┌─────────────────────────────────────────────────────────────────┐
│                 TWO-AGENT ARCHITECTURE                           │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  SESSION 1: INITIALIZER AGENT                                   │
│  ┌─────────────────────────────────────────────────────────┐    │
│  │ • Read requirements / spec                               │    │
│  │ • Create project structure                               │    │
│  │ • Generate feature_list.json (200+ tests)                │    │
│  │ • Initialize Git repository                              │    │
│  │ • ✨ Prompt for GitHub URL (optional)                    │    │
│  │ • ✨ Create README.md & PLANNING.md                      │    │
│  │ • Commit initial state                                   │    │
│  │ • ✨ Push to GitHub & create issues                      │    │
│  └─────────────────────────────────────────────────────────┘    │
│                              │                                   │
│                    feature_list.json                             │
│                    (Single Source of Truth)                      │
│                              │                                   │
│  SESSIONS 2+: BUILDER AGENT (fresh context each session)        │
│  ┌─────────────────────────────────────────────────────────┐    │
│  │ Step 1: Get Context (pwd, ls, git log, progress)         │    │
│  │ Step 2: Start/verify server                              │    │
│  │ Step 3: Verify previous tests (regression check)         │    │
│  │ Step 4: Select next "passes": false feature              │    │
│  │ Step 5: Implement feature                                │    │
│  │ Step 6: Browser automation test                          │    │
│  │ Step 7: Update feature_list.json                         │    │
│  │ Step 8: Generate workflow report                         │    │
│  │ Step 9: Git commit + GitHub push                        │    │
│  │ Step 10: Update progress notes                           │    │
│  │ Step 11: Clean exit (auto-continue in 3s)                │    │
│  └─────────────────────────────────────────────────────────┘    │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

PLAN -> BUILD -> TEST -> DEBUG -> DEPLOY -> (REPEAT)
  |                                    |
  +------------------------------------+

AUTO-RESUME PROTOCOL:
┌─────────────────────────────────────────────────────────────────┐
│  Session Start                                                  │
│       │                                                         │
│       ▼                                                         │
│  Check .builder/state.json exists?                              │
│       │                                                         │
│       ├─ NO → Initialize new project                            │
│       │                                                         │
│       └─ YES → Resume from saved state:                         │
│              1. Read current_phase                               │
│              2. Read current_feature                             │
│              3. Read pending_features[]                          │
│              4. Continue from last checkpoint                    │
│                                                                 │
│  After each feature completion:                                 │
│       │                                                         │
│       ▼                                                         │
│  More pending features?                                         │
│       │                                                         │
│       ├─ YES → Auto-start next feature (NO user input needed)   │
│       │                                                         │
│       └─ NO → All complete! Generate report                     │
└─────────────────────────────────────────────────────────────────┘

{
  "auto_continue": true,
  "resume_token": "feat-003-phase-implement",
  "next_action": "Continue implementing feat-003",
  "features_remaining": 3,
  "estimated_completion": "2026-02-14T18:00:00Z"
}

# After completing a feature, automatically proceed:

def on_feature_complete(feature_id: str, state: ProjectState):
    """Called when a feature is marked complete."""

    # 1. Save checkpoint
    save_checkpoint(state, feature_id)

    # 2. Update feature status
    state.features[feature_id].status = "completed"
    state.features[feature_id].completed_at = datetime.now()

    # 3. Check for pending features
    pending = [f for f in state.features if f.status == "pending"]

    if pending:
        # 4. Auto-select next feature (NO user input)
        next_feature = select_next_feature(pending, state)
        state.current_feature = next_feature.id
        state.current_phase = "implement"

        # 5. Save state immediately
        save_state(state)

        # 6. LOG and CONTINUE (not ask user)
        log_progress(f"Auto-continuing to {next_feature.name}")
        return ContinueAction(feature=next_feature)
    else:
        # All complete!
        return CompleteAction(report=generate_final_report(state))

## 🔄 Session Resume Detected

**Previous Session**: Session #5
**Last Activity**: 2 hours ago
**Current Feature**: feat-003 (User Authentication)
**Phase**: implement (60% complete)

**Pending Features**: 3 remaining
- feat-004: API Rate Limiting
- feat-005: Email Notifications
- feat-006: Final Documentation

**Auto-Continuing**: Resuming feat-003 implementation...

[Proceeding without user input - type "pause" to stop]

.builder/
├── state.json           # Current project state
├── features.json        # Feature list with status
├── architecture.md      # Design decisions
├── progress.md          # Session log
├── errors.json          # Error history and resolutions
├── checkpoints/         # Recovery checkpoints
├── auto-continue.{sh,bat,ps1}  # Auto-restart script (auto-generated)
└── supervisor.json      # Self-supervision config

ON PROJECT INITIALIZATION:

1. Check for Claude_Skills_中文指南.md in workspace root
2. If found:
   - Read and parse skill catalog
   - Store available skills in state.json
3. For each feature:
   - Analyze feature requirements
   - Match against skill catalog
   - Add recommended_skills to feature definition

DURING IMPLEMENTATION:

1. Before each implementation step:
   - Check step's invoke_skill field
   - Or analyze step for skill match

2. Auto-invoke skill:
   - Use Skill tool with skill: {skill_name}
   - Execute with skill's guidance
   - Continue with enhanced capabilities

3. Log skill usage to state.json

{
  "id": "feat-001",
  "name": "Data Analysis Module",
  "recommended_skills": [
    {"skill": "exploratory-data-analysis", "phase": "implementation"},
    {"skill": "data-artist", "phase": "implementation"}
  ],
  "skill_dispatch_schedule": [
    {"step": 1, "action": "Explore data", "invoke_skill": "exploratory-data-analysis"},
    {"step": 2, "action": "Create charts", "invoke_skill": "data-artist"}
  ]
}

ON SESSION START:

1. DISCOVER MCP servers
   - Run /mcp to list configured servers
   - Parse available tools from each server
   - Build capability map

2. CHECK critical capabilities:
   - browser_automation (puppeteer)
   - code_execution (ide)
   - desktop_control (desktop) - optional

3. AUTO-INSTALL missing servers if needed:
   - For web projects: puppeteer
   - For desktop apps: desktop
   - For database work: sqlite/postgres

4. UPDATE state.json → mcp_integration

Task Pattern                    → MCP Tool
─────────────────────────────────────────────
"open website/url"              → mcp__puppeteer_navigate
"click button/element"          → mcp__puppeteer_click
"fill form/type text"           → mcp__puppeteer_type
"take screenshot"               → mcp__puppeteer_screenshot
"run JavaScript"                → mcp__puppeteer_evaluate
"control mouse"                 → mcp__desktop_mouse_move
"press key/hotkey"              → mcp__desktop_hotkey
"execute Python"                → mcp__ide__executeCode

## E2E Test Flow (Automatic)

1. mcp__puppeteer_navigate → "https://myapp.com"
2. mcp__puppeteer_screenshot → capture initial state
3. mcp__puppeteer_fill → "#username", "testuser"
4. mcp__puppeteer_click → "#submit"
5. mcp__puppeteer_wait → ".dashboard"
6. mcp__puppeteer_evaluate → verify page state
7. mcp__puppeteer_screenshot → capture result

ON PROJECT INITIALIZATION:
1. Create .builder/ directory
2. Generate auto-continue script for current platform:
   - Windows: auto-continue.ps1
   - Linux/macOS: auto-continue.sh
3. Create supervisor.json with monitoring config
4. Script runs in background, monitors session health

#!/bin/bash
# .builder/auto-continue.sh - Auto-generated by autonomous-builder

PROJECT_DIR="/path/to/project"
BUILDER_DIR="$PROJECT_DIR/.builder"
STATE_FILE="$BUILDER_DIR/state.json"
SUPERVISOR_CONFIG="$BUILDER_DIR/supervisor.json"

# Self-supervision loop
while true; do
    # Check if project is complete
    if [ -f "$STATE_FILE" ]; then
        STATUS=$(grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' "$STATE_FILE" | head -1 | cut -d'"' -f4)
        if [ "$STATUS" = "completed" ]; then
            echo "[$(date)] Project completed. Exiting supervisor."
            exit 0
        fi
    fi

    # Check last activity (if no activity for 5 min, restart)
    LAST_ACTIVITY=$(grep -o '"last_activity"[[:space:]]*:[[:space:]]*"[^"]*"' "$STATE_FILE" | cut -d'"' -f4)
    if [ -n "$LAST_ACTIVITY" ]; then
        # Parse and check timeout...
        # If timeout exceeded, trigger new session
    fi

    # Start/resume Claude session with permission bypass for unattended operation
    # WARNING: --dangerously-skip-permissions bypasses all user confirmations
    echo "[$(date)] Starting Claude session..."
    claude --skill autonomous-builder --project "$PROJECT_DIR" --dangerously-skip-permissions

    # Log session end
    echo "[$(date)] Session ended. Checking state..."

    # Wait before restart (configurable)
    sleep 5
done

{
  "supervisor_version": "1.0",
  "project_path": "/path/to/project",
  "enabled": true,

  "monitoring": {
    "check_interval_seconds": 60,
    "session_timeout_seconds": 300,
    "max_restart_attempts": 10,
    "restart_cooldown_seconds": 5
  },

  "health_checks": {
    "progress_stall_threshold": 600,
    "error_rate_threshold": 0.5,
    "context_usage_warning": 0.8
  },

  "notifications": {
    "on_completion": true,
    "on_error_spike": true,
    "on_stall": true,
    "log_file": ".builder/supervisor.log"
  },

  "statistics": {
    "total_sessions": 0,
    "total_restarts": 0,
    "total_runtime_seconds": 0,
    "last_restart_time": null
  }
}

{
  "project_name": "string",
  "current_phase": "init|design|implement|test|deploy",
  "current_feature": "feature-id",
  "tech_stack": {
    "language": "string",
    "framework": "string",
    "runtime": "string"
  },
  "completed_features": ["feat-001"],
  "pending_features": ["feat-002"],
  "session_count": 0,
  "last_activity": "ISO-8601-timestamp"
}

STRIKE 1: Direct Fix
  - Analyze error type and root cause
  - Apply known solution pattern
  - Run tests to verify

STRIKE 2: Alternative Approach
  - Try different library/algorithm
  - Simplify implementation
  - Use different design pattern

STRIKE 3: Architecture Rethink
  - Question design assumptions
  - Research alternatives
  - Consider partial implementation

AFTER 3 STRIKES: Save checkpoint, request user guidance

DETECTION RULES:
┌─────────────────────────────────────────────────────────────────┐
│  Condition                    │ Threshold │ Action              │
├─────────────────────────────────────────────────────────────────┤
│  Same error repeated          │ 3 times   │ ESCALATE immediately│
│  Same file modified           │ 5 times   │ STOP, review approach│
│  Same command executed        │ 3 times   │ Try alternative     │
│  No progress in N operations  │ 10 ops    │ PAUSE, reassess     │
│  Single session too long      │ 50 turns  │ Checkpoint & pause  │
└─────────────────────────────────────────────────────────────────┘

class LoopDetector:
    MAX_SAME_ERROR = 3        # Same error appears 3 times
    MAX_SAME_FILE_EDIT = 5    # Same file edited 5 times
    MAX_SAME_COMMAND = 3      # Same command run 3 times
    MAX_NO_PROGRESS = 10      # No feature completed in 10 ops
    MAX_SESSION_TURNS = 50    # Maximum turns per session

    def check_loop(self, state):
        # Check 1: Same error repeating
        if self.count_same_error(state.errors) >= self.MAX_SAME_ERROR:
            return LoopAlert("SAME_ERROR_LOOP", "Escalate to user")

        # Check 2: Same file being edited repeatedly
        if self.count_same_file_edits(state.recent_edits) >= self.MAX_SAME_FILE_EDIT:
            return LoopAlert("FILE_EDIT_LOOP", "Review approach")

        # Check 3: Same command executing repeatedly
        if self.count_same_commands(state.recent_commands) >= self.MAX_SAME_COMMAND:
            return LoopAlert("COMMAND_LOOP", "Try alternative")

        # Check 4: No progress indicator
        if self.count_operations_without_progress(state) >= self.MAX_NO_PROGRESS:
            return LoopAlert("NO_PROGRESS", "Reassess strategy")

        # Check 5: Session too long
        if state.session_turns >= self.MAX_SESSION_TURNS:
            return LoopAlert("SESSION_LIMIT", "Create checkpoint and pause")

        return None  # No loop detected

## LOOP ALERT: [Type]

**Detected Pattern**: [What repeated]
**Occurrences**: [Count] times
**Time Spent**: [Duration]
**Token Estimate**: [Approximate tokens used]

**Actions Taken**:
1. Stopped current operation
2. Saved checkpoint to .builder/checkpoints/
3. Logged loop pattern to .builder/loop-log.json

**Status**: PAUSED - Awaiting user input

**Options**:
A) Skip this feature and continue with next
B) Accept partial implementation
C) Provide additional context/guidance
D) Abort and generate report

{
  "loop_detection": {
    "error_history": [
      {"error_hash": "abc123", "count": 2, "first_seen": "...", "last_seen": "..."}
    ],
    "file_edit_history": [
      {"file": "src/app.py", "edit_count": 3, "last_edit": "..."}
    ],
    "command_history": [
      {"command": "npm test", "run_count": 2, "last_run": "..."}
    ],
    "progress_check": {
      "operations_since_last_feature": 5,
      "last_completed_feature": "feat-002",
      "last_completion_time": "..."
    },
    "session_metrics": {
      "start_time": "...",
      "turn_count": 25,
      "tokens_estimated": 50000
    }
  }
}

After every 20 operations:
  └─ Check progress: Did any feature advance?
      ├─ YES: Continue
      └─ NO: Pause and reassess

After every 10 minutes:
  └─ Review: Are we making meaningful progress?
      ├─ YES: Continue
      └─ NO: Checkpoint and evaluate

On same error 2nd occurrence:
  └─ Warning: Same error detected, trying different approach
  └─ Log: Record pattern for analysis

On same error 3rd occurrence:
  └─ STOP: Loop detected, escalate to user
  └─ Save: Create checkpoint before pause

SEGMENT_SIZE = 200  # lines per segment

# First segment: create file
write_file(path, first_segment)

# Subsequent segments: append
edit_file(path, append=next_segment)

def detect_tech_stack(project_path):
    indicators = {
        'python': ['requirements.txt', 'pyproject.toml', '*.py'],
        'nodejs': ['package.json', '*.ts', '*.js'],
        'rust': ['Cargo.toml', '*.rs'],
        'go': ['go.mod', '*.go'],
    }
    # Auto-detect and return primary stack

Before ANY operation, verify:

1. IS TARGET INSIDE WORKSPACE?
   ✅ Path starts with project root -> Proceed
   ⚠️ Path outside workspace -> STOP and confirm

2. IS OPERATION DESTRUCTIVE?
   ✅ Read/Write/Create in workspace -> Proceed
   ⚠️ Delete/Format/Truncate -> STOP and confirm

3. IS OPERATION SYSTEM-WIDE?
   ✅ Project-local operation -> Proceed
   ⚠️ Global install/System config -> STOP and confirm

4. COULD DATA BE LOST?
   ✅ New file creation -> Proceed
   ⚠️ Overwrite/Delete existing -> STOP and backup first

System directories:
- Windows: C:\Windows\, C:\Program Files\, C:\Program Files (x86)\
- Linux: /etc/, /usr/, /var/, /root/, /home/ (other users)
- macOS: /System/, /Library/, /Applications/

User data outside workspace:
- Desktop, Documents, Downloads (outside project)
- Any path containing "backup", "archive", "important"
- Database files not in project directory
- Configuration files: .bashrc, .zshrc, .gitconfig (global)

IF operation touches files outside workspace:
  1. STOP execution immediately
  2. Display warning to user:
     "⚠️ SAFETY ALERT: This operation affects files outside the workspace"
     - Target path: [full path]
     - Operation type: [read/write/delete]
     - Potential impact: [description]
  3. Ask for explicit confirmation:
     "Do you want to proceed? This action cannot be undone."
  4. If user declines -> Abort and suggest alternatives
  5. If user approves -> Log the approval and proceed cautiously

IF operation could cause data loss:
  1. Create backup before proceeding
  2. Log the operation to .builder/safety-log.json
  3. Provide rollback instructions

## E2E Test Pattern
1. Launch browser: mcp__puppeteer_navigate
2. Interact: mcp__puppeteer_click, mcp__puppeteer_type
3. Verify: mcp__puppeteer_evaluate, mcp__puppeteer_screenshot
4. Cleanup: mcp__puppeteer_close

## Code Execution Pattern
1. Write code to file
2. Execute: mcp__ide__executeCode
3. Check diagnostics: mcp__ide__getDiagnostics
4. Fix errors and retry

version: "1.0"
enabled: true

reporting:
  language: "zh-CN"
  detail_level: "detailed"
  output_dir: "docs/workflows"

skills:
  autonomous-builder:
    workflow_reporting: true

workflow_reporting:
  enabled: true
  use_unified_template: true
  language: "zh-CN"
  detail_level: "detailed"
  record_all_tools: true
  record_decisions: true

{
  "session_id": "session-2026-02-15-001",
  "feature_id": "feat-003",
  "start_time": "2026-02-15T14:00:00Z",
  "end_time": "2026-02-15T14:45:00Z",
  "user_prompts": [
    {
      "timestamp": "2026-02-15T14:00:00Z",
      "prompt": "实现用户认证功能",
      "context": "用户希望添加JWT token验证"
    }
  ],
  "workflow_steps": [
    {
      "step": 1,
      "action": "分析需求",
      "tool": "Read",
      "files": ["server/auth.ts"],
      "duration_seconds": 120
    }
  ],
  "decisions": [
    {
      "point": "选择认证方案",
      "options": ["JWT", "Session", "OAuth"],
      "chosen": "JWT",
      "reason": "无状态，适合API"
    }
  ],
  "errors": [
    {
      "type": "TypeError",
      "message": "Cannot read property 'userId'",
      "solution": "更新User接口定义",
      "attempts": 2
    }
  ]
}

feat: 实现用户认证功能

添加了JWT token验证和用户登录API端点。

工作流步骤: 8
决策点: 3
遇到错误: 2
调试迭代: 4

详见工作流报告: docs/workflows/2026-02/15_workflow_feature_user-auth.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

# Windows
winget install GitHub.cli

# macOS
brew install gh

# Linux
sudo apt install gh

gh auth login
gh auth status  # Verify

feat: 实现用户认证功能

添加了JWT token验证和用户登录API端点。

工作流步骤: 8
决策点: 3
遇到错误: 2
调试迭代: 4

详见工作流报告: docs/workflows/2026-02/15_workflow_feature_user-auth.md

Closes #123

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

# Rollback to previous feature
git log --oneline
git reset --hard <commit_hash>
git push --force origin main
gh issue reopen <issue_number>

# Rollback to release tag
git checkout v0.1.0
git checkout -b rollback-to-v0.1.0

ON SESSION START (Step 0 - 在 Step 1 之前执行):

1. 使用 ToolSearch 探测所有可用插件:
   - ToolSearch("+playwright") → 浏览器自动化工具
   - ToolSearch("+github") → GitHub 操作工具
   - ToolSearch("+serena") → 代码语义分析工具
   - ToolSearch("context7") → 文档查询工具
   - ToolSearch("getDiagnostics") → IDE 诊断工具
   - ToolSearch("executeCode") → 代码执行工具

2. 构建能力矩阵并存入 .builder/state.json:
   {
     "discovered_plugins": {
       "playwright": true/false,
       "github_mcp": true/false,
       "serena": true/false,
       "context7": true/false,
       "ide_diagnostics": true/false,
       "ide_execute": true/false
     },
     "last_discovery": "ISO-8601-timestamp"
   }

3. 根据发现的插件调整工作流策略

DURING FEATURE IMPLEMENTATION:

1. 代码分析阶段:
   IF serena 可用:
     → ToolSearch("+serena find_symbol") 定位目标符号
     → ToolSearch("+serena find_referencing_symbols") 分析影响范围
     → ToolSearch("+serena get_symbols_overview") 理解文件结构
   ELSE:
     → 回退到 Grep + Read 方式

2. 代码编辑阶段:
   IF serena 可用:
     → ToolSearch("+serena replace_symbol_body") 精确替换符号
     → ToolSearch("+serena insert_after_symbol") 插入新代码
   ELSE:
     → 回退到 Edit 工具

3. 测试阶段:
   IF playwright 可用:
     → ToolSearch("+playwright navigate") 打开应用
     → ToolSearch("+playwright snapshot") 获取页面状态
     → ToolSearch("+playwright click") 模拟交互
     → ToolSearch("+playwright browser_evaluate") 执行 JS 验证
   ELSE IF puppeteer 可用:
     → 使用 puppeteer MCP 工具
   ELSE:
     → 回退到 Bash 执行测试命令

4. 文档查询阶段:
   IF context7 可用:
     → ToolSearch("context7") 查询库文档
     → 获取最新 API 用法和最佳实践
   ELSE:
     → 使用 WebSearch/WebFetch

5. 代码质量检查:
   IF ide_diagnostics 可用:
     → ToolSearch("getDiagnostics") 获取诊断
     → 在提交前修复所有错误和警告
   ELSE:
     → 使用 Bash 运行 linter/type-checker

旧方式 (静态):
  ON SESSION START → 运行 /mcp → 解析工具列表 → 硬编码工具名

新方式 (动态 ToolSearch):
  ON NEED → ToolSearch(关键词) → 发现工具 → 立即使用

优势:
  - 无需预先知道工具名称
  - 自动适应不同环境的插件配置
  - 按需加载，减少上下文占用
  - 关键词搜索比精确名称更灵活