microsoft/autogen · error · ValueError

The model does not support function calling.

Error message

The model does not support function calling.

What it means

AssistantAgent raises this ValueError when the tools parameter is non-empty but the supplied model_client's model_info reports function_calling=False. The agent cannot emit tool calls without function-calling support, so it refuses at construction time.

Source

Thrown at python/packages/autogen-agentchat/src/autogen_agentchat/agents/_assistant_agent.py:774

                input_model=output_content_type, format_string=output_content_type_format
            )

        self._memory = None
        if memory is not None:
            if isinstance(memory, list):
                self._memory = memory
            else:
                raise TypeError(f"Expected Memory, List[Memory], or None, got {type(memory)}")

        self._system_messages: List[SystemMessage] = []
        if system_message is None:
            self._system_messages = []
        else:
            self._system_messages = [SystemMessage(content=system_message)]
        self._tools: List[BaseTool[Any, Any]] = []
        if tools is not None:
            if model_client.model_info["function_calling"] is False:
                raise ValueError("The model does not support function calling.")
            for tool in tools:
                if isinstance(tool, BaseTool):
                    self._tools.append(tool)
                elif callable(tool):
                    if hasattr(tool, "__doc__") and tool.__doc__ is not None:
                        description = tool.__doc__
                    else:
                        description = ""
                    self._tools.append(FunctionTool(tool, description=description))
                else:
                    raise ValueError(f"Unsupported tool type: {type(tool)}")
        # Check if tool names are unique.
        tool_names = [tool.name for tool in self._tools]
        if len(tool_names) != len(set(tool_names)):
            raise ValueError(f"Tool names must be unique: {tool_names}")

        # Handoff tools.
        self._handoff_tools: List[BaseTool[Any, Any]] = []

View on GitHub (pinned to 027ecf0a37)

Solutions

  1. Use a model/client combination that supports function calling (most current OpenAI/Azure models).
  2. If the model does support tools but model_info is wrong, pass a corrected model_info to the client constructor with function_calling=True.
  3. If the model truly has no tool support, remove the tools parameter (and handoffs/workbench) from the agent.

Example fix

# before
client = OpenAIChatCompletionClient(model="local-70b", model_info={"function_calling": False, ...})
agent = AssistantAgent(name="a", model_client=client, tools=[my_tool])

# after
client = OpenAIChatCompletionClient(model="local-70b-tool", model_info={"function_calling": True, ...})
agent = AssistantAgent(name="a", model_client=client, tools=[my_tool])
Defensive patterns

Strategy: validation

Validate before calling

info = model_client.model_info
if tools and not info.get("function_calling", False):
    raise ValueError(f"model {info.get('family')} lacks function calling; cannot attach tools")

Type guard

def supports_tools(client) -> bool:
    return bool(client.model_info.get("function_calling", False))

Try / catch

try:
    agent = AssistantAgent(name="a", model_client=client, tools=tools)
except ValueError as e:
    if "does not support function calling" in str(e):
        agent = AssistantAgent(name="a", model_client=client)  # degrade to no tools
    else:
        raise

Prevention

When it happens

Trigger: Constructing AssistantAgent(tools=[...]) with a model client whose model_info entry lacks or falsifies 'function_calling' — e.g. some open-source/local model client configs, OpenAIChatCompletionClient(model_info=...) for non-tool models, or replay/prototype clients.

Common situations: Swapping a GPT client for a local or legacy model without updating model_info, custom model client subclasses returning incomplete model_info dicts, or using a model that genuinely lacks tool support.

Related errors

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/14210657b8734a28. Report an issue: GitHub.