microsoft/semantic-kernel · error · AgentInitializationException

Encountered unexpected response_format type: {resp_type}. Al

Error message

Encountered unexpected response_format type: {resp_type}. Allowed types are `json_object`  and `json_schema`.

What it means

Raised by configure_response_format() when the response_format dict has a 'type' value that is neither 'json_object' nor 'json_schema'. The dict branch only recognizes those two; any other type string (e.g. 'text', 'json', a typo) is rejected because the library cannot map it to a valid assistant response_format option.

Source

Thrown at python/semantic_kernel/agents/open_ai/openai_assistant_agent.py:675

        """
        if response_format is None or response_format == "auto":
            return None

        configured_response_format = None
        if isinstance(response_format, dict):
            resp_type = response_format.get("type")
            if resp_type == "json_object":
                configured_response_format = {"type": "json_object"}
            elif resp_type == "json_schema":
                json_schema = response_format.get("json_schema")  # type: ignore
                if not isinstance(json_schema, dict):
                    raise AgentInitializationException(
                        "If response_format has type 'json_schema', 'json_schema' must be a valid dictionary."
                    )
                # We're assuming the response_format has already been provided in the correct format
                configured_response_format = response_format  # type: ignore
            else:
                raise AgentInitializationException(
                    f"Encountered unexpected response_format type: {resp_type}. Allowed types are `json_object` "
                    " and `json_schema`."
                )
        elif isinstance(response_format, type):
            # If it's a type, differentiate based on whether it's a BaseModel subclass
            if issubclass(response_format, BaseModel):
                configured_response_format = type_to_response_format_param(response_format)  # type: ignore
            else:
                generated_schema = KernelJsonSchemaBuilder.build(parameter_type=response_format, structured_output=True)
                assert generated_schema is not None  # nosec
                configured_response_format = generate_structured_output_response_format_schema(
                    name=response_format.__name__, schema=generated_schema
                )
        else:
            # If it's not a dict or a type, throw an exception
            raise AgentInitializationException(
                "response_format must be a dictionary, a subclass of BaseModel, a Python class/type, or None"
            )

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Use only 'json_object' or 'json_schema' for the dict-form response_format.
2. Pass response_format=None or 'auto' for plain text output.
3. Sanitize user-supplied type values against {'json_object','json_schema'} before calling.

Example fix

# before
fmt = OpenAIAssistantAgent.configure_response_format({'type':'json'})

# after
fmt = OpenAIAssistantAgent.configure_response_format({'type':'json_object'})

ALLOWED = {'json_object', 'json_schema'}
if isinstance(response_format, dict):
    assert response_format.get('type') in ALLOWED, f"type must be one of {ALLOWED}"

def is_allowed_response_format_type(rf) -> bool:
    return not isinstance(rf, dict) or rf.get('type') in {None, 'json_object', 'json_schema'}

from semantic_kernel.exceptions.agent_exceptions import AgentInitializationException
try:
    fmt = OpenAIAssistantAgent.configure_response_format(response_format)
except AgentInitializationException as e:
    if 'unexpected response_format type' in str(e):
        fmt = OpenAIAssistantAgent.configure_response_format({'type':'json_object'})

When it happens

Trigger: Passing response_format={'type':'text'} or {'type':'json'}; a stray/typo type value; using an OpenAI Responses-API type name against the Assistant API which supports a smaller set.

Common situations: Mixing Assistant API and Responses API response_format vocabularies; typo in the type field; reading a type from user input without validating the allowed set.

Related errors

• If response_format has type 'json_schema', 'json_schema' mus
• response_format must be a dictionary, a subclass of BaseMode
• Failed to create OpenAI settings.
• The OpenAI API key is required.
• The OpenAI model ID is required.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/5b8b7afea6794192. Report an issue: GitHub.