---
title: "SubagentReasoning"
---

Reasoning configuration forwarded to the subagent call. Use this to control reasoning effort and token budget for models that support extended thinking.


## Fields

| Field                                                                                                                       | Type                                                                                                                        | Required                                                                                                                    | Description                                                                                                                 |
| --------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- |
| `effort`                                                                                                                    | [Optional[components.SubagentReasoningEffort]](../components/subagentreasoningeffort.mdx)                                    | :heavy_minus_sign:                                                                                                          | Reasoning effort level for the subagent call.                                                                               |
| `max_tokens`                                                                                                                | *Optional[int]*                                                                                                             | :heavy_minus_sign:                                                                                                          | Maximum number of reasoning tokens the subagent may use. Accepted and validated but not yet forwarded to the subagent call. |