langchain-ai/langgraph · error · ValueError

Expected input to call_model to have 'llm_input_messages' or

Error message

Expected input to call_model to have 'llm_input_messages' or 'messages' key, but got {state}

What it means

Error "Expected input to call_model to have 'llm_input_messages' or 'messages' key, but got {state}" thrown in langchain-ai/langgraph.

Source

Thrown at libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py:649

            elif remaining_steps < 2 and has_tool_calls:
                return True

        return False

    def _get_model_input_state(state: StateSchema) -> StateSchema:
        if pre_model_hook is not None:
            messages = (
                _get_state_value(state, "llm_input_messages")
            ) or _get_state_value(state, "messages")
            error_msg = f"Expected input to call_model to have 'llm_input_messages' or 'messages' key, but got {state}"
        else:
            messages = _get_state_value(state, "messages")
            error_msg = (
                f"Expected input to call_model to have 'messages' key, but got {state}"
            )

        if messages is None:
            raise ValueError(error_msg)

        _validate_chat_history(messages)
        # we're passing messages under `messages` key, as this is expected by the prompt
        if isinstance(state_schema, type) and issubclass(state_schema, BaseModel):
            state.messages = messages  # type: ignore
        else:
            state["messages"] = messages  # type: ignore

        return state

    # Define the function that calls the model
    def call_model(
        state: StateSchema, runtime: Runtime[ContextT], config: RunnableConfig
    ) -> StateSchema:
        if is_async_dynamic_model:
            msg = (
                "Async model callable provided but agent invoked synchronously. "
                "Use agent.ainvoke() or agent.astream(), or "

View on GitHub (pinned to 38031739e5)

When it happens

Trigger: Thrown at libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py:649 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/f0d86c6d5af33352. Report an issue: GitHub.