Skip to content
RRanked By Task

This Week

Copilot code review settings move to the API

GitHub's 6 November note lets the API manage Copilot code review settings, from an enterprise policy down to one repository.

Official source (opens in a new tab)

GitHub's changelog for 6 November 2026 says you can manage GitHub Copilot code review settings through the REST and GraphQL APIs, from enterprise policy down to individual repositories. The same update makes Copilot's review overview comment more compact. GitHub says the updates are available on Copilot Pro, Pro+, Max, Business, and Enterprise.

You could already request reviews, choose their effort, and read results through the REST API. The API can now mark Copilot's reviews and comments with attribution fields, show the review effort when that metadata is available, and show which skills, MCP servers, and custom instructions Copilot reported as sources for a comment. Repository administrators can manage review effort and whether reviews use custom instructions and MCP tools.

New review overviews keep findings at the top. Effort and surveys move into a compact footer. Skipped files and content-excluded files share one "Files not reviewed" section, with filenames and linked exclusion reasons. Empty sections are left out. GitHub also says failed or timed-out reviews are retried once, and Copilot can switch to another eligible model when the preferred one is unavailable. Billing and preview settings stay in place when you turn code review off and on again.

Who it's for: an admin who wants code review policy in the API, or a reviewer who wants a shorter overview on the pull request.

Fits: Best for Vibe Coding stays Cursor. GitHub Copilot stays the assistant that can review a pull request inside GitHub. The coding guide and the Copilot alternatives are unchanged. The verdict is unchanged.