langchain-ai/langgraph · error · TypeError

Expected `model` to be a ChatModel or RunnableBinding (e.g…

Error message

Expected `model` to be a ChatModel or RunnableBinding (e.g. model.bind_tools(...)), got {type}

What it means

Raised by _get_model() when the object passed as `model` to create_react_agent, after unwrapping RunnableBinding/RunnableSequence, is still not a BaseChatModel. The agent requires an actual chat model to bind tools to; passing a plain string, an arbitrary Runnable, or a non-chat wrapper triggers this guard.

Solutions

1. Pass a chat model instance, e.g. `init_chat_model("openai:gpt-4o")` or `ChatOpenAI(model="gpt-4o")`
2. If binding tools, pass `model.bind_tools(tools)` so the value is a RunnableBinding around a BaseChatModel
3. If using a RunnableSequence, include the BaseChatModel step so it can be extracted

When it happens

Trigger: Thrown at libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py:236 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/c3d661465be917e5. Report an issue: GitHub.

Appendix: source

Thrown at libs/prebuilt/langgraph/prebuilt/chat_agent_executor.py:236

def _get_model(model: LanguageModelLike) -> BaseChatModel:
    """Get the underlying model from a RunnableBinding or return the model itself."""
    if isinstance(model, RunnableSequence):
        model = next(
            (
                step
                for step in model.steps
                if isinstance(step, (RunnableBinding, BaseChatModel))
            ),
            model,
        )

    if isinstance(model, RunnableBinding):
        model = model.bound

    if not isinstance(model, BaseChatModel):
        raise TypeError(
            f"Expected `model` to be a ChatModel or RunnableBinding (e.g. model.bind_tools(...)), got {type(model)}"
        )

    return model


def _validate_chat_history(
    messages: Sequence[BaseMessage],
) -> None:
    """Validate that all tool calls in AIMessages have a corresponding ToolMessage."""
    all_tool_calls = [
        tool_call
        for message in messages
        if isinstance(message, AIMessage)
        for tool_call in message.tool_calls
    ]
    tool_call_ids_with_results = {
        message.tool_call_id for message in messages if isinstance(message, ToolMessage)

View on GitHub (pinned to 38031739e5)