devsquad 4.4.0__tar.gz → 4.5.0__tar.gz

{devsquad-4.4.0 → devsquad-4.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsquad
-Version: 4.4.0
+Version: 4.5.0
 Summary: Production-Ready Multi-Role AI Task Orchestrator
 Author-email: DevSquad Team <devsquad@example.com>
 License: MIT
@@ -54,9 +54,9 @@ Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
 Requires-Dist: pytest-cov>=4.1; extra == "dev"
-Requires-Dist: ruff>=0.4.0; extra == "dev"
-Requires-Dist: mypy>=1.0; extra == "dev"
-Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: ruff==0.15.20; extra == "dev"
+Requires-Dist: mypy==2.2.0; extra == "dev"
+Requires-Dist: black==26.5.1; extra == "dev"
 Requires-Dist: flake8>=6.0; extra == "dev"
 Requires-Dist: httpx2>=2.5.0; extra == "dev"
 Requires-Dist: streamlit>=1.28.0; extra == "dev"
@@ -96,14 +96,14 @@ Dynamic: license-file
 <p align="center">
   <strong>🎯 把「单个 AI 助手」升级成「7 人 AI 专业团队」</strong>
   <br>
-  <em>One task → Multi-role AI collaboration → One conclusion | V4.4.0 (5 new enhancement modules)</em>
+  <em>One task → Multi-role AI collaboration → One conclusion | V4.5.0 (cross-session continuity + protocol-native skills + action-first reports) | V4.4.0 (5 enhancement modules)</em>
 </p>
 
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white" />
   <img alt="License" src="https://img.shields.io/badge/License-MIT-green" />
-  <img alt="Tests" src="https://img.shields.io/badge/Tests-8136%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V4.4.0-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-8260%2B%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V4.5.0-success" />
   <img alt="CI" src="https://img.shields.io/badge/CI-GitHub_Actions-blue?logo=githubactions" />
   <img alt="Quality" src="https://img.shields.io/badge/Code%20Quality-4.3%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%86-blue" />
   <img alt="Security" src="https://img.shields.io/badge/Security-5%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%85-success" />
@@ -164,51 +164,77 @@ devsquad run "设计一个安全的用户认证系统" --roles architect,securit
 <details>
 <summary>🔍 点击展开：完整功能介绍与架构详解</summary>
 
-## 🚀 V4.3.0 (V4.3.0 candidate): 安全债清理 + 上游精细化升级 + 测试金字塔达标
+## 🚀 V4.5.0: Cross-Session Continuity + Protocol-Native Skills + Action-First Reports
+
+**DevSquad V4.5.0** (merging V4.4.3 + V4.4.4 + V4.5.0 changes) delivers 10 new features for cross-session continuity, protocol-native skill architecture, and action-first reporting. The 7-role AI team orchestrates complex engineering tasks with full audit trails and consensus mechanisms. See [docs/VISION.md](docs/VISION.md) for the project vision.
+
+### V4.5.0 — 10 New Features
+- **ScratchpadHistoryStore**: SQLite-backed cross-session Scratchpad search
+- **AgentIdentity**: Deterministic agent ID for cross-session tracking
+- **WorkflowTrace**: Transparent workflow trace in dispatch reports
+- **GitContext**: Git branch/commit context injection into dispatch
+- **SkillProvider Protocol**: Protocol-native skill architecture (Builtin + MCP providers)
+- **OutputStyle**: Action-first report format (from i-have-adhd insights)
+- **SessionResume CLI**: `devsquad sessions list` + `dispatch --resume`
+- **FileBundler**: Deterministic file bundling for review mode (from open-code-review)
+- **SKILL.md Modular Split**: 1216→282 lines + 3 reference docs (MODULE_REFERENCE / SUB_SKILLS / VERSION_HISTORY)
+- **VISION Documents**: docs/VISION.md + VISION_ORCHESTRATION.md + VISION_AGENT_COLLABORATION.md
+
+### V4.4.0 — P0-P3 Enhancement Modules (5 new modules)
+- **P0-1 RiskRegister**: PMP risk management with 7-role weighted assessment (probability × impact) + 4 response strategies (avoid/transfer/mitigate/accept) + `GateType.RISK_CHECK` gate (exposure ≥ 0.36 blocks)
+- **P0-2 ViewpointRegistry**: TOGAF architecture viewpoints with 7-role bound formal viewpoints + `is_orthogonal()` orthogonality check + `check_consistency()` conflict detection
+- **P1-1 ErrorBudgetTracker**: SRE error budget with SLO 99.9% default + `GateType.ERROR_BUDGET` P10 gate (budget exhaustion blocks deployment) + `burn_rate()` consumption rate
+- **P1-2 GapAnalyzer**: TOGAF gap analysis with `analyze(current, target)` + `prioritize()` + `generate_roadmap()` + `suggest_scheduler_decision()` driving LoopScheduler
+- **P2-1 DoraMetricsCollector**: DORA metrics (Deployment Frequency / Lead Time / Change Failure Rate / MTTR) + `GateType.DORA_CHECK` P11 gate (CFR > 15% triggers architecture review) + Elite/High/Medium/Low rating
+
+### V4.4.1 — External Docs Restructure
+- Archived orphan i18n docs (docs/i18n/ → docs/_archive/i18n/)
+- Retired CHANGELOG-CN.md (CHANGELOG.md is now SSOT for all languages)
+- Consolidated admin credentials to INSTALL.md only (single source of truth)
+- Renumbered INSTALL.md methods to continuous 1-7
+- Synced version numbers across all external docs (README/SKILL/INSTALL/CLAUDE)
+
+### V4.4.2 — Multilingual + Dashboard Enhancement
+- Multilingual role prompts (EN/CN/JP) for all 7 roles
+- Dashboard 6-tab visibility (Overview/Dispatch/Lifecycle/Metrics/Audit/Settings)
+- P2 Kanban evaluation (work-in-progress limits + cycle time tracking)
+- P3 ITSM evaluation (incident management + change advisory board simulation)
+- 13 E2E tests xpass + anti-ghost counters
+
+### Anti-Ghost Feature Guarantee
+Every new module includes `_call_counter` mechanism + E2E anti_ghost test + CI `check_module_activation.py` verification. Modules must be truly integrated into dispatch pipeline (not just instantiated), with Markdown report sections user-visible.
+
+### Test Pyramid Achieved
+- **Contract tests**: 5.2% (target ≥5% ✅)
+- **Integration tests**: 15.1% (target ≥15% ✅)
+- **Total tests**: 8260+ (CI authoritative)
+- **E2E coverage**: 107 e2e + 1244 integration + 13 V4.4.0 anti-ghost
+
+### Historical Features (V4.0.0-V4.3.3)
+- **V4.3.3**: P0-P3 enhancement E2E skeletons (xfail TDD for V4.4.0)
+- **V4.3.2**: LLM vs Mock quality gap measurement (calibration gate + thin-slice probe)
+- **V4.3.0 Phase 3**: Quality hardening + user simulation E2E (NPS 9/10)
+- **V4.3.0 Phase 2**: OutputValidator full integration (LLM output safety detection)
+- **V4.3.0 Phase 1**: DependencyHallucinationChecker (anti-slopsquatting supply chain attack)
+- **V4.3.0 Phase 0**: DeploymentComplianceChecker (anti-violation deployment backstop)
+- **V4.0.0 P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling
+- **V4.0.0 P1-2 UI/UX Patrol**: 4-dimension audit + PIL pixel diff visual regression
+- **V4.0.0 P2-1 Adversarial Verification**: red team attack + blue team defense + judge arbitration
+- **V4.0.0 P2-2 DAG Visualization**: Mermaid / JSON / DOT three formats
+- **V4.0.0 P3-1 Autonomous**: plan → dev → verify → fix 4-stage autonomous iteration
+- **V4.0.0 P3-2 Plugin Hot-Loading**: 3 loading paths + path traversal 3-layer protection + reload rollback
+
+8260+ tests passing (CI authoritative).
 
-**DevSquad V4.3.0** 是 V4.3.0 的预发布候选版本，整合技术债跟踪、pickle→JSON 迁移、上游 TraeMultiAgentSkill v2.6-v2.8 精细化启发三方面输入，按 7-Role 共识推进：
-
-### V4.3.0 P0 — 安全债清理（必做）
-- **P0-1 pickle→JSON 迁移阶段 1**: 删除 2 处 dead code + fallback 安全收紧（`require_password` 校验）
-- **P0-2 技术债持续监控**: `todo_drift_monitor.py` 自动扫描 TODO/FIXME/HACK + pre-commit 阻塞 + CI lint 集成
-
-### V4.3.0 P1 — 上游精细化升级（重要）
-- **P1-1 Ponytail lite/full 双模式**: 8 核心红线（lite）+ 16 红线（full），`# ponytail:` 债务收集 + `[REQ-XXX]` 需求追踪
-- **P1-4 LoopKernel RollbackStrategy**: D1-D6 失败精准回退 + 独立硬上限（默认 3）+ 累计上下文传递
-- **P1-5 UIUX 子项审计**: 4 维度 20 子项注册表 + PASS/WARN/FAIL/NOT_IMPLEMENTED 审计
-- **P1-6 Dashboard V4.3.0 面板**: Ponytail 模式 / Loop 回退 / Plugin 事件 / 技术债状态可视化
-
-### V4.3.0 P2 — 收尾（一般）
-- **P2-1 pickle fallback 完全移除**（用户确认从 V4.3.1 并入 V4.3.0）: `allow_pickle_fallback` 参数移除，`serialization_format="pickle"` 构造时拒绝
-
-### V4.2+ / V4.3+ Roadmap 已落地项
-- **P2-1 PrototypeSkill**: 快速原型生成验证假设
-- **P2-2 TeachSkill**: 8 主题新用户引导课程
-- **P2-4 pre-commit hooks**: 依赖版本锁检查
-- **P2-UI-1 CLI 命令词表**: 基于 impeccable 23 命令词表对齐
-- **P2-UI-2 Live Browser 模式**: 实时 UI 审查迭代闭环
-- **P2-UI-3 Meta-skills 分层**: 8 子技能 6 层架构
-
-### 测试金字塔达标
-- **Contract 测试**: 3.06% → 5.0%（目标 ≥5% ✅）
-- **Integration 测试**: 8.84% → 15.2%（目标 ≥15% ✅）
-- **总测试数**: 5250+ → 7681（+2431 测试）
+---
 
-### 历史特性（V4.0.0-V4.2.1）
-- **V4.0.0 P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling 五步闭环
-- **V4.0.0 P1-2 UI/UX 巡检**: 4 维度审计 + PIL 像素 diff 视觉回归
-- **V4.0.0 P2-1 Adversarial 验证**: 红队攻击 + 蓝队防御 + 裁判仲裁
-- **V4.0.0 P2-2 DAG 可视化**: Mermaid / JSON / DOT 三格式
-- **V4.0.0 P3-1 Autonomous**: plan → dev → verify → fix 4 阶段自主迭代
-- **V4.0.0 P3-2 插件热加载**: 3 加载路径 + 路径穿越三层防护 + reload 回滚
+## ⚡ Quick Start (7 Ways to Invoke DevSquad)
 
-7681 tests passing。
+### Method 1: TRAE Skill (Recommended — you're already here)
 
----
+DevSquad is registered as a TRAE Skill. Simply describe your task in the TRAE IDE chat, and the 7-role team will collaborate automatically. No CLI or API setup needed.
 
-## ⚡ Quick Start (5 Ways to Use DevSquad)
-
-### Method 1: CLI (Recommended for Beginners)
+### Method 2: CLI (Recommended for Terminal Users)
 
 ```bash
 # Interactive setup wizard (1-2 minutes)
@@ -218,18 +244,28 @@ python scripts/cli.py init
 devsquad dispatch -t "your task description"
 ```
 
-### Method 2: Web Dashboard (Recommended for Teams)
+### Method 3: MCP Server (For IDE / Tool Integration)
+
+```bash
+# Start MCP server with stdio transport (for IDE integration)
+python3 scripts/mcp_server.py
+
+# Or SSE transport (for remote access)
+python3 scripts/mcp_server.py --port 8080
+```
+
+### Method 4: Web Dashboard (Recommended for Teams)
 
 ```bash
 # Start Streamlit dashboard with authentication
 streamlit run scripts/dashboard.py
 
 # Open http://localhost:8501
-# Login with default account, then change password immediately.
-# Username: admin   Password: admin123   (change in production)
+# Login with default dev credentials (see INSTALL.md "Default credentials" section).
+# Change all defaults in production.
 ```
 
-### Method 3: REST API (Recommended for Integration)
+### Method 5: REST API (Recommended for Integration)
 
 ```bash
 # Install dependencies
@@ -242,7 +278,7 @@ uvicorn scripts.api_server:app --host 0.0.0.0 --port 8000 --reload
 # Access ReDoc:      http://localhost:8000/redoc
 ```
 
-### Method 4: Python API (Recommended for Developers)
+### Method 6: Python API (Recommended for Developers)
 
 ```python
 from scripts.collaboration.dispatcher import MultiAgentDispatcher
@@ -256,7 +292,7 @@ print(result.report)
 print(result.consensus)
 ```
 
-### Method 5: One-Click Startup Script (V3.9.2+)
+### Method 7: One-Click Startup Script (V3.9.2+)
 
 ```bash
 # One-click startup — 4 phases: env check → DB init → frontend build → service start
@@ -485,7 +521,7 @@ All modules are **optional switches** — DevSquad works perfectly without them.
 
 ## 🧩 Layered Sub-Skill Architecture (V3.6.0)
 
-> DevSquad provides **6 atomic sub-skills** that can be used independently or together.
+> DevSquad provides **8 atomic sub-skills** that can be used independently or together.
 > Each sub-skill is a thin wrapper (~50 lines) importing existing core modules — no duplicated logic.
 
 ```
@@ -495,7 +531,9 @@ skills/
 ├── review/         → ReviewSkill   — FiveAxisConsensusEngine (5-axis code review)
 ├── security/       → SecuritySkill — InputValidator + OperationClassifier + PermissionGuard
 ├── test/           → TestSkill     — TestQualityGuard + test strategy generation
-└── retrospective/  → RetroSkill    — RetrospectiveEngine + pattern extraction
+├── retrospective/  → RetroSkill    — RetrospectiveEngine + pattern extraction
+├── prototype/      → PrototypeSkill — Rapid prototype scaffolding (V4.5.0)
+└── teach/          → TeachSkill     — Knowledge transfer & onboarding (V4.5.0)
 ```
 
 ### Sub-Skill Quick Reference
@@ -766,6 +804,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-07-24 | Version: V4.2.1 (V4.3.0 in progress — see [Roadmap](#-roadmap))*
+*Last updated: 2026-08-03 | Version: V4.5.0 (cross-session continuity + protocol-native skills + action-first reports — 10 new features) | V4.4.0 (5 enhancement modules: RiskRegister / ViewpointRegistry / ErrorBudgetTracker / GapAnalyzer / DoraMetricsCollector — see [CHANGELOG.md](CHANGELOG.md))*
 
 </details>

{devsquad-4.4.0 → devsquad-4.5.0}/README.md

@@ -3,14 +3,14 @@
 <p align="center">
   <strong>🎯 把「单个 AI 助手」升级成「7 人 AI 专业团队」</strong>
   <br>
-  <em>One task → Multi-role AI collaboration → One conclusion | V4.4.0 (5 new enhancement modules)</em>
+  <em>One task → Multi-role AI collaboration → One conclusion | V4.5.0 (cross-session continuity + protocol-native skills + action-first reports) | V4.4.0 (5 enhancement modules)</em>
 </p>
 
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white" />
   <img alt="License" src="https://img.shields.io/badge/License-MIT-green" />
-  <img alt="Tests" src="https://img.shields.io/badge/Tests-8136%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V4.4.0-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-8260%2B%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V4.5.0-success" />
   <img alt="CI" src="https://img.shields.io/badge/CI-GitHub_Actions-blue?logo=githubactions" />
   <img alt="Quality" src="https://img.shields.io/badge/Code%20Quality-4.3%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%86-blue" />
   <img alt="Security" src="https://img.shields.io/badge/Security-5%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%85-success" />
@@ -71,51 +71,77 @@ devsquad run "设计一个安全的用户认证系统" --roles architect,securit
 <details>
 <summary>🔍 点击展开：完整功能介绍与架构详解</summary>
 
-## 🚀 V4.3.0 (V4.3.0 candidate): 安全债清理 + 上游精细化升级 + 测试金字塔达标
+## 🚀 V4.5.0: Cross-Session Continuity + Protocol-Native Skills + Action-First Reports
+
+**DevSquad V4.5.0** (merging V4.4.3 + V4.4.4 + V4.5.0 changes) delivers 10 new features for cross-session continuity, protocol-native skill architecture, and action-first reporting. The 7-role AI team orchestrates complex engineering tasks with full audit trails and consensus mechanisms. See [docs/VISION.md](docs/VISION.md) for the project vision.
+
+### V4.5.0 — 10 New Features
+- **ScratchpadHistoryStore**: SQLite-backed cross-session Scratchpad search
+- **AgentIdentity**: Deterministic agent ID for cross-session tracking
+- **WorkflowTrace**: Transparent workflow trace in dispatch reports
+- **GitContext**: Git branch/commit context injection into dispatch
+- **SkillProvider Protocol**: Protocol-native skill architecture (Builtin + MCP providers)
+- **OutputStyle**: Action-first report format (from i-have-adhd insights)
+- **SessionResume CLI**: `devsquad sessions list` + `dispatch --resume`
+- **FileBundler**: Deterministic file bundling for review mode (from open-code-review)
+- **SKILL.md Modular Split**: 1216→282 lines + 3 reference docs (MODULE_REFERENCE / SUB_SKILLS / VERSION_HISTORY)
+- **VISION Documents**: docs/VISION.md + VISION_ORCHESTRATION.md + VISION_AGENT_COLLABORATION.md
+
+### V4.4.0 — P0-P3 Enhancement Modules (5 new modules)
+- **P0-1 RiskRegister**: PMP risk management with 7-role weighted assessment (probability × impact) + 4 response strategies (avoid/transfer/mitigate/accept) + `GateType.RISK_CHECK` gate (exposure ≥ 0.36 blocks)
+- **P0-2 ViewpointRegistry**: TOGAF architecture viewpoints with 7-role bound formal viewpoints + `is_orthogonal()` orthogonality check + `check_consistency()` conflict detection
+- **P1-1 ErrorBudgetTracker**: SRE error budget with SLO 99.9% default + `GateType.ERROR_BUDGET` P10 gate (budget exhaustion blocks deployment) + `burn_rate()` consumption rate
+- **P1-2 GapAnalyzer**: TOGAF gap analysis with `analyze(current, target)` + `prioritize()` + `generate_roadmap()` + `suggest_scheduler_decision()` driving LoopScheduler
+- **P2-1 DoraMetricsCollector**: DORA metrics (Deployment Frequency / Lead Time / Change Failure Rate / MTTR) + `GateType.DORA_CHECK` P11 gate (CFR > 15% triggers architecture review) + Elite/High/Medium/Low rating
+
+### V4.4.1 — External Docs Restructure
+- Archived orphan i18n docs (docs/i18n/ → docs/_archive/i18n/)
+- Retired CHANGELOG-CN.md (CHANGELOG.md is now SSOT for all languages)
+- Consolidated admin credentials to INSTALL.md only (single source of truth)
+- Renumbered INSTALL.md methods to continuous 1-7
+- Synced version numbers across all external docs (README/SKILL/INSTALL/CLAUDE)
+
+### V4.4.2 — Multilingual + Dashboard Enhancement
+- Multilingual role prompts (EN/CN/JP) for all 7 roles
+- Dashboard 6-tab visibility (Overview/Dispatch/Lifecycle/Metrics/Audit/Settings)
+- P2 Kanban evaluation (work-in-progress limits + cycle time tracking)
+- P3 ITSM evaluation (incident management + change advisory board simulation)
+- 13 E2E tests xpass + anti-ghost counters
+
+### Anti-Ghost Feature Guarantee
+Every new module includes `_call_counter` mechanism + E2E anti_ghost test + CI `check_module_activation.py` verification. Modules must be truly integrated into dispatch pipeline (not just instantiated), with Markdown report sections user-visible.
+
+### Test Pyramid Achieved
+- **Contract tests**: 5.2% (target ≥5% ✅)
+- **Integration tests**: 15.1% (target ≥15% ✅)
+- **Total tests**: 8260+ (CI authoritative)
+- **E2E coverage**: 107 e2e + 1244 integration + 13 V4.4.0 anti-ghost
+
+### Historical Features (V4.0.0-V4.3.3)
+- **V4.3.3**: P0-P3 enhancement E2E skeletons (xfail TDD for V4.4.0)
+- **V4.3.2**: LLM vs Mock quality gap measurement (calibration gate + thin-slice probe)
+- **V4.3.0 Phase 3**: Quality hardening + user simulation E2E (NPS 9/10)
+- **V4.3.0 Phase 2**: OutputValidator full integration (LLM output safety detection)
+- **V4.3.0 Phase 1**: DependencyHallucinationChecker (anti-slopsquatting supply chain attack)
+- **V4.3.0 Phase 0**: DeploymentComplianceChecker (anti-violation deployment backstop)
+- **V4.0.0 P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling
+- **V4.0.0 P1-2 UI/UX Patrol**: 4-dimension audit + PIL pixel diff visual regression
+- **V4.0.0 P2-1 Adversarial Verification**: red team attack + blue team defense + judge arbitration
+- **V4.0.0 P2-2 DAG Visualization**: Mermaid / JSON / DOT three formats
+- **V4.0.0 P3-1 Autonomous**: plan → dev → verify → fix 4-stage autonomous iteration
+- **V4.0.0 P3-2 Plugin Hot-Loading**: 3 loading paths + path traversal 3-layer protection + reload rollback
+
+8260+ tests passing (CI authoritative).
 
-**DevSquad V4.3.0** 是 V4.3.0 的预发布候选版本，整合技术债跟踪、pickle→JSON 迁移、上游 TraeMultiAgentSkill v2.6-v2.8 精细化启发三方面输入，按 7-Role 共识推进：
-
-### V4.3.0 P0 — 安全债清理（必做）
-- **P0-1 pickle→JSON 迁移阶段 1**: 删除 2 处 dead code + fallback 安全收紧（`require_password` 校验）
-- **P0-2 技术债持续监控**: `todo_drift_monitor.py` 自动扫描 TODO/FIXME/HACK + pre-commit 阻塞 + CI lint 集成
-
-### V4.3.0 P1 — 上游精细化升级（重要）
-- **P1-1 Ponytail lite/full 双模式**: 8 核心红线（lite）+ 16 红线（full），`# ponytail:` 债务收集 + `[REQ-XXX]` 需求追踪
-- **P1-4 LoopKernel RollbackStrategy**: D1-D6 失败精准回退 + 独立硬上限（默认 3）+ 累计上下文传递
-- **P1-5 UIUX 子项审计**: 4 维度 20 子项注册表 + PASS/WARN/FAIL/NOT_IMPLEMENTED 审计
-- **P1-6 Dashboard V4.3.0 面板**: Ponytail 模式 / Loop 回退 / Plugin 事件 / 技术债状态可视化
-
-### V4.3.0 P2 — 收尾（一般）
-- **P2-1 pickle fallback 完全移除**（用户确认从 V4.3.1 并入 V4.3.0）: `allow_pickle_fallback` 参数移除，`serialization_format="pickle"` 构造时拒绝
-
-### V4.2+ / V4.3+ Roadmap 已落地项
-- **P2-1 PrototypeSkill**: 快速原型生成验证假设
-- **P2-2 TeachSkill**: 8 主题新用户引导课程
-- **P2-4 pre-commit hooks**: 依赖版本锁检查
-- **P2-UI-1 CLI 命令词表**: 基于 impeccable 23 命令词表对齐
-- **P2-UI-2 Live Browser 模式**: 实时 UI 审查迭代闭环
-- **P2-UI-3 Meta-skills 分层**: 8 子技能 6 层架构
-
-### 测试金字塔达标
-- **Contract 测试**: 3.06% → 5.0%（目标 ≥5% ✅）
-- **Integration 测试**: 8.84% → 15.2%（目标 ≥15% ✅）
-- **总测试数**: 5250+ → 7681（+2431 测试）
+---
 
-### 历史特性（V4.0.0-V4.2.1）
-- **V4.0.0 P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling 五步闭环
-- **V4.0.0 P1-2 UI/UX 巡检**: 4 维度审计 + PIL 像素 diff 视觉回归
-- **V4.0.0 P2-1 Adversarial 验证**: 红队攻击 + 蓝队防御 + 裁判仲裁
-- **V4.0.0 P2-2 DAG 可视化**: Mermaid / JSON / DOT 三格式
-- **V4.0.0 P3-1 Autonomous**: plan → dev → verify → fix 4 阶段自主迭代
-- **V4.0.0 P3-2 插件热加载**: 3 加载路径 + 路径穿越三层防护 + reload 回滚
+## ⚡ Quick Start (7 Ways to Invoke DevSquad)
 
-7681 tests passing。
+### Method 1: TRAE Skill (Recommended — you're already here)
 
----
+DevSquad is registered as a TRAE Skill. Simply describe your task in the TRAE IDE chat, and the 7-role team will collaborate automatically. No CLI or API setup needed.
 
-## ⚡ Quick Start (5 Ways to Use DevSquad)
-
-### Method 1: CLI (Recommended for Beginners)
+### Method 2: CLI (Recommended for Terminal Users)
 
 ```bash
 # Interactive setup wizard (1-2 minutes)
@@ -125,18 +151,28 @@ python scripts/cli.py init
 devsquad dispatch -t "your task description"
 ```
 
-### Method 2: Web Dashboard (Recommended for Teams)
+### Method 3: MCP Server (For IDE / Tool Integration)
+
+```bash
+# Start MCP server with stdio transport (for IDE integration)
+python3 scripts/mcp_server.py
+
+# Or SSE transport (for remote access)
+python3 scripts/mcp_server.py --port 8080
+```
+
+### Method 4: Web Dashboard (Recommended for Teams)
 
 ```bash
 # Start Streamlit dashboard with authentication
 streamlit run scripts/dashboard.py
 
 # Open http://localhost:8501
-# Login with default account, then change password immediately.
-# Username: admin   Password: admin123   (change in production)
+# Login with default dev credentials (see INSTALL.md "Default credentials" section).
+# Change all defaults in production.
 ```
 
-### Method 3: REST API (Recommended for Integration)
+### Method 5: REST API (Recommended for Integration)
 
 ```bash
 # Install dependencies
@@ -149,7 +185,7 @@ uvicorn scripts.api_server:app --host 0.0.0.0 --port 8000 --reload
 # Access ReDoc:      http://localhost:8000/redoc
 ```
 
-### Method 4: Python API (Recommended for Developers)
+### Method 6: Python API (Recommended for Developers)
 
 ```python
 from scripts.collaboration.dispatcher import MultiAgentDispatcher
@@ -163,7 +199,7 @@ print(result.report)
 print(result.consensus)
 ```
 
-### Method 5: One-Click Startup Script (V3.9.2+)
+### Method 7: One-Click Startup Script (V3.9.2+)
 
 ```bash
 # One-click startup — 4 phases: env check → DB init → frontend build → service start
@@ -392,7 +428,7 @@ All modules are **optional switches** — DevSquad works perfectly without them.
 
 ## 🧩 Layered Sub-Skill Architecture (V3.6.0)
 
-> DevSquad provides **6 atomic sub-skills** that can be used independently or together.
+> DevSquad provides **8 atomic sub-skills** that can be used independently or together.
 > Each sub-skill is a thin wrapper (~50 lines) importing existing core modules — no duplicated logic.
 
 ```
@@ -402,7 +438,9 @@ skills/
 ├── review/         → ReviewSkill   — FiveAxisConsensusEngine (5-axis code review)
 ├── security/       → SecuritySkill — InputValidator + OperationClassifier + PermissionGuard
 ├── test/           → TestSkill     — TestQualityGuard + test strategy generation
-└── retrospective/  → RetroSkill    — RetrospectiveEngine + pattern extraction
+├── retrospective/  → RetroSkill    — RetrospectiveEngine + pattern extraction
+├── prototype/      → PrototypeSkill — Rapid prototype scaffolding (V4.5.0)
+└── teach/          → TeachSkill     — Knowledge transfer & onboarding (V4.5.0)
 ```
 
 ### Sub-Skill Quick Reference
@@ -673,6 +711,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-07-24 | Version: V4.2.1 (V4.3.0 in progress — see [Roadmap](#-roadmap))*
+*Last updated: 2026-08-03 | Version: V4.5.0 (cross-session continuity + protocol-native skills + action-first reports — 10 new features) | V4.4.0 (5 enhancement modules: RiskRegister / ViewpointRegistry / ErrorBudgetTracker / GapAnalyzer / DoraMetricsCollector — see [CHANGELOG.md](CHANGELOG.md))*
 
 </details>