Update all function signatures to use proper typing
- Add return type annotations to _cleanup_old_public_data
- Improves code maintainability and IDE support

* feat: add CASCADE DELETE to meeting_consent foreign key

- Add ondelete="CASCADE" to meeting_consent.meeting_id foreign key
- Generate and apply migration to update existing constraint
- Remove manual consent deletion from cleanup code
- Add unit test to verify CASCADE DELETE behavior

* style: linting

* fix: alembic migration branchpoint

* fix: correct downgrade constraint name in CASCADE DELETE migration

* fix: regenerate CASCADE DELETE migration with proper constraint names

- Delete problematic migration and regenerate with correct names
- Use explicit constraint name in both upgrade and downgrade
- Ensure migration works bidirectionally
- All tests passing including CASCADE DELETE test

* style: linting

* refactor: simplify cleanup to use transcripts as entry point

- Remove orphaned_recordings cleanup (not part of this PR scope)
- Remove separate old_meetings cleanup
- Transcripts are now the main entry point for cleanup
- Associated meetings and recordings are deleted with their transcript
- Use single database connection for all operations
- Update tests to reflect new approach

* refactor: cleanup and rename functions for clarity

- Rename _cleanup_old_public_data to cleanup_old_public_data (make public)
- Rename celery task to cleanup_old_public_data_task for clarity
- Update docstrings and improve code organization
- Remove unnecessary comments and simplify deletion logic
- Update tests to use new function names
- All tests passing

* style: linting\

* style: typing and review

* fix: add transaction on cleanup_single_transcript

* fix: naming

---------

Co-authored-by: pr-agent-monadical[bot] <198624643+pr-agent-monadical[bot]@users.noreply.github.com>
2025-08-29 08:47:14 -06:00

60 lines
2.0 KiB
Python

import celery
import structlog
from celery import Celery
from celery.schedules import crontab
from reflector.settings import settings
logger = structlog.get_logger(__name__)
if celery.current_app.main != "default":
logger.info(f"Celery already configured ({celery.current_app})")
app = celery.current_app
else:
app = Celery(__name__)
app.conf.broker_url = settings.CELERY_BROKER_URL
app.conf.result_backend = settings.CELERY_RESULT_BACKEND
app.conf.broker_connection_retry_on_startup = True
app.autodiscover_tasks(
[
"reflector.pipelines.main_live_pipeline",
"reflector.worker.healthcheck",
"reflector.worker.process",
"reflector.worker.cleanup",
]
)
# crontab
app.conf.beat_schedule = {
"process_messages": {
"task": "reflector.worker.process.process_messages",
"schedule": float(settings.SQS_POLLING_TIMEOUT_SECONDS),
},
"process_meetings": {
"task": "reflector.worker.process.process_meetings",
"schedule": float(settings.SQS_POLLING_TIMEOUT_SECONDS),
},
"reprocess_failed_recordings": {
"task": "reflector.worker.process.reprocess_failed_recordings",
"schedule": crontab(hour=5, minute=0), # Midnight EST
},
}
if settings.PUBLIC_MODE:
app.conf.beat_schedule["cleanup_old_public_data"] = {
"task": "reflector.worker.cleanup.cleanup_old_public_data_task",
"schedule": crontab(hour=3, minute=0),
}
logger.info(
"Public mode cleanup enabled",
retention_days=settings.PUBLIC_DATA_RETENTION_DAYS,
)
if settings.HEALTHCHECK_URL:
app.conf.beat_schedule["healthcheck_ping"] = {
"task": "reflector.worker.healthcheck.healthcheck_ping",
"schedule": 60.0 * 10,
}
logger.info("Healthcheck enabled", url=settings.HEALTHCHECK_URL)
else:
logger.warning("Healthcheck disabled, no url configured")