> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coderabbit.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration V2 reference

> Complete reference for CodeRabbit configuration options with detailed explanations, types, and examples.

> [!NOTE]
>
> This reference is automatically generated from the CodeRabbit configuration schema. **Last updated: November 19, 2026**

CodeRabbit's behavior can be customized using a `.coderabbit.yaml` file in your repository root. This reference covers all available configuration options with clear property names and examples.

This page documents V2, used when the file omits `version` or declares `version: 2`. For eligible organizations using the V3 preview, see the [V3 reference](https://docs.coderabbit.ai/reference/configuration-v3.md) and [migration guide](https://docs.coderabbit.ai/configuration/guides/migrate-to-v3.md).

> [card] [Quick Start](https://docs.coderabbit.ai/configuration/file.md)
>
> Get started with basic configuration

> [card] [YAML config examples](https://github.com/coderabbitai/awesome-coderabbit/tree/main/configs)
>
> Browse example configurations

## Configuration sections

> [card] [General settings](#general-settings)
>
> Configure general settings

> [card] [Code reviews](#reviews)
>
> Configure automatic code reviews, tools, and review behavior

> [card] [Chat](#chat)
>
> Configure interactive chat features

> [card] [Knowledge base](#knowledge-base)
>
> Configure knowledge base features

> [card] [Code generation](#code-generation)
>
> Configure code generation settings

> [card] [Issue enrichment](#issue-enrichment)
>
> Configure automatic Issue enrichment and planning

## General settings

**language** `enum` (default: en-US)

Set the language for reviews by using the corresponding ISO language code.

One of the following: `de`, `de-DE`, `de-AT`, `de-CH`, `en`, `en-US`, `en-AU`, `en-GB`, `en-CA`, `en-NZ`, `en-ZA`, `es`, `es-AR`, `fr`, `fr-CA`, `fr-CH`, `fr-BE`, `nl`, `nl-BE`, `pt-AO`, `pt`, `pt-BR`, `pt-MZ`, `pt-PT`, `ar`, `ast-ES`, `ast`, `be-BY`, `be`, `br-FR`, `br`, `ca-ES`, `ca`, `ca-ES-valencia`, `ca-ES-balear`, `da-DK`, `da`, `de-DE-x-simple-language`, `el-GR`, `el`, `eo`, `fa`, `ga-IE`, `ga`, `gl-ES`, `gl`, `it`, `ja-JP`, `ja`, `km-KH`, `km`, `ko-KR`, `ko`, `pl-PL`, `pl`, `ro-RO`, `ro`, `ru-RU`, `ru`, `sk-SK`, `sk`, `sl-SI`, `sl`, `sv`, `ta-IN`, `ta`, `tl-PH`, `tl`, `tr`, `uk-UA`, `uk`, `zh-CN`, `zh`, `zh-TW`, `crh-UA`, `crh`, `cs-CZ`, `cs`, `nb`, `no`, `nl-NL`, `de-DE-x-simple-language-DE`, `es-ES`, `it-IT`, `fa-IR`, `sv-SE`, `de-LU`, `fr-FR`, `bg-BG`, `bg`, `he-IL`, `he`, `hi-IN`, `hi`, `vi-VN`, `vi`, `th-TH`, `th`, `bn-BD`, `bn`

**tone\_instructions** `string`

Set the tone of reviews and chat. Example: 'You must talk like Mr. T. I pity the fool who doesn't!'

> [!NOTE]
>
> Max length: 250

**early\_access** `boolean` (default: false)

Enable early-access features.

**enable\_free\_tier** `boolean` (default: true)

Enable free tier features for users not on a paid plan.

**inheritance** `boolean` (default: false)

**Inheritance**: Use parent settings for any values not defined here. Inheritance only propagates upward if enabled at each level.

Learn more: [Inheritance and merging](https://docs.coderabbit.ai/configuration/inheritance-and-merging.md#turn-on-inheritance)

## Reviews

Settings related to reviews.

**reviews.profile** `enum` (default: chill)

Set the review profile: quiet for only the most important feedback, chill for balanced feedback, assertive for more feedback (which may feel nitpicky).

One of the following: `quiet`, `chill`, `assertive`

<ul>
  <li>`quiet`: Posts only the most important comments inline and groups the other review comments in the review summary.</li>
  <li>`chill`: Balanced feedback.</li>
  <li>`assertive`: More feedback, which may feel nitpicky.</li>
</ul>

**reviews.merge\_risk\_instructions** `string`

**Merge Risk Instructions**: Describe what makes a pull request more or less risky to merge in this codebase. CodeRabbit uses this when rating merge risk, which `auto_approvals.max_merge_risk` can limit for automatic approval. Up to 3000 characters. Example: `Database migrations and billing changes are high risk. Docs-only and test-only changes are low risk.`

> [!NOTE]
>
> Max length: 3000

Learn more: [Merge Risk](https://docs.coderabbit.ai/pr-reviews/merge-risk.md#guide-merge-risk)

**reviews.security\_risk\_instructions** `string`

**Security Risk Instructions**: Describe facts about your system that affect security risk, such as which services are internet-facing, where tenant isolation is enforced, or which controls protect a path. CodeRabbit uses this when rating security architecture risk, which `auto_approvals.max_security_risk` can limit for automatic approval. Security risk assessments require the Advanced plan or above. Unlike Security scan context, which guides security findings in reviews and scans, this only affects the risk rating. Up to 3000 characters. Example: `The admin service is reachable only over the corporate VPN. Changes to tenant isolation in packages/tenancy are high risk.`

> [!NOTE]
>
> Max length: 3000

Learn more: [Security Architecture Review](https://docs.coderabbit.ai/security/architecture-review.md#guide-the-risk-rating)

**reviews.high\_level\_summary** `boolean` (default: true)

Generate a high-level summary of the changes in the PR description or walkthrough.

Learn more: [PR Summaries](https://docs.coderabbit.ai/pr-reviews/summaries.md#disabling-the-summary)

**reviews.high\_level\_summary\_instructions** `string`

By default, CodeRabbit generates release notes in the description. Use this to customize the summary content and format. Example: 'Create concise release notes as a bullet-point list, followed by a Markdown table showing lines added and removed by each contributing author.' Note: Use `high_level_summary_in_walkthrough` to place the summary in the walkthrough instead of the description.

Learn more: [PR Summaries](https://docs.coderabbit.ai/pr-reviews/summaries.md#customizing-the-summary)

**reviews.high\_level\_summary\_placeholder** `string` (default: @coderabbitai summary)

Placeholder in the PR description that CodeRabbit replaces with the high-level summary. If `high_level_summary` is false, the summary is still generated when this placeholder is present.

Learn more: [PR Summaries](https://docs.coderabbit.ai/pr-reviews/summaries.md#controlling-placement)

**reviews.high\_level\_summary\_in\_walkthrough** `boolean` (default: false)

Include the high-level summary in the walkthrough comment.

Learn more: [PR Summaries](https://docs.coderabbit.ai/pr-reviews/summaries.md#moving-the-summary-to-the-walkthrough)

**reviews.auto\_title\_placeholder** `string` (default: @coderabbitai)

Add this keyword to the PR title to auto-generate a title.

**reviews.auto\_title\_instructions** `string`

**Auto Title Instructions**: Customize how CodeRabbit generates the PR title.

**reviews.review\_status** `boolean` (default: true)

Post review status messages (e.g., when a review is skipped) in the walkthrough summary comment.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#review-status-messages)

**reviews.review\_info** `boolean` (default: true)

Post review information such as the configuration used, reviewed commits, and skipped files.

**reviews.review\_details** `boolean` (default: false)

Post review details (ignored files, extra context used, suppressed comments, etc.).

**reviews.review\_progress** `boolean` (default: true)

On GitHub with CodeRabbit Cloud, report each review as a check run named `CodeRabbit` that shows the review's progress and outcome. When disabled, CodeRabbit posts the `CodeRabbit` commit status instead, if `commit_status` is enabled. GitLab, Azure DevOps, Bitbucket, and self-hosted CodeRabbit use the commit status.

Learn more: [CodeRabbit status check](https://docs.coderabbit.ai/pr-reviews/status-check.md)

**reviews.commit\_status** `boolean` (default: true)

Post a commit status named `CodeRabbit` on the pull request's latest commit. It is pending while CodeRabbit reviews and turns successful when the review ends, including when it is skipped or rate limited. Used on GitLab, Azure DevOps, Bitbucket, and self-hosted CodeRabbit, and on GitHub when `review_progress` is disabled. Require it in branch protection to keep pull requests from merging while a review is in progress.

Learn more: [CodeRabbit status check](https://docs.coderabbit.ai/pr-reviews/status-check.md)

**reviews.fail\_commit\_status** `boolean` (default: false)

Report a review that stops because of an error as failed, so a required `CodeRabbit` check blocks merging. When disabled, the GitHub check run ends as neutral and the commit status ends as successful, with the error in its description. Rate-limited reviews never fail.

Learn more: [CodeRabbit status check](https://docs.coderabbit.ai/pr-reviews/status-check.md)

**reviews.collapse\_walkthrough** `boolean` (default: true)

Wrap the walkthrough in a Markdown collapsible section.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#overview)

**reviews.changed\_files\_summary** `boolean` (default: true)

Include a summary of the changed files in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#changed-files-summary)

**reviews.sequence\_diagrams** `boolean` (default: true)

Include sequence diagrams in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#sequence-diagrams)

**reviews.estimate\_code\_review\_effort** `boolean` (default: true)

Include an estimated code review effort in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#estimated-review-effort)

**reviews.assess\_linked\_issues** `boolean` (default: true)

Include an assessment of how well the changes address linked issues in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#linked-issue-assessment)

**reviews.related\_issues** `boolean` (default: true)

Include potentially related issues in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#related-issues)

**reviews.related\_prs** `boolean` (default: true)

**Related PRs**: Include potentially related PRs in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#related-prs)

**reviews.suggested\_labels** `boolean` (default: true)

Suggest labels based on the changes, and include them in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#suggested-labels)

**reviews.labeling\_instructions** `array of object`

**Labeling Instructions**: Define allowed labels and when to suggest them. When provided, CodeRabbit suggests only from this list (still informed by prior PRs); when empty, suggestions rely entirely on prior PRs.

**options**

**reviews.labeling\_instructions\[].label** `string`

Label to suggest for the PR. Example: frontend

**reviews.labeling\_instructions\[].instructions** `string`

Instructions for the label. Example: Apply when the PR contains changes to React components.

> [!NOTE]
>
> Max length: 3000

```yaml .coderabbit.yaml theme={null}
reviews:
  labeling_instructions:
    - label: "frontend"
      instructions: "Apply when the PR contains changes to React components."
    - label: "coderabbit"
      instructions: "Apply if this PR contains changes to `.coderabbit.yaml`."
```

**reviews.mutually\_exclusive\_groups** `object`

**Mutually Exclusive Groups**: Define labels that should not coexist. Example: `{ risk: ['critical', 'high', 'medium', 'low'] }`.

**reviews.auto\_apply\_labels** `boolean` (default: false)

Automatically apply suggested labels to the PR.

**reviews.suggested\_reviewers** `boolean` (default: true)

Suggest reviewers based on the changes, and include them in the walkthrough.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#suggested-reviewers)

**reviews.auto\_assign\_reviewers** `boolean` (default: false)

Automatically assign the suggested reviewers to the PR.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#custom-reviewer-rules)

**reviews.suggested\_reviewers\_instructions** `array of object`

**Reviewer Instructions**: Map reviewers (users or team) to PR scenarios where they should be assigned. When empty, suggestions rely on prior PRs. Team handles are supported only on GitHub.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#custom-reviewer-rules)

**options**

**reviews.suggested\_reviewers\_instructions\[].reviewers** `array of object`

List of reviewers to assign when the PR matches the instructions below. Each entry pairs a handle (username or team slug) with its type (user or group).

**options**

**reviews.suggested\_reviewers\_instructions\[].reviewers\[].handle** `string`

Reviewer username or team slug to assign. Example: security-pdl

> [!NOTE]
>
> Min length: 1

**reviews.suggested\_reviewers\_instructions\[].reviewers\[].type** `enum` (default: user)

Whether the reviewer is an individual user or a team/group.

One of the following: `user`, `group`

**reviews.suggested\_reviewers\_instructions\[].instructions** `string`

Instructions for when to assign these reviewers. Example: Assign when the PR contains Windows registry changes.

> [!NOTE]
>
> Min length: 1, Max length: 3000

**reviews.in\_progress\_fortune** `boolean` (default: true)

Post a fortune message while the review is running.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#fortune-while-you-wait)

**reviews.poem** `boolean` (default: false)

Generate a poem in the walkthrough comment.

Learn more: [PR Walkthroughs](https://docs.coderabbit.ai/pr-reviews/walkthroughs.md#poem)

**reviews.enable\_prompt\_for\_ai\_agents** `boolean` (default: true)

**Prompt for Coding Agents**: Include the '🤖 Prompt for Coding Agents' section in inline review comments to provide codegen instructions for AI agents.

**reviews.path\_filters** `array of string`

Specify file patterns to include or exclude in a review using glob patterns (e.g., `!dist/**`, `src/**`). These patterns also apply to 'git sparse-checkout', including specified patterns and ignoring excluded ones (starting with '!') when cloning the repository.

Learn more: [Choose which files are reviewed](https://docs.coderabbit.ai/pr-reviews/which-files.md)

```yaml .coderabbit.yaml theme={null}
reviews:
  path_filters:
    - "src/**"
    - "!src/generated/**"
```

**reviews.path\_instructions** `array of object`

**Path Instructions**: Add path-specific guidance for code review.

Learn more: [Teach CodeRabbit your review rules](https://docs.coderabbit.ai/pr-reviews/review-instructions.md#add-path-instructions)

**options**

**reviews.path\_instructions\[].path** `string`

File path glob pattern. Example: `**/*.js`.

**reviews.path\_instructions\[].instructions** `string`

Additional review guidance for matching paths.

> [!NOTE]
>
> Max length: 20000

```yaml .coderabbit.yaml theme={null}
reviews:
  path_instructions:
    - path: "src/controllers/**"
      instructions: |
        - Focus on authentication, authorization, and input validation.
        - Flag any direct database queries that bypass the ORM layer.
    - path: "tests/**"
      instructions: |
        Ensure descriptive test names are used and that edge cases and error paths are covered.
```

**reviews.abort\_on\_close** `boolean` (default: true)

Abort the in-progress review if the PR is closed or merged.

**reviews.disable\_cache** `boolean` (default: false)

Disable caching of code and dependencies; fetch them fresh on each run.

Learn more: [Caching](https://docs.coderabbit.ai/reference/caching.md#disable-caching)

**reviews.post\_merge\_actions** `array of object`

**Custom Post-merge Actions**: Define custom actions to run after merging. Each action needs a unique name (≤100 chars) and a deterministic prompt (≤10,000 chars).

Learn more: [Post-Merge Actions](https://docs.coderabbit.ai/pr-reviews/post-merge-actions.md#configuration)

**options**

**reviews.post\_merge\_actions\[].enabled** `boolean` (default: true)

**Enabled**: Run this action after a PR is merged.

**reviews.post\_merge\_actions\[].name** `string`

**Name**: Display name (max 100 characters).

> [!NOTE]
>
> Min length: 1, Max length: 100

**reviews.post\_merge\_actions\[].prompt** `string`

**Prompt**: Deterministic instructions describing the action to perform (max 10,000 characters).

> [!NOTE]
>
> Min length: 1, Max length: 10000

### Automatic approvals

`reviews.auto_approvals`

Control automatic approval, optional risk limits, and overrides for teams or paths. Limits and disabled overrides apply to approve and resolve commands too. Missing, failed, disabled or stale required assessments withhold approval.

Learn more: [Approval risk limits](https://docs.coderabbit.ai/pr-reviews/approval-risk-limits.md#choose-what-to-limit)

**reviews.auto\_approvals.enabled** `boolean` (default: false)

**Automatic approvals**: Request changes for blocking findings. Automatically approve when required threads are resolved, the latest commit is reviewed, pre-merge checks pass, and configured risk limits are satisfied. In GitLab, required discussions must be resolved.

Learn more: [Automatic Approvals](https://docs.coderabbit.ai/pr-reviews/automatic-approvals.md#turn-on-automatic-approvals)

**reviews.auto\_approvals.min\_blocking\_severity** `enum`

**Minimum blocking severity**: Set the lowest finding severity that can block automatic approval. Lower-severity findings remain visible as advisory feedback. Enable automatic approvals to use this setting. Leave it unset to keep the default blocking behavior. Required pre-merge checks, provider discussion rules, and approval risk limits still apply. In Perforce, only published inline findings count toward this threshold.

One of the following: `major`, `critical`

**reviews.auto\_approvals.approve\_on\_skipped\_review** `boolean` (default: false)

**Approve skipped reviews**: When automatic approvals are enabled, allow approval when the entire review is intentionally skipped, such as for a draft pull request or a file limit. Errors and cancelled reviews are excluded. Existing findings, pre-merge checks and configured risk limits still apply.

**reviews.auto\_approvals.max\_merge\_risk** `enum`

**Maximum merge risk for approval**: Highest inclusive merge risk that permits approval. Omitted limits can be inherited; merge risk is unrestricted only when no configuration source sets a limit. A configured limit requires an assessment covering the current commit.

One of the following: `minimal`, `low`, `moderate`, `high`, `critical`

Learn more: [Approval risk limits](https://docs.coderabbit.ai/pr-reviews/approval-risk-limits.md#set-a-merge-risk-limit)

**reviews.auto\_approvals.allow\_author\_approval** `boolean` (default: true)

**Allow author approval commands**: Allow pull request authors to use top-level @coderabbitai approve and @coderabbitai resolve commands on their own pull requests. When disabled, another reviewer must run them. The pull request's branch configuration cannot re-enable this permission. Commands still honor approval risk limits. This does not require human review or change automatic approvals after normal review requirements pass.

Learn more: [Automatic Approvals](https://docs.coderabbit.ai/pr-reviews/automatic-approvals.md#limit-author-approval-commands)

**reviews.auto\_approvals.max\_security\_risk** `enum`

**Maximum security risk for approval**: Highest inclusive security architecture risk that permits approval. Security risk assessments require the Advanced plan or above. Omitted limits can be inherited; security risk is unrestricted only when no configuration source sets a limit. This is separate from Security finding severity. A configured limit requires an assessment covering the current commit.

One of the following: `minimal`, `low`, `moderate`, `high`, `critical`

Learn more: [Approval risk limits](https://docs.coderabbit.ai/pr-reviews/approval-risk-limits.md#set-a-security-risk-limit)

**reviews.auto\_approvals.overrides** `array of object`

**Overrides**: Disable approvals or override risk limits by author team, changed paths, or both. When teams and paths are set, both must match. A matching file applies the override to the whole pull request. Any matching disabled override withholds approval. Otherwise, the strictest explicitly configured value wins for each limit; omitted values inherit the global limit. At most 15 distinct teams may be checked. Unavailable required team membership or changed-file evidence withholds approval.

Learn more: [Approval risk limits](https://docs.coderabbit.ai/pr-reviews/approval-risk-limits.md#set-different-limits-for-paths)

**options**

**reviews.auto\_approvals.overrides\[].enabled** `boolean`

**Automatic approvals**: Set to false to withhold approval for matching pull requests, regardless of risk. Omit to use the global setting. Any matching disabled override wins. Review comments and requests for changes continue normally; overrides cannot turn on a globally disabled workflow.

**reviews.auto\_approvals.overrides\[].teams** `array of string`

**Teams**: Apply this override when the pull request author belongs to any listed GitHub team. Use organization/team-slug.

**reviews.auto\_approvals.overrides\[].paths** `array of string`

**Paths**: Apply this override when any changed file matches these repository-relative globs. Uses the same glob syntax as `path_filters`, including ! exclusions. Renames match both old and new paths. When teams and paths are set, both must match. Omit to match all paths.

**reviews.auto\_approvals.overrides\[].max\_merge\_risk** `enum`

**Maximum merge risk for approval**: Override the global merge-risk limit for matching pull requests. Omit to inherit the global limit.

One of the following: `minimal`, `low`, `moderate`, `high`, `critical`

**reviews.auto\_approvals.overrides\[].max\_security\_risk** `enum`

**Maximum security risk for approval**: Override the global security-risk limit for matching pull requests. Omit to inherit the global limit. Security risk assessments require the Advanced plan or above.

One of the following: `minimal`, `low`, `moderate`, `high`, `critical`

### Anti-Slop

`reviews.slop_detection`

Settings for detecting spam or low-quality pull requests and merge requests. Private repositories require the Essentials plan or higher. Public GitHub, GitLab, and Bitbucket repositories are eligible on all plans. Author exemptions, integration availability, labeling, and rechecks vary by platform.

Learn more: [Slop Detection](https://docs.coderabbit.ai/pr-reviews/slop-detection.md#platform-availability-and-restrictions)

**reviews.slop\_detection.enabled** `boolean` (default: true)

Enable or disable slop and low-quality PR detection.

**reviews.slop\_detection.include\_all\_authors** `boolean` (default: false)

Include authors otherwise exempt because of their repository relationship, including same-repository pull requests on Azure DevOps and Bitbucket. Recognized automation accounts remain exempt.

Learn more: [Slop Detection](https://docs.coderabbit.ai/pr-reviews/slop-detection.md#include-all-pull-request-authors)

**reviews.slop\_detection.label** `string`

Label to apply when a request is classified as spam or slop on platforms that support labeling. The label is applied in addition to the warning in the PR Walkthrough comment. When no label is configured, only the warning is added. Requests with this label are eligible for analysis on subsequent reviews on GitHub, GitLab, and Azure DevOps. Bitbucket does not support label-based rechecks.

> [!NOTE]
>
> Min length: 1

Learn more: [Slop Detection](https://docs.coderabbit.ai/pr-reviews/slop-detection.md#label-flagged-prs)

### Auto review

`reviews.auto_review`

Learn more: [Control when reviews run](https://docs.coderabbit.ai/pr-reviews/when-reviews-run.md)

**reviews.auto\_review\.enabled** `boolean` (default: true)

**Automatic Review**: Review PRs automatically.

**reviews.auto\_review\.description\_keyword** `string`

Keyword in the PR description that triggers a review when automatic reviews are disabled. If `enabled` is false and this field is not empty, CodeRabbit reviews the PR only when this keyword is present in the description.

**reviews.auto\_review\.auto\_incremental\_review** `boolean` (default: true)

**Incremental Review**: Re-run the review on each push.

**reviews.auto\_review\.auto\_pause\_after\_reviewed\_commits** `integer` (default: 5)

**Auto Pause After Reviewed Commits**: Pause automatic reviews after this many reviewed commits since the last pause. Set to 0 to disable.

> [!NOTE]
>
> Min: 0, Max: 9007199254740991

**reviews.auto\_review\.ignore\_title\_keywords** `array of string`

Skip reviews when the PR title contains any of these keywords (case-insensitive).

**reviews.auto\_review\.labels** `array of string`

Labels that control which PRs are reviewed. Labels starting with '!' are negative matches. Examples: \['bug', 'feature'] reviews PRs with either label. \['!wip'] reviews all PRs except those labeled 'wip' when automatic reviews are enabled. \['bug', '!wip'] reviews PRs labeled 'bug' but not 'wip'. When `enabled` is false, a positive label match (for example \['review-ready']) triggers a review; negative-only labels such as \['!wip'] remain exclusion filters and do not opt PRs in by themselves.

```yaml .coderabbit.yaml theme={null}
reviews:
  auto_review:
    enabled: false
    labels:
      - "review-ready"
```

**reviews.auto\_review\.drafts** `boolean` (default: false)

Include draft PRs.

**reviews.auto\_review\.base\_branches** `array of string`

Base branches (other than the default branch) to review. Accepts regex patterns. Use '.\*' to match all branches.

Each entry is a regular expression tested against the target branch name without anchoring, so `develop` also matches `develop-2`. Use `^` and `$` to match the whole name.

```yaml .coderabbit.yaml theme={null}
reviews:
  auto_review:
    base_branches:
      - "^develop$"
      - "^release/.*$"
```

**reviews.auto\_review\.ignore\_usernames** `array of string`

Skip reviews for pull requests authored by these usernames. Matching is exact and case-sensitive. Bitbucket Cloud matches the author's display name, and Azure DevOps matches their unique name, usually the sign-in email, in lowercase.

Learn more: [Control when reviews run](https://docs.coderabbit.ai/pr-reviews/when-reviews-run.md#what-to-enter-in-ignore_usernames)

### Finishing touches

`reviews.finishing_touches`

Learn more: [Finishing Touches overview](https://docs.coderabbit.ai/finishing-touches)

**reviews.finishing\_touches.unit\_tests** `object`

**Unit Tests**: Configure unit test generation.

**options**

**reviews.finishing\_touches.unit\_tests.enabled** `boolean` (default: true)

**Unit Tests**: Generate unit tests for changes in PRs.

**reviews.finishing\_touches.simplify** `object`

**Simplify**: Configure code simplification.

**options**

**reviews.finishing\_touches.simplify.enabled** `boolean` (default: false)

**Simplify**: Enable the simplify finishing touch (trigger via the ✨ Simplify code checkbox). CodeRabbit reviews changed code for reuse, quality, and efficiency, then applies targeted improvements.

**reviews.finishing\_touches.autofix** `object`

**Fix comments**: Configure the Fix comments finishing touch for one-off review repairs.

Learn more: [Fix comments: apply CodeRabbit code fixes to pull requests](https://docs.coderabbit.ai/finishing-touches/autofix.md)

**options**

**reviews.finishing\_touches.autofix.enabled** `boolean` (default: true)

**Fix comments**: Enable the Fix comments finishing touch (trigger via the Fix comments checkbox in a GitHub review comment or the `@coderabbitai fix comments` command). When disabled, the review checkbox and command instructions are hidden, the command is removed from help, and CodeRabbit declines one-off repair requests, including compatibility aliases, with or without `stacked pr`.

**reviews.finishing\_touches.fix\_ci** `object`

**Fix Failing CI**: Configure the CI fixer.

Learn more: [Fix CI failures](https://docs.coderabbit.ai/finishing-touches/fix-ci.md#configuration)

**options**

**reviews.finishing\_touches.fix\_ci.enabled** `boolean` (default: true)

**Fix Failing CI**: Enable the fix-ci finishing touch on GitHub and Azure DevOps; requires a Team plan. When CI failures are attributed to the current pull request, Finishing Touches offers the delivery modes supported by the repository. Where both modes are available, it offers mutually exclusive stacked-pull-request and direct-commit options; where stacked-pull-request delivery is unavailable but direct commits are supported, it offers direct commit only. The `@coderabbitai fix-ci` command requests a stacked pull request by default, but commits in place on a CodeRabbit-authored pull request to avoid creating another stacked pull request. Use `@coderabbitai fix-ci commit` to request a direct commit. When disabled, both commands are removed from help and CodeRabbit declines fix-ci requests.

**reviews.finishing\_touches.resolve\_merge\_conflict** `object`

**Resolve Merge Conflicts**: Configure the merge-conflict resolver.

Learn more: [Resolve Merge Conflicts](https://docs.coderabbit.ai/finishing-touches/resolve-merge-conflict.md#configuration)

**options**

**reviews.finishing\_touches.resolve\_merge\_conflict.enabled** `boolean` (default: true)

**Resolve Merge Conflicts**: Enable the merge-conflict resolver (trigger via `@coderabbitai resolve merge conflict`). CodeRabbit analyzes the intent behind both sides of a conflict and commits a resolution to your branch. When disabled, the command is removed from help and CodeRabbit declines resolution requests. Available on GitHub and GitLab; requires a Team plan.

**reviews.finishing\_touches.custom** `array of object`

**Custom Recipes**: Define custom finishing touch recipes up to your plan limit. Trigger a recipe with `@coderabbitai run <recipe name>`.

Learn more: [Custom Finishing Touch recipes](https://docs.coderabbit.ai/finishing-touches/custom-finishing-touches.md#configuration)

**options**

**reviews.finishing\_touches.custom\[].enabled** `boolean` (default: true)

**Enabled**: Enable this custom finishing touch recipe.

**reviews.finishing\_touches.custom\[].name** `string`

**Name**: Recipe name used in commands (for example: `@coderabbitai run cleanup stale imports`). Run with `@coderabbitai run <recipe name>`.

> [!NOTE]
>
> Min length: 1, Max length: 100

**reviews.finishing\_touches.custom\[].instructions** `string`

**Instructions**: Describe what this recipe should do. Trigger with `@coderabbitai run <recipe name>` or the checkbox under "✨ Finishing Touches". CodeRabbit provides PR context and runs this with an agent.

> [!NOTE]
>
> Min length: 1, Max length: 10000

### Pre-Merge Checks

`reviews.pre_merge_checks`

Learn more: [Built-in Pre-Merge Checks](https://docs.coderabbit.ai/pr-reviews/pre-merge-checks.md)

**reviews.pre\_merge\_checks.override\_requested\_reviewers\_only** `boolean` (default: false)

**Override Requested Reviewers Only**: When enabled, the pull request author cannot override/ignore failing pre-merge checks. Eligible actors are individually requested reviewers and, on GitHub, members of requested reviewer teams or submitted reviewers whose author association is OWNER, MEMBER, or COLLABORATOR.

**reviews.pre\_merge\_checks.title** `object`

**Title Check**: Validate the PR title against the requirements.

**options**

**reviews.pre\_merge\_checks.title.mode** `enum` (default: warning)

**Mode**: Enforcement level: `off` disables the check, `warning` posts a warning, and `error` requires resolution before merging. If the request-changes workflow is enabled, `error` can block the PR until the check passes.

One of the following: `off`, `warning`, `error`

**reviews.pre\_merge\_checks.title.requirements** `string`

**Requirements**: Describe title requirements. Example: 'Title should be concise and descriptive, ideally under 50 characters.'

**reviews.pre\_merge\_checks.description** `object`

**Description Check**: Check that the PR description follows best practices.

**options**

**reviews.pre\_merge\_checks.description.mode** `enum` (default: warning)

**Mode**: Enforcement level: `off` disables the check, `warning` posts a warning, and `error` requires resolution before merging. If the request-changes workflow is enabled, `error` can block the PR until the check passes.

One of the following: `off`, `warning`, `error`

**reviews.pre\_merge\_checks.issue\_assessment** `object`

**Linked Issue Assessment**: Assess how well the PR addresses linked issues.

**options**

**reviews.pre\_merge\_checks.issue\_assessment.mode** `enum` (default: warning)

**Mode**: Enforcement level: `off` disables the check, `warning` posts a warning, and `error` requires resolution before merging. If the request-changes workflow is enabled, `error` can block the PR until the check passes.

One of the following: `off`, `warning`, `error`

**reviews.pre\_merge\_checks.custom\_checks** `array of object`

**Custom Pre-merge Checks**: Define custom checks that must pass before merging. Each check needs a unique name (≤50 chars) and deterministic instructions (≤10,000 chars).

Learn more: [Custom checks](https://docs.coderabbit.ai/pr-reviews/custom-checks.md)

**options**

**reviews.pre\_merge\_checks.custom\_checks\[].mode** `enum` (default: warning)

**Mode**: Enforcement level: `off` disables the check, `warning` posts a warning, and `error` requires resolution before merging. If the request-changes workflow is enabled, `error` can block the PR until the check passes.

One of the following: `off`, `warning`, `error`

**reviews.pre\_merge\_checks.custom\_checks\[].name** `string`

**Name**: Display name (max 50 characters).

> [!NOTE]
>
> Min length: 1, Max length: 50

**reviews.pre\_merge\_checks.custom\_checks\[].instructions** `string`

**Instructions**: Deterministic pass/fail criteria (max 10,000 characters).

> [!NOTE]
>
> Min length: 1, Max length: 10000

```yaml .coderabbit.yaml theme={null}
reviews:
  pre_merge_checks:
    custom_checks:
      - name: "Undocumented Breaking Changes"
        mode: "warning"
        instructions: |
          All breaking changes to public APIs, CLI flags, environment variables, or database schemas must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md.
```

### Tools

`reviews.tools`

Tools that provide additional context to code reviews.

Learn more: [Third-party tools overview](https://docs.coderabbit.ai/tools.md)

**reviews.tools.ast-grep** `object`

ast-grep is a code analysis tool that helps you to find patterns in your codebase using abstract syntax trees patterns.

Version: `v0.51.1`

**options**

**reviews.tools.ast-grep.enabled** `boolean` (default: true)

**Enable ast-grep**

**reviews.tools.ast-grep.rule\_dirs** `array of string`

List of rules directories.

**reviews.tools.ast-grep.util\_dirs** `array of string`

List of utils directories.

**reviews.tools.ast-grep.essential\_rules** `boolean` (default: true)

Use ast-grep essentials package.

**reviews.tools.ast-grep.packages** `array of string`

Predefined packages to be used.

**reviews.tools.shellcheck** `object`

ShellCheck is a static analysis tool that finds bugs in your shell scripts.

Version: `v0.11.0`

**options**

**reviews.tools.shellcheck.enabled** `boolean` (default: true)

**Enable ShellCheck**: ShellCheck is a static analysis tool that finds bugs in your shell.

**reviews.tools.ruff** `object`

Ruff is a Python linter and code formatter.

Version: `v0.17.4`

**options**

**reviews.tools.ruff.enabled** `boolean` (default: true)

**Enable Ruff**

**reviews.tools.ruff.config\_file** `string`

Optional path to a Ruff configuration file relative to the repository. When set, this configuration is used for every reviewed file instead of Ruff's closest-config discovery.

**reviews.tools.markdownlint** `object`

markdownlint-cli2 is a static analysis tool to enforce standards and consistency for Markdown files.

Version: `v0.24.0`

**options**

**reviews.tools.markdownlint.enabled** `boolean` (default: true)

**Enable markdownlint**

**reviews.tools.github-checks** `object`

GitHub Checks integration configuration.

**options**

**reviews.tools.github-checks.enabled** `boolean` (default: true)

**Enable GitHub Checks**: Enable integration, defaults to true

**reviews.tools.languagetool** `object`

LanguageTool is a style and grammar checker for 30+ languages.

**options**

**reviews.tools.languagetool.enabled** `boolean` (default: true)

**Enable LanguageTool**: Enable LanguageTool integration.

**reviews.tools.languagetool.enabled\_rules** `array of string`

IDs of rules to be enabled. The rule won't run unless 'level' is set to a level that activates the rule.

**reviews.tools.languagetool.disabled\_rules** `array of string`

IDs of rules to be disabled. Note: EN\_UNPAIRED\_BRACKETS, and EN\_UNPAIRED\_QUOTES are always disabled.

**reviews.tools.languagetool.enabled\_categories** `array of string`

IDs of categories to be enabled.

**reviews.tools.languagetool.disabled\_categories** `array of string`

IDs of categories to be disabled. Note: TYPOS, TYPOGRAPHY, and CASING are always disabled.

**reviews.tools.languagetool.enabled\_only** `boolean` (default: false)

Run only the rules and categories listed in `enabled_rules` or `enabled_categories`, instead of the default set.

With `enabled_only: true`, at least one rule or category is required. If both lists are empty, CodeRabbit skips LanguageTool and reports an error.

**reviews.tools.languagetool.level** `enum` (default: default)

If set to 'picky', additional rules will be activated, i.e. rules that you might only find useful when checking formal text.

One of the following: `default`, `picky`

**reviews.tools.biome** `object`

Biome is a fast formatter, linter, and analyzer for web projects.

Version: `v2.6.5`

**options**

**reviews.tools.biome.enabled** `boolean` (default: true)

**Enable Biome**

**reviews.tools.hadolint** `object`

Hadolint is a Dockerfile linter.

Version: `v2.15.1`

**options**

**reviews.tools.hadolint.enabled** `boolean` (default: true)

**Enable Hadolint**

**reviews.tools.swiftlint** `object`

SwiftLint integration configuration object.

Version: `v0.65.1`

**options**

**reviews.tools.swiftlint.enabled** `boolean` (default: true)

**Enable SwiftLint**: SwiftLint is a Swift linter.

**reviews.tools.swiftlint.config\_file** `string`

Optional path to the SwiftLint configuration file relative to the repository. This is useful when the configuration file is named differently than the default '.swiftlint.yml' or '.swiftlint.yaml'.

**reviews.tools.phpstan** `object`

PHPStan is a tool to analyze PHP code.

Version: `v2.3.5`

**options**

**reviews.tools.phpstan.enabled** `boolean` (default: true)

**Enable PHPStan**: PHPStan requires [config file](https://phpstan.org/config-reference#config-file) in your repository root. Please ensure that this file contains the `paths:` parameter.

**reviews.tools.phpstan.level** `enum` (default: default)

**Level**: Specify the [rule level](https://phpstan.org/user-guide/rule-levels) to run. When set to `default`, the level is determined by the review profile: `chill` uses level 3 (real bugs only — return/property type mismatches, array offset errors) and `assertive` uses level 8 (adds dead code detection, argument type checking, null safety, and typehint checks). This setting is ignored if your configuration file already has a `level:` parameter.

One of the following: `0`, `1`, `2`, `3`, `4`, `5`, `6`, `7`, `8`, `9`, `default`, `max`

**reviews.tools.phpmd** `object`

PHPMD is a tool to find potential problems in PHP code.

Version: `v3.0.0`

**options**

**reviews.tools.phpmd.enabled** `boolean` (default: true)

**Enable PHPMD**

**reviews.tools.phpcs** `object`

PHP CodeSniffer is a PHP linter and coding standard checker.

Version: `v3.13.6`

**options**

**reviews.tools.phpcs.enabled** `boolean` (default: true)

**Enable PHP CodeSniffer**

**reviews.tools.golangci-lint** `object`

golangci-lint is a fast linters runner for Go.

Version: `v2.15.0`

**options**

**reviews.tools.golangci-lint.enabled** `boolean` (default: true)

**Enable golangci-lint**

**reviews.tools.golangci-lint.config\_file** `string`

Optional path to the golangci-lint configuration file relative to the repository. Useful when the configuration file is named differently than the default '.golangci.yml', '.golangci.yaml', '.golangci.toml', '.golangci.json'.

**reviews.tools.yamllint** `object`

YAMLlint is a linter for YAML files.

Version: `v1.37.1`

**options**

**reviews.tools.yamllint.enabled** `boolean` (default: true)

**Enable YAMLlint**

**reviews.tools.gitleaks** `object`

Betterleaks is a secret scanner.

Version: `v1.9.0`

**options**

**reviews.tools.gitleaks.enabled** `boolean` (default: true)

**Enable Betterleaks**

**reviews.tools.trufflehog** `object`

TruffleHog is a secret scanner with verification capabilities that can detect and verify secrets in code.

Version: `v3.99.8`

**options**

**reviews.tools.trufflehog.enabled** `boolean` (default: true)

**Enable TruffleHog**: TruffleHog is a secret scanner with verification capabilities.

**reviews.tools.checkov** `object`

Checkov is a static code analysis tool for infrastructure-as-code files.

Version: `v3.4.3`

**options**

**reviews.tools.checkov.enabled** `boolean` (default: true)

**Enable Checkov**

**reviews.tools.tflint** `object`

TFLint is a Terraform linter for finding potential errors and enforcing best practices.

Version: `v0.66.0`

**options**

**reviews.tools.tflint.enabled** `boolean` (default: true)

**Enable TFLint**: TFLint is a Terraform linter for finding potential errors.

**reviews.tools.detekt** `object`

Detekt is a static code analysis tool for Kotlin files.

Version: `v1.23.8`

**options**

**reviews.tools.detekt.enabled** `boolean` (default: true)

**Enable detekt**: detekt is a static code analysis tool for Kotlin files.

**reviews.tools.detekt.config\_file** `string`

Optional path to the detekt configuration file relative to the repository.

**reviews.tools.eslint** `object`

ESLint is a static code analysis tool for JavaScript files.

**options**

**reviews.tools.eslint.enabled** `boolean` (default: true)

**Enable ESLint**

**reviews.tools.eslint.config\_file** `string`

Optional path to an ESLint configuration file relative to the repository. When set, this configuration is used for every file instead of discovering ESLint configurations recursively.

**reviews.tools.eslint.e18e** `object`

@e18e/eslint-plugin modernization, performance, and dependency replacement checks.

**options**

**reviews.tools.eslint.e18e.enabled** `boolean` (default: true)

**Enable @e18e/eslint-plugin**: Detects dependencies with modern replacements, flags unmaintained packages, and suggests native API alternatives or lighter replacements

Version: `v0.8.1`

**reviews.tools.flake8** `object`

Flake8 is a Python linter that wraps PyFlakes, pycodestyle and Ned Batchelder's McCabe script.

Version: `v7.5.0`

**options**

**reviews.tools.flake8.enabled** `boolean` (default: true)

**Enable Flake8**

**reviews.tools.fbinfer** `object`

Configuration for Infer to find bugs in Java and C/C++ code

Version: `v1.3.0`

**options**

**reviews.tools.fbinfer.enabled** `boolean` (default: true)

Enable Infer for static bug analysis in Java and C/C++ code

**reviews.tools.fbinfer.enable\_java** `boolean` (default: false)

**Enable Java analysis**: Disabled by default because Java analysis may require compiling more than the changed files.

**reviews.tools.fortitudeLint** `object`

Fortitude is a Fortran linter that checks for code quality and style issues.

Version: `v0.10.1`

**options**

**reviews.tools.fortitudeLint.enabled** `boolean` (default: true)

**Enable Fortitude**: Fortitude is a Fortran linter that checks for code quality and style issues

**reviews.tools.rubocop** `object`

RuboCop is a Ruby static code analyzer (a.k.a. linter) and code formatter.

Version: `v1.92.2`

**options**

**reviews.tools.rubocop.enabled** `boolean` (default: true)

**Enable RuboCop**

**reviews.tools.buf** `object`

Buf offers linting for Protobuf files.

Version: `v1.74.0`

**options**

**reviews.tools.buf.enabled** `boolean` (default: true)

**Enable Buf**

**reviews.tools.regal** `object`

Regal is a linter and language server for Rego.

Version: `v0.43.0`

**options**

**reviews.tools.regal.enabled** `boolean` (default: true)

**Enable Regal**

**reviews.tools.actionlint** `object`

actionlint is a static checker for GitHub Actions workflow files.

Version: `v1.7.12`

**options**

**reviews.tools.actionlint.enabled** `boolean` (default: true)

**Enable actionlint**

**reviews.tools.zizmor** `object`

zizmor is a static security analyzer for GitHub Actions workflow files.

Version: `v1.32.0`

**options**

**reviews.tools.zizmor.enabled** `boolean` (default: true)

**Enable zizmor**

**reviews.tools.pmd** `object`

PMD is an extensible multilanguage static code analyzer. It’s mainly concerned with Java.

Version: `v7.29.0`

**options**

**reviews.tools.pmd.enabled** `boolean` (default: true)

**Enable PMD**

**reviews.tools.pmd.config\_file** `string`

Optional path to the PMD configuration file relative to the repository.

**reviews.tools.clang** `object`

Configuration for Clang to perform static analysis on C and C++ code

Version: `v23.1.4`

**options**

**reviews.tools.clang.enabled** `boolean` (default: true)

Enable Clang for C/C++ static analysis and code quality checks

**reviews.tools.cppcheck** `object`

Cppcheck is a static code analysis tool for the C and C++ programming languages.

Version: `v2.22.0`

**options**

**reviews.tools.cppcheck.enabled** `boolean` (default: true)

**Enable Cppcheck**

**reviews.tools.vale** `object`

Vale lints prose using the repository's checked-in style rules.

Version: `v3.24.0`

**options**

**reviews.tools.vale.enabled** `boolean` (default: true)

**Enable Vale**: Vale checks prose against repository-defined editorial style rules. It runs only when a supported root Vale configuration is present.

**reviews.tools.verilator** `object`

Verilator statically analyzes Verilog and SystemVerilog source files.

Version: `v5.054`

**options**

**reviews.tools.verilator.enabled** `boolean` (default: true)

**Enable Verilator**: Verilator lints Verilog and SystemVerilog for syntax, width, connectivity, and behavioral correctness issues.

**reviews.tools.opengrep** `object`

OpenGrep is a high-performance static code analysis engine, compatible with Semgrep configurations.

Version: `v1.33.1`

**options**

**reviews.tools.opengrep.enabled** `boolean` (default: true)

**Enable OpenGrep**: OpenGrep is a high-performance static code analysis engine for finding security vulnerabilities and bugs across 17+ languages.

**reviews.tools.semgrep** `object`

Semgrep is a static analysis tool designed to scan code for security vulnerabilities and code quality issues.

Version: `v1.183.0`

**options**

**reviews.tools.semgrep.enabled** `boolean` (default: true)

**Enable Semgrep**

**reviews.tools.semgrep.config\_file** `string`

Optional path to the Semgrep configuration file relative to the repository.

**reviews.tools.circleci** `object`

CircleCI tool is a static checker for CircleCI config files.

Version: `v1.9.0`

**options**

**reviews.tools.circleci.enabled** `boolean` (default: true)

**Enable CircleCI**

**reviews.tools.clippy** `object`

Clippy is a collection of lints to catch common mistakes and improve your Rust code.

**options**

**reviews.tools.clippy.enabled** `boolean` (default: true)

**Enable Clippy**

**reviews.tools.sqlfluff** `object`

SQLFluff is an open source, dialect-flexible and configurable SQL linter.

Version: `v4.5.0`

**options**

**reviews.tools.sqlfluff.enabled** `boolean` (default: true)

**Enable SQLFluff**

**reviews.tools.sqlfluff.config\_file** `string`

Optional path to the SQLFluff configuration file relative to the repository. Use this when the config file is not named one of SQLFluff's default filenames.

**reviews.tools.squawk** `object`

Configuration for Squawk to lint Postgres migrations and SQL for safe schema changes

Version: `v2.71.0`

**options**

**reviews.tools.squawk.enabled** `boolean` (default: true)

**Enable Squawk for Postgres migration linting**: Detects unsafe schema changes that can cause downtime or blocking locks

**reviews.tools.trivy** `object`

Trivy is a comprehensive security scanner that detects misconfigurations and secrets in Infrastructure as Code files

Version: `v0.76.2`

**options**

**reviews.tools.trivy.enabled** `boolean` (default: true)

Enable Trivy for security scanning of IaC files (Terraform, Kubernetes, Docker, etc.)

**reviews.tools.prismaLint** `object`

Configuration for Prisma Schema linting to ensure schema file quality

Version: `v0.13.1`

**options**

**reviews.tools.prismaLint.enabled** `boolean` (default: true)

**Enable Prisma Schema linting**: Prisma Schema linting helps maintain consistent and error-free schema files

**reviews.tools.pylint** `object`

Pylint is a Python static code analysis tool.

Version: `v4.1.3`

**options**

**reviews.tools.pylint.enabled** `boolean` (default: true)

**Enable Pylint**

**reviews.tools.oxc** `object`

Oxlint is a JavaScript/TypeScript linter for OXC written in Rust.

Version: `v1.89.0`

**options**

**reviews.tools.oxc.enabled** `boolean` (default: true)

**Enable Oxlint**

**reviews.tools.shopifyThemeCheck** `object`

Configuration for Shopify Theme Check to ensure theme quality and best practices

Version: `cli 5.0.1, theme 3.58.2`

**options**

**reviews.tools.shopifyThemeCheck.enabled** `boolean` (default: true)

**Enable Shopify Theme Check**: A linter for Shopify themes that helps you follow Shopify theme & Liquid best practices

**reviews.tools.luacheck** `object`

Configuration for Lua code linting to ensure code quality

Version: `v1.2.0`

**options**

**reviews.tools.luacheck.enabled** `boolean` (default: true)

**Enable Lua code linting**: Luacheck helps maintain consistent and error-free Lua code

**reviews.tools.brakeman** `object`

Brakeman is a static analysis security vulnerability scanner for Ruby on Rails applications.

Version: `v8.1.0`

**options**

**reviews.tools.brakeman.enabled** `boolean` (default: true)

**Enable Brakeman**

**reviews.tools.dotenvLint** `object`

dotenv-linter is a tool for checking and fixing .env files for problems and best practices

Version: `v4.0.0`

**options**

**reviews.tools.dotenvLint.enabled** `boolean` (default: true)

**Enable dotenv-linter**

**reviews.tools.htmlhint** `object`

HTMLHint is a static code analysis tool for HTML files.

Version: `v1.9.2`

**options**

**reviews.tools.htmlhint.enabled** `boolean` (default: true)

**Enable HTMLHint**

**reviews.tools.stylelint** `object`

Stylelint is a linter for stylesheets (CSS, SCSS, Sass, Less, SugarSS, Stylus) that helps avoid errors and enforce conventions.

Version: `v17.14.0`

**options**

**reviews.tools.stylelint.enabled** `boolean` (default: true)

**Enable Stylelint**

**reviews.tools.checkmake** `object`

checkmake is a linter for Makefiles.

Version: `v0.3.2`

**options**

**reviews.tools.checkmake.enabled** `boolean` (default: true)

**Enable checkmake**

**reviews.tools.osvScanner** `object`

OSV Scanner is a tool for vulnerability package scanning.

Version: `v2.7.0`

**options**

**reviews.tools.osvScanner.enabled** `boolean` (default: true)

**Enable OSV Scanner**: OSV Scanner is a tool for vulnerability package scanning

**reviews.tools.oasdiff** `object`

oasdiff detects breaking changes between OpenAPI specifications.

Version: `v1.34.0`

**options**

**reviews.tools.oasdiff.enabled** `boolean` (default: true)

**Enable oasdiff**

**reviews.tools.reactDoctor** `object`

React Doctor scans React codebases for security, performance, correctness, and accessibility issues.

Version: `v0.9.22`

**options**

**reviews.tools.reactDoctor.enabled** `boolean` (default: true)

**Enable React Doctor**

**reviews.tools.presidio** `object`

Microsoft Presidio Analyzer 2.2.366 detects sensitive identifiers (including payment cards, US SSN, cryptocurrency wallets, and phone numbers) in changed files. Tune entities, thresholds, and languages in repository Presidio configuration (for example .presidiocli or AnalyzerEngineProvider YAML); the built-in scan uses fixed defaults and is skipped when that configuration is present.

Version: `v2.2.366`

**options**

**reviews.tools.presidio.enabled** `boolean` (default: true)

Enable Microsoft Presidio Analyzer for high-signal PII in changed files

**reviews.tools.blinter** `object`

Blinter is a linter for Windows batch files that provides comprehensive static analysis to identify syntax errors, security vulnerabilities, performance issues, and style problems.

Version: `v1.1.62`

**options**

**reviews.tools.blinter.enabled** `boolean` (default: true)

**Enable Blinter**

**reviews.tools.smartyLint** `object`

smarty-lint is a linter for Smarty 3 template files that checks for common issues such as incorrect operator usage, naming conventions, empty blocks, and unquoted strings.

Version: `v0.3.3`

**options**

**reviews.tools.smartyLint.enabled** `boolean` (default: true)

**Enable smarty-lint**

**reviews.tools.emberTemplateLint** `object`

ember-template-lint is a linter for Handlebars template files that checks for common issues such as accessibility violations, deprecated patterns, and template anti-patterns.

Version: `v7.9.4`

**options**

**reviews.tools.emberTemplateLint.enabled** `boolean` (default: true)

**Enable ember-template-lint**

**reviews.tools.skillspector** `object`

SkillSpector is a security scanner for AI agent skills that detects vulnerabilities, malicious patterns, and security risks

Version: `v2.12.0`

**options**

**reviews.tools.skillspector.enabled** `boolean` (default: true)

**Enable SkillSpector**: SkillSpector is a security scanner for AI agent skills. It detects vulnerabilities, malicious patterns, and security risks in SKILL.md manifests and MCP configurations.

**reviews.tools.psscriptanalyzer** `object`

PSScriptAnalyzer is a static code checker for PowerShell scripts and modules.

Version: `v1.25.0`

**options**

**reviews.tools.psscriptanalyzer.enabled** `boolean` (default: true)

**Enable PSScriptAnalyzer**

## Chat

**chat.art** `boolean` (default: true)

Generate art in chat responses (ASCII or emoji).

**chat.allow\_non\_org\_members** `boolean` (default: true)

Allow non-organization members to interact with CodeRabbit in comment chat. Set to false to restrict issue/review comment interactions to organization members on GitHub organization repositories. This does not affect automatic PR review eligibility.

**chat.auto\_reply** `boolean` (default: true)

Let CodeRabbit reply automatically without requiring a mention/tag.

### Integrations

`chat.integrations`

**chat.integrations.jira** `object`

Learn more: [Jira Integration](https://docs.coderabbit.ai/connections/jira.md#configure-coderabbit-for-jira)

**options**

**chat.integrations.jira.usage** `enum` (default: auto)

**Jira**: Allow creating Jira issues from chat. 'auto' disables the integration for public repositories.

One of the following: `auto`, `enabled`, `disabled`

**chat.integrations.jira.issue\_template** `string`

**Jira Issue Template**: Structure to use for the description of Jira issues created from chat. Provide the headings your team expects, one per line, for example '## Goal', '## Description', '## Acceptance Criteria'. Leave empty to let CodeRabbit choose the structure.

> [!NOTE]
>
> Max length: 3000

**chat.integrations.linear** `object`

Learn more: [Linear Integration](https://docs.coderabbit.ai/connections/linear.md#configure-coderabbit-for-linear)

**options**

**chat.integrations.linear.usage** `enum` (default: auto)

**Linear**: Allow creating Linear issues from chat. 'auto' disables the integration for public repositories.

One of the following: `auto`, `enabled`, `disabled`

## Knowledge base

**knowledge\_base.opt\_out** `boolean` (default: false)

**Opt Out**: Disable knowledge base features that require data retention. Opting out removes any existing stored knowledge base data.

Learn more: [Knowledge Base overview](https://docs.coderabbit.ai/knowledge-base.md#global-configuration)

**knowledge\_base.automatic\_linking\_mode** `enum` (default: disabled)

**Automatic Linking Mode**: For Auto, private repositories may automatically link to public or private repositories, while public repositories may automatically link only to public repositories. Enabled uses context from any eligible repository in the organization, whether public or private. Disabled creates no automatic repository links. Manual repository links configured below are unaffected.

One of the following: `auto`, `enabled`, `disabled`

Learn more: [Multi-Repo Analysis](https://docs.coderabbit.ai/knowledge-base/multi-repo-analysis.md#automatic-repository-linking)

**knowledge\_base.automatic\_repository\_linking** `boolean` (default: false)

**Automatic Repository Linking**: Deprecated. This setting has no effect. Use `knowledge_base.automatic_linking_mode` instead.

Learn more: [Multi-Repo Analysis](https://docs.coderabbit.ai/knowledge-base/multi-repo-analysis.md#automatic-repository-linking)

**knowledge\_base.linked\_repositories** `array of object`

**Linked Repositories**: Repositories that CodeRabbit should consider when reviewing PRs in this repo. Use this to surface cross-repo dependencies and catch breaking changes across related codebases.

Learn more: [Multi-Repo Analysis](https://docs.coderabbit.ai/knowledge-base/multi-repo-analysis.md)

**options**

**knowledge\_base.linked\_repositories\[].repository** `string`

Repository name in owner/repo format (e.g., GitHub: myorg/backend-api, Azure DevOps: My Project/backend-api, GitLab: group/subgroup/repo, Bitbucket: workspace/repo)

**knowledge\_base.linked\_repositories\[].instructions** `string`

Optionally provide description and guidance on what this repository contains for CodeRabbit to consider during reviews. Example: 'Contains REST API endpoints and database models.'

> [!NOTE]
>
> Max length: 2000

### Web search

`knowledge_base.web_search`

Learn more: [Web Search](https://docs.coderabbit.ai/knowledge-base/web-search.md)

**knowledge\_base.web\_search.enabled** `boolean` (default: true)

**Web Search**: Use web search to gather additional context.

### Code guidelines

`knowledge_base.code_guidelines`

Use your coding guideline documents (see File Patterns) as review criteria.

Learn more: [Code Guidelines](https://docs.coderabbit.ai/knowledge-base/code-guidelines.md)

**knowledge\_base.code\_guidelines.enabled** `boolean` (default: true)

**Enabled**: Apply your organization's coding standards during reviews.

**knowledge\_base.code\_guidelines.filePatterns** `array of object`

**File Patterns**: Additional guideline files, as glob strings or `{ files, applyTo }` objects. A string entry such as `**/CODING_STANDARDS.md` locates guideline files. An object entry sets `files` (the guideline documents) and `applyTo` (the source files they govern, for example `**/*.ts`), each a comma-separated list of globs. Either form can name a file in another repository of your organization as `repo:path` or `owner/repo:path` (for example `engineering-standards:frontend/react.md`), read from that repository's default branch. On Azure DevOps Services, use `repo:path` within the reviewed project or `org/project/repo:path` for another project in the same organization; write project names with literal spaces. Supplements the [default patterns](https://docs.coderabbit.ai/knowledge-base/code-guidelines.md#supported-files); does not replace them. File names are case-sensitive.

### Learnings

`knowledge_base.learnings`

Learn more: [Learnings](https://docs.coderabbit.ai/knowledge-base/learnings.md)

**knowledge\_base.learnings.scope** `enum` (default: auto)

**Learnings**: Choose scope: 'local' (repo), 'global' (org), or 'auto' (local for public repos, global for private repos).

One of the following: `local`, `global`, `auto`

<ul>
  <li>`auto`: When reviewing a public repository, uses only that repository's learnings. When reviewing a private repository, uses all of your organization's learnings.</li>
  <li>`global`: Uses all of your organization's learnings in every review.</li>
  <li>`local`: Uses only the learnings of the repository being reviewed.</li>
</ul>

**knowledge\_base.learnings.approval\_delay** `integer` (default: 0)

Days admins have to approve or reject a learning before it is automatically applied. Must be an integer between 0 and 30. Set to 0 to apply learnings immediately without approval.

> [!NOTE]
>
> Min: 0, Max: 30

### Issues

`knowledge_base.issues`

Learn more: [Knowledge Base overview](https://docs.coderabbit.ai/knowledge-base.md#issue-trackers-and-past-pull-requests)

**knowledge\_base.issues.scope** `enum` (default: auto)

**Issues**: Choose scope for GitHub/GitLab issues: 'local' (repo), 'global' (org), or 'auto' (local for public repos, global for private repos).

One of the following: `local`, `global`, `auto`

### Jira

`knowledge_base.jira`

Learn more: [Knowledge Base overview](https://docs.coderabbit.ai/knowledge-base.md#issue-trackers-and-past-pull-requests)

**knowledge\_base.jira.usage** `enum` (default: auto)

**Jira**: Use Jira as a knowledge source. 'auto' disables the integration for public repositories.

One of the following: `auto`, `enabled`, `disabled`

**knowledge\_base.jira.project\_keys** `array of string`

**Jira Project Keys**: Restrict Jira context to these projects.

Learn more: [Jira Integration](https://docs.coderabbit.ai/connections/jira.md#configure-coderabbit-for-jira)

**knowledge\_base.jira.excluded\_project\_keys** `array of string`

**Jira Excluded Project Keys**: Never use these Jira projects as CodeRabbit context, regardless of repository allowlists. Managed at the workspace level as a security policy; exclusions always take precedence over any allowlist.

Learn more: [Jira Integration](https://docs.coderabbit.ai/connections/jira.md#configure-coderabbit-for-jira)

### Linear

`knowledge_base.linear`

Learn more: [Knowledge Base overview](https://docs.coderabbit.ai/knowledge-base.md#issue-trackers-and-past-pull-requests)

**knowledge\_base.linear.usage** `enum` (default: auto)

**Linear**: Use Linear as a knowledge source. 'auto' disables the integration for public repositories.

One of the following: `auto`, `enabled`, `disabled`

**knowledge\_base.linear.team\_keys** `array of string`

**Linear Team Keys**: Restrict Linear context to these teams (e.g. 'ENG').

Learn more: [Linear Integration](https://docs.coderabbit.ai/connections/linear.md#configure-coderabbit-for-linear)

### Pull requests

`knowledge_base.pull_requests`

Learn more: [Knowledge Base overview](https://docs.coderabbit.ai/knowledge-base.md#issue-trackers-and-past-pull-requests)

**knowledge\_base.pull\_requests.scope** `enum` (default: auto)

**PRs**: Choose scope: 'local' (repo), 'global' (org), or 'auto' (local for public repos, global for private repos).

One of the following: `local`, `global`, `auto`

### MCP

`knowledge_base.mcp`

Learn more: [MCP Servers](https://docs.coderabbit.ai/knowledge-base/mcp-context.md)

**knowledge\_base.mcp.usage** `enum` (default: auto)

**MCP**: Use MCP servers as a knowledge source. 'auto' disables the integration for public repositories.

One of the following: `auto`, `enabled`, `disabled`

<ul>
  <li>`auto`: Uses MCP servers as a knowledge source on private repositories and skips them on public repositories.</li>
  <li>`enabled`: Uses MCP servers on all repositories, including public ones.</li>
  <li>`disabled`: Never uses MCP servers as a knowledge source.</li>
</ul>

**knowledge\_base.mcp.disabled\_servers** `array of string`

**Disabled MCP Servers**: Specify MCP server labels to disable (case-insensitive). These servers will be excluded from reviews and knowledge base queries.

## Code generation

### Unit Test Generation

`code_generation.unit_tests`

Settings for generating unit tests.

Learn more: [Generate unit tests](https://docs.coderabbit.ai/finishing-touches/unit-test-generation.md)

**code\_generation.unit\_tests.path\_instructions** `array of object`

**Path Instructions**: Add path-specific guidelines for unit test generation.

Learn more: [Generate unit tests](https://docs.coderabbit.ai/finishing-touches/unit-test-generation.md#path-specific-customization)

**options**

**code\_generation.unit\_tests.path\_instructions\[].path** `string`

File path glob pattern. Example: `**/*.js`.

**code\_generation.unit\_tests.path\_instructions\[].instructions** `string`

Additional unit-test-generation guidelines for matching paths.

> [!NOTE]
>
> Max length: 20000

## Issue enrichment

### Auto enrich

`issue_enrichment.auto_enrich`

Settings for automatic issue enrichment.

Learn more: [Issue Enrichment](https://docs.coderabbit.ai/issues/enrichment.md#disable-issue-enrichment)

**issue\_enrichment.auto\_enrich.enabled** `boolean` (default: false)

**Automatic Issue Enrichment**: Analyze and enrich issues with additional context (related code, potential solutions, complexity assessment).

### Planning

`issue_enrichment.planning`

Settings for issue planning.

Learn more: [Issue Planner](https://docs.coderabbit.ai/issues/planner)

**issue\_enrichment.planning.enabled** `boolean` (default: true)

**Issue Planning**: Generate an implementation plan for issues (early preview).

**issue\_enrichment.planning.auto\_planning** `object`

**options**

**issue\_enrichment.planning.auto\_planning.enabled** `boolean` (default: true)

**Automatic Planning**: Trigger issue planning based on labels.

**issue\_enrichment.planning.auto\_planning.labels** `array of string`

Labels that trigger automatic issue planning. Labels starting with '!' are negative matches. Examples: \['feature', 'enhancement'] plans issues with either label. \['!wip'] plans all issues except those labeled 'wip'. \['feature', '!wip'] plans issues labeled 'feature' but not 'wip'.

### Labeling

`issue_enrichment.labeling`

Settings for issue labeling.

Learn more: [Issue Enrichment](https://docs.coderabbit.ai/issues/enrichment.md#smart-auto-labeling)

**issue\_enrichment.labeling.labeling\_instructions** `array of object`

**Labeling Instructions**: Define issue labels to suggest and when to suggest them.

**options**

**issue\_enrichment.labeling.labeling\_instructions\[].label** `string`

Label to suggest for the issue. Example: enhancement

**issue\_enrichment.labeling.labeling\_instructions\[].instructions** `string`

Instructions for the label. Example: New feature or request.

> [!NOTE]
>
> Max length: 3000

**issue\_enrichment.labeling.auto\_apply\_labels** `boolean` (default: false)

Automatically apply suggested labels to the issue. When enabled without labeling instructions, labels are auto-suggested based on similar issues.

## Related resources

> [card] [Review commands](https://docs.coderabbit.ai/reference/review-commands.md)
>
> Learn about @coderabbitai commands

> [card] [Tools reference](https://docs.coderabbit.ai/tools/reference.md)
>
> Browse all supported linters and analyzers


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.