fix(cloud-api): retry lifecycle iterations

apps/cloud-api/cloud_api/app.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import logging
 from collections.abc import Callable
 from contextlib import asynccontextmanager
 from dataclasses import dataclass
@@ -26,6 +27,7 @@ from core.models import utc_now
 
 
 DatabaseFactory = Callable[[CloudControlConfig], CloudDatabase]
+logger = logging.getLogger(__name__)
 
 
 class _RepositoryProxy:
@@ -159,7 +161,13 @@ async def _run_scheduler_loop(
     interval_seconds: float,
 ) -> None:
     while not stop.is_set():
-        services.scheduler.assign()
+        try:
+            services.scheduler.assign()
+        except Exception:
+            logger.exception(
+                "cloud lifecycle iteration failed",
+                extra={"worker": "scheduler"},
+            )
         if await _wait_for_stop(stop, interval_seconds):
             return
 
@@ -172,10 +180,16 @@ async def _run_lease_reaper_loop(
     max_attempts: int,
 ) -> None:
     while not stop.is_set():
-        services.repository.reap_expired_leases(
-            now=utc_now(),
-            max_attempts=max_attempts,
-        )
+        try:
+            services.repository.reap_expired_leases(
+                now=utc_now(),
+                max_attempts=max_attempts,
+            )
+        except Exception:
+            logger.exception(
+                "cloud lifecycle iteration failed",
+                extra={"worker": "lease_reaper"},
+            )
         if await _wait_for_stop(stop, interval_seconds):
             return