From the source
GitHub now lets administrators manage Copilot code review settings through the REST and GraphQL APIs, from enterprise policy down to individual repositories.
- Enterprise administrators can enable or disable code review for all organizations or leave the choice to organization administrators, while organization administrators manage enablement, default review effort and runner configuration, and repository administrators manage review effort and whether reviews use custom instructions and MCP tools.
- Settings an enterprise manages cannot be overridden, and the enterprise and organization settings endpoints, including the organization runner endpoint, do not support GitHub Apps or fine-grained personal access tokens.
- The repository settings endpoints support both, requiring Administration: read permission to read settings and Administration: write permission to update them, while classic personal access tokens need repository administrator access.
- The API also adds explicit attribution fields for Copilot's reviews and comments, shows the review effort a review used when that metadata is available, and reports which skills, MCP servers and custom instructions Copilot cited as sources.
- The review overview comment is now more compact, with the review effort and surveys moved to a footer, skipped and content-excluded files sharing one "Files not reviewed" section, and empty sections left out.
- Copilot code review agent sessions now show the AI credits consumed in a review, and the Automatically request Copilot code review repository rule supports the bypass list.
- Balanced effort reviews now use three reviewer models with another model combining their findings, failed or timed-out reviews are retried once automatically, and Copilot can switch to another eligible model when the preferred one is unavailable.
- These updates are available to Copilot Pro, Pro+, Max, Business, and Enterprise plans.






