GitHub Copilot weekly release rolls out tiered auto model selection

What this rests on

1. Copilot code review now resolves addressed comments during subsequent reviews, leaving outstanding feedback open.

   GitHub Copilot weekly releases — September 14 · GitHub

2. GitHub says new efficiency, balance and intelligence tiers in Copilot auto model selection let users weigh cost, quality and response time; the update is rolling out in VS Code, Copilot CLI and the Copilot app

   narrowed to what the source supports
   GitHub Copilot weekly releases — September 14 · GitHub

3. The Copilot weekly release note includes a section of VS Code 1.138 release updates

   narrowed to what the source supports
   GitHub Copilot weekly releases — September 14 · GitHub

We checked every sentence above against its source by opening it. Nothing appears on this site that we have not opened and linked.

Filed under

• Agents reviewing and approving pull requests watching
• Tools choosing the model per task watching
• Code review
• GitHub
• GitHub Copilot
• Model routing
• VS Code

Also that week

• Models and releasesAnthropic released Claude Opus 5.5 with a 1M-token context window
• Models and releasesSpaceXAI released Grok 4.7 with a 500k-token context window
• Research worth knowingGoogle Research describes a generative-UI framework for classroom simulations