┌─────────────────────────────────────────────────────────────┐
│                      Main Agent (Xiaoa)                        │
│  - Main session processing                                                 │
│  - Task distribution and coordination                                             │
│  - Complex decision-making and planning                                             │
│  - Model: opus-4.5 (High quality)                                    │
└─────────────────────────────────────────────────────────────┘
                              │
          ┌───────────────────┼───────────────────┐
          ▼                   ▼                   ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│   News Agent    │ │   Code Agent    │ │  Research Agent │
│  - News scraping     │ │  - Code generation     │ │  - In-depth research     │
│  - Content summarization     │ │  - Bug fixing     │ │  - Document analysis     │
│  - Scheduled push notifications     │ │  - Code review     │ │  - Knowledge integration     │
│  Model: sonnet   │ │  Model: codex    │ │  Model: opus     │
└─────────────────┘ └─────────────────┘ └─────────────────┘
          │                   │                   │
          ▼                   ▼                   ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│  Quick Agent    │ │  Batch Agent    │ │  Monitor Agent  │
│  - Quick Q&A     │ │  - Batch processing     │ │  - System monitoring     │
│  - Simple tasks     │ │  - Data processing     │ │  - Health check     │
│  - Low-latency response   │ │  - File operations     │ │  - Alert notifications     │
│  Model: flash    │ │  Model: mini     │ │  Model: mini     │
└─────────────────┘ └─────────────────┘ └─────────────────┘

~/.openclaw/agents/
├── main/           # Main Agent (Exists)
│   └── agent/
│       ├── AGENTS.md
│       ├── SOUL.md
│       └── ...
├── news/           # News Agent
│   └── agent/
│       ├── AGENTS.md
│       └── config.json
├── code/           # Code Agent
│   └── agent/
│       ├── AGENTS.md
│       └── config.json
├── research/       # Research Agent
│   └── agent/
│       ├── AGENTS.md
│       └── config.json
├── quick/          # Quick Response Agent
│   └── agent/
│       └── config.json
└── batch/          # Batch Processing Agent
    └── agent/
        └── config.json

{
  "model": {
    "primary": "anthropic/claude-sonnet-4-5"
  },
  "systemPrompt": "You are an expert in news scraping and summarization. Focus on:\n1. Scrape real news from authoritative sources\n2. Generate concise and accurate summaries\n3. Ensure each news item has the original link\n4. Push to specified channels on time",
  "tools": {
    "allow": ["web_fetch", "exec", "message"]
  }
}

{
  "model": {
    "primary": "openrouter-vip/gpt-5.2-codex"
  },
  "systemPrompt": "You are a code expert. Focus on:\n1. High-quality code generation\n2. Bug analysis and fixing\n3. Code review and optimization\n4. Technical documentation writing",
  "tools": {
    "allow": ["read", "write", "edit", "exec"]
  }
}

{
  "model": {
    "primary": "google/gemini-flash-latest"
  },
  "systemPrompt": "You are a quick response assistant. Features:\n1. Concise and direct answers\n2. Low-latency response\n3. Handle simple queries\n4. Tasks that do not require in-depth analysis"
}

{
  "agents": {
    "entries": {
      "news": {
        "enabled": true,
        "allowSpawnFrom": ["main"]
      },
      "code": {
        "enabled": true,
        "allowSpawnFrom": ["main"]
      },
      "research": {
        "enabled": true,
        "allowSpawnFrom": ["main"]
      },
      "quick": {
        "enabled": true,
        "allowSpawnFrom": ["main"]
      },
      "batch": {
        "enabled": true,
        "allowSpawnFrom": ["main"]
      }
    },
    "defaults": {
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }
}

# Add intelligent spawn logic in AGENTS.md

## 🧠 Intelligent Task Distribution

When receiving a task, evaluate the following factors:

1. **Task Complexity**
   - Simple queries → quick agent
   - Medium tasks → specialized agents
   - Complex tasks → handled by main or research agent

2. **Task Type**
   - News-related → news agent
   - Code-related → code agent
   - Research and analysis → research agent
   - Batch operations → batch agent

3. **Time Sensitivity**
   - Requires quick response → quick agent
   - Can wait → specialized agents

4. **Resource Consumption**
   - High token consumption → use agents with cheaper models
   - Requires high quality → use agents with opus

### Spawn Command Examples

```python
# News Task
sessions_spawn(
    task="Scrape today's tech news and push to the DailyNews group",
    agentId="news",
    label="news-morning"
)

# Code Task
sessions_spawn(
    task="Fix the login bug in auth.py",
    agentId="code",
    label="fix-auth-bug"
)

# Research Task
sessions_spawn(
    task="In-depth analysis of GPT-5's technical architecture",
    agentId="research",
    label="gpt5-analysis"
)

# Quick Query
sessions_spawn(
    task="Check today's weather",
    agentId="quick",
    label="weather-check"
)

{
  "agents": {
    "defaults": {
      "maxConcurrent": 4,      // Maximum concurrency for main agent
      "subagents": {
        "maxConcurrent": 8    // Maximum concurrency for sub agents
      }
    }
  }
}

User message → Main Agent
              │
              ├─→ spawn(news) ──→ Scrape news
              │
              ├─→ spawn(code) ──→ Fix bug
              │
              └─→ spawn(research) ──→ In-depth analysis
              
              ↓ (Executed in parallel)
              
         Report after all tasks are completed

{
  "channels": {
    "telegram": {
      "defaultAgent": "main"
    },
    "whatsapp": {
      "defaultAgent": "main"
    }
  },
  "agents": {
    "entries": {
      "news": {
        "channels": ["telegram-newsbot"]
      }
    }
  }
}

# List all sessions
openclaw sessions list

# View sessions for a specific agent
openclaw sessions list --agent news

# In code
sessions_list(kinds=["spawn"], limit=10)

# Set timeout when spawning
sessions_spawn(
    task="...",
    agentId="code",
    runTimeoutSeconds=300,  # 5-minute timeout
    cleanup="keep"          # Keep session for debugging
)