aida_log_review
Log code review results to track quality and identify patterns in AI-assisted development sessions.
Instructions
当你完成一轮代码审查后调用。记录审查结果。
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| taskId | No | 关联的任务ID | |
| result | Yes | 审查结果：pass 或 fail | |
| issues | No | 发现的问题，逗号分隔。通过时不填。 | |
| scope | No | 审查覆盖的文件或模块范围 |
Implementation Reference
- src/mcp/server.ts:404-427 (handler)Implementation of the handleLogReview function, which logs a review entry into the system data.
function handleLogReview(args: any): any { const result = args.result || 'pass'; const { path, data } = ensureRunJson(); const id = nextId(data.reviews, 'REV'); const issues = args.issues ? args.issues.split(',').map((s: string) => s.trim()).filter(Boolean) : []; const review: ReviewItem = { reviewId: id, taskId: args.taskId || data.context.currentTaskId || null, result: result as ReviewItem['result'], issueCount: issues.length, scope: args.scope || '', reviewedAt: now(), issues, }; data.reviews.push(review); data.summary.reviewCount = data.reviews.length; data.summary.reviewPassCount = data.reviews.filter(r => r.result === 'pass').length; data.summary.reviewFailCount = data.reviews.filter(r => r.result === 'fail').length; addEvent(data, 'review_created', { reviewId: id, result }); addTimeline(data, 'review', `${id}: ${result}`); save(path, data); syncTokenUsage(path, data); return { success: true, reviewId: id, message: `${id}: ${result}` }; } - src/mcp/server.ts:695-697 (registration)Registration of the aida_log_review tool handler in the main server switch block.
case 'aida_log_review': result = handleLogReview(args); break;