Re-raising here the issue now with production deployment after a 3d w/o any issues.
Several errors surrounding Redis:
[ERROR] Background worker scheduler failed
Traceback (most recent call last):
File "/usr/lib/python3.12/site-packages/langgraph_runtime_postgres/queue.py", line 312, in queue
async for run, attempt, encryption_context in Runs.next(
File "/api/langgraph_api/grpc/ops/runs.py", line 847, in next
File "/usr/lib/python3.12/site-packages/grpc/aio/_call.py", line 327, in __await__
raise _create_rpc_error(
grpc.aio._call.AioRpcError: <AioRpcError of RPC that terminated with:
status = StatusCode.INTERNAL
details = "failed to get next run from queue"
debug_error_string = "UNKNOWN:Error received from peer {grpc_message:"failed to get next run from queue", grpc_status:13}"
>
[ERROR] redis: 2026/04/02 16:52:44 pool.go:617: redis: connection pool: failed to dial after 5 attempts: dial tcp 192.168.103.108:6379: connect: connection refused
[ERROR] redis: 2026/04/02 16:52:43 pool.go:617: redis: connection pool: failed to dial after 5 attempts: dial tcp 192.168.103.108:6379: connect: connection refused
[ERROR] redis: 2026/04/02 16:52:42 pool.go:617: redis: connection pool: failed to dial after 5 attempts: dial tcp 192.168.103.108:6379: connect: connection refused
The deployment never actually reaches a stable state, it just keeps timing out on the Redis connection and rebooting.
Edit: after ~20min the deployment reached a stable state but this is unacceptable to our service uptime requirements. After ~10 consecutive or so runs it crashes again and the process repeats.
Is there anything we can do ensure the reliability of these infra upstream dependencies or are we essentially hands tied when using the managed cloud deployment ?
Thanks in advance