GitHub Copilot weekly releases — September 14

This week, GitHub Copilot adds new model selection options, code review updates, and Sentry integration in the Copilot app. There are also updates for admins, plus new agent features in VS Code.

• Copilot code review now resolves addressed comments during subsequent reviews, leaving outstanding feedback open. It also suggests commit messages when you apply its code suggestions. Reviews can use shell tools to validate changes, and Lite reviews now combine findings from multiple agents.
• Choose how Copilot weighs cost, quality, and response time with the new efficiency, balance, and intelligence tiers in auto model selection. All three tiers select from the same available models. This update is rolling out in VS Code, Copilot CLI, and the Copilot app.

• Measure adoption and activity in the dedicated VS Code Agents window with new usage metrics that are now generally available. Enterprise and organization reports include daily active users, session counts, and user message totals, alongside user-level activity data. These metrics are separate from the editor-window metrics.
• Get help choosing values for repository custom properties with Copilot suggestions, now in public preview. For example, when you create an internet-facing property, Copilot can suggest yes and no as allowed values. Organization and enterprise owners can turn suggestions on or off through a Copilot policy.
• Request a higher Copilot budget from your organization or enterprise when you reach your AI credit limit. Owners and billing managers can approve, adjust, or deny requests in settings. Approval restores access to AI credits. This is now generally available for Copilot Business and Copilot Enterprise plans with usage-based billing. This feature is not available for enterprises with managed users.

Fix production crashes from Sentry reports. Move from crash report to code fix with the new Sentry canvas in the GitHub Copilot app. Review errors, stack traces, and related context, then work with Copilot to investigate the cause, validate a fix, and prepare a pull request.

Download the Copilot app.

• Run agents with your project’s tools and dependencies using local Dev Containers in the Agents window. Support is rolling out gradually and requires both Docker and a supported Dev Container configuration.
• Automatically mark inactive sessions as Done once all their pull requests merge, with optional deletion after a separate grace period. Automatic cleanup is opt-in and now in preview.
• Create pull requests from Agent Host sessions without leaving the Agents window. Review the generated title and description, choose draft status, and create the pull request directly or ask your agent to do it.

Explore everything that’s new in the full release notes.