langchain-ai/langgraph · error · TypeError

Object of type is not serializable

Error message

Object of type {obj.__class__.__name__} is not serializable

What it means

Terminal guard in JsonPlusSerializer's msgpack encoder (_msgpack_default): while packing a checkpoint value, an object was reached that has none of the supported special-case handlers (bytes/bytearray, datetime/date/time/timedelta, UUID, Enum, numpy scalar/array, dataclasses with to_json, sets, Counter, maps, AgentChatMessage, etc.). The object's type name is included in the message.

Solutions

1. Keep checkpoint/state values to JSON-friendly primitives (dict, list, str, int, float, bool, None)
2. Convert custom objects to dicts before storing them in state, and reconstruct them after loading
3. If the type is genuinely needed and trusted, enable pickle fallback on the serializer (pickle_fallback=True)

When it happens

Trigger: Thrown at libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:534 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/ec89b3fe92636a50. Report an issue: GitHub.

Appendix: source

Thrown at libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py:534

        obj, np_mod.ndarray
    ):
        order = "F" if obj.flags.f_contiguous and not obj.flags.c_contiguous else "C"
        if obj.flags.c_contiguous:
            mv = memoryview(obj)
            try:
                meta = (obj.dtype.str, obj.shape, order, mv)
                return ormsgpack.Ext(EXT_NUMPY_ARRAY, _msgpack_enc(meta))
            finally:
                mv.release()
        else:
            buf = obj.tobytes(order="A")
            meta = (obj.dtype.str, obj.shape, order, buf)
            return ormsgpack.Ext(EXT_NUMPY_ARRAY, _msgpack_enc(meta))

    elif isinstance(obj, BaseException):
        return repr(obj)
    else:
        raise TypeError(f"Object of type {obj.__class__.__name__} is not serializable")


def _send_from_args(args: Sequence[Any]) -> Any:
    # ya we have a cyclic import here ¯\_(ツ)_/¯
    from langgraph.types import Send  # type: ignore

    if len(args) == 2:
        return Send(*args)
    return Send(args[0], args[1], timeout=args[2])


def _create_msgpack_ext_hook(
    allowed_modules: set[tuple[str, ...]] | Literal[True] | None,
) -> Callable[[int, bytes], Any]:
    """Create msgpack ext hook with allowlist.

    Args:
        allowed_modules: Set of (module, name) tuples that are allowed to be

View on GitHub (pinned to 38031739e5)