microsoft/semantic-kernel · error · ServiceInvalidRequestError

Unsupported item type in Assistant message while formatting…

Error message

Unsupported item type in Assistant message while formatting chat history for Google AI Inference: {type(item)}

What it means

Raised by format_assistant_message when a ChatMessageContent item in an assistant-role message is not a TextContent, FunctionCallContent, or ImageContent. The Google AI assistant-message formatter serializes text, function calls (tool invocations), and images only. Any other item type (e.g. FunctionResultContent, BinaryContent) in an assistant message is unsupported.

Solutions

Ensure assistant messages contain only TextContent, FunctionCallContent, or ImageContent.
Move FunctionResultContent items into tool-role messages (add_message(role=AuthorRole.TOOL, ...)) rather than assistant messages.
Pre-validate assistant-message items before sending to the Google AI service.

Example fix

# before
history.add_message(
    role=AuthorRole.ASSISTANT,
    items=[TextContent(text='calling tool'), FunctionResultContent(id='1', name='search', result='{...}')],
)

# after
history.add_message(role=AuthorRole.ASSISTANT, items=[TextContent(text='calling tool')])
history.add_message(role=AuthorRole.TOOL, items=[FunctionResultContent(id='1', name='search', result='{...}')])

Defensive patterns

Strategy: type-guard

Validate before calling

from semantic_kernel.contents.text_content import TextContent
from semantic_kernel.contents.image_content import ImageContent
from semantic_kernel.contents.function_call_content import FunctionCallContent

ALLOWED = (TextContent, ImageContent, FunctionCallContent)
def validate_assistant_items(message):
    for item in message.items:
        if not isinstance(item, ALLOWED):
            raise TypeError(f'Unsupported assistant item type: {type(item).__name__}')

Type guard

from semantic_kernel.contents.text_content import TextContent
from semantic_kernel.contents.image_content import ImageContent
from semantic_kernel.contents.function_call_content import FunctionCallContent

def is_valid_assistant_item(item) -> bool:
    return isinstance(item, (TextContent, ImageContent, FunctionCallContent))

Prevention

Put FunctionResultContent in tool-role messages, not assistant messages.
Validate assistant-message items before sending to Google AI.
When migrating history from another connector, normalize item types per role.

When it happens

Trigger: An assistant-role ChatMessageContent whose items include a type outside {TextContent, FunctionCallContent, ImageContent}, then calling a chat completion method that formats chat history.

Common situations: Chat history replay where assistant messages were populated with FunctionResultContent instead of putting results in tool-role messages; cross-connector history migration; custom content subclasses in assistant items.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/8a9a0b04deffeed6. Report an issue: GitHub.

Appendix: source

Thrown at python/semantic_kernel/connectors/ai/google/google_ai/services/utils.py:116

                    Part(
                        function_call={
                            "name": item.name,  # type: ignore[arg-type]
                            "args": json.loads(item.arguments) if isinstance(item.arguments, str) else item.arguments,
                        },
                        thought_signature=thought_signature,
                    )
                )
            else:
                parts.append(
                    Part.from_function_call(
                        name=item.name,  # type: ignore[arg-type]
                        args=json.loads(item.arguments) if isinstance(item.arguments, str) else item.arguments,  # type: ignore[arg-type]
                    )
                )
        elif isinstance(item, ImageContent):
            parts.append(_create_image_part(item))
        else:
            raise ServiceInvalidRequestError(
                "Unsupported item type in Assistant message while formatting chat history for Google AI"
                f" Inference: {type(item)}"
            )

    return parts


def format_tool_message(message: ChatMessageContent) -> list[Part]:
    """Format a tool message to the expected object for the client.

    Args:
        message: The tool message.

    Returns:
        The formatted tool message.
    """
    parts: list[Part] = []
    for item in message.items:

View on GitHub (pinned to c028a0c7dc)