langchain-ai/langgraph · error · RuntimeError

AsyncThreadStream is closed.

Error message

AsyncThreadStream is closed.

What it means

Error "AsyncThreadStream is closed." thrown in langchain-ai/langgraph.

Source

Thrown at libs/sdk-py/langgraph_sdk/_async/stream.py:146

        return False
    return data.get("event") in _ROOT_TERMINAL_LIFECYCLE_EVENTS


class _AgentModule:
    """Assistant graph helpers scoped to one thread stream."""

    def __init__(self, owner: AsyncThreadStream) -> None:
        self._owner = owner

    async def get_tree(
        self,
        *,
        xray: int | bool = False,
        headers: Mapping[str, str] | None = None,
        params: QueryParamTypes | None = None,
    ) -> dict[str, list[dict[str, Any]]]:
        if self._owner._closed:
            raise RuntimeError("AsyncThreadStream is closed.")
        query_params: dict[str, Any] = {}
        if xray:
            query_params["xray"] = xray
        if params:
            query_params.update(dict(params))
        request_headers = {**self._owner._headers, **dict(headers or {})}
        return await self._owner._http.get(
            f"/assistants/{self._owner.assistant_id}/graph",
            params=query_params,
            headers=request_headers or None,
        )


class RunModule:
    """Command dispatcher for `run.start`.

    Bound to one `AsyncThreadStream`; accesses its transport and id allocator.
    """

View on GitHub (pinned to 38031739e5)

When it happens

Trigger: Thrown at libs/sdk-py/langgraph_sdk/_async/stream.py:146 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/68fcd2b1b7df11cc. Report an issue: GitHub.