langchain-ai/deepagents · error · ModelConfigError

Invalid model configuration for '{provider}:{model_name}': {

Error message

Invalid model configuration for '{provider}:{model_name}': {e}

What it means

Raised when the provider was resolved but `init_chat_model` raised ValueError/TypeError while constructing the model, meaning the spec/provider is known but the model configuration is invalid for that provider. The original exception is chained for diagnosis.

Source

Thrown at libs/code/deepagents_code/config.py:5509

                else:
                    install_hint = f"Install the '{package}' package manually"
                msg = (
                    f"Missing package for provider '{provider}'. "
                    f"{install_hint}, then retry with `/model`."
                )
            raise MissingProviderPackageError(
                msg, provider=provider, package=package
            ) from e
        raise ModelConfigError(msg) from e
    except (ValueError, TypeError) as e:
        if not provider:
            # Both app auto-detection and `init_chat_model`'s own inference
            # failed; surface a structured error so the UI can render the
            # docs URL as a clickable link.
            raise UnknownProviderError(model_spec=model_name) from e
        spec = f"{provider}:{model_name}"
        msg = f"Invalid model configuration for '{spec}': {e}"
        raise ModelConfigError(msg) from e
    except Exception as e:  # provider SDK auth/network errors
        spec = f"{provider}:{model_name}" if provider else model_name
        msg = f"Failed to initialize model '{spec}': {e}"
        raise ModelConfigError(msg) from e


@dataclass(frozen=True)
class ModelResult:
    """Result of creating a chat model, bundling the model with its metadata.

    This separates model creation from runtime-state mutation so callers can
    decide when to commit the metadata to process-wide state.

    Attributes:
        model: The instantiated chat model.
        model_name: Resolved model name.
        provider: Resolved provider name.
        context_limit: Max input tokens from the model profile, or `None`.

View on GitHub (pinned to a1af029e6e)

Solutions

1. Verify the model name is valid for the named provider and correct the spec.
2. Read the chained exception (raised `from e`) for the underlying cause.
3. Check extra_kwargs / config.toml model kwargs for invalid or renamed options.
4. Upgrade the provider package (e.g. langchain-openai) in case the model id is newer than the integration supports.

Example fix

// before
model = create_model("anthropic:gpt-5.5")  # wrong provider for model
// after
model = create_model("openai:gpt-5.5")

try:
    result = create_model(spec)
except ModelConfigError as e:
    logger.error("%s (cause: %r)", e, e.__cause__)
    # fall back to a known-good default spec

When it happens

Trigger: `create_model('provider:model')` where the provider package is installed but the constructor rejects the arguments — e.g. an unknown/unsupported model name for that provider, or invalid extra_kwargs / retry kwargs passed through.

Common situations: Model ID not offered by the named provider ('anthropic:gpt-4'), deprecated model removed from the provider SDK, config.toml kwargs incompatible with the provider class version.

Related errors

• Unable to infer a model provider for {model_spec!r}. Specify
• Could not apply {label} to model '{model_name}': {exc}. The
• Invalid model spec '{model_spec}': model name is required (e
• modes can only be provided when agent is a factory
• models can only be provided when agent is a factory

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/9afe0d627e4dd025. Report an issue: GitHub.