Copilot code review adds Adaptive, which picks review effort per pull request by complexity and risk, and can flag exposed secrets during review
No more picking a review level by hand for every PR, and cross-repository context and secret detection join the public preview. The three features and their admin limits, for teams using Copilot for code review.
// Key points
- Adaptive (public preview) chooses Lite, Balanced or Max for each PR based on its complexity and risk and shows which it picked; it never goes above the maximum set for the enterprise, organization or repository, and Balanced stays the default.
- Cross-repository context (public preview, public repositories): reviews can read related public repositories to find code that depends on the change, plus documentation, custom instructions and skills stored elsewhere.
- Secret detection (public preview) uses regex for 500+ known secret types from 150+ partners, and LLMs plus GitHub's own model to find secrets with no recognizable format.
- The features are for Copilot Pro, Pro+, Max, Business and Enterprise; each repository's Insights tab now shows how code review feedback is addressed.
Builder's takeI would make Adaptive the repo default but cap the maximum at Balanced for two weeks, see how many PRs it rates Lite, and only then open up Max, so cost does not creep up quietly. Turn secret detection on now: coding agents dropping a test key into config is common. Read with the 11-13 AI Scan API item, GitHub is filling in code security quickly.
// Background · from #Coding agents
Full timeline →- Nov 18 OpenAI releases GPT-6.2 Astra and GPT-6.2 Sol, with better professional outputs, coding, computer use and efficiency at lower cost
- Nov 18 Microsoft Ignite: MAI Code 2 and Code 2 Flash coding models, MAI Licensed Weights for trusted customers, and over 50 million agents in Agent 365
- Nov 18 GitHub Copilot Evals enters public preview: use /eval to write repeatable tests for your own skills, custom agents and MCP tools