Phase 5 (v2): Processing-Recovery, Retention-Cleanup, Replay-Delivery-Reset

- recover_stuck_events: Reset processing events stuck >120s back to pending
- cleanup_published_events: Delete published events older than 30 days
- Replay now resets outbox_deliveries for clean retry
- Worker: hourly retention cleanup cron job
- API: /recover-stuck and /cleanup-published endpoints
- process_outbox_batch: auto-recovery at start of each tenant iteration
- 23/23 tests passing (5 new tests)

app/routes/outbox.py

@@ -18,9 +18,11 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.core.db import get_db
 from app.core.outbox import (
+    cleanup_published_events,
     get_consumer_registry,
     get_failed_events,
     get_outbox_stats,
+    recover_stuck_events,
     replay_all_failed_events,
     replay_failed_event,
 )
@@ -128,3 +130,33 @@ async def outbox_consumer_registry(
     This is read from ``event_bus._handlers`` at request time.
     """
     return {"registry": get_consumer_registry()}
+
+
+@router.post("/recover-stuck")
+async def outbox_recover_stuck(
+    timeout_seconds: int = Query(120, ge=10, le=3600),
+    db: AsyncSession = Depends(get_db),
+    current_user: dict[str, Any] = Depends(require_admin),
+):
+    """Reset events stuck in 'processing' status back to 'pending'.
+
+    If a worker crashes mid-processing, events remain in 'processing' forever.
+    This endpoint resets events that have been in 'processing' longer than
+    *timeout_seconds* back to 'pending' so they can be retried.
+    """
+    count = await recover_stuck_events(db, timeout_seconds=timeout_seconds)
+    return {"recovered_count": count, "timeout_seconds": timeout_seconds}
+
+
+@router.post("/cleanup-published")
+async def outbox_cleanup_published(
+    retention_days: int = Query(30, ge=1, le=365),
+    db: AsyncSession = Depends(get_db),
+    current_user: dict[str, Any] = Depends(require_admin),
+):
+    """Delete published events older than *retention_days*.
+
+    Prevents the outbox table from growing indefinitely.
+    """
+    count = await cleanup_published_events(db, retention_days=retention_days)
+    return {"deleted_count": count, "retention_days": retention_days}