Summary
On September 11, 2026, GitHub shipped updates to Copilot code review: it now resolves its own review comments once you address them, writes commit messages when you apply its suggestions, and uses a broader set of shell tools to validate the code it reviews. An ensemble of agents produces a more thorough review even at the Lite effort level.
What changed
GitHub updated Copilot code review on September 11, 2026 to auto-resolve addressed comments, auto-generate commit messages for applied suggestions, run shell tools to validate reviewed code, and use a multi-agent ensemble at the Lite effort level.
Why it matters
Self-resolving comments and validation-by-execution cut review-loop noise and move Copilot from suggesting to verifying changes, tightening the automated-review workflow that increasingly gates merges. It raises the baseline of what a 'lite' AI review does before a human looks.
Evidence excerpt
Copilot code review now resolves its own comments once you address them and writes smart commit messages for you when you apply its code suggestions. Copilot now uses a broader set of shell tools to validate the code it reviews, and an ensemble of agents produce a more thorough review within the Lite effort level.