为 Copilot 云端代理自定义推理级别

当你将任务委派给 GitHub Copilot 云端代理时，现在可以为支持该功能的模型设置推理级别。

这使你能够控制模型在响应前进行多少推理。更高的级别可以改善复杂问题的回答质量，但会消耗更多 token，因此也会使用更多额度。

启动任务时，可在选择模型的同时选择推理级别，Copilot 云端代理将在本次运行中使用该设置。

该功能适用于所有包含 Copilot 云端代理的付费 Copilot 套餐（即 Copilot Pro、Pro+、Business、Enterprise 和 Max）。

欲了解更多信息，请参阅我们的文档：为你的任务选择合适的 AI 模型。

When you delegate a task to GitHub Copilot cloud agent, you can now set the reasoning level for models that support it.

This allows you to control how much the model reasons before it responds. A higher level can improve answers to complex problems, but it consumes more tokens, and therefore more credits.

Pick a reasoning level alongside the model when you start a task, and Copilot cloud agent will use it for the run.

This is available on all paid Copilot plans that include Copilot cloud agent (i.e., Copilot Pro, Pro+, Business, Enterprise, and Max).

To learn more, see our documentation on choosing the right AI model for your task.