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

# Reviews

> Endpoints for triggering AI code reviews, querying review results, and accessing review details such as comments, files, rounds, and AI logs.

All review endpoints are under `/api/reviews` and require authentication.

***

## List reviews

`GET /api/reviews`

Returns a paginated list of review history records, optionally filtered by project, status, or date range.

```bash theme={null}
curl -X GET "https://your-domain.com/api/reviews?page=1&pageSize=20" \
  -H "Authorization: Bearer <api-key>"
```

**Query parameters**

<ParamField query="page" type="number">
  Page number (1-indexed). Default: `1`.
</ParamField>

<ParamField query="pageSize" type="number">
  Items per page. Default: `20`.
</ParamField>

<ParamField query="projectId" type="string">
  Filter by project UUID.
</ParamField>

<ParamField query="status" type="string">
  Filter by review status. Values: `pending`, `completed`, `failed`.
</ParamField>

<ParamField query="startDate" type="string">
  ISO 8601 start date for date range filter.
</ParamField>

<ParamField query="endDate" type="string">
  ISO 8601 end date for date range filter.
</ParamField>

**Response `200`**

<ResponseField name="data.items" type="array">
  List of review history objects.

  <Expandable title="Review history fields">
    <ResponseField name="id" type="string">Review UUID.</ResponseField>
    <ResponseField name="projectId" type="string">Project UUID.</ResponseField>
    <ResponseField name="projectName" type="string">Human-readable project name.</ResponseField>
    <ResponseField name="mrIid" type="number">MR / PR number on the platform.</ResponseField>
    <ResponseField name="mrTitle" type="string">MR / PR title.</ResponseField>
    <ResponseField name="mrUrl" type="string">URL to the MR / PR on the platform.</ResponseField>
    <ResponseField name="status" type="string">`pending` | `completed` | `failed`</ResponseField>
    <ResponseField name="aiProvider" type="string">AI provider used for this review.</ResponseField>
    <ResponseField name="aiModel" type="string">Model identifier.</ResponseField>
    <ResponseField name="commentCount" type="number">Number of review comments posted.</ResponseField>
    <ResponseField name="triggeredBy" type="string">`auto` | `manual`</ResponseField>
    <ResponseField name="overallRating" type="string">Rating grade: `A`, `B`, `C`, `D`, or `F`.</ResponseField>
    <ResponseField name="summary" type="string">AI-generated review summary.</ResponseField>
    <ResponseField name="createdAt" type="string">ISO 8601 timestamp.</ResponseField>
    <ResponseField name="completedAt" type="string | null">ISO 8601 timestamp when the review finished.</ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="data.stats" type="object">
  Aggregate statistics for the filtered result set.
</ResponseField>

<ResponseField name="meta.pagination" type="object">
  Standard pagination metadata.
</ResponseField>

***

## Trigger a manual review

`POST /api/reviews/trigger-manual-review`

Manually queues an AI review for a specific merge request or pull request. Returns `202 Accepted` with a task ID you can poll for status.

Requires the `review:create` permission.

```bash theme={null}
curl -X POST https://your-domain.com/api/reviews/trigger-manual-review \
  -H "Authorization: Bearer <api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "projectId": "<project-uuid>",
    "mrIid": 42,
    "sendToPlatform": true,
    "templateId": "<template-uuid>"
  }'
```

**Request body**

<ParamField body="projectId" type="string" required>
  UUID of the project to review.
</ParamField>

<ParamField body="mrIid" type="number" required>
  Internal MR / PR number on the platform (the `!42` or `#42` number).
</ParamField>

<ParamField body="sendToPlatform" type="boolean">
  Whether to post review comments back to GitLab / GitHub. Defaults to the project setting.
</ParamField>

<ParamField body="templateId" type="string">
  UUID of the review template to use. Defaults to the project or global default.
</ParamField>

**Response `202`**

<ResponseField name="data.queued" type="boolean">
  `true` when the task was successfully queued.
</ResponseField>

<ResponseField name="data.task" type="object">
  <Expandable title="Task fields">
    <ResponseField name="id" type="string">Task ID for polling.</ResponseField>
    <ResponseField name="status" type="string">`queued` | `failed`</ResponseField>
    <ResponseField name="sentToPlatform" type="boolean">Whether comments will be posted to the platform.</ResponseField>
    <ResponseField name="location" type="string">URL path to poll for task status.</ResponseField>
  </Expandable>
</ResponseField>

***

## Get review details

`GET /api/reviews/:reviewId`

Returns full details for a single review.

```bash theme={null}
curl -X GET https://your-domain.com/api/reviews/<review-uuid> \
  -H "Authorization: Bearer <api-key>"
```

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data.review" type="object">
  Full review record. Same fields as the list response items, plus `baseCommitSha`, `headCommitSha`, `roundNumber`, `appliedRuleIds`, and `reviewedLines`.
</ResponseField>

***

## List review comments

`GET /api/reviews/:reviewId/comments`

Returns AI-generated comments for a review with optional filtering.

```bash theme={null}
curl -X GET "https://your-domain.com/api/reviews/<review-uuid>/comments?severity=error" \
  -H "Authorization: Bearer <api-key>"
```

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

<ParamField query="filePath" type="string">
  Filter comments to a specific file path.
</ParamField>

<ParamField query="severity" type="string">
  Filter by severity. Values: `info`, `warning`, `error`.
</ParamField>

<ParamField query="limit" type="number">
  Maximum number of comments to return. Default: `20`.
</ParamField>

<ParamField query="offset" type="number">
  Number of comments to skip for pagination. Default: `0`.
</ParamField>

**Response `200`**

<ResponseField name="data.items" type="array">
  <Expandable title="Comment fields">
    <ResponseField name="id" type="string">Comment UUID.</ResponseField>
    <ResponseField name="reviewId" type="string">Parent review UUID.</ResponseField>
    <ResponseField name="filePath" type="string">File path the comment references.</ResponseField>
    <ResponseField name="lineNumber" type="number">Line number in the diff.</ResponseField>
    <ResponseField name="severity" type="string">`info` | `warning` | `error`</ResponseField>
    <ResponseField name="message" type="string">The review comment text.</ResponseField>
    <ResponseField name="gitlabDiscussionId" type="string | null">GitLab discussion ID if the comment was posted.</ResponseField>
    <ResponseField name="createdAt" type="string">ISO 8601 timestamp.</ResponseField>
  </Expandable>
</ResponseField>

***

## List review files

`GET /api/reviews/:reviewId/files`

Returns the files that were reviewed.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data.files" type="array">
  <Expandable title="File fields">
    <ResponseField name="id" type="string">File record UUID.</ResponseField>
    <ResponseField name="filePath" type="string">File path relative to repository root.</ResponseField>
    <ResponseField name="oldPath" type="string | null">Previous path for renamed files.</ResponseField>
    <ResponseField name="changeType" type="string">`new` | `modified` | `deleted` | `renamed`</ResponseField>
    <ResponseField name="summary" type="string | null">AI-generated summary for the file.</ResponseField>
    <ResponseField name="commentCount" type="number">Number of comments on this file.</ResponseField>
  </Expandable>
</ResponseField>

***

## Get file review progress

`GET /api/reviews/:reviewId/files/progress`

Returns per-file processing progress and prompt summary for an in-progress or completed review.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data.files" type="array">
  Array of file progress objects, each containing the file path and current processing status.
</ResponseField>

***

## Retry a single file review

`POST /api/reviews/:reviewId/files/:fileId/retry`

Re-runs the AI review for a single file within an existing review. Requires `review:create` permission.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

<ParamField path="fileId" type="string" required>
  UUID of the review file record to retry.
</ParamField>

***

## List review rounds

`GET /api/reviews/:reviewId/rounds`

Returns all review rounds. Multi-round reviews are used for differential re-reviews after new commits.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data.rounds" type="array">
  <Expandable title="Round fields">
    <ResponseField name="id" type="string">Round UUID.</ResponseField>
    <ResponseField name="roundNumber" type="number">Sequential round number starting at 1.</ResponseField>
    <ResponseField name="isDifferential" type="boolean">Whether this round only reviewed changed files since the previous round.</ResponseField>
    <ResponseField name="createdAt" type="string">ISO 8601 timestamp.</ResponseField>
  </Expandable>
</ResponseField>

***

## List review feedbacks

`GET /api/reviews/:reviewId/feedbacks`

Returns user feedback records (positive / negative) for a review's comments.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data.feedbacks" type="array">
  <Expandable title="Feedback fields">
    <ResponseField name="id" type="string">Feedback UUID.</ResponseField>
    <ResponseField name="feedbackType" type="string">`positive` | `negative`</ResponseField>
    <ResponseField name="trackingStatus" type="string">`pending` | `accepted` | `rejected` | `implemented`</ResponseField>
    <ResponseField name="username" type="string | null">User who gave the feedback.</ResponseField>
    <ResponseField name="createdAt" type="string">ISO 8601 timestamp.</ResponseField>
  </Expandable>
</ResponseField>

***

## Get AI call logs

`GET /api/reviews/:reviewId/ai-logs`

Returns a log of every AI API call made during the review, including token usage and response times.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

<ParamField query="limit" type="number">
  Maximum number of log entries to return. Default: `50`, max: `200`.
</ParamField>

<ParamField query="offset" type="number">
  Number of entries to skip. Default: `0`.
</ParamField>

<ParamField query="provider" type="string">
  Filter by AI provider name.
</ParamField>

<ParamField query="status" type="string">
  Filter by call status (e.g., `success`, `failed`).
</ParamField>

**Response `200`**

<ResponseField name="data.items" type="array">
  <Expandable title="AI log fields">
    <ResponseField name="id" type="string">Log entry UUID.</ResponseField>
    <ResponseField name="provider" type="string">AI provider name.</ResponseField>
    <ResponseField name="model" type="string">Model identifier.</ResponseField>
    <ResponseField name="status" type="string">Call outcome: `success` | `failed`.</ResponseField>
    <ResponseField name="durationMs" type="number">Round-trip duration in milliseconds.</ResponseField>
    <ResponseField name="promptTokens" type="number">Tokens in the prompt.</ResponseField>
    <ResponseField name="completionTokens" type="number">Tokens in the completion.</ResponseField>
    <ResponseField name="totalTokens" type="number">Total tokens consumed.</ResponseField>
    <ResponseField name="filePath" type="string | null">File being reviewed at call time.</ResponseField>
    <ResponseField name="createdAt" type="string">ISO 8601 timestamp.</ResponseField>
  </Expandable>
</ResponseField>

***

## Get execution logs

`GET /api/reviews/:reviewId/logs`

Returns runner / executor execution logs for a review.

<ParamField path="reviewId" type="string" required>
  UUID of the review.
</ParamField>

**Response `200`**

<ResponseField name="data" type="object">
  Execution log data for the review's runner task.
</ResponseField>

***

## List all review tasks

`GET /api/reviews/tasks`

Returns a paginated list of all review queue tasks (both automatic and manual).

<ParamField query="page" type="number">
  Page number. Default: `1`.
</ParamField>

<ParamField query="pageSize" type="number">
  Items per page. Default: `20`.
</ParamField>

<ParamField query="status" type="string">
  Filter by task status (e.g., `pending`, `completed`, `failed`).
</ParamField>

***

## Manual review helper endpoints

### Get projects available for manual review

`GET /api/reviews/manual/projects`

Returns projects that are enabled and can have a manual review triggered.

### Get manual review history

`GET /api/reviews/manual/history`

<ParamField query="limit" type="number">
  Number of recent entries to return. Min: `1`, max: `20`, default: `5`.
</ParamField>

### Get merge requests for a project

`GET /api/reviews/manual/merge-requests`

Fetches open MRs / PRs from the platform for use in the manual review dialog.

<ParamField query="projectId" type="string" required>
  UUID of the project.
</ParamField>

<ParamField query="state" type="string">
  MR state filter: `all` | `opened` | `merged` | `closed`. Default: `opened`.
</ParamField>

<ParamField query="search" type="string">
  Search term to filter MRs by title.
</ParamField>

### Get recent manual tasks

`GET /api/reviews/manual/tasks/recent`

<ParamField query="limit" type="number">
  Number of tasks to return. Default: `5`.
</ParamField>

### Get manual task status

`GET /api/reviews/manual/tasks/:taskId`

Poll the status of a specific manual review task.

<ParamField path="taskId" type="string" required>
  Task ID returned by the trigger endpoint.
</ParamField>

**Response `200`**

<ResponseField name="data.task" type="object">
  Task record including `id`, `status`, `reviewId`, and timestamps.
</ResponseField>

***

## List review templates

`GET /api/reviews/templates/all`

Returns all available review prompt templates.

**Response `200`**

<ResponseField name="data.templates" type="array">
  <Expandable title="Template fields">
    <ResponseField name="id" type="string">Template UUID.</ResponseField>
    <ResponseField name="name" type="string">Template display name.</ResponseField>
    <ResponseField name="description" type="string | null">Optional description.</ResponseField>
    <ResponseField name="isDefault" type="boolean">Whether this is the global default template.</ResponseField>
  </Expandable>
</ResponseField>

***

## List review rules

`GET /api/reviews/rules/all`

Returns all configured review rules (file pattern matching, severity filters, etc.).

**Response `200`**

<ResponseField name="data.rules" type="array">
  <Expandable title="Rule fields">
    <ResponseField name="id" type="string">Rule UUID.</ResponseField>
    <ResponseField name="ruleName" type="string">Rule display name.</ResponseField>
    <ResponseField name="enabled" type="boolean">Whether the rule is active.</ResponseField>
    <ResponseField name="fileTypePatterns" type="array">Glob patterns for file extensions to match.</ResponseField>
    <ResponseField name="filePathPatterns" type="array">Glob patterns for file paths to match.</ResponseField>
    <ResponseField name="priority" type="number">Rule evaluation order (higher = earlier).</ResponseField>
  </Expandable>
</ResponseField>