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>
92 lines
2.9 KiB
Python
92 lines
2.9 KiB
Python
"""Rate limiter cleanup background task.
|
|
|
|
Registers an APScheduler job that periodically removes expired rate-limit
|
|
entries from the in-memory rate limiter. Without this cleanup, the
|
|
rate-limiter state dictionary grows unbounded over long runtimes, eventually
|
|
consuming excessive memory.
|
|
|
|
The cleanup is conservative: it only removes IPs with no recent attempts
|
|
(all timestamps outside the rate-limit window), so active or recently-active
|
|
IPs are preserved.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.tasks.timeout_utils import run_with_timeout
|
|
|
|
if TYPE_CHECKING:
|
|
from fastapi import FastAPI
|
|
|
|
log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
|
|
|
#: How often the cleanup job fires (seconds). Chosen to balance memory
|
|
#: management against CPU overhead. A 30-minute interval handles typical
|
|
#: brute-force attack patterns while staying lightweight.
|
|
RATE_LIMITER_CLEANUP_INTERVAL: int = 30 * 60 # 30 minutes
|
|
|
|
#: Stable APScheduler job ID — ensures re-registration replaces, not duplicates.
|
|
JOB_ID: str = "rate_limiter_cleanup"
|
|
|
|
#: Maximum seconds to allow for rate limiter cleanup to complete.
|
|
TASK_TIMEOUT_SECONDS: int = 5
|
|
|
|
|
|
async def _run_cleanup(app: FastAPI) -> None:
|
|
"""Trigger cleanup of expired rate-limiter entries.
|
|
|
|
Cleans up both the login-specific rate limiter (exponential backoff)
|
|
and the global request rate limiter.
|
|
|
|
Args:
|
|
app: The FastAPI application instance (holds the rate limiters).
|
|
"""
|
|
|
|
async def _do_cleanup() -> None:
|
|
login_limiter = getattr(app.state, "login_rate_limiter", None)
|
|
if login_limiter is None:
|
|
log.warning(
|
|
"rate_limiter_cleanup_skipped",
|
|
reason="login_rate_limiter not found on app.state",
|
|
)
|
|
else:
|
|
login_limiter.cleanup_expired()
|
|
|
|
global_limiter = getattr(app.state, "global_rate_limiter", None)
|
|
if global_limiter is None:
|
|
log.warning(
|
|
"rate_limiter_cleanup_skipped",
|
|
reason="global_rate_limiter not found on app.state",
|
|
)
|
|
else:
|
|
global_limiter.cleanup_expired()
|
|
|
|
await run_with_timeout("rate_limiter_cleanup", _do_cleanup(), TASK_TIMEOUT_SECONDS)
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Add (or replace) the rate-limiter 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.
|
|
"""
|
|
app.state.scheduler.add_job(
|
|
_run_cleanup,
|
|
trigger="interval",
|
|
seconds=RATE_LIMITER_CLEANUP_INTERVAL,
|
|
kwargs={"app": app},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
)
|
|
log.info(
|
|
"rate_limiter_cleanup_scheduled",
|
|
interval_seconds=RATE_LIMITER_CLEANUP_INTERVAL,
|
|
)
|