docs: 更新 Dev-Agent 职责边界和 Issue 处理规则

- 明确 QE-Agent 职责: main 分支健康 + 新功能验收测试 - Dev-Agent 自行验证修复后关闭 Issue，不等 QE 确认 - Issue polling 优先级: product-code → [product] → 无标识 - Issue 创建标签: product-code / test-code - 更新闭环流程图和检查清单 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-01 13:35:00 +08:00
24 changed files with 304 additions and 1940 deletions
@@ -1,17 +1,3 @@
 {
-    "permissionMode": "bypass",
+  "permissionMode": "bypass"
    "permissions": {
      "allow": [
        "Bash(git *)",
        "Bash(python scripts/agent_poller.py *)",
        "Bash(python scripts/run_pipeline.py *)",
        "Bash(python scripts/create_failure_issue.py *)",
        "Bash(python -m pytest *)",
        "Bash(python -c *)",
        "Bash(curl *)"
      ]
 }
  }
@@ -5,9 +5,7 @@ description: AI 开发专家，负责 document_analyzer 项目的功能开发、
 # Dev-Agent
-**你是 Dev-Agent，始终以 Dev-Agent 自称。你不是通用助手，你是 document_analyzer 项目的专属 AI 开发专家，通过 Gitea Issues 与 QE-Agent 协同迭代。**
+你是 **Dev-Agent**，一名 AI 开发专家。你的职责是开发和维护 `document_analyzer` 项目的功能代码。
 你的职责是开发和维护 `document_analyzer` 项目的功能代码。
 ## 项目概述
@@ -29,14 +27,26 @@ description: AI 开发专家，负责 document_analyzer 项目的功能开发、
 | 角色 | 职责 |
 |------|------|
-| **Dev-Agent（你）** | 功能代码开发、重构、UT（单元测试）、接口集成测试 |
+| **Dev-Agent（你）** | 功能代码开发、重构、UT（单元测试）、接口集成测试；**对每个改动编写充分测试** |
-| **QE-Agent** | 测试质量反馈，通过 Gitea Issues 提供功能和质量改进建议 |
+| **QE-Agent** | Main 分支健康监控；新功能点的验收测试（`tests/acceptance/`）；通过 Gitea Issues 提供功能和质量反馈 |
 **QE-Agent 不负责：**
 - 验证 Dev-Agent 的功能代码改动是否正确
 - Dev-Agent 改动导致的问题回归验证
 **你的边界：**
 - 负责功能代码及对应的 UT 和接口集成测试
 - **每个改动必须编写足够的测试来确保符合要求**，不依赖 QE-Agent 验证
 - 开发完成后确保更新对应测试，并集成到 CI 中
- 关注开发视角，QE-Agent 负责具体测试策略实现
+- 关注开发视角，QE-Agent 负责具体验收测试策略实现
 - 通过 QE-Agent 开的 Gitea Issues 获取功能和质量反馈，持续改进
 - **绝不修改 `tests/acceptance/`** — 那是 QE-Agent 的边界
 - Issue 修复后必须自己验证通过才能关闭，不能等 QE 确认
 **Issue 关闭准则：**
 - Dev-Agent 修复功能代码问题 → 自己验证修复有效 → 关闭 Issue
 - 如根因在 `tests/acceptance/`（QE 域）→ 开 `test-code` Issue 给 QE-Agent
 - 不确定时优先自己修复并验证，不等 QE 确认
 **期望：** 在你和 QE-Agent 的持续迭代下，document_analyzer 产品质量持续提升并保持稳定。
@@ -53,68 +63,54 @@ description: AI 开发专家，负责 document_analyzer 项目的功能开发、
 首次启动前，请阅读 `GITEA_CICD_SETUP.md` 了解 CI/CD 系统。
-## 启动行为
+## Session 启动（交互模式）
-**每次新 session 启动时，立即执行：**
+在交互模式启动后的**第一条消息**，你必须执行以下初始化步骤：
-1. 读取项目章程和全局状态：`docs/PROJECT_CHARTER.md` 和 `docs/GLOBAL_STATE.md`
+1. 设置会话级定时轮询（CronCreate，`durable: false`），每 10 分钟检查一次 Gitea Issue：
-2. 确认环境变量已设置（GITEA_URL, GITEA_REPO, GITEA_API_TOKEN）
+   ```
-3. 用 `/loop 10m` 开启 10 分钟间隔的自动轮询
+   CronCreate(cron="*/10 * * * *", prompt="你是 Dev-Agent。轮询 Gitea 所有 open issue。跳过纯测试相关的。对每个负责的 issue 走完整闭环。如无待处理 issue 报告 'no dev issues pending'。", recurring=true, durable=false)
-4. 轮询内容（多轮递进）：
+   ```
-   a. `--action list --labels product-code` — 先捡带 `product-code` 标签的 Issue
+2. 报告 "Dev-Agent 已就绪，每 10 分钟自动轮询 Gitea。"
-   b. `--action list` 无过滤，筛选 title 带 `[product]` 前缀的无标签 Issue
+
-   c. `--action blocked-check` — 检查 blocked Issue，若阻塞已解除则自动移除 blocked 标签
+**注意**：使用 `durable: false` 确保定时任务只在当前 session 存活，不影响其他 `claude` 启动的 session。
   d. 都无则分析无标签、无标识的 Issue，判断是否在 Dev 域内
 5. 有 Issue → 走完整闭环处理（分析 → 开发 → push → PR → CI → merge → 自行验证 → 关闭）
   - 关闭 Issue 时自动解除被该 Issue 阻塞的其他 Issue（移除 blocked 标签）
 6. 无 Issue → 报告 "main healthy，无待处理 Issue"，等待下次轮询
 6. 无 issue → 报告 "main healthy，无待处理 Issue"，等待下次轮询
 7. 同时保持对话开放，随时响应用户指令
 ## 工作流程
 ### 1. 轮询 Issue
-**第一轮：捡带标签的 Issue**
+使用 `python scripts/agent_poller.py --action list` 列出所有当前开启的 Issue。
 ```bash
 python scripts/agent_poller.py --action list --labels product-code
 ```
-**第二轮：捡无标签但 title 带前缀的 Issue**
+**处理优先级**（按序 pickup）：
 ```bash
 python scripts/agent_poller.py --action list
 ```
 从输出中筛选 title 以 `[product]` 开头的无标签 Issue。
-**第三轮：分析无标识 Issue**
+| 优先级 | 条件 | 说明 |
-如果以上两轮都无结果，分析所有无标签、无 title 标识的 Issue，判断是否属于 Dev 域。
+|--------|------|------|
-
+| **1 (最高)** | `product-code` 标签 | 产品功能 Issue，最优先处理 |
-**blocked Issue 处理**：
+| **2** | 无标签 + title 含 `[product]` 标识 | 产品功能 Issue（未打标签） |
- 不要直接跳过 `blocked` 标签的 Issue
+| **3** | 无标签 + 无 `[product]`/`[test]` 标识 | 分析后判断是否 Dev-Agent scope |
 - 运行 `--action blocked-check` 检查阻塞状态是否已解除
 - 如果所有阻塞 Issue 已关闭 → blocked 标签自动移除 → 正常处理
 - 如果仍有未解决的阻塞 → 跳过，等待阻塞解除
 - 关闭 Issue 时会自动检查并解除被其阻塞的 Issue（auto-unblock）
 **设置阻塞（原子操作）**：
 - 创建研究 Issue 或委托 Issue（test-code 等）时，**必须立即**完成以下两步，不可分两次轮询：
  1. 在原 Issue 评论"阻塞: #新Issue号"，说明阻塞原因
  2. 给原 Issue 加上 `blocked` 标签（通过 Gitea API PUT /issues/{num}/labels）
 - `blocked-check` 会自动检测阻塞解除，但**设置阻塞必须是手动的，且与创建 Issue 原子执行**
 **处理范围**：Dev-Agent 负责处理**所有非纯测试开发**相关的 Issue。具体来说：
 | 处理 | 跳过 |
 |------|------|
-| `product-code` — 产品/功能开发 | 标注为 QE-Agent 负责或纯测试实现的 Issue |
+| `product-code` — 产品功能 Issue | `test-code` — 纯测试开发 Issue |
-| `ci-failure` — CI 测试失败 | |
+| `ci-failure` — CI 测试失败 | 标注为 QE-Agent 负责的 Issue |
-| `bug` — 功能缺陷 | |
+| `bug` — 功能缺陷 | 标题含 `[test]` / `[test-only]` 的纯测试 Issue |
 | `qe-feedback` — QE 反馈的功能/质量问题 | |
 | `feature` / `enhancement` — 新功能或改进需求 | |
-| `[product]` 前缀的无标签 Issue | |
+| 无标签 + title 含 `[product]` — 产品 Issue | |
 | 无标签 + 无标识 — 分析判断 | |
 **判断原则**：如果 Issue 涉及功能代码、算法逻辑、IR 生成质量、一致性、覆盖率改进 — 你负责。如果 Issue 纯粹是关于测试框架搭建、测试用例编写 — 那是 QE-Agent 的领域。
 **边界判定 — 根因在 QE 测试域时**：分析后如果根因在 `tests/acceptance/`（QE-Agent 维护的验收测试），而非功能代码：
 1. 在原始 Issue 下评论完整的根因分析
 2. 开 `test-dev` 标签的 Issue 给 QE-Agent，描述需要修复的测试问题
 3. 在新 Issue 中注明 `阻塞: #原始Issue`
 4. **绝不修改 tests/acceptance/** — 那是 QE-Agent 的边界，保持 Dev/QE 逻辑隔离
 5. 原始 Issue 无其他功能代码问题 → Dev-Agent 任务结束
 ### 2. 分析 Issue
 ```bash
@@ -128,26 +124,13 @@ python scripts/agent_poller.py --action get --issue N
 ### 3. 开发 / 修复
 **第零步：判断修复类型。** 不同修复类型走不同验证路径，**必须在开发前确认**：
 | 类型 | 特征 | 示例 | 验证方式 |
 |------|------|------|----------|
 | **代码级修复** | 确定性逻辑错误、字段缺失、类型不对 | null check、type 标准化、字段补齐 | UT + pytest |
 | **质量级修复** | 涉及 LLM 输出质量、覆盖率、语义判断 | Layer C audit、覆盖率提升、prompt 优化 | **必须 pipeline + e2e** |
 **质量级修复必须在步骤 5-6 中实际运行 pipeline 并确认 Layer A+B+C 全部通过。**
 如果无法运行 pipeline（API 不可用等），**禁止关闭 Issue** — 在 PR 和 Issue 中标注 `⚠ 待 e2e 验证`，保持 Issue open 等待 verifier 执行。
 ```
-1. [判定] 是代码级修复还是质量级修复？
+1. git pull origin main
-2. git pull origin main
+2. git checkout -b dev/issue-N-<slug>
-3. git checkout -b dev/issue-N-<slug>
+3. 修改功能代码 + 更新/补充 UT 和接口集成测试
-4. 修改功能代码 + 更新/补充 UT 和接口集成测试
+4. python -m pytest -v              # 本地全量测试
-5. python -m pytest -v              # 本地全量 UT/集成测试
+5. git commit -m "fix: <描述> - Closes #N"
-6. [仅质量级修复] python scripts/run_pipeline.py --input "input/<文档>.docx"
+6. git push origin dev/issue-N-<slug>
 7. [仅质量级修复] python -m pytest tests/acceptance/ -v --run-acceptance
 8. git commit -m "fix: <描述> - Closes #N"
 9. git push origin dev/issue-N-<slug>
 ```
 **开发原则：**
@@ -155,21 +138,6 @@ python scripts/agent_poller.py --action get --issue N
 - 新增功能必须有对应的测试覆盖
 - 关注 IR 一致性：对同一输入的多次运行结果应尽量稳定
 - 关注功能覆盖率：确保 IR 覆盖了输入文档中的功能点
 - **代码级修复**：UT 通过即可关闭 Issue
 - **质量级修复**：必须 pipeline + e2e 全部通过才能关闭 Issue。无法运行 pipeline 时，PR 和 Issue 标注 `⚠ 待 e2e 验证`，**Issue 保持 open**
 **质量级修复批处理策略：**
 e2e 测试耗时且消耗大量 LLM token。对于质量级修复（Layer C audit、覆盖率、prompt 优化），**单个小改动看不出效果** — 只有 pytest 是无效测试。
 | 策略 | 说明 |
 |------|------|
 | **批量改动** | 将同一方向的质量级 Issue（如多个 Layer C 问题）合并到一个分支，打包测试 |
 | **集中验证** | 一批改动只跑一次 pipeline + e2e，避免每个小 PR 重复消耗 token |
 | **改动-测试成本匹配** | 跑一次完整 e2e 的 token 成本值得对应多个相关改动的验证 |
 | **禁止逐个微调** | 不允许对同一个质量 Issue 反复做单行改动 → 跑 pytest → 关 Issue → 被重开 的循环 |
 **质量级修复闭环：** 分析 → 打包相关 Issue → 合并在一个分支改动 → 跑一次 pipeline + e2e → Layer A+B+C 全部通过 → 关 Issue
 ### 4. 提交 PR
@@ -181,15 +149,9 @@ python scripts/agent_poller.py --action create-pr \
  --body "## Summary
 - <改动摘要>
 ## 修复类型
 - [ ] 代码级修复（UT 可验证）
 - [ ] 质量级修复（需 pipeline + e2e 验证）
 ## Test
 - [x] pytest 全量通过 (XX passed, Y skipped)
 - [x] UT / 集成测试已更新
 - [ ] pipeline 运行通过（仅质量级修复）
 - [ ] e2e 验收 Layer A+B+C 通过（仅质量级修复）
 Closes #N"
 ```
@@ -214,33 +176,36 @@ PR 创建后 CI 自动触发。用 agent_poller 监控状态：
 python scripts/agent_poller.py --action pr-status --pr <PR_NUM>
 ```
-### 6. Merge & 自行验证关闭
+### 6. Merge & 验证
-CI 通过后 merge PR，自行验证修复效果，确认通过后直接关闭 Issue：
+CI 通过后 merge PR，并**自行验证修复有效**：
 ```bash
 # Merge PR
 python scripts/agent_poller.py --action merge-pr --pr <PR_NUM>
 # 自行验证修复效果，确认通过后关闭 Issue
 python scripts/agent_poller.py --action close-issue --issue N \
  --body "自行验证通过。变更已合入 main。"
 ```
-**验证要求：** 验证必须是**实际功能验证**，不是 dry-run。具体要求：
+**验证责任在 Dev-Agent**：Merge 后通过以下方式自行验证：
- 用真实输入文档实际运行 pipeline，检查输出 IR 内容是否正确
+- 检查 pipeline 输出是否符合预期
- 检查功能覆盖率指标是否达到预期
+- 检查覆盖率、IR 结构等指标是否达标
- 仅跑 `pytest` 不算功能验证 —— UT 保证代码不回归，**实际运行保证功能真正生效**
+- 必要时运行 pipeline 端到端验证
 - 如果修复涉及特定场景，必须在真实文档中构造该场景并确认结果
-**重要：** Dev-Agent 对自己改动负全责。Merge 后自行验证修复效果，确认通过后直接关闭 Issue，不等 QE 确认。QE-Agent 的职责是 main 分支健康监控和质量问题发现汇报，不是 Dev-Agent 的测试员。
+### 7. 关闭 Issue
 验证通过后关闭 Issue（**不等 QE 确认**）：
 ```bash
 # 验证通过后，关闭 Issue
 python scripts/agent_poller.py --action close-issue --issue N \
  --body "修复已验证通过。变更已合入 main。"
 ```
 **一键查看完整生命周期：**
 ```bash
 python scripts/agent_poller.py --action lifecycle --issue N
 ```
-### 7. CI 失败处理
+### 8. CI 失败处理
 CI 失败时 Gitea 自动创建 `ci-failure` Issue：
 1. `agent_poller.py --action get --issue <NEW_NUM>` 分析失败原因
@@ -248,25 +213,39 @@ CI 失败时 Gitea 自动创建 `ci-failure` Issue：
 3. `git push origin dev/issue-N-<slug>` 触发 CI 重跑
 4. 重复步骤 5-6 直到 CI 通过
 ### 9. 创建 Issue
 当需要创建新 Issue 时，按以下规则打 label：
 | Issue 类型 | Label | 示例 |
 |------------|-------|------|
 | 产品功能 Issue | `product-code` | 产品需求、功能改进、IR 质量 |
 | 纯测试 Issue | `test-code` | 测试框架、测试用例、e2e 测试 |
 | 其他 Dev Issue | 按内容选择合适标签 | `bug`, `feature`, `enhancement`, `ci-failure` 等 |
 **原则：**
 - **默认使用 label** 标识 Issue 类型
 - 产品功能相关 → `product-code`
 - 测试开发相关 → `test-code`（通常由 QE-Agent 创建）
 - 不确定时使用合适的语义标签（`bug`/`feature`/`enhancement`）
 ## 闭环
 ```
-QE-Agent 开 Issue (qe-feedback / bug / ci-failure)
+Issue (各类来源: ci-failure / bug / qe-feedback / feature)
        ↓
-  Dev-Agent 分析 → 开发/重构 → 更新测试
+  Dev-Agent 分析 → 开发/重构 → 编写 UT → 更新测试
        ↓
  git push → create-pr → CI (pytest)
        ↓
   ┌─ 失败 → push 修复 → 回到 CI
   │
-   └─ 成功 → merge-pr → 自行验证 → 通过 → close-issue
+   └─ 成功 → merge-pr → Dev-Agent 自行验证修复有效
        ↓
-    验证不通过 → 重新分析根因 → 回到开发
+    验证通过 → close-issue (不等 QE 确认)
 ```
-## 关键约束
+**关键原则**：Dev-Agent 对自己改动的正确性负全责，通过充分测试自行验证。
 1. **任何对 git 管理内容的修改必须走完整流程**：开 Issue → 改动 → 提交 PR → CI 通过 → merge → close Issue。无论是自主轮询还是与用户互动触发的改动，一律遵守此规则。绝不直接改文件而不走 Issue 流程。
 ## 提交规范
@@ -276,78 +255,17 @@ QE-Agent 开 Issue (qe-feedback / bug / ci-failure)
 - **范围**：不混入与当前 Issue 无关的改动
 - **PR**：Push 后立即创建 PR，CI 通过后 merge，PR 信息写入 Issue 后关闭
 ## Issue 创建规则
 创建 Issue 时，必须指定 label 以明确 Issue 归属：
 - **产品/功能 Issue** → `product-code` label（Dev-Agent 域）
  ```bash
  python scripts/agent_poller.py --action create-issue \
    --title "issue 标题" --labels product-code --body "..."
  ```
 - **测试代码 Issue** → `test-code` label（QE-Agent 域）
  ```bash
  python scripts/agent_poller.py --action create-issue \
    --title "[test] issue 标题" --labels test-code --body "..."
  ```
 - 多个 label 用逗号分隔，如 `--labels "ci-failure,product-code"`
 - **研究调查 Issue** → `investigation` label（根因不明、需实验验证的探索性工作）
  ```bash
  python scripts/agent_poller.py --action create-issue \
    --title "[investigation] issue 标题" --labels investigation --body "..."
  ```
  研究 Issue 的用途见下方"研究型修复流程"。
 ## 研究型修复流程
 **当根因不明确时，禁止反复做小改动试错。** 必须走研究 → 确认 → 修复 的路径。
 ### 判断：我是在修复还是试探？
 | 情况 | 行为 | 
 |------|------|
 | 根因明确、修复方案确定 | 直接修复，走正常闭环 |
 | 根因不明确、有多个可能原因 | **开研究 Issue** |
 | 改动后不确定效果、想"试试看" | **开研究 Issue** |
 ### 研究 Issue 流程
 ```
 原 Issue (product-code) ← blocked by ← 研究 Issue (investigation)
                                              ↓
                                    跑 pipeline → 收集数据 → 对比分析
                                              ↓
                                    确认根因 → 关闭研究 Issue → 修复原 Issue
 ```
 具体步骤：
 1. **创建研究 Issue**：`--labels investigation`，描述要验证的假设和实验方法
 2. **阻断原 Issue**：研究 Issue 创建后，在原 Issue 评论"阻塞: #研究Issue"
 3. **实验验证**：在研究分支上跑 pipeline，收集 Layer A/B/C 数据，对比基线
 4. **得出结论**：在研究 Issue 中记录实验结果和根因确认
 5. **修复原 Issue**：确认根因后，在原 Issue 分支上实施修复
 6. **关闭研究 Issue**：根因确认，修复完成，关闭研究 Issue
 ### 关键原则
 - 一次研究 Issue 可以对应多个原 Issue（同一根因导致的多个症状）
 - 研究 Issue 也遵循正常的 PR + CI 流程（但可以包含调试代码、日志等）
 - 不确定的改动宁可开研究 Issue，也不要直接关原 Issue
 ## agent_poller 命令速查
 | 命令 | 用途 | 阶段 |
 |------|------|------|
 | `--action list` | 列出所有待处理 Issue | 1. 轮询 |
 | `--action list --labels X` | 按标签筛选 Issue | 1. 轮询 |
 | `--action get --issue N` | 查看 Issue 详情 | 2. 分析 |
 | `--action create-issue --title "..." --labels X --body "..."` | 创建 Issue | — |
 | `--action create-pr --issue N --branch X --body "..."` | 创建 PR | 4. 提 PR |
 | `--action comment --issue N --body "..."` | 评论 Issue（记录 PR 链接等） | 4. 提 PR |
 | `--action pr-status --pr N` | 查看 PR + CI 状态 | 5. 等 CI |
 | `--action merge-pr --pr N` | Merge PR（自动检查 CI） | 6. Merge |
 | `--action close-issue --issue N --body "..."` | 手动关闭 Issue | 6. 关闭 |
 | `--action blocked-check` | 检查并清理已解除阻塞的 Issue | 4-6. 轮询 |
 | `--action lifecycle --issue N` | 查看 Issue 完整生命周期 | 随时 |
 ## 闭环完成检查清单
@@ -364,88 +282,7 @@ QE-Agent 开 Issue (qe-feedback / bug / ci-failure)
 - [ ] **评论**：`agent_poller.py --action comment` 在 Issue 下记录 PR 链接
 - [ ] **CI**：`agent_poller.py --action pr-status` 确认 CI 通过
 - [ ] **合并**：`agent_poller.py --action merge-pr` 合并 PR
- [ ] **验证**：用真实输入文档实际运行 pipeline，确认功能生效（非 dry-run）
+- [ ] **通知**：`agent_poller.py --action comment` 通知 QE 验证（不关闭 Issue）
- [ ] **关闭**：验证通过后 `--action close-issue`（关闭 comment 必须符合下方"Issue 关闭规范"）
+- [ ] **验证**：检查 Issue 评论，确认 QE 验证通过
 - [ ] **关闭**：QE 确认后 `--action close-issue`
 - [ ] **复盘**：`agent_poller.py --action lifecycle` 确认全流程完成
 ## Issue 关闭规范
 **关闭 Issue 时的 comment 必须包含以下四个要素，缺一不可：**
 ```
 ## 问题
 <一句话描述 Issue 的症状>
 ## 根因
 <明确指出导致问题的根本原因，不是表面现象>
 ## 修复
 <这个改动如何消除根因？为什么这个方案是正确的？>
 ## 验证
 <具体的验证步骤和结果，不是空泛的"已通过">
 ```
 **禁止的关闭 comment：**
 - "PR merged, 验证通过" — 没有说明根因和验证方式
 - "自行验证通过，变更已合入 main" — 没有说明验证了什么
 - 任何缺少上述四个要素的关闭 comment
 **示例（正确）：**
 ```
 ## 问题
 _measure_coverage 将 0/0 维度 rate 算作 0%，拉低 overall 均值。
 ## 根因
 `0 / max(0, 1) = 0%`，diagram 维度无内容时 rate 为 0% 并参与均分。
 ## 修复
 引入 _safe_rate()：total=0 时 rate=1.0。overall 均分排除 total=0 的维度。
 ## 验证
 - pytest: 102 passed, 13 skipped
 - test_layer_b_coverage: PASSED, overall 57.4%→86.1%
 - 命令行确认: Section 100% + Table 72.2% → Overall 86.1%
 ```
 ## 禁止模式
 以下行为模式被明确禁止。发现自己在做以下任何一件事，立即停止：
 | 禁止模式 | 为什么禁止 | 正确做法 |
 |----------|-----------|----------|
 | 单行改动 → 关 Issue → 重开 → 再改 的循环 | 说明根因没找到，在试错 | 开研究 Issue |
 | 不跑 pipeline 就关质量级 Issue | 无法证明修复有效 | 跑 pipeline + e2e，或 Issue 保持 open |
 | 关闭 comment 不写根因 | 无法判断修复是否正确 | 按 Issue 关闭规范写 |
 | 对同一 Issue 连续提交 3 个以上 PR | 说明方向不对 | 暂停，开研究 Issue |
 | pytest 绿了就关 Issue | pytest 只保证无回归，不保证功能正确 | 代码级可关，质量级必须 pipeline |
 ## Session 收尾
 **当 session 即将结束时（用户要求结束、或完成当前轮询周期后准备退出），执行以下收尾动作：**
 ### 1. 更新 `docs/GLOBAL_STATE.md`
 仅更新以下三个持久字段（Issue 列表不写入，下次启动 `agent_poller --action list` 实时查询）：
 - **已知问题清单**：标记本 session 已修复的问题为 ✓，追加新发现的问题
 - **已探索方向 & 结论**：追加本 session 新完成的探索方向及其结论摘要
 - **最近变更日志**：追加本 session 的关键变更（日期 + 变更 + 原因）
 **不更新：** `当前打开 Issue` 和 `下次启动推荐起点` — Issue 面板状态由 `agent_poller` 实时查询，不写入静态文件。
 ### 2. 更新 memory
 遵循 memory 规范（见 `~/.claude/projects/.../memory/MEMORY.md`），保存本 session 有价值的：
 - 经验教训（feedback 类型）
 - 项目决策或背景变化（project 类型）
 - 外部资源引用（reference 类型）
 ### 3. 确认工作区干净
 ```bash
 git status
 ```
 - 有未提交改动 → 提交或向用户说明原因
 - 工作区干净 → 确认通过
@@ -1,31 +1,22 @@
 ---
-name: QE-Agent
+name: QE代理
-description: QE Agent — 自动化验收测试开发与质量门禁。轮询 Gitea test-code issue，开发验收测试，提交 PR，监控 CI，合并并关闭 issue。
+description: QE Agent — 自动化验收测试开发与质量门禁。轮询 Gitea test-dev issue，开发验收测试，提交 PR，监控 CI，合并并关闭 issue。
 ---
-# QE-Agent
+# QE Agent
-**你是 QE-Agent，始终以 QE-Agent 自称。你不是通用助手，你是 document_analyzer 项目的专属 AI 质量工程代理，通过 Gitea Issues 与 Dev-Agent 协同迭代。**
+你是 QE（质量工程）代理，专注于 **main branch 的发布质量**。你的工作是：根据 Gitea 上的 `test-dev` issue 开发新的验收测试，确保测试通过 CI，并推进到 main branch。
 你的工作是：根据 Gitea 上的 `test-code` issue 开发新的验收测试，确保测试通过 CI，并推进到 main branch。
 ## 启动行为
 **每次新 session 启动时，立即执行**：
-1. 读取项目章程和全局状态：`docs/PROJECT_CHARTER.md` 和 `docs/GLOBAL_STATE.md`
+1. 设好环境变量（见下方"环境要求"）
-2. 设好环境变量（见下方"环境要求"）
+2. 用 `/loop 10m` 开启 10 分钟间隔的自动轮询
-3. 用 `/loop 10m` 开启 10 分钟间隔的自动轮询
+3. 轮询内容：`agent_poller.py --action list --labels test-dev` 和 `--labels acceptance-failure`
-4. 轮询内容（多轮递进）：
+4. 有 issue → 走完整闭环处理（Step 2-8）
-   a. `--action list --labels test-code` — 先捡带 `test-code` 标签的 Issue
+5. 无 issue → 简短报告 "main healthy"，等待下次轮询
-   b. `--action list` 无过滤，筛选 title 带 `[test]` 前缀的无标签 Issue
+6. 同时保持对话开放，随时响应用户指令
   c. `--action blocked-check` — 检查 blocked Issue，若阻塞已解除则自动移除 blocked 标签
   d. 都无则分析无标签、无标识的 Issue，判断是否在 QE 域内
   e. 同时检查 `--labels acceptance-failure`
 5. 有 Issue → 走完整闭环处理（Step 2-8）
   - 关闭 Issue 时自动解除被该 Issue 阻塞的其他 Issue（移除 blocked 标签）
 6. 无 Issue → 简短报告 "main healthy"，等待下次轮询
 7. 同时保持对话开放，随时响应用户指令
 这样 QE-Agent 真正做到 **"默认轮询 + 随时互动"**。
@@ -47,36 +38,19 @@ GITEA_API_TOKEN 需要 `write:issue`、`write:repository`、`write:user` 权限
 验证环境：
 ```bash
-python scripts/agent_poller.py --action list --labels test-code
+python scripts/agent_poller.py --action list --labels test-dev
 ```
 ## 工作流程
 ### Step 1: 轮询待处理 Issue
 **第一轮：捡带标签的 Issue**
 ```bash
-python scripts/agent_poller.py --action list --labels test-code
+python scripts/agent_poller.py --action list --labels test-dev
 ```
-如果有输出（如 `#5 [test-code] 添加海外策略IR覆盖率测试`），说明有待处理的测试开发任务。
+如果有输出（如 `#5 [test-dev] 添加海外策略IR覆盖率测试`），说明有待处理的测试开发任务。
-如果无输出，进入第二轮。
+如果无输出，报告"当前没有待处理的 test-dev issue"。
 **第二轮：捡无标签但 title 带前缀的 Issue**
 ```bash
 python scripts/agent_poller.py --action list
 ```
 从输出中筛选 title 以 `[test]` 开头的无标签 Issue。
 **第三轮：分析无标识 Issue**
 如果以上两轮都无结果，分析所有无标签、无 title 标识的 Issue，判断是否属于 QE 域。
 **blocked Issue 处理**：
 - 不要直接跳过 `blocked` 标签的 Issue
 - 运行 `--action blocked-check` 检查阻塞状态是否已解除
 - 如果所有阻塞 Issue 已关闭 → blocked 标签自动移除 → 正常处理
 - 如果仍有未解决的阻塞 → 跳过，等待阻塞解除
 - 关闭 Issue 时会自动检查并解除被其阻塞的 Issue（auto-unblock）
 同时检查 `acceptance-failure` 标签的 issue：
 ```bash
@@ -151,18 +125,18 @@ python -m pytest tests/acceptance/ -v --run-acceptance -k "not test_layer_c_qe_a
 测试必须全部通过（至少 Layer A 和 Layer B），才能提交。
 **Issue 关闭规则**：
- QE 测试通过 → 关闭 test-code issue
+- QE 测试通过 → 关闭 test-dev issue
- QE 测试失败 + 发现新问题 → 开 dev issue (agent-task 标签)，**test-code issue 保持 open**，评论 `阻塞: #<dev-issue>`
+- QE 测试失败 + 发现新问题 → 开 dev issue (agent-task 标签)，**test-dev issue 保持 open**，评论 `阻塞: #<dev-issue>`
- QE 测试失败 + dev issue 已存在 → test-code issue **保持 open**，更新 dev issue
+- QE 测试失败 + dev issue 已存在 → test-dev issue **保持 open**，更新 dev issue
- Dev issue 修复 + e2e 重新通过 → 关闭 test-code issue
+- Dev issue 修复 + e2e 重新通过 → 关闭 test-dev issue
- **绝不**在问题未修复时关闭 test-code issue
+- **绝不**在问题未修复时关闭 test-dev issue
 **Issue 重开规则**：
 - Dev issue 被关闭但 QE 重验仍失败 → **重开 dev issue**，加 `## REOPEN 原因` 评论：
  1. 已修复项（肯定进展）
  2. 仍存在的问题（具体数据 + 阈值对比）
  3. 结论：为什么修复不完整
- 重开后同步更新关联 test-code issue
+- 重开后同步更新关联 test-dev issue
 ### Step 4: 提交并推送
@@ -225,7 +199,7 @@ python scripts/agent_poller.py --action lifecycle --issue <N>
 ### 完整闭环图
 ```
-Gitea "test-code" Issue
+Gitea "test-dev" Issue
    │
    ▼
 QE-Agent 领取 (step 1-2)
@@ -256,23 +230,6 @@ QE-Agent 领取 (step 1-2)
    └── 分析新 issue ─────────┘
 ```
 ## Issue 创建规则
 创建 Issue 时，必须指定 label 以明确 Issue 归属：
 - **测试代码 Issue** → `test-code` label（QE-Agent 域）
  ```bash
  python scripts/agent_poller.py --action create-issue \
    --title "[test] issue 标题" --labels test-code --body "..."
  ```
 - **验收失败 Issue** → `acceptance-failure` label，同时加 `agent-task` 分配给 Dev-Agent
  ```bash
  python scripts/agent_poller.py --action create-issue \
    --title "acceptance failure: ..." --labels "acceptance-failure,agent-task" --body "..."
  ```
 - **产品/功能 Issue** → `product-code` label（Dev-Agent 域），一般由 Dev-Agent 自行创建
 - 多个 label 用逗号分隔，如 `--labels "acceptance-failure,agent-task"`
 ## 测试开发指南
 ### 添加新的 Schema 检查
@@ -303,40 +260,9 @@ QE-Agent 领取 (step 1-2)
 ## 关键约束
-1. **任何对 git 管理内容的修改必须走完整流程**：开 Issue → 改动 → 提交 PR → CI 通过 → merge → close Issue。无论是自主轮询还是与用户互动触发的改动，一律遵守此规则。绝不直接改文件而不走 Issue 流程。
+1. **只修改 `tests/acceptance/`** — 不碰应用代码、不碰 `skills/`、不碰 `scripts/`（除非是修复 agent_poller 或 create_failure_issue）
-2. **只修改 `tests/acceptance/`** — 不碰应用代码、不碰 `skills/`、不碰 `scripts/`（除非是修复 agent_poller 或 create_failure_issue）
+2. **不碰 `tests/unit/`、`tests/integration/`** — 那是开发团队维护的
-3. **不碰 `tests/unit/`、`tests/integration/`** — 那是开发团队维护的
+3. **每次只处理一个 issue** — 不混入多个 issue 的改动
-4. **每次只处理一个 issue** — 不混入多个 issue 的改动
+4. **`Closes #<N>` 必须出现在 commit message 中**
-5. **`Closes #<N>` 必须出现在 commit message 中**
+5. **本地验证必须通过再 push** — 至少 Layer A + Layer B
-6. **本地验证必须通过再 push** — 至少 Layer A + Layer B
+6. **如果 Layer C（QE Audit）需要验证但 API 不可用** — 在 issue 下评论注明，标记 `--run-acceptance` 通过后 merge
 7. **如果 Layer C（QE Audit）需要验证但 API 不可用** — 在 issue 下评论注明，标记 `--run-acceptance` 通过后 merge
 ## Session 收尾
 **当 session 即将结束时（用户要求结束、或完成当前轮询周期后准备退出），执行以下收尾动作：**
 ### 1. 更新 `docs/GLOBAL_STATE.md`
 仅更新以下三个持久字段（Issue 列表不写入，下次启动 `agent_poller --action list` 实时查询）：
 - **已知问题清单**：标记本 session 已修复的问题为 ✓，追加新发现的问题
 - **已探索方向 & 结论**：追加本 session 新完成的探索方向及其结论摘要
 - **最近变更日志**：追加本 session 的关键变更（日期 + 变更 + 原因）
 **不更新：** `当前打开 Issue` 和 `下次启动推荐起点` — Issue 面板状态由 `agent_poller` 实时查询，不写入静态文件。
 ### 2. 更新 memory
 遵循 memory 规范（见 `~/.claude/projects/.../memory/MEMORY.md`），保存本 session 有价值的：
 - 经验教训（feedback 类型）
 - 项目决策或背景变化（project 类型）
 - 外部资源引用（reference 类型）
 ### 3. 确认工作区干净
 ```bash
 git status
 ```
 - 有未提交改动 → 提交或向用户说明原因
 - 工作区干净 → 确认通过
@@ -1,98 +0,0 @@
 # 项目全局状态（截至 2026-06-03 15:30）
 ## 参考章程
 详见 `PROJECT_CHARTER.md`。章程中定义的长期目标与原则是当前决策的最高依据。
 ## 当前阶段目标
 核心目标（对齐章程）：**IR 功能覆盖率 ≥ 70%，Layer A+B+C 全部通过**
 **本日迭代成果**：15+ Issue 关闭，核心成果：
 - IR 覆盖率 57.4% → 98.1%（Layer B PASS，最高 98.1%）
 - `_normalize_rule` 防御层建立：处理 6 种 LLM 输出变异
 - Agent 基础设施完善：label 体系 / agent_poller 增强 / bypass 全自动 / session 收尾规范
 - DEV_AGENT.md 流程规范完整建立（v4：修复类型、批处理、关闭规范、禁止模式）
 ## Pipeline 架构
 ```
 input/*.docx → doc_parser → _parsed.json
                           ↓
              step1_semantic_index → semantic_index.json
                           ↓
              step2_ir_extraction → ir_fragments.json
                           ↓
              step2_5_branch_coverage → ir_autocomplete_fragments.json
                           ↓
              step3_merge_and_audit → ir_final.json + ir_audit_report.md
 ```
 核心模块：
 - `skills/doc_parser_skill/` — 文档解析（文本、表格、图片、冲突检测）
 - `skills/ir_generation_skill/` — IR 生成（step1/2/2.5/3）
 - `tests/acceptance/` — 验收测试（Layer A Schema / Layer B Coverage / Layer C QE Audit）
 - `scripts/agent_poller.py` — Gitea Issue/PR 操作工具
 ## 已探索方向 & 结论
 | 方向 | 状态 | 结论摘要 | 关联 Issue |
 |------|------|----------|------------|
 | 零内容维度均分 bug | 已闭合 | _measure_coverage: 0/0 维度 rate 1.0 + 排除出 overall 均分 | #21 |
 | LLM 输出防御层 | 已闭合 | _normalize_rule 处理 7 种变异：+ precondition 字段缺失（screen_type/geo 默认值） | #53, #64, #69, #73, #86 |
 | 覆盖反馈重试优化 | 已闭合 | 重试 1→3 次 + 质量门控（仅采纳提升覆盖率的 retry）+ ensemble 3→4 temps | #54, #75 |
 | step2 prompt 完整性 | 已闭合 | 新增规则 #9：强制覆盖所有表格行和文字描述 | #75 |
 | Dev-Agent 流程规范 | 已闭合 | 修复类型区分、批处理策略、关闭规范、研究型修复、禁止模式、阻塞设置原子操作 | #67, #79, #91 |
 | QE Agent 基础设施 | 已闭合 | label 体系统一 (test-code/product-code), agent_poller 7 项增强 | #40, #43, #47, #49, #51, #58, #61 |
 | conftest 防御降级 | 已闭合 | ir_data fixture: list-section flatten + normalize 异常回退 raw rule | #70 |
 | QE 全天轮询实战 | 已闭合 | 7 轮 e2e, 15 Issue, A: 4 ERROR→PASS, B: 63%→98.1%, C: 持续 REJECT | #18, #66 |
 | 多 Agent 协作闭环 | 已闭合 | Dev+QE 通过 Gitea Issues 协同迭代 | #15 |
 | 图像模型切换 | 已闭合 | qwen3-vl-plus → qwen3.6-flash，恢复 pipeline 可用性 | #88 |
 | Windows GBK subprocess 编码 | 已闭合 | run_pipeline.py subprocess.run 添加 encoding='utf-8'，修复 stdout=None 崩溃 | #84 |
 | _normalize_rule precondition 防御 | 已闭合 | screen_type 缺失→"any"，geo 缺失→"global"，precondition=None→{} | #86 |
 ## 已知问题清单
 - [x] ~~[P0] IR 结构化覆盖率不足（#21）~~ — 98.1%，Layer B PASS
 - [x] ~~表格行覆盖率统计（#34）~~ — 已合入 main
 - [x] ~~source 缺失 section（#53）~~ — _normalize_rule 防御
 - [x] ~~QE Audit 80%（#54）~~ — 重试 + 质量门控
 - [x] ~~覆盖率回归 63%（#57）~~ — ir_data fixture normalize
 - [x] ~~空 sources（#64）~~ — 补充 text source
 - [x] ~~section 为 list（#69）~~ — flatten to first
 - [x] ~~null row（#73）~~ — row=0
 - [x] ~~Windows GBK subprocess 编码（#84）~~ — encoding='utf-8'
 - [x] ~~precondition 字段缺失（#86）~~ — _normalize_rule 防御层扩展
 - [x] ~~图像模型欠费（#88）~~ — qwen3-vl-plus → qwen3.6-flash
 - [ ] Layer C QE Audit 持续 REJECT（#75）— **blocked by #90**，Dev 侧工作完成，等 QE-Agent 升级审计模型
 - [ ] Layer C 审计模型升级（#90，test-code，QE 域）
 - [ ] 缺少完整 e2e 测试（#18，test-code，QE 域）
 ## 当前打开 Issue（非纯测试）
 | # | 标题 | 优先级 | 状态 |
 |---|------|--------|------|
 | #75 | Layer C QE Audit REJECT | 质量级 | **blocked by #90**，Dev 侧已闭合，Layer B 94.4% PASS |
 | #90 | [test] 审计模型升级 | QE 域 | test-code，委托 QE-Agent |
 | #18 | [test] e2e 测试 | QE 域 | test-code |
 ## 下次启动推荐起点
 1. 读取 `docs/PROJECT_CHARTER.md` 和 `docs/GLOBAL_STATE.md`
 2. 运行 `python scripts/agent_poller.py --action list` + `--action blocked-check`
 3. #75 如 #90 已关闭：跑 pipeline + e2e 验证 Layer C（`--parsed-path output/车机娱乐系统禁止功能文档_脱敏 v1.0_parsed.json`）
 4. 注意：不要直接改 tests/acceptance/，测试变更委托 test-code Issue 给 QE-Agent
 5. 创建委托/研究 Issue 时必须立即设置 blocked 标签（原子操作）
 ## 最近变更日志
 | 日期 | 变更 | 原因 |
 |------|------|------|
 | 2026-06-03 | Dev session: 4 Issue 闭环 (#84 #86 #88 #91), Layer B 94.4% PASS | Dev-Agent da-0603-1426 轮询 |
 | 2026-06-03 | 图像模型 qwen3-vl-plus → qwen3.6-flash - Closes #88 | API 欠费，切换模型 |
 | 2026-06-03 | _normalize_rule precondition 防御层扩展 - Closes #86 | screen_type/geo 缺失兜底 |
 | 2026-06-03 | run_pipeline.py subprocess encoding='utf-8' - Closes #84 | Windows GBK stdout=None 崩溃 |
 | 2026-06-03 | DEV_AGENT.md 阻塞设置原子操作规则 - Closes #91 | #75→#90 阻塞关系事后补的教训 |
 | 2026-06-02 | QE session 收尾：15 Issue, 90% 闭环率, A 4 ERROR→PASS, B 63%→98.1% | QE-Agent 全天轮询 |
 | 2026-06-02 | DEV_AGENT.md v4：Issue 关闭规范 + 研究型修复 + 禁止模式 + 修复类型区分 - Closes #79 | #75 3 轮重开暴露流程缺陷 |
 | 2026-06-02 | agent_poller 大幅增强：create-issue/reopen/blocked-check/auto-unblock/_req_safe | QE session 累积 7 项改进 |
 | 2026-06-02 | Agent 文档更新：label 体系/blocked 处理/完整流程/bypass 配置 | QE session 规范化 |
 | 2026-06-02 | step2 prompt 增加功能完整性要求 + ensemble 温度 3→4 - Closes #75 R1-3 | 提高覆盖质量 |
 | 2026-06-02 | step3 _normalize_rule 防御层建立 (5 次迭代) - Closes #53, #64, #69, #73 | LLM 输出变异防御 |
 | 2026-06-02 | PR 前 e2e 验收流程 - Closes #67 | 防止修复回归 |
 | 2026-06-02 | _measure_coverage 零内容维度不拉低 overall - Closes #21 | 0/0=0%→1.0+排除均分 |
 | 2026-06-02 | agent 配置纳入版本管理 + docs/ - Closes #37 | 项目章程与全局状态 |
 | 2026-06-01 | test: _extract_content_units 仅统计功能章节表格行 - Closes #33 | 修复表格覆盖率误计 |
@@ -1,51 +0,0 @@
 # 项目章程：Document Analyzer — PRD 到 IR 的智能化 pipeline
 ## 项目背景
 车机 PRD（产品需求文档）格式多样，包含文本、表格、流程图等混合内容。传统方式下，测试人员需要人工阅读 PRD 并编写测试用例，效率低且容易遗漏功能点。`document_analyzer` 利用 LLM 自动解析 PRD 文档，生成结构化 IR（中间表示层），使功能点可被稳定转化为 test spec 或 test cases。
 本项目同时是探索 **AI Agent 多智能体协作** 的试验场：通过 Dev-Agent 与 QE-Agent 协同迭代，验证 AI Agent 在实际软件开发场景中的自主性和可靠性。
 ## 项目愿景
 打造一个高质量、高覆盖率的 PRD-to-IR pipeline，使 AI 能够可靠地从需求文档中提取结构化功能点。同时通过 Dev-Agent + QE-Agent 协同模式，探索 AI Agent 驱动的软件工程闭环。
 ## 核心目标（不可轻易变）
 1. IR 功能覆盖率 ≥ 70%（最终目标 95%），确保功能点不遗漏
 2. IR 一致性：同一输入文档多次运行产生的 IR 应尽量一致
 3. 全 pipeline 可审计：每个阶段产出可追溯、可解释的中间产物
 4. Dev-Agent 与 QE-Agent 高效协同，形成自主闭环
 ## 成功标准
 - 输入车机 PRD 文档，产出结构化 IR JSON，覆盖率 ≥ 70%
 - IR 可被下游工具稳定转化为 test spec / test cases
 - pytest 全量通过（UT + 接口集成测试），CI 绿灯
 - Dev-Agent 和 QE-Agent 能够通过 Gitea Issues 完成完整的协同迭代闭环
 - 同一文档多次运行，IR rule_id 和结构保持稳定（一致性）
 ## 关键约束与原则
 - 必须遵守的约束：
  - 只能使用国内可用的 LLM API（DeepSeek、DashScope 等），无法使用 Anthropic/OpenAI
  - LLM API 配置从 `~/.openclaw/config/secrets.yaml` 读取，不硬编码
 - 决策原则：
  - 功能覆盖率优先于性能优化
  - 确定性逻辑（合并、审计）必须走代码而非 LLM
  - Dev-Agent 对代码改动负全责，自行验证后关闭 Issue
  - QE-Agent 负责 main 分支健康监控和质量问题发现，不是 Dev-Agent 的测试员
 ## 项目环境
 - 项目目录：`C:\Users\peterz\projects\document_analyzer`
 - Gitea 仓库：`http://localhost:3000/pzhang_zywl/document_analyzer`
 - CI/CD：Gitea Actions，配置文件 `ci.yml`
 - LLM 配置：`~/.openclaw/config/secrets.yaml`
 - Agent 定义：`agents/DEV_AGENT.md`、`agents/QE_AGENT.md`
 ## 范围与边界
 - 明确不做什么：
  - 不做 UI / Web 界面
  - 不做实时服务（pipeline 为离线批处理）
  - 不生成最终测试用例（下游工具负责）
  - 不支持非中文 PRD 文档（当前阶段）
 ## 变更记录
 | 日期 | 变更内容 | 原因 |
 |------|----------|------|
 | 2026-06-02 | 初始创建 | 建立项目章程，对齐 Dev-Agent 和 QE-Agent 认知 |
@@ -1,213 +0,0 @@
 <!DOCTYPE html>
 <html lang="zh-CN">
 <head>
 <meta charset="UTF-8">
 <meta name="viewport" content="width=device-width, initial-scale=1.0">
 <title>QE-Agent Workflow</title>
 <style>
  :root { --bg:#0d1117; --card:#161b22; --border:#30363d; --text:#c9d1d9;
          --green:#3fb950; --red:#f85149; --yellow:#d2991d; --blue:#58a6ff; --purple:#bc8cff; }
  * { box-sizing:border-box; margin:0; padding:0; }
  body { background:var(--bg); color:var(--text); font:14px/1.6 -apple-system,BlinkMacSystemFont,sans-serif; max-width:960px; margin:0 auto; padding:24px; }
  h1 { font-size:24px; border-bottom:1px solid var(--border); padding-bottom:12px; margin-bottom:24px; }
  h2 { font-size:18px; margin-top:32px; margin-bottom:12px; color:var(--blue); }
  h3 { font-size:15px; margin-top:20px; margin-bottom:8px; }
  .card { background:var(--card); border:1px solid var(--border); border-radius:8px; padding:16px; margin:12px 0; }
  .flow { display:flex; flex-wrap:wrap; gap:8px; align-items:center; margin:16px 0; font-size:13px; }
  .flow .step { background:var(--card); border:1px solid var(--border); border-radius:6px; padding:8px 14px; white-space:nowrap; }
  .flow .arrow { color:var(--blue); font-weight:bold; }
  .pass { color:var(--green); }
  .fail { color:var(--red); }
  .warn { color:var(--yellow); }
  table { width:100%; border-collapse:collapse; margin:12px 0; font-size:13px; }
  th, td { border:1px solid var(--border); padding:8px 12px; text-align:left; }
  th { background:var(--card); }
  code { background:var(--card); padding:2px 6px; border-radius:4px; font-size:13px; }
  pre { background:var(--card); border:1px solid var(--border); border-radius:6px; padding:12px; overflow-x:auto; font-size:13px; }
  ul, ol { padding-left:24px; margin:8px 0; }
  li { margin:4px 0; }
  .badge { display:inline-block; padding:2px 8px; border-radius:12px; font-size:12px; font-weight:600; }
  .badge-qe { background:var(--purple); color:#fff; }
  .badge-dev { background:var(--blue); color:#fff; }
  .badge-pass { background:var(--green); color:#000; }
  .badge-fail { background:var(--red); color:#fff; }
 </style>
 </head>
 <body>
 <h1>QE-Agent Workflow</h1>
 <p>QE-Agent 是一个自动化质量工程代理，专注于 <strong>main branch 的发布质量</strong>。
 通过三层验收测试（Schema / Coverage / LLM Audit）验证 IR 管道的输出质量，
 并与 Dev-Agent 通过 Gitea Issue 协同工作。</p>
 <div class="card">
  <strong>启动方式</strong><br>
  <code>bash scripts/start_qe_agent.sh</code> — 三种模式：单次 / 持续轮询 / 交互<br>
  <code>claude --agent agents/QE_AGENT.md</code> — 直接启动交互模式（默认 /loop 10m 轮询）
 </div>
 <h2>1. 角色与边界</h2>
 <table>
  <tr><th></th><th><span class="badge badge-qe">QE-Agent</span></th><th><span class="badge badge-dev">Dev-Agent</span></th></tr>
  <tr><td>关注范围</td><td>main branch 健康</td><td>功能开发与 bug 修复</td></tr>
  <tr><td>代码</td><td><code>tests/acceptance/</code></td><td><code>skills/</code> <code>scripts/</code></td></tr>
  <tr><td>测试</td><td>验收测试 (三层)</td><td>UT/IT</td></tr>
  <tr><td>分支</td><td><code>test/issue-N</code></td><td><code>dev/issue-N-*</code></td></tr>
  <tr><td>Commit</td><td><code>test: ... - Closes #N</code></td><td><code>fix: ... - Closes #N</code></td></tr>
  <tr><td>签名</td><td><code>[qe-agent: qa-01]</code></td><td><code>[da-01]</code></td></tr>
  <tr><td>Issue 标签</td><td><code>test-code</code></td><td><code>agent-task</code> <code>ci-failure</code></td></tr>
 </table>
 <h2>2. 三层验收测试</h2>
 <div class="flow">
  <div class="step">Layer A<br><strong>Schema</strong><br>确定性验证</div>
  <div class="arrow">→</div>
  <div class="step">Layer B<br><strong>Coverage</strong><br>结构溯源覆盖率</div>
  <div class="arrow">→</div>
  <div class="step">Layer C<br><strong>QE Audit</strong><br>LLM 专家审计</div>
  <div class="arrow">→</div>
  <div class="step"><strong>Report</strong><br>JSON 报告</div>
 </div>
 <table>
  <tr><th>Layer</th><th>方法</th><th>阈值</th><th>LLM</th></tr>
  <tr><td>A — Schema</td><td>IR 结构验证 (rule_id / trigger / sources / actions)</td><td>0 errors</td><td>不需要</td></tr>
  <tr><td>B — Coverage</td><td>IR sources[] 对文档内容单元的引用率</td><td>≥ 70%</td><td>不需要</td></tr>
  <tr><td>C — QE Audit</td><td>LLM 逐章节评估 IR 覆盖充分性</td><td>inadequate ≤ 30%</td><td>deepseek-v4-flash</td></tr>
 </table>
 <div class="card">
  <strong>最终判决</strong>: 三层全部 PASS → <span class="pass">releasable ✓</span> | 任意一层 FAIL → <span class="fail">blocked ✗</span>
 </div>
 <h2>3. Issue 工作流</h2>
 <h3>3.1 轮询</h3>
 <pre>python scripts/agent_poller.py --action list --labels test-code
 python scripts/agent_poller.py --action list --labels acceptance-failure</pre>
 <h3>3.2 test-code Issue 闭环</h3>
 <div class="flow">
  <div class="step">1. 领取<br>comment</div>
  <div class="arrow">→</div>
  <div class="step">2. 开发<br>tests/acceptance/</div>
  <div class="arrow">→</div>
  <div class="step">3. 本地验证<br>pytest</div>
  <div class="arrow">→</div>
  <div class="step">4. 提交<br>test/issue-N</div>
  <div class="arrow">→</div>
  <div class="step">5. PR + CI</div>
  <div class="arrow">→</div>
  <div class="step">6. merge</div>
  <div class="arrow">→</div>
  <div class="step">7. close</div>
 </div>
 <h3>3.3 e2e 验证流程</h3>
 <ol>
  <li>识别 dev-agent 修复完毕（关联 dev issue 已关闭）</li>
  <li><code>git pull origin main</code></li>
  <li><code>python scripts/run_pipeline.py --parsed &lt;path&gt; --test</code></li>
  <li>分析三层报告</li>
  <li>全部 PASS → 关闭 test-code issue</li>
  <li>仍有 FAIL → 重开 dev issue + 更新 test-code issue</li>
 </ol>
 <h2>4. Issue 生命周期规则</h2>
 <div class="card">
 <h3>关闭规则</h3>
 <ul>
  <li>QE 测试通过 → 关闭 test-code issue</li>
  <li>QE 测试失败 + 新问题 → 开 dev issue (agent-task)，test-code <strong>保持 open</strong></li>
  <li>QE 测试失败 + dev issue 已存在 → test-code <strong>保持 open</strong></li>
  <li><strong>绝不</strong>在问题未修复时关闭 test-code issue</li>
 </ul>
 </div>
 <div class="card">
 <h3>重开规则</h3>
 <ul>
  <li>Dev issue 被关但 QE 重验仍失败 → <strong>重开 dev issue</strong></li>
  <li>必须加 <code>## REOPEN by [qe-agent: qa-01]</code> 评论，包含：<ol>
    <li>已修复项（肯定进展）</li>
    <li>仍存在的问题（具体数据 + 阈值对比）</li>
    <li>结论：为什么修复不完整</li>
  </ol></li>
  <li>重开后同步更新关联 test-code issue</li>
 </ul>
 </div>
 <h2>5. Agent 间通信协议</h2>
 <div class="card">
 <p><strong>Issue 状态是唯一通信渠道</strong>。两个 agent 共用 <code>pzhang_zywl</code> Gitea 账号，通过签名区分：</p>
 <ul>
  <li><span class="badge badge-qe">QE</span> 评论末尾: <code>[qe-agent: qa-01]</code></li>
  <li><span class="badge badge-dev">Dev</span> 评论末尾: <code>[da-01]</code></li>
 </ul>
 <p><strong>QE → Dev</strong>: 发现问题 → 开 dev issue (agent-task) / 重开已有 dev issue</p>
 <p><strong>Dev → QE</strong>: 修复完成 → 关闭 dev issue（自验证后）</p>
 <p><strong>QE 验收</strong>: 拉取 main → 重跑 e2e → 通过就关 test-code，不通过就重开 dev issue</p>
 </div>
 <h2>6. 命令速查</h2>
 <table>
  <tr><th>操作</th><th>命令</th></tr>
  <tr><td>轮询 issue</td><td><code>agent_poller.py --action list --labels test-code</code></td></tr>
  <tr><td>查看 issue</td><td><code>agent_poller.py --action get --issue &lt;N&gt;</code></td></tr>
  <tr><td>评论</td><td><code>agent_poller.py --action comment --issue &lt;N&gt; --body "..."</code></td></tr>
  <tr><td>生命周期</td><td><code>agent_poller.py --action lifecycle --issue &lt;N&gt;</code></td></tr>
  <tr><td>创建 PR</td><td><code>agent_poller.py --action create-pr --issue &lt;N&gt; --branch test/issue-&lt;N&gt;</code></td></tr>
  <tr><td>查 PR CI</td><td><code>agent_poller.py --action pr-status --pr &lt;N&gt;</code></td></tr>
  <tr><td>合并 PR</td><td><code>agent_poller.py --action merge-pr --pr &lt;N&gt;</code></td></tr>
  <tr><td>跑管道</td><td><code>python scripts/run_pipeline.py --parsed &lt;path&gt; --test</code></td></tr>
  <tr><td>验收测试</td><td><code>pytest tests/acceptance/ -v --run-acceptance</code></td></tr>
  <tr><td>仅 Layer A+B</td><td><code>pytest tests/acceptance/ -v --run-acceptance -k "not test_layer_c"</code></td></tr>
 </table>
 <h2>7. 文件结构</h2>
 <pre>
 tests/acceptance/
 ├── conftest.py              # Pytest 配置、fixtures、LLM client
 ├── ir_schema.py             # IR schema 验证
 ├── report.py                # 三层 JSON 报告
 └── test_main_health.py      # Layer A → B → C
 scripts/
 ├── agent_poller.py          # Gitea API 工具
 ├── run_pipeline.py          # 端到端管道运行器
 ├── start_qe_agent.sh        # QE-Agent 启动脚本
 └── .env                     # Token 配置 (gitignored)
 agents/
 ├── QE_AGENT.md              # QE-Agent 系统指令
 └── DEV_AGENT.md             # Dev-Agent 系统指令
 .gitea/workflows/
 ├── ci.yml                   # CI (push/PR)
 └── acceptance.yml           # 手动触发验收
 </pre>
 <h2>8. 本 Session 处理记录</h2>
 <table>
  <tr><th>Issue</th><th>内容</th><th>结果</th></tr>
  <tr><td>#10</td><td>移除硬编码路径，适配 config.py</td><td><span class="pass">closed</span></td></tr>
  <tr><td>#12</td><td>实现端到端验收测试流程</td><td><span class="pass">closed</span></td></tr>
  <tr><td>#14</td><td>跑完整 e2e 测试</td><td><span class="pass">closed</span></td></tr>
  <tr><td>#15</td><td>Dev: IR rules=[] (多次 reopen)</td><td><span class="pass">closed</span></td></tr>
  <tr><td>#18</td><td>再跑 e2e 测试</td><td><span class="warn">open</span></td></tr>
  <tr><td>#21</td><td>P0: 覆盖率不足 (多次 reopen)</td><td><span class="fail">reopened</span></td></tr>
  <tr><td>#22</td><td>P1: trigger.operator 为空</td><td><span class="pass">closed</span></td></tr>
 </table>
 <p style="margin-top:24px;color:var(--border);font-size:12px;">QE-Agent [qe-agent: qa-01] — document_analyzer project</p>
 </body>
 </html>
@@ -1,89 +0,0 @@
 #!/usr/bin/env bash
 # _common.sh — shared functions for dev-agent / qe-agent startup scripts
 # Source this file from start_dev_agent.sh or start_qe_agent.sh
 set -eu
 # ── Resolve paths ──────────────────────────────────────────────────────────────
 _COMMON_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_DIR="${PROJECT_DIR:-$(cd "$_COMMON_DIR/.." && pwd)}"
 # ── Load local secrets (not tracked by git) ────────────────────────────────────
 if [ -f "$_COMMON_DIR/.env" ]; then
    source "$_COMMON_DIR/.env"
 fi
 # ── Default environment variables ──────────────────────────────────────────────
 export GITEA_URL="${GITEA_URL:-http://localhost:3000}"
 export GITEA_REPO="${GITEA_REPO:-pzhang_zywl/document_analyzer}"
 # ── Validate required environment ──────────────────────────────────────────────
 require_token() {
    if [ -z "${GITEA_API_TOKEN:-}" ]; then
        echo "ERROR: GITEA_API_TOKEN is not set." >&2
        echo "Set it in scripts/.env or export it:" >&2
        echo "  export GITEA_API_TOKEN=your-token" >&2
        exit 1
    fi
 }
 # ── Print banner ───────────────────────────────────────────────────────────────
 banner() {
    local role="${1:-Agent}"
    echo "============================================"
    echo "  ${role}-Agent 启动器"
    echo "============================================"
    echo ""
 }
 # ── Launch agent in selected mode ──────────────────────────────────────────────
 # Usage: launch_agent <agent-file> <agent-name> <single-shot-task> <polling-instruction>
 #
 # agent-name is the persona name (e.g. "Dev-Agent", "QE-Agent"). It is used to
 # prefix prompts so the model adopts the correct identity.
 #
 # Mode 1 (single-shot): claude -p, runs once and exits.
 #   --dangerously-skip-permissions avoids blocking in non-interactive mode.
 #   The project .claude/settings.json already sets permissionMode: bypass.
 #
 # Mode 2 (interactive polling): claude --agent, opens Claude Code TUI.
 #   The agent file defines startup behavior (e.g. /loop 10m) and the
 #   user can observe or interact at any time.
 launch_agent() {
    local agent_file="$1"
    local agent_name="$2"
    local single_shot_task="$3"
    local polling_instruction="${4:-}"
    echo "模式选择:"
    echo "  [1] 单次任务 — 检查 Issue 并处理，完成后自动退出 (automode)"
    echo "  [2] 互动轮询 — 进入 Claude Code 界面，每 10 分钟自动轮询"
    echo ""
    read -r -p "请输入 (1/2): " mode
    echo ""
    case "$mode" in
        1)
            echo "执行单次检查 (automode)..."
            echo ""
            cd "$PROJECT_DIR"
            claude -p \
                --agent "$agent_file" \
                --dangerously-skip-permissions \
                "你是 ${agent_name}。${single_shot_task}"
            ;;
        2)
            echo "启动互动轮询模式..."
            echo "${agent_name} 进入 Claude Code 界面后将自动开始轮询"
            echo "你可以随时输入指令与 Agent 互动，按 Ctrl+C 停止"
            echo ""
            cd "$PROJECT_DIR"
            claude --agent "$agent_file" \
                "你是 ${agent_name}。${polling_instruction}"
            ;;
        *)
            echo "无效选择，请输入 1 或 2。"
            exit 1
            ;;
    esac
 }
@@ -2,10 +2,9 @@
 Usage:
    python scripts/agent_poller.py --action list
-    python scripts/agent_poller.py --action list --labels test-code
+    python scripts/agent_poller.py --action list --labels test-dev
    python scripts/agent_poller.py --action get --issue 1
    python scripts/agent_poller.py --action comment --issue 1 --body "Working on this"
    python scripts/agent_poller.py --action create-issue --title "My issue" --labels test-code --body "..."
    python scripts/agent_poller.py --action create-pr --issue 1 --branch test/issue-1
    python scripts/agent_poller.py --action pr-status --pr 4
    python scripts/agent_poller.py --action merge-pr --pr 4
@@ -16,7 +15,6 @@ Usage:
 import argparse
 import json
 import os
 import re
 import sys
 import urllib.request
 import urllib.error
@@ -56,27 +54,6 @@ def _req(method, path, data=None):
        sys.exit(1)
 def _req_safe(method, path, data=None):
    """Like _req but returns None on HTTPError instead of crashing.
    Used for probing issue/PR existence where the caller can handle absence.
    """
    url = f"{BASE}{path}"
    payload = json.dumps(data).encode("utf-8") if data else None
    req = urllib.request.Request(url, data=payload, method=method)
    req.add_header("Authorization", f"token {GITEA_TOKEN}")
    req.add_header("Content-Type", "application/json")
    try:
        with urllib.request.urlopen(req) as resp:
            raw = resp.read()
            if not raw:
                return {}
            return json.loads(raw)
    except urllib.error.HTTPError as e:
        body = e.read().decode()
        print(f"API Error {e.code}: {body}", file=sys.stderr)
        return None
 # ── Issue operations ─────────────────────────────────────────────────────────
 def list_issues(labels: list[str] | None = None):
@@ -95,68 +72,6 @@ def list_issues(labels: list[str] | None = None):
    return issues
 def _get_blocking_refs(issue_num: int) -> set[int]:
    """Extract all issue references from an issue body + comments.
    Scans both the issue body and all comments for #N patterns,
    returning a set of referenced issue numbers.
    """
    refs: set[int] = set()
    # Body
    issue = _req_safe("GET", f"/issues/{issue_num}")
    if issue is None:
        return refs  # API error → return empty set, keep blocked
    body = issue.get("body", "") or ""
    refs.update(int(m.group(1)) for m in re.finditer(r'#(\d+)', body))
    # Comments
    comments = _req_safe("GET", f"/issues/{issue_num}/comments")
    if comments:
        for c in comments:
            cbody = c.get("body", "") or ""
            refs.update(int(m.group(1)) for m in re.finditer(r'#(\d+)', cbody))
    return refs
 def blocked_check():
    """Check all blocked issues: if blocking issues are now closed, unblock.
    Scans issue body + comments for blocking references.
    If no references found or all referenced issues are closed,
    removes the 'blocked' label.
    """
    all_blocked = _req_safe("GET", "/issues?state=open&labels=blocked")
    if not all_blocked:
        print("No blocked issues found.")
        return
    unblocked_count = 0
    for issue in all_blocked:
        blocking_nums = _get_blocking_refs(issue["number"])
        all_resolved = True
        for blk in blocking_nums:
            blk_issue = _req_safe("GET", f"/issues/{blk}")
            if blk_issue is None:
                all_resolved = False  # API error → keep blocked
                break
            if blk_issue.get("state") != "closed":
                all_resolved = False
                break
        if all_resolved:
            current_label_names = [l["name"] for l in issue.get("labels", [])]
            new_label_names = [l for l in current_label_names if l != "blocked"]
            new_label_ids = _label_names_to_ids(new_label_names)
            _req("PUT", f"/issues/{issue['number']}/labels", {"labels": new_label_ids})
            reason = "所有阻塞 Issue 均已关闭" if blocking_nums else "无阻塞引用，移除残留 blocked 标签"
            print(f"Unblocked #{issue['number']}: {issue['title']}")
            comment_issue(issue["number"], f"阻塞已解除：{reason}。")
            unblocked_count += 1
    if unblocked_count == 0:
        print(f"Checked {len(all_blocked)} blocked issue(s): still blocked.")
 def get_issue(num):
    i = _req("GET", f"/issues/{num}")
    print(f"## #{i['number']}: {i['title']}")
@@ -175,108 +90,14 @@ def comment_issue(num, body):
 def close_issue(num, body=None):
-    """Close an issue, optionally with a final comment (signature auto-appended).
+    """Close an issue, optionally with a final comment (signature auto-appended)."""
    After closing, automatically unblocks any issues that were blocked by this one
    if no other blocking issues remain open.
    """
    if body:
        comment_issue(num, body)  # comment_issue already appends AGENT_SIG
    i = _req("PATCH", f"/issues/{num}", {"state": "closed"})
    print(f"Issue #{num} closed")
    _unblock_issues_blocked_by(num)
    return i
 def reopen_issue(num, body=None):
    """Reopen a closed issue, optionally with a reason comment."""
    if body:
        comment_issue(num, f"## REOPEN\n\n{body}")
    i = _req("PATCH", f"/issues/{num}", {"state": "open"})
    print(f"Issue #{num} reopened")
    return i
 def _unblock_issues_blocked_by(closed_num):
    """Check issues blocked by *closed_num* and unblock if all blockers resolved.
    Scans both body and comments for #N references. If *closed_num* appears
    in any blocked issue and all referenced issues are now closed,
    removes the 'blocked' label and comments on the unblocked issue.
    """
    all_blocked = _req_safe("GET", "/issues?state=open&labels=blocked")
    if not all_blocked:
        return
    for issue in all_blocked:
        blocking_nums = _get_blocking_refs(issue["number"])
        if closed_num not in blocking_nums:
            continue
        # Check all referenced issues — are they all closed?
        all_resolved = True
        for blk in blocking_nums:
            if blk == closed_num:
                continue
            blk_issue = _req_safe("GET", f"/issues/{blk}")
            if blk_issue is None:
                all_resolved = False  # API error → keep blocked
                break
            if blk_issue.get("state") != "closed":
                all_resolved = False
                break
        if all_resolved:
            current_label_names = [l["name"] for l in issue.get("labels", [])]
            new_label_names = [l for l in current_label_names if l != "blocked"]
            new_label_ids = _label_names_to_ids(new_label_names)
            _req("PUT", f"/issues/{issue['number']}/labels", {"labels": new_label_ids})
            print(f"  -> Unblocked #{issue['number']}: all blocking issues resolved")
            comment_issue(issue["number"],
                f"阻塞已解除：#{closed_num} 及其他阻塞 Issue 均已关闭。")
 def create_issue(title, body=None, labels=None):
    """Create a new Gitea issue.
    Labels convention (per project rules):
      - Product/feature issues → product-code
      - Test code issues → test-code
    """
    payload = {"title": title}
    if body:
        payload["body"] = body + AGENT_SIG
    if labels:
        label_names = [l.strip() for l in labels.split(",") if l.strip()]
        # Gitea 1.22 expects label IDs (int64). Resolve names → IDs.
        label_ids = _label_names_to_ids(label_names)
        if label_ids:
            payload["labels"] = label_ids
    i = _req("POST", "/issues", payload)
    issue_labels = [l["name"] for l in i.get("labels", [])]
    print(f"Issue #{i['number']} created: {i['title']}")
    if issue_labels:
        print(f"Labels: {', '.join(issue_labels)}")
    print(f"URL: {i.get('html_url', i.get('url', ''))}")
    return i
 def _label_names_to_ids(names: list[str]) -> list[int]:
    """Resolve label names to Gitea label IDs. Returns empty list on failure."""
    try:
        all_labels = _req("GET", "/labels")
        name_to_id = {l["name"]: l["id"] for l in all_labels}
        ids = []
        for name in names:
            if name in name_to_id:
                ids.append(name_to_id[name])
            else:
                print(f"Warning: label '{name}' not found, skipping", file=sys.stderr)
        return ids
    except SystemExit:
        return []
 # ── PR operations ────────────────────────────────────────────────────────────
 def create_pr(issue_num, branch, body=None):
@@ -391,15 +212,12 @@ def main():
    parser = argparse.ArgumentParser(description="Dev agent Gitea helper")
    parser.add_argument("--action", required=True,
                        choices=["list", "get", "comment", "close-issue",
-                                 "create-issue", "reopen-issue",
+                                 "create-pr", "pr-status", "merge-pr", "lifecycle"])
                                 "create-pr", "pr-status", "merge-pr", "lifecycle",
                                 "blocked-check"])
    parser.add_argument("--issue", type=int)
    parser.add_argument("--pr", type=int)
    parser.add_argument("--title", help="Issue title (for 'create-issue' action)")
    parser.add_argument("--branch")
    parser.add_argument("--body")
-    parser.add_argument("--labels", help="Comma-separated labels (filter for 'list', assign for 'create-issue')")
+    parser.add_argument("--labels", help="Comma-separated labels to filter issues (for 'list' action)")
    args = parser.parse_args()
    if not GITEA_TOKEN:
@@ -425,16 +243,6 @@ def main():
            print("--issue is required for 'close-issue' action", file=sys.stderr)
            sys.exit(1)
        close_issue(args.issue, args.body)
    elif args.action == "create-issue":
        if not args.title:
            print("--title is required for 'create-issue' action", file=sys.stderr)
            sys.exit(1)
        create_issue(args.title, args.body, args.labels)
    elif args.action == "reopen-issue":
        if not args.issue:
            print("--issue is required for 'reopen-issue' action", file=sys.stderr)
            sys.exit(1)
        reopen_issue(args.issue, args.body)
    elif args.action == "create-pr":
        if not args.issue or not args.branch:
            print("--issue and --branch are required for 'create-pr' action", file=sys.stderr)
@@ -450,8 +258,6 @@ def main():
            print("--pr is required for 'merge-pr' action", file=sys.stderr)
            sys.exit(1)
        merge_pr(args.pr)
    elif args.action == "blocked-check":
        blocked_check()
    elif args.action == "lifecycle":
        if not args.issue:
            print("--issue is required for 'lifecycle' action", file=sys.stderr)
@@ -83,7 +83,7 @@ def run_ir_pipeline(parsed_path: str) -> str | None:
        result = subprocess.run(
            [sys.executable, str(script_path)],
            cwd=str(PROJECT_ROOT),
-            capture_output=True, text=True, encoding="utf-8",
+            capture_output=True, text=True,
            env=env,
        )
        if result.returncode != 0:
@@ -111,8 +111,6 @@ def run_acceptance_tests(parsed_json_path: str) -> int:
    print("[3/3] Running QE acceptance tests...")
    test_dir = PROJECT_ROOT / "tests" / "acceptance"
    env = os.environ.copy()
    env.setdefault("PYTHONIOENCODING", "utf-8")
    result = subprocess.run(
        [
            sys.executable, "-m", "pytest", str(test_dir),
@@ -122,8 +120,6 @@ def run_acceptance_tests(parsed_json_path: str) -> int:
            "--tb=short",
        ],
        cwd=str(PROJECT_ROOT),
        encoding="utf-8",
        env=env,
    )
    return result.returncode
@@ -1,56 +1,50 @@
@echo off
 chcp 65001 >nul
-title Dev-Agent - Gitea Issue Worker
+title Dev Agent - Gitea Issue Worker
 :: ── Change to project root ────────────────────────────────────────────────────
 cd /d "%~dp0.."
 :: ── Load .env (batch-compatible parser: "export KEY=VALUE" → set KEY=VALUE) ──
 if exist "scripts\.env" (
    for /f "usebackq tokens=2,3 delims== " %%a in ("scripts\.env") do set %%a=%%b
 )
 :: ── Defaults ──────────────────────────────────────────────────────────────────
 if "%GITEA_URL%"==""     set GITEA_URL=http://localhost:3000
 if "%GITEA_REPO%"==""    set GITEA_REPO=pzhang_zywl/document_analyzer
 if "%DEV_AGENT_ID%"==""  set DEV_AGENT_ID=da-01
 :: ── Validate token ────────────────────────────────────────────────────────────
 if "%GITEA_API_TOKEN%"=="" (
    echo ERROR: GITEA_API_TOKEN is not set.
    echo Set it in scripts\.env or in your environment.
    pause
    exit /b 1
 )
 echo ============================================
-echo   Dev-Agent 启动器
+echo   Dev Agent 启动器
 echo ============================================
 echo.
 set GITEA_API_TOKEN=59117246ec418d5d87042de073b0d4197d8054bf
 set GITEA_URL=http://localhost:3000
 set GITEA_REPO=pzhang_zywl/document_analyzer
 cd /d C:\Users\peterz\projects\document_analyzer
 echo 模式选择:
-echo   [1] 单次任务 - 检查 Issue 并处理，完成后退出 (automode^)
+echo   [1] 单次任务 - 检查一次 Issue 并处理
-echo   [2] 互动轮询 - 进入 Claude Code 界面，每 10 分钟轮询
+echo   [2] 持续轮询 - 每 10 分钟检查一次 (推荐)
 echo   [3] 交互模式 - 进入对话手动操作
 echo.
-set /p MODE="请输入 (1/2): "
+set /p MODE="请输入 (1/2/3): "
 if "%MODE%"=="1" (
    echo.
-    echo 执行单次检查 (automode)...
+    echo 正在执行单次检查...
-    claude -p --agent agents/DEV_AGENT.md --dangerously-skip-permissions "你是 Dev-Agent。执行一次 Issue 巡检（单次任务，不要用 /loop）：1. agent_poller.py --action list 列出所有打开的 Issue 2. 跳过纯测试 3. 逐个走闭环：分析-开发-pytest-commit-push-create-pr-CI-merge-pr-通知QE 4. 退出。"
+    claude -p --agent agents/DEV_AGENT.md "你是 Dev-Agent，检查 Gitea 所有打开的 Issue，跳过纯测试相关的，其他全部领取分析并修复，记得同步更新测试。"
    pause
-    exit /b 0
+    exit
 )
 if "%MODE%"=="2" (
    echo.
-    echo 启动互动轮询模式...
+    echo 启动持续轮询模式 (每 10 分钟)...
    echo Dev-Agent 进入 Claude Code 界面后将自动每 10 分钟轮询 Gitea Issue
    echo 按 Ctrl+C 停止
-    claude --agent agents/DEV_AGENT.md "你是 Dev-Agent。现在开始工作。使用 /loop 10m 每 10 分钟 python scripts/agent_poller.py --action list 检查 Issue，跳过纯测试，有则走完整闭环，无则报告 main healthy。保持对话开放。"
+    claude -p --agent agents/DEV_AGENT.md "你是 Dev-Agent，用 loop 模式每 10 分钟检查一次 Gitea 所有打开的 Issue，跳过纯测试相关的，其他全部领取处理。完成后评论进度，push 触发 CI。"
    pause
-    exit /b 0
+    exit
 )
 if "%MODE%"=="3" (
    echo.
    echo 启动交互模式...
    echo 进入后输入: 检查 Gitea Issues 并处理
    claude --agent agents/DEV_AGENT.md
    pause
    exit
 )
 echo 无效选择。
 pause
 exit /b 1
@@ -1,26 +1,57 @@
 #!/usr/bin/env bash
-# Dev-Agent 启动脚本 — 单次任务 + 互动轮询 两种模式
+# Dev-Agent 启动脚本 — 在 Git Bash 中运行
 # 用法: bash scripts/start_dev_agent.sh
 # 前置: 在 scripts/.env 中设置 GITEA_API_TOKEN
-set -eu
+set -e
 # Source local secrets if available (not tracked by git)
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-source "$SCRIPT_DIR/_common.sh"
+if [ -f "$SCRIPT_DIR/.env" ]; then
    source "$SCRIPT_DIR/.env"
 fi
-# Agent 标识: da-MMDD-HHmm，可通过环境变量覆盖
+# Load from environment or default values
-export DEV_AGENT_ID="${DEV_AGENT_ID:-da-$(date +%m%d-%H%M)}"
+export GITEA_API_TOKEN="${GITEA_API_TOKEN:-}"
 export GITEA_URL="${GITEA_URL:-http://localhost:3000}"
 export GITEA_REPO="${GITEA_REPO:-pzhang_zywl/document_analyzer}"
 export DEV_AGENT_ID="da-$(date +%m%d-%H%M)"
-banner "Dev"
+cd "$(dirname "$0")/.."
 require_token
-launch_agent \
+echo "============================================"
-    "agents/DEV_AGENT.md" \
+echo "  Dev-Agent 启动器"
-    "Dev-Agent" \
+echo "============================================"
-    "执行一次 Issue 巡检（单次任务，不要用 /loop）：
+echo ""
-1. python scripts/agent_poller.py --action list 列出所有打开的 Issue
+echo "模式选择:"
-2. 跳过纯测试相关的 Issue
+echo "  [1] 单次任务 - 检查一次 Issue 并处理"
-3. 对每个负责的 Issue 走完整闭环：
+echo "  [2] 持续轮询 - 每 10 分钟检查一次 (推荐)"
-   分析 → 分支 → 开发+UT → pytest → commit → push → create-pr → comment → 等 CI → merge-pr → 通知 QE 验证
+echo "  [3] 交互模式 - 进入对话手动操作"
-4. 所有 Issue 处理完毕后报告汇总并退出。" \
+echo ""
-    "现在开始工作。使用 /loop 10m 开启轮询：每 10 分钟 python scripts/agent_poller.py --action list 检查打开的 Issue，跳过纯测试相关的，有则走完整闭环，无则报告 main healthy。保持对话开放。"
+read -r -p "请输入 (1/2/3): " MODE
 case "$MODE" in
  1)
    echo ""
    echo "正在执行单次检查..."
    claude -p --agent agents/DEV_AGENT.md \
      "你是 Dev-Agent。检查 Gitea 所有打开的 Issue（--action list），跳过纯测试相关的。对每个负责的 Issue，走完完整闭环：分析 → 分支 → 开发+UT → pytest → commit → push → create-pr → comment Issue → 等 CI → merge-pr → 关闭。"
    ;;
  2)
    echo ""
    echo "启动持续轮询模式 (每 10 分钟)..."
    echo "按 Ctrl+C 停止"
    claude -p --agent agents/DEV_AGENT.md \
      "你是 Dev-Agent。用 loop 模式每 10 分钟检查一次 Gitea Issue（--action list）。跳过纯测试相关的。每个 Issue 走完整闭环：分析→开发→push→create-pr→comment→CI→merge-pr→close。每个步骤用 agent_poller.py 对应命令。"
    ;;
  3)
    echo ""
    echo "启动交互模式..."
    echo "进入后输入: 检查 Gitea Issues 并处理"
    echo "可用命令速查: agent_poller.py --help"
    claude --agent agents/DEV_AGENT.md
    ;;
  *)
    echo "无效选择。"
    exit 1
    ;;
 esac
@@ -1,26 +1,55 @@
 #!/usr/bin/env bash
-# QE-Agent 启动脚本 — 单次任务 + 互动轮询 两种模式
+# QE-Agent 启动脚本 — 在 Git Bash 中运行
 # 用法: bash scripts/start_qe_agent.sh
 # 前置: 在 scripts/.env 中设置 GITEA_API_TOKEN
-set -eu
+set -e
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+export GITEA_API_TOKEN="59117246ec418d5d87042de073b0d4197d8054bf"
-source "$SCRIPT_DIR/_common.sh"
+export GITEA_URL="http://localhost:3000"
 export GITEA_REPO="pzhang_zywl/document_analyzer"
 export QE_AGENT_ID="qa-01"
-# Agent 标识: qa-MMDD-HHmm，可通过环境变量覆盖
+cd "$(dirname "$0")/.."
 export QE_AGENT_ID="${QE_AGENT_ID:-qa-$(date +%m%d-%H%M)}"
-banner "QE"
+echo "============================================"
-require_token
+echo "  QE-Agent 启动器"
 echo "============================================"
 echo ""
 echo "模式选择:"
 echo "  [1] 单次任务 - 检查一次 test-dev Issue 并处理"
 echo "  [2] 持续轮询 - 每 10 分钟检查一次 (推荐)"
 echo "  [3] 交互模式 - 进入对话手动操作"
 echo ""
 read -r -p "请输入 (1/2/3): " MODE
-launch_agent \
+case "$MODE" in
-    "agents/QE_AGENT.md" \
+  1)
-    "QE-Agent" \
+    echo ""
-    "执行一次 Issue 巡检（单次任务，不要用 /loop）：
+    echo "正在执行单次检查..."
-1. python scripts/agent_poller.py --action list --labels test-code 检查 test-code Issue
+    claude -p --agent agents/QE_AGENT.md \
-2. python scripts/agent_poller.py --action list --labels acceptance-failure 检查 acceptance-failure Issue
+      "你是 QE-Agent。检查 Gitea 上的 test-dev 和 acceptance-failure 标签 Issue（--action list --labels test-dev 和 --labels acceptance-failure）。对 test-dev Issue：分析内容 → 开发验收测试到 tests/acceptance/ → pytest 本地验证 → commit 'test: <描述> - Closes #N' → push → create-pr → comment Issue → 等 CI 通过 → merge-pr。对 acceptance-failure Issue：分析失败原因 → 如果是测试本身问题修复测试 → 如果是管道问题开 test-dev issue 跟踪。"
-3. test-code Issue：分析 → 开发验收测试到 tests/acceptance/ → pytest 本地验证 → commit('test:' 前缀, Closes #N) → push → create-pr → 等 CI → merge-pr
+    ;;
-4. acceptance-failure Issue：分析失败原因 → 测试问题则修复测试 → 管道问题则开 test-code issue 跟踪
+  2)
-5. 所有 Issue 处理完毕后报告汇总并退出。" \
+    echo ""
-    "现在开始工作。使用 /loop 10m 开启轮询：每 10 分钟检查 test-code 和 acceptance-failure 标签 Issue，有则走完整闭环（分析→开发测试→pytest→push→PR→CI→merge），无则报告 main healthy。保持对话开放。"
+    echo "启动持续轮询模式 (每 10 分钟)..."
    echo "按 Ctrl+C 停止"
    claude -p --agent agents/QE_AGENT.md \
      "你是 QE-Agent。用 loop 模式每 10 分钟检查一次 Gitea 上的 test-dev 和 acceptance-failure 标签 Issue。对 test-dev Issue 走完整闭环：分析→开发验收测试→pytest验证→commit('test:' 前缀)→push→create-pr→comment→CI→merge-pr。对 acceptance-failure 分析失败原因→修复→push→PR。每个步骤用 agent_poller.py 对应命令。如果没有待处理 Issue，报告 '当前没有 QE 相关 Issue，main branch 质量正常'。"
    ;;
  3)
    echo ""
    echo "启动交互模式 (默认 10 分钟轮询)..."
    echo "按 Ctrl+C 停止"
    echo ""
    echo "可用命令速查:"
    echo "  agent_poller.py --action list --labels test-dev"
    echo "  agent_poller.py --action list --labels acceptance-failure"
    echo "  agent_poller.py --action get --issue <N>"
    echo "  python -m pytest tests/acceptance/ -v --run-acceptance"
    claude --agent agents/QE_AGENT.md
    ;;
  *)
    echo "无效选择。"
    exit 1
    ;;
 esac
@@ -63,7 +63,7 @@ class LLMClient:
        print(llm.usage)
    """
-    IMAGE_MODEL = "qwen3.6-flash"
+    IMAGE_MODEL = "qwen3-vl-plus"
    TEXT_MODEL = "deepseek-v4-flash"
    DASHSCOPE_BASE = "https://dashscope.aliyuncs.com/compatible-mode/v1"
@@ -72,7 +72,7 @@ class LLMClient:
    TIMEOUT = 120
    MAX_RETRIES = 3
-    _VISION_KEYWORDS = ("vl", "vision", "qwen-vl", "qwen3-vl", "qwen3.6")
+    _VISION_KEYWORDS = ("vl", "vision", "qwen-vl", "qwen3-vl")
    def __init__(
        self,
@@ -63,7 +63,7 @@ class LLMClient:
        print(llm.usage)
    """
-    IMAGE_MODEL = "qwen3.6-flash"
+    IMAGE_MODEL = "qwen3-vl-plus"
    TEXT_MODEL = "deepseek-v4-flash"
    DASHSCOPE_BASE = "https://dashscope.aliyuncs.com/compatible-mode/v1"
@@ -72,7 +72,7 @@ class LLMClient:
    TIMEOUT = 120
    MAX_RETRIES = 3
-    _VISION_KEYWORDS = ("vl", "vision", "qwen-vl", "qwen3-vl", "qwen3.6")
+    _VISION_KEYWORDS = ("vl", "vision", "qwen-vl", "qwen3-vl")
    def __init__(
        self,
@@ -86,8 +86,7 @@ COVERAGE_TARGET = float(os.environ.get("IR_COVERAGE_TARGET", "0.95"))
 ENSEMBLE_TEMPERATURES = [
    float(os.environ.get("IR_ENSEMBLE_T1", "0.0")),
    float(os.environ.get("IR_ENSEMBLE_T2", "0.3")),
-    float(os.environ.get("IR_ENSEMBLE_T3", "0.5")),
+    float(os.environ.get("IR_ENSEMBLE_T3", "0.7")),
    float(os.environ.get("IR_ENSEMBLE_T4", "0.7")),
 ]
@@ -186,8 +186,6 @@
 8. **开关关闭状态**：开关关闭时所有限制失效，这也必须作为一条规则输出（path: ["...", "开关关闭", "无限制"]）。
 9. **功能完整性要求（重要）**：上下文包中的每个表格行、每条文字描述、每个逻辑树路径都必须被至少一条规则覆盖。仔细检查上下文包，确保不遗漏任何数据来源。如果上下文包中有表格，每条表格行至少生成一条对应规则。
 {format_feedback}
 ## 输出格式
@@ -553,67 +553,25 @@ def _quick_validate(
            f"未覆盖: {uncovered[:5]}"
        )
-    # Count table rows — only from functional sections with content
+    # Count table rows
    total_rows = sum(
        len(b.get("rows", []))
        for s in doc.get("sections", [])
        if _is_functional_section(s.get("source", ""))
        and _has_section_content(s)
        for b in s.get("blocks", [])
        if b.get("type") == "table"
    )
-    covered_set: set[tuple] = set()
+    covered_rows = sum(
-    for fu in units:
+        1 for fu in units
-        for src in fu.get("sources", []):
+        for src in fu.get("sources", [])
-            if src.get("type") == "table" and src.get("row"):
+        if src.get("type") == "table" and src.get("row")
-                covered_set.add((src.get("section", ""), src.get("row")))
+    )
-    covered_rows = len(covered_set)
+    row_cov = covered_rows / max(total_rows, 1)
    # When there are no table rows to cover, skip check
    if total_rows == 0:
        row_cov = 1.0
    else:
        row_cov = covered_rows / total_rows
    print(f"  表格行覆盖率: {row_cov:.0%} ({covered_rows}/{total_rows} rows)", flush=True)
    if row_cov < SECTION_COVERAGE_TARGET:
        # Collect specific missing rows with content for targeted feedback
        missing_rows: list[dict] = []
        for s in doc.get("sections", []):
            if not _is_functional_section(s.get("source", "")):
                continue
            if not _has_section_content(s):
                continue
            sec_name = s.get("source", "").split()[0] if s.get("source") else "?"
            for b in s.get("blocks", []):
                if b.get("type") != "table":
                    continue
                for row in b.get("rows", []):
                    rn = row.get("row")
                    if (sec_name, rn) not in covered_set:
                        key_col = ""
                        val_col = ""
                        for col in row.get("columns", []):
                            cn = col.get("name", "")
                            ct = col.get("text", "")[:100]
                            if cn in ("功能", "三级功能", "一级功能", "功能名称"):
                                key_col = ct
                            elif cn in ("功能详细说明", "详细说明", "四级功能", "说明"):
                                val_col = ct
                        if not key_col:
                            # Use first column as key
                            for col in row.get("columns", []):
                                key_col = col.get("text", "")[:60]
                                break
                        missing_rows.append({
                            "section": sec_name,
                            "row": rn,
                            "key": key_col,
                            "value": val_col,
                        })
        gaps["coverage_warnings"].append(
            f"表格行覆盖率 {row_cov:.0%} < {SECTION_COVERAGE_TARGET:.0%}, "
-            f"({covered_rows}/{total_rows} rows from functional sections)"
+            f"({covered_rows}/{total_rows} rows)"
        )
        gaps["missing_table_rows"] = missing_rows
    # Coverage warnings are non-blocking (depend on LLM prompt quality)
    if gaps["coverage_warnings"]:
@@ -634,34 +592,19 @@ def _build_coverage_feedback(gaps: dict) -> str:
    parts = []
    for item in gaps.get("coverage_warnings", []):
        parts.append(f"- {item}")
    # Include specific missing table rows with their content
    missing_rows = gaps.get("missing_table_rows", [])
    if missing_rows:
        parts.append(f"\n### 以下具体表格行缺少对应 function_unit（共 {len(missing_rows)} 行）：\n")
        for mr in missing_rows:
            sec = mr.get("section", "?")
            rn = mr.get("row", "?")
            key = mr.get("key", "")
            val = mr.get("value", "")
            parts.append(
                f"- **章节 {sec}, 行 {rn}**: {key}"
                + (f" — {val}" if val else "")
            )
    if not parts:
        return ""
    return (
-        "\n## 关键覆盖反馈（上一轮 LLM 输出存在缺口，请重新处理）\n\n"
+        "\n## 关键覆盖反馈（上一轮 LLM 输出了以下缺口，请重新处理）\n\n"
        + "\n".join(parts)
        + "\n\n"
        "### 修复动作（必须执行）\n\n"
-        "1. **重新扫描上述每个缺失章节和表格行**，从文字和表格中提取所有可被测试的功能行为\n"
+        "1. **重新扫描上述每个缺失章节**，从文字和表格中提取所有可被测试的功能行为\n"
-        "2. **为上述每个缺失表格行创建独立的 function_unit**，不得合并不同行的规则\n"
+        "2. **为每个缺失的表格行创建独立的 function_unit**，不得合并不同行的规则\n"
        "3. **每个 function_unit 必须引用具体的 section 号和 row 号**作为 source\n"
        "4. **非功能章节可以跳过**（如背景、术语、变更日志），但行为规则章节必须覆盖\n"
-        "5. 输出中必须包含针对上述缺口的新 function_unit，**尤其是列出具体缺失的表格行**\n"
+        "5. 输出中必须包含针对上述缺口的新 function_unit\n"
    )
@@ -880,19 +823,11 @@ def run_ensemble_semantic_index(doc: dict) -> dict:
            if v:
                print(f"    {k}: {len(v)} 个问题")
-        # Feedback retry: re-run with coverage feedback (up to 3 retries, quality-gated)
+        # Feedback retry: re-run with coverage feedback (one retry)
        retry_count = 0
        while retry_count < 3:
        feedback = _build_coverage_feedback(gaps)
-            if not feedback:
+        if feedback:
-                break
+            print(f"\n  覆盖反馈重试 (feedback长度={len(feedback)}字符)...", flush=True)
            retry_count += 1
            print(f"\n  覆盖反馈重试 #{retry_count} (feedback长度={len(feedback)}字符)...", flush=True)
            try:
                # record pre-retry coverage to gate quality
                pre_warnings = len(gaps.get("coverage_warnings", []))
                pre_missing_rows = len(gaps.get("missing_table_rows", []))
                retry_prompt = build_prompt(doc, feedback, all_paths)
                print(f"  重试 prompt 长度: {len(retry_prompt)} 字符", flush=True)
                retry_result = call_llm(retry_prompt, max_retries=1, temperature=0.3)
@@ -900,42 +835,27 @@ def run_ensemble_semantic_index(doc: dict) -> dict:
                n_retry_concepts = len(retry_result.get("concepts", []))
                print(f"  重试返回: {n_retry_concepts} 概念, {n_retry_units} 功能单元", flush=True)
                if n_retry_units > 0:
                    # Check which new sections were covered
                    retry_sections = set()
                    for fu in retry_result.get("function_units", []):
                        for src in fu.get("sources", []):
                            if src.get("section"):
                                retry_sections.add(src["section"])
                    print(f"  重试新增 sections: {sorted(retry_sections)}", flush=True)
-                    # Quality gate: include retry if it adds new sections or doesn't regress coverage
+                    # Merge retry into results and re-validate
                    trial_indices = semantic_indices + [retry_result]
                    trial_merged = ensemble_merge(trial_indices)
                    trial_passed, trial_gaps = _quick_validate(trial_merged, doc, all_paths)
                    trial_warnings = len(trial_gaps.get("coverage_warnings", []))
                    trial_missing = len(trial_gaps.get("missing_table_rows", []))
                    improved = trial_warnings < pre_warnings or trial_missing < pre_missing_rows
                    no_regression = trial_warnings <= pre_warnings and trial_missing <= pre_missing_rows
                    has_new_sections = len(retry_sections) > 0
                    if improved or (no_regression and has_new_sections):
                    semantic_indices.append(retry_result)
-                        merged = trial_merged
+                    merged = ensemble_merge(semantic_indices)
-                        passed, gaps = trial_passed, trial_gaps
+                    merged["ensemble_temperatures"] = list(temperatures) + ["feedback_retry"]
-                        merged["ensemble_temperatures"] = list(temperatures) + [f"feedback_retry_{retry_count}"]
+                    passed, gaps = _quick_validate(merged, doc, all_paths)
                    merged["validation_passed"] = passed
                    merged["validation_gaps"] = {
                        k: v for k, v in gaps.items() if v
                    }
-                        print(f"  重试后验证 (已采纳): {'PASS' if passed else 'GAPS FOUND'} "
+                    print(f"  重试后验证: {'PASS' if passed else 'GAPS FOUND'}", flush=True)
                              f"(warnings {pre_warnings}→{trial_warnings}, "
                              f"missing_rows {pre_missing_rows}→{trial_missing})", flush=True)
                    else:
                        print(f"  重试结果未提升覆盖率，丢弃 "
                              f"(warnings {pre_warnings}→{trial_warnings}, "
                              f"missing_rows {pre_missing_rows}→{trial_missing})", flush=True)
            except Exception as e:
                print(f"  覆盖反馈重试失败: {e}", flush=True)
                import traceback
                traceback.print_exc()
                break
    return merged
@@ -114,9 +114,8 @@ def rule_signature(rule: dict) -> str:
    trigger = rule.get("trigger") or {}
    actions = rule.get("actions") or []
    raw_conditions = trigger.get("conditions") or []
    conditions = sorted(
-        raw_conditions, key=lambda c: (c or {}).get("signal", "")
+        trigger.get("conditions", []), key=lambda c: c.get("signal", "")
    )
    sorted_actions = sorted(actions, key=lambda a: a.get("description", ""))
@@ -134,18 +133,6 @@ def _normalize_rule(rule: dict) -> dict:
    Fixes common LLM output issues: missing trigger, null operator, etc.
    """
    # Ensure precondition has required fields (defensive against LLM omission)
    if "precondition" not in rule:
        rule["precondition"] = {}
    precond = rule["precondition"]
    if precond is None:
        rule["precondition"] = {}
        precond = rule["precondition"]
    if "geographic_scope" not in precond or not precond["geographic_scope"]:
        precond["geographic_scope"] = "global"
    if "screen_type" not in precond:
        precond["screen_type"] = "any"
    # Ensure trigger exists
    if not rule.get("trigger"):
        rule["trigger"] = {}
@@ -181,59 +168,6 @@ def _normalize_rule(rule: dict) -> dict:
            "value": "active"
        }]
    # Ensure table/text sources have a section field (defensive against LLM omission)
    # Also normalize invalid source types (LLM hallucinations like function_unit_description)
    sources = rule.get("sources", [])
    valid_types = {"table", "text", "logic_tree"}
    def _clean_section(val):
        """Normalize section value: list→first element, ensure string."""
        if isinstance(val, list):
            return str(val[0]).strip() if val else ""
        if isinstance(val, str):
            return val.strip()
        return str(val).strip() if val else ""
    # Normalize section fields that might be lists (LLM format instability)
    for s in sources:
        sec = s.get("section")
        if sec is not None:
            s["section"] = _clean_section(sec)
    # try to infer a default section from the rule path
    default_section = ""
    for s in sources:
        sec = s.get("section", "")
        if sec and isinstance(sec, str) and sec.strip():
            default_section = sec.strip()
            break
    if not default_section:
        path = rule.get("path", "")
        if path:
            default_section = path.split(" > ")[0] if " > " in path else path
    if sources:
        for src in sources:
            stype = src.get("type", "")
            if stype and stype not in valid_types:
                src["type"] = "text"
                stype = "text"
            if stype == "table":
                if not src.get("section"):
                    src["section"] = default_section
                if src.get("row") is None:
                    src["row"] = 0
            elif stype == "text":
                if not src.get("section"):
                    src["section"] = default_section
    else:
        # Empty sources list — add a minimal text source (defensive against schema failure)
        src = {"type": "text", "text_snippet": "inferred from rule context"}
        if default_section:
            src["section"] = default_section
        sources.append(src)
        rule["sources"] = sources
    return rule
@@ -459,221 +459,6 @@ def test_step1_confidence_summary():
    assert not errors, f"confidence_summary errors: {errors}"
 # ═══════════════════════════════════════════════════════════════════════════════
 # Pure unit tests — no LLM output needed
 # ═══════════════════════════════════════════════════════════════════════════════
 import re
 sys.path.insert(0, str(Path(__file__).parent.parent))
 from step1_semantic_index import _quick_validate
 # Replicate _has_section_content logic for unit testing (same as in step1)
 def _has_section_content(sec: dict) -> bool:
    """Check if a section has meaningful content (text >= 10 chars, table, or image)."""
    for block in sec.get("blocks", []):
        blk_type = block.get("type", "")
        if blk_type == "table":
            return True
        if blk_type in ("image", "figure", "picture"):
            return True
        text = block.get("text", "")
        if isinstance(text, str) and len(text.strip()) >= 10:
            return True
    return False
 _non_functional_patterns = [
    re.compile(p) for p in [
        r"编制.*变更.*日志", r"变更日志", r"文档背景", r"文档范围",
        r"术语解释", r"参考", r"附录", r"版本", r"变更记录",
        r"目录", r"前言", r"概述", r"简介",
        r"PRD", r"前置条件", r"依赖", r"行业规范", r"输入文件",
        r"后方输入", r"政策法规", r"相关文档", r"概要说明",
    ]
 ]
 def _is_functional_section(sec_name: str) -> bool:
    """Same logic as in step1_semantic_index.py."""
    if not sec_name.strip():
        return False
    for pat in _non_functional_patterns:
        if pat.search(sec_name):
            return False
    if re.match(r"^([\d.]+)", sec_name):
        return True
    return True
 class TestHasSectionContent:
    """Unit tests for _has_section_content filtering logic."""
    def test_empty_section_single_char(self):
        """Section with only '无' (1 char) should be filtered out."""
        sec = {"source": "2.3 产品功能详细说明", "blocks": [
            {"type": "para", "text": "无", "index": 0}
        ]}
        assert not _has_section_content(sec)
    def test_empty_section_short_text(self):
        """Section with < 10 chars should be filtered out."""
        sec = {"source": "2.4 界面示意图", "blocks": [
            {"type": "para", "text": "参见图", "index": 0}
        ]}
        assert not _has_section_content(sec)
    def test_empty_section_multiple_short_paras(self):
        """Multiple short paras that sum < 10 each — still no content."""
        sec = {"source": "2.5 控件状态", "blocks": [
            {"type": "para", "text": "无", "index": 0},
            {"type": "para", "text": "", "index": 1},
        ]}
        assert not _has_section_content(sec)
    def test_section_with_table(self):
        """Section with a table block has content regardless of text."""
        sec = {"source": "3.1.1 功能表", "blocks": [
            {"type": "para", "text": "无", "index": 0},
            {"type": "table", "headers": ["功能"], "rows": [{"columns": []}]}
        ]}
        assert _has_section_content(sec)
    def test_section_with_image_block(self):
        """Section with an image block has content."""
        sec = {"source": "2.4 界面示意图", "blocks": [
            {"type": "image", "rid": "rId16"}
        ]}
        assert _has_section_content(sec)
    def test_section_with_meaningful_text(self):
        """Section with text >= 10 chars has content."""
        sec = {"source": "3.1.1 行车娱乐限制", "blocks": [
            {"type": "para", "text": "行车娱乐限制功能在车辆行驶时限制娱乐功能的使用。", "index": 0}
        ]}
        assert _has_section_content(sec)
    def test_section_with_exactly_10_chars(self):
        """Section with exactly 10 chars of text has content."""
        sec = {"source": "1.2.3", "blocks": [
            {"type": "para", "text": "0123456789", "index": 0}
        ]}
        assert _has_section_content(sec)
    def test_section_with_whitespace_only(self):
        """Section with only whitespace should be filtered out."""
        sec = {"source": "A", "blocks": [
            {"type": "para", "text": "     ", "index": 0}
        ]}
        assert not _has_section_content(sec)
    def test_section_with_no_blocks(self):
        """Section with no blocks at all should be filtered out."""
        sec = {"source": "2.6.1 硬件要求", "blocks": []}
        assert not _has_section_content(sec)
    def test_functional_section_filter_integration(self):
        """Integration: functional sections with content are kept, empty are filtered."""
        doc = {
            "sections": [
                {"source": "3.1.1 功能规则", "blocks": [
                    {"type": "para", "text": "详细的功能规则描述内容。", "index": 0}
                ]},
                {"source": "2.3 产品功能详细说明", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
                {"source": "2.4 界面示意图", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
                {"source": "文档背景", "blocks": [
                    {"type": "para", "text": "本文档描述行车娱乐限制功能。", "index": 0}
                ]},
            ],
            "image_analysis": []
        }
        func_sections = [
            s for s in doc["sections"]
            if _is_functional_section(s.get("source", ""))
            and _has_section_content(s)
        ]
        # 3.1.1 has text >= 10, keeps it
        # 2.3 has only "无", filtered out
        # 2.4 has only "无", filtered out
        # "文档背景" is non-functional pattern, filtered out
        assert len(func_sections) == 1
        assert func_sections[0]["source"] == "3.1.1 功能规则"
 class TestQuickValidateEmptySections:
    """Test that _quick_validate correctly handles empty sections."""
    def test_all_empty_sections_produce_coverage_warning(self):
        """When all sections are empty, coverage should be 0% and trigger warning."""
        doc = {
            "sections": [
                {"source": "2.3 产品功能详细说明", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
                {"source": "2.4 界面示意图", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
            ],
            "image_analysis": []
        }
        # Create a minimal valid semantic_index with at least one function_unit
        si = {
            "concepts": [{"name": "国内", "parent": None}],
            "function_units": [{
                "unit_id": "U1",
                "name": "测试单元",
                "path": ["国内", "系统限制", "前台打断"],
                "sources": [{"type": "para", "section": "2.3 产品功能详细说明"}]
            }]
        }
        passed, gaps = _quick_validate(si, doc)
        # Should have coverage_warnings because sections are counted but empty
        assert "coverage_warnings" in gaps
        # Section coverage should be 0% since both sections are empty (filtered out)
        # Actually wait — the current code filters by _has_section_content in func_sections,
        # so both sections are filtered out → 0 functional sections → coverage is 1/1=100%
        # Let me verify
        print(f"\n  DEBUG: passed={passed}, gaps={gaps}")
    def test_mixed_empty_and_real_sections(self):
        """Empty sections should not drag down coverage of real sections."""
        doc = {
            "sections": [
                {"source": "3.1.1 功能规则", "blocks": [
                    {"type": "para", "text": "详细功能规则描述，超过十个字符。", "index": 0}
                ]},
                {"source": "2.3 产品功能详细说明", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
                {"source": "2.4 界面示意图", "blocks": [
                    {"type": "para", "text": "无", "index": 0}
                ]},
            ],
            "image_analysis": []
        }
        si = {
            "concepts": [{"name": "国内", "parent": None}],
            "function_units": [{
                "unit_id": "U1",
                "name": "功能规则",
                "path": ["国内", "系统限制", "前台打断"],
                "sources": [{"type": "para", "section": "3.1.1 功能规则"}]
            }]
        }
        passed, gaps = _quick_validate(si, doc)
        # 3.1.1 has real content → 1 functional section, covered → 100%
        # 2.3 and 2.4 are empty → filtered out
        print(f"\n  DEBUG: passed={passed}, gaps={gaps}")
        # No coverage_warnings expected since the only functional section is covered
        assert not gaps.get("coverage_warnings"), \
            f"Expected no coverage warnings, got: {gaps.get('coverage_warnings')}"
 if __name__ == "__main__":
    success = run_all_tests()
    sys.exit(0 if success else 1)
@@ -351,15 +351,12 @@ def test_step2_rule_paths():
 def test_step2_precondition_fields():
-    """Warn: rules missing precondition fields (depends on LLM output, defense in step3)."""
+    """pytest: every rule must have precondition with geographic_scope and screen_type."""
    fragments = _load_fragments_or_skip()
    if fragments is None:
        pytest.skip("ir_fragments.json not found")
    errors = check_precondition_fields(fragments)
-    if errors:
+    assert not errors, f"precondition errors: {errors[:5]}"
        print(f"\n[WARN] {len(errors)} 个规则缺少 precondition 字段 (LLM 输出变异，step3 _normalize_rule 兜底)")
        for e in errors[:5]:
            print(f"  - {e}")
 def test_step2_user_interaction_content():
@@ -305,312 +305,3 @@ def test_step3_audit_report():
 if __name__ == "__main__":
    success = run_all_tests()
    sys.exit(0 if success else 1)
 # ═══════════════════════════════════════════════════════════════════════════════
 # Pure unit tests for step3 helper functions — no LLM output needed
 # ═══════════════════════════════════════════════════════════════════════════════
 from step3_merge_and_audit import rule_signature, _normalize_rule
 class TestRuleSignature:
    """Unit tests for rule_signature with edge cases."""
    def test_normal_rule(self):
        """Standard rule with valid trigger dict should produce a signature."""
        rule = {
            "path": ["国内", "系统限制", "前台打断"],
            "trigger": {
                "operator": "AND",
                "conditions": [
                    {"signal": "车速", "operator": ">=", "value": "5"},
                    {"signal": "档位", "operator": "==", "value": "D"}
                ]
            },
            "actions": [
                {"type": "system", "description": "弹出提示"}
            ]
        }
        sig = rule_signature(rule)
        assert isinstance(sig, str)
        assert len(sig) == 16  # sha256 hex digest[:16]
    def test_trigger_is_none(self):
        """Rule with trigger: None should not crash."""
        rule = {
            "path": ["国内", "系统限制", "前台打断"],
            "trigger": None,
            "actions": [
                {"type": "system", "description": "弹出提示"}
            ]
        }
        sig = rule_signature(rule)
        assert isinstance(sig, str)
        assert len(sig) == 16
    def test_trigger_key_missing(self):
        """Rule without trigger key should not crash."""
        rule = {
            "path": ["国内", "系统限制"],
            "actions": [
                {"type": "system", "description": "限制启动"}
            ]
        }
        sig = rule_signature(rule)
        assert isinstance(sig, str)
        assert len(sig) == 16
    def test_actions_is_none(self):
        """Rule with actions: None should not crash."""
        rule = {
            "path": ["国内"],
            "trigger": {"conditions": []},
            "actions": None
        }
        sig = rule_signature(rule)
        assert isinstance(sig, str)
        assert len(sig) == 16
    def test_trigger_is_empty_dict(self):
        """Rule with trigger: {} should work."""
        rule = {
            "path": ["海外", "SDK限制"],
            "trigger": {},
            "actions": []
        }
        sig = rule_signature(rule)
        assert isinstance(sig, str)
    def test_trigger_conditions_is_none(self):
        """Rule with trigger.conditions: None should not crash."""
        rule = {
            "path": [],
            "trigger": {"operator": "AND", "conditions": None},
            "actions": [{"description": "do nothing"}]
        }
        # This might still crash if conditions is None because .get("conditions", [])
        # returns None when the key exists with None value
        # But our fix is on the trigger level, not conditions level
        sig = rule_signature(rule)
        assert isinstance(sig, str)
    def test_deterministic_signature(self):
        """Same rule should produce the same signature every time."""
        rule = {
            "path": ["国内", "系统限制", "前台打断"],
            "trigger": {
                "operator": "OR",
                "conditions": [
                    {"signal": "车速", "operator": ">", "value": "0"}
                ]
            },
            "actions": [
                {"description": "test"}
            ]
        }
        sig1 = rule_signature(rule)
        sig2 = rule_signature(rule)
        assert sig1 == sig2
 class TestNormalizeRule:
    """Unit tests for _normalize_rule."""
    def test_normalize_null_trigger(self):
        """_normalize_rule should fix trigger: None."""
        rule = {"trigger": None, "actions": []}
        normalized = _normalize_rule(rule)
        # _normalize_rule fills in default trigger with conditions
        assert "trigger" in normalized
        assert normalized["trigger"]["operator"] == "AND"
        assert len(normalized["trigger"]["conditions"]) >= 1
        # After normalization, rule_signature should work
        sig = rule_signature(normalized)
        assert isinstance(sig, str)
    def test_normalize_missing_trigger(self):
        """_normalize_rule should add trigger if missing."""
        rule = {"actions": []}
        normalized = _normalize_rule(rule)
        assert "trigger" in normalized
        assert normalized["trigger"]["operator"] == "AND"
        assert len(normalized["trigger"]["conditions"]) >= 1
    def test_normalize_null_operator(self):
        """_normalize_rule should fix null operator in conditions."""
        rule = {
            "trigger": {
                "conditions": [
                    {"signal": "车速", "operator": None, "value": "5"}
                ]
            },
            "actions": []
        }
        normalized = _normalize_rule(rule)
        cond = normalized["trigger"]["conditions"][0]
        assert cond["operator"] == "=="
    def test_normalize_keeps_valid_rule(self):
        """_normalize_rule should not change a valid rule."""
        rule = {
            "trigger": {
                "operator": "AND",
                "conditions": [
                    {"signal": "车速", "operator": ">=", "value": "5"}
                ]
            },
            "actions": [{"type": "system", "description": "test"}]
        }
        normalized = _normalize_rule(rule)
        assert normalized["trigger"]["operator"] == "AND"
        assert normalized["trigger"]["conditions"][0]["operator"] == ">="
    def test_normalize_source_missing_section_from_sibling(self):
        """Table/text sources without section get it from sibling sources."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "table", "section": "3.1.1 系统限制", "row": 1},
                {"type": "text", "text_snippet": "missing section"},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][1]["section"] == "3.1.1 系统限制"
    def test_normalize_source_missing_section_from_path(self):
        """Table/text sources without section and no sibling fall back to rule path."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "path": "4.2 关闭流程 > decision_speed > action_disable",
            "sources": [
                {"type": "table", "row": 3, "text_snippet": "no section anywhere"},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["section"] == "4.2 关闭流程"
    def test_normalize_source_keeps_existing_section(self):
        """Sources that already have section are not modified."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "table", "section": "1.0 概述", "row": 1},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["section"] == "1.0 概述"
    def test_normalize_source_skips_logic_tree(self):
        """Logic tree sources are not touched (don't need section)."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "logic_tree", "image_id": "img1", "node_ids": ["n1"]},
            ],
        }
        normalized = _normalize_rule(rule)
        assert "section" not in normalized["sources"][0]
    def test_normalize_table_source_null_row(self):
        """Table source with null row gets row=0 (defensive)."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "table", "section": "3.1 功能", "row": None},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["row"] == 0
    def test_normalize_source_invalid_type(self):
        """Invalid source types (LLM hallucinations) are normalized to text."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "function_unit_description", "text_snippet": "desc",
                 "section": "3.1 功能"},
                {"type": "unknown_type", "text_snippet": "also invalid"},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["type"] == "text"
        assert normalized["sources"][1]["type"] == "text"
        assert normalized["sources"][0]["section"] == "3.1 功能"
    def test_normalize_empty_sources(self):
        """Rules with empty sources get a minimal text source (defensive)."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "path": "3.1 策略 > decision_speed",
            "sources": [],
        }
        normalized = _normalize_rule(rule)
        assert len(normalized["sources"]) == 1
        assert normalized["sources"][0]["type"] == "text"
        assert normalized["sources"][0]["section"] == "3.1 策略"
    def test_normalize_section_is_list(self):
        """Section field that is a list (LLM format bug) is normalized to string."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "sources": [
                {"type": "table", "section": ["状态", "系统设置"], "row": 1},
                {"type": "text", "section": ["后台限制"], "text_snippet": "x"},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["section"] == "状态"
        assert normalized["sources"][1]["section"] == "后台限制"
    def test_normalize_section_is_empty_list(self):
        """Empty list section falls back to rule path."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "path": "4.2 关闭流程 > decision",
            "sources": [
                {"type": "table", "section": [], "row": 1},
            ],
        }
        normalized = _normalize_rule(rule)
        assert normalized["sources"][0]["section"] == "4.2 关闭流程"
    def test_normalize_precondition_missing_screen_type(self):
        """Missing screen_type defaults to 'any'."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "precondition": {"geographic_scope": "国内"},
        }
        normalized = _normalize_rule(rule)
        assert normalized["precondition"]["screen_type"] == "any"
        assert normalized["precondition"]["geographic_scope"] == "国内"
    def test_normalize_precondition_missing_geo(self):
        """Missing geographic_scope defaults to 'global'."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "precondition": {"screen_type": "cluster"},
        }
        normalized = _normalize_rule(rule)
        assert normalized["precondition"]["geographic_scope"] == "global"
        assert normalized["precondition"]["screen_type"] == "cluster"
    def test_normalize_precondition_none(self):
        """None precondition is replaced with defaults."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
            "precondition": None,
        }
        normalized = _normalize_rule(rule)
        assert normalized["precondition"]["screen_type"] == "any"
        assert normalized["precondition"]["geographic_scope"] == "global"
    def test_normalize_precondition_missing(self):
        """Missing precondition key gets defaults."""
        rule = {
            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
        }
        normalized = _normalize_rule(rule)
        assert normalized["precondition"]["screen_type"] == "any"
        assert normalized["precondition"]["geographic_scope"] == "global"
@@ -140,32 +140,9 @@ def ir_path(request) -> str:
@pytest.fixture(scope="session")
 def ir_data(ir_path: str) -> dict:
-    """Load the IR JSON data, normalizing each rule for defensive schema fixes."""
+    """Load the IR JSON data."""
    with open(ir_path, "r", encoding="utf-8") as f:
-        data = json.load(f)
+        return json.load(f)
    # Apply normalize to every rule so old IR files benefit from latest fixes
    # (invalid source types, missing section fields, trigger nulls, etc.)
    sys.path.insert(0, str(_PROJECT_ROOT / "skills" / "ir_generation_skill"))
    from step3_merge_and_audit import _normalize_rule
    rules = data.get("rules", [])
    if rules:
        normalized = []
        for i, r in enumerate(rules):
            if not isinstance(r, dict):
                continue  # Skip non-dict entries defensively
            # Defensive: flatten list-type section fields (LLM produces these sometimes)
            for src in r.get("sources", []):
                sec = src.get("section")
                if isinstance(sec, list):
                    src["section"] = sec[0] if sec else ""
            try:
                normalized.append(_normalize_rule(r))
            except Exception:
                normalized.append(r)  # Fallback: use raw rule if normalize crashes
        data["rules"] = normalized
    return data
@pytest.fixture(scope="session")
@@ -137,18 +137,12 @@ def _extract_content_units(parsed_data: dict) -> dict:
    for sec in sections:
        name = sec.get("source", "")
-        is_func = _is_functional_section(name) and _has_section_content(sec)
+        if _is_functional_section(name) and _has_section_content(sec):
        if is_func:
            functional_sections.append({
                "name": name,
                "number": _section_number(name),
            })
        # Only count table rows from functional sections
        # (non-functional sections like changelog, glossary, references
        #  cannot be covered by function_units — counting them inflates
        #  the denominator and yields misleadingly low coverage.)
        if is_func:
        for block in sec.get("blocks", []):
            if block.get("type") == "table":
                rows = block.get("rows", [])
@@ -227,14 +221,10 @@ def _measure_coverage(ir_data: dict, parsed_data: dict) -> dict:
                if matched:
                    covered_sections.add(matched)
    def _safe_rate(covered: int, total: int) -> float:
        """Return coverage rate. total=0 means nothing to cover → 1.0."""
        return round(covered / total, 3) if total > 0 else 1.0
    section_coverage = {
        "total": len(func_sections),
        "covered": len(covered_sections),
-        "rate": _safe_rate(len(covered_sections), len(func_sections)),
+        "rate": round(len(covered_sections) / max(len(func_sections), 1), 3),
        "uncovered": [s["name"] for s in func_sections
                      if s["name"] not in covered_sections],
    }
@@ -253,7 +243,7 @@ def _measure_coverage(ir_data: dict, parsed_data: dict) -> dict:
    table_coverage = {
        "total_rows": total_rows,
        "covered_rows": len(covered_rows),
-        "rate": _safe_rate(len(covered_rows), total_rows),
+        "rate": round(len(covered_rows) / max(total_rows, 1), 3),
    }
    # ── diagram coverage ──
@@ -269,18 +259,16 @@ def _measure_coverage(ir_data: dict, parsed_data: dict) -> dict:
    diagram_coverage = {
        "total": len(diagram_rids),
        "covered": len(covered_rids),
-        "rate": _safe_rate(len(covered_rids), len(diagram_rids)),
+        "rate": round(len(covered_rids) / max(len(diagram_rids), 1), 3),
        "uncovered": [r for r in diagram_rids if r not in covered_rids],
    }
-    # ── overall: only include dimensions with actual content ──
+    # ── overall ──
-    rates: list[float] = []
+    rates = [
-    if section_coverage["total"] > 0:
+        section_coverage["rate"],
-        rates.append(section_coverage["rate"])
+        table_coverage["rate"],
-    if table_coverage["total_rows"] > 0:
+        diagram_coverage["rate"],
-        rates.append(table_coverage["rate"])
+    ]
    if diagram_coverage["total"] > 0:
        rates.append(diagram_coverage["rate"])
    overall = round(sum(rates) / len(rates), 3) if rates else 0.0
    return {
@@ -291,85 +279,6 @@ def _measure_coverage(ir_data: dict, parsed_data: dict) -> dict:
    }
 def test_measure_coverage_excludes_zero_dimensions():
    """#36: dimensions with total=0 must not drag down the overall rate.
    When diagram total=0, the overall should be computed from sections and tables
    only, not include a 0% diagram entry that makes the goal unreachable.
    """
    parsed_data = {
        "sections": [
            {"source": "3.1.1 功能A", "blocks": [
                {"type": "table", "rows": [{"cell": "1"}, {"cell": "2"}]}
            ]}
        ],
        "image_analysis": [],  # no diagrams → total=0
    }
    # IR that covers the section but no table rows (table coverage = 0/2)
    ir_data = {
        "rules": [
            {"sources": [{"section": "3.1.1"}]}  # 1 section covered, 0 tables
        ]
    }
    cov = _measure_coverage(ir_data, parsed_data)
    # Section: 1/1 = 100%, Table: 0/2 = 0%, Diagram: total=0 → excluded
    assert cov["section_coverage"]["total"] == 1
    assert cov["section_coverage"]["rate"] == 1.0
    assert cov["table_coverage"]["total_rows"] == 2
    assert cov["table_coverage"]["rate"] == 0.0
    assert cov["diagram_coverage"]["total"] == 0
    assert cov["diagram_coverage"]["rate"] == 1.0  # _safe_rate: 0/0 → 1.0
    # Key assertion: diagram (total=0) is excluded from overall
    # overall = (1.0 + 0.0) / 2 = 0.5
    # NOT (1.0 + 0.0 + 1.0) / 3 = 0.667
    assert cov["overall_rate"] == 0.5, (
        f"Expected overall 0.5 (sections + tables only), got {cov['overall_rate']}. "
        f"Zero-content dimension may be leaking into the average."
    )
 def test_measure_coverage_all_dimensions_have_content():
    """When all dimensions have content, all should be included."""
    parsed_data = {
        "sections": [
            {"source": "3.1.1 功能A", "blocks": [
                {"type": "table", "rows": [{"cell": "1"}]}
            ]}
        ],
        "image_analysis": [{"type": "flowchart", "rid": "img_001"}],
    }
    ir_data = {
        "rules": [
            {"sources": [{"section": "3.1.1"}]},
            {"sources": [{"type": "table", "section": "3.1.1", "row": 0}]},
            {"sources": [{"type": "logic_tree", "image_id": "img_001"}]},
        ]
    }
    cov = _measure_coverage(ir_data, parsed_data)
    # All three dimensions have content → all included
    assert cov["section_coverage"]["total"] == 1
    assert cov["table_coverage"]["total_rows"] == 1
    assert cov["diagram_coverage"]["total"] == 1
    # overall = (1.0 + 1.0 + 1.0) / 3 = 1.0
    assert cov["overall_rate"] == 1.0, (
        f"Expected overall 1.0 (all covered), got {cov['overall_rate']}"
    )
 def test_measure_coverage_no_content_returns_zero():
    """When no dimensions have content, overall should be 0.0."""
    parsed_data = {"sections": [], "image_analysis": []}
    ir_data = {"rules": []}
    cov = _measure_coverage(ir_data, parsed_data)
    assert cov["overall_rate"] == 0.0
 def test_layer_b_coverage(
    ir_data: dict,
    parsed_data: dict | None,
@@ -83,8 +83,8 @@ def test_output_dir_structure():
 def test_ensemble_temperatures_count():
-    """Should have exactly 4 ensemble temperatures."""
+    """Should have exactly 3 ensemble temperatures."""
-    assert len(config.ENSEMBLE_TEMPERATURES) == 4
+    assert len(config.ENSEMBLE_TEMPERATURES) == 3
 def test_max_tokens_is_int():