BerriAI/litellm · error · ValueError

messages is required

Error message

messages is required

What it means

validate_input_kwargs raises when 'messages' is missing from kwargs or is not a list. The bridge converts chat messages into Responses API input items, so a valid list of message dicts is mandatory. This is an internal-API contract check; normal litellm.completion calls always supply messages.

Source

Thrown at litellm/completion_extras/litellm_responses_transformation/handler.py:118

        return response

    def validate_input_kwargs(self, kwargs: dict) -> ResponsesToCompletionBridgeHandlerInputKwargs:
        from litellm import LiteLLMLoggingObj
        from litellm.types.utils import ModelResponse

        typed_kwargs: Final[dict[str, object]] = kwargs

        model: Final = typed_kwargs.get("model")
        if model is None or not isinstance(model, str):
            raise ValueError("model is required")

        custom_llm_provider: Final = typed_kwargs.get("custom_llm_provider")
        if custom_llm_provider is None or not isinstance(custom_llm_provider, str):
            raise ValueError("custom_llm_provider is required")

        messages: Final = typed_kwargs.get("messages")
        if messages is None or not isinstance(messages, list):
            raise ValueError("messages is required")

        optional_params: Final = typed_kwargs.get("optional_params")
        if optional_params is None or not isinstance(optional_params, dict):
            raise ValueError("optional_params is required")

        litellm_params: Final = typed_kwargs.get("litellm_params")
        if litellm_params is None or not isinstance(litellm_params, dict):
            raise ValueError("litellm_params is required")

        headers: Final = typed_kwargs.get("headers")
        if headers is None or not isinstance(headers, dict):
            raise ValueError("headers is required")

        model_response: Final = typed_kwargs.get("model_response")
        if model_response is None or not isinstance(model_response, ModelResponse):
            raise ValueError("model_response is required")

        logging_obj: Final = typed_kwargs.get("logging_obj")

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Pass messages as a list of role/content dicts: [{"role": "user", "content": "..."}]
2. Prefer litellm.completion(model=..., messages=[...]) which validates and forwards everything
3. Check upstream code that builds kwargs for a mutation that drops or replaces the messages key

Example fix

# before
kwargs = {"model": "gpt-4o", "messages": "hello"}

# after
kwargs = {"model": "gpt-4o", "messages": [{"role": "user", "content": "hello"}]}

def has_messages_kwarg(kwargs: dict) -> bool:
    return isinstance(kwargs.get("messages"), list) and len(kwargs["messages"]) > 0

def is_message_list(v) -> bool:
    return isinstance(v, list) and all(
        isinstance(m, dict) and isinstance(m.get("role"), str) for m in v
    )

When it happens

Trigger: Calling the bridge handler with kwargs where messages is None, a string, a single dict, or absent.

Common situations: Direct handler use in custom pipelines; passing a bare prompt string where a messages list is expected; tests with incomplete fixture data.

Related errors

• model is required
• custom_llm_provider is required
• optional_params is required
• litellm_params is required
• headers is required

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/94b47104eb3dcd64. Report an issue: GitHub.