BerriAI/litellm · error · ValueError

Message must be a dictionary

Error message

Message {i} must be a dictionary

What it means

Raised while iterating a Converse-format messages list: element i is not a dict. Each message must be an object with role/content keys; a non-dict element (string, number, nested list) fails per-index validation and the message includes the offending index.

Solutions

1. Find element i named in the error and wrap/convert it into {'role': ..., 'content': ...}
2. Parse JSON strings before insertion: json.loads(m) if isinstance(m, str) and m.startswith('{')
3. Sanitize the list upstream: messages = [m for m in messages if isinstance(m, dict)] plus explicit conversion of stragglers

Example fix

# before
messages = ['hello', {'role': 'assistant', 'content': 'hi'}]

# after
messages = [
    {'role': 'user', 'content': 'hello'},
    {'role': 'assistant', 'content': 'hi'},
]

def assert_all_messages_are_dicts(messages: list) -> None:
    for i, m in enumerate(messages):
        if not isinstance(m, dict):
            raise TypeError(f'message {i} is {type(m).__name__}, expected dict: {m!r:.80}')

def all_messages_dicts(messages: list) -> bool:
    return all(isinstance(m, dict) for m in messages)

try:
    handler.count_tokens(body)
except ValueError as e:
    m = re.search(r'Message (\d+) must be a dictionary', str(e))
    if m:
        i = int(m.group(1))
        body['messages'][i] = normalize_to_message(body['messages'][i])  # str -> {'role':'user','content':s}
        handler.count_tokens(body)
    else:
        raise

When it happens

Trigger: messages=['hello', {...}] (mixed raw strings and message objects); messages=[[{...}]] (extra nesting); messages containing JSON strings that were never parsed: messages=['{"role": "user"}'].

Common situations: Concatenating user-typed input directly into the list; LLM-generated request bodies with inconsistent shapes; pipelines that sometimes emit content-only strings instead of {role, content} dicts.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• Message must have a 'content' field
• Message must have a 'role' field
• messages must be a list
• messages parameter is required for Converse input
• model parameter is required

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/34736f53a762b65d. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bedrock/count_tokens/transformation.py:271

            ValueError: If the request is invalid
        """
        if not request_data.get("model"):
            raise ValueError("model parameter is required")

        input_type: Final = self._detect_input_type(request_data)

        if input_type == "converse":
            # Validate Converse format (messages-based)
            messages: Final = request_data.get("messages", [])
            if not messages:
                raise ValueError("messages parameter is required for Converse input")

            if not isinstance(messages, list):
                raise ValueError("messages must be a list")

            for i, message in enumerate(messages):
                if not isinstance(message, dict):
                    raise ValueError(f"Message {i} must be a dictionary")

                if "role" not in message:
                    raise ValueError(f"Message {i} must have a 'role' field")

                if "content" not in message:
                    raise ValueError(f"Message {i} must have a 'content' field")
        else:
            # For InvokeModel format, we need at least some content to count tokens
            # The content structure varies by model, so we do minimal validation
            if len(request_data) <= 1:  # Only has 'model' field
                raise ValueError("Request must contain content to count tokens")

View on GitHub (pinned to 77b7c6c40c)