BerriAI/litellm · error · Exception

Prop `type` is not a string

Error message

Prop `type` is not a string

What it means

Before sending messages to Bytez, LiteLLM normalizes each content part; this guard fires when a content-part dict has no 'type' key or a falsy 'type' (empty string/None). Every part must carry a non-empty type string so it can be looked up in open_ai_to_bytez_content_item_map.

Solutions

1. Give every content part a valid 'type' ("text", "image_url", "input_audio", "video_url").
2. Validate parts with a small helper before calling bytez models.
3. When wrapping plain strings, let litellm normalize by using a plain string content or {"type":"text","text":...}.

Example fix

# before
messages = [{"role": "user", "content": [{"text": "hi"}]}]

# after
messages = [{"role": "user", "content": [{"type": "text", "text": "hi"}]}]

def content_parts_valid(content: list) -> bool:
    return all(
        isinstance(p, dict) and isinstance(p.get("type"), str) and p["type"]
        for p in content
    )

def is_typed_content_part(part: object) -> bool:
    return isinstance(part, dict) and isinstance(part.get("type"), str) and len(part["type"]) > 0

try:
    litellm.completion(model="bytez/org/model", messages=messages)
except Exception as e:
    if "`type` is not a string" in str(e):
        messages = normalize_parts(messages)  # ensure every part has a type
        litellm.completion(model="bytez/org/model", messages=messages)
    else:
        raise

When it happens

Trigger: A message like {"role": "user", "content": [{"text": "hi"}]} (missing type), or {"type": "", "text": "hi"}; programmatically built parts where the type field was dropped; mixing raw strings inside a dict part by mistake.

Common situations: Hand-rolled prompt assemblers; parts produced by another SDK with different casing (e.g. 'kind' instead of 'type'); data corruption or empty dicts slipping into content lists.

Related errors

• Prop ` ` is not a string
• `content` can only contain strings or openai content dicts
• kwarg `messages` must be an array of messages that follow…
• Prop ` ` is not supported
• Each content item must be a dictionary

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/8cecb80d89894194. Report an issue: GitHub.

Appendix: source

Thrown at litellm/llms/bytez/chat/transformation.py:393

}


def adapt_messages_to_bytez_standard(messages: list[dict]):
    messages = _adapt_string_only_content_to_lists(messages)

    new_messages: Final = []

    for message in messages:
        role = message["role"]
        content: list = message["content"]

        new_content = []

        for content_item in content:
            type: str | None = content_item.get("type")

            if not type:
                raise Exception("Prop `type` is not a string")

            content_item_map = open_ai_to_bytez_content_item_map[type]

            if not content_item_map:
                raise Exception(f"Prop `{type}` is not supported")

            new_type = content_item_map["type"]

            value_name = content_item_map["value_name"]

            value: str | None = content_item.get(value_name)

            if not value:
                raise Exception(f"Prop `{value_name}` is not a string")

            new_content.append({"type": new_type, value_name: value})

        new_messages.append({"role": role, "content": new_content})

View on GitHub (pinned to 77b7c6c40c)