What causes "Model is required!" in FoundationAgents/MetaGPT?

Pass an explicit model id, e.g. 'qwen-max', 'qwen-plus', 'qwen-turbo'.

FoundationAgents/MetaGPT · error · ModelRequired

Model is required!

Error message

Model is required!

What it means

Companion guard in DashScope Generation.acall: after the prompt/messages check, a falsy model (None or '') raises ModelRequired('Model is required!'). The model positional must be a non-empty string naming a DashScope model.

Source

Thrown at metagpt/provider/dashscope_api.py:122

    return request


class AGeneration(Generation, BaseAioApi):
    @classmethod
    async def acall(
        cls,
        model: str,
        prompt: Any = None,
        history: list = None,
        api_key: str = None,
        messages: List[Message] = None,
        plugins: Union[str, Dict[str, Any]] = None,
        **kwargs,
    ) -> Union[GenerationResponse, AsyncGenerator[GenerationResponse, None]]:
        if (prompt is None or not prompt) and (messages is None or not messages):
            raise InputRequired("prompt or messages is required!")
        if model is None or not model:
            raise ModelRequired("Model is required!")
        task_group, function = "aigc", "generation"  # fixed value
        if plugins is not None:
            headers = kwargs.pop("headers", {})
            if isinstance(plugins, str):
                headers["X-DashScope-Plugin"] = plugins
            else:
                headers["X-DashScope-Plugin"] = json.dumps(plugins)
            kwargs["headers"] = headers
        input, parameters = cls._build_input_parameters(model, prompt, history, messages, **kwargs)

        api_key, model = BaseAioApi._validate_params(api_key, model)
        request = build_api_arequest(
            model=model,
            input=input,
            task_group=task_group,
            task=Generation.task,
            function=function,
            api_key=api_key,

View on GitHub (pinned to 11cdf466d0)

Solutions

Pass an explicit model id, e.g. 'qwen-max', 'qwen-plus', 'qwen-turbo'.
Validate/fail fast at startup that the configured model name is non-empty.
Check the provider config (models.yaml dashscope entry) has its model field set.

Example fix

// before
resp = await Generation.acall(model=os.getenv("DS_MODEL"), prompt="hi")  # None if unset

// after
model = os.environ["DS_MODEL"]  # fail fast if missing
resp = await Generation.acall(model=model, prompt="hi")

Defensive patterns

Strategy: validation

Validate before calling

def model_ok(model) -> bool:
    return isinstance(model, str) and bool(model.strip())

assert model_ok(cfg_model), f"model must be a non-empty string, got {cfg_model!r}"

Type guard

def is_nonempty_model_str(m: object) -> bool:
    return isinstance(m, str) and len(m.strip()) > 0

Try / catch

try:
    resp = await Generation.acall(model=model, prompt=prompt)
except Exception as e:
    if "Model is required" in str(e):
        raise ValueError(f"model unset; check env/config (got {model!r})") from e
    raise

Prevention

Fail fast at startup when a required model env var is missing.
Use os.environ[...] (KeyError) instead of os.getenv(...) for mandatory values.

When it happens

Trigger: Calling Generation.acall(model=None) or model=''; commonly when model is read from config/env and the key is missing, defaulting to None.

Common situations: Config-driven model names with a typo'd env var; version upgrades renaming model fields; failing to set the model in the dashscope LLM provider config.

Related errors

AI-assisted analysis of FoundationAgents/MetaGPT@11cdf466d0 (2026-08-14). Data as JSON: /api/errors/a41ee3faf6b11b95. Report an issue: GitHub.