Customize the reasoning level for Copilot cloud agent
UpdateVerifiedAdded Sep 22, 2026
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.
Topics: AI agents, Pricing, Observability, Developer tools, Coding agents
Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.
More GitHub Copilot releases
Every GitHub Copilot release| Date | Release | Type |
|---|---|---|
| Aug 3 | Enterprise team specialization for managed settings Update | Update |
| Aug 3 | Trigger Copilot automations with comments Update | Update |
| Aug 4 | Retiring the Copilot Billing Preview app Deprecation | Deprecation |
| Aug 4 | Upcoming deprecation of GitHub Spark on github.com Deprecation | Deprecation |
| Aug 6 | Kimi K3 is now available in GitHub Copilot GA | GA |
| Jul 31 | Upcoming August 2026 model deprecations in GitHub Copilot Deprecation | Deprecation |
| Jul 31 | Gemini 2.5 Pro and Gemini 3 Flash deprecated Deprecation | Deprecation |
| Jul 31 | Enterprise teams model policy targeting in public preview Preview | Preview |
