# current_effort_from_model_params

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/reasoning_effort/current_effort_from_model_params)

Read canonical or native effort settings using integration precedence.

This compatibility reader does not modify the supplied parameters. It only
reports settings that may come from `--model-params`, `/model`, or a resumed
thread.

## Signature

```python
current_effort_from_model_params(
    model_spec: str | None,
    model_params: dict[str, Any] | None,
) -> str | None
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `model_spec` | `str \| None` | Yes | `provider:model` spec for the active model. |
| `model_params` | `dict[str, Any] \| None` | Yes | Per-session model constructor parameters. |

## Returns

`str | None`

The effective configured effort, or `None` when none is recognized.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/caaa7e7c12d214afa5cf0a1afed8eb6232aa6f7b/libs/code/deepagents_code/reasoning_effort.py#L259)