mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-14 02:42:04 +08:00

Files

catlog22 7aa1cda367 feat: add issue discovery view for managing discovery sessions and findings

- Implemented main render function for the issue discovery view.
- Added data loading functions to fetch discoveries, details, findings, and progress.
- Created rendering functions for discovery list and detail sections.
- Introduced filtering and searching capabilities for findings.
- Implemented actions for exporting and dismissing findings.
- Added polling mechanism to track discovery progress.
- Included utility functions for HTML escaping and cleanup.

2025-12-28 17:21:07 +08:00

1.8 KiB

Raw Blame History

Phase 3.5: Consolidation

使用 universal-executor 子 Agent 执行质量检查，避免主 Agent 内存溢出。

核心原则

主 Agent 负责编排，子 Agent 负责繁重计算。

执行流程

const agentResults = JSON.parse(Read(`${workDir}/agent-results.json`));

// 委托给 universal-executor 执行整合检查
const result = Task({
  subagent_type: 'universal-executor',
  run_in_background: false,
  prompt: buildConsolidationPrompt(workDir)
});

const consolidationResult = JSON.parse(result);

Prompt 构建

function buildConsolidationPrompt(workDir) {
  return `
[ROLE] Quality Analyst

[TASK]
检查所有章节的一致性和完整性

[INPUT]
- 章节文件: ${workDir}/sections/section-*.md
- Agent 结果: ${workDir}/agent-results.json

[CHECKS]
1. Markdown 语法有效性
2. 截图标记格式 (<!-- SCREENSHOT: id="..." -->)
3. 交叉引用有效性
4. 术语一致性
5. 代码块语言标注

[OUTPUT]
1. 写入 ${workDir}/consolidation-summary.md
2. 写入 ${workDir}/screenshots-list.json (截图清单)

[RETURN JSON]
{
  "status": "completed",
  "sections_checked": <n>,
  "screenshots_found": <n>,
  "issues": { "errors": <n>, "warnings": <n> },
  "quality_score": <0-100>
}
`;
}

Agent 职责

读取章节 → 逐个检查 section-*.md
提取截图 → 收集所有截图标记
验证引用 → 检查交叉引用有效性
评估质量 → 计算综合分数
输出报告 → consolidation-summary.md

输出

consolidation-summary.md - 质量报告
screenshots-list.json - 截图清单（供 Phase 4 使用）

质量门禁

无错误
总分 >= 60%
交叉引用有效

下一阶段

→ Phase 4: Screenshot Capture

1.8 KiB Raw Blame History