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/core/worker.py

@@ -256,6 +256,44 @@ async def process_outbox_job(ctx: dict[str, Any]) -> None:
 register_job("process_outbox", process_outbox_job)
 
 
+# ── Outbox retention cleanup job ─────────────────────────────────────────────
+
+async def cleanup_outbox_job(ctx: dict[str, Any]) -> None:
+    """Delete published outbox events older than 30 days.
+
+    Runs hourly to prevent the outbox table from growing indefinitely.
+    Iterates per-tenant for RLS compliance.
+    """
+    from app.core.db import get_worker_session_factory
+    from app.core.outbox import cleanup_published_events
+    from sqlalchemy import text as sa_text
+
+    factory = get_worker_session_factory()
+    async with factory() as db:
+        try:
+            tenant_result = await db.execute(sa_text("SELECT id FROM tenants"))
+            tenant_ids = [row[0] for row in tenant_result]
+
+            total_deleted = 0
+            for tenant_id in tenant_ids:
+                await db.execute(
+                    sa_text("SELECT set_config('app.current_tenant_id', :tid, true)"),
+                    {"tid": str(tenant_id)},
+                )
+                deleted = await cleanup_published_events(db, retention_days=30)
+                total_deleted += deleted
+                await db.commit()
+
+            if total_deleted:
+                logger.info("Outbox retention: cleaned up %d published events", total_deleted)
+        except Exception:
+            logger.error("Outbox retention cleanup failed", exc_info=True)
+            await db.rollback()
+
+
+register_job("cleanup_outbox", cleanup_outbox_job)
+
+
 class WorkerSettings:
     """ARQ worker settings."""
     functions = get_all_jobs()
@@ -280,4 +318,9 @@ class WorkerSettings:
             _wrap_cron_with_lock("process_outbox", process_outbox_job, ttl_seconds=30),
             second={0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55},
         ),
+        # Outbox retention cleanup — hourly
+        cron(
+            _wrap_cron_with_lock("cleanup_outbox", cleanup_outbox_job, ttl_seconds=300),
+            minute=0,
+        ),
     ]