Comment Quality Review — PR #
【免费下载链接】ArchonThe first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.项目地址: https://gitcode.com/GitHub_Trending/archon3/Archon
Summary
<1-2 sentences. Comment quality: good / minor-issues / significant-rot-risk.>
Findings
HIGH — inaccurate comments (don't match the code)
- file:line:
- Suggested fix:
MEDIUM — comment rot risk
- (same format — references that will rot, restated-what-not-why, multi-paragraph fluff)
LOW — style / consistency
- (same format)
Comments that are actually valuable
<optionally call out 1-2 cases where the new comments do a great job of capturing non-obvious WHY. Helps reinforce good patterns.>
Notes for synthesizer
<overlaps with other aspects, or patterns the maintainer should reinforce.>
模板设计的几个要点： - **严重度分级**（HIGH / MEDIUM / LOW）与代码评审命令（[maintainer-review-code-review.md](https://link.gitcode.com/i/91253189aa352c80627e58e604a9e61e) 的 CRITICAL/HIGH/MEDIUM/LOW 体系）对齐但不相同——注释问题几乎不会构成 CRITICAL 级别的阻塞，所以从 HIGH 起步； - **每条 HIGH 必须同时给出精确位置（file:line）、问题描述和修复建议（update or remove）**，保证可操作性； - **专门保留“有价值的注释”小节**（Comments that are actually valuable），用于正向强化优秀模式——这不是客套，而是让评审在“挑毛病”之外也能沉淀可复制的良好注释范例； - **Notes for synthesizer 小节**是给下游汇总节点看的，用于标注与其他评审方面的重叠或需要维护者特别留意的模式。 若注释整体干净，则按命令要求写入 `## Findings\n\nComments are accurate and capture non-obvious WHY where present.` 并直接结束——**不要为了凑发现而制造问题**。这一“禁止编造问题”的要求与代码评审命令中的 “Don't manufacture issues” 一脉相承，是整个评审体系可靠性的底线。 产物文件被下游消费的链路是：`maintainer-review-synthesize` 节点读取 `$ARTIFACTS_DIR/review/` 下所有评审产物（含 `comment-quality-findings.md`）进行跨方面去重、按严重度归并，最终写成 `$ARTIFACTS_DIR/review/synthesis.md` 与可直接发到 PR 的 `$ARTIFACTS_DIR/review/review-comment.md`（见 [maintainer-review-synthesize.md](https://link.gitcode.com/i/9ef76a33b9235340c914362acafa3e03)）。因此注释质量评审只需写好产物文件，后续的汇总与发布由工作流自动接续。 --- ## 六、Phase 4：RETURN——单行摘要与质量门禁 评审完成时，Agent 只需返回一行固定格式的摘要（完整发现留在产物文件中，由 synthesize 读取）：Comment-quality review complete. HIGH, MEDIUM, LOW findings. Quality: <good|minor-issues|significant-rot-risk>.
【免费下载链接】ArchonThe first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.项目地址: https://gitcode.com/GitHub_Trending/archon3/Archon
创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考
