microsoft/semantic-kernel · error · ServiceInvalidExecutionSettingsError

The settings must be an OpenAIChatPromptExecutionSettings.

Error message

The settings must be an OpenAIChatPromptExecutionSettings.

What it means

Raised in _verify_function_choice_settings when the settings object passed to the tool-call auto-invocation path is not an instance of OpenAIChatPromptExecutionSettings. This method is overridden from the base AI service to enforce that only OpenAI-specific execution settings carry the function-call configuration needed for tool invocation.

Source

Thrown at python/semantic_kernel/connectors/ai/open_ai/services/open_ai_chat_completion_base.py:143

                        content="",
                        choice_index=i,
                        inner_content=chunk,
                        ai_model_id=settings.ai_model_id,
                        metadata=chunk_metadata,
                        function_invoke_attempt=function_invoke_attempt,
                    )
                    for i in range(settings.number_of_responses or 1)
                ]
            else:
                yield [
                    self._create_streaming_chat_message_content(chunk, choice, chunk_metadata, function_invoke_attempt)
                    for choice in chunk.choices
                ]

    @override
    def _verify_function_choice_settings(self, settings: "PromptExecutionSettings") -> None:
        if not isinstance(settings, OpenAIChatPromptExecutionSettings):
            raise ServiceInvalidExecutionSettingsError("The settings must be an OpenAIChatPromptExecutionSettings.")
        if settings.number_of_responses is not None and settings.number_of_responses > 1:
            raise ServiceInvalidExecutionSettingsError(
                "Auto-invocation of tool calls may only be used with a "
                "OpenAIChatPromptExecutions.number_of_responses of 1."
            )

    @override
    def _update_function_choice_settings_callback(
        self,
    ) -> Callable[["FunctionCallChoiceConfiguration", "PromptExecutionSettings", FunctionChoiceType], None]:
        return update_settings_from_function_call_configuration

    @override
    def _reset_function_choice_settings(self, settings: "PromptExecutionSettings") -> None:
        if hasattr(settings, "tool_choice"):
            settings.tool_choice = None
        if hasattr(settings, "tools"):
            settings.tools = None

View on GitHub (pinned to c028a0c7dc)

Solutions

Pass OpenAIChatPromptExecutionSettings to the completion call, not the base PromptExecutionSettings
Use kernel.get_prompt_execution_settings_from_settings(settings) to auto-convert, or construct OpenAIChatPromptExecutionSettings directly
Ensure your kernel's service_id mapping resolves to the OpenAI chat service when expecting OpenAI settings

Example fix

# before
from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
settings = PromptExecutionSettings()
# after
from semantic_kernel.connectors.ai.open_ai import OpenAIChatPromptExecutionSettings
settings = OpenAIChatPromptExecutionSettings()

Defensive patterns

Strategy: type-guard

Validate before calling

from semantic_kernel.connectors.ai.open_ai import OpenAIChatPromptExecutionSettings

if not isinstance(settings, OpenAIChatPromptExecutionSettings):
    settings = OpenAIChatPromptExecutionSettings(**settings.model_dump() if hasattr(settings, 'model_dump') else {})

Type guard

from semantic_kernel.connectors.ai.open_ai import OpenAIChatPromptExecutionSettings

def is_openai_chat_settings(settings) -> bool:
    return isinstance(settings, OpenAIChatPromptExecutionSettings)

Prevention

Always construct provider-specific settings objects rather than passing the base class
If your code handles multiple providers, branch on provider type before calling the completion method

When it happens

Trigger: Calling a chat completion with auto-function-invocation enabled but passing a generic PromptExecutionSettings or a non-OpenAI settings subclass (e.g., a custom settings class) instead of OpenAIChatPromptExecutionSettings.

Common situations: Building a multi-provider abstraction that passes a base PromptExecutionSettings to all services; accidentally using settings from a different connector (e.g., Azure-specific or a third-party connector) with the OpenAI chat completion service; misconfigured kernel service-resolver that returns the wrong settings type.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/219b911f9162978a. Report an issue: GitHub.