Bug: Everything works fine and then randomly the langgraph server errors and stops responding

[SethTurin]

Followed the local setup instructions, and used a local langgraph server setup. Everything works, but then after some amount of time, I'll get this very unspecific error. After the error, the server stops responding and thus the app stops working.

langgraph-api-1       |   File "/usr/local/lib/python3.12/asyncio/runners.py", line 194, in run
langgraph-api-1       |     return runner.run(main)
langgraph-api-1       |            ^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/usr/local/lib/python3.12/asyncio/runners.py", line 118, in run
langgraph-api-1       |     return self._loop.run_until_complete(task)
langgraph-api-1       |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "uvloop/loop.pyx", line 1512, in uvloop.loop.Loop.run_until_complete
langgraph-api-1       |   File "uvloop/loop.pyx", line 1505, in uvloop.loop.Loop.run_until_complete
langgraph-api-1       |   File "uvloop/loop.pyx", line 1379, in uvloop.loop.Loop.run_forever
langgraph-api-1       |   File "uvloop/loop.pyx", line 557, in uvloop.loop.Loop._run
langgraph-api-1       |   File "uvloop/loop.pyx", line 476, in uvloop.loop.Loop._on_idle
langgraph-api-1       |   File "uvloop/cbhandles.pyx", line 83, in uvloop.loop.Handle._run
langgraph-api-1       |   File "uvloop/cbhandles.pyx", line 63, in uvloop.loop.Handle._run
langgraph-api-1       |   File "/api/langgraph_api/graph.py", line 269, in _handle_exception
langgraph-api-1       | SystemExit: 1
langgraph-api-1       |
langgraph-api-1       | During handling of the above exception, another exception occurred:
langgraph-api-1       |
langgraph-api-1       | Traceback (most recent call last):
langgraph-api-1       |   File "/api/langgraph_api/lifespan.py", line 37, in lifespan
langgraph-api-1       |   File "/usr/local/lib/python3.12/site-packages/starlette/routing.py", line 700, in lifespan
langgraph-api-1       |     await receive()
langgraph-api-1       |   File "/usr/local/lib/python3.12/site-packages/uvicorn/lifespan/on.py", line 137, in receive
langgraph-api-1       |     return await self.receive_queue.get()
langgraph-api-1       |            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/usr/local/lib/python3.12/asyncio/queues.py", line 158, in get
langgraph-api-1       |     await getter
langgraph-api-1       | asyncio.exceptions.CancelledError
langgraph-api-1       |
langgraph-api-1       | During handling of the above exception, another exception occurred:
langgraph-api-1       |
langgraph-api-1       | Traceback (most recent call last):
langgraph-api-1       |   File "/usr/local/lib/python3.12/site-packages/starlette/routing.py", line 693, in lifespan
langgraph-api-1       |     async with self.lifespan_context(app) as maybe_state:
langgraph-api-1       |                ^^^^^^^^^^^^^^^^^^^^^^^^^^
langgraph-api-1       |   File "/usr/local/lib/python3.12/contextlib.py", line 231, in __aexit__
langgraph-api-1       |     await self.gen.athrow(value)```

[n-sviridenko]

Similar to langchain-ai/langgraph#1601

[bracesproul]

Hi @SethTurin we recently released an in memory server for LangGraph.js which is now the recommended method for running LangGraph.js locally for testing/development.

You can use the in mem server by running the yarn dev:server script!