add docs/tests#49
Conversation
|
Warning Review limit reached
More reviews will be available in 48 minutes and 44 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
PR 标题
docs: 添加 Prompt 调优测试报告(V1 基线 与 V3 对比)
功能描述
本次新增两份 Prompt 调优测试报告文档,用于记录 AI PR Review 系统中 Prompt 迭代的效果对比:
test1 — V1 基线报告:对 TheAlgorithms/Java#7427(QR 分解)PR 执行 10 轮 AI 评审,记录成功率、风险评级分布、跨文件问题检出、架构建议、响应时间及跨轮一致性。
test2 — V3 对比报告:对同一 PR 执行 5 轮 V3 版本 Prompt 的 AI 评审,并与 V1 进行量化对比,涵盖数值稳定性检出率、边界条件覆盖、摘要模板一致性、issueType 多样性等维度。
报告存放在 backend/pr/src/main/resources/docs/ 下,作为 Prompt 迭代调优的历史记录与决策依据,供团队回溯各版本 Prompt 的实际表现。
实现思路
采用格式化纯文本(Markdown 兼容)格式记录测试报告,每轮运行独立记录以下要素:AI 输出摘要、风险等级及理由、跨文件问题列表、架构建议、响应时间、错误信息。末尾附跨轮聚合统计(风险分布、一致性指标)以及版本间的量化对比数据。报告由 /review 流程自动生成并写入 resources 目录,无需额外依赖。
测试:
无需测试