From the source
GitHub added adaptive review effort, cross-repository context and secret detection to Copilot code review, all in public preview for Copilot Pro, Pro+, Max, Business and Enterprise plans.
- Adaptive picks a review depth for each pull request instead of leaving the choice to a person, choosing between Lite, Balanced or Max based on the change's complexity and risk, and each review shows which level it picked.
- It never picks a level above the maximum review effort set for the enterprise, organization or repository, and Balanced remains the default.
- Cross-repository context lets Copilot read related public repositories during a review to find code that depends on the change, and is in public preview for public repositories.
- Secret detection flags exposed credentials in review comments using deterministic detectors built with 150+ partners across 500+ secret types, plus LLM and a purpose-built model for secrets without a recognizable format.
- GitHub also made Copilot code review for Azure Repos generally available, billed in GitHub AI credits to the linked Azure subscription, and added repository insights for tracking how review feedback is addressed.





