User/Agent      ──────▶│   Flexus L Instance   │──────▶│   JiuwenSwarm App    │──────▶│ Model Config     │ ──────▶│  Channel Config     │ 
(Skill caller)           (Target Host)                 (Multi-Agent Platform)           (API_BASE/KEY)            (Xiaoyi/Feishu/Dingtalk)            

Phase 1: Environment Preparation → Phase 2: Create Instance → Phase 3: Install Dependencies → COC Status Query → Phase 4: Deploy Service → COC Status Query → Phase 5: Verify Deployment → Phase 6: Model Configuration → Phase 7: Message Channel Configuration

============================================================
⚠️ Cloud Resource Creation Confirmation
============================================================
Operation to be executed: Create new Flexus L instance

Instance Specifications:
  - Name: {instance_name}
  - Flavor: {flavor}
  - Region: {region}
  - Estimated Cost: ~100 RMB/month (actual price subject to Huawei Cloud pricing)

Resources will be created immediately after confirmation.
Please reply "confirm" or "agree" to continue.
============================================================

1. Verify Huawei Cloud credentials (AK/SK)
2. Set environment variable: PYTHONIOENCODING=utf-8
3. Check dependency modules: requests, huaweicloudsdkcore, huaweicloudsdkcoc, huaweicloudsdkrms
4. Validate credential validity (via IAM API)

⚠️ The following steps can only be executed after obtaining customer confirmation!

1. Display instance configuration information to customer (name, flavor, region, estimated cost)
2. Wait for customer confirmation (reply "confirm" or "agree")
3. After confirmation, execute:
   - Get Project ID (via IAM API)
   - Call Flexus L create API
   - Save order_id for subsequent queries
   - Wait for instance creation to complete (poll RMS API)
   - Get instance information: instance_id, public_ip, ecs_instance_id

Based on instance information from Phase 2: instance_id, public_ip, ecs_instance_id, execute:
1. Execute dependency installation script via COC
2. Install base tools: git, curl, vim, wget, net-tools, etc.
3. Check Python and Node.js environment
4. Wait for deployment to complete. Note: script execution takes approximately 8 minutes. Please be patient. Only retry if script execution errors occur.

1. Read deployment script template (assets/deploy_script_template.sh)
2. Execute complete deployment script on instance via COC
3. Install JiuwenSwarm and related dependencies
4. Configure systemd service
5. Start JiuwenSwarm service
6. Wait for deployment to complete. Note: script execution takes approximately 15 minutes. Please be patient. Only retry if script execution errors occur.

1. Query COC deployment task status
2. Verify port 5173 listening
3. Check service health status
4. Output web access URL

1. Interactively collect model configuration information:
   - API_BASE: Model API URL
   - API_KEY: Model API key
   - MODEL_NAME: Model name
   - MODEL_PROVIDER: Model provider
2. Generate configuration script (COC remote execution):
   - Backup original .env file
   - Update only four core parameters (API_BASE, API_KEY, MODEL_NAME, MODEL_PROVIDER)
   - Keep other configuration parameters unchanged
   - Set file permission to 600
3. Restart JiuwenSwarm service

1. Select channel type: xiaoyi / feishu / dingtalk
2. Collect configuration information based on channel type:
   - xiaoyi: AK, SK, Agent ID
   - feishu: App ID, App Secret
   - dingtalk: Client ID, Client Secret, Allow From
3. Generate configuration script (COC remote execution):
   - Backup original config.yaml file
   - Update only key configuration fields for specified channel, keep other configurations unchanged
   - Xiaoyi: Update only ak, sk, agent_id, enabled
   - Feishu: Update only app_id, app_secret, enabled
   - DingTalk: Update only client_id, client_secret, allow_from, enabled
   - Set file permission to 644
4. Restart JiuwenSwarm service

1. Query task status by COC execution UUID
2. Support three query methods:
   - Direct query: python query_coc_status.py --uuid <execute_uuid>
   - Detailed output: python query_coc_status.py --uuid <execute_uuid> --verbose
   - Wait for completion: pythonquery_coc_status.py --uuid <execute_uuid> --wait
3. Load UUID from JSON file:
   - python query_coc_status.py --from-file new_instance_info.json
4. Return task status, duration, output results, etc.

COC task status query supports the following features:
1. Single query - Query current status of specified UUID task
2. Detailed output - Display script execution output
3. Wait for completion - Continuous polling until task completes or timeout
4. File loading - Read UUID from JSON file saved during deployment

Script location: scripts/query_coc_status.py

Usage examples:
  # Query single task status
  python query_coc_status.py --uuid SCT20250101000000000000000

  # Query with detailed output
  python query_coc_status.py --uuid SCT20250101000000000000000 --verbose

  # Wait for task completion
  python query_coc_status.py --uuid SCT20250101000000000000000 --wait

  # Custom wait time and polling interval
  python query_coc_status.py --uuid SCT20250101000000000000000 --wait --timeout 3600 --interval 30

  # Load UUID from JSON file
  python query_coc_status.py --from-file new_instance_info.json

COC Task Status Description:
| Status | Description |
|--------|-------------|
| READY | Ready |
| PROCESSING | Running, waiting required |
| FINISHED | Completed successfully |
| ABNORMAL | Execution abnormal, failed |
| CANCELED | Canceled |

============================================================
  JiuwenSwarm COC Deployment - Complete
============================================================

Target Instance:
  Name: {instance_name}
  ID: {instance_id}
  IP: {public_ip}

COC Execution:
  Execute UUID: {execute_uuid}
  Status: FINISHED

Deployment Result:
  Web Access: http://{public_ip}:5173
  Submit Time: {submit_time}

============================================================
[SUCCESS] Deployment task completed!
============================================================

============================================================
[ERROR] Deployment Failed
============================================================

Error: {error_message}

Suggestions:
  1. Check Huawei Cloud credentials
  2. Verify instance status
  3. Check deployment logs

============================================================

huawei-cloud-flexus-l-deploy-jiuwenSwarm/
├── SKILL.md                    # Skill documentation
├── requirements.txt            # Python dependency list
├── scripts/                    # Phased deployment scripts
│   ├── utils.py                # Utility functions
│   ├── prepare_env.py   # Environment preparation
│   ├── create_instance.py # Create Flexus L instance
│   ├── install_deps.py  # COC remote dependency installation
│   ├── deploy_service.py # COC remote service deployment
│   ├── verify_deployment.py # Verify deployment result
│   ├── config_model.py  # Model configuration
│   ├── config_channel.py # Message channel configuration
│   └── query_coc_status.py # COC task status query
├── assets/                     # Template files
│   ├── deploy_script_template.sh # Deployment script template
│   ├── jiuwenswarm.service.template # systemd service template
│   ├── config_template.yaml    # Configuration template
│   └── env.template            # Environment variable template
└── references/                 # Reference documents
    ├── api_specs.md            # API specifications
    ├── deployment_checklist.md # Deployment checklist
    ├── iam_policies.md         # IAM policies
    └── troubleshooting.md      # Troubleshooting guide

undefined

undefined

undefined

---