microsoft/semantic-kernel · error · ServiceInitializationError

The specified type `{type_value}` is not supported. Allowed

Error message

The specified type `{type_value}` is not supported. Allowed types are: `auto`, `none`, `required`.

What it means

Raised by FunctionChoiceBehavior.from_string when the provided string (lowercased) is not one of 'auto', 'none', or 'required'. from_string maps a behavior keyword to a behavior instance, so any other value is unsupported.

Source

Thrown at python/semantic_kernel/connectors/ai/function_choice_behavior.py:222

            filters=filters,
            **data,
        )

    @classmethod
    def from_string(cls: type[_T], data: str) -> _T:
        """Create a FunctionChoiceBehavior from a string.

        This method converts the provided string to a FunctionChoiceBehavior object
        for the specified type.
        """
        type_value = data.lower()
        if type_value == "auto":
            return cls.Auto()
        if type_value == "none":
            return cls.NoneInvoke()
        if type_value == "required":
            return cls.Required()
        raise ServiceInitializationError(
            f"The specified type `{type_value}` is not supported. Allowed types are: `auto`, `none`, `required`."
        )

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Use exactly one of: 'auto', 'none', or 'required' (case-insensitive).
2. Validate/whitelist the input string before calling from_string and surface a friendly error to the end user.
3. If you need richer config (filters, auto_invoke), use FunctionChoiceBehavior.from_dict or the Auto/NoneInvoke/Required classmethods directly.

Example fix

# before
behavior = FunctionChoiceBehavior.from_string("tool")
# after
behavior = FunctionChoiceBehavior.from_string("required")

ALLOWED = {"auto", "none", "required"}

def is_valid_behavior_string(value: str) -> bool:
    return isinstance(value, str) and value.lower() in ALLOWED

ALLOWED = {"auto", "none", "required"}

def is_function_choice_string(value: object) -> bool:
    return isinstance(value, str) and value.lower() in ALLOWED

from semantic_kernel.exceptions.service_exceptions import ServiceInitializationError

try:
    behavior = FunctionChoiceBehavior.from_string(raw)
except ServiceInitializationError as e:
    if "not supported" in str(e):
        raise ValueError(f"Invalid function choice '{raw}'. Use one of: auto, none, required") from e
    raise

When it happens

Trigger: Calling FunctionChoiceBehavior.from_string('tool'), from_string('always'), from_string(''), or any value outside the allowed set; a config-driven code path that feeds an unvalidated string into from_string.

Common situations: User config or CLI argument with a typo; expecting an OpenAI-style value like 'required'/'none'/'auto' but passing 'tools' or 'function'; migrating from an older API that accepted different keywords.

Related errors

• Values for filter key '{key}' are not lists.
• Invalid kernel selection. {selectedKernelName} is not a vali
• Azure AI Search tool definition must have both 'index_connec
• The option keys 'asset_identifiers' and 'asset_type' are req
• The option keys 'store_name' and 'data_sources' are required

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/20819997ac8269ce. Report an issue: GitHub.