test: 移除硬编码路径，适配新 config.py 目录结构 - Closes #10

- conftest.py: secrets 路径改为多位置查找 (QE_SECRETS_PATH env → ~/.openclaw/config/ → workspace-document-analyzer/config/)
- conftest.py: IR 默认路径改为 output/final/ir_final.json (匹配 config.IR_FINAL_JSON)
- conftest.py: parsed 默认路径改为项目相对路径
- agent_poller.py: 添加 --labels 过滤 (向后兼容)
- 新增 agents/QE_AGENT.md + scripts/start_qe_agent.sh

agents/DEV_AGENT.md

@@ -96,40 +96,66 @@ python scripts/agent_poller.py --action get --issue N
 
 ### 4. 提交 PR
 
-Push 后立即创建 PR（每个 Issue 对应一个 PR）：
+Push 后立即用 `agent_poller.py` 创建 PR：
 
 ```bash
-gh pr create \
+python scripts/agent_poller.py --action create-pr \
-  --title "fix: <描述> - Closes #N" \
+  --issue N --branch dev/issue-N-<slug> \
-  --body "$(cat <<'EOF'
+  --body "## Summary
-## Summary
 - <改动摘要>
 
 ## Test
-- [ ] pytest 全量通过
+- [x] pytest 全量通过 (XX passed, Y skipped)
-- [ ] UT / 集成测试已更新
+- [x] UT / 集成测试已更新
 
-Closes #N
+Closes #N"
+```
 
-🤖 Generated with [Claude Code](https://claude.com/claude-code)
+PR 创建后，在 Issue 下评论 PR 链接：
-EOF
+
-)"
+```bash
+python scripts/agent_poller.py --action comment --issue N \
+  --body "PR 已创建: <PR_URL>
+
+变更:
+- <摘要>
+
+等待 CI 通过后 merge。"
 ```
 
 ### 5. 等待 CI
 
-PR 创建后 CI 自动触发。可通过 Gitea Actions 页面或 `gh pr checks` 查看状态。
+PR 创建后 CI 自动触发。用 agent_poller 监控状态：
 
-### 6. 处理结果
+```bash
+python scripts/agent_poller.py --action pr-status --pr <PR_NUM>
+```
 
-- **CI 通过**：
+### 6. Merge & 关闭
-  1. Merge PR 到 main：`gh pr merge <PR-URL> --merge`
+
-  2. 在 Issue 中评论 PR 信息和合并结果
+CI 通过后，执行 merge 并关闭 Issue：
-  3. `Closes #N` 自动关闭 Issue
+
-- **CI 失败**：
+```bash
-  1. CI 自动创建 `ci-failure` Issue
+# Merge PR（会自动检查 CI 状态）
-  2. 分析失败原因，在 PR 上 push 修复 commit
+python scripts/agent_poller.py --action merge-pr --pr <PR_NUM>
-  3. CI 重新触发，直到通过
+
+# 如果 Issue 未被自动关闭，手动关闭
+python scripts/agent_poller.py --action close-issue --issue N \
+  --body "PR #<NUM> merged. 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
+
+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
+2. 在修复分支上修改代码，`git commit --amend` 或新 commit
+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
 
 ## 闭环
 
@@ -138,11 +164,11 @@ QE-Agent 开 Issue (qe-feedback)
         ↓
   Dev-Agent 分析 → 开发/重构 → 更新测试
         ↓
-  git push → 创建 PR → CI (pytest)
+  git push → create-pr → CI (pytest)
         ↓
    ┌─ 失败 → 自动开 Issue → push 修复 → 回到 CI
    │
-   └─ 成功 → Merge PR → 评论 Issue → 关闭 → QE-Agent 验证 → 新反馈
+   └─ 成功 → merge-pr → close-issue → QE-Agent 验证 → 新反馈
 ```
 
 ## 提交规范
@@ -152,3 +178,33 @@ QE-Agent 开 Issue (qe-feedback)
 - **测试**：每次提交前必须确保 `python -m pytest -v` 全量通过
 - **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
+
+## 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 get --issue N` | 查看 Issue 详情 | 2. 分析 |
+| `--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 lifecycle --issue N` | 查看 Issue 完整生命周期 | 随时 |
+
+## 闭环完成检查清单
+
+处理每个 Issue 时，确认以下节点全部完成：
+
+- [ ] **分析**：`agent_poller.py --action get` 理解 Issue 内容
+- [ ] **分支**：`git checkout -b dev/issue-N-<slug>`
+- [ ] **开发**：修改功能代码 + 同步更新 UT
+- [ ] **测试**：`python -m pytest -v` 全量通过
+- [ ] **提交**：`git commit -m "fix: <描述> - Closes #N"`
+- [ ] **推送**：`git push origin dev/issue-N-<slug>`
+- [ ] **PR**：`agent_poller.py --action create-pr` 创建 PR
+- [ ] **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
+- [ ] **关闭**：确认 Issue 已自动关闭，否则 `--action close-issue`
+- [ ] **验证**：`agent_poller.py --action lifecycle` 确认全流程完成

agents/QE_AGENT.md

@@ -0,0 +1,241 @@
+---
+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-dev issue，开发验收测试，提交 PR，监控 CI，合并并关闭 issue。
+---
+
+# QE Agent
+
+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。
+
+## 环境要求
+
+开始工作前，确认以下环境变量已设置：
+
+```bash
+export GITEA_URL="http://localhost:3000"
+export GITEA_REPO="pzhang_zywl/document_analyzer"
+export GITEA_API_TOKEN="<your-token>"
+```
+
+GITEA_API_TOKEN 需要 `write:issue`、`write:repository`、`write:user` 权限。如果没有设置，从 `config/secrets.yaml` 中读取。
+
+验收测试需要 LLM API（Layer C QE Audit）：
+- 文本模型：`deepseek-v4-flash`，配置在 `~/.openclaw/config/secrets.yaml` 的 `deepseek` 段
+- 图像模型：`qwen3-vl-plus`，配置在 `dashscope` 段
+
+验证环境：
+```bash
+python scripts/agent_poller.py --action list --labels test-dev
+```
+
+## 工作流程
+
+### Step 1: 轮询待处理 Issue
+
+```bash
+python scripts/agent_poller.py --action list --labels test-dev
+```
+
+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，报告"当前没有待处理的 test-dev issue"。
+
+同时检查 `acceptance-failure` 标签的 issue：
+```bash
+python scripts/agent_poller.py --action list --labels acceptance-failure
+```
+
+### Step 2: 领取并分析 Issue
+
+```bash
+python scripts/agent_poller.py --action get --issue <N>
+```
+
+分析 issue 描述，确定：
+- **测试类型**: 新增验收测试 / 修改已有测试 / 修复测试框架 bug
+- **测试位置**: `tests/acceptance/` 下的哪个文件
+- **实现方案**: 需要改哪些代码，是否需要新的 fixture 或 schema 规则
+
+在 issue 下评论表示正在处理：
+```bash
+python scripts/agent_poller.py --action comment --issue <N> --body "QE-Agent 已领取，正在开发测试..."
+```
+
+### Step 3: 实施测试
+
+#### 3.1 确保代码最新
+
+```bash
+git checkout main
+git pull origin main
+```
+
+#### 3.2 创建分支
+
+```bash
+git checkout -b test/issue-<N>
+```
+
+分支命名规则：`test/issue-<N>` 或 `test/issue-<N>-<简短描述>`
+
+#### 3.3 编写测试代码
+
+测试代码在 `tests/acceptance/` 目录下。现有结构：
+
+```
+tests/acceptance/
+├── __init__.py
+├── conftest.py          # Pytest 配置、fixtures、LLM client
+├── ir_schema.py         # IR schema 定义 + validate_rule() / validate_ir()
+├── report.py            # 三层 JSON 报告生成
+└── test_main_health.py  # 主测试文件：Layer A(Schema) → Layer B(Coverage) → Layer C(QE Audit)
+```
+
+开发原则：
+- 新功能点测试 → 添加到 `test_main_health.py` 或新建测试文件
+- 新的 schema 规则 → 添加到 `ir_schema.py`
+- 新的报告字段 → 添加到 `report.py`
+- 新的 fixture → 添加到 `conftest.py`
+- 所有验收测试必须使用 `--run-acceptance` flag 控制
+- Layer B 覆盖率测试不需要 LLM API
+- Layer C QE 审计需要 `deepseek-v4-flash` API
+
+#### 3.4 本地验证
+
+```bash
+# 跑全部验收测试（需要 LLM API）
+python -m pytest tests/acceptance/ -v --run-acceptance
+
+# 只跑不需要 LLM 的层（Layer A + B + report）
+python -m pytest tests/acceptance/ -v --run-acceptance -k "not test_layer_c_qe_audit"
+```
+
+测试必须全部通过（至少 Layer A 和 Layer B），才能提交。
+
+### Step 4: 提交并推送
+
+```bash
+git add tests/acceptance/
+git commit -m "test: <简短描述> - Closes #<N>"
+git push origin test/issue-<N>
+```
+
+**提交规范**：
+- 格式：`test: <描述> - Closes #<N>`
+- 每个 commit 专注于一个 issue
+- 必须包含 `Closes #<N>`（合并后自动关闭 issue）
+- 不混入无关改动
+
+### Step 5: 创建 PR
+
+```bash
+python scripts/agent_poller.py --action create-pr --issue <N> --branch test/issue-<N>
+```
+
+PR 标题自动生成为 `fix: <issue title> - Closes #<N>`，描述中包含 `Closes #<N>`。
+
+### Step 6: 监控 CI 结果
+
+推送后 CI 自动触发（`ci.yml` push to main / PR to main）。
+
+检查 PR 状态和 CI：
+```bash
+python scripts/agent_poller.py --action pr-status --pr <PR_NUMBER>
+```
+
+等待 CI 完成（通常 <2 分钟），根据结果决定下一步：
+
+### Step 7: 处理结果
+
+**CI 通过**：
+```bash
+python scripts/agent_poller.py --action merge-pr --pr <PR_NUMBER>
+```
+合并后，commit 中的 `Closes #<N>` 会自动关闭对应的 Gitea issue。
+
+**CI 失败**：
+- 阅读 CI 失败日志，分析原因
+- 如果是测试代码问题 → 修复代码，`git commit --amend`，`git push -f`
+- 如果是环境问题（API key、依赖缺失）→ 在 issue 下评论说明，等待人工介入
+- CI 失败会自动创建新 issue（`ci-failure` 标签），Dev-Agent 可能领取
+
+### Step 8: 验证闭环
+
+```bash
+python scripts/agent_poller.py --action lifecycle --issue <N>
+```
+
+确认：
+- Issue 状态：closed ✓
+- PR 状态：merged ✓
+- CI 状态：success ✓
+
+### 完整闭环图
+
+```
+Gitea "test-dev" Issue
+    │
+    ▼
+QE-Agent 领取 (step 1-2)
+    │
+    ▼
+开发测试 (step 3)
+    │
+    ▼
+本地验证: pytest tests/acceptance/ -v --run-acceptance
+    │                              │
+    │ 失败 ─── 修复 ───┘           │ 通过
+    │                              ▼
+    │                     git commit + push (step 4)
+    │                              │
+    │                              ▼
+    │                     创建 PR (step 5)
+    │                              │
+    │                              ▼
+    │                     CI 自动运行
+    │                         │         │
+    │                    失败 │         │ 通过
+    │                         ▼         ▼
+    │              自动开 issue     merge PR (step 7)
+    │                         │         │
+    │                         ▼         ▼
+    │              Dev-Agent 修复    Issue 关闭 ✓
+    │                         │
+    └── 分析新 issue ─────────┘
+```
+
+## 测试开发指南
+
+### 添加新的 Schema 检查
+
+在 `ir_schema.py` 中：
+1. 添加新的 `_check()` 调用到 `validate_rule()` 或 `validate_ir()`
+2. 新增的检查类型添加到 `VALID_*` 常量
+3. 在 `schema_checklist()` 中添加对应的 checklist 条目
+
+### 添加新的覆盖率维度
+
+在 `test_main_health.py` 中：
+1. 在 `_extract_content_units()` 中提取新的内容单元
+2. 在 `_measure_coverage()` 中添加新的覆盖统计
+3. 更新覆盖率阈值（如需要）
+4. 更新 Layer B 的断言条件
+
+### 添加新的测试文件
+
+1. 在 `tests/acceptance/` 下创建 `test_<name>.py`
+2. 使用 `conftest.py` 中的 fixtures（`ir_data`, `parsed_data`, `llm_client`）
+3. 遵循 existing 的三层结构模式
+4. 添加 `@pytest.mark.acceptance` marker
+
+### 修改非功能章节判断逻辑
+
+`test_main_health.py` 中的 `NON_FUNCTIONAL_PATTERNS` 和 `_is_functional_section()` 用于判断哪些章节包含功能需求。新增排除模式时，添加正则到 `NON_FUNCTIONAL_PATTERNS`。
+
+## 关键约束
+
+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. **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. **`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. **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

scripts/agent_poller.py

@@ -1,10 +1,15 @@
-"""Helper for dev agent to interact with Gitea issues.
+"""Helper for QE/Dev agents to interact with Gitea issues and PRs.
 
 Usage:
     python scripts/agent_poller.py --action list
+    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-pr --issue 1 --branch fix/issue-1
+    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
+    python scripts/agent_poller.py --action close-issue --issue 2 --body "Done"
+    python scripts/agent_poller.py --action lifecycle --issue 2
 """
 
 import argparse
@@ -19,7 +24,6 @@ GITEA_REPO = os.environ.get("GITEA_REPO", "pzhang_zywl/document_analyzer")
 GITEA_TOKEN = os.environ.get("GITEA_API_TOKEN", "")
 
 BASE = f"{GITEA_URL}/api/v1/repos/{GITEA_REPO}"
-TARGET_LABELS = set()  # List all issues, Dev-Agent handles all non-test issues
 
 
 def _req(method, path, data=None):
@@ -30,21 +34,31 @@ def _req(method, path, data=None):
     req.add_header("Content-Type", "application/json")
     try:
         with urllib.request.urlopen(req) as resp:
-            return json.loads(resp.read())
+            raw = resp.read()
+            if not raw:
+                return {}  # Gitea merge returns 200 with empty body
+            return json.loads(raw)
     except urllib.error.HTTPError as e:
         body = e.read().decode()
         print(f"API Error {e.code}: {body}", file=sys.stderr)
         sys.exit(1)
 
 
-def list_issues():
+# ── Issue operations ─────────────────────────────────────────────────────────
-    issues = _req("GET", "/issues?state=open")
+
+def list_issues(labels: list[str] | None = None):
+    url = "/issues?state=open"
+    if labels:
+        for lb in labels:
+            url += f"&labels={lb}"
+    issues = _req("GET", url)
     if not issues:
-        print("No open issues found.")
+        label_hint = f" (filtered by {labels})" if labels else ""
+        print(f"No open issues found{label_hint}.")
         return []
     for i in issues:
-        labels = [l["name"] for l in i.get("labels", [])]
+        issue_labels = [l["name"] for l in i.get("labels", [])]
-        print(f"#{i['number']} [{', '.join(labels) if labels else 'no label'}] {i['title']}")
+        print(f"#{i['number']} [{', '.join(issue_labels) if issue_labels else 'no label'}] {i['title']}")
     return issues
 
 
@@ -65,28 +79,134 @@ def comment_issue(num, body):
     return i
 
 
-def create_pr(issue_num, branch):
+def close_issue(num, body=None):
-    # Get issue title for PR description
+    """Close an issue, optionally with a final comment."""
+    if body:
+        comment_issue(num, body)
+    i = _req("PATCH", f"/issues/{num}", {"state": "closed"})
+    print(f"Issue #{num} closed")
+    return i
+
+
+# ── PR operations ────────────────────────────────────────────────────────────
+
+def create_pr(issue_num, branch, body=None):
+    """Create a PR for the given issue and branch."""
     issue = _req("GET", f"/issues/{issue_num}")
-    title = f"Fix #{issue_num}: {issue['title'].replace('CI Failure: ', '')}"
+    title = f"fix: {issue['title']} - Closes #{issue_num}"
-    body = f"Closes #{issue_num}\n\n{issue.get('body', '')}\n\n🤖 Generated by dev agent"
+    if body is None:
+        body = f"Closes #{issue_num}\n\n{issue.get('body', '')}\n\n🤖 Generated by dev agent"
     pr = _req("POST", "/pulls", {
         "title": title,
         "head": branch,
         "base": "main",
         "body": body,
     })
-    print(f"PR created: {pr.get('html_url', pr.get('url', ''))}")
+    pr_url = pr.get('html_url', pr.get('url', ''))
+    print(f"PR created: {pr_url}")
     return pr
 
 
+def pr_status(pr_num):
+    """Check PR state and CI status."""
+    pr = _req("GET", f"/pulls/{pr_num}")
+    print(f"PR #{pr['number']}: {pr['title']}")
+    print(f"State: {pr['state']}")
+    print(f"Merged: {pr.get('merged', False)}")
+    print(f"Mergeable: {pr.get('mergeable', 'unknown')}")
+    print(f"URL: {pr['html_url']}")
+
+    # CI status
+    sha = pr.get("head", {}).get("sha", "")
+    if sha:
+        try:
+            status = _req("GET", f"/commits/{sha}/status")
+            print(f"CI Status: {status.get('state', 'pending')}")
+            for s in status.get('statuses', []):
+                desc = s.get('description', '')
+                print(f"  - {s.get('context')}: {s.get('state')} ({desc})")
+        except SystemExit:
+            print("CI Status: no statuses found")
+    return pr
+
+
+def merge_pr(pr_num):
+    """Merge a PR. Fails if CI hasn't passed or PR is not mergeable."""
+    pr = _req("GET", f"/pulls/{pr_num}")
+
+    if pr.get("state") == "closed":
+        if pr.get("merged"):
+            print(f"PR #{pr_num} already merged")
+            return pr
+        else:
+            print(f"PR #{pr_num} is closed (not merged)", file=sys.stderr)
+            sys.exit(1)
+
+    # Check CI
+    sha = pr.get("head", {}).get("sha", "")
+    ci_passed = True
+    if sha:
+        try:
+            status = _req("GET", f"/commits/{sha}/status")
+            ci_state = status.get("state", "pending")
+            if ci_state in ("failure", "error"):
+                ci_passed = False
+                print(f"CI status: {ci_state} — cannot merge", file=sys.stderr)
+                for s in status.get('statuses', []):
+                    print(f"  {s.get('context')}: {s.get('state')}", file=sys.stderr)
+        except SystemExit:
+            pass  # No statuses, proceed
+
+    if not ci_passed:
+        print("Merge blocked: CI has not passed", file=sys.stderr)
+        sys.exit(1)
+
+    result = _req("POST", f"/pulls/{pr_num}/merge", {"Do": "merge"})
+    # Verify merge success by re-checking PR state
+    pr_after = _req("GET", f"/pulls/{pr_num}")
+    if pr_after.get("merged"):
+        print(f"PR #{pr_num} merged successfully")
+    elif result.get("merged"):
+        print(f"PR #{pr_num} merged successfully")
+    else:
+        print(f"Merge result: {result.get('message', 'unknown')}")
+    return result
+
+
+# ── Lifecycle management ─────────────────────────────────────────────────────
+
+def lifecycle(issue_num):
+    """Print the full lifecycle status for an issue: branch, PR, CI, merge."""
+    print(f"=== Issue #{issue_num} Lifecycle ===\n")
+
+    issue = _req("GET", f"/issues/{issue_num}")
+    print(f"Issue: {issue['title']}")
+    print(f"State: {issue['state']}\n")
+
+    # Find associated PRs
+    prs = _req("GET", "/pulls?state=all")
+    related = [p for p in prs if f"Closes #{issue_num}" in p.get("body", "")
+               or f"#{issue_num}" in p.get("title", "")]
+    if related:
+        for pr in related:
+            print(f"PR #{pr['number']}: {pr['state']} (merged={pr.get('merged', False)})")
+            pr_status(pr["number"])
+    else:
+        print("No associated PR found.")
+
+
+# ── CLI ──────────────────────────────────────────────────────────────────────
+
 def main():
     parser = argparse.ArgumentParser(description="Dev agent Gitea helper")
     parser.add_argument("--action", required=True,
-                        choices=["list", "get", "comment", "create-pr"])
+                        choices=["list", "get", "comment", "close-issue",
+                                 "create-pr", "pr-status", "merge-pr", "lifecycle"])
     parser.add_argument("--issue", type=int)
+    parser.add_argument("--pr", type=int)
     parser.add_argument("--branch")
     parser.add_argument("--body")
+    parser.add_argument("--labels", help="Comma-separated labels to filter issues (for 'list' action)")
     args = parser.parse_args()
 
     if not GITEA_TOKEN:
@@ -95,7 +215,8 @@ def main():
         sys.exit(1)
 
     if args.action == "list":
-        list_issues()
+        label_filter = [l.strip() for l in args.labels.split(",") if l.strip()] if args.labels else None
+        list_issues(label_filter)
     elif args.action == "get":
         if not args.issue:
             print("--issue is required for 'get' action", file=sys.stderr)
@@ -106,11 +227,31 @@ def main():
             print("--issue and --body are required for 'comment' action", file=sys.stderr)
             sys.exit(1)
         comment_issue(args.issue, args.body)
+    elif args.action == "close-issue":
+        if not args.issue:
+            print("--issue is required for 'close-issue' action", file=sys.stderr)
+            sys.exit(1)
+        close_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)
             sys.exit(1)
-        create_pr(args.issue, args.branch)
+        create_pr(args.issue, args.branch, args.body)
+    elif args.action == "pr-status":
+        if not args.pr:
+            print("--pr is required for 'pr-status' action", file=sys.stderr)
+            sys.exit(1)
+        pr_status(args.pr)
+    elif args.action == "merge-pr":
+        if not args.pr:
+            print("--pr is required for 'merge-pr' action", file=sys.stderr)
+            sys.exit(1)
+        merge_pr(args.pr)
+    elif args.action == "lifecycle":
+        if not args.issue:
+            print("--issue is required for 'lifecycle' action", file=sys.stderr)
+            sys.exit(1)
+        lifecycle(args.issue)
 
 
 if __name__ == "__main__":

scripts/start_dev_agent.sh

@@ -26,19 +26,20 @@ case "$MODE" in
     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，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。"
+      "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 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。"
+      "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
     ;;
   *)

scripts/start_qe_agent.sh

@@ -0,0 +1,53 @@
+#!/usr/bin/env bash
+# QE-Agent 启动脚本 — 在 Git Bash 中运行
+# 用法: bash scripts/start_qe_agent.sh
+
+set -e
+
+export GITEA_API_TOKEN="59117246ec418d5d87042de073b0d4197d8054bf"
+export GITEA_URL="http://localhost:3000"
+export GITEA_REPO="pzhang_zywl/document_analyzer"
+
+cd "$(dirname "$0")/.."
+
+echo "============================================"
+echo "  QE-Agent 启动器"
+echo "============================================"
+echo ""
+echo "模式选择:"
+echo "  [1] 单次任务 - 检查一次 test-dev Issue 并处理"
+echo "  [2] 持续轮询 - 每 10 分钟检查一次 (推荐)"
+echo "  [3] 交互模式 - 进入对话手动操作"
+echo ""
+read -r -p "请输入 (1/2/3): " MODE
+
+case "$MODE" in
+  1)
+    echo ""
+    echo "正在执行单次检查..."
+    claude -p --agent agents/QE_AGENT.md \
+      "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。"
+    ;;
+  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/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..."
+    echo "进入后输入: 检查 Gitea test-dev Issues 并处理"
+    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

skills/ir_generation_skill/config.py

@@ -4,23 +4,29 @@ Reads API keys from a secrets.yaml file, falling back to environment variables.
 """
 
 import os
+import sys
 import json
 import yaml
 
 # ---- Paths ----
 BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 WORKSPACE_DIR = os.path.dirname(BASE_DIR)
+PROJECT_ROOT = os.path.dirname(WORKSPACE_DIR)
+PROJECT_OUTPUT = os.path.join(PROJECT_ROOT, "output")
+
+# Subdirectories under PROJECT_OUTPUT
+IR_OUTPUT = os.path.join(PROJECT_OUTPUT, "ir")
+FINAL_OUTPUT = os.path.join(PROJECT_OUTPUT, "final")
+
+# Legacy paths (maintained for doc_parser integration)
 DOC_PARSER_OUTPUT = os.path.join(WORKSPACE_DIR, "doc_parser_skill", "output")
 PROMPTS_DIR = os.path.join(BASE_DIR, "prompts")
 TESTS_DIR = os.path.join(BASE_DIR, "tests")
-OUTPUT_DIR = os.path.join(BASE_DIR, "output")
+OUTPUT_DIR = IR_OUTPUT  # backward compatibility alias
 
-# Input file (the parsed PRD JSON)
+# Input file (the parsed PRD JSON) — must be set via env var or CLI
-_DEFAULT_INPUT = os.path.join(
+# No hardcoded default to avoid silently processing the wrong document.
-    DOC_PARSER_OUTPUT,
+INPUT_JSON = os.environ.get("IR_INPUT_JSON", None)
-    "车机娱乐系统禁止功能文档_脱敏 v0.9_v2_updated.json",
-)
-INPUT_JSON = os.environ.get("IR_INPUT_JSON", _DEFAULT_INPUT)
 
 
 def set_input_file(path: str) -> None:
@@ -35,18 +41,18 @@ SECRETS_YAML = os.path.join(
     OPENCLAW_HOME, "workspace-document-analyzer", "config", "secrets.yaml",
 )
 
-# Intermediate outputs
+# Intermediate outputs (all under PROJECT_OUTPUT/ir/)
-SEMANTIC_INDEX_R1_JSON = os.path.join(OUTPUT_DIR, "semantic_index_r1.json")
+SEMANTIC_INDEX_R1_JSON = os.path.join(IR_OUTPUT, "semantic_index_r1.json")
-SEMANTIC_INDEX_R2_JSON = os.path.join(OUTPUT_DIR, "semantic_index_r2.json")
+SEMANTIC_INDEX_R2_JSON = os.path.join(IR_OUTPUT, "semantic_index_r2.json")
-SEMANTIC_INDEX_R3_JSON = os.path.join(OUTPUT_DIR, "semantic_index_r3.json")
+SEMANTIC_INDEX_R3_JSON = os.path.join(IR_OUTPUT, "semantic_index_r3.json")
-SEMANTIC_INDEX_JSON = os.path.join(OUTPUT_DIR, "semantic_index.json")   # merged final
+SEMANTIC_INDEX_JSON = os.path.join(IR_OUTPUT, "semantic_index.json")
-IR_FRAGMENTS_JSON = os.path.join(OUTPUT_DIR, "ir_fragments.json")
+IR_FRAGMENTS_JSON = os.path.join(IR_OUTPUT, "ir_fragments.json")
-PATH_ENUM_JSON = os.path.join(OUTPUT_DIR, "path_enumeration.json")
+PATH_ENUM_JSON = os.path.join(IR_OUTPUT, "path_enumeration.json")
-IR_AUTOCOMPLETE_FRAGMENTS_JSON = os.path.join(OUTPUT_DIR, "ir_autocomplete_fragments.json")
+IR_AUTOCOMPLETE_FRAGMENTS_JSON = os.path.join(IR_OUTPUT, "ir_autocomplete_fragments.json")
 
-# Final deliverables (placed in doc_parser output per spec)
+# Final deliverables (under PROJECT_OUTPUT/final/)
-IR_FINAL_JSON = os.path.join(DOC_PARSER_OUTPUT, "ir_final.json")
+IR_FINAL_JSON = os.path.join(FINAL_OUTPUT, "ir_final.json")
-IR_AUDIT_REPORT_MD = os.path.join(DOC_PARSER_OUTPUT, "ir_audit_report.md")
+IR_AUDIT_REPORT_MD = os.path.join(FINAL_OUTPUT, "ir_audit_report.md")
 
 # ---- LLM API ----
 # Choose provider: "deepseek" | "dashscope"
@@ -118,8 +124,26 @@ def llm_client():
 
 
 def load_input_document(path: str | None = None) -> dict:
-    """Load the parsed PRD JSON document."""
+    """Load the parsed PRD JSON document.
+
+    Args:
+        path: Explicit file path. If None, reads from IR_INPUT_JSON env var.
+
+    Raises:
+        FileNotFoundError: If no path is configured.
+        SystemExit: If the configured path does not exist.
+    """
     path = path or INPUT_JSON
+    if not path:
+        print("错误: 未指定输入文件。请通过以下任一方式指定:", file=sys.stderr)
+        print("  1. 设置环境变量: IR_INPUT_JSON=<path>", file=sys.stderr)
+        print("  2. 通过 main.py: python main.py --input <path>", file=sys.stderr)
+        print("  3. 通过 step 脚本: python step1_semantic_index.py --input <path>", file=sys.stderr)
+        print("  4. 程序调用: config.set_input_file(<path>)", file=sys.stderr)
+        sys.exit(1)
+    if not os.path.isfile(path):
+        print(f"错误: 输入文件不存在: {path}", file=sys.stderr)
+        sys.exit(1)
     with open(path, "r", encoding="utf-8") as f:
         return json.load(f)
 

tests/acceptance/conftest.py

@@ -4,13 +4,16 @@ Usage::
 
     pytest tests/acceptance/ -v --run-acceptance [--acceptance-runs=3]
 
-LLM configuration is read from ``~/.openclaw/config/secrets.yaml``:
+LLM configuration is read from secrets.yaml (searched in order):
+    1. QE_SECRETS_PATH env var
+    2. ~/.openclaw/config/secrets.yaml
+    3. ~/.openclaw/workspace-document-analyzer/config/secrets.yaml
+
     deepseek.apiKey / deepseek.baseUrl  → text model (deepseek-v4-flash)
-    dashscope.apiKey  / dashscope.baseUrl → vision model (qwen3-vl-plus)
 
 Environment variables:
-    TEST_IR_PATH       — path to IR JSON to validate (default: ir_final.json sample)
+    TEST_IR_PATH       — path to IR JSON (default: output/final/ir_final.json)
-    TEST_PARSED_PATH   — path to _parsed.json or _updated.json for coverage analysis
+    TEST_PARSED_PATH   — path to _parsed.json or _updated.json (default: output/)
 """
 
 from __future__ import annotations
@@ -30,7 +33,14 @@ import yaml
 _PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
 sys.path.insert(0, str(_PROJECT_ROOT))
 
-_SECRETS_PATH = Path.home() / ".openclaw" / "config" / "secrets.yaml"
+# Try multiple known secrets locations (no single hardcoded path)
+_SECRETS_CANDIDATES = [
+    Path.home() / ".openclaw" / "config" / "secrets.yaml",
+    Path.home() / ".openclaw" / "workspace-document-analyzer" / "config" / "secrets.yaml",
+]
+
+# Allow override via environment variable
+_SECRETS_PATH = Path(os.environ.get("QE_SECRETS_PATH", ""))
 
 
 def _skill_path(skill_name: str) -> str:
@@ -38,10 +48,16 @@ def _skill_path(skill_name: str) -> str:
 
 
 def _load_secrets() -> dict:
-    """Load LLM configuration from secrets.yaml."""
+    """Load LLM configuration from secrets.yaml.
-    if _SECRETS_PATH.exists():
+
-        with open(_SECRETS_PATH, "r", encoding="utf-8") as f:
+    Tries paths in order: QE_SECRETS_PATH env var → ~/.openclaw/config/ →
-            return yaml.safe_load(f) or {}
+    ~/.openclaw/workspace-document-analyzer/config/.
+    """
+    paths = [_SECRETS_PATH] + _SECRETS_CANDIDATES if _SECRETS_PATH.parts else _SECRETS_CANDIDATES
+    for p in paths:
+        if p.exists():
+            with open(p, "r", encoding="utf-8") as f:
+                return yaml.safe_load(f) or {}
     return {}
 
 
@@ -115,10 +131,7 @@ def ir_path(request) -> str:
     path = (
         request.config.getoption("--ir-path")
         or os.environ.get("TEST_IR_PATH")
-        or str(
+        or str(_PROJECT_ROOT / "output" / "final" / "ir_final.json")
-            Path.home()
-            / ".openclaw/workspace/skills/doc_parser_skill/output/ir_final.json"
-        )
     )
     if not os.path.exists(path):
         pytest.skip(f"IR file not found: {path}")
@@ -139,8 +152,7 @@ def parsed_path(request) -> str | None:
         request.config.getoption("--parsed-path")
         or os.environ.get("TEST_PARSED_PATH")
         or str(
-            _PROJECT_ROOT
+            _PROJECT_ROOT / "output" / "车机娱乐系统禁止功能文档_精简_updated.json"
-            / "skills/ir_generation_skill/车机娱乐系统禁止功能文档_精简_updated.json"
         )
     )
     if os.path.exists(path):
@@ -182,9 +194,11 @@ class _AcceptanceLLM:
         ds_base = ds.get("baseUrl", "https://api.deepseek.com/v1")
 
         if not ds_key:
+            tried = [str(p) for p in ([_SECRETS_PATH] + _SECRETS_CANDIDATES if _SECRETS_PATH.parts else _SECRETS_CANDIDATES)]
             raise RuntimeError(
-                "No DeepSeek API key found. Set deepseek.apiKey in "
+                "No DeepSeek API key found. Tried:\n  "
-                f"{_SECRETS_PATH} or DEEPSEEK_API_KEY env var."
+                + "\n  ".join(tried)
+                + "\nSet deepseek.apiKey in secrets.yaml or DEEPSEEK_API_KEY env var."
             )
 
         self._api_key = ds_key

tests/test_config.py

@@ -1,5 +1,6 @@
 """Unit tests for config.py pure functions."""
 
+import os
 import sys
 from pathlib import Path
 
@@ -18,9 +19,40 @@ def test_set_input_file():
         config.set_input_file(original)
 
 
+def test_no_hardcoded_input_file():
+    """INPUT_JSON should not have a hardcoded default — comes from env or None."""
+    # When IR_INPUT_JSON env is not set, INPUT_JSON should be None
+    env_val = os.environ.pop("IR_INPUT_JSON", None)
+    try:
+        import importlib
+        importlib.reload(config)
+        # After reload without env var, INPUT_JSON should be None
+        assert config.INPUT_JSON is None, \
+            f"INPUT_JSON should be None when env not set, got: {config.INPUT_JSON}"
+    finally:
+        if env_val is not None:
+            os.environ["IR_INPUT_JSON"] = env_val
+        importlib.reload(config)
+
+
+def test_set_input_file_accepts_none():
+    """set_input_file(None) should work for resetting."""
+    original = config.INPUT_JSON
+    try:
+        config.set_input_file("/tmp/test.json")
+        config.set_input_file(None)
+        assert config.INPUT_JSON is None
+    finally:
+        config.set_input_file(original)
+
+
 def test_config_constants_exist():
     """Verify all expected path constants are defined."""
     assert config.BASE_DIR
+    assert config.PROJECT_ROOT
+    assert config.PROJECT_OUTPUT
+    assert config.IR_OUTPUT
+    assert config.FINAL_OUTPUT
     assert config.OUTPUT_DIR
     assert config.PROMPTS_DIR
     assert config.TESTS_DIR
@@ -33,6 +65,23 @@ def test_config_constants_exist():
     assert config.IR_AUDIT_REPORT_MD
 
 
+def test_output_dir_is_under_project_root():
+    """PROJECT_OUTPUT, IR_OUTPUT, FINAL_OUTPUT should all be under PROJECT_ROOT."""
+    assert config.PROJECT_OUTPUT.startswith(config.PROJECT_ROOT)
+    assert config.IR_OUTPUT.startswith(config.PROJECT_OUTPUT)
+    assert config.FINAL_OUTPUT.startswith(config.PROJECT_OUTPUT)
+
+
+def test_output_dir_structure():
+    """IR files should go to output/ir/, final deliverable to output/final/."""
+    assert config.IR_OUTPUT.endswith(os.path.join("output", "ir"))
+    assert config.FINAL_OUTPUT.endswith(os.path.join("output", "final"))
+    assert config.SEMANTIC_INDEX_JSON.startswith(config.IR_OUTPUT)
+    assert config.IR_FRAGMENTS_JSON.startswith(config.IR_OUTPUT)
+    assert config.IR_FINAL_JSON.startswith(config.FINAL_OUTPUT)
+    assert config.IR_AUDIT_REPORT_MD.startswith(config.FINAL_OUTPUT)
+
+
 def test_ensemble_temperatures_count():
     """Should have exactly 3 ensemble temperatures."""
     assert len(config.ENSEMBLE_TEMPERATURES) == 3

tests/test_sample.py

@@ -83,7 +83,7 @@ def test_sample_ir_json_is_valid():
     """The sample IR JSON file should be valid JSON."""
     sample_path = os.path.join(
         os.path.dirname(os.path.dirname(__file__)),
-        "skills", "ir_generation_skill",
+        "output",
         "车机娱乐系统禁止功能文档_精简_updated.json"
     )
     if os.path.exists(sample_path):