Lukas
52f237d5d4
CRITICAL FIX: Background tasks (especially blocklist_import) crashed mid-execution, leaving partial state. On retry, the same bans were applied again, causing duplicates. Solution: Content-hash based operation tracking for blocklist imports: - Added import_runs table (migration 6) to track operations by source + content hash - Before banning, check if this exact content has already been imported - If completed: skip banning (already done), optionally re-warm cache - If new or failed: proceed with ban and mark as completed or failed Changes: - Database: Migration 6 adds import_runs table with operation state tracking - Model: Added ImportRunEntry for import run records - Repository: New import_run_repo module with CRUD operations - Workflow: Updated blocklist_import_workflow to check operation history before banning - Dependencies: Registered import_run_repo for dependency injection - Tests: Added test_import_source_idempotent_on_retry and test_import_source_different_content_not_reused - Documentation: Added Task Idempotency section to Backend-Development.md Verification: - All 7 import tests pass (5 existing + 2 new idempotency tests) - Type checking: mypy --strict ✅ - Linting: ruff ✅ - No API changes, backwards compatible via automatic migration Fixes: Background tasks not idempotent #CRITICAL Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
"""Session cleanup background task.
|
|
|
|
Registers an APScheduler job that periodically removes expired sessions from
|
|
the ``sessions`` table. Without this cleanup, the table grows unbounded over
|
|
months of operation and degrades query performance.
|
|
|
|
Individual expired sessions are removed on-demand when validated, but the bulk
|
|
cleanup ensures comprehensive pruning at a predictable interval.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.repositories import session_repo
|
|
from app.tasks.db import task_db
|
|
from app.tasks.timeout_utils import run_with_timeout
|
|
from app.utils.runtime_state import get_effective_settings
|
|
from app.utils.time_utils import utc_now
|
|
|
|
if TYPE_CHECKING:
|
|
from fastapi import FastAPI
|
|
|
|
from app.config import Settings
|
|
|
|
log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
|
|
|
#: How often the cleanup job fires (seconds). Configurable tuning constant.
|
|
SESSION_CLEANUP_INTERVAL: int = 6 * 60 * 60 # 6 hours
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "session_cleanup"
|
|
|
|
#: Maximum seconds to allow for session cleanup to complete.
|
|
TASK_TIMEOUT_SECONDS: int = 30
|
|
|
|
|
|
async def _run_cleanup_with_resources(settings: Settings) -> None:
|
|
"""Delete all expired sessions from the database.
|
|
|
|
Args:
|
|
settings: The resolved application settings used for database access.
|
|
"""
|
|
|
|
async def _do_cleanup() -> None:
|
|
now_iso = utc_now().isoformat()
|
|
async with task_db(settings) as db:
|
|
deleted_count = await session_repo.delete_expired_sessions(db, now_iso)
|
|
|
|
log.info("session_cleanup_ran", deleted_count=deleted_count, cutoff_time=now_iso)
|
|
|
|
await run_with_timeout("session_cleanup", _do_cleanup(), TASK_TIMEOUT_SECONDS)
|
|
|
|
|
|
async def _run_cleanup(app: FastAPI) -> None:
|
|
await _run_cleanup_with_resources(get_effective_settings(app))
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the session cleanup job in the application scheduler.
|
|
|
|
Must be called after the scheduler has been started (i.e., inside the
|
|
lifespan handler, after ``scheduler.start()``).
|
|
|
|
Args:
|
|
app: The :class:`fastapi.FastAPI` application instance whose
|
|
``app.state.scheduler`` will receive the job.
|
|
"""
|
|
settings = get_effective_settings(app)
|
|
app.state.scheduler.add_job(
|
|
_run_cleanup_with_resources,
|
|
trigger="interval",
|
|
seconds=SESSION_CLEANUP_INTERVAL,
|
|
kwargs={"settings": settings},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info("session_cleanup_scheduled", interval_seconds=SESSION_CLEANUP_INTERVAL)
|