c1e06d4c0a
Some checks failed
Aegis CI / lint-and-test (push) Has been cancelled
- Phase 6.1: WebhookConfig model, CRUD router (/api/v1/webhooks, admin-only), dispatch_webhook() with HMAC signing; integrated into test validation, campaign completion, and MITRE sync job - Phase 7.1: SMTP email service with send_test_validated_email, send_campaign_completed_email, send_new_mitre_techniques_email; notify_role_with_email() added to notification_service - Phase 7.2: notification_preferences and jira_account_id on User model; PATCH /users/me/preferences endpoint; Alembic migrations b031phase6 and b032phase7 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
303 lines
9.7 KiB
Python
303 lines
9.7 KiB
Python
"""Scheduled background jobs.
|
|
|
|
Registers periodic tasks on an APScheduler ``BackgroundScheduler``:
|
|
|
|
* **MITRE sync** — every 24 hours (see :func:`sync_mitre`)
|
|
* **Intel scan** — every 7 days (see :func:`scan_intel`)
|
|
|
|
Each job manages its own database session (created on entry, closed in
|
|
``finally``) so it is fully independent from FastAPI's request-scoped
|
|
sessions.
|
|
"""
|
|
|
|
import logging
|
|
from datetime import datetime, timedelta, timezone
|
|
|
|
from apscheduler.schedulers.background import BackgroundScheduler
|
|
|
|
from app.database import SessionLocal
|
|
from app.services.mitre_sync_service import sync_mitre
|
|
from app.services.intel_service import scan_intel
|
|
from app.services.notification_service import cleanup_old_notifications
|
|
from app.services.snapshot_service import create_snapshot, cleanup_old_snapshots
|
|
from app.services.campaign_scheduler_service import check_and_run_recurring_campaigns
|
|
from app.jobs.jira_sync_job import sync_all_jira_links
|
|
from app.services.osint_enrichment_service import enrich_all_techniques
|
|
from app.services.stale_detection_service import detect_stale_coverage
|
|
from app.jobs.retention_job import run_retention_job
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Module-level scheduler instance
|
|
# ---------------------------------------------------------------------------
|
|
|
|
scheduler = BackgroundScheduler()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Job functions
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _run_mitre_sync() -> None:
|
|
"""Execute a MITRE sync inside its own DB session."""
|
|
from app.services.webhook_service import dispatch_webhook
|
|
logger.info("Scheduled MITRE sync job starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
summary = sync_mitre(db)
|
|
logger.info("Scheduled MITRE sync job finished — %s", summary)
|
|
dispatch_webhook("mitre.synced", {"created": summary.get("created", 0), "updated": summary.get("updated", 0)})
|
|
except Exception:
|
|
logger.exception("Scheduled MITRE sync job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_notification_cleanup() -> None:
|
|
"""Clean up old read notifications."""
|
|
logger.info("Scheduled notification cleanup job starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
deleted = cleanup_old_notifications(db, days=90)
|
|
logger.info("Notification cleanup finished — deleted %d old notifications", deleted)
|
|
except Exception:
|
|
logger.exception("Notification cleanup job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_weekly_snapshot() -> None:
|
|
"""Create a weekly coverage snapshot and clean up old ones."""
|
|
logger.info("Scheduled weekly snapshot job starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
snapshot = create_snapshot(db, name="Auto-weekly")
|
|
logger.info(
|
|
"Weekly snapshot created — score %.1f, %d techniques",
|
|
snapshot.organization_score,
|
|
snapshot.total_techniques,
|
|
)
|
|
deleted = cleanup_old_snapshots(db, keep_last=52)
|
|
if deleted:
|
|
logger.info("Cleaned up %d old snapshots", deleted)
|
|
except Exception:
|
|
logger.exception("Weekly snapshot job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_recurring_campaigns() -> None:
|
|
"""Check and run any due recurring campaigns."""
|
|
logger.info("Scheduled recurring campaigns check starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
spawned = check_and_run_recurring_campaigns(db)
|
|
logger.info("Recurring campaigns check finished — spawned %d campaigns", spawned)
|
|
except Exception:
|
|
logger.exception("Recurring campaigns check failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_intel_scan() -> None:
|
|
"""Execute an intel scan inside its own DB session."""
|
|
logger.info("Scheduled intel scan job starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
summary = scan_intel(db)
|
|
logger.info("Scheduled intel scan job finished — %s", summary)
|
|
except Exception:
|
|
logger.exception("Scheduled intel scan job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_osint_enrichment() -> None:
|
|
"""Execute weekly OSINT enrichment inside its own DB session."""
|
|
logger.info("Scheduled OSINT enrichment job starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
total = enrich_all_techniques(db)
|
|
logger.info("OSINT enrichment finished — %d new items", total)
|
|
except Exception:
|
|
logger.exception("OSINT enrichment job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
_FREQUENCY_INTERVALS: dict[str, timedelta] = {
|
|
"daily": timedelta(days=1),
|
|
"weekly": timedelta(weeks=1),
|
|
"monthly": timedelta(days=30),
|
|
}
|
|
|
|
|
|
def _run_data_sources_sync() -> None:
|
|
"""Check all enabled data sources and sync those that are overdue."""
|
|
logger.info("Scheduled data sources sync check starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
from app.models.data_source import DataSource
|
|
from app.services.data_source_service import sync_source
|
|
|
|
now = datetime.now(timezone.utc)
|
|
sources = (
|
|
db.query(DataSource)
|
|
.filter(DataSource.is_enabled == True) # noqa: E712
|
|
.all()
|
|
)
|
|
synced = 0
|
|
for ds in sources:
|
|
freq = ds.sync_frequency
|
|
if not freq or freq == "manual":
|
|
continue
|
|
interval = _FREQUENCY_INTERVALS.get(freq)
|
|
if interval is None:
|
|
continue
|
|
last = ds.last_sync_at
|
|
if last is None:
|
|
# Never synced — run it now
|
|
overdue = True
|
|
else:
|
|
# Make last timezone-aware if needed
|
|
if last.tzinfo is None:
|
|
last = last.replace(tzinfo=timezone.utc)
|
|
overdue = now - last >= interval
|
|
if overdue:
|
|
logger.info(
|
|
"Data source '%s' is overdue (freq=%s, last=%s) — syncing",
|
|
ds.name, freq, last,
|
|
)
|
|
try:
|
|
sync_source(db, str(ds.id))
|
|
synced += 1
|
|
except Exception:
|
|
logger.exception("Failed to sync data source '%s'", ds.name)
|
|
logger.info("Data sources sync check finished — %d source(s) synced", synced)
|
|
except Exception:
|
|
logger.exception("Data sources sync check failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def _run_stale_detection() -> None:
|
|
"""Execute daily stale coverage detection inside its own DB session."""
|
|
logger.info("Scheduled stale coverage detection starting...")
|
|
db = SessionLocal()
|
|
try:
|
|
count = detect_stale_coverage(db)
|
|
logger.info("Stale detection finished — %d techniques flagged", count)
|
|
except Exception:
|
|
logger.exception("Stale coverage detection job failed")
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Scheduler bootstrap
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def start_scheduler() -> None:
|
|
"""Register all periodic jobs and start the background scheduler.
|
|
|
|
Jobs registered:
|
|
|
|
* ``mitre_sync`` — every **24 hours**
|
|
* ``intel_scan`` — every **7 days**
|
|
|
|
Neither job fires immediately on startup.
|
|
"""
|
|
scheduler.add_job(
|
|
_run_mitre_sync,
|
|
trigger="interval",
|
|
hours=24,
|
|
id="mitre_sync",
|
|
name="MITRE ATT&CK sync (every 24h)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_intel_scan,
|
|
trigger="interval",
|
|
weeks=1,
|
|
id="intel_scan",
|
|
name="Intel scan (every 7d)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_notification_cleanup,
|
|
trigger="interval",
|
|
hours=24,
|
|
id="notification_cleanup",
|
|
name="Notification cleanup (daily)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_weekly_snapshot,
|
|
trigger="cron",
|
|
day_of_week="sun",
|
|
hour=0,
|
|
minute=0,
|
|
id="weekly_snapshot",
|
|
name="Weekly coverage snapshot (Sundays 00:00)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_recurring_campaigns,
|
|
trigger="interval",
|
|
hours=24,
|
|
id="recurring_campaigns",
|
|
name="Recurring campaigns check (daily)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
sync_all_jira_links,
|
|
trigger="interval",
|
|
hours=1,
|
|
id="jira_sync",
|
|
name="Jira link sync (hourly)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_osint_enrichment,
|
|
trigger="interval",
|
|
weeks=1,
|
|
id="osint_enrichment",
|
|
name="OSINT enrichment (weekly)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_stale_detection,
|
|
trigger="interval",
|
|
hours=24,
|
|
id="stale_detection",
|
|
name="Stale coverage detection (daily)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
run_retention_job,
|
|
trigger="interval",
|
|
hours=24,
|
|
id="retention_policies",
|
|
name="Data retention policies (daily)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.add_job(
|
|
_run_data_sources_sync,
|
|
trigger="interval",
|
|
hours=6,
|
|
id="data_sources_sync",
|
|
name="Data sources auto-sync (every 6h)",
|
|
replace_existing=True,
|
|
)
|
|
scheduler.start()
|
|
logger.info(
|
|
"Background scheduler started — mitre_sync (24h), intel_scan (7d), "
|
|
"notification_cleanup (24h), weekly_snapshot (Sundays 00:00), "
|
|
"recurring_campaigns (daily), jira_sync (1h), "
|
|
"osint_enrichment (weekly), stale_detection (daily), "
|
|
"retention_policies (daily), data_sources_sync (6h)"
|
|
)
|