langchain-ai/langgraph · error · TypeError

stream_events(version='v3') / astream_events(version='v3') d

Error message

stream_events(version='v3') / astream_events(version='v3') do not accept {', '.join(collisions)}; v3 owns these (stream_mode is built from the transformer mux, subgraphs is forced True so nested namespaces flow through scoped muxes).

What it means

Error "stream_events(version='v3') / astream_events(version='v3') do not accept {', '.join(collisions)}; v3 owns these (stream_mode is built from the transformer mux, subgraphs is forced True so nested namespaces flow through scoped muxes)." thrown in langchain-ai/langgraph.

Source

Thrown at libs/langgraph/langgraph/pregel/main.py:390

            bound=self._bound,
            retry_policy=self._retry_policy,
            cache_policy=self._cache_policy,
            timeout=self._timeout,
        )


# Kwargs that ``stream_events(version="v3")`` / ``astream_events(version="v3")``
# manage internally and must not be overridden by callers. ``stream_mode`` is
# derived from the transformer mux; ``subgraphs`` is forced True so nested
# namespaces flow through scoped muxes. Forwarding either to the inner
# ``stream(...)`` would silently break v3's invariants, so we raise instead.
_V3_INVARIANT_KWARGS: tuple[str, ...] = ("stream_mode", "subgraphs")


def _reject_v3_invariant_kwargs(kwargs: dict[str, Any]) -> None:
    collisions = [k for k in _V3_INVARIANT_KWARGS if k in kwargs]
    if collisions:
        raise TypeError(
            "stream_events(version='v3') / astream_events(version='v3') do "
            f"not accept {', '.join(collisions)}; v3 owns these "
            "(stream_mode is built from the transformer mux, subgraphs is "
            "forced True so nested namespaces flow through scoped muxes)."
        )


def _collect_stream_modes(mux: Any) -> list[StreamMode]:
    """Return the union of `required_stream_modes` across registered transformers.

    Transformers declare the stream modes they need to function, and
    `stream_events(version="v3")` asks the graph for exactly that union — no hardcoded
    default set. If zero transformers declare a given mode, the graph
    does not stream events for it.
    """
    modes: set[StreamMode] = set()
    for transformer in mux._transformers:
        modes.update(

View on GitHub (pinned to 38031739e5)

When it happens

Trigger: Thrown at libs/langgraph/langgraph/pregel/main.py:390 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/dd0116d9206c42a1. Report an issue: GitHub.