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>
73 lines
2.1 KiB
Python
73 lines
2.1 KiB
Python
"""History sync background task.
|
|
|
|
Periodically copies new records from the fail2ban sqlite database into the
|
|
BanGUI application archive table to prevent gaps when fail2ban purges old rows.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime
|
|
from typing import TYPE_CHECKING
|
|
|
|
import structlog
|
|
|
|
from app.services import history_service
|
|
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
|
|
|
|
if TYPE_CHECKING:
|
|
from fastapi import FastAPI
|
|
|
|
from app.config import Settings
|
|
|
|
log: structlog.stdlib.BoundLogger = structlog.get_logger()
|
|
|
|
#: Stable APScheduler job id.
|
|
JOB_ID: str = "history_sync"
|
|
|
|
#: Interval in seconds between sync runs.
|
|
HISTORY_SYNC_INTERVAL: int = 300
|
|
|
|
#: Backfill window when archive is empty (seconds).
|
|
BACKFILL_WINDOW: int = 648000
|
|
|
|
#: Maximum seconds to allow for history sync to complete.
|
|
TASK_TIMEOUT_SECONDS: int = 60
|
|
|
|
|
|
async def _run_sync_with_settings(settings: Settings) -> None:
|
|
socket_path: str = settings.fail2ban_socket
|
|
|
|
async def _do_sync() -> None:
|
|
try:
|
|
async with task_db(settings) as db:
|
|
synced = await history_service.sync_from_fail2ban_db(db, socket_path)
|
|
log.info("history_sync_complete", synced=synced)
|
|
except Exception:
|
|
log.exception("history_sync_failed")
|
|
|
|
await run_with_timeout("history_sync", _do_sync(), TASK_TIMEOUT_SECONDS)
|
|
|
|
|
|
async def _run_sync(app: FastAPI) -> None:
|
|
await _run_sync_with_settings(get_effective_settings(app))
|
|
|
|
|
|
def register(app: FastAPI) -> None:
|
|
"""Register the history sync periodic job.
|
|
|
|
Should be called after scheduler startup, from the lifespan handler.
|
|
"""
|
|
settings = get_effective_settings(app)
|
|
app.state.scheduler.add_job(
|
|
_run_sync_with_settings,
|
|
trigger="interval",
|
|
seconds=HISTORY_SYNC_INTERVAL,
|
|
kwargs={"settings": settings},
|
|
id=JOB_ID,
|
|
replace_existing=True,
|
|
next_run_time=datetime.datetime.now(tz=datetime.UTC),
|
|
)
|
|
log.info("history_sync_scheduled", interval_seconds=HISTORY_SYNC_INTERVAL)
|