Copilot code review settings can now be managed through the REST and GraphQL APIs

GitHub's changelog, November 6, 2026, says Copilot code review settings can be read and updated through the REST and GraphQL APIs, at enterprise, organization and repository level. The update is available on Copilot Pro, Pro+, Max, Business and Enterprise plans.

• API: reviews and comments carry explicit attribution fields, and the API can show the review effort used and which skills, MCP servers and custom instructions Copilot reported as sources for a comment. Enterprise admins can enable or disable code review for all organizations or leave the choice to organization admins; organization admins manage enablement, default effort and runner configuration; repository admins manage effort and whether reviews use custom instructions and MCP tools. The enterprise and organization endpoints do not support GitHub Apps or fine-grained personal access tokens; the repository endpoints do.
• Review overview: findings stay at the top, while the effort used and surveys move to a footer. Skipped and excluded files share one "Files not reviewed" section. A 👎 on an overview lets you pick a reason.
• Other changes: agent sessions show the AI credits a review consumed; the automatic-review repository rule supports a bypass list; on later reviews of a pull request, findings unrelated to recent changes are collapsed and then hidden; Balanced-effort reviews use three reviewer models plus one that combines their findings.
• Fixes: billing and preview settings are kept when code review is turned off and on; failed or timed-out reviews are retried once, and Copilot can switch to another eligible model; bot-authored pull requests can again get reviews requested by apps the organization owns when external Copilot licenses are blocked; false failure reports just after a review starts are gone.