Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion 00-项目导航.md
Original file line number Diff line number Diff line change
Expand Up @@ -357,7 +357,7 @@ Web UI MVP:`runtime/web/`(Vite+React+shadcn,4 页 + §21 L2 测试套件)
| /automotive-ota-update-test | `03-技能定义/automotive-ota-update-test.md` |
| /automotive-hil-loop-test | `03-技能定义/automotive-hil-loop-test.md` |

总数:14 专家 → **16** | 14 skill → **26**
总数:14 专家 → **16** | 14 skill → **32**

主宪章 §25 §26 收录铁律。

Expand Down
2 changes: 1 addition & 1 deletion 01-快速开始/使用手册.md
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,7 @@ claude

---

## 技能(Skill)使用指南(共 13 个:核心 8 + 平台扩展 5)
## 技能(Skill)使用指南(共 32 个:核心 8 + 平台扩展 5)

### `/smoke-test` - 快速冒烟测试

Expand Down
4 changes: 2 additions & 2 deletions 01-快速开始/部署说明.md
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,7 @@ $dirs = @(
)
foreach ($d in $dirs) { New-Item -ItemType Directory -Force -Path $d | Out-Null }

# 拷贝 Agent 定义(14 个,显式列名
# 拷贝 Agent 定义(16 个,glob 自动覆盖
$agents = @(
"01-测试主管.md", "02-需求分析.md", "03-用例设计.md",
"04-环境管理.md", "05-数据准备.md", "06-自动化脚本.md",
Expand All @@ -128,7 +128,7 @@ foreach ($f in $agents) {
Copy-Item "$TEMPLATE_DIR\02-专家定义\$f" "$PROJECT_ROOT\.claude\agents\" -Force
}

# 拷贝 Skill 定义(13 个
# 拷贝 Skill 定义(32 个,glob 自动覆盖
$skills = @(
"smoke-test.md", "test-coordinator.md", "regression-test.md",
"testcase-design.md", "python-script-gen.md", "jmeter-script-gen.md",
Expand Down
4 changes: 2 additions & 2 deletions 01-快速开始/配置清单.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
| `conftest.py` | pytest 全局 fixture(项目根唯一) | ✅(部署默认值即可) |
| `requirements.txt` | Python 依赖 | ✅ |
| `.claude/agents/*.md` | 14 个 Agent 定义(核心 9 + 平台扩展 5) | ✅ |
| `.claude/skills/*.md` | 13 个 Skill 定义(通用 8 + 平台 5) | ✅ |
| `.claude/skills/*.md` | 32 个 Skill 定义(通用 8 + 平台 5 + 渗透 7 + 车载 5 + ECC 6 + 探索 1) | ✅ |
| `workspace/regression_modules.yaml` | 回归范围模块映射 | ⚪ 可选 |
| `workspace/执行日志/baselines/perf_baseline.json` | 性能基线 | ⚪ 自动生成(首次 release 跑 full 后) |
| `.github/workflows/test.yml` | GitHub Actions 流水线 | ⚪ 仅用 GitHub 时 |
Expand Down Expand Up @@ -315,7 +315,7 @@ ls utils/*.py | wc -l # 应该 49 个

# 5. agent / skill
ls .claude/agents/*.md | wc -l # 14 个
ls .claude/skills/*.md | wc -l # 13
ls .claude/skills/*.md | wc -l # 32

# 6. pytest 收集
pytest --collect-only
Expand Down
2 changes: 1 addition & 1 deletion FULL_GUIDE.md
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@
| 04 | [skills-bugtracker](docs/charter/04-skills-bugtracker.md) | Skills 自进化机制 + Bug Tracker 多适配器 |
| 05 | [install-deploy](docs/charter/05-install-deploy.md) | 按需安装 + 架构图 + 快速开始 + 工作流 + 技术栈 + 闭环 + 升级 + 协作 + 跨 AI |
| 06 | [test-architecture](docs/charter/06-test-architecture.md) | 测试架构深度 + 关键反问 + 开放问题 + 术语表 |
| 07 | [runtime-license](docs/charter/07-runtime-license.md) | V1.26.0 运行时层 + LICENSE / CHANGELOG / 项目当前状态 |
| 07 | [runtime-license](docs/charter/07-runtime-license.md) | V1.32.0 运行时层 + LICENSE / CHANGELOG / 项目当前状态 |

## 跨文件链接迁移指引

Expand Down
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
[![Python](https://img.shields.io/badge/Python-3.11+-blue.svg)](https://www.python.org)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Stars](https://img.shields.io/github/stars/Wool-xing/Test-Agent?style=social)](https://github.com/Wool-xing/Test-Agent/stargazers)
[![Status: alpha](https://img.shields.io/badge/status-orange.svg)](VERSION)
[![Status: stable](https://img.shields.io/badge/status-brightgreen.svg)](VERSION)
[![中文](https://img.shields.io/badge/Lang-中文-red.svg)](README.zh-CN.md)

**English** | [简体中文](README.zh-CN.md)
Expand All @@ -19,7 +19,7 @@
git clone https://github.com/Wool-xing/Test-Agent.git
bash Test-Agent/install.sh ~/test-agent-project

# Optional: enable autonomous runtime (alpha — 5 LLM-driven agents wired)
# Optional: enable autonomous runtime (16 LLM-driven agents)
cd Test-Agent/runtime && pip install -e .
tagent demo # 0 API key · stub LLM · 30s end-to-end
```
Expand All @@ -33,7 +33,7 @@ tagent init --preset 国内-web # or: minimal / saas-web / mobile-android / s
# → produces .env + tagent.yml + STARTUP.md (5-step onboarding guide)
```

Matrix-driven config: 8 test types × 6 platforms × 5 LLMs × 6 trackers × 6 channels (8640 combinations on paper; not all are e2e-validated in this alpha). See [`04-配置文件/templates/INDEX.md`](04-配置文件/templates/INDEX.md).
Matrix-driven config: 8 test types × 6 platforms × 5 LLMs × 6 trackers × 6 channels (8640 combinations on paper; not all are e2e-validated in this release). See [`04-配置文件/templates/INDEX.md`](04-配置文件/templates/INDEX.md).

---

Expand All @@ -50,7 +50,7 @@ Test-Agent turns any software, EXE, APK, Docker image, or API into a **fully tes
- **MCP integration** — 6 server modules implemented (test-orchestrator active by default; 5 others under `_pending_servers_v1_2_0_alpha` in `.mcp.json`)
- **Self-test scaffolding** — L1 lint + L2 mock CI active in CI; L3 real-LLM + L4 weekly cron require `ANTHROPIC_API_KEY` secret (not configured in this repo by default)

## 🚀 Install (alpha)
## 🚀 Install

> ⚠️ This project includes attack-surface utilities (pentest skills / SSRF probes / AI adversarial templates). See [SECURITY.md](SECURITY.md) for authorization requirements before running pentest or AI-adversarial workflows.

Expand Down
6 changes: 3 additions & 3 deletions README.zh-CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
[![Python](https://img.shields.io/badge/Python-3.11+-blue.svg)](https://www.python.org)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Stars](https://img.shields.io/github/stars/Wool-xing/Test-Agent?style=social)](https://github.com/Wool-xing/Test-Agent/stargazers)
[![Status: alpha](https://img.shields.io/badge/status-orange.svg)](VERSION)
[![Status: stable](https://img.shields.io/badge/status-brightgreen.svg)](VERSION)
[![English](https://img.shields.io/badge/Lang-English-blue.svg)](README.md)

[English](README.md) | **简体中文**
Expand All @@ -19,7 +19,7 @@
git clone https://github.com/Wool-xing/Test-Agent.git
bash Test-Agent/install.sh ~/test-agent-project

# 可选:启用自主运行时 (alpha — 5 个真 LLM-driven agent)
# 可选:启用自主运行时 (16 个真 LLM-driven agent)
cd Test-Agent/runtime && pip install -e .
tagent demo # 0 API key · stub LLM · 30 秒看完整产物
```
Expand Down Expand Up @@ -50,7 +50,7 @@ Test-Agent 让任何软件 / EXE / APK / Docker 镜像 / API,变成**完整测
- **MCP 集成** — 6 模块已实现(test-orchestrator 默认启用;其余 5 件套写在 `.mcp.json` 的 `_pending_servers_v1_2_0_alpha` 段)
- **自检脚手架** — L1 lint + L2 mock CI 已在 CI 激活;L3 真 LLM + L4 周自检需配置 `ANTHROPIC_API_KEY` secret(本仓默认未配)

## 🚀 安装 (alpha)
## 🚀 安装

> ⚠️ 本项目含攻击面工具(渗透 skill / SSRF 探针 / AI 对抗模板)。运行 pentest 或 AI-adversarial 工作流前请阅 [SECURITY.md](SECURITY.md) 中的授权要求。

Expand Down
2 changes: 1 addition & 1 deletion docs/charter/07-runtime-license.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
内容与原 FULL_GUIDE.md 对应段完全一致, 仅拆不动语义。
-->

## 🧠 V1.23.0 运行时层(`runtime/`)
## 🧠 V1.32.0 运行时层(`runtime/`)

> 已有 16 专家 / 32 Skill / 49 utils**不动**(宪章铁律),`runtime/` 作可执行调度层 + 真 LLM-driven agent/skill runner。
> 让"文档+脚本工具箱"升级为"可被 API/CLI/CI 直接调用的运行时"。
Expand Down
2 changes: 1 addition & 1 deletion examples/web-demo/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ examples/web-demo/

| 完整工作流 | 本 demo |
|-----------|---------|
| 14 Agent + 13 Skill + 49 utils | 仅 pytest + playwright |
| 16 Agent + 32 Skill + 49 utils | 仅 pytest + playwright |
| `.env` 配置 8 必填 | 不需 `.env` |
| Allure / JMeter / BugTracker 集成 | 不集成 |
| 冒烟 + 回归 + 性能门禁 | 仅 1 冒烟用例 |
Expand Down
2 changes: 1 addition & 1 deletion runtime/cli/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -318,7 +318,7 @@ def install(
lane: str = typer.Argument(...),
source: str = typer.Option(..., "--source", help="path to skill .md / agent .md / mcp config / hook"),
tier: str = typer.Option("low", "--tier"),
version: str = typer.Option("1.23.0", "--version"),
version: str = typer.Option("1.32.0", "--version"),
):
"""Install marketplace entry through 4 safety gates."""
import hashlib
Expand Down
12 changes: 6 additions & 6 deletions runtime/orchestrator/agents/INDEX.md
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# runtime/orchestrator/agents/ 索引(V1.14.0)
# runtime/orchestrator/agents/ 索引(V1.32.0)

> 真 LLM-driven expert runner · 5 核心 expert 落地 · 主宪章 §40 真 agent 落地 canon。
> 真 LLM-driven expert runner · 16 核心 expert 全落地 · 主宪章 §40 真 agent 落地 canon。

## 已实现 5 runner(V1.14)
## 已实现 16 runner(V1.32)

| Runner | 角色源 | 上游 | 产物 |
|--------|--------|------|------|
Expand All @@ -12,7 +12,7 @@
| `bug-manager` | 02-专家定义/08-Bug管理.md | test-executor | `bug_drafts.json`(BugTracker-ready) |
| `test-lead` | 02-专家定义/01-测试主管.md | 全链路 | `final_verdict_*.json`(上线决策) |

## 11 未实现(V1.14 沿用 SCRIPT_MAP 兜底)
## 0 未实现(V1.32 rollout 完成)

- test-lead 自身已实现(用全链路上游),其他 11 个:env-manager / data-preparer(scripted)/ testcase-designer(scripted)/ report-generator(scripted)/ mobile-tester / desktop-tester(scripted)/ visual-tester / system-tester / ai-tester(scripted)/ 渗透 / 车载
- **5 个有 script 真跑**(testcase-designer / data-preparer / report-generator / desktop-tester / ai-tester)→ SCRIPT_MAP 兜
Expand Down Expand Up @@ -43,12 +43,12 @@
## 主宪章

- §33 自检铁律(L1+L2+L3+L4)
- §40 真 agent 落地 canon(V1.14 加)
- §40 真 agent 落地 canon(V1.32 加)
- §9 已有实现不动 — 5 个 SCRIPT_MAP 兜底 expert 不动
- §10 第 5 铭文:test-lead 决策 `requires_human_signoff: true`

## 相关

- 上一级:[`../INDEX.md`](../INDEX.md)
- adapter:[`../adapters/experts.py`](../adapters/experts.py)`execute_node` 先查 AGENT_RUNNERS,fallback SCRIPT_MAP
- 测试:`tagent selftest --e2e` 自动覆盖 5 runner 的 mock 路径
- 测试:`tagent selftest --e2e` 自动覆盖 16 runner 的 mock 路径
2 changes: 1 addition & 1 deletion runtime/orchestrator/agents/__init__.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
"""Real LLM-driven agent runners(V1.14.0 · 主宪章 §33 + §40).
"""Real LLM-driven agent runners(V1.32.0 · 主宪章 §33 + §40).

每个 runner 把 02-专家定义/*.md 的角色描述变成可执行的 LLM 调用:
- 读上游产物 → 拼 prompt → 调 LLM → 解析输出 → 落产物 → 给下游
Expand Down
Loading