Catching complex bugs with GitHub Copilot medium depth code review

GitHub introduces GitHub Copilot code review “medium depth” reviews (public preview), showing how the higher-reasoning review mode can produce longer, more thorough pull request feedback for complex logic and security-sensitive changes, and how admins can enable it at the repository or organization level.

Overview

GitHub Copilot code review adds a medium depth review option in public preview. The update routes pull requests to a higher reasoning model to provide longer and more thorough analysis, especially for:

• Complex logic
• Security-sensitive code
• Cross-service changes

The walkthrough focuses on how repository and organization admins can enable medium depth reviews, and includes a real-world example where the review catches a subtle logic issue involving integer math order of operations.