
Consolidated Review: PR #{number}【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/ArchonDate: {ISO timestamp}Agents: code-review, error-handling, test-coverage, comment-quality, docs-impactTotal Findings: {count}### 4.2 Executive Summary 与总体裁决 markdown ## Executive Summary {3-5 sentence overview of PR quality and main concerns} **Overall Verdict**: {APPROVE | REQUEST_CHANGES | NEEDS_DISCUSSION} **Auto-fix Candidates**: {n} CRITICAL HIGH issues can be auto-fixed **Manual Review Needed**: {n} MEDIUM LOW issues require decision这里定义了三个决策关键量总体裁决三个取值、可自动修复数CRITICALHIGH 之和直接决定下游archon-implement-review-fixes的工作量、需要人工决策数MEDIUMLOW。4.3 Statistics 表| Agent | CRITICAL | HIGH | MEDIUM | LOW | Total | |-------|----------|------|--------|-----|-------| | Code Review | {n} | {n} | {n} | {n} | {n} | | Error Handling | {n} | {n} | {n} | {n} | {n} | | Test Coverage | {n} | {n} | {n} | {n} | {n} | | Comment Quality | {n} | {n} | {n} | {n} | {n} | | Docs Impact | {n} | {n} | {n} | {n} | {n} | | **Total** | **{n}** | **{n}** | **{n}** | **{n}** | **{n}** |4.4 CRITICAL / HIGH 问题的条目模板每个 CRITICAL 或 HIGH 问题采用统一条目结构### Issue 1: {Title} **Source Agent**: {agent-name} **Location**: {file}:{line} **Category**: {category} **Problem**: {description} **Recommended Fix**: typescript {fix code}Why Critical: {impact explanation}**Recommended Fix** 必须携带可直接落地的修复代码因为下游实施步骤见下文第 6 节会直接消费这段代码——archon-implement-review-fixes 明确指出 If consolidated doesnt have full fix code, read original artifacts说明主产物中的修复代码是首选输入缺失时才回退到各 Agent 原始产物。 ### 4.5 MEDIUM 问题的选项表 MEDIUM 问题不给唯一答案而是提供三选项决策表 markdown | Option | Approach | Effort | Risk if Skipped | |--------|----------|--------|-----------------| | Fix Now | {approach} | {LOW/MED/HIGH} | {risk} | | Create Issue | Defer to separate PR | LOW | {risk} | | Skip | Accept as-is | NONE | {risk} |并附Recommendation字段说明推荐哪条路径及理由。这正是合成阶段「把判断权留给人类、把信息备齐」的设计MEDIUM/LOW 问题由用户决策Agent 只提供选项和推荐。4.6 LOW 问题与积极观察LOW 问题以紧凑表格呈现| Issue | Location | Agent | Suggestion | |-------|----------|-------|------------| | {title} | file:line | {agent} | {brief recommendation} |Positive Observations汇总各 Agent 的正面发现结构良好的代码、某处良好的错误处理、对某功能的全面测试、清晰的文档保证评审不是只报问题。4.7 后续 Issue 建议与 Next Steps## Suggested Follow-up Issues | Issue Title | Priority | Related Finding | |-------------|----------|-----------------| | {suggested issue title} | {P1/P2/P3} | MEDIUM issue #{n} |Next Steps 明确下游动作自动修复步骤处理 CRITICALHIGH → 人工决策 MEDIUM → 考虑 LOW。4.8 Agent Artifacts 与 Metadata最后用两张表收尾Agent Artifacts 表各 Agent 的产物文件名与发现数、Metadata合成时间戳与产物路径。Phase 3 检查点Consolidated artifact createdAll findings includedSeverity ordering correctOptions provided for MEDIUM/LOW5. Phase 4POST —— 发布 GitHub PR 评论合成后的第二步交付物是一段 GitHub 友好的评审评论通过ghCLI 发布gh pr comment {number} --body $(cat EOF # Comprehensive PR Review **PR**: #{number} **Reviewed by**: 5 specialized agents **Date**: {date} --- ## Summary {executive summary} **Verdict**: {APPROVE | REQUEST_CHANGES} | Severity | Count | |----------|-------| | CRITICAL | {n} | | HIGH | {n} | | MEDIUM | {n} | | LOW | {n} | EOF )评论模板完整见 archon-synthesize-review.md在设计上有几个值得注意的要点严重级别 emoji 约定 CRITICAL / HIGH / MEDIUM / LOW与 archon-post-review-to-pr.md 中的约定LOW 用 略有差异但语义一致可折叠详情每个修复方案包在detailssummaryView fix/summary.../details中控制评论体积避免长 PR 评论刷屏CRITICAL/HIGH 标注 Auto-fixing明示这些将由下游自动修复而 MEDIUM 标注 Needs Decision评论尾部注明*Reviewed by Archon comprehensive-pr-review workflow*与产物路径$ARTIFACTS_DIR/review/。Phase 4 检查点GitHub comment postedFormatting renders correctlyAll severity levels included6. Phase 5OUTPUT 与成功标准合成命令的最后输出只保留一句极简确认因其会作为评论发布保持输出干净是刻意设计✅ Review synthesis complete. Proceeding to auto-fix step...【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