langchain-ai/langgraph · error · RuntimeError

AsyncThreadStream is closed and cannot be re-entered.

Error message

AsyncThreadStream is closed and cannot be re-entered.

What it means

Error "AsyncThreadStream is closed and cannot be re-entered." thrown in langchain-ai/langgraph.

Source

Thrown at libs/sdk-py/langgraph_sdk/_async/stream.py:1245

        self.values = _ValuesProjection(self)
        self.messages = _MessagesProjection(self, namespace=[])
        self.tool_calls = _ToolCallsProjection(self, namespace=[])
        self.subgraphs = _SubgraphsProjection(self, scope=())
        self.subagents = self.subgraphs
        self.extensions = _ExtensionsProjection(self, namespace=[])

    @property
    def _controller(self) -> AsyncThreadStream:
        """Return self as the subscription controller (duck-type compatible with StreamController).

        Exposes `_subscriptions` so tests can verify subscription counts via
        `thread._controller._subscriptions` without requiring a separate controller object.
        """
        return self

    async def __aenter__(self) -> AsyncThreadStream:
        if self._closed:
            raise RuntimeError("AsyncThreadStream is closed and cannot be re-entered.")
        transport_cls = (
            ProtocolWebSocketTransport
            if self._transport_kind == "websocket"
            else ProtocolSseTransport
        )
        self._transport = transport_cls(
            client=self._http.client,
            thread_id=self.thread_id,
            headers=self._headers,
            max_queue_size=self._max_queue_size,
        )
        # Create the run-done future here (async context guarantees a running loop).
        self._run_done = asyncio.get_running_loop().create_future()
        # Start the lifecycle watcher immediately so reattach and thread.output
        # work without a preceding run.start call.
        self._ensure_lifecycle_watcher_running()
        return self

View on GitHub (pinned to 38031739e5)

When it happens

Trigger: Thrown at libs/sdk-py/langgraph_sdk/_async/stream.py:1245 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of langchain-ai/langgraph@38031739e5 (2026-08-26). Data as JSON: /api/errors/848263ef993ad4de. Report an issue: GitHub.