GitHub-native AI reviewer that reads diffs, leaves line-by-line comments, and suggests fixes. Catches bugs, security issues, and style drift before a human looks at the PR.
Configure external service connectors once, then use scopes to control access across Review, Slack, and Discord. Base and named scopes let security-sensitive repositories or channels be excluded from shared connections, reducing duplicate setup across products.
Teams can now configure chat.integrations.jira.issue_template to define custom Jira issue structures, ensuring CodeRabbit-created issues follow team standards instead of using default formatting.
Service configuration is now centralized with a single setup per connector, with scopes controlling usage across repositories and chat platforms. Base scopes define defaults while named scopes can override or exclude access for specific repositories or teams, allowing security-sensitive areas to restrict connector access.
Developers can configure custom Jira issue description structures through the chat.integrations.jira.issue_template setting instead of using CodeRabbit defaults. This ensures created issues match team formatting and field requirements.
Developers can now configure connectors once instead of separately for pull request reviews, Slack, and Discord. Named scopes control which products can use each connector in specific repositories or channels, eliminating duplicate setup and improving security control for sensitive repositories.
Enterprise organizations can now retrieve finding-level metadata for CodeRabbit review comments on merged pull requests through GET /v1/metrics/review-comments, including severity, category, resolution outcome, and comment URL. This enables programmatic analysis of code review findings without accessing comment text.
Enterprise orgs can retrieve finding-level metadata (severity, category, resolution outcome, comment URL) for CodeRabbit review comments via GET /v1/metrics/review-comments without exposing comment text, enabling analytics and auditing.
Comment @coderabbitai generate project vocabulary to receive an alphabetized list of up to 50 project-specific terms extracted from source code and documentation, automatically excluding generic frameworks and dependencies.
Enterprise organizations can retrieve metadata for CodeRabbit findings on merged PRs via GET /v1/metrics/review-comments, including severity, category, resolution outcomes, and comment URLs. This enables programmatic tracking and analysis of code review findings.
Large reviews now send smaller requests and report oversized payloads directly instead of generic errors. Security findings display category, CWE, reachability, and exploitability information. Usage reporting more accurately reflects actual review spending.
