Compare commits
78 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| f74ae30d41 | |||
| 67b504c5db | |||
| 230b8c9cd9 | |||
| 5b73319aaf | |||
| 8c7c277167 | |||
| 999cd1cc10 | |||
| 0475e40529 | |||
| ca9b750656 | |||
| 7e832ee865 | |||
| 1c7be0e782 | |||
| 49d0b3a789 | |||
| 5505ac9c5c | |||
| f5bf671410 | |||
| ccb5d5d3ea | |||
| ee825db818 | |||
| cdf984aa0c | |||
| 6798f098b5 | |||
| 33e38254c1 | |||
| 166172e0b8 | |||
| 0bd1caff90 | |||
| f615326514 | |||
| c2c6c9a7f6 | |||
| f26de6cfda | |||
| 1ff4d98a03 | |||
| a953fc0bc7 | |||
| 7f17ee69d7 | |||
| f1e513cba2 | |||
| 627982db09 | |||
| 9ec601d747 | |||
| cc5c7f5ad1 | |||
| d6cb854f68 | |||
| 1f373d5cb5 | |||
| a8c9d25857 | |||
| 660ac4b659 | |||
| 91685ebfdd | |||
| 65910f5417 | |||
| 17b87290c8 | |||
| bd5735f970 | |||
| 05f9112fab | |||
| b926b35703 | |||
| 8df1d4a83c | |||
| aad5a6b317 | |||
| ad34750075 | |||
| cd7e24cd3c | |||
| 0521b7b6f0 | |||
| fc30f91183 | |||
| 8c72ff0565 | |||
| cc2e5aa64c | |||
| d09fd4a173 | |||
| 5db4c89fe7 | |||
| e70816a69f | |||
| 33521b8b39 | |||
| f55a037c98 | |||
| 923971ad92 | |||
| 3f07c528b6 | |||
| 207c2aaaef | |||
| a89a70a983 | |||
| 1c939bfa27 | |||
| 080d1d0b23 | |||
| d1ef64b5cc | |||
| e83ad1de73 | |||
| a27ea8ed89 | |||
| 146816303f | |||
| 11349b5225 | |||
| a037497053 | |||
| f6f26d7763 | |||
| 920bc75c53 | |||
| 976d9ce7c8 | |||
| fd3a889fae | |||
| 925ebe8556 | |||
| 4ef9f68ff3 | |||
| 50d1d0b5e6 | |||
| 6e6b52fe3b | |||
| 3bca794902 | |||
| a5d5d2d974 | |||
| 3b9ad83405 | |||
| c89863a288 | |||
| 90f4e3284c |
@@ -0,0 +1,34 @@
|
||||
name: Bug 报告
|
||||
about: 报告一个 Bug
|
||||
title: "[moz] bug: "
|
||||
labels:
|
||||
- type/bug
|
||||
body:
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: Bug 描述
|
||||
description: 清晰描述什么行为是错误的
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: reproduce
|
||||
attributes:
|
||||
label: 复现步骤
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: expected
|
||||
attributes:
|
||||
label: 预期行为
|
||||
validations:
|
||||
required: true
|
||||
- type: dropdown
|
||||
id: priority
|
||||
attributes:
|
||||
label: 优先级
|
||||
options:
|
||||
- P0 紧急
|
||||
- P1 高
|
||||
- P2 中
|
||||
- P3 低
|
||||
@@ -0,0 +1,27 @@
|
||||
name: 功能需求
|
||||
about: 提出一个新功能需求
|
||||
title: "[moz] feat: "
|
||||
labels:
|
||||
- type/feat
|
||||
body:
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: 需求描述
|
||||
description: 你希望实现什么功能?为什么需要?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: solution
|
||||
attributes:
|
||||
label: 建议方案
|
||||
description: 如果有初步想法可以写 here
|
||||
- type: dropdown
|
||||
id: priority
|
||||
attributes:
|
||||
label: 优先级
|
||||
options:
|
||||
- P0 紧急
|
||||
- P1 高
|
||||
- P2 中
|
||||
- P3 低
|
||||
@@ -0,0 +1,20 @@
|
||||
name: 测试任务
|
||||
about: 创建一个测试任务(E2E、集成测试等)
|
||||
title: "[moz] test: "
|
||||
labels:
|
||||
- type/test
|
||||
body:
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: 测试目标
|
||||
description: 要验证什么场景?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: steps
|
||||
attributes:
|
||||
label: 测试步骤
|
||||
description: 关键步骤或验收标准
|
||||
validations:
|
||||
required: true
|
||||
@@ -0,0 +1,26 @@
|
||||
## 改动概述
|
||||
|
||||
<!-- 一句话说明这个 PR 做了什么 -->
|
||||
|
||||
## 关联 Issue
|
||||
|
||||
<!-- #issue_number,如果没有关联可删掉 -->
|
||||
|
||||
## 改动类型
|
||||
|
||||
- [ ] feat: 新功能
|
||||
- [ ] impl: 实现
|
||||
- [ ] fix: 修复
|
||||
- [ ] docs: 文档
|
||||
- [ ] test: 测试
|
||||
- [ ] refactor: 重构
|
||||
- [ ] ci: CI/CD
|
||||
- [ ] chore: 杂项
|
||||
|
||||
## 检查清单
|
||||
|
||||
- [ ] 标题格式正确:`[代号] type(scope): 简述`
|
||||
- [ ] 改动在开发目录(`~/.openclaw/sanguo_projects/`)完成
|
||||
- [ ] 已同步到安装目录(`~/.sanguo_projects/`)
|
||||
- [ ] 已运行测试(如适用)
|
||||
- [ ] 已更新相关设计文档(如适用)
|
||||
+39
-5
@@ -26,7 +26,9 @@ jobs:
|
||||
|
||||
- name: Setup Python
|
||||
run: |
|
||||
rm -rf /tmp/ci-venv-lint
|
||||
python3 -m venv /tmp/ci-venv-lint
|
||||
/tmp/ci-venv-lint/bin/pip install --quiet --upgrade pip
|
||||
/tmp/ci-venv-lint/bin/pip install --quiet flake8
|
||||
|
||||
- name: Lint with flake8
|
||||
@@ -42,19 +44,49 @@ jobs:
|
||||
|
||||
- name: Setup Python
|
||||
run: |
|
||||
rm -rf /tmp/ci-venv-test
|
||||
python3 -m venv /tmp/ci-venv-test
|
||||
/tmp/ci-venv-test/bin/pip install --quiet fastapi pydantic pyyaml uvicorn requests pytest pytest-asyncio httpx
|
||||
/tmp/ci-venv-test/bin/pip install --quiet --upgrade pip
|
||||
/tmp/ci-venv-test/bin/pip install --quiet --no-cache-dir fastapi pydantic pyyaml uvicorn requests pytest pytest-asyncio httpx
|
||||
|
||||
- name: Debug environment
|
||||
run: |
|
||||
echo "PWD=$(pwd)"
|
||||
echo "PYTHONPATH=$PYTHONPATH"
|
||||
python3 -c "import sys; [print(p) for p in sys.path if 'sanguo' in p.lower() or 'openclaw' in p.lower()]"
|
||||
grep -c "assignee = agent_id" src/daemon/toolchain_handler.py || true
|
||||
grep -c "_BUSINESS_FAIL_THRESHOLD" src/daemon/toolchain_handler.py || true
|
||||
|
||||
- name: Run tests (exclude E2E)
|
||||
run: |
|
||||
/tmp/ci-venv-test/bin/pytest tests/ -m "not e2e" -x -q
|
||||
PYTHONPATH=$(pwd) /tmp/ci-venv-test/bin/pytest tests/ -m "not e2e" -x -q || \
|
||||
(echo '=== RETRY WITH VERBOSE ===' && \
|
||||
PYTHONPATH=$(pwd) /tmp/ci-venv-test/bin/pytest tests/ -m "not e2e" -x -v 2>&1 | tail -30)
|
||||
|
||||
# ── Job 3: CI 失败通知 ───────────────────────────────
|
||||
# ── Job 3: Frontend Build ───────────────────────────
|
||||
frontend:
|
||||
runs-on: macos-arm64
|
||||
needs: lint
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Node
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 20
|
||||
|
||||
- name: Install & Build
|
||||
run: |
|
||||
cd src/frontend
|
||||
npm ci || npm install
|
||||
npm run build
|
||||
|
||||
# ── Job 4: CI 失败通知 ───────────────────────────────
|
||||
# 使用 needs.<job>.result 直接判断,不查询 commit status API
|
||||
# 根因:notify 自身的 pending status 会污染 commit status 查询结果(竞态条件)
|
||||
notify-on-failure:
|
||||
runs-on: macos-arm64
|
||||
needs: [lint, test]
|
||||
needs: [lint, test, frontend]
|
||||
if: always()
|
||||
steps:
|
||||
- name: Check results and notify
|
||||
@@ -62,12 +94,13 @@ jobs:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
LINT_RESULT: ${{ needs.lint.result }}
|
||||
TEST_RESULT: ${{ needs.test.result }}
|
||||
FRONTEND_RESULT: ${{ needs.frontend.result }}
|
||||
run: |
|
||||
echo "Lint result: $LINT_RESULT"
|
||||
echo "Test result: $TEST_RESULT"
|
||||
|
||||
# 只有 lint 或 test 明确失败时才发通知
|
||||
if [ "$LINT_RESULT" = "failure" ] || [ "$TEST_RESULT" = "failure" ]; then
|
||||
if [ "$LINT_RESULT" = "failure" ] || [ "$TEST_RESULT" = "failure" ] || [ "$FRONTEND_RESULT" = "failure" ]; then
|
||||
echo "CI has failures, sending notification..."
|
||||
|
||||
# 如果是 PR 事件,写评论通知
|
||||
@@ -77,6 +110,7 @@ jobs:
|
||||
FAILED_JOBS=""
|
||||
[ "$LINT_RESULT" = "failure" ] && FAILED_JOBS="${FAILED_JOBS}lint "
|
||||
[ "$TEST_RESULT" = "failure" ] && FAILED_JOBS="${FAILED_JOBS}test "
|
||||
[ "$FRONTEND_RESULT" = "failure" ] && FAILED_JOBS="${FAILED_JOBS}frontend "
|
||||
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token $GITEA_TOKEN" \
|
||||
|
||||
@@ -110,15 +110,7 @@ jobs:
|
||||
PR_AUTHOR=$(curl --max-time 5 -sf \
|
||||
-H "Authorization: token $GITEA_TOKEN" \
|
||||
"$API_URL/repos/$REPO/pulls?state=closed&sort=updated&order=desc&limit=10" | \
|
||||
python3 -c "
|
||||
import json, sys
|
||||
sha = '$COMMIT_SHA'
|
||||
for pr in json.load(sys.stdin):
|
||||
merge_sha = pr.get('merge_commit_sha', '') or ''
|
||||
if merge_sha.startswith(sha) or sha.startswith(merge_sha):
|
||||
print(pr['user']['login'])
|
||||
break
|
||||
" 2>/dev/null || echo "")
|
||||
python3 -c "import json,sys; sha='$COMMIT_SHA'; matches=[pr['user']['login'] for pr in json.load(sys.stdin) if (pr.get('merge_commit_sha','') or '').startswith(sha) or sha.startswith(pr.get('merge_commit_sha','') or '')]; print(matches[0] if matches else '')" 2>/dev/null || echo "")
|
||||
|
||||
# 确定通知对象
|
||||
if [ -n "$PR_AUTHOR" ]; then
|
||||
|
||||
@@ -245,11 +245,14 @@ pm2 show sanguo-act-runner # 详情
|
||||
|------|------|
|
||||
| `feat` | 新功能 |
|
||||
| `fix` | Bug 修复 |
|
||||
| `impl` | 按设计文档实现 |
|
||||
| `refactor` | 重构(不改行为) |
|
||||
| `test` | 测试相关 |
|
||||
| `docs` | 文档 |
|
||||
| `chore` | 构建/工具/配置 |
|
||||
|
||||
sanguo 组织所有仓库统一使用此 commit 规范。
|
||||
|
||||
---
|
||||
|
||||
## §4. 问题管理
|
||||
@@ -266,15 +269,19 @@ pm2 show sanguo-act-runner # 详情
|
||||
|
||||
### 4.2 Issue 标签体系
|
||||
|
||||
| 标签 | 颜色 | 说明 |
|
||||
|------|------|------|
|
||||
| `bug` | 红 | 功能异常 |
|
||||
| `feature` | 蓝 | 新功能需求 |
|
||||
| `improvement` | 绿 | 改进优化 |
|
||||
| `security` | 橙 | 安全相关 |
|
||||
| `risk:high/standard/low` | 分级色 | 风险级别(见 §6.1 判定规则) |
|
||||
| `priority:high/medium/low` | 黄/灰 | 优先级 |
|
||||
| `blocked` | 紫 | 阻塞中 |
|
||||
| 标签 | 颜色 | 色值 | 说明 |
|
||||
|------|------|------|------|
|
||||
| `type/bug` | 红 | #ee0701 | Bug 修复 |
|
||||
| `type/feat` | 蓝 | #84b6eb | 新功能 |
|
||||
| `type/impl` | 浅蓝 | #c5def5 | 按设计实现 |
|
||||
| `type/docs` | 黄 | #fbca04 | 文档 |
|
||||
| `type/test` | 绿 | #0e8a16 | 测试 |
|
||||
| `type/ci` | 紫 | #d4c5f9 | CI/CD |
|
||||
| `type/refactor` | 橙 | #ff6f00 | 重构 |
|
||||
| `priority/P0` | 深红 | #b60205 | 紧急 |
|
||||
| `priority/P1` | 红 | #d93f0b | 高 |
|
||||
| `priority/P2` | 黄 | #fbca04 | 中 |
|
||||
| `priority/P3` | 浅蓝 | #c5def5 | 低 |
|
||||
|
||||
### 4.3 需求/问题 Review 前置
|
||||
|
||||
@@ -296,6 +303,29 @@ Open → In Progress → Review → Closed
|
||||
└──── Reopened ←───────────────────┘
|
||||
```
|
||||
|
||||
### 4.5 标题规范
|
||||
|
||||
所有 Issue 和 PR 标题**必须**包含项目代号前缀,让人类一眼识别项目+类型:
|
||||
|
||||
**Issue**: `[代号] type: 简述`
|
||||
**PR**: `[代号] type(scope): 简述`
|
||||
|
||||
项目代号:
|
||||
|
||||
| 仓库 | 代号 |
|
||||
|------|------|
|
||||
| sanguo_moziplus_v2 | moz |
|
||||
| sanguo_quant_live | quant |
|
||||
| sanguo_vnpy | vnpy |
|
||||
|
||||
示例:
|
||||
- `[moz] bug: Mail API 500 when comment_type invalid`
|
||||
- `[moz] impl(daemon): 知识注入 L2 引擎层 — WikiGuideSection`
|
||||
- `[quant] feat: 趋势跟踪策略骨架`
|
||||
|
||||
此规范通过 L2 引擎层 `GiteaConventionSection`(priority=55)自动注入所有 Agent prompt。
|
||||
完整规范文档:L3 Skill `gitea-conventions`。规范设计原理详见 [§26](#26-gitea-协作规范设计)。
|
||||
|
||||
---
|
||||
|
||||
## §5. CI/CD 管道设计
|
||||
@@ -3297,3 +3327,120 @@ async def _handle_issue_comment(payload):
|
||||
|------|------|------|
|
||||
| 2026-06-09 | v1.0 | 初版:E2E 真实场景暴露问题 → 四层改造方案 + @mention 通知 + Mail type 改造 |
|
||||
|
||||
---
|
||||
|
||||
## §26. Gitea 协作规范设计
|
||||
|
||||
> **状态**: ✅ 已实现(PR #69)
|
||||
> **日期**: 2026-06-14
|
||||
|
||||
### 26.1 设计目标
|
||||
|
||||
团队三个仓库(moziplus_v2 / quant_live / vnpy)在 Gitea 上独立存在,协作时存在三个问题:
|
||||
|
||||
1. **标题不可辨识**:`Fix mail API` 看不出是哪个项目、什么类型的改动
|
||||
2. **Label 缺失**:无统一标签体系,无法按类型/优先级筛选
|
||||
3. **填写无约束**:Issue/PR 内容格式随意,审查时缺少关键信息
|
||||
|
||||
本规范的目标:让人类一眼识别项目+类型,让 Agent 可程序化遵循,让模板降低填写门槛。
|
||||
|
||||
### 26.2 规范设计
|
||||
|
||||
#### 26.2.1 标题规范
|
||||
|
||||
**规则**:所有 Issue/PR 标题必须包含项目代号前缀。
|
||||
|
||||
| 类型 | 格式 | 示例 |
|
||||
|------|------|------|
|
||||
| Issue | `[代号] type: 简述` | `[moz] bug: Mail API 500 when comment_type invalid` |
|
||||
| PR | `[代号] type(scope): 简述` | `[moz] impl(daemon): WikiGuideSection 注入` |
|
||||
|
||||
**项目代号**:moz=moziplus_v2, quant=quant_live, vnpy=vnpy
|
||||
|
||||
**type 清单**:bug / feat / impl / fix / docs / test / ci / refactor / chore
|
||||
|
||||
**设计决策**:
|
||||
- 为什么用代号前缀而不是靠仓库隔离?— 团队成员同时在多仓库协作,通知列表(Mail、Gitea dashboard)混合展示时代号前缀提供即时辨识。仓库隔离解决不了跨仓库视图的辨识问题
|
||||
- PR 加 `scope` 是因为 PR 通常涉及具体模块(daemon / api / frontend),Issue 不需要
|
||||
|
||||
#### 26.2.2 Label 体系
|
||||
|
||||
采用 `type/*` + `priority/*` 双命名空间,替代旧标签(bug/feature/improvement/security):
|
||||
|
||||
| 标签 | 色值 | 说明 |
|
||||
|------|------|------|
|
||||
| `type/bug` | #ee0701 | Bug 修复 |
|
||||
| `type/feat` | #84b6eb | 新功能 |
|
||||
| `type/impl` | #c5def5 | 按设计实现 |
|
||||
| `type/docs` | #fbca04 | 文档 |
|
||||
| `type/test` | #0e8a16 | 测试 |
|
||||
| `type/ci` | #d4c5f9 | CI/CD |
|
||||
| `type/refactor` | #ff6f00 | 重构 |
|
||||
| `priority/P0` | #b60205 | 紧急 |
|
||||
| `priority/P1` | #d93f0b | 高 |
|
||||
| `priority/P2` | #fbca04 | 中 |
|
||||
| `priority/P3` | #cfd3d7 | 低 |
|
||||
|
||||
**设计决策**:
|
||||
- 用 `type/` `priority/` 命名空间而非扁平命名,避免标签膨胀时冲突,且在 Gitea UI 中按前缀分组显示
|
||||
- type 用暖色系(红/橙/黄),priority 用冷→热渐变(灰→蓝→黄→红),视觉上两类标签不混淆
|
||||
- ⚠️ 已知问题:`type/impl`(#c5def5) 与 `priority/P3` 色值相近。P3 已调整为灰色 #cfd3d7 以区分
|
||||
|
||||
#### 26.2.3 Issue/PR 模板
|
||||
|
||||
**Issue 模板**(3 种):bug.yml / feature.yml / test.yml
|
||||
|
||||
覆盖决策:只做最高频的 3 种类型(bug 报告、功能需求、测试任务),其余类型(docs/ci/refactor)频率低,走自由创建。每种模板包含描述、复现/方案、优先级字段。
|
||||
|
||||
**PR 模板**(1 种):PULL_REQUEST_TEMPLATE.md
|
||||
|
||||
改动类型 checklist + 检查清单(标题格式、开发→安装目录同步、测试、设计文档更新)。
|
||||
|
||||
### 26.3 执行机制
|
||||
|
||||
规范通过四层路径保证执行,每层职责不同:
|
||||
|
||||
| 层 | 载体 | 职责 | Token 成本 |
|
||||
|----|------|------|-----------|
|
||||
| **L1** | TOOLS.md(Agent workspace) | 代号表 + 格式速查,Agent 静态可见 | ~100 |
|
||||
| **L2** | `GiteaConventionSection`(priority=55) | 每次 spawn 动态注入,提醒标题格式 | ~80 |
|
||||
| **L3** | `gitea-conventions` Skill(extraDirs) | 完整规范(标题/分支/commit/label),Agent 按需加载 | 按需 |
|
||||
| **Gitea** | Issue/PR Template + Label(仓库级) | 人类创建时表单引导,标签选择 | — |
|
||||
|
||||
**L2 设计决策**:
|
||||
- `GiteaConventionSection` priority=55,排在 Constraints(50) 之后、Extension(60) 之前。标题规范属于约束类,但优先级低于安全/流程约束
|
||||
- 注入所有 handler(Task/Toolchain/Mail),因为任何 handler 都可能创建 Issue/PR
|
||||
- ⚠️ L1 文件在各 Agent workspace(`~/.openclaw/workspace-*/TOOLS.md`),不在仓库管理。Agent workspace 变更不通过 PR
|
||||
|
||||
### 26.4 Label 迁移策略
|
||||
|
||||
旧标签(bug/feature/improvement/security/risk:high/priority:high)已由新体系替代:
|
||||
|
||||
- **旧标签保留不动**(不删除),避免历史 Issue 丢失标签信息
|
||||
- **新 Issue/PR 使用新标签**(type/* + priority/*)
|
||||
- 当前不做批量迁移。如有需要可后续通过 Gitea API 批量替换
|
||||
|
||||
### 26.5 与其他章节的关系
|
||||
|
||||
| 章节 | 关系 |
|
||||
|------|------|
|
||||
| §4.2 Issue 标签体系 | §26.2.2 Label 设计在问题管理场景的具体应用(已随 PR #69 更新) |
|
||||
| §4.5 标题规范 | §26.2.1 标题规范的执行层摘要(已随 PR #69 新增) |
|
||||
| §5 CI/CD 管道 | CI 事件通过标题前缀 `[CI]` 做事件路由(见 §16 事件中枢) |
|
||||
| §6 代码审查流程 | PR Template 检查清单约束审查前置条件 |
|
||||
|
||||
### 26.6 实现记录
|
||||
|
||||
| 文件 | 改动 |
|
||||
|------|------|
|
||||
| `prompt_composer.py` | 新增 `GiteaConventionSection`(priority=55) |
|
||||
| `task_handler.py` | `get_sections()` 注册 `GiteaConventionSection()` |
|
||||
| `toolchain_handler.py` | `get_sections()` 注册 `GiteaConventionSection()` |
|
||||
| `mail_handler.py` | `get_sections()` 注册 `GiteaConventionSection()` |
|
||||
| `db.py` | `COMMENT_TYPES` 补 `action_report`(修 API 500 bug) |
|
||||
| `.gitea/ISSUE_TEMPLATE/` | bug.yml / feature.yml / test.yml |
|
||||
| `.gitea/PULL_REQUEST_TEMPLATE.md` | PR 检查清单模板 |
|
||||
| Gitea Labels | 3 仓库各创建 11 个 Label(type × 7 + priority × 4) |
|
||||
|
||||
PR #69,2026-06-14 合并。
|
||||
|
||||
|
||||
@@ -1,10 +1,11 @@
|
||||
---
|
||||
title: "TaskTypeRegistry + Handler 架构重构"
|
||||
created: 2026-06-10
|
||||
version: v3.0
|
||||
version: v3.1
|
||||
---
|
||||
|
||||
> 状态: ✅ 已完成(Step 1-5 全部合并,394 passed)
|
||||
> v3.1 新增 §18:Mail Handler Verify/Prompt 强化(2026-06-16,进行中)
|
||||
|
||||
# §1 现状分析(v3.0 更新说明:§1-§13 保留原样,新增 §14-§18,更新 §3/§5/§7)
|
||||
|
||||
@@ -585,6 +586,18 @@ class PromptComposer:
|
||||
| 50-59 | 硬约束 | 安全红线、禁止行为 |
|
||||
| 60-69 | 扩展段 | 保留给未来使用 |
|
||||
|
||||
## 共性 Section(三 handler 共享)
|
||||
|
||||
以下三个 Section 在 `prompt_composer.py` 中统一定义,被 Task/Mail/Toolchain 三个 handler 共同注入:
|
||||
|
||||
| Section | priority | 用途 |
|
||||
|---------|----------|------|
|
||||
| `GiteaConventionSection` | 55 | Gitea Issue/PR 标题规范、分支命名、提交格式 |
|
||||
| `DeliveryChecklistSection` | 55 | 交付前检查清单(产出格式、验证项、必读文档) |
|
||||
| `WikiGuideSection` | 60 | Wiki 知识库检索指引(检索路径、优先级、知识缺口记录) |
|
||||
|
||||
设计意图:将跨 handler 的共性约束从各 handler 的 ConstraintsSection 中抽离,避免重复维护。
|
||||
|
||||
---
|
||||
|
||||
# §13 三个 Handler 的 Section 注册
|
||||
@@ -601,6 +614,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
RoleSkillSection(priority=30), # BootstrapBuilder 段 3(Skill 全文)
|
||||
TaskApiSection(priority=40), # API 操作指令,success_status="review"
|
||||
TaskConstraintsSection(priority=50), # 硬约束
|
||||
GiteaConventionSection(priority=55), # Gitea 协作规范(共性)
|
||||
WikiGuideSection(priority=60), # Wiki 知识库检索指引(共性)
|
||||
DeliveryChecklistSection(priority=55), # 交付检查清单(共性)
|
||||
]
|
||||
```
|
||||
|
||||
@@ -611,6 +627,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
| RoleSkillSection | BootstrapBuilder 段 3 | 个性:只有 task 读 Skill 全文 |
|
||||
| TaskApiSection | spawner `_build_api_section` | **共性基础 + 个性参数**(success_status) |
|
||||
| TaskConstraintsSection | BootstrapBuilder 段 4 | 个性:每种 task 约束不同 |
|
||||
| GiteaConventionSection | prompt_composer.py | **共性**:Gitea Issue/PR 规范 |
|
||||
| WikiGuideSection | prompt_composer.py | **共性**:Wiki 检索指引 |
|
||||
| DeliveryChecklistSection | prompt_composer.py | **共性**:交付前检查清单 |
|
||||
|
||||
## MailHandler sections
|
||||
|
||||
@@ -620,6 +639,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
MailContextSection(priority=10), # from/to/title/text,区分 inform/request
|
||||
MailApiSection(priority=40), # API 操作指令,success_status="done"
|
||||
MailConstraintsSection(priority=50), # 硬约束(禁止状态转换命令等)
|
||||
GiteaConventionSection(priority=55), # Gitea 协作规范(共性)
|
||||
WikiGuideSection(priority=60), # Wiki 知识库检索指引(共性)
|
||||
DeliveryChecklistSection(priority=55), # 交付检查清单(共性)
|
||||
]
|
||||
```
|
||||
|
||||
@@ -628,6 +650,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
| MailContextSection | MAIL_INFORM_TEMPLATE / MAIL_REQUEST_TEMPLATE | 个性:邮件格式 |
|
||||
| MailApiSection | spawner `_build_api_section` 变体 | **共性基础 + 个性参数**(success_status="done",含 Mail API 指令) |
|
||||
| MailConstraintsSection | 模板中的 ⚠️ 约束 | 个性 |
|
||||
| GiteaConventionSection | prompt_composer.py | **共性**:Gitea Issue/PR 规范 |
|
||||
| WikiGuideSection | prompt_composer.py | **共性**:Wiki 检索指引 |
|
||||
| DeliveryChecklistSection | prompt_composer.py | **共性**:交付前检查清单 |
|
||||
|
||||
## ToolchainHandler sections
|
||||
|
||||
@@ -637,6 +662,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
ToolchainContextSection(priority=10), # 事件类型 + 事件详情
|
||||
ToolchainApiSection(priority=40), # API 操作指令,success_status="done"
|
||||
ToolchainConstraintsSection(priority=50), # 硬约束
|
||||
GiteaConventionSection(priority=55), # Gitea 协作规范(共性)
|
||||
WikiGuideSection(priority=60), # Wiki 知识库检索指引(共性)
|
||||
DeliveryChecklistSection(priority=55), # 交付检查清单(共性)
|
||||
]
|
||||
```
|
||||
|
||||
@@ -645,6 +673,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
| ToolchainContextSection | toolchain_templates.py + md 文件 | 个性:事件格式 |
|
||||
| ToolchainApiSection | spawner `_build_api_section` 变体 | **共性基础 + 个性参数** |
|
||||
| ToolchainConstraintsSection | 新增 | 个性 |
|
||||
| GiteaConventionSection | prompt_composer.py | **共性**:Gitea Issue/PR 规范 |
|
||||
| WikiGuideSection | prompt_composer.py | **共性**:Wiki 检索指引 |
|
||||
| DeliveryChecklistSection | prompt_composer.py | **共性**:交付前检查清单 |
|
||||
|
||||
## Section 复用分析
|
||||
|
||||
@@ -655,6 +686,9 @@ def get_sections(self) -> list[PromptSection]:
|
||||
| *ConstraintsSection | ✅ | ✅ | ✅ | ❌ 约束内容不同,各自实现 |
|
||||
| PriorOutputsSection | ✅ | ❌ | ❌ | 仅 task |
|
||||
| RoleSkillSection | ✅ | ❌ | ❌ | 仅 task |
|
||||
| GiteaConventionSection | ✅ | ✅ | ✅ | **共性**:三 handler 共享,prompt_composer.py 定义 |
|
||||
| WikiGuideSection | ✅ | ✅ | ✅ | **共性**:三 handler 共享,prompt_composer.py 定义 |
|
||||
| DeliveryChecklistSection | ✅ | ✅ | ✅ | **共性**:三 handler 共享,prompt_composer.py 定义 |
|
||||
|
||||
**结论**:ApiSection 可以抽一个 BaseApiSection(curl 模板 + success_status 参数),其余 section 各自实现。
|
||||
|
||||
@@ -667,9 +701,9 @@ src/daemon/
|
||||
├── task_type_registry.py # §3 + §4:Protocol + Registry
|
||||
├── prompt_composer.py # §12 PromptSection + PromptContext + PromptComposer
|
||||
├── base_task_handler.py # §16 BaseTaskHandler 基类
|
||||
├── task_handler.py # §13 TaskHandler(继承 BaseTaskHandler)+ 5 sections
|
||||
├── mail_handler.py # §13 MailHandler(继承 BaseTaskHandler)+ 3 sections
|
||||
├── toolchain_handler.py # §13 ToolchainHandler(继承 BaseTaskHandler)+ 3 sections
|
||||
├── task_handler.py # §13 TaskHandler(继承 BaseTaskHandler)+ 8 sections
|
||||
├── mail_handler.py # §13 MailHandler(继承 BaseTaskHandler)+ 6 sections
|
||||
├── toolchain_handler.py # §13 ToolchainHandler(继承 BaseTaskHandler)+ 6 sections
|
||||
├── dispatcher.py # §6 改动
|
||||
├── spawner.py # §6 改动
|
||||
├── ticker.py # §6 改动
|
||||
@@ -952,7 +986,219 @@ handler.post_complete(task_id, agent_id, outcome, db_path)
|
||||
|
||||
---
|
||||
|
||||
## §14. Mail 失败通知机制
|
||||
## §18. Mail Handler Verify/Prompt 强化
|
||||
|
||||
> 日期:2026-06-16 | 作者:庞统 | 状态:方向 1-5 全部已确认
|
||||
|
||||
## 18.1 问题背景
|
||||
|
||||
### 触发事件
|
||||
|
||||
2026-06-12 daemon 重启后,_mail DB 中积压的 E2E 测试遗留邮件(5/18~6/1 创建,type=request,performative="text")被 dispatch 给 agent。agent 正常处理并输出文本(如"已阅,无需处理"),但 `verify_completion` 判定 no_reply → 标 failed → 触发 `notify_mail_failed` → 产生 38 封 `[投递失败]` 通知邮件,每 ~2.5 分钟一轮,持续 10 轮。
|
||||
|
||||
### 根因链
|
||||
|
||||
```
|
||||
E2E 测试脚本 bug(type="text")
|
||||
→ mail_routes.py 不校验 type 值,直接透传
|
||||
→ performative="text" ≠ "inform" → 走 _check_reply
|
||||
→ _check_reply 查 in_reply_to task,agent 没用 Mail API 回复
|
||||
→ verify 失败 → on_failure 标 failed
|
||||
→ notify_mail_failed 发 [投递失败] 通知
|
||||
→ 通知本身也是 task,循环触发
|
||||
```
|
||||
|
||||
### 三种 handler verify 对比
|
||||
|
||||
| 维度 | TaskHandler | MailHandler | ToolchainHandler |
|
||||
|------|------------|-------------|------------------|
|
||||
| verify 信号 | output / comment(≥50字) / terminal_status(三信号) | in_reply_to task(单信号) | action_report / output / comment(≥20字)(三层 fallback) |
|
||||
| inform 处理 | N/A | 直接通过(不检查执行证据) | N/A |
|
||||
| verify 失败后 | **留 working**(覆盖 post_complete) | **标 failed**(base post_complete + mail on_failure) | 标 failed(base post_complete + tc on_failure) |
|
||||
| agent 输出持久化 | 靠 agent 主动 POST output/comment | **无**(agent 输出只在内存) | 靠 agent 主动 POST action_report |
|
||||
|
||||
**关键发现**:
|
||||
1. MailHandler 继承 BaseTaskHandler,未覆盖 `post_complete` → verify 失败时走 base 的 `on_failure` → 标 failed
|
||||
2. TaskHandler 覆盖了 `post_complete` → verify 失败时留 working,让 ticker 重试
|
||||
3. MailHandler 的 verify 只有 `in_reply_to` 一条路径,没有 fallback
|
||||
4. inform 类型直接通过(`VerifyResult(True)`),不检查任何执行证据——inform 是"无需回复"不是"无需检查"
|
||||
5. E2E 测试用 `TestClient(app)` 写生产 `_mail DB`,且测试脚本用了非标准 `type="text"`
|
||||
|
||||
## 18.2 修复方向
|
||||
|
||||
### 方向 1:mail verify 对齐 toolchain 模式(✅ 已确认)
|
||||
|
||||
**问题**:mail verify 只有 in_reply_to task 一条路径。task/toolchain 都有多层 fallback(outputs / comments)。
|
||||
|
||||
**方案**:mail 对齐 toolchain 模式——prompt 加 action report 要求,verify 优先查 action_report → fallback outputs → fallback comments。in_reply_to 回复邮件从唯一信号降为 request 类型的第 4 优先级信号。
|
||||
|
||||
#### prompt 强化(MailApiSection)
|
||||
|
||||
参照 ToolchainApiSection,在 mail prompt 中追加 action report 要求:
|
||||
```
|
||||
### 完成后必须提交 action report
|
||||
执行完邮件处理后,必须提交 action report:
|
||||
curl -s -X POST "http://localhost:8083/api/projects/_mail/tasks/{task_id}/comments" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"author": "{agent_id}", "comment_type": "action_report", "body": "处理结果摘要"}'
|
||||
|
||||
⚠️ 不提交 action report 的任务会被标记为 failed。
|
||||
```
|
||||
|
||||
#### verify 改造(MailHandler.verify_completion)
|
||||
|
||||
```python
|
||||
def verify_completion(self, task_id, db_path) -> VerifyResult:
|
||||
performative = self._parse_performative(task_id, db_path)
|
||||
|
||||
# 1. 优先检查 action_report comment(所有类型通用)
|
||||
if self._has_action_report(task_id, db_path):
|
||||
return VerifyResult(True, "has_action_report", "action_report found")
|
||||
|
||||
# 2. fallback: outputs
|
||||
if self._has_outputs(task_id, db_path):
|
||||
return VerifyResult(True, "has_output", f"output_count={count}")
|
||||
|
||||
# 3. fallback: 有实质内容的 comment(≥20字,非 system)
|
||||
if self._has_comment(task_id, db_path):
|
||||
return VerifyResult(True, "has_comment", f"comment_count={count}")
|
||||
|
||||
# 4. request 特有:检查 in_reply_to 回复邮件
|
||||
if performative == "request":
|
||||
if self._check_reply(task_id, db_path):
|
||||
return VerifyResult(True, "has_reply", "in_reply_to found")
|
||||
|
||||
return VerifyResult(False, "no_action",
|
||||
"no action_report, no output, no comment, no reply")
|
||||
```
|
||||
|
||||
注意:action_report 提交到 moziplus DB(comments 表),不是 Gitea。Gitea comment 是跨 agent 协作用的,不是 verify 检查的依据。
|
||||
|
||||
### 方向 2:prompt 约束强化(✅ 已确认)
|
||||
|
||||
**问题**:当前 mail prompt 只给了 curl 示例,没有硬约束要求 agent 必须输出处理结果。agent 判断"已阅"后直接跳过,不创建 in_reply_to task。
|
||||
|
||||
**方案**:mail request/inform prompt 加 JSON 输出约束(参考 toolchain 的 Red Flags 模式)。
|
||||
|
||||
#### MailContextSection 强化
|
||||
|
||||
**request 类型**追加:
|
||||
```
|
||||
### 输出要求
|
||||
- 你的回复必须包含对邮件的实际处理结果
|
||||
- 如果是第一次收到:正常处理,输出处理结果
|
||||
- 如果是重复邮件(你之前处理过相同 ID 的邮件):输出"此前已处理" + 之前的处理结果摘要
|
||||
- ⚠️ "已阅""无需处理"不是有效处理结果
|
||||
```
|
||||
|
||||
**inform 类型**追加:
|
||||
```
|
||||
### 输出要求
|
||||
- 你的回复必须确认已处理(读取/执行/记录),不能只说"已阅"
|
||||
- 如果是重复邮件:输出"此前已处理" + 处理结果摘要
|
||||
- ⚠️ "已阅"不是有效输出
|
||||
```
|
||||
|
||||
**MailConstraintsSection** 追加 Red Flags:
|
||||
```
|
||||
| Agent 想法 | Red Flag 驳回 |
|
||||
|------------|--------------|
|
||||
| "已阅即可" | ❌ 错!必须输出处理结果或确认执行 |
|
||||
| "重复邮件忽略" | ❌ 错!输出"此前已处理" + 结果摘要 |
|
||||
| "无需回复" | ❌ 错!request 必须回复,inform 必须确认处理 |
|
||||
```
|
||||
|
||||
### 方向 3:inform 也要检查执行证据(✅ 已确认)
|
||||
|
||||
**问题**:当前 inform verify 直接返回 `VerifyResult(True)`,不检查任何执行证据。inform 是"无需回复"不是"无需检查"。
|
||||
|
||||
**方案**:inform verify 改为检查 agent 是否有实质输出(comment/output),和 request 走不同的验证路径但都需要验证。
|
||||
|
||||
**改动文件**:`src/daemon/mail_handler.py` `verify_completion` 方法
|
||||
|
||||
### 方向 4:verify 失败保持 working(✅ 已确认)
|
||||
|
||||
**问题**:MailHandler 继承 BaseTaskHandler,verify 失败时走 base 的 `on_failure` → 标 failed。而 TaskHandler 覆盖了 `post_complete`,verify 失败时留 working。
|
||||
|
||||
**原始设计意图**(§2 设计文档):"不通过 → 留 working,ticker 重查(最多 3 次,然后标 failed)"。
|
||||
|
||||
**方案**:MailHandler 覆盖 `post_complete`,verify 失败时不标 failed,保持 working。ticker 的 `_check_timeouts` 超时兜底:
|
||||
- `check_completion` 通过(有回复)→ done
|
||||
- `check_completion` 不通过 → 超时后标 failed
|
||||
- Runaway Guard(§15 dispatch_count ≥ 10)兜底防止无限循环
|
||||
|
||||
**改动文件**:`src/daemon/mail_handler.py`,新增 `post_complete` 覆盖
|
||||
|
||||
### 方向 5:type 校验 + E2E 修复 + DB 清理(✅ 已确认)
|
||||
|
||||
#### 5.1 mail_routes.py type 校验
|
||||
|
||||
**问题**:`mail_type = body.get("type")` 直接透传,传什么存什么。`"text"` 不是标准值。
|
||||
|
||||
**方案**:创建时校验 type 只允许 `inform` / `request`,非法值默认 `request`。
|
||||
|
||||
```python
|
||||
mail_type = body.get("type")
|
||||
if mail_type is None:
|
||||
mail_type = "inform" if in_reply_to else "request"
|
||||
elif mail_type not in ("inform", "request"):
|
||||
# 非标准值,校正为默认值
|
||||
mail_type = "inform" if in_reply_to else "request"
|
||||
```
|
||||
|
||||
**改动文件**:`src/api/mail_routes.py`
|
||||
|
||||
#### 5.2 _parse_performative 容错
|
||||
|
||||
**问题**:`meta.get("performative", meta.get("type", "request"))` 当 performative="text" 时返回 "text",不等于 "inform" → 走 _check_reply。
|
||||
|
||||
**方案**:只认 `inform` 和 `request` 两个值,其他一律当 `request`。
|
||||
|
||||
```python
|
||||
def _parse_performative(self, task_id, db_path) -> str:
|
||||
raw = meta.get("performative", meta.get("type", "request"))
|
||||
if raw == "inform":
|
||||
return "inform"
|
||||
return "request" # 非标准值一律当 request
|
||||
```
|
||||
|
||||
**改动文件**:`src/daemon/mail_handler.py` `_parse_performative` 方法
|
||||
|
||||
#### 5.3 E2E 测试修复
|
||||
|
||||
**问题**:`tests/e2e/test_e2e_v27.py` 用 `type="text"` 创建测试邮件,且用 `TestClient(app)` 写生产 `_mail DB`。
|
||||
|
||||
**修复**:
|
||||
1. `type="text"` 全部改为 `type="inform"` 或 `type="request"`
|
||||
2. E2E 测试跑完后清理测试邮件(`mail_ids` 列表中记录的 task)
|
||||
|
||||
**改动文件**:`tests/e2e/test_e2e_v27.py`
|
||||
|
||||
#### 5.4 生产 DB 清理
|
||||
|
||||
**问题**:生产 `_mail DB` 中残留大量 E2E 测试邮件(5/18~6/3 创建的"筛选测试""详情测试""已读测试""任务分配"等)。
|
||||
|
||||
**方案**:手动清理这些测试残留(一次性操作,不需要代码改动)。
|
||||
|
||||
## 18.3 影响范围
|
||||
|
||||
| 文件 | 改动类型 | 影响面 |
|
||||
|------|---------|--------|
|
||||
| `src/daemon/mail_handler.py` | verify + post_complete + prompt section | MailHandler 核心逻辑 |
|
||||
| `src/api/mail_routes.py` | type 校验 | Mail API 创建入口 |
|
||||
| `tests/e2e/test_e2e_v27.py` | type 值修正 + 清理 | E2E 测试 |
|
||||
| 生产 `_mail DB` | 清理测试残留 | 一次性操作 |
|
||||
|
||||
## 18.4 验证计划
|
||||
|
||||
1. 单元测试:mail_handler verify/prompt 变更
|
||||
2. 集成测试:mail dispatch → verify → done/working 全链路
|
||||
3. 回归测试:`pytest -m "not e2e"` 全量
|
||||
4. 手工验证:创建 inform/request 邮件,确认 verify 行为正确
|
||||
|
||||
---
|
||||
|
||||
# §14. Mail 失败通知机制
|
||||
|
||||
### 20.1 背景
|
||||
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
# §15 Runaway Guard — Per-Task Dispatch 上限
|
||||
|
||||
> 设计文档 v1.0 | 2026-06-16
|
||||
|
||||
## 问题
|
||||
|
||||
mail/toolchain task 走 handler auto-working(跳过 claim 阶段),不受 claim_timeout 的 3 次重试兜底保护。如果一个 auto-working task 反复 spawn 但永远到不了 done/failed,会无限循环消耗资源。
|
||||
|
||||
### 实际案例
|
||||
|
||||
2026-06-15 mention 重复投递事件:`spawn_full_agent` 在 `use_main_session=True` 时返回 `None`,ticker `_process_mentions` 误判为失败,每次 tick(30s)都重试。同一 mention 投递了 4 次,直到 retry_count 达到 mention_queue 的 5 次上限才停止。
|
||||
|
||||
直接根因已由 PR #80 修复,但如果类似 bug 再次出现,当前没有任何机制阻止 task 层面的无限循环。
|
||||
|
||||
## 设计
|
||||
|
||||
### 机制
|
||||
|
||||
tasks 表新增 `dispatch_count` 字段,每次 ticker 成功 dispatch 一个 task 时递增。当 `dispatch_count >= 10`(全局默认)时,自动标 failed。
|
||||
|
||||
### 默认值选择
|
||||
|
||||
全局默认 10 次。参考 Hermes v0.13 Best Practices §3 "Per-Task 重试上限":
|
||||
|
||||
- 简单任务重试 1 次
|
||||
- 复杂任务重试 3 次
|
||||
- crash recovery(3 次)+ api_retry(3 次)余量 = ~10 次
|
||||
|
||||
### 适用范围
|
||||
|
||||
所有 task 类型(task/mail/toolchain),所有非终态(pending/working/claimed)。
|
||||
|
||||
### 检查时机
|
||||
|
||||
在 `_check_timeouts` 方法开头,先于现有的 claimed/working 超时检查执行。
|
||||
|
||||
### 与现有机制的关系
|
||||
|
||||
| 机制 | 覆盖场景 | 触发动作 |
|
||||
|------|---------|---------|
|
||||
| claim_timeout retry_count >= 3 | 广播任务无人认领 | 升级庞统 |
|
||||
| crash_limit 3/30min | working 状态 crash | 标 failed |
|
||||
| api_retry_count | API 连续失败 | 标 failed |
|
||||
| 续杯 max_retries 3 | 续杯耗尽 | 标 failed |
|
||||
| working timeout | working 超时 | 标 failed 或 done |
|
||||
| **runaway_guard 10 次** | **任何状态的无限循环** | **标 failed** |
|
||||
|
||||
runaway_guard 是最后一道防线,覆盖所有其他机制遗漏的循环场景。
|
||||
|
||||
## 改动文件
|
||||
|
||||
| 文件 | 改动 |
|
||||
|------|------|
|
||||
| `src/blackboard/db.py` | `_safe_add_column(conn, "tasks", "dispatch_count", "INTEGER DEFAULT 0")` |
|
||||
| `src/blackboard/models.py` | Task dataclass 加 `dispatch_count: int = 0` |
|
||||
| `src/daemon/ticker.py` | `_dispatch_pending` / `_dispatch_reviews` 递增 dispatch_count;`_check_timeouts` 加 runaway guard 检查 |
|
||||
|
||||
## 参考
|
||||
|
||||
- Hermes v0.13 Kanban Best Practices §3 "Per-Task 重试上限"
|
||||
- 实际案例:2026-06-15 mention 重复投递事件(PR #80 修复了直接根因,runaway guard 作为兜底)
|
||||
@@ -0,0 +1,307 @@
|
||||
# #16 知识注入设计
|
||||
|
||||
> 状态:v2 设计中
|
||||
> 作者:庞统
|
||||
> 日期:2026-06-13(v1),2026-06-14(v2 对齐 #11 四层架构)
|
||||
> 评审:待司马懿评审
|
||||
|
||||
## 一、问题
|
||||
|
||||
### 1.1 现状
|
||||
|
||||
Agent(庞统、司马懿、张飞等)在执行任务时,不主动查询已有知识库(wiki-vault)。导致:
|
||||
|
||||
1. **重复调研**:赵云查过的数据清洗经验,张飞又从头调研一遍
|
||||
2. **重复踩坑**:wiki-vault 里已有"vnpy load_bar 需要显式指定 end=None"的实践,张飞还是踩了
|
||||
3. **方案质量低**:做方案时纯靠推理,不查已有的优秀实践
|
||||
4. **知识 gap 无人管**:查不到相关知识时没记录,下次还是查不到
|
||||
|
||||
### 1.2 根因
|
||||
|
||||
不是没有知识库(wiki-vault 有 50+ practices 页面),也不是没有检索能力(wiki-query Skill 已存在)。
|
||||
|
||||
**根因是注入时机**:Agent 不知道什么时候该查、没有强制机制让 Agent 在关键决策点查。
|
||||
|
||||
### 1.3 目标
|
||||
|
||||
1. Agent 在关键决策点**主动查询** wiki-vault
|
||||
2. 查不到相关知识时**自动记录** knowledge gap
|
||||
3. 定时任务处理 gap + 总结经验,**持续丰富** wiki-vault
|
||||
4. 不增加 prompt token 负担(不自动注入知识全文,只引导查询)
|
||||
|
||||
## 二、调研
|
||||
|
||||
### 2.1 Superpowers:强制 Skill 检查(最有效)
|
||||
|
||||
**核心设计**:session-start hook 注入铁律级指令——
|
||||
|
||||
> "If you think there is even a **1% chance** a skill might apply, you **ABSOLUTELY MUST** invoke the skill. This is not negotiable."
|
||||
|
||||
配合 **Red Flags 表**防止 Agent 自合理化跳过:
|
||||
|
||||
| Agent 的想法 | Red Flag 驳回 |
|
||||
|---|---|
|
||||
| "这个问题很简单" | 简单问题也需要查实践 |
|
||||
| "我需要更多上下文" | Skill 检查在澄清问题之前 |
|
||||
| "先看看代码" | Skill 告诉你怎么看代码 |
|
||||
| "我记住了这个 Skill" | Skill 会更新,重新读 |
|
||||
|
||||
**为什么有效**:不靠 Agent "想起来",靠铁律强制。Skill 触发在任何响应之前。
|
||||
|
||||
### 2.2 Hermes:经验闭环 + Session Search
|
||||
|
||||
**经验闭环**:完成复杂任务(5+ tool calls)→ 自动创建 Skill → 下次自然触发。
|
||||
|
||||
**Session Search**:系统提示注入——"当用户提及过去内容时,主动搜索而非要求用户重复"。
|
||||
|
||||
**为什么有效**:不是"知识查询"而是"行为内化"——经验变成 Skill,Skill 有 description 触发词。
|
||||
|
||||
### 2.3 结论
|
||||
|
||||
综合两个项目的优势:
|
||||
|
||||
| 设计点 | 来源 | 我们的做法 |
|
||||
|--------|------|-----------|
|
||||
| 铁律级强制 | Superpowers | L0 Hook 注入 + L1 SOUL.md 行为引导 |
|
||||
| Red Flags 反合理化 | Superpowers | 知识查询 Red Flags 表(L1 SOUL.md) |
|
||||
| 经验内化 | Hermes | 经验→wiki-vault→下次查询 |
|
||||
| 渐进式披露 | Hermes | 先查 summary,按需读全文 |
|
||||
|
||||
## 三、设计决策(对齐 #11 四层架构)
|
||||
|
||||
> **层级体系严格对齐 [#11](./11-context-layers-redesign.md)**,不自创命名。
|
||||
|
||||
### 总览
|
||||
|
||||
| #11 层级 | 知识注入角色 | 本设计覆盖 | 注入方式 |
|
||||
|----------|------------|-----------|---------|
|
||||
| **L0 铁律层** | "做方案前先查 wiki-vault" | ✅ D16-1 | Hook 每轮强制注入 |
|
||||
| **L1 角色层** | TOOLS.md 知识库速查表 + SOUL.md Red Flags | ✅ D16-2 | Workspace 文件自动注入 |
|
||||
| **L2 引擎注入层** | 三种 handler 各注入 WikiGuideSection | ✅ D16-3 | PromptComposer 拼装 |
|
||||
| **L3 被动参考层** | wiki-query Skill 按需触发 | ✅ D16-4 | extraDirs Description 匹配 |
|
||||
| 运维层 | gap 闭环 cron job | ✅ D16-5 | 不属于上下文分层 |
|
||||
|
||||
### D16-1:L0 铁律层 — 新增一条 wiki 查询铁律
|
||||
|
||||
L0 只放跨系统通用的、不可绕过的行为底线。wiki 查询铁律和 GATE 门控同级。
|
||||
|
||||
**新增铁律**:
|
||||
|
||||
```
|
||||
<wiki-rule>
|
||||
做方案前先查 wiki-vault,有 1% 相关就要查。查不到记 knowledge-gaps.md。
|
||||
</wiki-rule>
|
||||
```
|
||||
|
||||
**注入方式**:和 `<gate-rules>` / `<delegation-rule>` 并列,Hook 每轮强制注入。
|
||||
|
||||
**覆盖范围**:所有 Agent、所有场景(不限于 moziplus spawn 的子任务)。
|
||||
|
||||
### D16-2:L1 角色层 — TOOLS.md + SOUL.md
|
||||
|
||||
#### TOOLS.md(✅ 已完成)
|
||||
|
||||
各 Agent workspace 的 TOOLS.md 中已有「LLM Wiki 知识库」段,包含:
|
||||
|
||||
- 速查表(场景 → 怎么做 → 什么时候用)
|
||||
- 检索原则(index.md → summary → grep → 整页读取,从便宜到昂贵)
|
||||
- 目录结构(wiki-vault / practices / concepts / skills / ...)
|
||||
- 铁律(做方案前先查、查不到记 gap)
|
||||
|
||||
#### SOUL.md Red Flags
|
||||
|
||||
在各 Agent 的 SOUL.md 中加入知识查询 Red Flags 表(和 Superpowers 一致):
|
||||
|
||||
| Agent 的想法 | 反驳 |
|
||||
|---|---|
|
||||
| "这个我以前做过" | 知识库可能已更新,查一下确认 |
|
||||
| "先做再说" | 做方案前查实践比做错了返工便宜 |
|
||||
| "这个领域我熟悉" | 熟悉≠知道最新实践,wiki-vault 持续更新 |
|
||||
| "查知识库浪费时间" | 重复踩坑浪费的时间远大于查询时间 |
|
||||
|
||||
### D16-3:L2 引擎注入层 — 三种 handler 各注入 WikiGuideSection
|
||||
|
||||
L2 是 BootstrapBuilder/PromptComposer 动态拼装的 prompt 段。当前有三种 handler,各有自己的 PromptSection 实现:
|
||||
|
||||
#### 当前 handler 结构
|
||||
|
||||
| Handler | Sections(priority) | 有 wiki 引导? |
|
||||
|---------|---------------------|--------------|
|
||||
| **TaskHandler** | Context(10) → Prior(20) → RoleSkill(30) → API(40) → Constraints(50) | ❌ |
|
||||
| **MailHandler** | Context(10) → API(40) → Constraints(50) | ❌ |
|
||||
| **ToolchainHandler** | Context(10) → API(40) → Constraints(50) | ❌ |
|
||||
|
||||
#### 新增 WikiGuideSection(priority=60,PRIORITY_EXTENSION)
|
||||
|
||||
创建一个**通用 PromptSection**,三种 handler 的 `get_sections()` 都注入:
|
||||
|
||||
```python
|
||||
# 可放在 prompt_composer.py 或独立文件,三种 handler 共用
|
||||
|
||||
class WikiGuideSection:
|
||||
"""知识查询引导段 — 引导 Agent 在关键决策点查 wiki-vault。"""
|
||||
|
||||
name: str = "wiki_guide"
|
||||
priority: int = 60 # PRIORITY_EXTENSION
|
||||
|
||||
WIKI_GUIDE = (
|
||||
"## 知识查询引导\n"
|
||||
"涉及方案设计、编码实现、故障排查时,先查 wiki-vault 相关实践:\n"
|
||||
"- 路径:/Volumes/KnowledgeBase/wiki-vault/\n"
|
||||
"- 速查:index.md → grep 关键词 → summary 字段 → 按需读全文\n"
|
||||
"- 查不到:在 _meta/knowledge-gaps.md 记录"
|
||||
)
|
||||
|
||||
def render(self, context: PromptContext) -> str:
|
||||
return self.WIKI_GUIDE
|
||||
|
||||
def should_include(self, context: PromptContext) -> bool:
|
||||
return True
|
||||
```
|
||||
|
||||
#### 三种 handler 改动
|
||||
|
||||
每种 handler 的 `get_sections()` 末尾加 `WikiGuideSection()`:
|
||||
|
||||
```python
|
||||
# TaskHandler
|
||||
def get_sections(self) -> list:
|
||||
return [
|
||||
TaskContextSection(),
|
||||
PriorOutputsSection(),
|
||||
RoleSkillSection(),
|
||||
TaskApiSection(),
|
||||
TaskConstraintsSection(),
|
||||
WikiGuideSection(), # ← 新增
|
||||
]
|
||||
|
||||
# MailHandler
|
||||
def get_sections(self) -> list:
|
||||
return [
|
||||
MailContextSection(),
|
||||
MailApiSection(),
|
||||
MailConstraintsSection(),
|
||||
WikiGuideSection(), # ← 新增
|
||||
]
|
||||
|
||||
# ToolchainHandler
|
||||
def get_sections(self) -> list:
|
||||
return [
|
||||
ToolchainContextSection(),
|
||||
ToolchainApiSection(),
|
||||
ToolchainConstraintsSection(),
|
||||
WikiGuideSection(), # ← 新增
|
||||
]
|
||||
```
|
||||
|
||||
#### 为什么三种 handler 都需要
|
||||
|
||||
- **TaskHandler**:executor 做方案/编码,最需要查实践
|
||||
- **ToolchainHandler**:CI 失败排查、部署问题,有相关运维实践可参考
|
||||
- **MailHandler**:request 类型回复杂问题时也可能需要查已有经验
|
||||
|
||||
#### token 开销
|
||||
|
||||
WikiGuideSection 固定 ~60 字(~30 tokens),对 L2 预算影响可忽略。
|
||||
|
||||
### D16-4:L3 被动参考层 — wiki-query Skill
|
||||
|
||||
#### 现状
|
||||
|
||||
`wiki-query` Skill 已部署在 `~/.sanguo_projects/sanguo_mozi/skills/wiki/wiki-query/SKILL.md`,description 包含中文触发词:
|
||||
|
||||
> 调查、研究、分析、优秀实践、最佳实践、经验、怎么做X、有没有X的经验、以前怎么处理的
|
||||
|
||||
#### 触发机制
|
||||
|
||||
Agent 通过 extraDirs 加载 Skill header(name + description),按 Description 匹配自主 `read` 全文。这是标准 L3 行为,和 #11 设计一致。
|
||||
|
||||
#### 待确认:extraDirs 子目录递归
|
||||
|
||||
wiki-query 在 `skills/wiki/wiki-query/` 子目录下。需确认 moziplus spawn 子 agent 时 extraDirs 是否递归扫描子目录。如果不递归,需要:
|
||||
- 方案 A:把 wiki-query 移到 `skills/` 顶层
|
||||
- 方案 B:配置 extraDirs 包含 `skills/wiki/` 子目录
|
||||
|
||||
### D16-5:知识 gap 记录 + 定时任务(运维层)
|
||||
|
||||
> 不属于上下文分层体系,是独立的运维流程。
|
||||
|
||||
#### gap 记录机制(已有基础设施)
|
||||
|
||||
- **位置**:`/Volumes/KnowledgeBase/wiki-vault/_meta/knowledge-gaps.md`
|
||||
- **格式**:`- [日期] Agent名查"主题" → 待处理`
|
||||
- **已有 20+ 条历史记录**,处理后标注 `→ 已建立 ✅`
|
||||
|
||||
wiki-query Skill 的 Step 5 已内置 gap 记录逻辑。
|
||||
|
||||
#### 定时任务(已有 cron 基础)
|
||||
|
||||
| 任务 | 时间 | 内容 | 状态 |
|
||||
|------|------|------|------|
|
||||
| wiki-daily-update | 每天 04:00 | 处理 knowledge gaps + 当天经验总结 → 写入 wiki-vault | ✅ 已有 cron,需完善 |
|
||||
| pangtong-vault-sync | 每天 05:00 | 同步 wiki-vault 到 agent workspace | ✅ 已有 |
|
||||
|
||||
**wiki-daily-update 完善内容**:
|
||||
1. 读取 knowledge-gaps.md 中"待处理"条目
|
||||
2. 对每个 gap:搜索 knowledge_base 是否有相关源码/文档 → 有则提炼写入 wiki-vault
|
||||
3. 搜索最近一天的 jsonl 日志,提取有价值的经验
|
||||
4. 新建或更新 wiki-vault 页面
|
||||
5. 更新 knowledge-gaps.md(标记为"已建立 ✅"或"无KB内容,跳过")
|
||||
|
||||
### D16-6:和 #11 各层关系总结
|
||||
|
||||
| #11 层级 | #11 原始定义 | 知识注入贡献 | 本设计 |
|
||||
|---------|------------|------------|--------|
|
||||
| L0 铁律 | GATE 门控 + Delegation + 安全底线 | wiki 查询铁律 | ✅ D16-1 |
|
||||
| L1 角色 | SOUL.md + AGENTS.md + TOOLS.md + MEMORY.md | TOOLS.md 速查表 + SOUL.md Red Flags | ✅ D16-2 |
|
||||
| L2 引擎 | 任务上下文 + 角色操作规范 + 硬约束 | WikiGuideSection 通用段 | ✅ D16-3 |
|
||||
| L3 参考 | A/B/C/D 类 Skill,靠 Description 触发 | wiki-query Skill | ✅ D16-4 |
|
||||
| 运维 | — | gap 闭环 cron job | ✅ D16-5 |
|
||||
|
||||
### D16-7:为什么不做 PromptComposer 自动注入知识全文
|
||||
|
||||
1. **token 浪费**:每次任务都注入可能不相关的知识
|
||||
2. **覆盖范围有限**:只影响 moziplus 子任务 Agent
|
||||
3. **Agent 主动查询更精准**:知道自己缺什么知识,按需查询
|
||||
|
||||
## 四、改动清单
|
||||
|
||||
### 4.1 已完成 ✅
|
||||
|
||||
| 改动 | 文件 | 层级 | 说明 |
|
||||
|------|------|------|------|
|
||||
| TOOLS.md 知识库段 | 各 Agent workspace TOOLS.md | L1 | 速查表 + 检索原则 + 目录结构 + 铁律 |
|
||||
| wiki-query Skill 部署 | `skills/wiki/wiki-query/SKILL.md` | L3 | 中文触发词 + 渐进式检索协议 |
|
||||
| knowledge-gaps.md | `_meta/knowledge-gaps.md` | 运维 | 已有 20+ 条记录 |
|
||||
| wiki-daily-update cron | cron job | 运维 | 每天 04:00,需完善处理逻辑 |
|
||||
| pangtong-vault-sync cron | cron job | 运维 | 每天 05:00 |
|
||||
|
||||
### 4.2 待实现
|
||||
|
||||
| 改动 | 文件 | 层级 | 说明 |
|
||||
|------|------|------|------|
|
||||
| L0 wiki 铁律 | Hook 注入配置(`prependContext`) | L0 | 新增 `<wiki-rule>` 段 |
|
||||
| SOUL.md Red Flags | 各 Agent workspace SOUL.md | L1 | 知识查询 Red Flags 表 |
|
||||
| WikiGuideSection | `prompt_composer.py` 或独立文件 | L2 | 通用 PromptSection,三种 handler 共用 |
|
||||
| TaskHandler 注入 | `task_handler.py` `get_sections()` | L2 | 末尾加 `WikiGuideSection()` |
|
||||
| MailHandler 注入 | `mail_handler.py` `get_sections()` | L2 | 末尾加 `WikiGuideSection()` |
|
||||
| ToolchainHandler 注入 | `toolchain_handler.py` `get_sections()` | L2 | 末尾加 `WikiGuideSection()` |
|
||||
| extraDirs 递归确认 | moziplus spawn 配置 | L3 | 确认 wiki-query 子目录可被发现 |
|
||||
| wiki-daily-update 完善 | cron job 脚本 | 运维 | gap 处理 + jsonl 经验提取 |
|
||||
|
||||
### 4.3 不做
|
||||
|
||||
| 项目 | 原因 |
|
||||
|------|------|
|
||||
| PromptComposer 知识全文注入 | token 浪费,Agent 主动查询更精准 |
|
||||
| experiences 表 | wiki-vault 已覆盖,不重复建设 |
|
||||
| 新 Skill(除 wiki-query 外) | wiki-query 已有,不需要新的 |
|
||||
|
||||
## 五、风险
|
||||
|
||||
| 风险 | 概率 | 缓解 |
|
||||
|------|------|------|
|
||||
| Agent 不主动查 wiki | 中 | L0 铁律强制 + L2 引导 + L3 Description 触发,三层保障 |
|
||||
| wiki-query 在子目录不被 extraDirs 发现 | 中 | 确认后决定移顶层或配置子目录 |
|
||||
| wiki-daily-update gap 处理质量不够 | 低 | 人工审核 + 逐步完善 |
|
||||
| WikiGuideSection 增加 token | 低 | 固定 ~30 tokens,影响可忽略 |
|
||||
@@ -391,7 +391,11 @@ def verify_completion(self, task_id: str, db_path: Path) -> VerifyResult:
|
||||
|
||||
#### 完整设计
|
||||
|
||||
三分路的详细伪代码、失败上限、决策依据见 §5.2.1~§5.2.3(on_failure 分路处理详细设计)。
|
||||
三分路的详细设计见 §6.4(基础设施 Issue 转交流程)和 toolchain_handler.py 实现(`_handle_infrastructure_failure` / `_classify_failure`)。
|
||||
|
||||
#### 首次 steps 分支指引
|
||||
|
||||
三分路是 verify 失败后的兜底机制。此外,ci_failure 和 deploy_failure 的首次 toolchain task steps 中**已包含分支指引**——agent 在执行过程中自行判断失败原因,如果是基础设施问题则直接创建 Issue 指派 jiangwei-infra(见 §6.4)。三分路作为第二道防线,覆盖 agent 未正确判断或未执行分支的情况。
|
||||
|
||||
### 5.3 action_report comment 格式
|
||||
|
||||
@@ -431,9 +435,9 @@ Agent 可能写了 action_report 但没真做。缓解机制:
|
||||
| Review 请求 → reviewer | review_request | toolchain | 4 步 | 读 diff + 审查 + 提交 Review + report |
|
||||
| Review 有新提交 → reviewer | review_updated | toolchain | 4 步 | 读 diff + 检查修改 + 提交 Review + report |
|
||||
| Review 评论 → PR 作者 | review_comment | toolchain | 3 步 | 查看评论 + 响应(修改/回复)+ report |
|
||||
| CI 失败 → PR 作者 | ci_failure | toolchain | 4 步 | 查 CI 日志 + 修测试 + push + report |
|
||||
| Issue 指派 → 开发者 | issue_assigned | toolchain | 6 步 | 创建分支 + 编码 + push + CI + PR + report |
|
||||
| 部署失败 → 运维 | deploy_failure | toolchain | 4 步 | 查日志 + 排查 + 修+重部署 + report |
|
||||
| CI 失败 → PR 作者 | ci_failure | toolchain | 3 步 | 查 CI 日志 + 分支判断(代码问题自己修 / 基础设施问题提 Issue 给姜维)+ report |
|
||||
| Issue 指派 → 开发者 | issue_assigned / infrastructure_failure | toolchain | 6 步(编码)或 4 步(运维) | 按 label 分流:type/infrastructure → 运维排查;其他 → 创建分支 + 编码 + push + CI + PR + report |
|
||||
| 部署失败 → 运维 | deploy_failure | toolchain | 3 步 | 查日志 + 分支判断(代码/配置问题自己修 / 基础设施问题提 Issue 给姜维)+ report |
|
||||
| @mention → 被@者 | mention | toolchain | 按 guidance | 按 mention 模板的 response_guidance + report |
|
||||
| PR 合并 → PR 作者 | review_merged | toolchain | 0 步 | 纯通知,走 _send_toolchain_task(steps 为空,verify 始终通过) |
|
||||
|
||||
@@ -502,29 +506,42 @@ event_type: ci_failure
|
||||
action_type: ci_failure
|
||||
steps:
|
||||
1. 查看完整 CI 日志(PR 页面或 Gitea Actions 页面)
|
||||
2. 修复失败的测试
|
||||
3. push → CI 自动重跑
|
||||
4. 提交 action report
|
||||
2. 根据 CI 日志判断失败原因类型:
|
||||
a. 代码问题(lint/test 失败)→ 修复失败的测试 → push 到原分支 → CI 自动重跑
|
||||
b. 基础设施问题(runner 环境/Python/venv/Gitea/网络故障)→ 在该仓库创建 Issue 指派 jiangwei-infra(见 §6.4),label 必须包含 type/infrastructure
|
||||
3. 提交 action report — 报告中说明判断的原因类型和执行的操作
|
||||
context:
|
||||
pr_number, repo, branch, error_summary
|
||||
```
|
||||
|
||||
**分支设计说明**:原设计假设"CI 失败 = 代码问题",steps 只有"修测试 + push"一条路径。实际运行中发现 CI 失败可能是 runner 环境故障(如 ensurepip 失败),agent 判断为基础设施问题后不知道该做什么。现在 steps 中明确两条分支,agent 自行判断后走对应路径。
|
||||
|
||||
#### Issue 指派 → 开发者
|
||||
|
||||
```
|
||||
event_type: issue_assigned
|
||||
action_type: issue_assigned
|
||||
steps:
|
||||
event_type: issue_assigned 或 infrastructure_failure
|
||||
action_type: issue_assigned 或 infrastructure_failure
|
||||
steps(按 label 分流):
|
||||
|
||||
# 默认路径(编码任务):
|
||||
1. 创建分支 fix/{issue_number}-{brief}
|
||||
2. 编码 + 写 UT
|
||||
3. push → 等 CI
|
||||
4. CI 通过后创建 PR(Gitea API: POST /repos/{repo}/pulls)
|
||||
5. 等 Review
|
||||
6. 提交 action report
|
||||
|
||||
# type/infrastructure label 路径(运维任务):
|
||||
1. 根据 Issue body 中的错误来源和日志片段排查问题
|
||||
2. 修复基础设施问题(如修复 CI runner 环境、恢复网络、重启服务等)
|
||||
3. 修复后在 Issue 上 comment 说明修复方式和结果
|
||||
4. 提交 action report
|
||||
context:
|
||||
issue_number, repo, issue_title, labels, issue_body, brief
|
||||
```
|
||||
|
||||
**label 分流说明**:issue_assigned handler 检查 label 中是否包含 `type/infrastructure`。如果是,走运维排查 steps(event_type 设为 infrastructure_failure,verify 始终 auto-pass 防递归);否则走编码 steps。
|
||||
|
||||
#### 部署失败 → 运维
|
||||
|
||||
```
|
||||
@@ -532,9 +549,10 @@ event_type: deploy_failure
|
||||
action_type: deploy_failure
|
||||
steps:
|
||||
1. 检查 deploy 日志
|
||||
2. 排查失败原因
|
||||
3. 修复并重新部署
|
||||
4. 提交 action report
|
||||
2. 根据 deploy 日志判断失败原因类型:
|
||||
a. 代码/配置问题(rsync 路径错、依赖缺失、启动失败)→ 修复 → 重新部署
|
||||
b. 基础设施问题(Gitea 不可用、网络不通、磁盘满、SSH 故障)→ 在该仓库创建 Issue 指派 jiangwei-infra(见 §6.4),label 必须包含 type/infrastructure
|
||||
3. 提交 action report — 报告中说明判断的原因类型和执行的操作
|
||||
context:
|
||||
repo, commit_sha, reason
|
||||
```
|
||||
@@ -577,6 +595,69 @@ context:
|
||||
|
||||
**spawn 说明**:review_merged 仍会触发 spawn(Agent 只需阅读通知),verify auto-pass 后标 done。未来可优化为 ticker 直接 auto-done 跳过 spawn。
|
||||
|
||||
### 6.4 基础设施 Issue 转交流程
|
||||
|
||||
当 ci_failure / deploy_failure 的 agent 在调查后发现失败原因是基础设施问题(非代码问题),需要创建 Gitea Issue 指派 jiangwei-infra。
|
||||
|
||||
#### Issue 提在哪里
|
||||
|
||||
**根据问题来源决定**——哪个仓库的 CI/部署失败了,Issue 就提到那个仓库。CI runner 是全局共享的(一个 Mac mini),但 Issue 挂在触发的仓库最自然。如果 runner 故障影响多个仓库,各仓库会各自触发 ci_failure task,姜维看到任何一个 Issue 就能定位全局问题。
|
||||
|
||||
#### Issue 格式规范
|
||||
|
||||
```markdown
|
||||
## 问题描述
|
||||
|
||||
<简要描述问题现象>
|
||||
|
||||
## 错误来源
|
||||
|
||||
- 仓库: <repo>
|
||||
- PR/Commit: <链接>
|
||||
- CI/Deploy run: <Gitea Actions 页面链接>
|
||||
|
||||
## 日志关键片段
|
||||
|
||||
```
|
||||
<错误日志摘要,不需全文,但要让排查者看到关键信息>
|
||||
```
|
||||
|
||||
## 判断依据
|
||||
|
||||
<为什么判断为基础设施问题而非代码问题>
|
||||
```
|
||||
|
||||
**必填字段**:问题描述、错误来源(含链接)、日志片段、判断依据。Issue body 不完整会导致姜维无法高效排查。
|
||||
|
||||
**label 要求**:必须包含 `type/infrastructure`,用于 issue_assigned handler 分流(见下)。
|
||||
|
||||
#### issue_assigned handler label 分流
|
||||
|
||||
当 Gitea Issue 指派触发 webhook 时,issue_assigned handler 检查 label:
|
||||
|
||||
| label 包含 type/infrastructure | event_type | steps |
|
||||
|---|---|---|
|
||||
| 是 | infrastructure_failure | 运维排查:根据 Issue body 排查问题 → 修复 → Issue comment 说明修复方式 → action report |
|
||||
| 否 | issue_assigned | 编码:创建分支 → 编码 → push → CI → PR → 等 Review → action report |
|
||||
|
||||
基础设施路径的 verify 始终 auto-pass(防递归,已有逻辑覆盖)。
|
||||
|
||||
⚠️ **label 分流当前为设计目标**,toolchain_handler.py 尚未实现 issue_assigned 的 label 检查。当前只有 `_handle_infrastructure_failure`(verify 失败时)创建 infrastructure_failure task。issue_assigned handler 的 label 分流在后续代码 PR 中实现。
|
||||
|
||||
⚠️ **label 预创建**:使用前需确认仓库中已创建名为 `type/infrastructure` 的 label。sanguo_moziplus_v2 仓库已创建(ID=98)。其他仓库使用前需先创建。
|
||||
|
||||
#### API 指令位置
|
||||
|
||||
Issue 创建的 API 调用方式(curl 示例)统一在 ToolchainApiSection 中,与 action_report / comment 指引并列。steps 指令中不重复 API 调用方式,只描述"做什么"。
|
||||
|
||||
#### Red Flags 补充
|
||||
|
||||
硬约束 Red Flags 表新增一条:
|
||||
|
||||
| Agent 想法 | Red Flag 驳回 |
|
||||
|---|---|
|
||||
| "CI/部署失败不是我代码的问题,我什么也不用做" | ❌ 错!即使是基础设施问题,你也必须创建 Issue 指派 jiangwei-infra(body 含错误来源链接 + 日志 + 判断依据),并在 action report 中说明。不能只报告"不是我的问题"就完事 |
|
||||
|
||||
---
|
||||
|
||||
## §7. _send_toolchain_task 函数设计
|
||||
|
||||
@@ -0,0 +1,503 @@
|
||||
# API 聚合重构 + 工具链 Tab 设计
|
||||
|
||||
> **编号**: §18
|
||||
> **状态**: 设计中
|
||||
> **日期**: 2026-06-14
|
||||
> **作者**: 庞统(副军师)🐦
|
||||
> **审查**: 司马懿(mail-1781415763066 已回复,方案 B 调整版确认)
|
||||
|
||||
---
|
||||
|
||||
## 1. 背景与目标
|
||||
|
||||
### 1.1 问题
|
||||
|
||||
1. **blackboard_routes.py 膨胀**:572 行、22 个路由,task/comment/output/review/event/decision/observation/archive 全堆一个文件,维护困难
|
||||
2. **前端 N+1 请求**:打开 TaskModal 需要 5 次独立请求(task + events + subtasks + progress + comments),影响前端性能
|
||||
3. **工具链事件无前端展示**:`_toolchain` DB 隔离已完成,但前端无对应 Tab,工具链事件只能通过 Agent 收 Mail 感知
|
||||
|
||||
### 1.2 目标
|
||||
|
||||
1. 按领域拆分 blackboard_routes.py → 3 个文件
|
||||
2. 实现细粒度 expand 聚合接口,前端 1-2 次请求拿全任务详情
|
||||
3. 新增工具链 Tab(列表 + 详情 + 搜索栏)
|
||||
4. 任务列表支持标题搜索
|
||||
|
||||
### 1.3 不做
|
||||
|
||||
- checkpoint_routes.py 不纳入拆分(已独立)
|
||||
- mail_routes / toolchain_routes / project_routes 不动
|
||||
- SQL JOIN / batch query 性能优化(当前 SQLite 单写下多次查询可接受)
|
||||
|
||||
---
|
||||
|
||||
## 2. 后端 API 文件拆分
|
||||
|
||||
### 2.1 拆分方案(方案 B 调整版,司马懿确认)
|
||||
|
||||
| 新文件 | 内容 | 预估行数 |
|
||||
|--------|------|---------|
|
||||
| `task_routes.py` | task CRUD + create(含 AI 标题) + patch + progress + claim + status(含广播) + archive + archive-done | ~280 |
|
||||
| `task_relation_routes.py` | comments + outputs(含文件写入) + reviews + decisions + observations + events + experiences + summary | ~250 |
|
||||
| `shared.py` | `_bb()` / `_q()` / `_validate_project()` / `_task_to_dict()` / `_init_agent_ids()` / `_extract_mentions()` / 常量导入 | ~30 |
|
||||
|
||||
### 2.2 路由分配明细
|
||||
|
||||
**task_routes.py**(10 个路由):
|
||||
|
||||
| 路由 | 方法 | 函数 | 说明 |
|
||||
|------|------|------|------|
|
||||
| `/tasks` | GET | `list_tasks` | 列表(新增 `q` 搜索参数) |
|
||||
| `/tasks` | POST | `create_task` | 创建(含 `_generate_title`) |
|
||||
| `/tasks/{tid}` | GET | `get_task` | 详情(含 expand 聚合) |
|
||||
| `/tasks/{tid}` | PATCH | `patch_task` | 更新 |
|
||||
| `/tasks/{tid}/progress` | GET | `task_progress` | 进度 |
|
||||
| `/tasks/{tid}/claim` | POST | `claim_task` | 认领 |
|
||||
| `/tasks/{tid}/status` | POST | `update_status` | 状态流转(含广播逻辑) |
|
||||
| `/tasks/{tid}/archive` | POST | `archive_task` | 归档 |
|
||||
| `/tasks/archive-done` | POST | `archive_done_tasks` | 批量归档 |
|
||||
|
||||
**task_relation_routes.py**(13 个路由):
|
||||
|
||||
| 路由 | 方法 | 函数 | 说明 |
|
||||
|------|------|------|------|
|
||||
| `/tasks/{tid}/comments` | GET | `get_comments` | 评论列表 |
|
||||
| `/tasks/{tid}/comments` | POST | `add_comment` | 添加评论(含 @mention 提取) |
|
||||
| `/tasks/{tid}/outputs` | GET | `get_outputs` | 产出列表 |
|
||||
| `/tasks/{tid}/outputs` | POST | `write_output` | 写入产出(含文件写入逻辑) |
|
||||
| `/tasks/{tid}/decisions` | GET | `get_decisions` | 决策列表 |
|
||||
| `/tasks/{tid}/decisions` | POST | `add_decision` | 添加决策 |
|
||||
| `/tasks/{tid}/observations` | POST | `add_observation` | 添加观察 |
|
||||
| `/tasks/{tid}/reviews` | GET | `get_reviews` | 审查列表 |
|
||||
| `/tasks/{tid}/reviews` | POST | `add_review` | 添加审查 |
|
||||
| `/tasks/{tid}/events` | GET | `get_task_events` | 事件列表 |
|
||||
| `/tasks/{tid}/experiences` | GET | `get_task_experiences` | 经验列表 |
|
||||
| `/events` | GET | `get_events` | 项目级事件 |
|
||||
| `/summary` | GET | `task_summary` | 任务汇总 |
|
||||
|
||||
### 2.3 shared.py 共享件
|
||||
|
||||
从 blackboard_routes.py 提取到 shared.py:
|
||||
|
||||
| 符号 | 类型 | 说明 |
|
||||
|------|------|------|
|
||||
| `_validate_project()` | function | 项目 ID 校验 |
|
||||
| `_bb()` | function | Blackboard 实例获取 |
|
||||
| `_q()` | function | Queries 实例获取 |
|
||||
| `_task_to_dict()` | function | Task → dict 序列化 |
|
||||
| `_init_agent_ids()` | function | Agent ID 初始化 |
|
||||
| `_extract_mentions()` | function | @mention 提取 |
|
||||
| `VALID_STATUSES` | import | 从 db.py 重导出 |
|
||||
| `OUTPUT_TYPES` | import | 从 db.py 重导出 |
|
||||
|
||||
### 2.4 main.py 路由注册变更
|
||||
|
||||
```python
|
||||
# 拆分前
|
||||
from src.api.blackboard_routes import router as blackboard_router
|
||||
app.include_router(blackboard_router)
|
||||
|
||||
# 拆分后
|
||||
from src.api.task_routes import router as task_router
|
||||
from src.api.task_relation_routes import router as task_relation_router
|
||||
app.include_router(task_router)
|
||||
app.include_router(task_relation_router)
|
||||
```
|
||||
|
||||
URL prefix 不变:所有路由仍是 `/api/projects/{pid}/...`,前端 URL 零改动。
|
||||
|
||||
### 2.5 向后兼容
|
||||
|
||||
- 删除 `blackboard_routes.py`,所有引用指向新文件
|
||||
- `expand=all` 保持兼容(内部映射为全量 expand)
|
||||
- 不改变任何 API 的请求/响应格式(仅文件组织变化)
|
||||
|
||||
---
|
||||
|
||||
## 3. expand 聚合接口
|
||||
|
||||
### 3.1 设计
|
||||
|
||||
`GET /api/projects/{pid}/tasks/{tid}?expand=comments,outputs,reviews,events,decisions`
|
||||
|
||||
支持逗号分隔的细粒度选择,替代当前的 `expand=all`。
|
||||
|
||||
### 3.2 返回格式
|
||||
|
||||
```json
|
||||
{
|
||||
"task": { "id": "...", "title": "...", "status": "working", ... },
|
||||
"comments": {
|
||||
"items": [...],
|
||||
"total_count": 45,
|
||||
"limit": 20
|
||||
},
|
||||
"events": {
|
||||
"items": [...],
|
||||
"total_count": 120,
|
||||
"limit": 30
|
||||
},
|
||||
"outputs": [...],
|
||||
"reviews": [...],
|
||||
"decisions": [...]
|
||||
}
|
||||
```
|
||||
|
||||
### 3.3 limit 策略
|
||||
|
||||
| 关联资源 | expand 返回 | 分页支持 | 理由 |
|
||||
|----------|------------|---------|------|
|
||||
| comments | 最新 20 条 + total_count | `GET /comments?limit=50&offset=0` | 高频资源,长任务可能积累几十条 |
|
||||
| events | 最新 30 条 + total_count | `GET /events?limit=100&offset=0` | 运行几天可能上百条 |
|
||||
| outputs | 全部 | 不需要 | 通常 <5 条 |
|
||||
| reviews | 全部 | 不需要 | 通常 <5 条 |
|
||||
| decisions | 全部 | 不需要 | 通常 <5 条 |
|
||||
|
||||
前端拿到 `total_count > items.length` 时显示"还有 N 条",按需点击加载。
|
||||
|
||||
### 3.4 实现伪码
|
||||
|
||||
```python
|
||||
@router.get("/tasks/{task_id}")
|
||||
async def get_task(project_id: str, task_id: str,
|
||||
expand: Optional[str] = None):
|
||||
bb = _bb(project_id)
|
||||
task = bb.get_task(task_id)
|
||||
if not task:
|
||||
raise HTTPException(404, f"Task not found: {task_id}")
|
||||
|
||||
result = _task_to_dict(task)
|
||||
|
||||
if not expand:
|
||||
return result
|
||||
|
||||
expand_list = expand.split(",") if expand != "all" else [
|
||||
"comments", "outputs", "reviews", "events", "decisions"
|
||||
]
|
||||
|
||||
q = _q(project_id)
|
||||
|
||||
if "comments" in expand_list:
|
||||
all_comments = bb.get_comments(task_id)
|
||||
result["comments"] = {
|
||||
"items": [dict(c.__dict__) for c in all_comments[-20:]],
|
||||
"total_count": len(all_comments),
|
||||
"limit": 20,
|
||||
}
|
||||
|
||||
if "events" in expand_list:
|
||||
all_events = q.task_events(task_id)
|
||||
result["events"] = {
|
||||
"items": all_events[-30:],
|
||||
"total_count": len(all_events),
|
||||
"limit": 30,
|
||||
}
|
||||
|
||||
if "outputs" in expand_list:
|
||||
result["outputs"] = [dict(o.__dict__) for o in bb.get_outputs(task_id)]
|
||||
|
||||
if "reviews" in expand_list:
|
||||
result["reviews"] = [dict(r.__dict__) for r in bb.get_reviews(task_id)]
|
||||
|
||||
if "decisions" in expand_list:
|
||||
result["decisions"] = [dict(d.__dict__) for d in bb.get_decisions(task_id)]
|
||||
|
||||
return result
|
||||
```
|
||||
|
||||
### 3.5 性能分析
|
||||
|
||||
| 场景 | 当前(无 expand) | expand 后 | 改善 |
|
||||
|------|-----------------|-----------|------|
|
||||
| 打开 TaskModal | 5 次 HTTP 请求 | 2 次(task+expand + subtasks) | -60% 请求 |
|
||||
| 单次 expand 响应体 | — | ~5-15KB(典型) | 一次大请求 < 五次小请求 |
|
||||
| DB 查询次数 | 5 次(各端点独立查) | 5 次(expand 内部循环) | 相同,暂不优化 |
|
||||
|
||||
---
|
||||
|
||||
## 4. 任务列表搜索
|
||||
|
||||
### 4.1 设计
|
||||
|
||||
`GET /api/projects/{pid}/tasks?q=关键词`
|
||||
|
||||
在现有 `list_tasks` 基础上增加 `q` 查询参数,支持标题模糊搜索(SQL LIKE)。
|
||||
|
||||
### 4.2 实现
|
||||
|
||||
```python
|
||||
@router.get("/tasks")
|
||||
async def list_tasks(project_id: str, q: Optional[str] = None, ...):
|
||||
bb = _bb(project_id)
|
||||
tasks = bb.list_tasks(status=status, ...)
|
||||
|
||||
if q:
|
||||
q_lower = q.lower()
|
||||
tasks = [t for t in tasks if q_lower in (t.title or "").lower()]
|
||||
|
||||
return {"tasks": [_task_to_dict(t) for t in tasks]}
|
||||
```
|
||||
|
||||
**设计决策**:过滤在 Python 层做而非 SQL 层。
|
||||
- 理由:当前 `list_tasks` 已在 Python 层做 status 筛选,加一层 title 过滤一致性更好
|
||||
- 如果后续任务量大(>1000),再改为 SQL LIKE 查询
|
||||
|
||||
---
|
||||
|
||||
## 5. 前端:工具链 Tab
|
||||
|
||||
### 5.1 Tab 定义
|
||||
|
||||
```typescript
|
||||
// store.ts TabKey 新增
|
||||
| 'toolchain'
|
||||
|
||||
// TAB_DEFS 新增(插在 settings 前面)
|
||||
{ key: 'toolchain', label: '工具链', icon: '⛓️' },
|
||||
```
|
||||
|
||||
### 5.2 数据加载
|
||||
|
||||
```typescript
|
||||
// store.ts 新增
|
||||
toolchainTasks: any[];
|
||||
loadToolchain: async () => {
|
||||
const res = await fetch('/api/projects/_toolchain/tasks');
|
||||
const data = await res.json();
|
||||
set({ toolchainTasks: data.tasks || [] });
|
||||
}
|
||||
|
||||
// Tab 切换时加载
|
||||
if (tab === 'toolchain') s.loadToolchain();
|
||||
```
|
||||
|
||||
### 5.3 ToolchainPanel 组件
|
||||
|
||||
仿 MailPanel 结构,三个区域:
|
||||
|
||||
**搜索栏**(顶部):
|
||||
- 文本输入框,输入关键词实时过滤列表
|
||||
- 调用 `GET /api/projects/_toolchain/tasks?q=关键词`
|
||||
|
||||
**列表区**(左侧):
|
||||
- 工具链事件列表(时间倒序)
|
||||
- 每条显示:标题 + 时间 + 状态标签
|
||||
- 点击选中,高亮当前选中项
|
||||
|
||||
**详情区**(右侧):
|
||||
- 选中事件的完整内容
|
||||
- 调用 `GET /api/projects/_toolchain/tasks/{tid}?expand=comments` 获取详情
|
||||
- 展示:标题、描述、状态、评论(action_report 等)
|
||||
|
||||
### 5.4 和 Mail 的隔离
|
||||
|
||||
| 维度 | Mail Tab | 工具链 Tab |
|
||||
|------|---------|-----------|
|
||||
| 数据源 | `_mail` 项目 | `_toolchain` 项目 |
|
||||
| 事件类型 | Agent 间通信(inform/request) | 系统事件(CI/PR/部署/Review) |
|
||||
| 搜索 | 无(邮件量不大) | 有(工具链事件频率高) |
|
||||
|
||||
---
|
||||
|
||||
## 6. 测试设计
|
||||
|
||||
### 6.1 后端 API 拆分测试
|
||||
|
||||
**目标**:验证拆分后所有路由 URL 不变、行为不变。
|
||||
|
||||
**测试文件**:`tests/integration/test_api.py`(扩展现有)+ 新增 `tests/unit/test_task_routes.py`
|
||||
|
||||
| 测试类 | 测试用例 | 验证点 |
|
||||
|--------|---------|--------|
|
||||
| TestTaskRoutes | test_list_tasks | GET /tasks 返回格式不变 |
|
||||
| | test_list_tasks_with_search | q 参数过滤正确 |
|
||||
| | test_list_tasks_empty_q | q 为空时返回全部 |
|
||||
| | test_get_task | GET /tasks/{tid} 基本详情 |
|
||||
| | test_get_task_expand_comments | expand=comments 返回带 total_count + limit |
|
||||
| | test_get_task_expand_events | expand=events 返回带 total_count + limit |
|
||||
| | test_get_task_expand_outputs | expand=outputs 全量返回 |
|
||||
| | test_get_task_expand_multiple | expand=comments,outputs,reviews 组合 |
|
||||
| | test_get_task_expand_all | expand=all 向后兼容 |
|
||||
| | test_get_task_no_expand | 不传 expand 返回基本 task |
|
||||
| | test_create_task | POST 格式不变 |
|
||||
| | test_claim_task | 认领行为不变 |
|
||||
| | test_update_status | 状态流转不变 |
|
||||
| | test_patch_task | PATCH 不变 |
|
||||
| | test_archive_task | 归档不变 |
|
||||
|
||||
| 测试类 | 测试用例 | 验证点 |
|
||||
|--------|---------|--------|
|
||||
| TestTaskRelationRoutes | test_comments_crud | GET/POST comments 不变 |
|
||||
| | test_outputs_crud | GET/POST outputs 不变 |
|
||||
| | test_write_output_file | 文件写入逻辑不变 |
|
||||
| | test_reviews_crud | GET/POST reviews 不变 |
|
||||
| | test_decisions_crud | GET/POST decisions 不变 |
|
||||
| | test_observations_add | POST observations 不变 |
|
||||
| | test_events_list | GET events 不变 |
|
||||
| | test_experiences_list | GET experiences 不变 |
|
||||
| | test_project_events | GET /events 不变 |
|
||||
| | test_summary | GET /summary 不变 |
|
||||
|
||||
**兼容性验证脚本**:
|
||||
|
||||
```bash
|
||||
#!/bin/bash
|
||||
# tests/scripts/verify_api_compat.sh
|
||||
# 对比拆分前后所有路由 URL 和方法,确保零变化
|
||||
|
||||
echo "=== 拆分前路由清单 ==="
|
||||
# 从 git stash 或 main 分支提取
|
||||
git stash
|
||||
python -c "
|
||||
from src.main import app
|
||||
for route in app.routes:
|
||||
if hasattr(route, 'methods') and hasattr(route, 'path'):
|
||||
for m in sorted(route.methods):
|
||||
if m in ('GET','POST','PATCH','DELETE','PUT'):
|
||||
print(f'{m} {route.path}')
|
||||
" | sort > /tmp/routes_before.txt
|
||||
|
||||
git stash pop
|
||||
|
||||
echo "=== 拆分后路由清单 ==="
|
||||
python -c "
|
||||
from src.main import app
|
||||
for route in app.routes:
|
||||
if hasattr(route, 'methods') and hasattr(route, 'path'):
|
||||
for m in sorted(route.methods):
|
||||
if m in ('GET','POST','PATCH','DELETE','PUT'):
|
||||
print(f'{m} {route.path}')
|
||||
" | sort > /tmp/routes_after.txt
|
||||
|
||||
echo "=== Diff ==="
|
||||
diff /tmp/routes_before.txt /tmp/routes_after.txt
|
||||
if [ $? -eq 0 ]; then
|
||||
echo "✅ 路由完全一致"
|
||||
else
|
||||
echo "❌ 路由有差异"
|
||||
exit 1
|
||||
fi
|
||||
```
|
||||
|
||||
### 6.2 expand 聚合测试
|
||||
|
||||
**测试文件**:`tests/unit/test_expand_api.py`
|
||||
|
||||
| 测试用例 | 验证点 |
|
||||
|---------|--------|
|
||||
| test_expand_comments_limit | comments 返回最新 20 条 + total_count=25 |
|
||||
| test_expand_comments_are_latest | 验证返回的是最新 20 条(index 5-24) |
|
||||
| test_expand_events_limit | events 返回最新 30 条 + total_count=35 |
|
||||
| test_expand_outputs_full | outputs 全量返回(list 格式,不分页) |
|
||||
| test_expand_reviews_full | reviews 全量返回 |
|
||||
| test_expand_decisions_full | decisions 全量返回 |
|
||||
| test_expand_multiple_fields | expand=comments,outputs,reviews 组合,未请求的不返回 |
|
||||
| test_expand_all_compat | expand=all 向后兼容 |
|
||||
| test_no_expand | 不传 expand 只返回基本 task |
|
||||
| test_expand_invalid_field_ignored | 无效字段静默忽略 |
|
||||
|
||||
### 6.3 搜索测试
|
||||
|
||||
**测试文件**:`tests/unit/test_task_routes.py` 内 `TestTaskListRoutes`
|
||||
|
||||
| 测试用例 | 验证点 |
|
||||
|---------|--------|
|
||||
| test_list_tasks_with_search | q 参数标题模糊搜索 |
|
||||
| test_list_tasks_search_case_insensitive | 大小写不敏感 |
|
||||
| test_list_tasks_search_no_match | 无匹配返回空列表 |
|
||||
| test_list_tasks_search_empty_q | q 为空返回全部 |
|
||||
|
||||
### 6.4 前端测试(手动验证)
|
||||
|
||||
| 验证点 | 操作 | 预期 |
|
||||
|--------|------|------|
|
||||
| 工具链 Tab 出现 | 打开前端 | Tab 栏有 ⛓️ 工具链 |
|
||||
| 列表加载 | 点击工具链 Tab | 显示 _toolchain 事件列表 |
|
||||
| 搜索过滤 | 输入关键词 | 列表实时过滤 |
|
||||
| 详情展示 | 点击某条事件 | 右侧/弹窗显示完整内容 |
|
||||
| Tab 切换不丢数据 | 切到其他 Tab 再回来 | 数据保持 |
|
||||
|
||||
### 6.5 CI 集成
|
||||
|
||||
| 命令 | 说明 |
|
||||
|------|------|
|
||||
| `bash tests/scripts/verify_api_compat.sh` | 路由兼容性验证(CI 必跑) |
|
||||
| `pytest tests/unit/test_task_routes.py tests/unit/test_expand_api.py tests/integration/test_api.py -m "not e2e" -v` | 新增单元 + 集成测试 |
|
||||
|
||||
> 测试用例详细设计(fixture + 完整代码 + 覆盖矩阵)见 `docs/design/18-test-design.md`
|
||||
|
||||
---
|
||||
|
||||
## 7. 实施计划
|
||||
|
||||
### Phase 1: 后端 API 拆分(不含功能变更)
|
||||
|
||||
| 步骤 | 内容 | 验证 |
|
||||
|------|------|------|
|
||||
| 1.1 | 创建 `shared.py`,提取共享 helper | import 无报错 |
|
||||
| 1.2 | 创建 `task_routes.py`,迁移 10 个路由 | 路由注册成功 |
|
||||
| 1.3 | 创建 `task_relation_routes.py`,迁移 13 个路由 | 路由注册成功 |
|
||||
| 1.4 | 更新 `main.py` router 注册 | app 启动无报错 |
|
||||
| 1.5 | 删除 `blackboard_routes.py` | — |
|
||||
| 1.6 | 运行 `verify_api_compat.sh` | 路由清单 diff = 0 |
|
||||
| 1.7 | 运行现有测试 | 全量通过 |
|
||||
|
||||
### Phase 2: expand 聚合 + 搜索
|
||||
|
||||
| 步骤 | 内容 | 验证 |
|
||||
|------|------|------|
|
||||
| 2.1 | 重写 `get_task` expand 逻辑(细粒度) | TestExpandAPI 通过 |
|
||||
| 2.2 | `list_tasks` 加 `q` 参数 | TestTaskSearch 通过 |
|
||||
| 2.3 | 新增测试用例 | 覆盖率达标 |
|
||||
|
||||
### Phase 3: 前端工具链 Tab
|
||||
|
||||
| 步骤 | 内容 | 验证 |
|
||||
|------|------|------|
|
||||
| 3.1 | store.ts 新增 toolchain 数据加载 | — |
|
||||
| 3.2 | api.ts 新增 expand 调用封装 | — |
|
||||
| 3.3 | 创建 `ToolchainPanel.tsx` | 组件渲染正常 |
|
||||
| 3.4 | App.tsx 注册新 Tab | Tab 显示正确 |
|
||||
| 3.5 | TaskModal 改用 expand 减少 | 请求次数减少 |
|
||||
|
||||
### Phase 4: 联调 + 评审
|
||||
|
||||
| 步骤 | 内容 |
|
||||
|------|------|
|
||||
| 4.1 | 全量测试 `pytest -m "not e2e"` |
|
||||
| 4.2 | 发评审给司马懿 |
|
||||
| 4.3 | 前端手动验证 |
|
||||
|
||||
---
|
||||
|
||||
## 8. 风险评估
|
||||
|
||||
| 风险 | 级别 | 缓解 |
|
||||
|------|------|------|
|
||||
| 拆分后 import 路径断裂 | 中 | IDE 全局搜索 + 运行时验证 |
|
||||
| expand 返回体过大 | 低 | comments/events 有 limit |
|
||||
| 工具链事件量大影响前端 | 低 | 搜索栏 + 分页 |
|
||||
| expand=all 向后兼容 | 低 | 单独兼容分支处理 |
|
||||
|
||||
---
|
||||
|
||||
## 9. 评审记录
|
||||
|
||||
### 司马懿 mail-1781415763066(2026-06-14)
|
||||
|
||||
| 项目 | 结论 |
|
||||
|------|------|
|
||||
| 文件拆分 | 方案 B 调整版(task_routes + task_relation_routes + shared) |
|
||||
| expand | 细粒度,events/comments 带 limit+total_count |
|
||||
| 性能 | 当前 SQLite 多次查询可接受 |
|
||||
| checkpoint | 不纳入 |
|
||||
| _generate_title | 留在 task_routes.py |
|
||||
| write_output | 注意不是简单 CRUD |
|
||||
|
||||
---
|
||||
|
||||
## 10. 变更记录
|
||||
|
||||
| 日期 | 版本 | 内容 |
|
||||
|------|------|------|
|
||||
| 2026-06-14 | v1.0 | 初版设计 |
|
||||
@@ -0,0 +1,484 @@
|
||||
# §18 测试用例详细设计
|
||||
|
||||
> **关联**: `docs/design/18-api-refactor-and-toolchain-tab.md`
|
||||
> **日期**: 2026-06-14
|
||||
|
||||
---
|
||||
|
||||
## 1. 测试文件规划
|
||||
|
||||
| 文件 | 类型 | 测试数 | 说明 |
|
||||
|------|------|--------|------|
|
||||
| `tests/integration/test_api.py` | 集成 | 扩展现有 | 拆分后回归验证 |
|
||||
| `tests/unit/test_task_routes.py` | 单元 | 14 | task_routes 专项 |
|
||||
| `tests/unit/test_expand_api.py` | 单元 | 7 | expand 聚合专项 |
|
||||
| `tests/unit/test_task_search.py` | 单元 | 4 | 搜索专项 |
|
||||
| `tests/scripts/verify_api_compat.sh` | 脚本 | 1 | CI 路由兼容性 |
|
||||
|
||||
**总计**:26 个测试 + 1 个 CI 脚本
|
||||
|
||||
---
|
||||
|
||||
## 2. 预置 Fixture
|
||||
|
||||
```python
|
||||
# tests/conftest.py 新增(如果不存在则补充)
|
||||
|
||||
@pytest.fixture
|
||||
def expand_env(tmp_path):
|
||||
"""expand 测试环境:1 个 task + 预置关联数据"""
|
||||
project_root = tmp_path / "projects"
|
||||
project_root.mkdir()
|
||||
os.environ["BLACKBOARD_ROOT"] = str(project_root)
|
||||
|
||||
reg = ProjectRegistry(project_root)
|
||||
reg.create_project("test-proj", "Test Project", agents=["agent1"])
|
||||
|
||||
bb = Blackboard(project_root / "test-proj" / "blackboard.db")
|
||||
bb.create_task(Task(id="t1", title="Expand Test Task", task_type="coding"))
|
||||
|
||||
# 预置 25 条 comment
|
||||
for i in range(25):
|
||||
bb.add_comment("t1", agent="agent1", comment_type="general",
|
||||
content=f"Comment number {i}")
|
||||
|
||||
# 预置 5 条 output
|
||||
for i in range(5):
|
||||
bb.write_output("t1", agent="agent1",
|
||||
output_type="code",
|
||||
content=f"output content {i}",
|
||||
filename=f"file_{i}.py")
|
||||
|
||||
# 预置 3 条 review
|
||||
for i in range(3):
|
||||
bb.add_review("t1", reviewer="agent1",
|
||||
verdict="APPROVE",
|
||||
confidence=0.9,
|
||||
risk_level="low",
|
||||
summary=f"Review {i}")
|
||||
|
||||
# 预置 2 条 decision
|
||||
for i in range(2):
|
||||
bb.add_decision("t1", agent="agent1",
|
||||
decision_type="scope",
|
||||
rationale=f"Decision {i}")
|
||||
|
||||
# 预置 35 条 event
|
||||
from src.blackboard.queries import Queries
|
||||
q = Queries(project_root / "test-proj" / "blackboard.db")
|
||||
for i in range(35):
|
||||
q.add_event("t1", event_type="status_change",
|
||||
detail=f"Event {i}")
|
||||
|
||||
yield project_root
|
||||
del os.environ["BLACKBOARD_ROOT"]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. task_routes.py 测试(test_task_routes.py)
|
||||
|
||||
```python
|
||||
"""task_routes.py 路由测试 — 验证拆分后行为不变"""
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
from src.main import app
|
||||
|
||||
client = TestClient(app)
|
||||
pytestmark = pytest.mark.integration
|
||||
|
||||
|
||||
class TestTaskListRoutes:
|
||||
"""GET /tasks + 搜索"""
|
||||
|
||||
def test_list_tasks_basic(self, project_env):
|
||||
"""列表基本返回格式不变"""
|
||||
resp = client.get("/api/projects/test-proj/tasks")
|
||||
assert resp.status_code == 200
|
||||
data = resp.json()
|
||||
assert "tasks" in data
|
||||
assert isinstance(data["tasks"], list)
|
||||
|
||||
def test_list_tasks_with_search(self, project_env):
|
||||
"""q 参数搜索标题"""
|
||||
resp = client.get("/api/projects/test-proj/tasks?q=Existing")
|
||||
data = resp.json()
|
||||
assert len(data["tasks"]) == 1
|
||||
assert "Existing" in data["tasks"][0]["title"]
|
||||
|
||||
def test_list_tasks_search_case_insensitive(self, project_env):
|
||||
"""大小写不敏感"""
|
||||
resp = client.get("/api/projects/test-proj/tasks?q=existing")
|
||||
data = resp.json()
|
||||
assert len(data["tasks"]) == 1
|
||||
|
||||
def test_list_tasks_search_no_match(self, project_env):
|
||||
"""无匹配返回空列表"""
|
||||
resp = client.get("/api/projects/test-proj/tasks?q=nonexistent_xyz")
|
||||
data = resp.json()
|
||||
assert len(data["tasks"]) == 0
|
||||
|
||||
def test_list_tasks_search_empty_q(self, project_env):
|
||||
"""q 为空返回全部"""
|
||||
resp = client.get("/api/projects/test-proj/tasks?q=")
|
||||
data = resp.json()
|
||||
assert len(data["tasks"]) >= 1
|
||||
|
||||
|
||||
class TestTaskDetailRoutes:
|
||||
"""GET /tasks/{tid} + expand"""
|
||||
|
||||
def test_get_task_basic(self, project_env):
|
||||
"""无 expand 返回基本 task"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1")
|
||||
assert resp.status_code == 200
|
||||
data = resp.json()
|
||||
assert data["id"] == "t1"
|
||||
assert "comments" not in data # 无 expand 不含关联数据
|
||||
|
||||
def test_get_task_404(self, project_env):
|
||||
"""不存在的 task 返回 404"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/nonexistent")
|
||||
assert resp.status_code == 404
|
||||
|
||||
|
||||
class TestTaskActionRoutes:
|
||||
"""claim/status/patch/archive 行为不变"""
|
||||
|
||||
def test_claim_task(self, project_env):
|
||||
"""认领行为不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/claim",
|
||||
json={"agent": "agent1"})
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_update_status(self, project_env):
|
||||
"""状态流转不变"""
|
||||
client.post("/api/projects/test-proj/tasks/t1/claim",
|
||||
json={"agent": "agent1"})
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/status",
|
||||
json={"agent": "agent1", "status": "working"})
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_invalid_status_transition(self, project_env):
|
||||
"""非法状态转换返回 409"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/status",
|
||||
json={"agent": "agent1", "status": "done"})
|
||||
assert resp.status_code == 409
|
||||
|
||||
def test_patch_task(self, project_env):
|
||||
"""PATCH 更新不变"""
|
||||
resp = client.patch("/api/projects/test-proj/tasks/t1",
|
||||
json={"priority": 5})
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_archive_task(self, project_env):
|
||||
"""归档不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/archive",
|
||||
json={"agent": "agent1"})
|
||||
assert resp.status_code == 200
|
||||
|
||||
|
||||
class TestTaskCreateRoute:
|
||||
"""POST /tasks 创建行为不变"""
|
||||
|
||||
def test_create_task(self, project_env):
|
||||
"""创建格式不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks",
|
||||
json={"title": "New Task", "description": "test"})
|
||||
assert resp.status_code == 201
|
||||
data = resp.json()
|
||||
assert "id" in data
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 4. expand 聚合测试(test_expand_api.py)
|
||||
|
||||
```python
|
||||
"""expand 聚合接口测试"""
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
from src.main import app
|
||||
|
||||
client = TestClient(app)
|
||||
pytestmark = pytest.mark.integration
|
||||
|
||||
|
||||
class TestExpandComments:
|
||||
"""expand=comments"""
|
||||
|
||||
def test_comments_limit_and_count(self, expand_env):
|
||||
"""返回最新 20 条 + total_count=25"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=comments")
|
||||
data = resp.json()
|
||||
|
||||
comments = data["comments"]
|
||||
assert isinstance(comments, dict)
|
||||
assert len(comments["items"]) == 20
|
||||
assert comments["total_count"] == 25
|
||||
assert comments["limit"] == 20
|
||||
|
||||
def test_comments_are_latest(self, expand_env):
|
||||
"""返回的是最新 20 条(Comment 5-24)"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=comments")
|
||||
data = resp.json()
|
||||
first_content = data["comments"]["items"][0]["content"]
|
||||
last_content = data["comments"]["items"][-1]["content"]
|
||||
# 最新 20 条 = index 5 到 24
|
||||
assert "5" in first_content or "24" in last_content
|
||||
|
||||
|
||||
class TestExpandEvents:
|
||||
"""expand=events"""
|
||||
|
||||
def test_events_limit_and_count(self, expand_env):
|
||||
"""返回最新 30 条 + total_count=35"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=events")
|
||||
data = resp.json()
|
||||
|
||||
events = data["events"]
|
||||
assert isinstance(events, dict)
|
||||
assert len(events["items"]) == 30
|
||||
assert events["total_count"] == 35
|
||||
assert events["limit"] == 30
|
||||
|
||||
|
||||
class TestExpandFullResources:
|
||||
"""outputs/reviews/decisions 全量返回"""
|
||||
|
||||
def test_expand_outputs_full(self, expand_env):
|
||||
"""outputs 全量返回(5 条),格式是 list 不是 dict"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=outputs")
|
||||
data = resp.json()
|
||||
|
||||
outputs = data["outputs"]
|
||||
assert isinstance(outputs, list)
|
||||
assert len(outputs) == 5
|
||||
|
||||
def test_expand_reviews_full(self, expand_env):
|
||||
"""reviews 全量返回(3 条)"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=reviews")
|
||||
data = resp.json()
|
||||
|
||||
reviews = data["reviews"]
|
||||
assert isinstance(reviews, list)
|
||||
assert len(reviews) == 3
|
||||
|
||||
def test_expand_decisions_full(self, expand_env):
|
||||
"""decisions 全量返回(2 条)"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=decisions")
|
||||
data = resp.json()
|
||||
|
||||
decisions = data["decisions"]
|
||||
assert isinstance(decisions, list)
|
||||
assert len(decisions) == 2
|
||||
|
||||
|
||||
class TestExpandCombinations:
|
||||
"""组合 expand"""
|
||||
|
||||
def test_expand_multiple_fields(self, expand_env):
|
||||
"""expand=comments,outputs,reviews 组合"""
|
||||
resp = client.get(
|
||||
"/api/projects/test-proj/tasks/t1?expand=comments,outputs,reviews"
|
||||
)
|
||||
data = resp.json()
|
||||
|
||||
assert "comments" in data
|
||||
assert "outputs" in data
|
||||
assert "reviews" in data
|
||||
assert "events" not in data # 未请求
|
||||
assert "decisions" not in data
|
||||
|
||||
def test_expand_all_compat(self, expand_env):
|
||||
"""expand=all 向后兼容"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1?expand=all")
|
||||
data = resp.json()
|
||||
|
||||
# all 返回所有关联资源
|
||||
assert "comments" in data
|
||||
assert "outputs" in data
|
||||
assert "reviews" in data
|
||||
assert "events" in data
|
||||
assert "decisions" in data
|
||||
|
||||
def test_no_expand(self, expand_env):
|
||||
"""不传 expand 只返回基本 task"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1")
|
||||
data = resp.json()
|
||||
|
||||
assert "comments" not in data
|
||||
assert "outputs" not in data
|
||||
assert data["id"] == "t1"
|
||||
|
||||
def test_expand_invalid_field_ignored(self, expand_env):
|
||||
"""无效 expand 字段静默忽略"""
|
||||
resp = client.get(
|
||||
"/api/projects/test-proj/tasks/t1?expand=comments,invalid_field"
|
||||
)
|
||||
data = resp.json()
|
||||
|
||||
assert "comments" in data
|
||||
assert "invalid_field" not in data
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. task_relation_routes.py 回归测试
|
||||
|
||||
```python
|
||||
"""task_relation_routes.py 路由回归 — 验证拆分后行为不变"""
|
||||
|
||||
import pytest
|
||||
from fastapi.testclient import TestClient
|
||||
from src.main import app
|
||||
|
||||
client = TestClient(app)
|
||||
pytestmark = pytest.mark.integration
|
||||
|
||||
|
||||
class TestRelationRoutesRegression:
|
||||
"""关联路由回归测试"""
|
||||
|
||||
def test_comments_crud(self, project_env):
|
||||
"""GET/POST comments 不变"""
|
||||
# POST
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/comments",
|
||||
json={"agent": "a1", "comment_type": "general",
|
||||
"content": "test comment"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
# GET
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1/comments")
|
||||
assert resp.status_code == 200
|
||||
assert len(resp.json()["comments"]) >= 1
|
||||
|
||||
def test_outputs_crud(self, project_env):
|
||||
"""GET/POST outputs 不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/outputs",
|
||||
json={"agent": "a1", "type": "code",
|
||||
"content": "print('hello')"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1/outputs")
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_write_output_with_filename(self, project_env):
|
||||
"""output 含 filename 的文件写入不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/outputs",
|
||||
json={"agent": "a1", "type": "code",
|
||||
"content": "x = 1",
|
||||
"filename": "test.py"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
def test_write_output_invalid_type(self, project_env):
|
||||
"""output 无效 type 返回 422"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/outputs",
|
||||
json={"agent": "a1", "type": "invalid_type",
|
||||
"content": "x"})
|
||||
assert resp.status_code == 422
|
||||
|
||||
def test_reviews_crud(self, project_env):
|
||||
"""GET/POST reviews 不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/reviews",
|
||||
json={"reviewer": "a1", "verdict": "APPROVE",
|
||||
"confidence": 0.9, "risk_level": "low",
|
||||
"summary": "LGTM"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1/reviews")
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_decisions_crud(self, project_env):
|
||||
"""GET/POST decisions 不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/decisions",
|
||||
json={"agent": "a1", "decision_type": "scope",
|
||||
"rationale": "test"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1/decisions")
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_observations_add(self, project_env):
|
||||
"""POST observations 不变"""
|
||||
resp = client.post("/api/projects/test-proj/tasks/t1/observations",
|
||||
json={"agent": "a1", "observation_type": "note",
|
||||
"content": "observed"})
|
||||
assert resp.status_code == 201
|
||||
|
||||
def test_events_list(self, project_env):
|
||||
"""GET events 不变"""
|
||||
resp = client.get("/api/projects/test-proj/tasks/t1/events")
|
||||
assert resp.status_code == 200
|
||||
assert "events" in resp.json()
|
||||
|
||||
def test_project_events(self, project_env):
|
||||
"""GET /events 项目级事件不变"""
|
||||
resp = client.get("/api/projects/test-proj/events")
|
||||
assert resp.status_code == 200
|
||||
|
||||
def test_summary(self, project_env):
|
||||
"""GET /summary 不变"""
|
||||
resp = client.get("/api/projects/test-proj/summary")
|
||||
assert resp.status_code == 200
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. CI 集成
|
||||
|
||||
### .gitea/workflows/ci.yml 新增步骤
|
||||
|
||||
```yaml
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
# ... 现有步骤 ...
|
||||
|
||||
# API 兼容性验证
|
||||
- name: Verify API Compatibility
|
||||
run: |
|
||||
cd src/frontend && npm run build
|
||||
bash tests/scripts/verify_api_compat.sh
|
||||
|
||||
# 新增测试
|
||||
- name: Run API Tests
|
||||
run: |
|
||||
pytest tests/unit/test_task_routes.py \
|
||||
tests/unit/test_expand_api.py \
|
||||
tests/integration/test_api.py \
|
||||
-m "not e2e" -v
|
||||
```
|
||||
|
||||
### 本地开发验证流程
|
||||
|
||||
```bash
|
||||
# 1. 改完代码后先跑兼容性验证
|
||||
bash tests/scripts/verify_api_compat.sh
|
||||
|
||||
# 2. 跑全量测试
|
||||
pytest -m "not e2e" -v
|
||||
|
||||
# 3. 跑新增专项测试
|
||||
pytest tests/unit/test_task_routes.py tests/unit/test_expand_api.py -v
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. 测试覆盖矩阵
|
||||
|
||||
| 设计文档章节 | 测试文件 | 测试类 | 用例数 |
|
||||
|-------------|---------|--------|--------|
|
||||
| §2 路由拆分(兼容性) | verify_api_compat.sh | — | 1 |
|
||||
| §3.1 基本详情 | test_task_routes.py | TestTaskDetailRoutes | 2 |
|
||||
| §3.2 搜索 | test_task_routes.py | TestTaskListRoutes | 5 |
|
||||
| §3.3 动作路由 | test_task_routes.py | TestTaskActionRoutes | 5 |
|
||||
| §3.4 创建 | test_task_routes.py | TestTaskCreateRoute | 1 |
|
||||
| §4 expand comments | test_expand_api.py | TestExpandComments | 2 |
|
||||
| §4 expand events | test_expand_api.py | TestExpandEvents | 1 |
|
||||
| §4 expand 全量 | test_expand_api.py | TestExpandFullResources | 3 |
|
||||
| §4 expand 组合 | test_expand_api.py | TestExpandCombinations | 4 |
|
||||
| §5.2 关联回归 | test_api.py | TestRelationRoutesRegression | 10 |
|
||||
| **合计** | | | **34** |
|
||||
@@ -0,0 +1,810 @@
|
||||
# §19 Skill 生命周期管理 + 经验闭环四阶段设计
|
||||
|
||||
> 作者:庞统士元
|
||||
> 日期:2026-06-18(v2.0)
|
||||
> 状态:方案待确认
|
||||
> 前置:§14 Task 五层架构、§16 知识注入四层体系
|
||||
|
||||
## 变更摘要(v2.0)
|
||||
|
||||
| 变更项 | 原设计 | 新设计 | 理由 |
|
||||
|--------|--------|--------|------|
|
||||
| 蒸馏频率 | 庞统每天一次 | **双层 daily**:各 agent 03:00 自蒸馏 + 庞统 05:00 整合 | agent 是自己经验的最佳蒸馏者;庞统负责跨 agent 整合 |
|
||||
| 蒸馏者 | 庞统一人 | **双层**:L1 各 agent + L2 庞统 | 消除蒸馏者偏差;经验是 per-agent 的 |
|
||||
| .learnings/ | DISCOVER 数据源之一 | **废弃**。JSONL 是唯一数据源 | 信息冗余;agent 执行中不应分心写 .learnings/ |
|
||||
| 三重验证 | 跨任务复现 + 生成力 + 排他性 | **Recurrence-Count 机制**(融合 self-improvement skill) | ≥3 次自动触发提升,比主观判断更客观 |
|
||||
| Skill 数量 | 未明确 | **一个 skill:skill-management** + references/ 四阶段 | 减少上下文开销;DISCOVER/IMPROVE 是 cron 场景不需要独立 skill description |
|
||||
| self-improvement skill | 未提及 | **废弃**。优势融合到 DISCOVER 输出格式 | 职责重叠;统一为单一闭环 |
|
||||
| Skill 存放 | 未区分 | **per-agent 目录 + 公共目录** | agent 专属经验不污染其他 agent 上下文 |
|
||||
|
||||
## 1. 背景
|
||||
|
||||
moziplus v2.0 的 P4 剩余两项:
|
||||
- T7 C3:Skill 生命周期管理(draft → active → deprecated)
|
||||
- T7 C5:经验闭环 IMPROVE 阶段(DISCOVER → DISTILL → APPLY → IMPROVE 中的最后一步)
|
||||
|
||||
### 当前实现状态
|
||||
|
||||
| 组件 | 状态 | 问题 |
|
||||
|------|------|------|
|
||||
| `SkillRegistry`(skill_system.py) | 死代码 | 只有 register/match 方法,从未被外部调用 |
|
||||
| `SkillExecutor`(skill_system.py) | 死代码 | 从未被外部调用 |
|
||||
| `ExperienceDistiller`(experience.py) | 空转 | ticker 调用时没传 review_result 和 outputs,蒸馏函数收到 None 直接返回空 |
|
||||
| `ExperienceStore`(experience.py) | 空转 | experiences 目录全部为空 |
|
||||
| `experiences` 表(db.py) | 未使用 | 代码用 jsonl 文件不用 DB 表 |
|
||||
| Skill 生命周期 | 缺失 | 只有 enabled bool,无 draft/active/deprecated 状态流转 |
|
||||
|
||||
**结论**:现有的 experience.py 和 skill_system.py 需要重新设计,不是修补能解决的。
|
||||
|
||||
### 实际运行的知识体系
|
||||
|
||||
实际的 Skill 发现和加载走的是 **openclaw 原生 skill 机制**:
|
||||
- openclaw 扫描 skills 目录 → 生成 `<available_skills>` 列表注入 system prompt
|
||||
- Agent 按 description 匹配 → `read` SKILL.md → 按内容执行
|
||||
- moziplus 的 SkillRegistry/SkillExecutor 完全不参与
|
||||
|
||||
因此本设计**不重建 moziplus 的 skill 引擎**,而是基于 openclaw 原生机制构建。
|
||||
|
||||
## 2. 设计目标
|
||||
|
||||
1. 经验从「发现→蒸馏→应用→改善」形成完整闭环
|
||||
2. Skill 有明确的生命周期管理(draft → active → deprecated)
|
||||
3. 产物统一为 Skill,不再有 experiences.jsonl / .learnings/ 等中间形态散落各处
|
||||
4. 追踪 Skill 引用情况,支撑淘汰决策
|
||||
5. 充分利用 openclaw 已有的 skill_workshop 工具和 skill 加载机制
|
||||
6. **每个 agent 是自己经验的最佳蒸馏者**——经验 per-agent,精益求精
|
||||
|
||||
## 3. 核心设计决策
|
||||
|
||||
| # | 决策 | 理由 | 参考 |
|
||||
|---|------|------|------|
|
||||
| D1 | 统一产物:Skill-only | 不再有中间形态散落各处。Hermes 只有 Skill + Memory 两种载体,没有第三种 | Hermes skill_manage + memory_tool |
|
||||
| D2 | 生命周期通过 skill_workshop 管理 | OpenClaw 已有 pending → applied → rejected → quarantined 生命周期 | OpenClaw skill_workshop 工具 |
|
||||
| D3 | 蒸馏频率:双层 daily | L1 各 agent 每天 03:00 自蒸馏;L2 庞统每天 05:00 整合。有距离感的蒸馏优于即时记录 | self-improvement skill daily review;主公确认 |
|
||||
| D4 | 蒸馏者:双层(各 agent + 庞统) | L1 每个 agent 蒸馏自己的经验(自己最准);L2 庞统负责跨 agent 共性识别 + draft 审查 | Hermes skill_manage:「每个将军都应建立自己的 Skill 库」 |
|
||||
| D5 | 二级蒸馏抽象为根因模式 | 不固化在特定技术细节。description 描述「问题模式」而非「技术症状」 | Superpowers writing-skills:description = when not how |
|
||||
| D6 | 废弃 .learnings/ 作为数据源 | JSONL 已包含完整信息(工具调用、推理过程、错误输出)。.learnings/ 只是重复抄写,且打断 agent 执行流 | DISCOVER 统一采集;主公确认 |
|
||||
| D7 | 只创建一个 skill:skill-management | 四阶段的详细操作放到 references/ 目录。DISCOVER/IMPROVE 是 cron 场景不需要独立 skill description 常驻上下文 | moziplus skill-engineering practices §4:组合模式 |
|
||||
|
||||
## 4. L4 知识层:Skill Workshop
|
||||
|
||||
在现有 L0-L3 四层知识体系上新增 L4:
|
||||
|
||||
| 层级 | 名称 | 内容 | 加载方式 | 已有 |
|
||||
|------|------|------|---------|------|
|
||||
| L0 | 注入式上下文 | MEMORY.md / TOOLS.md | 每次 session 启动 | ✅ |
|
||||
| L1 | 确定性规则 | SOUL.md / AGENTS.md | 每次 session 启动 | ✅ |
|
||||
| L2 | 任务上下文 | BootstrapBuilder PromptSection | 按 task_type 注入 | ✅ |
|
||||
| L3 | 按需 Skill | openclaw skills | description 匹配 → agent read | ✅ |
|
||||
| **L4** | **Skill 生命周期** | **skill_workshop** | **draft → active → deprecated 管理** | **新增** |
|
||||
|
||||
L4 不是一个 prompt 层,而是 Skill 的**管理层**——负责 Skill 的创建、验证、应用、追踪、淘汰。
|
||||
|
||||
## 5. DISCOVER 阶段(双层)
|
||||
|
||||
### 5.1 L1 各 agent 自蒸馏(每天 03:00)
|
||||
|
||||
每个 agent 的 cron 扫描**自己当天**的 session JSONL,识别信号,蒸馏为 draft proposal。
|
||||
|
||||
**数据源(1 个)**:
|
||||
|
||||
| 数据源 | 位置 | 包含什么 |
|
||||
|--------|------|---------|
|
||||
| 自己的 Session JSONL | ~/.openclaw/agents/<agent_id>/sessions/*.jsonl | 当天完整思考过程、工具调用、错误恢复、用户对话 |
|
||||
|
||||
**不需要**扫描黑板/Gitea/Mail 等——那是 L2 庞统的职责。L1 聚焦自己的经验。
|
||||
|
||||
**信号识别(5 类高价值信号)**:
|
||||
|
||||
| 信号类型 | 从哪发现 | 识别特征 |
|
||||
|---------|---------|---------|
|
||||
| 失败模式 | task failed、CI failed、review rejected | 有明确的失败原因 |
|
||||
| 重复问题 | 跨多个任务出现同类问题 | 同关键词出现 ≥2 次 |
|
||||
| 决策转折 | rebuttal comment、需求澄清、主公纠正 | 原方向被推翻或修正 |
|
||||
| 新实践 | 设计文档新增、wiki-vault 新页面 | 之前没有的知识 |
|
||||
| 知识缺口 | agent 表达不确定、查不到的东西 | 查不到/不确定的东西 |
|
||||
|
||||
**输出**:draft skill proposal(提交到 skill_workshop,pending 状态)
|
||||
|
||||
### 5.2 L2 庞统整合(每天 05:00)
|
||||
|
||||
庞统的 cron 在 L1 全部完成后执行,扫描全量数据源 + 审查所有 L1 draft proposal。
|
||||
|
||||
**数据源(全量)**:
|
||||
|
||||
| 数据源 | 位置 | 包含什么 |
|
||||
|--------|------|---------|
|
||||
| 黑板 tasks | 各项目 blackboard.db | 任务生命周期:创建、分配、执行、完成/失败 |
|
||||
| 黑板 reviews | reviews 表 | 审查结论 + 逐步骤 verdict + suggestions |
|
||||
| 黑板 comments | comments 表 | @mention 讨论、rebuttal 推理、action_report |
|
||||
| 黑板 outputs | outputs 表 | 任务产出物内容 |
|
||||
| 黑板 events | events 表 | 状态变更、guardrail 拦截、异常检测 |
|
||||
| Gitea Issues/PRs | Gitea API | 问题报告、diff、review 评论 |
|
||||
| Gitea CI | Gitea Actions | lint/test/build 成功/失败 |
|
||||
| Mail | mail API | 跨 agent 通信、讨论推理过程 |
|
||||
| **所有 agent 的 Session JSONL** | ~/.openclaw/agents/*/sessions/ | 全团队完整思考过程 |
|
||||
| MEMORY.md | 各 agent workspace | 长期记忆、已有经验教训 |
|
||||
| knowledge-gaps.md | wiki-vault/_meta/ | 知识缺口 |
|
||||
| **L1 draft proposals** | skill_workshop pending | 各 agent 当天提交的 draft |
|
||||
|
||||
**核心职责**:
|
||||
|
||||
a. **跨 agent 共性模式识别**:张飞和关羽都在类似场景踩坑 → 合并为共享 Skill
|
||||
b. **审查 L1 draft proposals**:
|
||||
- APPROVE:质量达标的个人经验 → 变 active(仅作者 agent 可见)
|
||||
- MERGE:跨 agent 共性 → 合并为共享 Skill(所有 agent 可见)
|
||||
- REJECT:质量不够(附原因,agent 看到反馈后改进)
|
||||
c. **全局提升**:高确定性/高频率经验 → 提升到 AGENTS.md 规则(所有 agent 强制注入)
|
||||
|
||||
### 5.3 去重
|
||||
|
||||
同一事件在多个数据源出现(CI 失败 → toolchain task → mail → comment 讨论),按时间窗口 + 关键词去重,保留信息量最大的那条。
|
||||
|
||||
跨 agent 的同一模式,按 Pattern-Key 去重,合并为共享信号。
|
||||
|
||||
### 5.4 输出格式(融合 self-improvement skill 结构化字段)
|
||||
|
||||
每条候选信号包含:
|
||||
```
|
||||
信号类型 | 来源(task_id / PR / review / session)| 时间 | 简述(≤100 字)
|
||||
ID: SIG-YYYYMMDD-XXX
|
||||
Priority: low | medium | high | critical
|
||||
Status: pending | in_progress | resolved | promoted
|
||||
See Also: SIG-YYYYMMDD-XXX(关联信号)
|
||||
Recurrence-Count: N(同一模式出现次数)
|
||||
Pattern-Key: category.subcategory(稳定去重键,如 sync.field_mapping)
|
||||
```
|
||||
|
||||
**字段说明**(汲取自 self-improvement skill):
|
||||
|
||||
| 字段 | 用途 | 借鉴来源 |
|
||||
|------|------|---------|
|
||||
| ID | 唯一标识,便于交叉引用 | self-improvement logging format |
|
||||
| Priority | 优先级排序,critical/high 优先处理 | self-improvement priority guidelines |
|
||||
| Status | 生命周期跟踪 | self-improvement status lifecycle |
|
||||
| See Also | 关联相似信号,发现共性模式 | self-improvement recurring pattern detection |
|
||||
| Recurrence-Count | 同一模式出现次数,≥3 触发自动提升 | self-improvement recurring pattern + Skill Extraction Criteria |
|
||||
| Pattern-Key | 稳定去重键,跨 agent 匹配同一模式 | self-improvement Pattern-Key |
|
||||
|
||||
## 6. DISTILL 阶段
|
||||
|
||||
### 6.1 核心原则:HOW not WHAT
|
||||
|
||||
蒸馏的是「怎么做」不是「发生了什么」(nuwa-skill 实践 #5):
|
||||
|
||||
```
|
||||
❌ "PR #83 修复了 event_type 未知的问题"
|
||||
→ 这是 WHAT,无法复用
|
||||
|
||||
✅ "数据消费者与数据生产者解耦时,新增字段必须同步所有生产者的提取逻辑"
|
||||
→ 这是 HOW,可复用到任何消费者/生产者场景
|
||||
```
|
||||
|
||||
### 6.2 蒸馏产物 = Skill
|
||||
|
||||
直接产出 SKILL.md 格式或对现有 Skill 的 patch,提交到 skill_workshop。
|
||||
|
||||
**SKILL.md 编写规范**(参考 Superpowers writing-skills):
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: skill-name
|
||||
description: Use when [触发条件/问题模式描述],不描述工作流
|
||||
---
|
||||
|
||||
# Skill 标题
|
||||
|
||||
## 什么时候用
|
||||
(具体的触发场景,按问题模式描述,不按技术特定症状)
|
||||
|
||||
## 怎么做
|
||||
(根因分析 + 操作步骤)
|
||||
|
||||
## 常见错误
|
||||
(反模式:什么不该做)
|
||||
|
||||
## 来源
|
||||
(evidence:哪些 task/PR/review 提炼了这条经验)
|
||||
```
|
||||
|
||||
**description 关键规则**(Superpowers 的核心发现):
|
||||
- 只描述触发条件(when to use),**绝不描述工作流**(how)
|
||||
- 以「Use when...」开头
|
||||
- 描述问题模式,不描述技术特定症状
|
||||
- 原因:测试发现 description 如果总结了工作流,agent 会按 description 执行而跳过读完整 SKILL.md
|
||||
|
||||
### 6.3 蒸馏示例
|
||||
|
||||
**一级蒸馏**(从具体案例提取):
|
||||
|
||||
```yaml
|
||||
# 案例 1:PromptContext event_type 未知
|
||||
# 案例 2:PromptContext from_agent/mail_type 缺失(PR #26 D2)
|
||||
→ 共同根因:消费者/生产者字段同步问题
|
||||
|
||||
# 蒸馏为 Skill section(加到 trial-and-error-patterns):
|
||||
## 消费者/生产者字段同步
|
||||
|
||||
**什么时候用**:修改 dataclass 时,如果该 dataclass 由外部 JSON 提取填充
|
||||
|
||||
**怎么做**:
|
||||
1. 改 dataclass 定义
|
||||
2. 检查所有从 JSON 提取字段的代码路径,同步新增提取逻辑
|
||||
3. 检查所有构造该 dataclass 的调用点,同步新增参数
|
||||
4. 跑一次构建测试验证字段不为空
|
||||
|
||||
**常见错误**:只改 dataclass 不改提取逻辑 → 字段默认值为空 → 运行时不报错但行为异常
|
||||
```
|
||||
|
||||
**二级蒸馏**(从多个一级经验提取通用模式):
|
||||
|
||||
如果「消费者/生产者字段同步」经验在 ≥2 个不同场景复现(PromptContext + 其他),验证通过后,可以提升为独立 Skill 或固化到 AGENTS.md 规则。
|
||||
|
||||
### 6.4 验证机制(融合 self-improvement Recurrence-Count + Skill Extraction Criteria)
|
||||
|
||||
从 draft → active 的验证标准:
|
||||
|
||||
| 验证维度 | 标准 | 不通过的处理 |
|
||||
|---------|------|------------|
|
||||
| Recurrence-Count ≥ 2 | 同一 Pattern-Key 在 ≥2 个不同场景出现过 | 降级为 MEMORY.md 临时记录 |
|
||||
| 有生成力 | 能给出具体的操作指引 | 丢弃 |
|
||||
| 有排他性 | 不是「代码要测试」的常识 | 丢弃 |
|
||||
|
||||
**提升触发条件**(从 draft 提升为 active Skill,融合 self-improvement Skill Extraction Criteria):
|
||||
|
||||
全部满足时触发提升:
|
||||
- Recurrence-Count ≥ 3(同一模式 30 天内出现 3 次以上)
|
||||
- 跨 ≥2 个不同任务验证
|
||||
|
||||
**时间窗口**:Recurrence-Count 以 30 天为窗口,超过 30 天的记录不计入。6 个月内 3 次 vs 1 周内 3 次信号强度不同,30 天窗口确保经验仍然新鲜。
|
||||
|
||||
**Skill Extraction 质量 Gate**(汲取自 self-improvement skill):
|
||||
|
||||
| 标准 | 描述 |
|
||||
|------|------|
|
||||
| Recurring | 有 See Also 链接到 2+ 个相似信号 |
|
||||
| Verified | Status 是 resolved 且有工作修复 |
|
||||
| Non-obvious | 需要实际调试才能发现(不是常识) |
|
||||
| Broadly applicable | 不是项目特定,可跨场景复用 |
|
||||
|
||||
### 6.5 质量检查自动化
|
||||
|
||||
参考 nuwa-skill quality_check.py,对蒸馏产出做结构化检查:
|
||||
|
||||
| 检查项 | 标准 |
|
||||
|--------|------|
|
||||
| trigger 是否具体 | 不是「注意代码质量」这种泛泛而谈 |
|
||||
| action 是否可执行 | 不是「要小心」这种无操作指引 |
|
||||
| 是否与已有 Skill 重复 | 检查现有 skills 目录中是否已有覆盖 |
|
||||
| description 是否只含触发条件 | 不包含工作流描述 |
|
||||
|
||||
### 6.6 矛盾处理(nuwa-skill 实践 #10)
|
||||
|
||||
新经验与已有经验冲突时:
|
||||
- **时间性矛盾**(观点演化)→ 记录演化轨迹,以近期为主
|
||||
- **领域性矛盾**(不同场景不同规则)→ 分场景记录
|
||||
- **本质性张力**(价值观内在冲突)→ 标注为「核心张力」,两个版本都保留
|
||||
|
||||
**矛盾是特征,不是 Bug。** 强制调和会丢失关键信号。
|
||||
|
||||
### 6.7 蒸馏者(双层)
|
||||
|
||||
**L1:每个 agent 自己(每天 03:00 cron,各 agent 错开 15 分钟避免资源争用:03:00, 03:15, 03:30, ...)**
|
||||
1. 扫描自己的 session JSONL
|
||||
2. 用判断力提取根因模式(不是机械提取)
|
||||
3. 按 SKILL.md 格式产出
|
||||
4. 提交到 skill_workshop(pending proposal)
|
||||
|
||||
**L2:庞统(每天 05:00 cron)**
|
||||
1. 审查所有 agent 提交的 draft proposal(approve / merge / reject)
|
||||
2. 跨 agent 共性模式识别和合并
|
||||
3. 高频/高确定性经验提升到 AGENTS.md 规则
|
||||
|
||||
未来考虑半自动化(LLM 辅助草案 + agent 审阅确认)。
|
||||
|
||||
## 7. APPLY 阶段
|
||||
|
||||
### 7.1 统一走 openclaw skill 机制
|
||||
|
||||
**不新建 ExperienceSection 或任何 moziplus 自定义注入**。因为产物统一为 Skill,openclaw 已有的机制天然支持:
|
||||
|
||||
1. openclaw 扫描 skills 目录 → 生成 `<available_skills>` 列表
|
||||
2. Agent 按 description 匹配 → `read` SKILL.md
|
||||
3. Agent 按内容执行
|
||||
|
||||
### 7.2 Skill description 编写规范
|
||||
|
||||
这是 APPLY 阶段效果好坏的关键。参考 Superpowers writing-skills 的核心发现:
|
||||
|
||||
```yaml
|
||||
# ❌ BAD:描述了工作流,agent 会按 description 执行而跳过读 SKILL.md
|
||||
description: Use when modifying dataclass — checks all extraction points, runs tests, verifies non-null fields
|
||||
|
||||
# ✅ GOOD:只描述触发条件
|
||||
description: Use when modifying a dataclass that is populated from JSON extraction by another module
|
||||
|
||||
# ❌ BAD:太抽象
|
||||
description: Use for code quality
|
||||
|
||||
# ✅ GOOD:描述问题模式
|
||||
description: Use when a field added to a dataclass appears empty or as default value at runtime
|
||||
```
|
||||
|
||||
### 7.3 渐进式加载
|
||||
|
||||
openclaw 已有的机制:
|
||||
- L1:`<available_skills>` 列表(~100 token/skill,只有 name + description)
|
||||
- L2:Agent `read` SKILL.md(完整内容)
|
||||
- L3:SKILL.md 内引用的 references/ 文件(按需加载)
|
||||
|
||||
### 7.4 Skill 存放位置与可见性
|
||||
|
||||
agent 专属经验放到 agent 自己的 workspace skills 目录,全局共享 Skill 放到公共 skills 目录。openclaw 扫描时自动合并。
|
||||
|
||||
| Skill 位置 | 谁能看到 | 适用场景 |
|
||||
|-----------|---------|---------|
|
||||
| `~/.openclaw/workspace-zhangfei/skills/` | 只有张飞 | 编码模式、个人踩坑经验 |
|
||||
| `~/.openclaw/workspace-pangtong/skills/` | 只有庞统 | 规划经验、方向把控 |
|
||||
| `~/.openclaw/workspace-simayi/skills/` | 只有司马懿 | 审查技巧、挑战模式 |
|
||||
| `~/.sanguo_projects/sanguo_mozi/skills/` | 所有 moziplus agent | 团队共识、协作规范、通用实践 |
|
||||
|
||||
**设计原则**:
|
||||
- 个人经验不污染其他 agent 上下文(张飞的编码坑不需要司马懿看到)
|
||||
- 共性经验自动共享(庞统 MERGE 后放到公共目录)
|
||||
- openclaw 原生机制天然支持(扫描时合并所有 skills 目录)
|
||||
|
||||
## 8. IMPROVE 阶段
|
||||
|
||||
### 8.1 Skill 自我修补
|
||||
|
||||
参考 Hermes skill_manage 的设计哲学:
|
||||
|
||||
> "If you used a skill and hit issues not covered by it, patch it immediately."
|
||||
> "Skills that aren't maintained become liabilities."
|
||||
|
||||
Agent 使用 Skill 时发现问题(缺步骤、过时信息、命令变更)→ 立即通过 skill_workshop 提交 revise proposal(patch)。
|
||||
|
||||
这不需要定时任务,靠 agent 的主动维护。关键是在 agent 的 prompt 中注入这条规则(SOUL.md 或 AGENTS.md)。
|
||||
|
||||
### 8.2 引用追踪
|
||||
|
||||
**设计原则**:不追求精确归因,做时间维度的信号采集。
|
||||
|
||||
| 信号 | 采集方式 | 可信度 |
|
||||
|------|---------|--------|
|
||||
| Skill 最近被 read 的时间 | 扫描 session JSONL 中 `"tool":"read"` + SKILL.md 路径 | 中 |
|
||||
| Skill 在 available_skills 中被注入 | 扫描 JSONL 中 available_skills 列表 | 中(被注入但未必被用) |
|
||||
| Agent 在输出中提及了 skill name | grep skill name in assistant messages | 高(主动提到说明确实用了) |
|
||||
| Skill 文件最近修改时间 | git log / 文件 mtime | 高 |
|
||||
|
||||
**采集频率**:每周一次 cron,扫描过去 7 天的所有 session JSONL。
|
||||
|
||||
### 8.3 淘汰机制
|
||||
|
||||
**决策流程**:
|
||||
|
||||
```
|
||||
30 天无引用信号
|
||||
→ 生成淘汰候选报告(庞统审阅)
|
||||
→ 确认淘汰 → skill_workshop quarantine
|
||||
→ 保留观察 → 标注,下轮再查
|
||||
→ 更新后保留 → 修改 description / 内容,重置计时
|
||||
```
|
||||
|
||||
**注意**:openclaw 本身的 skill(~/.openclaw/plugin-skills/ 和全局 skills)也纳入追踪范围。主公可以据此决定哪些 openclaw skill 可以禁用。
|
||||
|
||||
### 8.4 经验提升路径
|
||||
|
||||
同一 Skill section 被频繁引用(≥5 次)且经过多次验证 → 考虑提升:
|
||||
|
||||
| 提升目标 | 条件 | 效果 |
|
||||
|---------|------|------|
|
||||
| 独立 Skill | 足够通用,有自己的触发条件 | 独立 SKILL.md,description 匹配 |
|
||||
| AGENTS.md 规则 | 确定性高,适用于所有 agent | L1 确定性注入,强制生效 |
|
||||
| guardrail | 安全相关,不可违反 | 强制检查 |
|
||||
|
||||
### 8.5 反馈到 DISCOVER
|
||||
|
||||
IMPROVE 发现的经验缺口(「这条 Skill 不适用 XXX 场景」)→ 写入 knowledge-gaps.md → 成为下一轮 DISCOVER L2 的输入。
|
||||
|
||||
## 9. 闭环全景
|
||||
|
||||
```
|
||||
DISCOVER L1(每天 03:00,各 agent cron)
|
||||
数据源:自己的 session JSONL
|
||||
信号识别:5 类高价值信号
|
||||
输出:draft skill proposal(structured,带 ID/Priority/Pattern-Key/Recurrence-Count)
|
||||
↓
|
||||
DISCOVER L2(每天 05:00,庞统 cron)
|
||||
数据源:全量 12 个数据源(含 L1 draft proposals)
|
||||
跨 agent 共性模式识别
|
||||
审查 draft proposals:approve / merge / reject
|
||||
↓
|
||||
DISTILL(L2 庞统执行)
|
||||
原则:HOW not WHAT(根因模式,不固化技术细节)
|
||||
验证:Recurrence-Count ≥ 2 + 生成力 + 排他性
|
||||
提升:Recurrence-Count ≥ 3 → 独立 Skill / AGENTS.md 规则
|
||||
质量:自动化检查 + 矛盾保留
|
||||
产物:Skill(通过 skill_workshop 管理)
|
||||
↓
|
||||
APPLY(实时,openclaw skill 机制)
|
||||
匹配:description 匹配 → agent read SKILL.md
|
||||
执行:agent 按内容执行
|
||||
自我修补:使用时发现问题 → 立即 revise proposal
|
||||
per-agent 隔离:专属 Skill 在 agent workspace,共享 Skill 在公共目录
|
||||
↓
|
||||
IMPROVE(每周 cron,庞统执行)
|
||||
追踪:scan JSONL 引用信号
|
||||
淘汰:30天无引用 → 庞统审查 → quarantine
|
||||
提升:高频引用 → 独立 Skill / AGENTS.md 规则 / guardrail
|
||||
反馈:知识缺口 → knowledge-gaps.md → 回到 DISCOVER L2
|
||||
```
|
||||
|
||||
## 10. 与现有实现的关系
|
||||
|
||||
| 组件 | 处理方式 |
|
||||
|------|---------|
|
||||
| `skill_system.py`(SkillRegistry/SkillExecutor) | **标记 deprecated,后续清理。** 死代码,实际不参与 skill 发现/加载 |
|
||||
| `experience.py`(ExperienceDistiller/ExperienceStore) | **标记 deprecated,后续清理。** 空转代码,experiences 目录全空 |
|
||||
| `experiences` 表 / `experience_tags` 表(db.py) | **保留表结构但不再写入。** 未来如果需要 DB 查询可以重新启用 |
|
||||
| ticker.py:336-348 经验蒸馏逻辑 | **移除。** 不再逐任务蒸馏,改为双层 daily cron |
|
||||
| `skill_workshop` 工具 | **核心使用。** 所有 Skill 生命周期通过它管理 |
|
||||
| openclaw `<available_skills>` 机制 | **核心依赖。** APPLY 阶段完全基于此 |
|
||||
| **self-improvement skill**(`~/.openclaw/workspace/skills/self-improving-agent/`) | **废弃。** 其优势(结构化 ID/Status/Priority/See Also/Recurrence-Count)已融合到 DISCOVER 输出格式中。原 skill 文件保留但标记 deprecated |
|
||||
| **.learnings/ 目录**(各 agent workspace) | **废弃。** JSONL 是唯一数据源。目录保留但不再写入新内容(历史数据保留) |
|
||||
| **SELF_IMPROVEMENT_REMINDER.md** | **废弃。** 规则已融合到 skill-management skill 中 |
|
||||
|
||||
## 11. 实现计划
|
||||
|
||||
| 步骤 | 内容 | 优先级 | 工作量 |
|
||||
|------|------|--------|--------|
|
||||
| S1 | 在 SOUL.md / AGENTS.md 加入 Skill 自我修补规则 + 双层 daily 蒸馏规则 | P0 | L1(改文案) |
|
||||
| S2 | 创建 skill-management Skill(主 SKILL.md + references/ 四阶段详细操作) | P0 | L2 |
|
||||
| S3 | 创建各 agent 的 03:00 cron(自蒸馏 L1) | P1 | L1 |
|
||||
| S4 | 创建庞统的 05:00 cron(整合 + 审查 L2) | P1 | L1-L2 |
|
||||
| S5 | 实现 IMPROVE cron:JSONL 引用追踪 + 淘汰报告(每周) | P2 | L2-L3 |
|
||||
| S6 | 清理 deprecated 代码(skill_system.py / experience.py / self-improvement skill / SELF_IMPROVEMENT_REMINDER.md) | P3 | L1 |
|
||||
|
||||
S1 和 S2 已完成(PR #85)。S3-S5 设计见下方 §11A。
|
||||
|
||||
## 11A. Cron 配置方案(S3-S5 详细设计)
|
||||
|
||||
### 设计决策
|
||||
|
||||
**每个 agent 用自己的 agentId 执行 L1 cron**,不由庞统代理。
|
||||
|
||||
理由(对照设计目标 D4):
|
||||
- L1 核心价值是"每个 agent 是自己经验的最佳蒸馏者"——agent 扫描自己的 JSONL,用自己的判断力识别信号
|
||||
- 如果庞统代理,变成庞统替别人蒸馏,消除不了蒸馏者偏差(D4 要解决的正是这个问题)
|
||||
- openclaw cron 原生支持 `agentId` 参数 + `sessionTarget: "isolated"`,技术上无障碍
|
||||
|
||||
### S3: L1 各 agent 自蒸馏 cron
|
||||
|
||||
6 个 agent,各创建一个 isolated cron,错开 15 分钟(和 discover-l1.md 时间表一致):
|
||||
|
||||
| Agent | agentId | cron 表达式 | 时区 |
|
||||
|-------|---------|-----------|------|
|
||||
| 张飞 | zhangfei-dev | `0 3 * * *` | Asia/Shanghai |
|
||||
| 关羽 | guanyu-dev | `15 3 * * *` | Asia/Shanghai |
|
||||
| 赵云 | zhaoyun-data | `30 3 * * *` | Asia/Shanghai |
|
||||
| 司马懿 | simayi-challenger | `45 3 * * *` | Asia/Shanghai |
|
||||
| 庞统 | pangtong-fujunshi | `0 4 * * *` | Asia/Shanghai |
|
||||
| 姜维 | jiangwei-infra | `15 4 * * *` | Asia/Shanghai |
|
||||
|
||||
**Cron 配置规范**(每个 L1 cron job):
|
||||
|
||||
```json
|
||||
{
|
||||
"schedule": { "kind": "cron", "expr": "<时间>", "tz": "Asia/Shanghai" },
|
||||
"sessionTarget": "isolated",
|
||||
"agentId": "<agent-id>",
|
||||
"payload": {
|
||||
"kind": "agentTurn",
|
||||
"message": "L1 自蒸馏 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/SKILL.md\n2. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/discover-l1.md\n3. 按 discover-l1.md 步骤执行自蒸馏\n4. 如有信号:蒸馏为 HOW 格式,使用 skill_workshop(action=create) 提交 draft proposal\n5. 如无有价值信号:不产出,这是正常的",
|
||||
"timeoutSeconds": 600
|
||||
},
|
||||
"delivery": { "mode": "announce" }
|
||||
}
|
||||
```
|
||||
|
||||
**设计要点**:
|
||||
- `sessionTarget: "isolated"`:每次创建临时 session,不污染 main session context
|
||||
- `delivery.mode: "announce"`:执行结果投递到 Control UI,保持可见性(早期使用 `none` 导致 cron 执行后零可见性,已修正)
|
||||
- `timeoutSeconds: 600`:10 分钟足够(扫描 JSONL + 蒸馏 + 提交 proposal)
|
||||
- message 指引 read SKILL.md + discover-l1.md:agent 按 references 指南执行,不依赖 memory
|
||||
|
||||
### S4: L2 庞统整合审查 cron
|
||||
|
||||
庞统的 L2 cron 在所有 L1 完成后执行(最后一个 agent 04:15 开始,L2 设在 05:00):
|
||||
|
||||
| 角色 | agentId | cron 表达式 | 时区 |
|
||||
|------|---------|-----------|------|
|
||||
| 庞统 | pangtong-fujunshi | `0 5 * * *` | Asia/Shanghai |
|
||||
|
||||
**Cron 配置**:
|
||||
|
||||
```json
|
||||
{
|
||||
"schedule": { "kind": "cron", "expr": "0 5 * * *", "tz": "Asia/Shanghai" },
|
||||
"sessionTarget": "isolated",
|
||||
"agentId": "pangtong-fujunshi",
|
||||
"payload": {
|
||||
"kind": "agentTurn",
|
||||
"message": "L2 整合审查 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/discover-l2.md\n2. 按 discover-l2.md 步骤执行:\n a. skill_workshop(action=list, status=pending) 获取所有 L1 draft proposals\n b. 全量数据源扫描,识别跨 agent 共性模式\n c. 逐个审查 proposal:approve / merge / reject\n d. 全局提升检查(Recurrence-Count >= 3 的经验提升为规则)\n e. 知识缺口反馈到 knowledge-gaps.md",
|
||||
"timeoutSeconds": 1200
|
||||
},
|
||||
"delivery": { "mode": "announce" }
|
||||
}
|
||||
```
|
||||
|
||||
**设计要点**:
|
||||
- `delivery.mode: "announce"`:审查决策结果投递到 Control UI,主公可见
|
||||
- `timeoutSeconds: 1200`(20 分钟):L2 需要扫描全量数据源 + 审查多个 proposal,时间更长
|
||||
- 庞统可以访问所有 agent 的 JSONL 和 skill_workshop proposals
|
||||
|
||||
### S5: IMPROVE 每周引用追踪 cron
|
||||
|
||||
庞统每周日 06:00 执行引用追踪(周日选活动量最低的时段):
|
||||
|
||||
| 角色 | agentId | cron 表达式 | 时区 |
|
||||
|------|---------|-----------|------|
|
||||
| 庞统 | pangtong-fujunshi | `0 6 * * 0` | Asia/Shanghai |
|
||||
|
||||
**Cron 配置**:
|
||||
|
||||
```json
|
||||
{
|
||||
"schedule": { "kind": "cron", "expr": "0 6 * * 0", "tz": "Asia/Shanghai" },
|
||||
"sessionTarget": "isolated",
|
||||
"agentId": "pangtong-fujunshi",
|
||||
"payload": {
|
||||
"kind": "agentTurn",
|
||||
"message": "IMPROVE 每周引用追踪 cron。请执行:\n1. read ~/.sanguo_projects/sanguo_mozi/skills/skill-management/references/improve.md\n2. 按 improve.md 步骤执行:\n a. 扫描过去 7 天所有 agent 的 session JSONL,采集 Skill 引用信号\n b. 生成淘汰候选报告(30 天无引用的 Skill)\n c. 庞统审阅决策:quarantine / 保留观察 / 更新后保留\n d. 经验提升检查(被频繁引用 >= 5 次的 Skill)\n e. 反馈知识缺口到 knowledge-gaps.md",
|
||||
"timeoutSeconds": 1800
|
||||
},
|
||||
"delivery": { "mode": "announce" }
|
||||
}
|
||||
```
|
||||
|
||||
**设计要点**:
|
||||
- `delivery.mode: "announce"`:淘汰/提升报告投递到 Control UI
|
||||
- `timeoutSeconds: 1800`(30 分钟):全量 JSONL 扫描是最重的操作
|
||||
- 每周一次频率足够——Skill 引用变化不会很快
|
||||
- 淘汰决策通过 skill_workshop quarantine 执行,提升决策通过手动编辑 AGENTS.md
|
||||
|
||||
### Cron 创建方式
|
||||
|
||||
使用 openclaw cron 工具创建。**不是 moziplus 管理**,而是直接在 openclaw 层面配置。
|
||||
|
||||
创建顺序:先 S3(L1),再 S4(L2),最后 S5(IMPROVE)。
|
||||
|
||||
创建后验证:`cron(action=list)` 确认所有 job 存在且 enabled=true。
|
||||
|
||||
### 去重和幂等
|
||||
|
||||
每个 cron job 的 name 包含 agent 名,避免命名冲突:
|
||||
- `l1-distill-zhangfei`
|
||||
- `l1-distill-guanyu`
|
||||
- `l1-distill-zhaoyun`
|
||||
- `l1-distill-simayi`
|
||||
- `l1-distill-pangtong`
|
||||
- `l1-distill-jiangwei`
|
||||
- `l2-review-pangtong`
|
||||
- `improve-weekly-pangtong`
|
||||
|
||||
创建前先 `cron(action=list)` 检查同名 job 是否已存在,避免重复创建。
|
||||
|
||||
## 11B. 一致性偏差修复清单(S6 补充)
|
||||
|
||||
§19 设计-实现一致性检查(2026-06-18)发现以下偏差,列入 S6 一并修复:
|
||||
|
||||
| # | 偏差 | 严重度 | 修复方式 |
|
||||
|---|------|--------|--------|
|
||||
| B4 | ticker.py:336-348 ExperienceDistiller 调用未移除 | 中 | 移除 experience_distiller 参数和调用,日志改为 debug 级空转提示 |
|
||||
| B5 | skill_system.py / experience.py 未标记 deprecated | 低 | 文件头部加 `# DEPRECATED — §19 重设计,不再参与 skill 发现/加载` 注释 |
|
||||
| B6 | SELF_IMPROVEMENT_REMINDER.md 引用残留 | 低 | AGENTS.md 中已标注废弃,但 system prompt 仍注入。从 workspace 文件列表中移除该文件 |
|
||||
|
||||
**B4 修复细节**:
|
||||
|
||||
ticker.py 构造函数 `__init__` 接受 `experience_distiller` 参数(默认 None),tick() 中第 336-348 行有条件调用。修复方式:
|
||||
- 保留参数(向后兼容),但条件块内加 `logger.debug("ExperienceDistiller deprecated per §19, skipping")` 后直接 return
|
||||
- 不删除代码(P3 级清理时再做物理删除)
|
||||
|
||||
**B6 修复细节**:
|
||||
|
||||
当前 Project Context 中注入了 `SELF_IMPROVEMENT_REMINDER.md` 的内容。该文件在 workspace-pangtong 中已不存在(被删),但 system prompt 模板仍引用它。修复方式:确认文件不存在即可——openclaw 会跳过不存在的注入文件。实际已无影响,标注为 resolved。
|
||||
|
||||
## 12. wiki-vault / 知识库参考实践映射
|
||||
|
||||
| 设计决策 | 参考来源 | 核心借鉴 |
|
||||
|---------|---------|---------|
|
||||
| 统一产物 Skill-only | Hermes skill_manage + memory_tool | 只有 Skill 和 Memory 两种载体 |
|
||||
| HOW not WHAT | nuwa-skill 实践 #5 | 蒸馏思维方式不是知识内容 |
|
||||
| description = when not how | Superpowers writing-skills | description 只描述触发条件 |
|
||||
| 质量检查自动化 | nuwa-skill quality_check.py | 结构化检查代替主观判断 |
|
||||
| 矛盾处理 | nuwa-skill 实践 #10 | 矛盾是特征不是 Bug |
|
||||
| Skill 自我修补 | Hermes skill_manage schema | 使用时发现问题立即 patch |
|
||||
| 闭环学习循环 | 知识管理体系实践 #1 | DISCOVER→DISTILL→APPLY→IMPROVE |
|
||||
| Experience→Skill 延迟转化 | moziplus 经验实践 #2 | 多次验证后才固化 |
|
||||
| Skill 生命周期 draft→active→deprecated | OpenClaw skill_workshop | pending→applied→rejected→quarantined |
|
||||
| 棘轮机制 | moziplus 经验实践 #2 | 经验只能改进不能退化 |
|
||||
| 优雅降级 | nuwa-skill 实践 #17 | 信息不足时不要强行蒸馏 |
|
||||
| 迭代上限 | nuwa-skill 实践 #18 | 最多 2 轮验证,不无限打磨 |
|
||||
| **双层 daily 蒸馏** | self-improvement skill daily review | 有距离感的蒸馏优于即时记录 |
|
||||
| **结构化信号格式** | self-improvement skill logging format | ID/Status/Priority/See Also/Recurrence-Count |
|
||||
| **Recurrence-Count 验证** | self-improvement skill recurring pattern detection | ≥3 次自动触发提升,比主观判断更客观 |
|
||||
| **Skill Extraction Criteria** | self-improvement skill extraction | Recurring + Verified + Non-obvious + Broadly applicable |
|
||||
| **per-agent Skill 目录** | Hermes skill_manage + self-improving-agent practice §5 | 每个 agent 建立自己的 Skill 库 |
|
||||
| **废弃 .learnings/** | DISCOVER 统一采集 | JSONL 是唯一数据源,避免信息冗余 |
|
||||
| **组合模式(主 skill + references)** | moziplus skill-engineering practices §4 | Skill 之间通过产出物松耦合传递 |
|
||||
|
||||
## 13. 部署目录结构
|
||||
|
||||
### 13.1 openclaw skill 加载优先级
|
||||
|
||||
OpenClaw 按 6 级优先级扫描 skill 目录,同名 skill 高优先级覆盖低优先级:
|
||||
|
||||
| 优先级 | 来源 | 路径 | 可见性 |
|
||||
|--------|------|------|--------|
|
||||
| 1 — 最高 | Workspace skills | `<workspace>/skills` | 只对该 agent |
|
||||
| 2 | Project agent skills | `<workspace>/.agents/skills` | 只对该 workspace 的 agent |
|
||||
| 3 | Personal agent skills | `~/.agents/skills` | 所有 agent |
|
||||
| 4 | Managed / local skills | `~/.openclaw/skills` | 所有 agent |
|
||||
| 5 | Bundled skills | 随安装包(`/opt/homebrew/.../openclaw/skills/`) | 所有 agent |
|
||||
| 6 — 最低 | Extra dirs + plugin skills | `skills.load.extraDirs` + `~/.openclaw/plugin-skills/` | 所有 agent |
|
||||
|
||||
### 13.2 skill-management Skill 目录结构
|
||||
|
||||
放在公共目录(`~/.sanguo_projects/sanguo_mozi/skills/`),所有 moziplus agent 可见:
|
||||
|
||||
```
|
||||
~/.sanguo_projects/sanguo_mozi/skills/skill-management/
|
||||
├── SKILL.md # 主 Skill:综述 + 核心原则 + 各阶段职责摘要
|
||||
├── references/
|
||||
│ ├── discover-l1.md # L1 各 agent 自蒸馏详细操作(03:00 cron 读这个)
|
||||
│ ├── discover-l2.md # L2 庞统整合详细操作(05:00 cron 读这个)
|
||||
│ ├── distill.md # DISTILL 阶段详细操作(蒸馏规范 + 验证标准)
|
||||
│ ├── apply.md # APPLY 阶段说明(openclaw 原生机制,简短)
|
||||
│ └── improve.md # IMPROVE 阶段详细操作(引用追踪 + 淘汰 + 提升)
|
||||
└── assets/
|
||||
├── templates/
|
||||
│ ├── skill-template.md # SKILL.md 标准模板
|
||||
│ └── signal-format.md # 信号输出格式模板(ID/Priority/Pattern-Key)
|
||||
└── checklists/
|
||||
└── quality-check.md # 质量检查清单
|
||||
```
|
||||
|
||||
**为什么放公共目录**:所有 agent 都需要触发这个 skill(DISCOVER L1 时各 agent 按 description 匹配 → read SKILL.md → 再按需 read references/)。DISCOVER/IMPROVE 是 cron 场景,cron payload 中直接指定 `read references/xxx.md` 按内容执行。
|
||||
|
||||
**为什么不拆分为独立 skill**:5 个 skill = 5 条 description 常驻上下文(~500-800 token)。其中 DISCOVER 和 IMPROVE 是 cron 触发不是 agent 按描述触发,不需要常驻 description。用 references/ 按需加载更省上下文。
|
||||
|
||||
### 13.3 Cron 产出流转路径
|
||||
|
||||
```
|
||||
L1 产出(各 agent 03:00)
|
||||
↓ skill_workshop create(pending proposal)
|
||||
↓ 存储:skill_workshop 内部管理(~/.openclaw/workspace-<agent>/.skill-workshop/)
|
||||
↓
|
||||
L2 审查(庞统 05:00)
|
||||
↓ skill_workshop list → inspect → 决策
|
||||
↓
|
||||
├─ APPROVE(个人经验,质量达标)
|
||||
│ → skill_workshop apply
|
||||
│ → 写入:~/.openclaw/workspace-<agent>/skills/<skill-name>/SKILL.md
|
||||
│ → 仅该 agent 可见(workspace skill,优先级 1)
|
||||
│
|
||||
├─ MERGE(跨 agent 共性)
|
||||
│ → 合并多个 proposal 为共享 Skill
|
||||
│ → skill_workshop apply 到庞统 workspace,然后 cp/symlink 到公共目录
|
||||
│ → 写入:~/.sanguo_projects/sanguo_mozi/skills/<skill-name>/SKILL.md
|
||||
│ → 所有 agent 可见(extra dir,优先级 6)
|
||||
│ → 清理:MERGE 后通知各 agent quarantine workspace 中的同名 draft
|
||||
│
|
||||
│ ⚠️ skill_workshop 只能写 workspace skills,不能写 extraDir。
|
||||
│ MERGE 流程的实际写入方式:庞统在 workspace apply 后,
|
||||
│ 手动 cp 到公共目录(或配置 skills.load.allowSymlinkTargets 用 symlink)。
|
||||
│
|
||||
├─ REJECT(质量不够)
|
||||
│ → skill_workshop reject(附原因)
|
||||
│ → agent 在下次 L1 蒸馏时看到反馈
|
||||
│
|
||||
└─ PROMOTE(高确定性,提升为确定性规则)
|
||||
→ 手动写入 AGENTS.md / SOUL.md / TOOLS.md
|
||||
→ 所有 agent 强制注入(L1 确定性规则层)
|
||||
```
|
||||
|
||||
**关键设计**:APPROVE 写入 per-agent workspace(优先级 1,最高),MERGE 写入公共目录(优先级 6,最低)。如果同名 skill 在两边都有,workspace 版本覆盖公共版本——agent 可以有自己改进过的版本。
|
||||
|
||||
### 13.4 Per-agent Skill 目录
|
||||
|
||||
各 agent workspace 下的 skills 目录(目前不存在,L2 审查 APPROVE 后由 skill_workshop 自动创建):
|
||||
|
||||
```
|
||||
~/.openclaw/workspace-zhangfei/skills/ # 张飞的个人经验 Skill
|
||||
~/.openclaw/workspace-guanyu/skills/ # 关羽的个人经验 Skill
|
||||
~/.openclaw/workspace-zhaoyun/skills/ # 赵云的个人经验 Skill
|
||||
~/.openclaw/workspace-simayi/skills/ # 司马懿的个人经验 Skill
|
||||
~/.openclaw/workspace-pangtong/skills/ # 庞统的个人经验 Skill
|
||||
~/.openclaw/workspace-jiangwei/skills/ # 姜维的个人经验 Skill
|
||||
```
|
||||
|
||||
**适用场景**:
|
||||
- 张飞的编码踩坑模式 → 只有张飞需要,不污染其他 agent 上下文
|
||||
- 司马懿的审查技巧 → 只有司马懿需要
|
||||
- 庞统的规划经验 → 只有庞统需要
|
||||
|
||||
### 13.5 Proposal 中间产物存储
|
||||
|
||||
```
|
||||
~/.openclaw/workspace-<agent>/.skill-workshop/
|
||||
├── proposals/
|
||||
│ ├── <proposal-id>/
|
||||
│ │ ├── PROPOSAL.md # 草案内容
|
||||
│ │ ├── metadata.json # 状态、hash、scanner state
|
||||
│ │ └── support-files/ # 附带的 references/assets
|
||||
│ └── ...
|
||||
├── applied/ # 已 apply 的 proposal 归档
|
||||
├── rejected/ # 已 reject 的 proposal 归档
|
||||
└── quarantined/ # 已 quarantine 的 proposal 归档
|
||||
```
|
||||
|
||||
**注意**:proposal 存储由 skill_workshop 内部管理,不需要手动操作。首次使用 skill_workshop 时自动创建 `.skill-workshop/` 目录。庞统 L2 cron 通过 `skill_workshop list`(查看所有 agent 的 pending proposal)+ `skill_workshop inspect`(查看具体内容)+ `skill_workshop apply/reject/quarantine`(执行决策)完成审查。
|
||||
|
||||
### 13.6 全景目录结构
|
||||
|
||||
```
|
||||
# ━━━━━━━ Skill 来源(按 openclaw 优先级) ━━━━━━━━
|
||||
|
||||
# P1: Per-agent workspace skills(个人经验,L2 APPROVE 后写入)
|
||||
~/.openclaw/workspace-<agent>/skills/<skill-name>/SKILL.md
|
||||
|
||||
# P4: Managed / local skills(保留,目前为空)
|
||||
~/.openclaw/skills/
|
||||
|
||||
# P5: Bundled skills(openclaw 自带,不动)
|
||||
/opt/homebrew/lib/node_modules/openclaw/skills/
|
||||
|
||||
# P6: Extra dirs + plugin skills
|
||||
~/.sanguo_projects/sanguo_mozi/skills/ # moziplus 团队共享 Skill
|
||||
├── skill-management/ # ← §19 核心 Skill
|
||||
│ ├── SKILL.md
|
||||
│ ├── references/{discover-l1, discover-l2, distill, apply, improve}.md
|
||||
│ └── assets/{templates, checklists}/
|
||||
├── blackboard-executor/ # 现有
|
||||
├── blackboard-reviewer/ # 现有
|
||||
├── trial-and-error-patterns/ # 现有(经验会追加到这里)
|
||||
└── ...(其他现有 skill)
|
||||
|
||||
~/.openclaw/plugin-skills/ # plugin Skill(feishu 等)
|
||||
|
||||
# ━━━━━━━ Cron 产出流转 ━━━━━━━━
|
||||
|
||||
# L1(03:00 各 agent)
|
||||
# 输入:~/.openclaw/agents/<agent_id>/sessions/*.jsonl
|
||||
# 产出:skill_workshop create → proposal(pending)
|
||||
# 存储:~/.openclaw/workspace-<agent>/.skill-workshop/proposals/
|
||||
|
||||
# L2(05:00 庞统)
|
||||
# 输入:全量数据源 + 所有 pending proposals
|
||||
# 审查:skill_workshop list → inspect → apply/merge/reject
|
||||
# 产出:
|
||||
# APPROVE → ~/.openclaw/workspace-<agent>/skills/<skill-name>/(per-agent)
|
||||
# MERGE → ~/.sanguo_projects/sanguo_mozi/skills/<skill-name>/(共享)
|
||||
# REJECT → proposal 归档到 rejected/
|
||||
# PROMOTE → 手动写入 AGENTS.md / SOUL.md / TOOLS.md
|
||||
|
||||
# IMPROVE(每周 庞统)
|
||||
# 输入:过去 7 天所有 agent 的 session JSONL
|
||||
# 产出:淘汰候选报告 → skill_workshop quarantine
|
||||
|
||||
# ━━━━━━━ 废弃的目录(保留历史,不再写入) ━━━━━━━━
|
||||
|
||||
# .learnings/ — 不再写入
|
||||
~/.openclaw/workspace-*/.learnings/
|
||||
|
||||
# self-improvement skill — 不再激活
|
||||
~/.openclaw/workspace/skills/self-improving-agent/
|
||||
|
||||
# SELF_IMPROVEMENT_REMINDER.md — 废弃
|
||||
# 规则已融合到 skill-management skill 中
|
||||
```
|
||||
@@ -0,0 +1,66 @@
|
||||
---
|
||||
name: skill-management
|
||||
description: "Use when managing skill lifecycle through the DISCOVER-DISTILL-APPLY-IMPROVE loop, when doing daily experience distillation, or when reviewing/auditing skill proposals."
|
||||
---
|
||||
|
||||
# Skill Management — 经验闭环 + Skill 生命周期
|
||||
|
||||
四阶段闭环:DISCOVER → DISTILL → APPLY → IMPROVE。双层 daily 蒸馏架构。
|
||||
|
||||
## 什么时候用
|
||||
|
||||
- **L1 自蒸馏**(每天 03:00,各 agent):扫描自己的 session JSONL,蒸馏自己的经验 → 提交 draft proposal
|
||||
- **L2 整合审查**(每天 05:00,庞统):扫描全量数据源 + 审查所有 L1 draft → approve/merge/reject
|
||||
- **IMPROVE**(每周,庞统):追踪 Skill 引用情况,淘汰 30 天无引用的 Skill
|
||||
- **自我修补**(实时,任何 agent):使用 Skill 时发现问题 → 立即 revise proposal
|
||||
|
||||
详细操作步骤见 references/ 目录,按当前阶段 `read` 对应文件。
|
||||
|
||||
## 核心原则
|
||||
|
||||
1. **统一产物 Skill-only**:产物只有 Skill(skill_workshop 管理)和 Memory(MEMORY.md),不再有 .learnings/ 等中间形态
|
||||
2. **HOW not WHAT**:蒸馏「怎么做」不是「发生了什么」。描述问题模式,不固化技术细节
|
||||
3. **description = when not how**:Skill 的 description 只描述触发条件,不描述工作流
|
||||
4. **双层蒸馏**:L1 各 agent 自己蒸馏(自己最准);L2 庞统负责跨 agent 共性识别 + 审查
|
||||
5. **矛盾是特征不是 Bug**:保留矛盾,标注类型(时间性/领域性/本质性),不强制调和
|
||||
|
||||
## 四阶段速查
|
||||
|
||||
| 阶段 | 谁 | 何时 | 做什么 | 详细文档 |
|
||||
|------|---|------|--------|---------|
|
||||
| DISCOVER L1 | 每个 agent | 03:00(错开 15min) | 扫描自己 JSONL → 蒸馏 → draft proposal | `references/discover-l1.md` |
|
||||
| DISCOVER L2 | 庞统 | 05:00 | 全量扫描 + 审查 draft → approve/merge/reject | `references/discover-l2.md` |
|
||||
| DISTILL | L1 各 agent + L2 庞统 | 同 DISCOVER | 提取根因模式,按 SKILL.md 格式产出 | `references/distill.md` |
|
||||
| APPLY | openclaw 原生 | 实时 | description 匹配 → read SKILL.md → 执行 | `references/apply.md` |
|
||||
| IMPROVE | 庞统 | 每周 | JSONL 引用追踪 + 淘汰 + 提升 | `references/improve.md` |
|
||||
|
||||
## 验证标准(Recurrence-Count 机制)
|
||||
|
||||
从 draft → active:
|
||||
|
||||
| 维度 | 标准 | 不通过 |
|
||||
|------|------|--------|
|
||||
| Recurrence-Count ≥ 2 | 同一 Pattern-Key 在 ≥2 个场景出现 | 降级为 MEMORY.md |
|
||||
| 有生成力 | 能给出具体操作指引 | 丢弃 |
|
||||
| 有排他性 | 不是常识 | 丢弃 |
|
||||
|
||||
提升触发(全部满足):30 天内 ≥3 次 + 跨 ≥2 个任务。
|
||||
|
||||
## 自我修补规则
|
||||
|
||||
使用 Skill 时发现缺步骤、过时信息、命令变更 → **立即** 通过 skill_workshop 提交 revise proposal。不等定时任务,不等到下次 review。
|
||||
|
||||
## 常见错误
|
||||
|
||||
| 错误 | 后果 | 正确做法 |
|
||||
|------|------|---------|
|
||||
| 蒸馏 WHAT 不 HOW | 经验无法复用 | 描述根因模式 |
|
||||
| description 包含工作流 | Agent 跳过读完整 SKILL.md | description 只描述触发条件 |
|
||||
| 缺少 Recurrence-Count | 偶发问题被固化 | 必须 ≥2 次才提升 |
|
||||
| 强制调和矛盾 | 丢失关键信号 | 保留矛盾,标注类型 |
|
||||
| skill_workshop 写公共目录 | 操作失败 | skill_workshop 只能写 workspace,公共目录用 cp/symlink |
|
||||
|
||||
## 来源
|
||||
|
||||
- 设计文档:`docs/design/19-skill-lifecycle-and-experience-loop.md` v2.0
|
||||
- 参考实践:Hermes skill_manage、nuwa-skill、Superpowers writing-skills、self-improvement skill
|
||||
@@ -0,0 +1,36 @@
|
||||
---
|
||||
name: quality-check
|
||||
description: "Skill 蒸馏产出质量检查清单"
|
||||
---
|
||||
|
||||
# 质量检查清单
|
||||
|
||||
蒸馏产出提交前,逐条检查:
|
||||
|
||||
## 结构检查
|
||||
|
||||
- [ ] frontmatter 有 name 和 description
|
||||
- [ ] description 以「Use when...」开头
|
||||
- [ ] description 只含触发条件,不含工作流
|
||||
- [ ] 有「什么时候用」章节
|
||||
- [ ] 有「怎么做」章节
|
||||
- [ ] 有「常见错误」章节
|
||||
- [ ] 有「来源」章节
|
||||
|
||||
## 内容检查
|
||||
|
||||
- [ ] trigger 是否具体(不是「注意代码质量」这种泛泛而谈)
|
||||
- [ ] action 是否可执行(不是「要小心」这种无操作指引)
|
||||
- [ ] 蒸馏的是 HOW 不是 WHAT(根因模式,不是事件描述)
|
||||
- [ ] 没有项目特定的硬编码值
|
||||
|
||||
## 验证检查
|
||||
|
||||
- [ ] Recurrence-Count ≥ 2(同一模式在 ≥2 个场景出现)
|
||||
- [ ] 有生成力(能给出具体操作指引)
|
||||
- [ ] 有排他性(不是常识)
|
||||
|
||||
## 重复检查
|
||||
|
||||
- [ ] 检查现有 skills 目录中是否已有覆盖
|
||||
- [ ] 如果是对已有 Skill 的增量更新,使用 revise 而非 create
|
||||
@@ -0,0 +1,39 @@
|
||||
---
|
||||
name: signal-format
|
||||
description: "DISCOVER 阶段信号输出格式模板"
|
||||
---
|
||||
|
||||
# 信号输出格式
|
||||
|
||||
每条候选信号包含:
|
||||
|
||||
```
|
||||
信号类型 | 来源(task_id / PR / review / session)| 时间 | 简述(≤100 字)
|
||||
ID: SIG-YYYYMMDD-XXX
|
||||
Priority: low | medium | high | critical
|
||||
Status: pending | in_progress | resolved | promoted
|
||||
See Also: SIG-YYYYMMDD-XXX(关联信号)
|
||||
Recurrence-Count: N(同一模式出现次数)
|
||||
Pattern-Key: category.subcategory(稳定去重键)
|
||||
```
|
||||
|
||||
## 字段说明
|
||||
|
||||
| 字段 | 用途 | 示例 |
|
||||
|------|------|------|
|
||||
| ID | 唯一标识,便于交叉引用 | SIG-20260618-001 |
|
||||
| Priority | 优先级排序 | critical: 阻断核心功能; high: 影响常见流程; medium: 有 workaround; low: 边缘场景 |
|
||||
| Status | 生命周期跟踪 | pending → in_progress → resolved / promoted |
|
||||
| See Also | 关联相似信号,发现共性模式 | SIG-20260617-003 |
|
||||
| Recurrence-Count | 同一模式出现次数,≥3 触发自动提升 | 2 |
|
||||
| Pattern-Key | 稳定去重键,跨 agent 匹配同一模式 | sync.field_mapping |
|
||||
|
||||
## 信号类型(5 类)
|
||||
|
||||
| 类型 | 识别特征 |
|
||||
|------|---------|
|
||||
| 失败模式 | 有明确的失败原因 + 排查过程 |
|
||||
| 重复问题 | 同关键词出现 ≥2 次 |
|
||||
| 决策转折 | 原方向被推翻或修正 |
|
||||
| 新实践 | 之前没有的知识 |
|
||||
| 知识缺口 | 查不到/不确定的东西 |
|
||||
@@ -0,0 +1,51 @@
|
||||
---
|
||||
name: skill-template
|
||||
description: "SKILL.md 标准模板 — 蒸馏产出时按此格式编写"
|
||||
---
|
||||
|
||||
# Skill 标准模板
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: <skill-name>
|
||||
description: "Use when <触发条件/问题模式描述>"
|
||||
---
|
||||
|
||||
# <Skill 标题>
|
||||
|
||||
## 什么时候用
|
||||
<具体的触发场景,按问题模式描述,不按技术特定症状>
|
||||
|
||||
## 怎么做
|
||||
<根因分析 + 操作步骤>
|
||||
|
||||
1. <步骤 1>
|
||||
2. <步骤 2>
|
||||
3. <步骤 3>
|
||||
|
||||
## 常见错误
|
||||
<反模式:什么不该做>
|
||||
|
||||
- ❌ <错误做法> → <后果>
|
||||
- ❌ <错误做法> → <后果>
|
||||
|
||||
## 来源
|
||||
<evidence:哪些 task/PR/review 提炼了这条经验>
|
||||
|
||||
- task <id>: <简述>
|
||||
- PR #<num>: <简述>
|
||||
```
|
||||
|
||||
## description 编写要点
|
||||
|
||||
- 以「Use when...」开头
|
||||
- 只描述触发条件(when),**不描述工作流**(how)
|
||||
- 描述问题模式,不描述技术特定症状
|
||||
- 控制在 1-2 句话
|
||||
|
||||
## 质量自检
|
||||
|
||||
- [ ] trigger 是否具体(不是「注意代码质量」)
|
||||
- [ ] action 是否可执行(不是「要小心」)
|
||||
- [ ] 是否与已有 Skill 重复
|
||||
- [ ] description 是否只含触发条件
|
||||
@@ -0,0 +1,34 @@
|
||||
# APPLY — Skill 应用阶段
|
||||
|
||||
## 机制
|
||||
|
||||
APPLY 完全基于 openclaw 原生 skill 机制,不需要额外代码:
|
||||
|
||||
1. openclaw 扫描 skills 目录 → 生成 `<available_skills>` 列表(只有 name + description)
|
||||
2. Agent 按 description 匹配 → `read` SKILL.md 完整内容
|
||||
3. Agent 按内容执行
|
||||
|
||||
## 渐进式加载
|
||||
|
||||
- L1:`<available_skills>` 列表(~100 token/skill)— 每次启动注入
|
||||
- L2:Agent `read` SKILL.md — 按需加载
|
||||
- L3:SKILL.md 内引用的 references/ 文件 — 按需加载
|
||||
|
||||
## Skill 存放位置与可见性
|
||||
|
||||
| 位置 | 可见性 | 优先级 |
|
||||
|------|--------|--------|
|
||||
| `~/.openclaw/workspace-<agent>/skills/` | 仅该 agent | 1(最高) |
|
||||
| `~/.sanguo_projects/sanguo_mozi/skills/` | 所有 moziplus agent | 6(最低) |
|
||||
|
||||
workspace 版本覆盖公共版本——agent 可以有自己改进过的版本。
|
||||
|
||||
## 自我修补
|
||||
|
||||
使用 Skill 时发现问题(缺步骤、过时信息、命令变更)→ **立即** 通过 skill_workshop 提交 revise proposal:
|
||||
|
||||
```python
|
||||
skill_workshop(action="revise", proposal_id="<id>", proposal_content="<修改后的内容>")
|
||||
```
|
||||
|
||||
不等定时任务,不等到下次 review。
|
||||
@@ -0,0 +1,84 @@
|
||||
# DISCOVER L1 — 各 agent 自蒸馏(每天 03:00)
|
||||
|
||||
## 你是谁
|
||||
|
||||
你是某个 agent(张飞/关羽/赵云/司马懿/庞统/姜维),在每天 03:00 被 cron 唤醒,执行自己的经验蒸馏。
|
||||
|
||||
## cron 错开时间
|
||||
|
||||
各 agent 错开 15 分钟避免资源争用:
|
||||
|
||||
| Agent | 时间 |
|
||||
|-------|------|
|
||||
| zhangfei-dev | 03:00 |
|
||||
| guanyu-dev | 03:15 |
|
||||
| zhaoyun-data | 03:30 |
|
||||
| simayi-challenger | 03:45 |
|
||||
| pangtong-fujunshi | 04:00 |
|
||||
| jiangwei-infra | 04:15 |
|
||||
|
||||
## 操作步骤
|
||||
|
||||
### Step 1: 扫描当天 session JSONL
|
||||
|
||||
```
|
||||
输入:~/.openclaw/agents/<your-agent-id>/sessions/*.jsonl
|
||||
时间范围:过去 24 小时(上次 L1 到现在)
|
||||
```
|
||||
|
||||
重点扫描以下内容:
|
||||
- `"tool":"exec"` 失败的命令(exit code 非 0)
|
||||
- `"role":"user"` 消息中的纠正(「不对」「错了」「应该是」等)
|
||||
- `"role":"assistant"` 中的反复返工(同一文件改了 3 次以上)
|
||||
- task status 变更为 failed 的事件
|
||||
- review verdict 为 REQUEST_CHANGES 的记录
|
||||
|
||||
### Step 2: 信号识别(5 类高价值信号)
|
||||
|
||||
| 信号类型 | 识别特征 | 示例 |
|
||||
|---------|---------|------|
|
||||
| 失败模式 | 有明确的失败原因 + 排查过程 | 命令报错、CI 失败、review 驳回 |
|
||||
| 重复问题 | 同关键词在当天出现 ≥2 次 | 反复修改同一段代码、同类错误 |
|
||||
| 决策转折 | 原方向被推翻或修正 | 主公纠正、需求澄清、rebuttal |
|
||||
| 新实践 | 之前没有的知识 | 新工具用法、新架构模式 |
|
||||
| 知识缺口 | 表达不确定、查不到 | 「不确定」「没找到」「推测」 |
|
||||
|
||||
### Step 3: 蒸馏(HOW not WHAT)
|
||||
|
||||
对每个信号,提取根因模式,不是事件描述:
|
||||
|
||||
```
|
||||
❌ "PR #83 修复了 event_type 未知的问题"(WHAT,无法复用)
|
||||
✅ "消费者/生产者字段同步:新增 dataclass 字段时,必须同步所有从 JSON 提取该字段的代码路径"(HOW,可复用)
|
||||
```
|
||||
|
||||
蒸馏规范详见 `references/distill.md`。
|
||||
|
||||
### Step 4: 产出 draft proposal
|
||||
|
||||
对蒸馏后的经验,使用 skill_workshop 提交:
|
||||
|
||||
```
|
||||
skill_workshop(action="create", name="<skill-name>", description="Use when <触发条件>", proposal_content="<SKILL.md 内容>")
|
||||
```
|
||||
|
||||
输出格式(每条信号):
|
||||
```
|
||||
信号类型 | 来源(task_id / session)| 时间 | 简述(≤100 字)
|
||||
ID: SIG-YYYYMMDD-XXX
|
||||
Priority: low | medium | high | critical
|
||||
Status: pending
|
||||
Recurrence-Count: N
|
||||
Pattern-Key: category.subcategory(如 sync.field_mapping)
|
||||
```
|
||||
|
||||
### Step 5: 完成
|
||||
|
||||
所有 draft proposal 提交后,L1 结束。不需要等待 L2 审查结果(庞统会在 05:00 处理)。
|
||||
|
||||
## 注意事项
|
||||
|
||||
- 数据源**只有**你自己的 session JSONL,不需要扫描黑板/Gitea/Mail
|
||||
- 如果当天没有有价值的信号(没踩坑、没被纠正、没新发现),不产出任何 proposal,这是正常的
|
||||
- 不要为了产出而强行蒸馏——偶发问题降级为 MEMORY.md,不提交 proposal
|
||||
- 质量优于数量:1 条高质量 proposal 比 5 条流水账有价值
|
||||
@@ -0,0 +1,118 @@
|
||||
# DISCOVER L2 — 庞统整合审查(每天 05:00)
|
||||
|
||||
## 你是谁
|
||||
|
||||
你是庞统,在每天 05:00 被 cron 唤醒,执行跨 agent 整合 + draft proposal 审查。
|
||||
|
||||
前提:所有 agent 的 L1 自蒸馏(03:00-04:15)已完成。
|
||||
|
||||
## 操作步骤
|
||||
|
||||
### Step 1: 获取所有 L1 draft proposals
|
||||
|
||||
```
|
||||
skill_workshop(action="list", status="pending")
|
||||
```
|
||||
|
||||
列出所有 pending 状态的 proposal,检查哪些是今天 L1 产出的。
|
||||
|
||||
### Step 2: 全量数据源扫描
|
||||
|
||||
扫描以下数据源,识别跨 agent 共性模式:
|
||||
|
||||
| 数据源 | 位置 | 关注什么 |
|
||||
|--------|------|---------|
|
||||
| 黑板 tasks | 各项目 blackboard.db | task failed、状态异常 |
|
||||
| 黑板 reviews | reviews 表 | REQUEST_CHANGES verdict + suggestions |
|
||||
| 黑板 comments | comments 表 | rebuttal 讨论、@mention 争议 |
|
||||
| 黑板 events | events 表 | guardrail 拦截、异常检测 |
|
||||
| Gitea Issues/PRs | Gitea API | 新问题、PR review 评论 |
|
||||
| Gitea CI | Gitea Actions | lint/test/build 失败 |
|
||||
| Mail | mail API | 跨 agent 讨论、推理过程 |
|
||||
| 所有 agent JSONL | ~/.openclaw/agents/*/sessions/ | 全团队当天思考过程 |
|
||||
| MEMORY.md | 各 agent workspace | 已有经验教训 |
|
||||
| knowledge-gaps.md | wiki-vault/_meta/ | 知识缺口 |
|
||||
| L1 draft proposals | skill_workshop pending | 各 agent 当天提交 |
|
||||
|
||||
### Step 3: 跨 agent 共性模式识别
|
||||
|
||||
寻找同一 Pattern-Key 在多个 agent 的 JSONL/proposal 中出现的情况:
|
||||
|
||||
```
|
||||
张飞 SIG-20260618-001: Pattern-Key: sync.field_mapping
|
||||
关羽 SIG-20260618-002: Pattern-Key: sync.field_mapping
|
||||
→ 共性信号!Recurrence-Count = 2,可合并为共享 Skill
|
||||
```
|
||||
|
||||
### Step 4: 审查每个 draft proposal
|
||||
|
||||
对每个 L1 draft proposal,逐条审查:
|
||||
|
||||
```
|
||||
skill_workshop(action="inspect", proposal_id="<id>")
|
||||
```
|
||||
|
||||
审查维度:
|
||||
|
||||
| 维度 | 标准 | 不通过 |
|
||||
|------|------|--------|
|
||||
| Recurrence-Count ≥ 2 | 同一 Pattern-Key 在 ≥2 个场景出现 | 降级为 MEMORY.md |
|
||||
| 有生成力 | 能给出具体操作指引 | 丢弃 |
|
||||
| 有排他性 | 不是常识 | 丢弃 |
|
||||
| description 合规 | 只描述触发条件,不含工作流 | 要求 revise |
|
||||
| trigger 具体 | 不是「注意代码质量」 | 要求 revise |
|
||||
|
||||
### Step 5: 执行决策
|
||||
|
||||
对每个 proposal 做出决策:
|
||||
|
||||
**APPROVE**(个人经验,质量达标):
|
||||
```python
|
||||
skill_workshop(action="apply", proposal_id="<id>")
|
||||
# skill_workshop 自动写入 agent workspace: ~/.openclaw/workspace-<agent>/skills/<skill-name>/
|
||||
# 仅该 agent 可见
|
||||
```
|
||||
|
||||
**MERGE**(跨 agent 共性):
|
||||
```python
|
||||
# 1. 在庞统 workspace apply 合并后的版本
|
||||
skill_workshop(action="apply", proposal_id="<id>")
|
||||
# 2. cp 到公共目录(skill_workshop 不能写 extraDir)
|
||||
cp ~/.openclaw/workspace-pangtong/skills/<skill-name>/SKILL.md \
|
||||
~/.sanguo_projects/sanguo_mozi/skills/<skill-name>/SKILL.md
|
||||
# 3. 通知各 agent quarantine workspace 中的同名 draft
|
||||
# 在相关 PR/Issue 中 @agent 说明
|
||||
```
|
||||
|
||||
**REJECT**(质量不够):
|
||||
```python
|
||||
skill_workshop(action="reject", proposal_id="<id>", reason="<具体原因>")
|
||||
# agent 在下次 L1 时看到反馈
|
||||
```
|
||||
|
||||
**PROMOTE**(高确定性经验,提升为规则):
|
||||
```python
|
||||
# 手动写入 AGENTS.md / SOUL.md / TOOLS.md 对应区块
|
||||
# 这不属于 skill_workshop 管理范围
|
||||
```
|
||||
|
||||
### Step 6: 全局提升检查
|
||||
|
||||
检查是否有经验达到提升条件(Recurrence-Count ≥ 3 + 跨 ≥2 任务 + 30 天内):
|
||||
|
||||
| 提升目标 | 条件 | 效果 |
|
||||
|---------|------|------|
|
||||
| 独立 Skill | 足够通用,有自己的触发条件 | 独立 SKILL.md |
|
||||
| AGENTS.md 规则 | 确定性高,适用于所有 agent | L1 强制注入 |
|
||||
| guardrail | 安全相关,不可违反 | 强制检查 |
|
||||
|
||||
### Step 7: 知识缺口反馈
|
||||
|
||||
IMPROVE 发现的经验缺口或 L2 发现的新领域 → 追加到 `knowledge-gaps.md`。
|
||||
|
||||
## 注意事项
|
||||
|
||||
- L2 时间窗口:05:00 执行,确保 L1 全部完成(最后一个 agent 04:15 开始)
|
||||
- 全量扫描不需要逐行读 JSONL,用 grep 定位关键词再精读匹配段
|
||||
- MERGE 后必须清理各 agent workspace 的同名 draft(避免覆盖公共版本)
|
||||
- REJECT 必须附具体原因,帮 agent 改进而非打击
|
||||
@@ -0,0 +1,137 @@
|
||||
# DISTILL — 蒸馏规范
|
||||
|
||||
## 核心原则:HOW not WHAT
|
||||
|
||||
蒸馏的是「怎么做」不是「发生了什么」:
|
||||
|
||||
```
|
||||
❌ "PR #83 修复了 event_type 未知的问题"
|
||||
→ 这是 WHAT,无法复用
|
||||
|
||||
✅ "消费者/生产者字段同步:新增 dataclass 字段时,必须同步所有从 JSON 提取该字段的代码路径"
|
||||
→ 这是 HOW,可复用到任何消费者/生产者场景
|
||||
```
|
||||
|
||||
## SKILL.md 编写规范
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: skill-name
|
||||
description: Use when [触发条件/问题模式描述],不描述工作流
|
||||
---
|
||||
|
||||
# Skill 标题
|
||||
|
||||
## 什么时候用
|
||||
(具体的触发场景,按问题模式描述,不按技术特定症状)
|
||||
|
||||
## 怎么做
|
||||
(根因分析 + 操作步骤)
|
||||
|
||||
## 常见错误
|
||||
(反模式:什么不该做)
|
||||
|
||||
## 来源
|
||||
(evidence:哪些 task/PR/review 提炼了这条经验)
|
||||
```
|
||||
|
||||
## description 关键规则
|
||||
|
||||
- 只描述触发条件(when to use),**绝不描述工作流**(how)
|
||||
- 以「Use when...」开头
|
||||
- 描述问题模式,不描述技术特定症状
|
||||
- 原因:测试发现 description 如果总结了工作流,agent 会按 description 执行而跳过读完整 SKILL.md
|
||||
|
||||
### 示例
|
||||
|
||||
```yaml
|
||||
# ❌ BAD:描述了工作流
|
||||
description: Use when modifying dataclass — checks all extraction points, runs tests
|
||||
|
||||
# ✅ GOOD:只描述触发条件
|
||||
description: Use when modifying a dataclass that is populated from JSON extraction by another module
|
||||
|
||||
# ❌ BAD:太抽象
|
||||
description: Use for code quality
|
||||
|
||||
# ✅ GOOD:描述问题模式
|
||||
description: Use when a field added to a dataclass appears empty or as default value at runtime
|
||||
```
|
||||
|
||||
## 蒸馏示例
|
||||
|
||||
**一级蒸馏**(从具体案例提取):
|
||||
|
||||
```yaml
|
||||
# 案例 1:PromptContext event_type 未知
|
||||
# 案例 2:PromptContext from_agent/mail_type 缺失(PR #26 D2)
|
||||
→ 共同根因:消费者/生产者字段同步问题
|
||||
|
||||
## 消费者/生产者字段同步
|
||||
|
||||
**什么时候用**:修改 dataclass 时,如果该 dataclass 由外部 JSON 提取填充
|
||||
|
||||
**怎么做**:
|
||||
1. 改 dataclass 定义
|
||||
2. 检查所有从 JSON 提取字段的代码路径,同步新增提取逻辑
|
||||
3. 检查所有构造该 dataclass 的调用点,同步新增参数
|
||||
4. 跑一次构建测试验证字段不为空
|
||||
|
||||
**常见错误**:只改 dataclass 不改提取逻辑 → 字段默认值为空 → 运行时不报错但行为异常
|
||||
```
|
||||
|
||||
**二级蒸馏**(从多个一级经验提取通用模式):
|
||||
|
||||
如果经验在 ≥2 个不同场景复现,验证通过后,可以提升为独立 Skill 或固化到 AGENTS.md 规则。
|
||||
|
||||
## 验证标准
|
||||
|
||||
从 draft → active:
|
||||
|
||||
| 维度 | 标准 | 不通过 |
|
||||
|------|------|--------|
|
||||
| Recurrence-Count ≥ 2 | 同一 Pattern-Key 在 ≥2 个场景出现 | 降级为 MEMORY.md |
|
||||
| 有生成力 | 能给出具体操作指引 | 丢弃 |
|
||||
| 有排他性 | 不是常识 | 丢弃 |
|
||||
|
||||
提升触发(全部满足):30 天内 ≥3 次 + 跨 ≥2 个任务。
|
||||
|
||||
## Skill Extraction 质量 Gate
|
||||
|
||||
| 标准 | 描述 |
|
||||
|------|------|
|
||||
| Recurring | 有 See Also 链接到 2+ 个相似信号 |
|
||||
| Verified | Status 是 resolved 且有工作修复 |
|
||||
| Non-obvious | 需要实际调试才能发现 |
|
||||
| Broadly applicable | 不是项目特定,可跨场景复用 |
|
||||
|
||||
## 质量检查
|
||||
|
||||
| 检查项 | 标准 |
|
||||
|--------|------|
|
||||
| trigger 是否具体 | 不是「注意代码质量」 |
|
||||
| action 是否可执行 | 不是「要小心」 |
|
||||
| 是否与已有 Skill 重复 | 检查现有 skills 目录 |
|
||||
| description 是否只含触发条件 | 不包含工作流描述 |
|
||||
|
||||
## 矛盾处理
|
||||
|
||||
新经验与已有经验冲突时:
|
||||
- **时间性矛盾**(观点演化)→ 记录演化轨迹,以近期为主
|
||||
- **领域性矛盾**(不同场景不同规则)→ 分场景记录
|
||||
- **本质性张力**(价值观内在冲突)→ 标注为「核心张力」,两个版本都保留
|
||||
|
||||
**矛盾是特征,不是 Bug。** 强制调和会丢失关键信号。
|
||||
|
||||
## 信号输出格式
|
||||
|
||||
每条信号包含:
|
||||
```
|
||||
信号类型 | 来源 | 时间 | 简述(≤100 字)
|
||||
ID: SIG-YYYYMMDD-XXX
|
||||
Priority: low | medium | high | critical
|
||||
Status: pending | in_progress | resolved | promoted
|
||||
See Also: SIG-YYYYMMDD-XXX
|
||||
Recurrence-Count: N
|
||||
Pattern-Key: category.subcategory
|
||||
```
|
||||
@@ -0,0 +1,70 @@
|
||||
# IMPROVE — 引用追踪 + 淘汰 + 提升(每周 cron)
|
||||
|
||||
## 你是谁
|
||||
|
||||
你是庞统,每周执行一次 IMPROVE cron,扫描过去 7 天的所有 session JSONL。
|
||||
|
||||
## 操作步骤
|
||||
|
||||
### Step 1: 引用追踪
|
||||
|
||||
扫描过去 7 天所有 agent 的 session JSONL,采集 Skill 引用信号:
|
||||
|
||||
| 信号 | 采集方式 | 可信度 |
|
||||
|------|---------|--------|
|
||||
| Skill 被 read 的时间 | grep `"tool":"read"` + SKILL.md 路径 | 中 |
|
||||
| Skill 在 available_skills 中被注入 | grep available_skills 列表 | 中(注入但未必用) |
|
||||
| Agent 输出中提及 skill name | grep skill name in assistant messages | 高 |
|
||||
| Skill 文件最近修改时间 | git log / 文件 mtime | 高 |
|
||||
|
||||
### Step 2: 生成淘汰候选报告
|
||||
|
||||
对每个 Skill 检查最近 30 天的引用信号:
|
||||
|
||||
```
|
||||
30 天无引用信号
|
||||
→ 加入淘汰候选列表
|
||||
```
|
||||
|
||||
输出淘汰候选报告:
|
||||
```
|
||||
| Skill 名称 | 最后引用时间 | 存放位置 | 建议 |
|
||||
|-----------|------------|---------|------|
|
||||
| xxx | 2026-05-15 | 公共目录 | 建议淘汰 |
|
||||
| yyy | 从未被引用 | 张飞 workspace | 建议淘汰 |
|
||||
```
|
||||
|
||||
### Step 3: 庞统审阅决策
|
||||
|
||||
逐条审阅淘汰候选:
|
||||
|
||||
- **确认淘汰** → `skill_workshop(action="quarantine", proposal_id="<id>")`
|
||||
- **保留观察** → 标注,下轮再查
|
||||
- **更新后保留** → 修改 description / 内容,重置计时
|
||||
|
||||
**注意**:openclaw 本身的 skill(~/.openclaw/plugin-skills/ 和全局 skills)也纳入追踪。报告给主公决定是否禁用。
|
||||
|
||||
### Step 4: 经验提升检查
|
||||
|
||||
检查是否有 Skill 达到提升条件(被频繁引用 ≥5 次 + 多次验证):
|
||||
|
||||
| 提升目标 | 条件 | 效果 |
|
||||
|---------|------|------|
|
||||
| 独立 Skill | 足够通用,有自己的触发条件 | 独立 SKILL.md |
|
||||
| AGENTS.md 规则 | 确定性高,适用于所有 agent | L1 强制注入 |
|
||||
| guardrail | 安全相关,不可违反 | 强制检查 |
|
||||
|
||||
### Step 5: 反馈到 DISCOVER
|
||||
|
||||
IMPROVE 发现的经验缺口写入 knowledge-gaps.md:
|
||||
```
|
||||
- [日期] IMPROVE 发现「<skill-name> 不适用 <场景>」→ 待 DISCOVER 处理
|
||||
```
|
||||
|
||||
成为下一轮 DISCOVER L2 的输入。
|
||||
|
||||
## 注意事项
|
||||
|
||||
- 不追求精确归因,做时间维度的信号采集
|
||||
- 淘汰决策由庞统判断,不自动执行
|
||||
- 提升到 AGENTS.md 的规则需要主公确认(影响所有 agent 的确定性注入)
|
||||
@@ -0,0 +1,73 @@
|
||||
"""共享 helper 和常量"""
|
||||
|
||||
from typing import Any, Dict
|
||||
from fastapi import HTTPException
|
||||
|
||||
from src.blackboard.operations import Blackboard
|
||||
from src.blackboard.queries import Queries
|
||||
from src.blackboard.models import Task
|
||||
from src.blackboard.registry import ProjectRegistry
|
||||
from src.utils import get_data_root
|
||||
|
||||
# 虚拟项目白名单
|
||||
_VIRTUAL_PROJECTS = frozenset({"_general", "_mail", "_toolchain"})
|
||||
|
||||
|
||||
def _validate_project(project_id: str) -> str:
|
||||
"""校验 project_id"""
|
||||
if project_id in _VIRTUAL_PROJECTS:
|
||||
return project_id
|
||||
reg = ProjectRegistry(get_data_root())
|
||||
if reg.get_project(project_id):
|
||||
return project_id
|
||||
raise HTTPException(400, {
|
||||
"ok": False,
|
||||
"error": "project_not_found",
|
||||
"detail": f"Project '{project_id}' is not registered.",
|
||||
"suggestions": [
|
||||
f"Register first: POST /api/projects with id='{project_id}'",
|
||||
"Or use '_general' for tasks without a specific project",
|
||||
],
|
||||
})
|
||||
|
||||
|
||||
def _bb(project_id: str) -> Blackboard:
|
||||
_validate_project(project_id)
|
||||
return Blackboard(get_data_root() / project_id / "blackboard.db")
|
||||
|
||||
|
||||
def _q(project_id: str) -> Queries:
|
||||
_validate_project(project_id)
|
||||
return Queries(get_data_root() / project_id / "blackboard.db")
|
||||
|
||||
|
||||
def _task_to_dict(t: Task) -> Dict[str, Any]:
|
||||
d = {k: v for k, v in t.__dict__.items() if v is not None}
|
||||
return d
|
||||
|
||||
|
||||
_KNOWN_AGENT_IDS: list = []
|
||||
|
||||
|
||||
def _init_agent_ids():
|
||||
"""从配置文件加载 Agent ID 列表"""
|
||||
global _KNOWN_AGENT_IDS
|
||||
if _KNOWN_AGENT_IDS:
|
||||
return
|
||||
try:
|
||||
import yaml
|
||||
import os
|
||||
cfg_path = os.path.join(os.path.dirname(__file__), "..", "..", "config", "default.yaml")
|
||||
with open(cfg_path) as f:
|
||||
cfg = yaml.safe_load(f)
|
||||
_KNOWN_AGENT_IDS = list(cfg.get("daemon", {}).get("agent_profiles", {}).keys())
|
||||
except Exception:
|
||||
_KNOWN_AGENT_IDS = []
|
||||
|
||||
|
||||
def _extract_mentions(text: str) -> list:
|
||||
"""从文本中自动提取 @agent-id 格式的 mention"""
|
||||
import re
|
||||
_init_agent_ids()
|
||||
candidates = set(re.findall(r'@([a-z][a-z0-9]*(?:-[a-z][a-z0-9]*)+)', text))
|
||||
return [a for a in candidates if a in _KNOWN_AGENT_IDS]
|
||||
@@ -0,0 +1,240 @@
|
||||
"""Task 关联路由 — comments / outputs / decisions / observations / reviews / events / experiences / summary"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Query
|
||||
|
||||
from src.blackboard.models import Review
|
||||
from src.blackboard.db import OUTPUT_TYPES
|
||||
|
||||
from src.api.shared import (
|
||||
_bb,
|
||||
_q,
|
||||
_extract_mentions,
|
||||
)
|
||||
|
||||
router = APIRouter(prefix="/api/projects/{project_id}", tags=["blackboard"])
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Comments
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks/{task_id}/comments")
|
||||
async def get_comments(project_id: str, task_id: str,
|
||||
comment_type: Optional[str] = None):
|
||||
bb = _bb(project_id)
|
||||
comments = bb.get_comments(task_id, comment_type=comment_type)
|
||||
return {"comments": [dict(c.__dict__) for c in comments]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/comments")
|
||||
async def add_comment(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
mentions_raw = body.get("mentions")
|
||||
comment_body = body["body"]
|
||||
|
||||
# #04: 自动从 body 提取 @mention,与显式传的 mentions 取并集
|
||||
auto_mentions = _extract_mentions(comment_body)
|
||||
if isinstance(mentions_raw, str):
|
||||
try:
|
||||
explicit_mentions = json.loads(mentions_raw)
|
||||
except Exception:
|
||||
explicit_mentions = []
|
||||
elif isinstance(mentions_raw, list):
|
||||
explicit_mentions = mentions_raw
|
||||
else:
|
||||
explicit_mentions = []
|
||||
merged_mentions = list(set(explicit_mentions + auto_mentions))
|
||||
|
||||
cid = bb.add_comment(task_id, body["author"], comment_body,
|
||||
comment_type=body.get("comment_type", "general"),
|
||||
mentions=merged_mentions)
|
||||
if merged_mentions:
|
||||
bb.record_mentions(cid, task_id, merged_mentions)
|
||||
# #10: SSE 通知前端黑板有新 comment
|
||||
try:
|
||||
from src.api.sse_routes import get_broker
|
||||
broker = get_broker()
|
||||
broker.publish_sync("comment_added", {
|
||||
"project_id": project_id,
|
||||
"task_id": task_id,
|
||||
"comment_id": cid,
|
||||
"author": body["author"],
|
||||
})
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return {"ok": True, "comment_id": cid, "mentions": merged_mentions}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Outputs
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks/{task_id}/outputs")
|
||||
async def get_outputs(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"outputs": [dict(o.__dict__) for o in bb.get_outputs(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/outputs")
|
||||
async def write_output(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
|
||||
# 字段校验 + Agent-friendly 错误
|
||||
agent = body.get("agent")
|
||||
if not agent:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: agent",
|
||||
"hint": "Provide your agent ID, e.g. 'zhangfei-dev'",
|
||||
})
|
||||
|
||||
# type 字段:接受 type 或 content_type(别名兼容)
|
||||
output_type = body.get("type") or body.get("content_type")
|
||||
valid_types = sorted(OUTPUT_TYPES)
|
||||
if not output_type:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: type",
|
||||
"valid_values": {"type": valid_types},
|
||||
"hint": "Use 'type' field. Also accepts 'content_type' as alias.",
|
||||
})
|
||||
if output_type not in OUTPUT_TYPES:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": f"Invalid type: '{output_type}'",
|
||||
"valid_values": {"type": valid_types},
|
||||
})
|
||||
|
||||
title = body.get("title")
|
||||
if not title:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: title",
|
||||
"hint": "Provide a brief title describing this output",
|
||||
})
|
||||
|
||||
# 内容模式:content(直传)或 content_path(引用)
|
||||
content = body.get("content")
|
||||
content_path = body.get("content_path") or body.get("path")
|
||||
|
||||
if content and not content_path:
|
||||
# 内容直传模式:自动写文件
|
||||
artifacts_dir = os.path.join(
|
||||
os.path.dirname(bb.db_path), "artifacts", task_id
|
||||
)
|
||||
os.makedirs(artifacts_dir, exist_ok=True)
|
||||
# 安全文件名
|
||||
safe_name = "".join(
|
||||
c if c.isalnum() or c in "._-" else "_" for c in title)
|
||||
if not safe_name:
|
||||
safe_name = "output"
|
||||
file_path = os.path.join(artifacts_dir, safe_name)
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
f.write(content)
|
||||
content_path = file_path
|
||||
|
||||
oid = bb.write_output(
|
||||
task_id, agent, output_type, title,
|
||||
content_path=content_path,
|
||||
summary=body.get("summary"),
|
||||
metadata=body.get("metadata"),
|
||||
)
|
||||
return {"ok": True, "output_id": oid}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Decisions
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks/{task_id}/decisions")
|
||||
async def get_decisions(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"decisions": [dict(d.__dict__) for d in bb.get_decisions(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/decisions")
|
||||
async def add_decision(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
did = bb.add_decision(task_id, body["decider"], body["decision"],
|
||||
body["rationale"],
|
||||
alternatives=body.get("alternatives"))
|
||||
return {"ok": True, "decision_id": did}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Observations
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.post("/tasks/{task_id}/observations")
|
||||
async def add_observation(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
oid = bb.add_observation(task_id, body["observer"], body["body"],
|
||||
severity=body.get("severity", "info"))
|
||||
return {"ok": True, "observation_id": oid}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Reviews
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks/{task_id}/reviews")
|
||||
async def get_reviews(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"reviews": [dict(r.__dict__) for r in bb.get_reviews(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/reviews")
|
||||
async def add_review(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
review = Review(
|
||||
id=body["id"], task_id=task_id, reviewer=body["reviewer"],
|
||||
review_type=body["review_type"], verdict=body["verdict"],
|
||||
summary=body["summary"], confidence=body.get("confidence"),
|
||||
round=body.get("round", 1), max_rounds=body.get("max_rounds", 3),
|
||||
)
|
||||
bb.add_review(review)
|
||||
return {"ok": True, "review_id": review.id}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Per-task Events & Experiences
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks/{task_id}/events")
|
||||
async def get_task_events(project_id: str, task_id: str,
|
||||
limit: int = Query(50, le=200)):
|
||||
q = _q(project_id)
|
||||
return {"events": q.task_events(task_id, limit)}
|
||||
|
||||
|
||||
@router.get("/tasks/{task_id}/experiences")
|
||||
async def get_task_experiences(project_id: str, task_id: str):
|
||||
q = _q(project_id)
|
||||
return {"experiences": q.task_experiences(task_id)}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Global Events
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/events")
|
||||
async def get_events(project_id: str, limit: int = Query(50, le=200)):
|
||||
q = _q(project_id)
|
||||
return {"events": q.recent_events(limit)}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Summary
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/summary")
|
||||
async def task_summary(project_id: str):
|
||||
q = _q(project_id)
|
||||
return {"summary": q.task_summary()}
|
||||
@@ -1,68 +1,45 @@
|
||||
"""API 路由 — 黑板 CRUD"""
|
||||
"""Task 核心路由 — CRUD、状态、归档"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sqlite3
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Query
|
||||
|
||||
from src.blackboard.operations import Blackboard
|
||||
from src.blackboard.models import Task, Review
|
||||
from src.blackboard.queries import Queries
|
||||
from src.blackboard.db import VALID_STATUSES, OUTPUT_TYPES
|
||||
from src.blackboard.registry import ProjectRegistry
|
||||
from fastapi import APIRouter, HTTPException
|
||||
|
||||
from src.blackboard.models import Task
|
||||
from src.blackboard.db import VALID_STATUSES, VALID_TRANSITIONS
|
||||
from src.utils import get_data_root
|
||||
|
||||
from src.api.shared import (
|
||||
_bb,
|
||||
_q,
|
||||
_task_to_dict,
|
||||
_extract_mentions,
|
||||
)
|
||||
|
||||
router = APIRouter(prefix="/api/projects/{project_id}", tags=["blackboard"])
|
||||
|
||||
# 虚拟项目白名单(不需要在 registry 注册)
|
||||
_VIRTUAL_PROJECTS = frozenset({"_general", "_mail"})
|
||||
|
||||
|
||||
def _validate_project(project_id: str) -> str:
|
||||
"""校验 project_id,已知项目/虚拟项目放行,未知项目返回 400"""
|
||||
if project_id in _VIRTUAL_PROJECTS:
|
||||
return project_id
|
||||
reg = ProjectRegistry(get_data_root())
|
||||
if reg.get_project(project_id):
|
||||
return project_id
|
||||
raise HTTPException(400, {
|
||||
"ok": False,
|
||||
"error": "project_not_found",
|
||||
"detail": f"Project '{project_id}' is not registered.",
|
||||
"suggestions": [
|
||||
f"Register first: POST /api/projects with id='{project_id}'",
|
||||
"Or use '_general' for tasks without a specific project",
|
||||
],
|
||||
})
|
||||
|
||||
|
||||
def _bb(project_id: str) -> Blackboard:
|
||||
_validate_project(project_id)
|
||||
return Blackboard(get_data_root() / project_id / "blackboard.db")
|
||||
|
||||
|
||||
def _q(project_id: str) -> Queries:
|
||||
_validate_project(project_id)
|
||||
return Queries(get_data_root() / project_id / "blackboard.db")
|
||||
|
||||
|
||||
# --- Tasks ---
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Tasks
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.get("/tasks")
|
||||
async def list_tasks(project_id: str,
|
||||
status: Optional[str] = None,
|
||||
assignee: Optional[str] = None,
|
||||
parent_task: Optional[str] = None):
|
||||
parent_task: Optional[str] = None,
|
||||
q: Optional[str] = None):
|
||||
bb = _bb(project_id)
|
||||
tasks = bb.list_tasks(
|
||||
status=status,
|
||||
assignee=assignee,
|
||||
parent_task=parent_task)
|
||||
tasks = bb.list_tasks(status=status, assignee=assignee, parent_task=parent_task)
|
||||
if q:
|
||||
q_lower = q.lower()
|
||||
tasks = [t for t in tasks if q_lower in (t.title or "").lower()]
|
||||
return {"tasks": [_task_to_dict(t) for t in tasks]}
|
||||
|
||||
|
||||
@@ -74,6 +51,11 @@ async def get_task(project_id: str, task_id: str,
|
||||
if not task:
|
||||
raise HTTPException(404, f"Task not found: {task_id}")
|
||||
result = _task_to_dict(task)
|
||||
|
||||
if not expand:
|
||||
return result
|
||||
|
||||
# expand=all: 保持旧格式(list + 聚合字段),向后兼容前端 TaskModal
|
||||
if expand == "all":
|
||||
q = _q(project_id)
|
||||
detail = q.task_detail(task_id)
|
||||
@@ -90,6 +72,37 @@ async def get_task(project_id: str, task_id: str,
|
||||
for d in bb.get_decisions(task_id)]
|
||||
result["events"] = q.task_events(task_id)
|
||||
result["experiences"] = q.task_experiences(task_id)
|
||||
return result
|
||||
|
||||
# 细粒度 expand: 新格式(comments/events 带 limit + total_count)
|
||||
expand_list = expand.split(",")
|
||||
q = _q(project_id)
|
||||
|
||||
if "comments" in expand_list:
|
||||
all_comments = bb.get_comments(task_id)
|
||||
result["comments"] = {
|
||||
"items": [dict(c.__dict__) for c in all_comments[-20:]],
|
||||
"total_count": len(all_comments),
|
||||
"limit": 20,
|
||||
}
|
||||
|
||||
if "events" in expand_list:
|
||||
all_events = q.task_events(task_id, limit=99999)
|
||||
result["events"] = {
|
||||
"items": all_events[-30:],
|
||||
"total_count": len(all_events),
|
||||
"limit": 30,
|
||||
}
|
||||
|
||||
if "outputs" in expand_list:
|
||||
result["outputs"] = [dict(o.__dict__) for o in bb.get_outputs(task_id)]
|
||||
|
||||
if "reviews" in expand_list:
|
||||
result["reviews"] = [dict(r.__dict__) for r in bb.get_reviews(task_id)]
|
||||
|
||||
if "decisions" in expand_list:
|
||||
result["decisions"] = [dict(d.__dict__) for d in bb.get_decisions(task_id)]
|
||||
|
||||
return result
|
||||
|
||||
|
||||
@@ -100,11 +113,9 @@ async def create_task(project_id: str, body: Dict[str, Any]):
|
||||
task_id = body.get("id")
|
||||
if not task_id:
|
||||
import re
|
||||
from datetime import datetime
|
||||
prefix = re.sub(r'[^a-z0-9]', '-', project_id.lower()).strip('-')[:20]
|
||||
date_str = datetime.now().strftime('%Y%m%d')
|
||||
# seq: 查当前项目最大 seq
|
||||
import sqlite3
|
||||
db_path = get_data_root() / project_id / "blackboard.db"
|
||||
try:
|
||||
conn = sqlite3.connect(str(db_path), timeout=5)
|
||||
@@ -237,7 +248,6 @@ async def update_status(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
})
|
||||
|
||||
# 检查转换是否合法
|
||||
from src.blackboard.db import VALID_TRANSITIONS
|
||||
current = old_task.status
|
||||
allowed = VALID_TRANSITIONS.get(current, set())
|
||||
if new_status not in allowed:
|
||||
@@ -271,220 +281,6 @@ async def update_status(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
return {"ok": True, "old_status": current, "new_status": new_status}
|
||||
|
||||
|
||||
# --- @mention 自动提取(#04) ---
|
||||
_KNOWN_AGENT_IDS: list = []
|
||||
|
||||
|
||||
def _init_agent_ids():
|
||||
"""从配置文件加载 Agent ID 列表"""
|
||||
global _KNOWN_AGENT_IDS
|
||||
if _KNOWN_AGENT_IDS:
|
||||
return
|
||||
try:
|
||||
import yaml
|
||||
cfg_path = os.path.join(
|
||||
os.path.dirname(__file__),
|
||||
"..",
|
||||
"..",
|
||||
"config",
|
||||
"default.yaml")
|
||||
with open(cfg_path) as f:
|
||||
cfg = yaml.safe_load(f)
|
||||
_KNOWN_AGENT_IDS = list(
|
||||
cfg.get(
|
||||
"daemon",
|
||||
{}).get(
|
||||
"agent_profiles",
|
||||
{}).keys())
|
||||
except Exception:
|
||||
_KNOWN_AGENT_IDS = []
|
||||
|
||||
|
||||
def _extract_mentions(text: str) -> list:
|
||||
"""从文本中自动提取 @agent-id 格式的 mention"""
|
||||
import re
|
||||
_init_agent_ids()
|
||||
candidates = set(
|
||||
re.findall(
|
||||
r'@([a-z][a-z0-9]*(?:-[a-z][a-z0-9]*)+)',
|
||||
text))
|
||||
return [a for a in candidates if a in _KNOWN_AGENT_IDS]
|
||||
|
||||
|
||||
# --- Comments ---
|
||||
|
||||
@router.get("/tasks/{task_id}/comments")
|
||||
async def get_comments(project_id: str, task_id: str,
|
||||
comment_type: Optional[str] = None):
|
||||
bb = _bb(project_id)
|
||||
comments = bb.get_comments(task_id, comment_type=comment_type)
|
||||
return {"comments": [dict(c.__dict__) for c in comments]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/comments")
|
||||
async def add_comment(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
mentions_raw = body.get("mentions")
|
||||
comment_body = body["body"]
|
||||
|
||||
# #04: 自动从 body 提取 @mention,与显式传的 mentions 取并集
|
||||
auto_mentions = _extract_mentions(comment_body)
|
||||
if isinstance(mentions_raw, str):
|
||||
try:
|
||||
explicit_mentions = json.loads(mentions_raw)
|
||||
except Exception:
|
||||
explicit_mentions = []
|
||||
elif isinstance(mentions_raw, list):
|
||||
explicit_mentions = mentions_raw
|
||||
else:
|
||||
explicit_mentions = []
|
||||
merged_mentions = list(set(explicit_mentions + auto_mentions))
|
||||
|
||||
cid = bb.add_comment(task_id, body["author"], comment_body,
|
||||
comment_type=body.get("comment_type", "general"),
|
||||
mentions=merged_mentions)
|
||||
if merged_mentions:
|
||||
bb.record_mentions(cid, task_id, merged_mentions)
|
||||
# #10: SSE 通知前端黑板有新 comment
|
||||
try:
|
||||
from src.api.sse_routes import get_broker
|
||||
broker = get_broker()
|
||||
broker.publish_sync("comment_added", {
|
||||
"project_id": project_id,
|
||||
"task_id": task_id,
|
||||
"comment_id": cid,
|
||||
"author": body["author"],
|
||||
})
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return {"ok": True, "comment_id": cid, "mentions": merged_mentions}
|
||||
|
||||
|
||||
# --- Outputs ---
|
||||
|
||||
@router.get("/tasks/{task_id}/outputs")
|
||||
async def get_outputs(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"outputs": [dict(o.__dict__) for o in bb.get_outputs(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/outputs")
|
||||
async def write_output(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
|
||||
# 字段校验 + Agent-friendly 错误
|
||||
agent = body.get("agent")
|
||||
if not agent:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: agent",
|
||||
"hint": "Provide your agent ID, e.g. 'zhangfei-dev'",
|
||||
})
|
||||
|
||||
# type 字段:接受 type 或 content_type(别名兼容)
|
||||
output_type = body.get("type") or body.get("content_type")
|
||||
valid_types = sorted(OUTPUT_TYPES)
|
||||
if not output_type:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: type",
|
||||
"valid_values": {"type": valid_types},
|
||||
"hint": "Use 'type' field. Also accepts 'content_type' as alias.",
|
||||
})
|
||||
if output_type not in OUTPUT_TYPES:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": f"Invalid type: '{output_type}'",
|
||||
"valid_values": {"type": valid_types},
|
||||
})
|
||||
|
||||
title = body.get("title")
|
||||
if not title:
|
||||
raise HTTPException(422, {
|
||||
"error": "validation_failed",
|
||||
"detail": "Missing required field: title",
|
||||
"hint": "Provide a brief title describing this output",
|
||||
})
|
||||
|
||||
# 内容模式:content(直传)或 content_path(引用)
|
||||
content = body.get("content")
|
||||
content_path = body.get("content_path") or body.get("path")
|
||||
|
||||
if content and not content_path:
|
||||
# 内容直传模式:自动写文件
|
||||
import os
|
||||
artifacts_dir = os.path.join(
|
||||
os.path.dirname(bb.db_path), "artifacts", task_id
|
||||
)
|
||||
os.makedirs(artifacts_dir, exist_ok=True)
|
||||
# 安全文件名
|
||||
safe_name = "".join(
|
||||
c if c.isalnum() or c in "._-" else "_" for c in title)
|
||||
if not safe_name:
|
||||
safe_name = "output"
|
||||
file_path = os.path.join(artifacts_dir, safe_name)
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
f.write(content)
|
||||
content_path = file_path
|
||||
|
||||
oid = bb.write_output(
|
||||
task_id, agent, output_type, title,
|
||||
content_path=content_path,
|
||||
summary=body.get("summary"),
|
||||
metadata=body.get("metadata"),
|
||||
)
|
||||
return {"ok": True, "output_id": oid}
|
||||
|
||||
|
||||
# --- Decisions ---
|
||||
|
||||
@router.get("/tasks/{task_id}/decisions")
|
||||
async def get_decisions(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"decisions": [dict(d.__dict__) for d in bb.get_decisions(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/decisions")
|
||||
async def add_decision(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
did = bb.add_decision(task_id, body["decider"], body["decision"],
|
||||
body["rationale"],
|
||||
alternatives=body.get("alternatives"))
|
||||
return {"ok": True, "decision_id": did}
|
||||
|
||||
|
||||
# --- Observations ---
|
||||
|
||||
@router.post("/tasks/{task_id}/observations")
|
||||
async def add_observation(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
oid = bb.add_observation(task_id, body["observer"], body["body"],
|
||||
severity=body.get("severity", "info"))
|
||||
return {"ok": True, "observation_id": oid}
|
||||
|
||||
|
||||
# --- Reviews ---
|
||||
|
||||
@router.get("/tasks/{task_id}/reviews")
|
||||
async def get_reviews(project_id: str, task_id: str):
|
||||
bb = _bb(project_id)
|
||||
return {"reviews": [dict(r.__dict__) for r in bb.get_reviews(task_id)]}
|
||||
|
||||
|
||||
@router.post("/tasks/{task_id}/reviews")
|
||||
async def add_review(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
bb = _bb(project_id)
|
||||
review = Review(
|
||||
id=body["id"], task_id=task_id, reviewer=body["reviewer"],
|
||||
review_type=body["review_type"], verdict=body["verdict"],
|
||||
summary=body["summary"], confidence=body.get("confidence"),
|
||||
round=body.get("round", 1), max_rounds=body.get("max_rounds", 3),
|
||||
)
|
||||
bb.add_review(review)
|
||||
return {"ok": True, "review_id": review.id}
|
||||
|
||||
|
||||
@router.patch("/tasks/{task_id}")
|
||||
async def patch_task(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
"""更新任务元数据(归档、标题等)"""
|
||||
@@ -497,7 +293,6 @@ async def patch_task(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
if not updates:
|
||||
return {"ok": True}
|
||||
# 直接用 SQL 更新
|
||||
import sqlite3
|
||||
conn = sqlite3.connect(str(bb.db_path), timeout=5)
|
||||
try:
|
||||
set_clause = ", ".join(f"{k}=?" for k in updates)
|
||||
@@ -509,38 +304,9 @@ async def patch_task(project_id: str, task_id: str, body: Dict[str, Any]):
|
||||
return {"ok": True}
|
||||
|
||||
|
||||
# --- Per-task Events & Experiences ---
|
||||
|
||||
@router.get("/tasks/{task_id}/events")
|
||||
async def get_task_events(project_id: str, task_id: str,
|
||||
limit: int = Query(50, le=200)):
|
||||
q = _q(project_id)
|
||||
return {"events": q.task_events(task_id, limit)}
|
||||
|
||||
|
||||
@router.get("/tasks/{task_id}/experiences")
|
||||
async def get_task_experiences(project_id: str, task_id: str):
|
||||
q = _q(project_id)
|
||||
return {"experiences": q.task_experiences(task_id)}
|
||||
|
||||
|
||||
# --- Global Events ---
|
||||
|
||||
@router.get("/events")
|
||||
async def get_events(project_id: str, limit: int = Query(50, le=200)):
|
||||
q = _q(project_id)
|
||||
return {"events": q.recent_events(limit)}
|
||||
|
||||
|
||||
# --- Summary ---
|
||||
|
||||
@router.get("/summary")
|
||||
async def task_summary(project_id: str):
|
||||
q = _q(project_id)
|
||||
return {"summary": q.task_summary()}
|
||||
|
||||
|
||||
# --- Archive (v2.8) ---
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Archive (v2.8)
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
@router.post("/tasks/{task_id}/archive")
|
||||
async def archive_task(project_id: str, task_id: str,
|
||||
@@ -563,10 +329,3 @@ async def archive_done_tasks(project_id: str):
|
||||
bb = _bb(project_id)
|
||||
count = bb.archive_done_tasks()
|
||||
return {"ok": True, "archived_count": count}
|
||||
|
||||
|
||||
# --- Helper ---
|
||||
|
||||
def _task_to_dict(t: Task) -> Dict[str, Any]:
|
||||
d = {k: v for k, v in t.__dict__.items() if v is not None}
|
||||
return d
|
||||
+310
-18
@@ -50,7 +50,15 @@ router = APIRouter(tags=["toolchain"])
|
||||
_delivery_cache: Set[str] = set()
|
||||
_delivery_timestamps: List[Tuple[float, str]] = []
|
||||
_TTL_SECONDS = 7 * 24 * 3600
|
||||
_idempotency_lock = asyncio.Lock()
|
||||
_idempotency_lock: Optional[asyncio.Lock] = None
|
||||
|
||||
|
||||
def _get_idempotency_lock() -> asyncio.Lock:
|
||||
"""懒加载 asyncio.Lock,避免模块级创建时 event loop 不存在(Python 3.9)。"""
|
||||
global _idempotency_lock
|
||||
if _idempotency_lock is None:
|
||||
_idempotency_lock = asyncio.Lock()
|
||||
return _idempotency_lock
|
||||
|
||||
|
||||
def _is_duplicate(event: str, delivery: str,
|
||||
@@ -189,6 +197,7 @@ def _calc_risk_level(changed_files: List[str]) -> str:
|
||||
|
||||
|
||||
MAIL_PROJECT_ID = "_mail"
|
||||
TOOLCHAIN_PROJECT_ID = "_toolchain"
|
||||
|
||||
|
||||
def _mail_db_path() -> Path:
|
||||
@@ -200,6 +209,73 @@ def _mail_db_path() -> Path:
|
||||
return db
|
||||
|
||||
|
||||
def _toolchain_db_path() -> Path:
|
||||
"""获取 Toolchain 数据库路径,确保目录和表存在。"""
|
||||
root = get_data_root()
|
||||
db = root / TOOLCHAIN_PROJECT_ID / "blackboard.db"
|
||||
db.parent.mkdir(parents=True, exist_ok=True)
|
||||
init_db(db)
|
||||
return db
|
||||
|
||||
|
||||
def _send_toolchain_task(
|
||||
to_agent: str,
|
||||
title: str,
|
||||
description: str,
|
||||
event_type: str,
|
||||
action_type: str,
|
||||
steps: list,
|
||||
context_data: dict | None = None,
|
||||
source: str = "webhook",
|
||||
) -> str:
|
||||
"""创建 Toolchain Task 并写入 _toolchain DB。
|
||||
|
||||
Args:
|
||||
to_agent: 收件人 Agent ID
|
||||
title: 任务标题
|
||||
description: 任务描述(模板渲染后的事件信息)
|
||||
event_type: 事件类型(review_result / ci_failure / ...)
|
||||
action_type: 动作分类(用于步骤选择和日志统计)
|
||||
steps: 结构化编号步骤列表
|
||||
context_data: 事件上下文数据(PR 号、仓库名等)
|
||||
source: 来源标识
|
||||
|
||||
Returns:
|
||||
创建的 Task ID
|
||||
"""
|
||||
if to_agent not in AGENT_IDS:
|
||||
logger.warning("Unknown agent: %s, skipping toolchain task", to_agent)
|
||||
return ""
|
||||
|
||||
task_id = f"tc-{int(datetime.now().timestamp() * 1000)}"
|
||||
must_hives = json.dumps({
|
||||
"event_type": event_type,
|
||||
"action_type": action_type,
|
||||
"steps": steps,
|
||||
"context": context_data or {},
|
||||
"from": "system",
|
||||
"source": source,
|
||||
}, ensure_ascii=False)
|
||||
|
||||
task = Task(
|
||||
id=task_id,
|
||||
title=title,
|
||||
description=description,
|
||||
assignee=to_agent,
|
||||
assigned_by="system",
|
||||
must_haves=must_hives,
|
||||
task_type="toolchain",
|
||||
status="pending",
|
||||
)
|
||||
bb = Blackboard(_toolchain_db_path())
|
||||
bb.create_task(task)
|
||||
logger.info(
|
||||
"Toolchain task sent: %s → %s [%s] action_type=%s",
|
||||
title[:40], to_agent, task_id, action_type,
|
||||
)
|
||||
return task_id
|
||||
|
||||
|
||||
def _send_mail(
|
||||
to_agent: str,
|
||||
title: str,
|
||||
@@ -327,7 +403,25 @@ async def _send_mention_mails(
|
||||
})
|
||||
|
||||
title = f"@mention ({intent_hint}): {source_type} {number_str} ({repo})"
|
||||
_send_mail(agent_id, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=agent_id,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="mention",
|
||||
action_type="mention",
|
||||
steps=[
|
||||
"按上方 mention 模板中的 response_guidance 执行",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
],
|
||||
context_data={
|
||||
"source_type": source_type,
|
||||
"source_url": source_url,
|
||||
"commenter": commenter,
|
||||
"content_snippet": content[:500],
|
||||
"repo": repo,
|
||||
"issue_number": issue_number,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -379,7 +473,27 @@ async def _handle_pr_opened(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"Review 请求: {pr_title} ({repo}#{pr_number})"
|
||||
_send_mail("simayi-challenger", title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent="simayi-challenger",
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="review_request",
|
||||
action_type="review_request",
|
||||
steps=[
|
||||
f"读取 PR diff(Gitea API: GET /repos/{repo}/pulls/{pr_number}.diff)",
|
||||
"按审查清单审查(参考 code-review Skill)",
|
||||
f"提交 Review(Gitea API: POST /repos/{repo}/pulls/{pr_number}/reviews)— APPROVE 或 REQUEST_CHANGES",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
],
|
||||
context_data={
|
||||
"pr_number": pr_number,
|
||||
"repo": repo,
|
||||
"pr_title": pr_title,
|
||||
"pr_author": pr_author,
|
||||
"branch": branch,
|
||||
"risk_level": risk_level,
|
||||
},
|
||||
)
|
||||
|
||||
# S3: PR body @mention 通知
|
||||
pr_body = pr.get("body", "") or ""
|
||||
@@ -488,7 +602,25 @@ async def _handle_pull_request_review(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"Review 评论: {pr_title} ({repo}#{pr_number})"
|
||||
_send_mail(pr_author, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=pr_author,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="review_comment",
|
||||
action_type="review_comment",
|
||||
steps=[
|
||||
f"查看评论(Gitea API: GET /repos/{repo}/issues/{pr_number}/comments)",
|
||||
"根据评论内容响应(修改代码或在 PR 上回复 comment)",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
],
|
||||
context_data={
|
||||
"pr_number": pr_number,
|
||||
"repo": repo,
|
||||
"pr_title": pr_title,
|
||||
"reviewer": reviewer,
|
||||
"comment_body": review_body,
|
||||
},
|
||||
)
|
||||
|
||||
# S5: Review body @mention 通知(COMMENTED 路径)
|
||||
await _send_review_mentions(review_body, reviewer, pr_author, pr, repo, pr_number)
|
||||
@@ -510,7 +642,34 @@ async def _handle_pull_request_review(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"Review {result}: {pr_title} ({repo}#{pr_number})"
|
||||
_send_mail(pr_author, title, text)
|
||||
if state == "APPROVED":
|
||||
tc_steps = [
|
||||
f"合并 PR(Gitea API: POST /repos/{repo}/pulls/{pr_number}/merge)",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
]
|
||||
else: # REQUEST_CHANGES
|
||||
tc_steps = [
|
||||
"按审查意见逐条修改代码",
|
||||
"push 到原分支 → CI 自动跑",
|
||||
"CI 通过后等重新 Review",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
]
|
||||
_send_toolchain_task(
|
||||
to_agent=pr_author,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="review_result",
|
||||
action_type="review_result",
|
||||
steps=tc_steps,
|
||||
context_data={
|
||||
"pr_number": pr_number,
|
||||
"repo": repo,
|
||||
"pr_title": pr_title,
|
||||
"result": result,
|
||||
"reviewer": reviewer,
|
||||
"review_body": review_body,
|
||||
},
|
||||
)
|
||||
|
||||
# S5: Review body @mention 通知(非 COMMENTED 路径)
|
||||
await _send_review_mentions(review_body, reviewer, pr_author, pr, repo, pr_number)
|
||||
@@ -579,11 +738,31 @@ async def _handle_pr_synchronize(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"PR 更新: {pr_title} ({repo}#{pr_number})"
|
||||
_send_mail(reviewer, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=reviewer,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="review_updated",
|
||||
action_type="review_updated",
|
||||
steps=[
|
||||
f"读取 PR diff(Gitea API: GET /repos/{repo}/pulls/{pr_number}.diff)",
|
||||
"重点检查上次 Review 意见的修改部分",
|
||||
f"提交 Review(Gitea API: POST /repos/{repo}/pulls/{pr_number}/reviews)",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
],
|
||||
context_data={
|
||||
"pr_number": pr_number,
|
||||
"repo": repo,
|
||||
"pr_title": pr_title,
|
||||
"pr_author": pr_author,
|
||||
"new_sha": new_sha,
|
||||
"reviewer": reviewer,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
def _send_deploy_failure_mail(repo: str, pr_number: int, pr_title: str, reason: str) -> None:
|
||||
"""CD 部署失败通知,复用 deploy_failure 模板"""
|
||||
def _send_deploy_failure_task(repo: str, pr_number: int, pr_title: str, reason: str) -> None:
|
||||
"""CD 部署失败通知,走 ToolchainHandler。"""
|
||||
text = render_template("deploy_failure", {
|
||||
"repo": repo,
|
||||
"commit_sha": f"PR #{pr_number}",
|
||||
@@ -591,7 +770,24 @@ def _send_deploy_failure_mail(repo: str, pr_number: int, pr_title: str, reason:
|
||||
title = f"部署失败: {repo} (auto-deploy, PR #{pr_number})"
|
||||
full_text = f"{text}\n\n失败原因: {reason}"
|
||||
for agent_id in ("jiangwei-infra", "pangtong-fujunshi"):
|
||||
_send_mail(agent_id, title, full_text)
|
||||
_send_toolchain_task(
|
||||
to_agent=agent_id,
|
||||
title=title,
|
||||
description=full_text,
|
||||
event_type="deploy_failure",
|
||||
action_type="deploy_failure",
|
||||
steps=[
|
||||
"检查 deploy 日志",
|
||||
"根据 deploy 日志判断失败原因类型:\n a. 代码/配置问题(rsync 路径错、依赖缺失、启动失败)→ 修复 → 重新部署\n b. 基础设施问题(Gitea 不可用、网络不通、磁盘满、SSH 故障)→ 在该仓库创建 Issue 指派 jiangwei-infra(见下方「需要创建 Issue 时」),label 必须包含 type/infrastructure",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)— 报告中说明判断的原因类型和执行的操作",
|
||||
],
|
||||
context_data={
|
||||
"repo": repo,
|
||||
"pr_number": pr_number,
|
||||
"pr_title": pr_title,
|
||||
"reason": reason,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
|
||||
@@ -623,7 +819,21 @@ async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"PR 已合并: {pr_title} ({repo}#{pr_number})"
|
||||
_send_mail(pr_author, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=pr_author,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="review_merged",
|
||||
action_type="review_merged",
|
||||
steps=[], # 纯通知,无步骤
|
||||
context_data={
|
||||
"pr_number": pr_number,
|
||||
"repo": repo,
|
||||
"pr_title": pr_title,
|
||||
"pr_author": pr_author,
|
||||
"merged_by": merged_by,
|
||||
},
|
||||
)
|
||||
|
||||
# 自动部署:git pull + rsync + 按需 post_deploy
|
||||
try:
|
||||
@@ -676,7 +886,7 @@ async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
|
||||
|
||||
if rsync_proc.returncode != 0:
|
||||
logger.error("Auto-deploy: rsync failed: %s", rsync_err.decode())
|
||||
_send_deploy_failure_mail(repo, pr_number, pr_title, f"rsync 失败: {rsync_err.decode()}")
|
||||
_send_deploy_failure_task(repo, pr_number, pr_title, f"rsync 失败: {rsync_err.decode()}")
|
||||
return
|
||||
|
||||
# Step 3: 判断是否需要执行 post_deploy
|
||||
@@ -731,7 +941,7 @@ async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
|
||||
|
||||
if deploy_proc.returncode != 0:
|
||||
logger.error("Auto-deploy: post_deploy failed: %s", deploy_err.decode())
|
||||
_send_deploy_failure_mail(repo, pr_number, pr_title, f"post_deploy 失败 ({cmd}): {deploy_err.decode()}")
|
||||
_send_deploy_failure_task(repo, pr_number, pr_title, f"post_deploy 失败 ({cmd}): {deploy_err.decode()}")
|
||||
break
|
||||
else:
|
||||
logger.info("Auto-deploy: all post_deploy commands succeeded (files: %s)", ", ".join(file_list[:5]))
|
||||
@@ -740,7 +950,7 @@ async def _handle_pr_closed(payload: Dict[str, Any]) -> None:
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
logger.error("Auto-deploy: timeout for %s", repo)
|
||||
_send_deploy_failure_mail(repo, pr_number, pr_title, "部署超时")
|
||||
_send_deploy_failure_task(repo, pr_number, pr_title, "部署超时")
|
||||
except Exception as e:
|
||||
logger.error("Auto-deploy: unexpected error: %s", e)
|
||||
|
||||
@@ -786,8 +996,58 @@ async def _handle_issues(payload: Dict[str, Any]) -> None:
|
||||
"brief": brief,
|
||||
})
|
||||
|
||||
title = f"Issue 指派: {issue_title} ({repo}#{issue_number})"
|
||||
_send_mail(assignee, title, text)
|
||||
# 检查是否是基础设施 Issue(按 label 分流)
|
||||
is_infrastructure = any("infrastructure" in lbl.lower() for lbl in labels_list)
|
||||
|
||||
if is_infrastructure:
|
||||
infra_steps = [
|
||||
"根据 Issue body 中的错误来源和日志片段排查问题",
|
||||
"修复基础设施问题(如修复 CI runner 环境、恢复网络、重启服务等)",
|
||||
"修复后在 Issue 上 comment 说明修复方式和结果",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
]
|
||||
title = f"基础设施 Issue: {issue_title} ({repo}#{issue_number})"
|
||||
_send_toolchain_task(
|
||||
to_agent=assignee,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="infrastructure_failure",
|
||||
action_type="infrastructure_failure",
|
||||
steps=infra_steps,
|
||||
context_data={
|
||||
"issue_number": issue_number,
|
||||
"repo": repo,
|
||||
"issue_title": issue_title,
|
||||
"labels": labels,
|
||||
"issue_body": issue_body or "(无描述)",
|
||||
"brief": brief,
|
||||
},
|
||||
)
|
||||
else:
|
||||
title = f"Issue 指派: {issue_title} ({repo}#{issue_number})"
|
||||
_send_toolchain_task(
|
||||
to_agent=assignee,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="issue_assigned",
|
||||
action_type="issue_assigned",
|
||||
steps=[
|
||||
f"创建分支 fix/{issue_number}-{brief}",
|
||||
"编码 + 写 UT",
|
||||
"push → 等 CI",
|
||||
f"CI 通过后创建 PR(Gitea API: POST /repos/{repo}/pulls)",
|
||||
"等 Review",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)",
|
||||
],
|
||||
context_data={
|
||||
"issue_number": issue_number,
|
||||
"repo": repo,
|
||||
"issue_title": issue_title,
|
||||
"labels": labels,
|
||||
"issue_body": issue_body or "(无描述)",
|
||||
"brief": brief,
|
||||
},
|
||||
)
|
||||
|
||||
elif action == "opened":
|
||||
if "部署失败" in issue_title:
|
||||
@@ -802,7 +1062,22 @@ async def _handle_issues(payload: Dict[str, Any]) -> None:
|
||||
|
||||
title = f"部署失败: {repo}"
|
||||
for agent_id in ("jiangwei-infra", "pangtong-fujunshi"):
|
||||
_send_mail(agent_id, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=agent_id,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="deploy_failure",
|
||||
action_type="deploy_failure",
|
||||
steps=[
|
||||
"检查 deploy 日志",
|
||||
"根据 deploy 日志判断失败原因类型:\n a. 代码/配置问题(rsync 路径错、依赖缺失、启动失败)→ 修复 → 重新部署\n b. 基础设施问题(Gitea 不可用、网络不通、磁盘满、SSH 故障)→ 在该仓库创建 Issue 指派 jiangwei-infra(见下方「需要创建 Issue 时」),label 必须包含 type/infrastructure",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)— 报告中说明判断的原因类型和执行的操作",
|
||||
],
|
||||
context_data={
|
||||
"repo": repo,
|
||||
"commit_sha": commit_sha or "(未知)",
|
||||
},
|
||||
)
|
||||
|
||||
# Issue body @mention(opened 时检查)
|
||||
issue_body = issue.get("body", "") or ""
|
||||
@@ -869,7 +1144,24 @@ async def _handle_issue_comment(payload: Dict[str, Any]) -> None:
|
||||
})
|
||||
|
||||
title = f"CI 失败: {repo}#{issue_number}"
|
||||
_send_mail(pr_author, title, text)
|
||||
_send_toolchain_task(
|
||||
to_agent=pr_author,
|
||||
title=title,
|
||||
description=text,
|
||||
event_type="ci_failure",
|
||||
action_type="ci_failure",
|
||||
steps=[
|
||||
"查看完整 CI 日志(PR 页面或 Gitea Actions 页面)",
|
||||
"根据 CI 日志判断失败原因类型:\n a. 代码问题(lint/test 失败)→ 修复失败的测试 → push 到原分支 → CI 自动重跑\n b. 基础设施问题(runner 环境/Python/venv/Gitea/网络故障)→ 在该仓库创建 Issue 指派 jiangwei-infra(见下方「需要创建 Issue 时」),label 必须包含 type/infrastructure",
|
||||
"提交 action report(POST http://localhost:8083/api/projects/_toolchain/tasks/<task_id>/comments,comment_type=action_report)— 报告中说明判断的原因类型和执行的操作",
|
||||
],
|
||||
context_data={
|
||||
"pr_number": issue_number,
|
||||
"repo": repo,
|
||||
"branch": branch,
|
||||
"error_summary": error_summary,
|
||||
},
|
||||
)
|
||||
# CI 处理完不 return,继续检查 @mention
|
||||
|
||||
# === 路径 2:@mention 通知(新增,独立路径) ===
|
||||
@@ -960,7 +1252,7 @@ async def gitea_webhook(
|
||||
|
||||
# 2. 幂等检查(需要在 payload 解析后,以支持内容去重)
|
||||
if x_gitea_event and x_gitea_delivery:
|
||||
async with _idempotency_lock:
|
||||
async with _get_idempotency_lock():
|
||||
if _is_duplicate(x_gitea_event, x_gitea_delivery, payload):
|
||||
logger.debug(
|
||||
"Duplicate webhook: %s/%s",
|
||||
|
||||
@@ -117,6 +117,7 @@ def _migrate_v28(conn: sqlite3.Connection) -> None:
|
||||
|
||||
_safe_add_column(conn, "tasks", "round_count", "INTEGER DEFAULT 0")
|
||||
_safe_add_column(conn, "tasks", "resumed_from", "TEXT")
|
||||
_safe_add_column(conn, "tasks", "dispatch_count", "INTEGER DEFAULT 0")
|
||||
|
||||
# 3. checkpoints 表(M3)
|
||||
conn.execute("""CREATE TABLE IF NOT EXISTS checkpoints (
|
||||
@@ -209,6 +210,7 @@ VALID_TRANSITIONS = {
|
||||
COMMENT_TYPES = frozenset({
|
||||
"general", "handoff", "observation", "review", "rebuttal",
|
||||
"rebuttal_response", "debate_argument", "debate_rebuttal", "debate_judgment",
|
||||
"action_report",
|
||||
})
|
||||
|
||||
SEVERITY_LEVELS = frozenset({"blocking", "warning", "info", "audit"})
|
||||
@@ -293,7 +295,7 @@ _SCHEMA_STATEMENTS = [
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
task_id TEXT NOT NULL REFERENCES tasks(id),
|
||||
author TEXT NOT NULL,
|
||||
comment_type TEXT NOT NULL DEFAULT 'general' CHECK (comment_type IN ('general','handoff','observation','review','rebuttal','rebuttal_response','debate_argument','debate_rebuttal','debate_judgment')),
|
||||
comment_type TEXT NOT NULL DEFAULT 'general',
|
||||
body TEXT NOT NULL,
|
||||
mentions TEXT,
|
||||
created_at TEXT NOT NULL DEFAULT (datetime('now'))
|
||||
|
||||
@@ -41,6 +41,8 @@ class Task:
|
||||
resumed_from: Optional[str] = None # 暂停前状态,恢复时回到原状态
|
||||
# v2.9 四相循环
|
||||
round_count: int = 0 # 庞统 review 轮次计数
|
||||
# §15 Runaway Guard
|
||||
dispatch_count: int = 0 # 被 ticker dispatch 的总次数
|
||||
# v2.8 归档
|
||||
archived: bool = False
|
||||
archived_at: Optional[str] = None
|
||||
|
||||
@@ -208,7 +208,7 @@ class Blackboard:
|
||||
params.append(parent_task)
|
||||
if conditions:
|
||||
query += " WHERE " + " AND ".join(conditions)
|
||||
query += " ORDER BY priority ASC, created_at ASC"
|
||||
query += " ORDER BY priority ASC, created_at DESC"
|
||||
rows = conn.execute(query, params).fetchall()
|
||||
return [Task.from_row(r) for r in rows]
|
||||
finally:
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
# DEPRECATED per §19 重设计 — 经验蒸馏改为双层 daily cron(L1 各 agent + L2 庞统)
|
||||
# 保留代码供参考,后续 P3 清理时物理删除
|
||||
"""Experience Distillation — 经验蒸馏
|
||||
|
||||
从已完成的任务产出中提取经验:
|
||||
|
||||
@@ -9,7 +9,7 @@ import logging
|
||||
from pathlib import Path
|
||||
|
||||
from src.daemon.base_task_handler import BaseTaskHandler, VerifyResult
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext, GiteaConventionSection, WikiGuideSection, DeliveryChecklistSection
|
||||
from src.blackboard.db import get_connection
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.handler.mail")
|
||||
@@ -36,7 +36,7 @@ class MailHandler(BaseTaskHandler):
|
||||
return composer.compose(context)
|
||||
|
||||
def get_sections(self) -> list:
|
||||
return [MailContextSection(), MailApiSection(), MailConstraintsSection()]
|
||||
return [MailContextSection(), MailApiSection(), MailConstraintsSection(), GiteaConventionSection(), WikiGuideSection(), DeliveryChecklistSection()]
|
||||
|
||||
def verify_completion(self, task_id: str, db_path: Path) -> VerifyResult:
|
||||
"""Mail 完成验证:区分 inform/request。
|
||||
|
||||
@@ -65,6 +65,8 @@ class PromptContext:
|
||||
# toolchain 专用
|
||||
event_type: str = "" # ci_failure / review_request / ...
|
||||
event_data: Dict = field(default_factory=dict)
|
||||
action_type: str = "" # 动作分类(review_result / ci_failure / ...)
|
||||
action_steps: list = field(default_factory=list) # 结构化编号步骤列表
|
||||
|
||||
# 前序产出
|
||||
depends_on_outputs: Optional[List] = None
|
||||
@@ -125,3 +127,74 @@ class PromptComposer:
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
class GiteaConventionSection:
|
||||
"""Gitea 标题规范引导段 — 提醒 Agent 创建 Issue/PR 时遵循标题格式。"""
|
||||
|
||||
name: str = "gitea_convention"
|
||||
priority: int = 55 # CONSTRAINTS(50) 和 EXTENSION(60) 之间
|
||||
|
||||
CONVENTION_TEXT = (
|
||||
"## Gitea 标题规范\n"
|
||||
"创建 Issue/PR 时,标题**必须**包含项目代号前缀:\n"
|
||||
"- Issue: `[代号] type: 简述`,如 `[moz] bug: Mail API 500`\n"
|
||||
"- PR: `[代号] type(scope): 简述`,如 `[moz] impl(daemon): WikiGuideSection 注入`\n"
|
||||
"代号:moz=moziplus_v2, quant=quant_live, vnpy=vnpy\n"
|
||||
"type: bug/feat/impl/fix/docs/test/ci/refactor/chore"
|
||||
)
|
||||
|
||||
def render(self, context: "PromptContext") -> str:
|
||||
return self.CONVENTION_TEXT
|
||||
|
||||
def should_include(self, context: "PromptContext") -> bool:
|
||||
return True
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# WikiGuideSection — 知识查询引导段
|
||||
# ---------------------------------------------------------------------------
|
||||
class WikiGuideSection:
|
||||
"""知识查询引导段 — 引导 Agent 在关键决策点查 wiki-vault。"""
|
||||
|
||||
name: str = "wiki_guide"
|
||||
priority: int = 60 # PRIORITY_EXTENSION
|
||||
|
||||
WIKI_GUIDE = (
|
||||
"## 知识查询引导\n"
|
||||
"涉及方案设计、编码实现、故障排查时,先查 wiki-vault 相关实践:\n"
|
||||
"- 路径:/Volumes/KnowledgeBase/wiki-vault/\n"
|
||||
"- 速查:index.md → grep 关键词 → summary 字段 → 按需读全文\n"
|
||||
"- 查不到:在 _meta/knowledge-gaps.md 记录"
|
||||
)
|
||||
|
||||
def render(self, context: "PromptContext") -> str:
|
||||
return self.WIKI_GUIDE
|
||||
|
||||
def should_include(self, context: "PromptContext") -> bool:
|
||||
return True
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# DeliveryChecklistSection — 交付检查清单
|
||||
# ---------------------------------------------------------------------------
|
||||
class DeliveryChecklistSection:
|
||||
"""交付检查清单 — 提醒 Agent 完成前同步关联成果物。"""
|
||||
|
||||
name: str = "delivery_checklist"
|
||||
priority: int = 55 # CONSTRAINTS(50) 和 EXTENSION(60) 之间
|
||||
|
||||
CHECKLIST_TEXT = (
|
||||
"## 交付检查\n"
|
||||
"完成代码改动前确认:\n"
|
||||
"- 改了实现 → docs/design/ 对应设计文档是否需要更新\n"
|
||||
"- 改了实现 → tests/ 是否有对应测试脚本需要更新\n"
|
||||
"- 所有成果物变更通过 PR 流程:PR review 把关设计合理性,CI 把关代码质量,CD 把关部署正确性\n"
|
||||
)
|
||||
|
||||
def render(self, context: "PromptContext") -> str:
|
||||
return self.CHECKLIST_TEXT
|
||||
|
||||
def should_include(self, context: "PromptContext") -> bool:
|
||||
return True
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
# DEPRECATED per §19 重设计 — 不再参与 skill 发现/加载
|
||||
# 实际 skill 发现走 openclaw 原生 <available_skills> 机制
|
||||
# 保留代码供参考,后续 P3 清理时物理删除
|
||||
"""Skill System — 技能注册、加载、匹配、执行
|
||||
|
||||
三层自由度:
|
||||
|
||||
+34
-5
@@ -286,10 +286,19 @@ class AgentSpawner:
|
||||
# 从 must_haves 解析 mail 元数据(from / performative)
|
||||
from_agent = ""
|
||||
mail_type = ""
|
||||
action_type = ""
|
||||
action_steps = []
|
||||
event_type = ""
|
||||
event_data = {}
|
||||
try:
|
||||
meta = json.loads(must_haves) if must_haves else {}
|
||||
from_agent = meta.get("from", "")
|
||||
mail_type = meta.get("performative", meta.get("type", ""))
|
||||
# toolchain 字段提取
|
||||
action_type = meta.get("action_type", "")
|
||||
action_steps = meta.get("steps", [])
|
||||
event_type = meta.get("event_type", "")
|
||||
event_data = meta.get("context", {})
|
||||
except Exception:
|
||||
pass
|
||||
ctx = PromptContext(
|
||||
@@ -298,6 +307,8 @@ class AgentSpawner:
|
||||
agent_id=agent_id, role=spawn_type,
|
||||
spawn_type=spawn_type,
|
||||
from_agent=from_agent, mail_type=mail_type,
|
||||
action_type=action_type, action_steps=action_steps,
|
||||
event_type=event_type, event_data=event_data,
|
||||
)
|
||||
return handler.build_prompt(ctx)
|
||||
|
||||
@@ -619,19 +630,24 @@ curl -X POST http://{self.api_host}:{self.api_port}/api/projects/{project_id}/ta
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
)
|
||||
self._register_session(session_id, agent_id, task_id, proc.pid,
|
||||
# use_main_session=True 时 session_id 为 None,但 _register_session 和
|
||||
# _monitor_process 需要一个非 None 的 key;同时 ticker 等调用方用
|
||||
# `result is not None` 判断 spawn 是否成功,返回 None 会被误判为失败。
|
||||
# 统一用 "main" 作为占位标识。
|
||||
effective_sid = session_id or "main"
|
||||
self._register_session(effective_sid, agent_id, task_id, proc.pid,
|
||||
broadcast_task_ids=broadcast_task_ids)
|
||||
logger.info("Spawned agent %s (session=%s, pid=%d)",
|
||||
agent_id, session_id, proc.pid)
|
||||
agent_id, effective_sid, proc.pid)
|
||||
|
||||
# Schedule monitor(传 wrapped_on_complete)
|
||||
asyncio.create_task(
|
||||
self._monitor_process(session_id, proc, agent_id, task_id,
|
||||
self._monitor_process(effective_sid, proc, agent_id, task_id,
|
||||
on_complete=_wrapped_on_complete,
|
||||
db_path=task_db_path or self.db_path)
|
||||
)
|
||||
|
||||
return session_id
|
||||
return effective_sid
|
||||
|
||||
except Exception as e:
|
||||
# spawn 失败也要 release counter
|
||||
@@ -1245,7 +1261,7 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
|
||||
conn = get_connection(db_path)
|
||||
try:
|
||||
row = conn.execute(
|
||||
"SELECT id, title, status FROM tasks WHERE id=?", (
|
||||
"SELECT id, title, status, must_haves FROM tasks WHERE id=?", (
|
||||
task_id,)
|
||||
).fetchone()
|
||||
if not row:
|
||||
@@ -1943,6 +1959,19 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
|
||||
try:
|
||||
from src.daemon.mail_notify import _is_mail_project, notify_mail_failed
|
||||
if _is_mail_project(db_path):
|
||||
# 防御性检查:如果 task 已经 done,不触发失败通知(竞态保护)
|
||||
# 场景:spawner 标 failed 和 handler 标 done 同时发生
|
||||
try:
|
||||
conn2 = get_connection(db_path)
|
||||
current_status = conn2.execute(
|
||||
"SELECT status FROM tasks WHERE id=?", (task_id,)
|
||||
).fetchone()
|
||||
conn2.close()
|
||||
if current_status and current_status["status"] == "done":
|
||||
logger.info("Task %s already done, skipping mail failure notification", task_id)
|
||||
return
|
||||
except Exception:
|
||||
pass
|
||||
# Mail 失败:通知发件人,不 @pangtong
|
||||
notify_mail_failed(db_path, task_id, reason, detail)
|
||||
else:
|
||||
|
||||
@@ -10,7 +10,7 @@ from pathlib import Path
|
||||
from typing import Dict, Optional
|
||||
|
||||
from src.daemon.base_task_handler import BaseTaskHandler, VerifyResult
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext, GiteaConventionSection, WikiGuideSection, DeliveryChecklistSection
|
||||
from src.blackboard.db import get_connection
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.handler")
|
||||
@@ -306,13 +306,16 @@ class TaskHandler(BaseTaskHandler):
|
||||
return True
|
||||
|
||||
def get_sections(self) -> list:
|
||||
"""返回 5 个 PromptSection 实例。"""
|
||||
"""返回 PromptSection 实例。"""
|
||||
return [
|
||||
TaskContextSection(),
|
||||
PriorOutputsSection(),
|
||||
RoleSkillSection(),
|
||||
TaskApiSection(),
|
||||
TaskConstraintsSection(),
|
||||
GiteaConventionSection(),
|
||||
WikiGuideSection(),
|
||||
DeliveryChecklistSection(),
|
||||
]
|
||||
|
||||
def build_prompt(self, context: PromptContext) -> str:
|
||||
|
||||
+54
-18
@@ -332,25 +332,10 @@ class Ticker:
|
||||
except Exception as e:
|
||||
logger.warning("HealthChecker error for %s: %s", project_id, e)
|
||||
|
||||
# 9. 经验蒸馏(完成的 task 自动触发)
|
||||
# 9. 经验蒸馏 — DEPRECATED per §19, 双层 daily cron 替代
|
||||
# 保留参数向后兼容,不再执行逐任务蒸馏
|
||||
if self.experience_distiller:
|
||||
try:
|
||||
conn2 = get_connection(db_path)
|
||||
try:
|
||||
done_tasks = conn2.execute(
|
||||
"SELECT id FROM tasks WHERE status='done' AND updated_at > datetime('now', '-60 seconds')"
|
||||
).fetchall()
|
||||
finally:
|
||||
conn2.close()
|
||||
for row in done_tasks:
|
||||
t = Blackboard(db_path).get_task(row[0])
|
||||
if t:
|
||||
self.experience_distiller.distill_from_task(
|
||||
task_id=t.id, task_title=t.title, task_type=t.task_type
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"ExperienceDistiller error for %s: %s", project_id, e)
|
||||
logger.debug("ExperienceDistiller deprecated per §19, skipping (use L1/L2 daily cron)")
|
||||
|
||||
# 10. 扫描后状态
|
||||
result["summary_after"] = queries.task_summary()
|
||||
@@ -1084,6 +1069,19 @@ Parent Task ID: {parent_task.id}
|
||||
broadcast_ids = await self._broadcast_claim(broadcast_tasks, db_path, project_id)
|
||||
dispatched.extend(broadcast_ids)
|
||||
|
||||
# §15 Runaway Guard: 统一递增 dispatch_count
|
||||
if dispatched:
|
||||
conn = get_connection(db_path)
|
||||
try:
|
||||
for tid in dispatched:
|
||||
conn.execute(
|
||||
"UPDATE tasks SET dispatch_count = COALESCE(dispatch_count, 0) + 1 WHERE id=?",
|
||||
(tid,),
|
||||
)
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
return dispatched
|
||||
|
||||
async def _broadcast_claim(self, tasks: list, db_path: Path,
|
||||
@@ -1376,6 +1374,19 @@ Parent Task ID: {parent_task.id}
|
||||
except Exception:
|
||||
logger.exception("Review dispatch failed for %s", task.id)
|
||||
|
||||
# §15 Runaway Guard: 统一递增 dispatch_count (review)
|
||||
if dispatched:
|
||||
conn = get_connection(db_path)
|
||||
try:
|
||||
for tid in dispatched:
|
||||
conn.execute(
|
||||
"UPDATE tasks SET dispatch_count = COALESCE(dispatch_count, 0) + 1 WHERE id=?",
|
||||
(tid,),
|
||||
)
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
return dispatched
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -1388,6 +1399,31 @@ Parent Task ID: {parent_task.id}
|
||||
reclaimed: List[str] = []
|
||||
now = datetime.utcnow() # UTC,与 SQLite datetime('now') 一致
|
||||
|
||||
# §15 Runaway Guard: per-task dispatch_count 上限检查
|
||||
# 覆盖所有状态,防止无限循环 dispatch
|
||||
MAX_DISPATCH_COUNT = 10
|
||||
for status_to_check in ("pending", "working", "claimed"):
|
||||
tasks_to_check = queries.tasks_by_status(status_to_check)
|
||||
for task in tasks_to_check:
|
||||
dispatch_count = getattr(task, 'dispatch_count', 0) or 0
|
||||
if dispatch_count >= MAX_DISPATCH_COUNT:
|
||||
conn = get_connection(db_path)
|
||||
try:
|
||||
ok = self._transition_status(
|
||||
conn, task.id, "failed",
|
||||
agent="daemon",
|
||||
detail={"reason": "runaway_guard",
|
||||
"dispatch_count": dispatch_count,
|
||||
"message": f"dispatch {dispatch_count} 次仍未完成,自动标 failed"},
|
||||
)
|
||||
if ok:
|
||||
reclaimed.append(task.id)
|
||||
logger.error(
|
||||
"Task %s: runaway guard triggered (dispatch_count=%d, status=%s), marking failed",
|
||||
task.id, dispatch_count, status_to_check)
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
# claimed 超时 → 重置为 pending(如果 retry_count >= 3 则升级庞统)
|
||||
claimed = queries.tasks_by_status("claimed")
|
||||
for task in claimed:
|
||||
|
||||
+400
-115
@@ -1,58 +1,122 @@
|
||||
"""toolchain_handler.py — 工具链事件 handler。
|
||||
"""toolchain_handler.py - 工具链事件 handler。
|
||||
|
||||
处理 Gitea Webhook 事件(CI 失败、Review 请求、Issue 指派等)。
|
||||
处理 Gitea Webhook 事件(CI 失败、Review 请求、Issue 指派等)。
|
||||
L2 引擎层强约束:输入(结构化步骤)+ 执行(Red Flags)+ 输出(action_report 验证)。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import Dict
|
||||
from typing import Dict, List
|
||||
|
||||
from src.daemon.base_task_handler import BaseTaskHandler, VerifyResult
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext
|
||||
from src.daemon.prompt_composer import PromptComposer, PromptContext, GiteaConventionSection, WikiGuideSection, DeliveryChecklistSection
|
||||
from src.daemon.toolchain_templates import render_template, _TEMPLATE_MAP
|
||||
from src.blackboard.db import get_connection
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.handler.toolchain")
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Gitea API 配置
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_GITEA_BASE = "http://192.168.2.154:3000/api/v1"
|
||||
_GITEA_TOKEN = os.environ.get("GITEA_TOKEN", "")
|
||||
|
||||
# action_type → action_hint 映射
|
||||
_ACTION_HINTS: Dict[str, str] = {
|
||||
"review_result": "你收到一个 Review 结果通知,这是一个需要你执行动作的事件(不是纯通知)。",
|
||||
"review_request": "你收到一个 Review 请求,这是一个需要你审查并提交 Review 的事件。",
|
||||
"review_updated": "你收到一个 PR 更新通知,这是一个需要你重新审查修改部分的事件。",
|
||||
"review_comment": "你收到一个 Review 评论,这是一个需要你查看并响应的事件。",
|
||||
"ci_failure": "你收到一个 CI 失败通知,这是一个需要你修复失败测试的事件。",
|
||||
"issue_assigned": "你收到一个 Issue 指派,这是一个需要你编码实现的事件。",
|
||||
"deploy_failure": "你收到一个部署失败通知,这是一个需要你排查并修复的事件。",
|
||||
"mention": "你收到一个 @mention 通知,这是一个需要你按指引响应的事件。",
|
||||
"review_merged": "你收到一个 PR 合并通知。这是一条纯通知,阅读即可。",
|
||||
"infrastructure_failure": "你收到一个基础设施问题报告,请排查并修复。",
|
||||
}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Toolchain PromptSections
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class ToolchainContextSection:
|
||||
"""事件类型 + 事件详情(priority=10)"""
|
||||
"""事件类型 + 事件详情 + 结构化步骤 + action_hint(priority=10)"""
|
||||
|
||||
name: str = "toolchain_context"
|
||||
priority: int = 10
|
||||
|
||||
EVENT_LABELS_ZH: Dict[str, str] = {
|
||||
"review_request": "Review 请求",
|
||||
"review_result": "Review 结果",
|
||||
"review_merged": "PR 合并",
|
||||
"review_comment": "Review 评论",
|
||||
"review_updated": "Review 更新",
|
||||
"ci_failure": "CI 失败",
|
||||
"deploy_failure": "部署失败",
|
||||
"issue_assigned": "Issue 指派",
|
||||
"mention": "@提及",
|
||||
}
|
||||
|
||||
def render(self, context: PromptContext) -> str:
|
||||
event_type = context.event_type
|
||||
event_data: Dict = context.event_data or {}
|
||||
|
||||
if event_type in _TEMPLATE_MAP:
|
||||
# 使用模板引擎渲染已知事件
|
||||
variables = {k: str(v) for k, v in event_data.items()}
|
||||
return render_template(event_type, variables)
|
||||
# 事件类型中文标签
|
||||
event_label = self.EVENT_LABELS_ZH.get(event_type, event_type or '未知')
|
||||
|
||||
# fallback:通用事件描述
|
||||
lines = ["## 工具链事件", ""]
|
||||
lines.append(f"- **事件类型**: {event_type or '未知'}")
|
||||
if event_data:
|
||||
lines.append("- **事件详情**:")
|
||||
for key, value in event_data.items():
|
||||
lines.append(f" - {key}: {value}")
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
# from / to 信息
|
||||
to_agent = context.agent_id or ''
|
||||
from_agent = 'system'
|
||||
|
||||
# Part 1: 事件信息(现有模板引擎)
|
||||
if event_type in _TEMPLATE_MAP:
|
||||
variables = {k: str(v) for k, v in event_data.items()}
|
||||
event_text = render_template(event_type, variables)
|
||||
# 补充事件类型中文标签 + from/to
|
||||
header = f"- **事件类型**: {event_label}\n- **来源**: {from_agent}\n- **指派**: {to_agent}\n"
|
||||
event_text = header + "\n" + event_text
|
||||
else:
|
||||
lines = ["## 工具链事件", ""]
|
||||
lines.append(f"- **事件类型**: {event_label}")
|
||||
lines.append(f"- **来源**: {from_agent}")
|
||||
lines.append(f"- **指派**: {to_agent}")
|
||||
if event_data:
|
||||
lines.append("- **事件详情**:")
|
||||
for key, value in event_data.items():
|
||||
lines.append(f" - {key}: {value}")
|
||||
lines.append("")
|
||||
event_text = "\n".join(lines)
|
||||
|
||||
# Part 2: 结构化编号步骤(新增,从 action_steps 渲染)
|
||||
steps: List[str] = context.action_steps or []
|
||||
if steps:
|
||||
step_lines = ["", "### 必须执行的步骤", ""]
|
||||
for i, step in enumerate(steps, 1):
|
||||
step_lines.append(f"{i}. {step}")
|
||||
steps_text = "\n".join(step_lines)
|
||||
else:
|
||||
steps_text = ""
|
||||
|
||||
# Part 3: action 指引(新增,按 action_type 选择)
|
||||
action_hint = _ACTION_HINTS.get(
|
||||
context.action_type,
|
||||
"你收到一个工具链事件,这是一个需要你执行动作的事件。",
|
||||
)
|
||||
|
||||
return f"{action_hint}\n\n{event_text}{steps_text}"
|
||||
|
||||
def should_include(self, context: PromptContext) -> bool:
|
||||
return True
|
||||
|
||||
|
||||
class ToolchainApiSection:
|
||||
"""API 操作指令(priority=40),success_status=done"""
|
||||
"""API 操作指令(priority=40)-- action_report 提交指引"""
|
||||
|
||||
name: str = "toolchain_api"
|
||||
priority: int = 40
|
||||
@@ -60,28 +124,61 @@ class ToolchainApiSection:
|
||||
API_HOST = "localhost:8083"
|
||||
|
||||
def render(self, context: PromptContext) -> str:
|
||||
task_id = context.task_id
|
||||
project_id = context.project_id
|
||||
agent_id = context.agent_id
|
||||
|
||||
lines = [
|
||||
"## API 操作指令",
|
||||
"",
|
||||
f"项目 ID: `{context.project_id}`",
|
||||
f"任务 ID: `{context.task_id}`",
|
||||
f"项目 ID: `{project_id}`",
|
||||
f"任务 ID: `{task_id}`",
|
||||
"",
|
||||
"### 完成后必须更新任务状态",
|
||||
"完成后务必通过以下命令将任务标记为 **done**:",
|
||||
"### 完成后必须提交 action report",
|
||||
"",
|
||||
"执行完所有步骤后,必须提交 action report:",
|
||||
"```bash",
|
||||
f'curl -s -X POST "http://{self.API_HOST}/api/projects/{context.project_id}/tasks/{context.task_id}/status" \\',
|
||||
f'curl -s -X POST "http://{self.API_HOST}/api/projects/{project_id}/tasks/{task_id}/comments" \\',
|
||||
' -H "Content-Type: application/json" \\',
|
||||
' -d \'{"status": "done"}\'',
|
||||
f' -d \'{{"author": "{agent_id}", "comment_type": "action_report", "body": "简要描述你执行了什么操作及结果"}}\'',
|
||||
"```",
|
||||
"",
|
||||
"⚠️ 不提交 action report 的任务会被标记为 failed。",
|
||||
"",
|
||||
"### 提交产出",
|
||||
"如有产出(如 review 结果、修复方案),提交到任务 outputs:",
|
||||
"",
|
||||
"如有产出(如 review 结果、修复方案),提交到任务 outputs:",
|
||||
"```bash",
|
||||
f'curl -s -X POST "http://{self.API_HOST}/api/projects/{context.project_id}/tasks/{context.task_id}/outputs" \\',
|
||||
f'curl -s -X POST "http://{self.API_HOST}/api/projects/{project_id}/tasks/{task_id}/outputs" \\',
|
||||
' -H "Content-Type: application/json" \\',
|
||||
' -d \'{"content": "<你的产出内容>", "type": "text"}\'',
|
||||
"```",
|
||||
"",
|
||||
"### 需要其他角色支持时",
|
||||
"",
|
||||
"如果在执行过程中需要其他角色协助(如缺数据、需要审批等),在关联的 PR/Issue 上创建 comment @对方:",
|
||||
"```bash",
|
||||
f'curl -s -X POST "{_GITEA_BASE}/repos/{{repo}}/issues/{{pr_number}}/comments" \\',
|
||||
' -H "Authorization: token <your-token>" \\',
|
||||
' -H "Content-Type: application/json" \\',
|
||||
' -d \'{"body": "@{agent-id} 需要你的支持:{描述问题}"}\'',
|
||||
"```",
|
||||
"",
|
||||
"⚠️ 不要使用 Mail API(飞鸽传书)。所有协作通过 Gitea 留痕。",
|
||||
"",
|
||||
"### 需要创建 Issue 时",
|
||||
"",
|
||||
"如果步骤中要求创建 Issue 指派他人(如 jiangwei-infra):",
|
||||
"```bash",
|
||||
f'curl -s -X POST "{_GITEA_BASE}/repos/{{repo}}/issues" \\',
|
||||
' -H "Authorization: token <your-token>" \\',
|
||||
' -H "Content-Type: application/json" \\',
|
||||
' -d \'{"title": "[moz] infra: 简述问题", "body": "## 问题描述\\n\\n<简要描述问题现象>\\n\\n## 错误来源\\n\\n- 仓库: <repo>\\n- PR/Commit: <链接>\\n- CI/Deploy run: <Gitea Actions 页面链接>\\n\\n## 日志关键片段\\n\\n```<错误日志摘要>```\\n\\n## 判断依据\\n\\n<为什么判断为基础设施问题>", "assignees": ["jiangwei-infra"], "labels": [<label_id>]}\'',
|
||||
"```",
|
||||
"",
|
||||
"⚠️ Issue body 必须包含错误来源链接(PR/Commit + CI run),让排查者能直接看到全貌。",
|
||||
"⚠️ label 数字 ID 先 GET /repos/{repo}/labels 查询 type/infrastructure 对应的 ID。",
|
||||
"",
|
||||
]
|
||||
return "\n".join(lines)
|
||||
|
||||
@@ -90,20 +187,51 @@ class ToolchainApiSection:
|
||||
|
||||
|
||||
class ToolchainConstraintsSection:
|
||||
"""硬约束(priority=50)"""
|
||||
"""硬约束 + Red Flags(priority=50)"""
|
||||
|
||||
name: str = "toolchain_constraints"
|
||||
priority: int = 50
|
||||
|
||||
def render(self, context: PromptContext) -> str:
|
||||
lines = [
|
||||
"## 硬约束",
|
||||
"## 硬约束(必须遵守)",
|
||||
"",
|
||||
"1. **必须标 done**:处理完成后必须通过 API 将任务状态更新为 `done`,否则视为未完成",
|
||||
"2. **产出不能为空**:必须提交有意义的产出(output 或 comment),不能只改状态",
|
||||
"3. **单一职责**:只处理本次事件相关的操作,不要越界执行无关任务",
|
||||
"4. **出错即报告**:如果无法处理(如权限不足、资源不存在),在 comment 中说明原因并标 done",
|
||||
"5. **不要创建新任务**:工具链事件只处理当前事件,不衍生新任务",
|
||||
"⚠️ 以下是强制要求,不是建议或参考。违反任何一条都会导致任务失败。",
|
||||
"",
|
||||
"### 1. 必须按步骤执行",
|
||||
'- 检查上方“必须执行的步骤”列表',
|
||||
'- 逐条执行每个步骤,不可跳过',
|
||||
'- 不要只读不做——这不是纯通知',
|
||||
"",
|
||||
"### 2. 必须提交 action report",
|
||||
'- 执行完所有步骤后,必须提交 action report',
|
||||
"- 提交方式:POST comment(comment_type='action_report')",
|
||||
'- 报告内容:简要描述你执行了什么操作、结果如何',
|
||||
'- ⚠️ 不提交 action report 的任务会被标记为 failed',
|
||||
"",
|
||||
"### 3. 不要执行任何状态转换命令",
|
||||
'- 不要手动标 working/done/review/failed,系统会自动处理',
|
||||
"",
|
||||
"### 4. 不需要回复",
|
||||
'- action report 就是你的完成凭证',
|
||||
'- 不要发送 Mail(飞鸽传书),你的所有操作在 toolchain 流程内完成',
|
||||
"",
|
||||
"### 5. 所有协作通过 Gitea 完成",
|
||||
'- 如果遇到问题需要其他角色支持,在关联的 PR/Issue 上创建 comment @对方',
|
||||
'- 不要使用 Mail API(飞鸽传书)发送消息',
|
||||
'- 你的所有操作都在 toolchain 流程内,通过 Gitea 留痕',
|
||||
"",
|
||||
"### Red Flags(如果脑海中出现以下想法,说明你错了)",
|
||||
"",
|
||||
'| Agent 想法 | Red Flag 驳回 |',
|
||||
'|------------|--------------|',
|
||||
'| “这个通知看看就行了” | ❌ 错!这是 action 指令,必须执行步骤列表中的每一项 |',
|
||||
'| “我不需要做任何事” | ❌ 错!检查“必须执行的步骤”列表,每一步都要执行 |',
|
||||
'| “先放着等会处理” | ❌ 错!立即执行,不要推迟 |',
|
||||
'| “我已经知道了” | ❌ 知道不等于执行。执行步骤 + 提交 action report 才算完成 |',
|
||||
'| “步骤太多了,选几个做就行” | ❌ 错!必须逐条执行,不可跳过 |',
|
||||
'| “这个步骤不适用于当前情况” | ❌ 如果确实不适用,在 action report 中说明原因,但其他步骤必须执行 |',
|
||||
'| “CI/部署失败不是我代码的问题,我什么也不用做” | ❌ 错!即使是基础设施问题,你也必须创建 Issue 指派 jiangwei-infra(body 含错误来源链接 + 日志 + 判断依据),并在 action report 中说明。不能只报告“不是我的问题”就完事 |',
|
||||
"",
|
||||
]
|
||||
return "\n".join(lines)
|
||||
@@ -127,15 +255,18 @@ class ToolchainHandler(BaseTaskHandler):
|
||||
return "done"
|
||||
|
||||
def pre_spawn(self, task_id: str, db_path: Path) -> bool:
|
||||
"""auto_working:pending → working"""
|
||||
"""auto_working:pending → working"""
|
||||
return self._auto_mark_working(task_id, db_path)
|
||||
|
||||
def get_sections(self) -> list:
|
||||
"""返回 3 个 Toolchain PromptSection 实例"""
|
||||
"""返回 Toolchain PromptSection 实例"""
|
||||
return [
|
||||
ToolchainContextSection(),
|
||||
ToolchainApiSection(),
|
||||
ToolchainConstraintsSection(),
|
||||
GiteaConventionSection(),
|
||||
WikiGuideSection(),
|
||||
DeliveryChecklistSection(),
|
||||
]
|
||||
|
||||
def build_prompt(self, context: PromptContext) -> str:
|
||||
@@ -145,27 +276,55 @@ class ToolchainHandler(BaseTaskHandler):
|
||||
return composer.compose(context)
|
||||
|
||||
def verify_completion(self, task_id: str, db_path: Path) -> VerifyResult:
|
||||
"""检查行动输出(output 或 comment 有实质内容)"""
|
||||
"""检查 action report(精确验证)+ 三层 fallback"""
|
||||
try:
|
||||
conn = get_connection(db_path)
|
||||
try:
|
||||
# 检查 output
|
||||
# 特殊处理:infrastructure_failure 始终通过(防递归)
|
||||
row = conn.execute(
|
||||
"SELECT must_haves FROM tasks WHERE id=?", (task_id,)
|
||||
).fetchone()
|
||||
if row and row["must_haves"]:
|
||||
try:
|
||||
meta = json.loads(row["must_haves"])
|
||||
except Exception:
|
||||
meta = {}
|
||||
if meta.get("action_type") == "infrastructure_failure":
|
||||
return VerifyResult(True, "infrastructure_passthrough",
|
||||
"infrastructure_failure auto-pass")
|
||||
|
||||
# 特殊处理:review_merged 始终通过(纯通知)
|
||||
if meta.get("action_type") == "review_merged":
|
||||
return VerifyResult(True, "merged_passthrough",
|
||||
"review_merged auto-pass")
|
||||
|
||||
# 1. 优先检查 action_report comment
|
||||
report_row = conn.execute(
|
||||
"SELECT id FROM comments WHERE task_id=? "
|
||||
"AND comment_type='action_report' LIMIT 1",
|
||||
(task_id,)
|
||||
).fetchone()
|
||||
if report_row:
|
||||
return VerifyResult(True, "has_action_report", "action_report found")
|
||||
|
||||
# 2. fallback:检查 output(向后兼容)
|
||||
output_count = conn.execute(
|
||||
"SELECT COUNT(*) FROM outputs WHERE task_id=?", (task_id,)
|
||||
).fetchone()[0]
|
||||
if output_count > 0:
|
||||
return VerifyResult(True, "has_output", f"output_count={output_count}")
|
||||
|
||||
# 检查 comment(非系统、有实质内容)
|
||||
# 3. fallback:检查有实质内容的 comment(向后兼容)
|
||||
comment_count = conn.execute(
|
||||
"SELECT COUNT(*) FROM comments WHERE task_id=? "
|
||||
"AND author != 'system' AND LENGTH(content) >= 20",
|
||||
"AND author != 'system' AND LENGTH(body) >= 20",
|
||||
(task_id,)
|
||||
).fetchone()[0]
|
||||
if comment_count > 0:
|
||||
return VerifyResult(True, "has_comment", f"comment_count={comment_count}")
|
||||
|
||||
return VerifyResult(False, "no_action", "output=0, comment=0")
|
||||
return VerifyResult(False, "no_action",
|
||||
"no action_report, no output, no valid comment")
|
||||
finally:
|
||||
conn.close()
|
||||
except Exception as e:
|
||||
@@ -174,32 +333,217 @@ class ToolchainHandler(BaseTaskHandler):
|
||||
|
||||
def on_failure(self, task_id: str, agent_id: str,
|
||||
db_path: Path, verify: VerifyResult) -> None:
|
||||
"""验证失败 → 标 failed + Mail API 通知主公"""
|
||||
"""验证失败 → 三分路处理(业务/系统/基础设施)"""
|
||||
self._mark_task_status(db_path, task_id, "failed")
|
||||
logger.info("Toolchain %s: verify failed (%s), marked failed", task_id, verify.reason)
|
||||
logger.info("Toolchain %s: verify failed (%s), marked failed",
|
||||
task_id, verify.reason)
|
||||
|
||||
# 从 db 读取事件上下文
|
||||
event_type = ""
|
||||
event_data: Dict = {}
|
||||
# 读取 must_hives 获取事件上下文 + assignee 从 tasks 表读取
|
||||
meta = {}
|
||||
assignee = agent_id
|
||||
try:
|
||||
conn = get_connection(db_path)
|
||||
row = conn.execute(
|
||||
"SELECT must_haves FROM tasks WHERE id=?", (task_id,)
|
||||
"SELECT must_haves, assignee FROM tasks WHERE id=?", (task_id,)
|
||||
).fetchone()
|
||||
if row and row["must_haves"]:
|
||||
meta = json.loads(row["must_haves"])
|
||||
event_type = meta.get("event_type", "")
|
||||
raw = meta.get("event_data", "{}")
|
||||
event_data = json.loads(raw) if isinstance(raw, str) else raw
|
||||
if row:
|
||||
if row["must_haves"]:
|
||||
meta = json.loads(row["must_haves"])
|
||||
assignee = row["assignee"] or agent_id
|
||||
conn.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
self._notify_via_mail_api(
|
||||
task_id, verify.reason, verify.evidence,
|
||||
event_type, event_data,
|
||||
action_type = meta.get("action_type", "")
|
||||
context_data = meta.get("context", {})
|
||||
|
||||
# 三分路决策
|
||||
route = self._classify_failure(verify)
|
||||
|
||||
if route == "business":
|
||||
self._handle_business_failure(
|
||||
task_id, agent_id, verify, action_type, context_data, assignee, db_path)
|
||||
elif route == "system":
|
||||
self._handle_system_failure(
|
||||
task_id, agent_id, verify, action_type, context_data, db_path)
|
||||
else: # infrastructure
|
||||
self._handle_infrastructure_failure(
|
||||
task_id, agent_id, verify, db_path)
|
||||
|
||||
def _classify_failure(self, verify: VerifyResult) -> str:
|
||||
"""分类失败类型:business / infrastructure(system 通过升级到达)"""
|
||||
# verify_error 或 DB 不可用 → 基础设施失败
|
||||
if verify.reason == "verify_error":
|
||||
return "infrastructure"
|
||||
# 默认:业务失败
|
||||
return "business"
|
||||
|
||||
def _handle_business_failure(
|
||||
self, task_id: str, agent_id: str, verify: VerifyResult,
|
||||
action_type: str, context_data: dict, assignee: str,
|
||||
db_path: Path,
|
||||
) -> None:
|
||||
"""业务失败 → 在关联 PR/Issue 上创建 comment @原始 assignee"""
|
||||
repo = context_data.get("repo", "")
|
||||
pr_number = context_data.get("pr_number") or context_data.get("issue_number", "")
|
||||
|
||||
if repo and pr_number:
|
||||
comment_body = (
|
||||
f"@{assignee or agent_id} 工具链任务执行失败\n\n"
|
||||
f"任务 ID: {task_id}\n"
|
||||
f"失败原因: {verify.reason}\n"
|
||||
f"证据: {verify.evidence}\n\n"
|
||||
f"请检查黑板任务并处理。"
|
||||
)
|
||||
success = self._create_gitea_comment(repo, pr_number, comment_body)
|
||||
if success:
|
||||
logger.info("Toolchain %s: business failure → Gitea comment on %s#%s",
|
||||
task_id, repo, pr_number)
|
||||
return
|
||||
# Gitea API failed → escalate to system failure
|
||||
logger.warning(
|
||||
"Toolchain %s: Gitea comment failed, escalating to system failure",
|
||||
task_id)
|
||||
self._handle_system_failure(
|
||||
task_id, agent_id, verify, action_type, context_data, db_path)
|
||||
else:
|
||||
# 没有 PR/Issue 关联 → fallback 到系统失败
|
||||
logger.warning(
|
||||
"Toolchain %s: no PR/Issue context for business failure, "
|
||||
"escalating to system failure", task_id)
|
||||
self._handle_system_failure(
|
||||
task_id, agent_id, verify, action_type, context_data, db_path)
|
||||
|
||||
def _handle_system_failure(
|
||||
self, task_id: str, agent_id: str, verify: VerifyResult,
|
||||
action_type: str, context_data: dict, db_path: Path,
|
||||
) -> None:
|
||||
"""系统失败 → 创建 Gitea Issue @pangtong-fujunshi"""
|
||||
repo = context_data.get("repo", "sanguo/sanguo_moziplus_v2")
|
||||
title = f"[toolchain-handler] 工具链事件处理失败: {task_id}"
|
||||
body = (
|
||||
f"任务 {task_id} 验证失败\n\n"
|
||||
f"事件类型: {action_type or '未知'}\n"
|
||||
f"失败原因: {verify.reason}\n"
|
||||
f"证据: {verify.evidence}\n\n"
|
||||
f"@pangtong-fujunshi 请检查黑板任务并手动处理。"
|
||||
)
|
||||
|
||||
# 尝试在 Gitea 创建 Issue
|
||||
created = self._create_gitea_issue(repo, title, body, ["pangtong-fujunshi"])
|
||||
if created:
|
||||
logger.info("Toolchain %s: system failure → Gitea Issue created on %s",
|
||||
task_id, repo)
|
||||
else:
|
||||
# Gitea API 不可用 → 基础设施失败
|
||||
logger.error(
|
||||
"Toolchain %s: Gitea API unavailable, escalating to infrastructure failure",
|
||||
task_id)
|
||||
self._handle_infrastructure_failure(
|
||||
task_id, agent_id, verify, db_path)
|
||||
|
||||
def _handle_infrastructure_failure(
|
||||
self, task_id: str, agent_id: str,
|
||||
verify: VerifyResult, db_path: Path,
|
||||
) -> None:
|
||||
"""基础设施失败 → 直接在 _toolchain DB 创建 task @jiangwei-infra(防递归)"""
|
||||
try:
|
||||
from datetime import datetime
|
||||
new_task_id = f"tc-{int(datetime.now().timestamp() * 1000)}"
|
||||
must_hives = json.dumps({
|
||||
"event_type": "infrastructure_failure",
|
||||
"action_type": "infrastructure_failure",
|
||||
"steps": [
|
||||
"检查 Gitea 服务状态(http://192.168.2.154:3000)",
|
||||
"检查网络连通性",
|
||||
"恢复后提交 action report",
|
||||
],
|
||||
"context": {"original_task_id": task_id, "verify_reason": verify.reason},
|
||||
"from": "system",
|
||||
"source": "toolchain_handler_on_failure",
|
||||
}, ensure_ascii=False)
|
||||
conn = get_connection(db_path)
|
||||
conn.execute(
|
||||
"INSERT INTO tasks (id, title, description, assignee, assigned_by, "
|
||||
"must_haves, task_type, status) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
new_task_id,
|
||||
f"[基础设施] Gitea API 不可用 - {task_id}",
|
||||
f"Gitea API 不可用,原任务 {task_id} 无法通过正常路径处理。\n"
|
||||
f"请检查 Gitea 服务状态和网络连通性。",
|
||||
"jiangwei-infra",
|
||||
"system",
|
||||
must_hives,
|
||||
"toolchain",
|
||||
"pending",
|
||||
)
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
logger.info(
|
||||
"Toolchain %s: infrastructure failure → task %s created for jiangwei-infra",
|
||||
task_id, new_task_id)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
"Toolchain %s: failed to create infrastructure_failure task: %s",
|
||||
task_id, e)
|
||||
|
||||
# -----------------------------------------------------------------------
|
||||
# Gitea API 辅助
|
||||
# -----------------------------------------------------------------------
|
||||
|
||||
def _create_gitea_comment(
|
||||
self, repo: str, pr_number: int, body: str,
|
||||
) -> bool:
|
||||
"""在 PR/Issue 上创建 comment。返回是否成功。"""
|
||||
if not _GITEA_TOKEN:
|
||||
return False
|
||||
payload = json.dumps({"body": body}, ensure_ascii=False).encode("utf-8")
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
f"{_GITEA_BASE}/repos/{repo}/issues/{pr_number}/comments",
|
||||
data=payload,
|
||||
headers={
|
||||
"Authorization": f"token {_GITEA_TOKEN}",
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
)
|
||||
urllib.request.urlopen(req, timeout=5)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.warning("Gitea comment failed on %s#%s: %s", repo, pr_number, e)
|
||||
return False
|
||||
|
||||
def _create_gitea_issue(
|
||||
self, repo: str, title: str, body: str,
|
||||
assignees: list = None,
|
||||
) -> bool:
|
||||
"""创建 Gitea Issue。返回是否成功。"""
|
||||
if not _GITEA_TOKEN:
|
||||
return False
|
||||
data = {"title": title, "body": body}
|
||||
if assignees:
|
||||
data["assignees"] = assignees
|
||||
payload = json.dumps(data, ensure_ascii=False).encode("utf-8")
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
f"{_GITEA_BASE}/repos/{repo}/issues",
|
||||
data=payload,
|
||||
headers={
|
||||
"Authorization": f"token {_GITEA_TOKEN}",
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
)
|
||||
urllib.request.urlopen(req, timeout=5)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.warning("Gitea create issue failed on %s: %s", repo, e)
|
||||
return False
|
||||
|
||||
# -----------------------------------------------------------------------
|
||||
# 兼容:保留旧方法签名(但不再被 on_failure 调用)
|
||||
# -----------------------------------------------------------------------
|
||||
|
||||
def _build_gitea_links(self, event_type: str, event_data: dict) -> str:
|
||||
"""根据事件类型构建 Gitea 链接。"""
|
||||
links = []
|
||||
@@ -215,63 +559,4 @@ class ToolchainHandler(BaseTaskHandler):
|
||||
if "branch" in event_data and "commit" not in event_data:
|
||||
links.append(f"分支: {event_data['branch']}")
|
||||
|
||||
return "\n".join(links) if links else "(无法提取链接,请检查黑板任务详情)"
|
||||
|
||||
def _notify_via_mail_api(
|
||||
self,
|
||||
task_id: str,
|
||||
reason: str,
|
||||
evidence: str,
|
||||
event_type: str,
|
||||
event_data: Dict,
|
||||
) -> None:
|
||||
"""通过 Mail API 发送丰富的失败通知给主公。"""
|
||||
# 构建行动指引
|
||||
action_hint = "请检查黑板任务并手动处理。"
|
||||
et_lower = event_type.lower()
|
||||
if "ci" in et_lower or "deploy" in et_lower:
|
||||
action_hint = "建议创建任务派给 jiangwei-infra 检查 CI/部署问题。"
|
||||
elif "review" in et_lower:
|
||||
action_hint = "建议查看 PR review 状态,必要时通知相关开发者。"
|
||||
elif "issue" in et_lower:
|
||||
action_hint = "建议创建任务派给对应开发者处理 Issue。"
|
||||
|
||||
# 构建事件详情
|
||||
event_details = ""
|
||||
if event_data:
|
||||
event_details = "\n".join(
|
||||
f" - {k}: {v}" for k, v in event_data.items()
|
||||
)
|
||||
|
||||
# 构建 Gitea 链接
|
||||
gitea_links = self._build_gitea_links(event_type, event_data)
|
||||
|
||||
title = f"[toolchain-handler] 工具链事件处理失败: {task_id}"
|
||||
text = (
|
||||
f"任务 {task_id} 验证失败\n\n"
|
||||
f"事件类型: {event_type or '未知'}\n"
|
||||
f"事件详情:\n{event_details or ' (无)'}\n\n"
|
||||
f"失败原因: {reason}\n"
|
||||
f"证据: {evidence}\n\n"
|
||||
f"{gitea_links}\n\n"
|
||||
f"行动指引: {action_hint}"
|
||||
)
|
||||
|
||||
payload = json.dumps({
|
||||
"from": "daemon",
|
||||
"to": "pangtong-fujunshi",
|
||||
"title": title,
|
||||
"text": text,
|
||||
"type": "inform",
|
||||
}, ensure_ascii=False).encode("utf-8")
|
||||
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
"http://localhost:8083/api/mail",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
urllib.request.urlopen(req, timeout=5)
|
||||
logger.info("Toolchain %s: sent failure notification via Mail API", task_id)
|
||||
except Exception as e:
|
||||
logger.warning("Toolchain %s: failed to notify via Mail API: %s", task_id, e)
|
||||
return "\n".join(links) if links else "(无法提取链接,请检查黑板任务详情)"
|
||||
|
||||
@@ -5,6 +5,7 @@
|
||||
|
||||
import { useState, useCallback } from 'react';
|
||||
import { api, AgentsStatusData } from '../api';
|
||||
import ToolchainPanel from './ToolchainPanel';
|
||||
|
||||
interface ServiceCheckResult {
|
||||
name: string;
|
||||
@@ -15,7 +16,7 @@ interface ServiceCheckResult {
|
||||
}
|
||||
|
||||
export default function SettingsPanel() {
|
||||
const [tab, setTab] = useState<'connections' | 'security' | 'version' | 'logs'>('connections');
|
||||
const [tab, setTab] = useState<'connections' | 'security' | 'version' | 'logs' | 'toolchain'>('connections');
|
||||
|
||||
// 接线状态巡检
|
||||
const [checking, setChecking] = useState(false);
|
||||
@@ -95,6 +96,7 @@ export default function SettingsPanel() {
|
||||
{ key: 'security' as const, label: '🛡️ 安全防务' },
|
||||
{ key: 'version' as const, label: '📦 版本更新' },
|
||||
{ key: 'logs' as const, label: '📋 城防日志' },
|
||||
{ key: 'toolchain' as const, label: '⛓️ 工具链' },
|
||||
].map((t) => (
|
||||
<button key={t.key} className={`btn ${tab === t.key ? 'btn-primary' : ''}`} onClick={() => setTab(t.key)}>
|
||||
{t.label}
|
||||
@@ -288,6 +290,9 @@ export default function SettingsPanel() {
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* ========== 工具链 ========== */}
|
||||
{tab === 'toolchain' && <ToolchainPanel />}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,250 @@
|
||||
/**
|
||||
* ToolchainPanel — 工具链事件(系统级)
|
||||
* 展示 _toolchain 项目的 tasks:CI/PR/部署/Review 通知
|
||||
*/
|
||||
import { useEffect, useState } from 'react';
|
||||
|
||||
const AGENT_NAMES: Record<string, string> = {
|
||||
'pangtong-fujunshi': '庞统',
|
||||
'simayi-challenger': '司马懿',
|
||||
'zhangfei-dev': '张飞',
|
||||
'guanyu-dev': '关羽',
|
||||
'zhaoyun-data': '赵云',
|
||||
'jiangwei-infra': '姜维',
|
||||
'system': '系统',
|
||||
};
|
||||
|
||||
const EVENT_LABELS: Record<string, string> = {
|
||||
'review_request': 'Review 请求',
|
||||
'review_result': 'Review 结果',
|
||||
'review_merged': 'PR 合并',
|
||||
'review_comment': 'Review 评论',
|
||||
'review_updated': 'Review 更新',
|
||||
'ci_failure': 'CI 失败',
|
||||
'deploy_failure': '部署失败',
|
||||
'issue_assigned': 'Issue 指派',
|
||||
'mention': '@提及',
|
||||
};
|
||||
|
||||
const STATUS_COLORS: Record<string, string> = {
|
||||
pending: '#f59e0b22', claimed: '#6a9eff22', working: '#6a9eff22',
|
||||
review: '#818cf822', done: '#2ecc8a22', failed: '#ef444422',
|
||||
cancelled: '#6b728022', blocked: '#ef444422',
|
||||
};
|
||||
|
||||
const STATUS_LABELS: Record<string, string> = {
|
||||
pending: '待处理', claimed: '已认领', working: '处理中',
|
||||
review: '审查中', done: '已完成', failed: '失败',
|
||||
cancelled: '已取消', blocked: '已拦截',
|
||||
};
|
||||
|
||||
function fmtTime(iso: string): string {
|
||||
try {
|
||||
const d = new Date(iso.includes('T') ? iso : iso.replace(' ', 'T') + 'Z');
|
||||
const now = Date.now();
|
||||
const diff = now - d.getTime();
|
||||
const mins = Math.floor(diff / 60000);
|
||||
if (mins < 1) return '刚刚';
|
||||
if (mins < 60) return `${mins}分钟前`;
|
||||
const hrs = Math.floor(mins / 60);
|
||||
if (hrs < 24) return `${hrs}小时前`;
|
||||
return `${d.getMonth() + 1}/${d.getDate()} ${d.getHours()}:${String(d.getMinutes()).padStart(2, '0')}`;
|
||||
} catch { return iso; }
|
||||
}
|
||||
|
||||
export default function ToolchainPanel() {
|
||||
const [tasks, setTasks] = useState<any[]>([]);
|
||||
const [selectedId, setSelectedId] = useState<string | null>(null);
|
||||
const [detail, setDetail] = useState<any>(null);
|
||||
const [searchQuery, setSearchQuery] = useState('');
|
||||
const [loading, setLoading] = useState(false);
|
||||
const [filterMode, setFilterMode] = useState<'all' | 'pending'>('all');
|
||||
|
||||
const loadTasks = async (q?: string) => {
|
||||
setLoading(true);
|
||||
try {
|
||||
const url = q
|
||||
? `/api/projects/_toolchain/tasks?q=${encodeURIComponent(q)}`
|
||||
: `/api/projects/_toolchain/tasks`;
|
||||
const res = await fetch(url);
|
||||
if (res.ok) {
|
||||
const data = await res.json();
|
||||
setTasks(data.tasks || []);
|
||||
}
|
||||
} catch { /* */ }
|
||||
setLoading(false);
|
||||
};
|
||||
|
||||
const displayed = filterMode === 'pending'
|
||||
? tasks.filter(t => !['done', 'failed', 'cancelled'].includes(t.status))
|
||||
: tasks;
|
||||
|
||||
useEffect(() => { loadTasks(); }, []);
|
||||
|
||||
// 搜索防抖 300ms
|
||||
useEffect(() => {
|
||||
const timer = setTimeout(() => {
|
||||
if (searchQuery !== undefined) loadTasks(searchQuery || undefined);
|
||||
}, 300);
|
||||
return () => clearTimeout(timer);
|
||||
}, [searchQuery]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!selectedId) { setDetail(null); return; }
|
||||
(async () => {
|
||||
try {
|
||||
const res = await fetch(
|
||||
`/api/projects/_toolchain/tasks/${selectedId}?expand=comments`
|
||||
);
|
||||
if (res.ok) setDetail(await res.json());
|
||||
} catch { /* */ }
|
||||
})();
|
||||
}, [selectedId]);
|
||||
|
||||
// 渲染评论列表(兼容 expand 和裸 list 格式)
|
||||
const renderComments = (comments: any[]) => {
|
||||
if (!comments || comments.length === 0) return null;
|
||||
return (
|
||||
<div style={{ marginTop: 16 }}>
|
||||
<div style={{ fontSize: 11, color: 'var(--muted)', marginBottom: 8, fontWeight: 600 }}>
|
||||
📋 处理记录 ({comments.length})
|
||||
</div>
|
||||
{comments.map((c: any, i: number) => (
|
||||
<div key={c.id || i} style={{
|
||||
padding: '8px 12px', background: 'var(--panel2)', borderRadius: 6, marginBottom: 6,
|
||||
}}>
|
||||
<div style={{ display: 'flex', justifyContent: 'space-between', marginBottom: 4 }}>
|
||||
<span style={{ fontSize: 10, color: 'var(--acc)', fontWeight: 600 }}>
|
||||
{c.author || 'system'}
|
||||
</span>
|
||||
<span style={{ fontSize: 9, color: 'var(--muted)' }}>{fmtTime(c.created_at)}</span>
|
||||
</div>
|
||||
<div style={{ fontSize: 12, color: '#a0aec0', lineHeight: 1.5 }}>{c.body}</div>
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
return (
|
||||
<div style={{ display: 'flex', gap: 0, height: '100%', minHeight: 500 }}>
|
||||
{/* 左侧列表 */}
|
||||
<div style={{ width: 380, borderRight: '1px solid var(--line)', display: 'flex', flexDirection: 'column', flexShrink: 0 }}>
|
||||
{/* 搜索栏 + 刷新 */}
|
||||
<div style={{ padding: '10px 14px', borderBottom: '1px solid var(--line)', display: 'flex', gap: 6, alignItems: 'center' }}>
|
||||
<input
|
||||
type="text"
|
||||
placeholder="搜索工具链事件..."
|
||||
value={searchQuery}
|
||||
onChange={e => setSearchQuery(e.target.value)}
|
||||
style={{
|
||||
flex: 1, padding: '4px 8px', borderRadius: 4, fontSize: 11,
|
||||
border: '1px solid #2a3550', background: '#161b2e', color: '#dde4f8',
|
||||
outline: 'none',
|
||||
}}
|
||||
/>
|
||||
<button onClick={() => loadTasks(searchQuery || undefined)} style={{
|
||||
padding: '3px 8px', borderRadius: 4, fontSize: 10,
|
||||
border: '1px solid #2a3550', background: '#161b2e', color: '#8899aa', cursor: 'pointer',
|
||||
}}>🔄</button>
|
||||
<button onClick={() => setFilterMode('all')} style={{
|
||||
padding: '3px 8px', borderRadius: 4, fontSize: 10,
|
||||
border: `1px solid ${filterMode === 'all' ? 'var(--acc)' : '#2a3550'}`,
|
||||
background: filterMode === 'all' ? 'var(--acc)22' : '#161b2e',
|
||||
color: filterMode === 'all' ? 'var(--acc)' : '#8899aa', cursor: 'pointer',
|
||||
}}>全部</button>
|
||||
<button onClick={() => setFilterMode('pending')} style={{
|
||||
padding: '3px 8px', borderRadius: 4, fontSize: 10,
|
||||
border: `1px solid ${filterMode === 'pending' ? 'var(--acc)' : '#2a3550'}`,
|
||||
background: filterMode === 'pending' ? 'var(--acc)22' : '#161b2e',
|
||||
color: filterMode === 'pending' ? 'var(--acc)' : '#8899aa', cursor: 'pointer',
|
||||
}}>未处理</button>
|
||||
<span style={{ fontSize: 10, color: 'var(--muted)' }}>{filterMode === 'pending' ? displayed.length : tasks.length} 条</span>
|
||||
</div>
|
||||
|
||||
{/* 事件列表 */}
|
||||
<div style={{ flex: 1, overflowY: 'auto' }}>
|
||||
{tasks.length === 0 && (
|
||||
<div style={{ textAlign: 'center', padding: 40, color: 'var(--muted)', fontSize: 12 }}>
|
||||
{loading ? '加载中...' : '暂无工具链事件'}
|
||||
</div>
|
||||
)}
|
||||
{displayed.map((t: any) => (
|
||||
<div key={t.id} onClick={() => setSelectedId(t.id)} style={{
|
||||
padding: '10px 14px', borderBottom: '1px solid var(--line)',
|
||||
cursor: 'pointer', transition: 'background .15s',
|
||||
background: selectedId === t.id ? 'var(--panel2)' : 'transparent',
|
||||
}}
|
||||
onMouseEnter={e => e.currentTarget.style.background = 'var(--panel2)'}
|
||||
onMouseLeave={e => e.currentTarget.style.background = selectedId === t.id ? 'var(--panel2)' : 'transparent'}
|
||||
>
|
||||
<div style={{ display: 'flex', justifyContent: 'space-between', alignItems: 'center', marginBottom: 4 }}>
|
||||
<span style={{
|
||||
fontSize: 9, padding: '1px 5px', borderRadius: 3,
|
||||
background: STATUS_COLORS[t.status] || '#2a3550',
|
||||
color: '#dde4f8',
|
||||
}}>{STATUS_LABELS[t.status] || t.status}</span>
|
||||
<span style={{ fontSize: 9, color: 'var(--muted)' }}>{fmtTime(t.created_at)}</span>
|
||||
</div>
|
||||
<div style={{
|
||||
fontSize: 12, fontWeight: 500, color: '#dde4f8',
|
||||
overflow: 'hidden', textOverflow: 'ellipsis', whiteSpace: 'nowrap',
|
||||
}}>{t.title}</div>
|
||||
<div style={{ fontSize: 10, color: 'var(--muted)', marginTop: 2 }}>
|
||||
{AGENT_NAMES['system'] || '系统'} → {AGENT_NAMES[t.assignee] || t.assignee || '?'}
|
||||
</div>
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* 右侧详情 */}
|
||||
<div style={{ flex: 1, padding: '16px 20px', overflowY: 'auto' }}>
|
||||
{!detail ? (
|
||||
<div style={{ textAlign: 'center', padding: 60, color: 'var(--muted)' }}>
|
||||
<div style={{ fontSize: 36, marginBottom: 12 }}>⛓️</div>
|
||||
<div style={{ fontSize: 13 }}>选择一条事件查看详情</div>
|
||||
</div>
|
||||
) : (
|
||||
<>
|
||||
{/* 头部 */}
|
||||
<div style={{ marginBottom: 16 }}>
|
||||
<div style={{ display: 'flex', alignItems: 'center', gap: 8, marginBottom: 6 }}>
|
||||
<span style={{ fontSize: 10, padding: '2px 6px', borderRadius: 4, background: STATUS_COLORS[detail.status] || '#2a3550', color: '#dde4f8' }}>
|
||||
{STATUS_LABELS[detail.status] || detail.status}
|
||||
</span>
|
||||
<span style={{ fontSize: 10, color: 'var(--muted)' }}>{detail.id}</span>
|
||||
</div>
|
||||
<div style={{ fontSize: 18, fontWeight: 700, lineHeight: 1.3 }}>{detail.title}</div>
|
||||
<div style={{ fontSize: 11, color: 'var(--muted)', marginTop: 4 }}>
|
||||
{AGENT_NAMES['system'] || '系统'} → {AGENT_NAMES[detail.assignee] || detail.assignee || '?'}
|
||||
</div>
|
||||
<div style={{ fontSize: 12, color: 'var(--muted)', marginTop: 6 }}>
|
||||
{fmtTime(detail.created_at)}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* 正文 */}
|
||||
{detail.description && (
|
||||
<div style={{
|
||||
padding: '14px 16px', background: 'var(--panel2)', borderRadius: 10,
|
||||
fontSize: 13, color: '#a0aec0', lineHeight: 1.7, whiteSpace: 'pre-wrap',
|
||||
}}>
|
||||
{detail.description}
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* action_report 评论 — expand 格式 {items, total_count} */}
|
||||
{detail.comments && detail.comments.items && detail.comments.items.length > 0 &&
|
||||
renderComments(detail.comments.items)
|
||||
}
|
||||
{/* 兼容裸 list 格式 */}
|
||||
{detail.comments && Array.isArray(detail.comments) && detail.comments.length > 0 &&
|
||||
renderComments(detail.comments)
|
||||
}
|
||||
</>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
+4
-2
@@ -7,7 +7,8 @@ from src.api.sse_routes import router as sse_router
|
||||
from src.api.project_routes import router as project_router
|
||||
from src.api.daemon_routes import router as daemon_router
|
||||
from src.api.checkpoint_routes import router as checkpoint_router
|
||||
from src.api.blackboard_routes import router as blackboard_router
|
||||
from src.api.task_routes import router as task_router
|
||||
from src.api.task_relation_routes import router as task_relation_router
|
||||
|
||||
import logging
|
||||
from contextlib import asynccontextmanager
|
||||
@@ -273,7 +274,8 @@ app.add_middleware(
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
app.include_router(blackboard_router)
|
||||
app.include_router(task_router)
|
||||
app.include_router(task_relation_router)
|
||||
app.include_router(checkpoint_router)
|
||||
app.include_router(daemon_router)
|
||||
app.include_router(project_router)
|
||||
|
||||
@@ -543,3 +543,94 @@ class TestCheckTimeoutsUnified:
|
||||
reclaimed = ticker._check_timeouts(db_path)
|
||||
|
||||
assert "t-review-dead" not in reclaimed
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# E13: §15 Runaway Guard — per-task dispatch_count 上限
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestRunawayGuard:
|
||||
"""E13: dispatch_count >= 10 → 自动标 failed(覆盖所有非终态)"""
|
||||
|
||||
@pytest.fixture
|
||||
def guard_project(self, tmp_path):
|
||||
"""创建项目 + 任务"""
|
||||
data_root = tmp_path / "projects"
|
||||
registry = ProjectRegistry(data_root)
|
||||
registry.create_project("guard-proj", "Guard Test", agents=["agent-a"])
|
||||
db_path = data_root / "guard-proj" / "blackboard.db"
|
||||
bb = Blackboard(db_path)
|
||||
return registry, db_path, bb
|
||||
|
||||
def test_runaway_guard_triggers_working(self, guard_project):
|
||||
"""E13.1: working 状态 dispatch_count >= 10 → 标 failed"""
|
||||
registry, db_path, bb = guard_project
|
||||
|
||||
bb.create_task(Task(
|
||||
id="t-runaway", title="Runaway Task", status="working",
|
||||
assigned_by="daemon", current_agent="agent-a",
|
||||
))
|
||||
|
||||
conn = bb._conn()
|
||||
try:
|
||||
conn.execute(
|
||||
"UPDATE tasks SET dispatch_count = 10 WHERE id = ?", ("t-runaway",))
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
ticker = Ticker(registry, tick_interval=30)
|
||||
reclaimed = ticker._check_timeouts(db_path)
|
||||
|
||||
assert "t-runaway" in reclaimed
|
||||
task = Queries(db_path).task_by_id("t-runaway")
|
||||
assert task.status == "failed"
|
||||
|
||||
def test_runaway_guard_triggers_pending(self, guard_project):
|
||||
"""E13.2: pending 状态 dispatch_count >= 10 → 标 failed"""
|
||||
registry, db_path, bb = guard_project
|
||||
|
||||
bb.create_task(Task(
|
||||
id="t-pending-runaway", title="Pending Runaway", status="pending",
|
||||
assigned_by="daemon",
|
||||
))
|
||||
|
||||
conn = bb._conn()
|
||||
try:
|
||||
conn.execute(
|
||||
"UPDATE tasks SET dispatch_count = 10 WHERE id = ?",
|
||||
("t-pending-runaway",))
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
ticker = Ticker(registry, tick_interval=30)
|
||||
reclaimed = ticker._check_timeouts(db_path)
|
||||
|
||||
assert "t-pending-runaway" in reclaimed
|
||||
task = Queries(db_path).task_by_id("t-pending-runaway")
|
||||
assert task.status == "failed"
|
||||
|
||||
def test_runaway_guard_not_triggered(self, guard_project):
|
||||
"""E13.3: dispatch_count < 10 → 正常流程不受影响"""
|
||||
registry, db_path, bb = guard_project
|
||||
|
||||
bb.create_task(Task(
|
||||
id="t-normal", title="Normal Task", status="working",
|
||||
assigned_by="daemon", current_agent="agent-a",
|
||||
))
|
||||
|
||||
conn = bb._conn()
|
||||
try:
|
||||
conn.execute(
|
||||
"UPDATE tasks SET dispatch_count = 5 WHERE id = ?", ("t-normal",))
|
||||
conn.commit()
|
||||
finally:
|
||||
conn.close()
|
||||
|
||||
ticker = Ticker(registry, tick_interval=30)
|
||||
reclaimed = ticker._check_timeouts(db_path)
|
||||
|
||||
assert "t-normal" not in reclaimed
|
||||
task = Queries(db_path).task_by_id("t-normal")
|
||||
assert task.status == "working"
|
||||
|
||||
Executable
+70
@@ -0,0 +1,70 @@
|
||||
#!/bin/bash
|
||||
# verify_api_compat.sh — 验证 API 拆分前后路由清单完全一致
|
||||
#
|
||||
# 用法:
|
||||
# bash tests/scripts/verify_api_compat.sh
|
||||
#
|
||||
# 前置:
|
||||
# - 当前在开发目录(sanguo_moziplus_v2/)
|
||||
# - git working tree 有拆分改动
|
||||
# - main 分支是拆分前的基准
|
||||
#
|
||||
# 输出:
|
||||
# ✅ 路由完全一致(exit 0)
|
||||
# ❌ 路由有差异(exit 1,打印 diff)
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
BEFORE_FILE="/tmp/routes_before_$$.txt"
|
||||
AFTER_FILE="/tmp/routes_after_$$.txt"
|
||||
|
||||
echo "=== 提取拆分前路由清单(main 分支)==="
|
||||
|
||||
# stash 当前改动(如果有 untracked 新文件,--include-untracked)
|
||||
STASHED=0
|
||||
if ! git diff --quiet || ! git diff --cached --quiet; then
|
||||
git stash --include-untracked
|
||||
STASHED=1
|
||||
fi
|
||||
|
||||
python3 -c "
|
||||
from src.main import app
|
||||
for route in app.routes:
|
||||
if hasattr(route, 'methods') and hasattr(route, 'path'):
|
||||
for m in sorted(route.methods):
|
||||
if m in ('GET','POST','PATCH','DELETE','PUT'):
|
||||
print(f'{m} {route.path}')
|
||||
" | sort > "$BEFORE_FILE"
|
||||
|
||||
echo "Routes before: $(wc -l < "$BEFORE_FILE")"
|
||||
|
||||
# 恢复改动
|
||||
if [ "$STASHED" = "1" ]; then
|
||||
git stash pop
|
||||
fi
|
||||
|
||||
echo "=== 提取拆分后路由清单(当前 working tree)==="
|
||||
|
||||
python3 -c "
|
||||
from src.main import app
|
||||
for route in app.routes:
|
||||
if hasattr(route, 'methods') and hasattr(route, 'path'):
|
||||
for m in sorted(route.methods):
|
||||
if m in ('GET','POST','PATCH','DELETE','PUT'):
|
||||
print(f'{m} {route.path}')
|
||||
" | sort > "$AFTER_FILE"
|
||||
|
||||
echo "Routes after: $(wc -l < "$AFTER_FILE")"
|
||||
|
||||
echo ""
|
||||
echo "=== Diff ==="
|
||||
|
||||
if diff "$BEFORE_FILE" "$AFTER_FILE"; then
|
||||
echo "✅ 路由完全一致"
|
||||
rm -f "$BEFORE_FILE" "$AFTER_FILE"
|
||||
exit 0
|
||||
else
|
||||
echo "❌ 路由有差异"
|
||||
rm -f "$BEFORE_FILE" "$AFTER_FILE"
|
||||
exit 1
|
||||
fi
|
||||
@@ -0,0 +1,595 @@
|
||||
"""Unit tests for §17 ToolchainHandler 强约束实现."""
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
# Add project root to path
|
||||
PROJECT_ROOT = Path(__file__).parent.parent.parent
|
||||
sys.path.insert(0, str(PROJECT_ROOT))
|
||||
|
||||
from src.daemon.prompt_composer import PromptContext, PromptComposer
|
||||
from src.daemon.toolchain_handler import (
|
||||
ToolchainHandler,
|
||||
ToolchainContextSection,
|
||||
ToolchainApiSection,
|
||||
ToolchainConstraintsSection,
|
||||
_ACTION_HINTS,
|
||||
)
|
||||
from src.daemon.base_task_handler import VerifyResult
|
||||
from src.blackboard.db import init_db, get_connection
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Fixtures
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@pytest.fixture
|
||||
def tmp_db():
|
||||
"""Create a temporary _toolchain DB for testing."""
|
||||
with tempfile.TemporaryDirectory() as d:
|
||||
db_path = Path(d) / "blackboard.db"
|
||||
init_db(db_path)
|
||||
yield db_path
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def handler():
|
||||
return ToolchainHandler()
|
||||
|
||||
|
||||
def _insert_task(db_path, task_id, must_haves_json, status="working"):
|
||||
"""Insert a task into DB for testing."""
|
||||
conn = get_connection(db_path)
|
||||
conn.execute(
|
||||
"INSERT INTO tasks (id, title, description, assignee, assigned_by, "
|
||||
"must_haves, task_type, status) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
|
||||
(task_id, "test", "test desc", "zhangfei-dev", "system",
|
||||
must_haves_json, "toolchain", status)
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
|
||||
def _insert_comment(db_path, task_id, author, body, comment_type="general"):
|
||||
"""Insert a comment into DB."""
|
||||
conn = get_connection(db_path)
|
||||
conn.execute(
|
||||
"INSERT INTO comments (task_id, author, comment_type, body) VALUES (?, ?, ?, ?)",
|
||||
(task_id, author, comment_type, body)
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
|
||||
def _insert_output(db_path, task_id, content="test output"):
|
||||
"""Insert an output into DB."""
|
||||
conn = get_connection(db_path)
|
||||
conn.execute(
|
||||
"INSERT INTO outputs (task_id, agent, output_type, title, summary) "
|
||||
"VALUES (?, ?, ?, ?, ?)",
|
||||
(task_id, "zhangfei-dev", "document", "test", content)
|
||||
)
|
||||
conn.commit()
|
||||
conn.close()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 1a: PromptContext new fields
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestPromptContextFields:
|
||||
def test_action_type_default(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
)
|
||||
assert ctx.action_type == ""
|
||||
|
||||
def test_action_steps_default(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
)
|
||||
assert ctx.action_steps == []
|
||||
|
||||
def test_action_type_set(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
action_type="review_result",
|
||||
)
|
||||
assert ctx.action_type == "review_result"
|
||||
|
||||
def test_action_steps_set(self):
|
||||
steps = ["step 1", "step 2"]
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
action_steps=steps,
|
||||
)
|
||||
assert ctx.action_steps == steps
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 2a: ToolchainContextSection steps rendering + action_hint
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestToolchainContextSection:
|
||||
def test_renders_steps(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
event_type="review_result",
|
||||
event_data={"pr_number": "42", "repo": "sanguo/test"},
|
||||
action_type="review_result",
|
||||
action_steps=["合并 PR", "提交 action report"],
|
||||
)
|
||||
section = ToolchainContextSection()
|
||||
result = section.render(ctx)
|
||||
assert "必须执行的步骤" in result
|
||||
assert "1. 合并 PR" in result
|
||||
assert "2. 提交 action report" in result
|
||||
|
||||
def test_renders_action_hint(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
event_type="ci_failure",
|
||||
action_type="ci_failure",
|
||||
action_steps=[],
|
||||
)
|
||||
section = ToolchainContextSection()
|
||||
result = section.render(ctx)
|
||||
assert "CI 失败" in result
|
||||
assert "需要你修复" in result
|
||||
|
||||
def test_renders_default_hint_for_unknown_action_type(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
event_type="unknown",
|
||||
action_type="unknown_type",
|
||||
action_steps=[],
|
||||
)
|
||||
section = ToolchainContextSection()
|
||||
result = section.render(ctx)
|
||||
assert "需要你执行动作的事件" in result
|
||||
|
||||
def test_no_steps_no_steps_section(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
event_type="review_merged",
|
||||
action_type="review_merged",
|
||||
action_steps=[],
|
||||
)
|
||||
section = ToolchainContextSection()
|
||||
result = section.render(ctx)
|
||||
assert "必须执行的步骤" not in result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 2b: ToolchainApiSection action_report guidance
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestToolchainApiSection:
|
||||
def test_has_action_report_instruction(self):
|
||||
ctx = PromptContext(
|
||||
task_id="tc-123", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="zhangfei-dev",
|
||||
)
|
||||
section = ToolchainApiSection()
|
||||
result = section.render(ctx)
|
||||
assert "action_report" in result
|
||||
assert "comment_type" in result
|
||||
assert "tc-123" in result
|
||||
|
||||
def test_no_manual_done_instruction(self):
|
||||
ctx = PromptContext(
|
||||
task_id="tc-123", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="zhangfei-dev",
|
||||
)
|
||||
section = ToolchainApiSection()
|
||||
result = section.render(ctx)
|
||||
# Should NOT contain the old "标记为 done" instruction
|
||||
assert "标记为 **done**" not in result
|
||||
assert '"status": "done"' not in result
|
||||
|
||||
def test_has_outputs_instruction(self):
|
||||
ctx = PromptContext(
|
||||
task_id="tc-123", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="zhangfei-dev",
|
||||
)
|
||||
section = ToolchainApiSection()
|
||||
result = section.render(ctx)
|
||||
assert "outputs" in result
|
||||
|
||||
def test_has_gitea_collaboration_instruction(self):
|
||||
ctx = PromptContext(
|
||||
task_id="tc-123", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="zhangfei-dev",
|
||||
)
|
||||
section = ToolchainApiSection()
|
||||
result = section.render(ctx)
|
||||
assert "Gitea" in result
|
||||
assert "Mail API" in result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 2c: ToolchainConstraintsSection Red Flags
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestToolchainConstraintsSection:
|
||||
def test_has_red_flags_table(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
)
|
||||
section = ToolchainConstraintsSection()
|
||||
result = section.render(ctx)
|
||||
assert "Red Flags" in result
|
||||
assert "❌" in result
|
||||
|
||||
def test_has_all_5_constraints(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
)
|
||||
section = ToolchainConstraintsSection()
|
||||
result = section.render(ctx)
|
||||
assert "必须按步骤执行" in result
|
||||
assert "必须提交 action report" in result
|
||||
assert "不要执行任何状态转换命令" in result
|
||||
assert "不需要回复" in result
|
||||
assert "所有协作通过 Gitea 完成" in result
|
||||
|
||||
def test_has_strong_language(self):
|
||||
ctx = PromptContext(
|
||||
task_id="t1", title="test", description="d",
|
||||
must_haves="", project_id="_toolchain", agent_id="a1",
|
||||
)
|
||||
section = ToolchainConstraintsSection()
|
||||
result = section.render(ctx)
|
||||
assert "强制要求" in result
|
||||
assert "不是建议" in result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 2d: verify_completion tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestVerifyCompletion:
|
||||
def test_action_report_passes(self, handler, tmp_db):
|
||||
"""action_report comment → pass"""
|
||||
must_haves = json.dumps({"action_type": "review_result"})
|
||||
_insert_task(tmp_db, "t1", must_haves)
|
||||
_insert_comment(tmp_db, "t1", "zhangfei-dev",
|
||||
"已修复 CI", comment_type="action_report")
|
||||
|
||||
result = handler.verify_completion("t1", tmp_db)
|
||||
assert result.passed is True
|
||||
assert result.reason == "has_action_report"
|
||||
|
||||
def test_no_action_report_fallback_output(self, handler, tmp_db):
|
||||
"""No action_report but has output → pass (fallback)"""
|
||||
must_haves = json.dumps({"action_type": "review_result"})
|
||||
_insert_task(tmp_db, "t2", must_haves)
|
||||
_insert_output(tmp_db, "t2", "review result content")
|
||||
|
||||
result = handler.verify_completion("t2", tmp_db)
|
||||
assert result.passed is True
|
||||
assert result.reason == "has_output"
|
||||
|
||||
def test_no_action_report_fallback_comment(self, handler, tmp_db):
|
||||
"""No action_report but has substantial comment → pass (fallback)"""
|
||||
must_haves = json.dumps({"action_type": "review_result"})
|
||||
_insert_task(tmp_db, "t3", must_haves)
|
||||
_insert_comment(tmp_db, "t3", "zhangfei-dev",
|
||||
"This is a sufficiently long comment about the task.")
|
||||
|
||||
result = handler.verify_completion("t3", tmp_db)
|
||||
assert result.passed is True
|
||||
assert result.reason == "has_comment"
|
||||
|
||||
def test_nothing_passes(self, handler, tmp_db):
|
||||
"""No action_report, no output, no comment → fail"""
|
||||
must_haves = json.dumps({"action_type": "review_result"})
|
||||
_insert_task(tmp_db, "t4", must_haves)
|
||||
|
||||
result = handler.verify_completion("t4", tmp_db)
|
||||
assert result.passed is False
|
||||
assert result.reason == "no_action"
|
||||
|
||||
def test_short_comment_fails(self, handler, tmp_db):
|
||||
"""Comment < 20 chars → fail"""
|
||||
must_haves = json.dumps({"action_type": "review_result"})
|
||||
_insert_task(tmp_db, "t5", must_haves)
|
||||
_insert_comment(tmp_db, "t5", "zhangfei-dev", "ok")
|
||||
|
||||
result = handler.verify_completion("t5", tmp_db)
|
||||
assert result.passed is False
|
||||
|
||||
def test_review_merged_auto_passes(self, handler, tmp_db):
|
||||
"""review_merged → always pass"""
|
||||
must_haves = json.dumps({"action_type": "review_merged"})
|
||||
_insert_task(tmp_db, "t6", must_haves)
|
||||
|
||||
result = handler.verify_completion("t6", tmp_db)
|
||||
assert result.passed is True
|
||||
assert result.reason == "merged_passthrough"
|
||||
|
||||
def test_infrastructure_failure_auto_passes(self, handler, tmp_db):
|
||||
"""infrastructure_failure → always pass (anti-recursion)"""
|
||||
must_haves = json.dumps({"action_type": "infrastructure_failure"})
|
||||
_insert_task(tmp_db, "t7", must_haves)
|
||||
|
||||
result = handler.verify_completion("t7", tmp_db)
|
||||
assert result.passed is True
|
||||
assert result.reason == "infrastructure_passthrough"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 3a: _send_toolchain_task tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestSendToolchainTask:
|
||||
def test_creates_task_in_toolchain_db(self):
|
||||
"""_send_toolchain_task creates a task in _toolchain DB."""
|
||||
from src.api.toolchain_routes import _send_toolchain_task, _toolchain_db_path
|
||||
|
||||
with patch("src.api.toolchain_routes.get_data_root") as mock_root:
|
||||
with tempfile.TemporaryDirectory() as d:
|
||||
mock_root.return_value = Path(d)
|
||||
|
||||
task_id = _send_toolchain_task(
|
||||
to_agent="zhangfei-dev",
|
||||
title="Test Task",
|
||||
description="Test description",
|
||||
event_type="ci_failure",
|
||||
action_type="ci_failure",
|
||||
steps=["Fix test", "Submit report"],
|
||||
context_data={"pr_number": 42},
|
||||
)
|
||||
|
||||
assert task_id.startswith("tc-")
|
||||
|
||||
# Verify task was written to _toolchain DB
|
||||
db_path = _toolchain_db_path()
|
||||
conn = get_connection(db_path)
|
||||
row = conn.execute(
|
||||
"SELECT * FROM tasks WHERE id=?", (task_id,)
|
||||
).fetchone()
|
||||
assert row is not None
|
||||
assert row["task_type"] == "toolchain"
|
||||
assert row["assignee"] == "zhangfei-dev"
|
||||
|
||||
# Verify must_haves JSON
|
||||
meta = json.loads(row["must_haves"])
|
||||
assert meta["event_type"] == "ci_failure"
|
||||
assert meta["action_type"] == "ci_failure"
|
||||
assert meta["steps"] == ["Fix test", "Submit report"]
|
||||
assert meta["context"]["pr_number"] == 42
|
||||
conn.close()
|
||||
|
||||
def test_unknown_agent_returns_empty(self):
|
||||
"""_send_toolchain_task with unknown agent returns empty string."""
|
||||
from src.api.toolchain_routes import _send_toolchain_task
|
||||
|
||||
task_id = _send_toolchain_task(
|
||||
to_agent="unknown-agent",
|
||||
title="Test",
|
||||
description="desc",
|
||||
event_type="test",
|
||||
action_type="test",
|
||||
steps=[],
|
||||
)
|
||||
assert task_id == ""
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 2e: on_failure three-way routing tests
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestOnFailureRouting:
|
||||
def test_business_failure_creates_gitea_comment(self, handler, tmp_db):
|
||||
"""Business failure → Gitea PR comment @task assignee (not must_hives field)"""
|
||||
# S4: must_hives does NOT contain assignee — production data doesn't have it
|
||||
must_haves = json.dumps({
|
||||
"action_type": "review_result",
|
||||
"context": {"repo": "sanguo/test", "pr_number": 42},
|
||||
"from": "system",
|
||||
})
|
||||
# assignee is set on the tasks table row (as production code writes it)
|
||||
_insert_task(tmp_db, "t-fail", must_haves)
|
||||
|
||||
with patch.object(handler, "_create_gitea_comment") as mock_comment:
|
||||
mock_comment.return_value = True
|
||||
verify = VerifyResult(False, "no_action", "no action_report")
|
||||
handler.on_failure("t-fail", "zhangfei-dev", tmp_db, verify)
|
||||
mock_comment.assert_called_once()
|
||||
call_args = mock_comment.call_args
|
||||
assert call_args[0][0] == "sanguo/test"
|
||||
assert call_args[0][1] == 42
|
||||
# M2: comment body should @ the task's assignee from tasks table
|
||||
comment_body = call_args[0][2]
|
||||
assert "@zhangfei-dev" in comment_body
|
||||
|
||||
def test_infrastructure_failure_creates_task(self, handler, tmp_db):
|
||||
"""Infrastructure failure → direct DB task for jiangwei-infra (no reverse dep)"""
|
||||
must_haves = json.dumps({
|
||||
"action_type": "review_result",
|
||||
"context": {"repo": "sanguo/test", "pr_number": 42},
|
||||
})
|
||||
_insert_task(tmp_db, "t-infra", must_haves)
|
||||
|
||||
with patch.object(handler, "_create_gitea_comment") as mock_comment:
|
||||
mock_comment.return_value = False # Gitea API down
|
||||
with patch.object(handler, "_create_gitea_issue") as mock_issue:
|
||||
mock_issue.return_value = False # Gitea API still down
|
||||
verify = VerifyResult(False, "no_action", "no action_report")
|
||||
handler.on_failure("t-infra", "zhangfei-dev", tmp_db, verify)
|
||||
|
||||
# S3: should directly INSERT into DB, not call _send_toolchain_task
|
||||
# Verify a new task was created in DB for jiangwei-infra
|
||||
conn = get_connection(tmp_db)
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM tasks WHERE assignee=?",
|
||||
("jiangwei-infra",)
|
||||
).fetchall()
|
||||
conn.close()
|
||||
assert len(rows) >= 1, "No infrastructure_failure task created"
|
||||
infra_task = rows[0]
|
||||
assert infra_task["task_type"] == "toolchain"
|
||||
meta = json.loads(infra_task["must_haves"])
|
||||
assert meta["action_type"] == "infrastructure_failure"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Regression: _mail path unaffected
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestMailRegression:
|
||||
def test_send_mail_still_exists(self):
|
||||
"""_send_mail function is preserved."""
|
||||
from src.api.toolchain_routes import _send_mail
|
||||
assert callable(_send_mail)
|
||||
|
||||
def test_send_mail_not_called_by_handlers(self):
|
||||
"""No toolchain handler calls _send_mail."""
|
||||
import inspect
|
||||
from src.api import toolchain_routes
|
||||
|
||||
# Get source of handler functions
|
||||
source = inspect.getsource(toolchain_routes)
|
||||
# _send_mail should appear only in its own definition, not in handler bodies
|
||||
lines = source.split("\n")
|
||||
in_handler = False
|
||||
handler_send_mail_calls = []
|
||||
for i, line in enumerate(lines):
|
||||
if line.strip().startswith("async def _handle_") or line.strip().startswith("async def _send_mention_mails"):
|
||||
in_handler = True
|
||||
elif line.strip().startswith("async def ") or line.strip().startswith("def _"):
|
||||
if not line.strip().startswith("async def _handle_") and not line.strip().startswith("async def _send_mention_mails"):
|
||||
in_handler = False
|
||||
if in_handler and "_send_mail(" in line and not line.strip().startswith("#"):
|
||||
handler_send_mail_calls.append((i, line.strip()))
|
||||
|
||||
assert len(handler_send_mail_calls) == 0, \
|
||||
f"_send_mail still called in handlers: {handler_send_mail_calls}"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Integration: full prompt build
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestFullPromptBuild:
|
||||
def test_prompt_contains_all_sections(self, handler):
|
||||
"""Full prompt has context, API, and constraints sections."""
|
||||
ctx = PromptContext(
|
||||
task_id="tc-test",
|
||||
title="CI 失败修复",
|
||||
description="Fix CI failure",
|
||||
must_haves=json.dumps({
|
||||
"event_type": "ci_failure",
|
||||
"action_type": "ci_failure",
|
||||
"steps": ["Fix test", "Push", "Submit report"],
|
||||
"context": {"pr_number": 42},
|
||||
}),
|
||||
project_id="_toolchain",
|
||||
agent_id="zhangfei-dev",
|
||||
event_type="ci_failure",
|
||||
event_data={"pr_number": "42", "repo": "sanguo/test"},
|
||||
action_type="ci_failure",
|
||||
action_steps=["Fix test", "Push", "Submit report"],
|
||||
)
|
||||
|
||||
prompt = handler.build_prompt(ctx)
|
||||
|
||||
# Must have action hint
|
||||
assert "CI 失败" in prompt
|
||||
assert "需要你修复" in prompt
|
||||
# Must have steps
|
||||
assert "必须执行的步骤" in prompt
|
||||
assert "1. Fix test" in prompt
|
||||
# Must have API section with action_report
|
||||
assert "action_report" in prompt
|
||||
assert "tc-test" in prompt
|
||||
# Must have constraints with Red Flags
|
||||
assert "Red Flags" in prompt
|
||||
assert "强制要求" in prompt
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# §17 v2: CI/deploy failure branching + issue label routing + Issue API guidance
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class TestCiFailureBranching:
|
||||
"""ci_failure steps should include a/b branching guidance."""
|
||||
|
||||
def test_ci_failure_steps_contain_branching(self):
|
||||
source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
|
||||
source = source_file.read_text()
|
||||
assert '基础设施问题' in source
|
||||
assert 'type/infrastructure' in source
|
||||
assert 'jiangwei-infra' in source
|
||||
|
||||
|
||||
class TestDeployFailureBranching:
|
||||
"""deploy_failure steps should include a/b branching guidance."""
|
||||
|
||||
def test_deploy_failure_steps_contain_branching(self):
|
||||
source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
|
||||
source = source_file.read_text()
|
||||
count = source.count('基础设施问题(Gitea 不可用')
|
||||
assert count >= 2, f'Expected >=2 deploy_failure branching, found {count}'
|
||||
|
||||
|
||||
class TestIssueAssignedLabelRouting:
|
||||
"""issue_assigned handler should route by type/infrastructure label."""
|
||||
|
||||
def test_label_check_in_source(self):
|
||||
source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
|
||||
source = source_file.read_text()
|
||||
assert 'is_infrastructure' in source
|
||||
assert 'infrastructure_failure' in source
|
||||
assert '基础设施 Issue' in source
|
||||
|
||||
def test_normal_issue_keeps_coding_steps(self):
|
||||
source_file = PROJECT_ROOT / "src" / "api" / "toolchain_routes.py"
|
||||
source = source_file.read_text()
|
||||
assert '创建分支 fix/' in source
|
||||
assert 'issue_assigned' in source
|
||||
|
||||
|
||||
class TestToolchainApiIssueGuidance:
|
||||
"""ToolchainApiSection should include Issue creation guidance."""
|
||||
|
||||
def test_has_issue_creation_section(self):
|
||||
source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
|
||||
source = source_file.read_text()
|
||||
assert "需要创建 Issue 时" in source
|
||||
assert "/issues" in source
|
||||
assert "jiangwei-infra" in source
|
||||
assert "type/infrastructure" in source
|
||||
|
||||
def test_issue_body_template_mentions_required_fields(self):
|
||||
source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
|
||||
source = source_file.read_text()
|
||||
assert "错误来源" in source
|
||||
assert "判断依据" in source
|
||||
|
||||
|
||||
class TestRedFlagsInfrastructure:
|
||||
"""Red Flags should include the 'not my code' entry."""
|
||||
|
||||
def test_has_infrastructure_red_flag(self):
|
||||
source_file = PROJECT_ROOT / "src" / "daemon" / "toolchain_handler.py"
|
||||
source = source_file.read_text()
|
||||
assert "不是我代码的问题" in source
|
||||
assert "基础设施问题" in source
|
||||
Reference in New Issue
Block a user