microsoft/autogen · error · ValueError

model is required for when using a Github model with AzureAI

Error message

model is required for when using a Github model with AzureAIChatCompletionClient

What it means

Raised by AzureAIChatCompletionClient._validate_config when _is_github_model(config['endpoint']) is true (endpoint points at GitHub Models, e.g. https://models.github.ai/inference/) but no 'model' kwarg was given. GitHub Models hosts many models behind one endpoint, so the model id must be named explicitly.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/models/azure/_azure_ai_client.py:309

        config = self._validate_config(kwargs)  # type: ignore
        self._model_info = config["model_info"]  # type: ignore
        self._client = self._create_client(config)
        self._create_args = self._prepare_create_args(config)

        self._actual_usage = RequestUsage(prompt_tokens=0, completion_tokens=0)
        self._total_usage = RequestUsage(prompt_tokens=0, completion_tokens=0)

    @staticmethod
    def _validate_config(config: Dict[str, Any]) -> AzureAIChatCompletionClientConfig:
        if "endpoint" not in config:
            raise ValueError("endpoint is required for AzureAIChatCompletionClient")
        if "credential" not in config:
            raise ValueError("credential is required for AzureAIChatCompletionClient")
        if "model_info" not in config:
            raise ValueError("model_info is required for AzureAIChatCompletionClient")
        validate_model_info(config["model_info"])
        if _is_github_model(config["endpoint"]) and "model" not in config:
            raise ValueError("model is required for when using a Github model with AzureAIChatCompletionClient")
        return cast(AzureAIChatCompletionClientConfig, config)

    @staticmethod
    def _create_client(config: AzureAIChatCompletionClientConfig) -> ChatCompletionsClient:
        # Only pass the parameters that ChatCompletionsClient accepts
        # Remove 'model_info' and other client-specific parameters
        client_config = {k: v for k, v in config.items() if k not in ("model_info",)}
        return ChatCompletionsClient(**client_config)  # type: ignore

    @staticmethod
    def _prepare_create_args(config: Mapping[str, Any]) -> Dict[str, Any]:
        create_args = {k: v for k, v in config.items() if k in create_kwargs}
        return create_args

    def add_usage(self, usage: RequestUsage) -> None:
        self._total_usage = RequestUsage(
            self._total_usage.prompt_tokens + usage.prompt_tokens,
            self._total_usage.completion_tokens + usage.completion_tokens,

View on GitHub (pinned to 027ecf0a37)

Solutions

Add the model kwarg, e.g. model='openai/gpt-4o' (org/model format used by GitHub Models)
Alternatively point endpoint at an Azure AI Foundry deployment URL where the model is bound to the route
Double-check the endpoint string: anything matching the GitHub Models host triggers this requirement even if unintended

Example fix

# before
client = AzureAIChatCompletionClient(
    endpoint="https://models.github.ai/inference", credential=cred, model_info=info)

# after
client = AzureAIChatCompletionClient(
    endpoint="https://models.github.ai/inference", credential=cred,
    model="openai/gpt-4o", model_info=info,
)

Defensive patterns

Strategy: validation

Validate before calling

def github_needs_model(endpoint: str, cfg: dict) -> bool:
    return "models.github.ai" in endpoint and "model" not in cfg

Prevention

Always pass model when the endpoint host is models.github.ai
Use org/model ids (e.g. 'openai/gpt-4o') for GitHub Models
Add a config lint rule keyed on the endpoint URL

When it happens

Trigger: AzureAIChatCompletionClient(endpoint='https://models.github.ai/inference', credential=..., model_info=...) with model omitted.

Common situations: Using a GitHub personal access token against the Models inference endpoint and copying an Azure Foundry config that did not need 'model'; forgetting that model is only optional for non-GitHub endpoints.

Related errors

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/d0f18d32d59f3023. Report an issue: GitHub.