Customize the reasoning level for Copilot cloud agent
GitHub Copilot cloud agent now supports customizable reasoning levels for compatible models, allowing you to control the depth of analysis when delegating tasks.
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.
The post Customize the reasoning level for Copilot cloud agent appeared first on The GitHub Blog.
Source: original entry ↗
More from GitHub
Follow GitHub to get its new changes in your feed and email digest.
Copilot model policy API for enterprise, orgs, and teams
REST API endpoints now available to retrieve and update Copilot model policies for enterprises, teams, apps, and organizations, enabling centralized policy management at scale.
GitHub Copilot models deprecated
GitHub has deprecated certain models across GitHub Copilot experiences including Chat, inline edits, and code completions, effective October 19, 2026. Users may need to migrate to supported models.
Some Git over HTTPS may temporarily require authentication
GitHub may temporarily require authentication for clones and fetches of public repositories over HTTPS during periods of unusual traffic to protect service availability.