langchain-ai/deepagents · error · ModelConfigError

Class '{class_name}' not found in module '{module_path}' for

Error message

Class '{class_name}' not found in module '{module_path}' for provider '{provider}'

What it means

Raised when the configured `class_path` module imports fine but does not expose the named attribute. `_create_model_from_class` does `getattr(module, class_name, None)` and rejects None: a symbol that does not exist means the configured provider is unusable.

Source

Thrown at libs/code/deepagents_code/config.py:5394

            "must be in module.path:ClassName format"
        )
        raise ModelConfigError(msg)

    module_path, class_name = class_path.rsplit(":", 1)

    try:
        module = importlib.import_module(module_path)
    except ImportError as e:
        msg = f"Could not import module '{module_path}' for provider '{provider}': {e}"
        raise ModelConfigError(msg) from e

    cls = getattr(module, class_name, None)
    if cls is None:
        msg = (
            f"Class '{class_name}' not found in module '{module_path}' "
            f"for provider '{provider}'"
        )
        raise ModelConfigError(msg)

    if not (isinstance(cls, type) and issubclass(cls, _BaseChatModel)):
        msg = (
            f"'{class_path}' is not a BaseChatModel subclass (got {type(cls).__name__})"
        )
        raise ModelConfigError(msg)

    try:
        return cls(model=model_name, **kwargs)
    except Exception as e:
        msg = f"Failed to instantiate '{class_path}' for '{provider}:{model_name}': {e}"
        raise ModelConfigError(msg) from e


def _create_model_via_init(
    model_name: str,
    provider: str,
    kwargs: dict[str, Any],

View on GitHub (pinned to a1af029e6e)

Solutions

Check exports: `python -c "import my_pkg.models as m; print(dir(m))"`
Correct the class name after the colon in config.toml to the current symbol
Pin the custom package version if a newer release renamed the class

Example fix

// before (config.toml)
class_path = "my_pkg.models:MyChatModel"  # renamed upstream

// after
class_path = "my_pkg.models:MyChatModelV2"

Defensive patterns

Strategy: validation

Validate before calling

import importlib
def class_exists(class_path: str) -> bool:
    module_path, class_name = class_path.rsplit(":", 1)
    module = importlib.import_module(module_path)
    return hasattr(module, class_name)

Type guard

def is_exported_class(module: object, class_name: str) -> bool:
    import types
    attr = getattr(module, class_name, None)
    return isinstance(attr, type)

Try / catch

from deepagents_code.model_config import ModelConfigError
try:
    model = create_model(spec, class_path=class_path)
except ModelConfigError as e:
    if "not found in module" in str(e):
        import importlib
        m = importlib.import_module(class_path.rsplit(":", 1)[0])
        raise SystemExit(f"Available: {[n for n in dir(m) if not n.startswith('_')]}" )
    raise

Prevention

Verify symbol names after every upgrade of the custom model package
Pin the package version in lock files to avoid surprise renames
Use dir(module) to confirm the exact exported class name

When it happens

Trigger: `class_path` resolves to an importable module but `ClassName` after the colon is not an attribute of it — the class was renamed, moved modules, the name is misspelled, or case does not match (config.py:5388-5394).

Common situations: Upgrading a custom model package where the class was renamed; copying `class_path` from older docs; pointing at a module that re-exports under a different name; case mistakes (`Chatmodel` vs `ChatModel`).

Related errors

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/baf41967f6c177f1. Report an issue: GitHub.