BerriAI/litellm · error · OCIError

Tool call `function` must be a dictionary

Error message

Tool call `function` must be a dictionary

What it means

Inside each tool call dict, the 'function' member must itself be a dictionary containing the tool name and arguments. If 'function' is missing, None, a string, or any non-dict value, OCIError(400) 'Tool call `function` must be a dictionary' is raised during OCI request construction.

Source

Thrown at litellm/llms/oci/chat/generic.py:129

    )


def adapt_messages_to_generic_oci_standard_tool_call(role: str, tool_calls: list) -> OCIMessage:
    """Convert an assistant tool-call message to OCI format."""
    tool_calls_formatted: Final = []
    for tool_call in tool_calls:
        if not isinstance(tool_call, dict):
            raise OCIError(status_code=400, message="Each tool call must be a dictionary")
        if tool_call.get("type") != "function":
            raise OCIError(status_code=400, message="OCI only supports function tool calls")

        tool_call_id = tool_call.get("id")
        if not isinstance(tool_call_id, str):
            raise OCIError(status_code=400, message="Tool call `id` must be a string")

        tool_function = tool_call.get("function")
        if not isinstance(tool_function, dict):
            raise OCIError(status_code=400, message="Tool call `function` must be a dictionary")

        function_name = tool_function.get("name")
        if not isinstance(function_name, str):
            raise OCIError(status_code=400, message="Tool call `function.name` must be a string")

        arguments = tool_call["function"].get("arguments", "{}")
        if not isinstance(arguments, str):
            raise OCIError(
                status_code=400,
                message="Tool call `function.arguments` must be a JSON string",
            )

        tool_calls_formatted.append(
            OCIToolCall(
                id=tool_call_id,
                type="FUNCTION",
                name=function_name,
                arguments=arguments,

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Nest the descriptor: 'function': {'name': str, 'arguments': json_string}.
2. When converting from other formats, wrap flat name/arguments into the nested object before sending.
3. Validate structure with a pre-flight recursive check (see defense).

Example fix

# before
{'id':'c1','type':'function','name':'get_weather','arguments':'{}'}

# after
{'id':'c1','type':'function','function':{'name':'get_weather','arguments':'{}'}}

for tc in msg.get('tool_calls') or []:
    assert isinstance(tc.get('function'), dict), f"tool call 'function' must be a dict: {tc!r}"

def tool_call_has_function_dict(tc: object) -> bool:
    return isinstance(tc, dict) and isinstance(tc.get('function'), dict)

When it happens

Trigger: Sending tool calls like {'id':'c1','type':'function','function':'get_weather'} or omitting 'function' entirely when calling an oci/ GENERIC model with assistant tool-call history.

Common situations: Flattening the function object into sibling keys ({'name':..., 'arguments':...}) by mistake; JSON payloads built from tuples; serializers that drop nested objects on missing data.

Related errors

• Message `tool_calls` must be a list
• Each tool call must be a dictionary
• OCI only supports function tool calls
• Tool call `id` must be a string
• Tool call `function.name` must be a string

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/34bbc070b088fe9c. Report an issue: GitHub.