AI TrackerGet the app
← All news
GitHub CopilotCodingProducts

Copilot code review adds Adaptive effort, cross-repository context and secret detection

GitHub says three new Copilot code review features are in public preview for Copilot Pro, Pro+, Max, Business and Enterprise.

  • Adaptive. Copilot judges each pull request's complexity and risk and reviews it at Lite, Balanced or Max effort, showing which level it picked. It can be chosen from the Reviewers bar or set as the default in personal, repository, organization or enterprise settings; Balanced remains the default, and Adaptive never goes above the maximum effort configured for the enterprise, organization or repository.
  • Cross-repository context. Reviews can read related public repositories, including code that depends on the change, documentation, custom instructions and skills.
  • Secret detection. Review comments flag exposed credentials using deterministic detectors (500+ secret types built with GitHub's secret scanning partners) and LLM-based detection for secrets with no recognizable format. It is turned on under Copilot > Code review in repository or organization settings.

GitHub also says Copilot code review for Azure Repos is now generally available, with branch-policy triggers, Lite and Balanced effort levels, custom instructions and skills, and billing in GitHub AI credits to the linked Azure subscription. A new Repository insights page in each repository's Insights tab shows how Copilot review comments were addressed: comments and high-severity comments addressed, pull requests with no later human change request, and merged pull requests without a Copilot review. The same metrics are in the Copilot usage metrics API.

Get news like this as a push.

AI Tracker alerts you when something changes for the tools you use.

Get the app