Files
ragflow/agent/sandbox/tests/MIGRATION_GUIDE.md
Zhichang Yu fd11aca8e5 feat: Implement pluggable multi-provider sandbox architecture (#12820)
## Summary

Implement a flexible sandbox provider system supporting both
self-managed (Docker) and SaaS (Aliyun Code Interpreter) backends for
secure code execution in agent workflows.

**Key Changes:**
-  Aliyun Code Interpreter provider using official
`agentrun-sdk>=0.0.16`
-  Self-managed provider with gVisor (runsc) security
-  Arguments parameter support for dynamic code execution
-  Database-only configuration (removed fallback logic)
-  Configuration scripts for quick setup

Issue #12479

## Features

### 🔌 Provider Abstraction Layer

**1. Self-Managed Provider** (`agent/sandbox/providers/self_managed.py`)
- Wraps existing executor_manager HTTP API
- gVisor (runsc) for secure container isolation
- Configurable pool size, timeout, retry logic
- Languages: Python, Node.js, JavaScript
- ⚠️ **Requires**: gVisor installation, Docker, base images

**2. Aliyun Code Interpreter**
(`agent/sandbox/providers/aliyun_codeinterpreter.py`)
- SaaS integration using official agentrun-sdk
- Serverless microVM execution with auto-authentication
- Hard timeout: 30 seconds max
- Credentials: `AGENTRUN_ACCESS_KEY_ID`, `AGENTRUN_ACCESS_KEY_SECRET`,
`AGENTRUN_ACCOUNT_ID`, `AGENTRUN_REGION`
- Automatically wraps code to call `main()` function

**3. E2B Provider** (`agent/sandbox/providers/e2b.py`)
- Placeholder for future integration

### ⚙️ Configuration System

- `conf/system_settings.json`: Default provider =
`aliyun_codeinterpreter`
- `agent/sandbox/client.py`: Enforces database-only configuration
- Admin UI: `/admin/sandbox-settings`
- Configuration validation via `validate_config()` method
- Health checks for all providers

### 🎯 Key Capabilities

**Arguments Parameter Support:**
All providers support passing arguments to `main()` function:
```python
# User code
def main(name: str, count: int) -> dict:
    return {"message": f"Hello {name}!" * count}

# Executed with: arguments={"name": "World", "count": 3}
# Result: {"message": "Hello World!Hello World!Hello World!"}
```

**Self-Describing Providers:**
Each provider implements `get_config_schema()` returning form
configuration for Admin UI

**Error Handling:**
Structured `ExecutionResult` with stdout, stderr, exit_code,
execution_time

## Configuration Scripts

Two scripts for quick Aliyun sandbox setup:

**Shell Script (requires jq):**
```bash
source scripts/configure_aliyun_sandbox.sh
```

**Python Script (interactive):**
```bash
python3 scripts/configure_aliyun_sandbox.py
```

## Testing

```bash
# Unit tests
uv run pytest agent/sandbox/tests/test_providers.py -v

# Aliyun provider tests
uv run pytest agent/sandbox/tests/test_aliyun_codeinterpreter.py -v

# Integration tests (requires credentials)
uv run pytest agent/sandbox/tests/test_aliyun_codeinterpreter_integration.py -v

# Quick SDK validation
python3 agent/sandbox/tests/verify_sdk.py
```

**Test Coverage:**
- 30 unit tests for provider abstraction
- Provider-specific tests for Aliyun
- Integration tests with real API
- Security tests for executor_manager

## Documentation

- `docs/develop/sandbox_spec.md` - Complete architecture specification
- `agent/sandbox/tests/MIGRATION_GUIDE.md` - Migration from legacy
sandbox
- `agent/sandbox/tests/QUICKSTART.md` - Quick start guide
- `agent/sandbox/tests/README.md` - Testing documentation

## Breaking Changes

⚠️ **Migration Required:**

1. **Directory Move**: `sandbox/` → `agent/sandbox/`
   - Update imports: `from sandbox.` → `from agent.sandbox.`

2. **Mandatory Configuration**: 
   - SystemSettings must have `sandbox.provider_type` configured
   - Removed fallback default values
- Configuration must exist in database (from
`conf/system_settings.json`)

3. **Aliyun Credentials**:
   - Requires `AGENTRUN_*` environment variables (not `ALIYUN_*`)
   - `AGENTRUN_ACCOUNT_ID` is now required (Aliyun primary account ID)

4. **Self-Managed Provider**:
   - gVisor (runsc) must be installed for security
   - Install: `go install gvisor.dev/gvisor/runsc@latest`

## Database Schema Changes

```python
# SystemSettings.value: CharField → TextField
api/db/db_models.py: Changed for unlimited config length

# SystemSettingsService.get_by_name(): Fixed query precision
api/db/services/system_settings_service.py: startswith → exact match
```

## Files Changed

### Backend (Python)
- `agent/sandbox/providers/base.py` - SandboxProvider ABC interface
- `agent/sandbox/providers/manager.py` - ProviderManager
- `agent/sandbox/providers/self_managed.py` - Self-managed provider
- `agent/sandbox/providers/aliyun_codeinterpreter.py` - Aliyun provider
- `agent/sandbox/providers/e2b.py` - E2B provider (placeholder)
- `agent/sandbox/client.py` - Unified client (enforces DB-only config)
- `agent/tools/code_exec.py` - Updated to use provider system
- `admin/server/services.py` - SandboxMgr with registry & validation
- `admin/server/routes.py` - 5 sandbox API endpoints
- `conf/system_settings.json` - Default: aliyun_codeinterpreter
- `api/db/db_models.py` - TextField for SystemSettings.value
- `api/db/services/system_settings_service.py` - Exact match query

### Frontend (TypeScript/React)
- `web/src/pages/admin/sandbox-settings.tsx` - Settings UI
- `web/src/services/admin-service.ts` - Sandbox service functions
- `web/src/services/admin.service.d.ts` - Type definitions
- `web/src/utils/api.ts` - Sandbox API endpoints

### Documentation
- `docs/develop/sandbox_spec.md` - Architecture spec
- `agent/sandbox/tests/MIGRATION_GUIDE.md` - Migration guide
- `agent/sandbox/tests/QUICKSTART.md` - Quick start
- `agent/sandbox/tests/README.md` - Testing guide

### Configuration Scripts
- `scripts/configure_aliyun_sandbox.sh` - Shell script (jq)
- `scripts/configure_aliyun_sandbox.py` - Python script

### Tests
- `agent/sandbox/tests/test_providers.py` - 30 unit tests
- `agent/sandbox/tests/test_aliyun_codeinterpreter.py` - Provider tests
- `agent/sandbox/tests/test_aliyun_codeinterpreter_integration.py` -
Integration tests
- `agent/sandbox/tests/verify_sdk.py` - SDK validation

## Architecture

```
Admin UI → Admin API → SandboxMgr → ProviderManager → [SelfManaged|Aliyun|E2B]
                                      ↓
                                  SystemSettings
```

## Usage

### 1. Configure Provider

**Via Admin UI:**
1. Navigate to `/admin/sandbox-settings`
2. Select provider (Aliyun Code Interpreter / Self-Managed)
3. Fill in configuration
4. Click "Test Connection" to verify
5. Click "Save" to apply

**Via Configuration Scripts:**
```bash
# Aliyun provider
export AGENTRUN_ACCESS_KEY_ID="xxx"
export AGENTRUN_ACCESS_KEY_SECRET="yyy"
export AGENTRUN_ACCOUNT_ID="zzz"
export AGENTRUN_REGION="cn-shanghai"
source scripts/configure_aliyun_sandbox.sh
```

### 2. Restart Service

```bash
cd docker
docker compose restart ragflow-server
```

### 3. Execute Code in Agent

```python
from agent.sandbox.client import execute_code

result = execute_code(
    code='def main(name: str) -> dict: return {"message": f"Hello {name}!"}',
    language="python",
    timeout=30,
    arguments={"name": "World"}
)

print(result.stdout)  # {"message": "Hello World!"}
```

## Troubleshooting

### "Container pool is busy" (Self-Managed)
- **Cause**: Pool exhausted (default: 1 container in `.env`)
- **Fix**: Increase `SANDBOX_EXECUTOR_MANAGER_POOL_SIZE` to 5+

### "Sandbox provider type not configured"
- **Cause**: Database missing configuration
- **Fix**: Run config script or set via Admin UI

### "gVisor not found"
- **Cause**: runsc not installed
- **Fix**: `go install gvisor.dev/gvisor/runsc@latest && sudo cp
~/go/bin/runsc /usr/local/bin/`

### Aliyun authentication errors
- **Cause**: Wrong environment variable names
- **Fix**: Use `AGENTRUN_*` prefix (not `ALIYUN_*`)

## Checklist

- [x] All tests passing (30 unit tests + integration tests)
- [x] Documentation updated (spec, migration guide, quickstart)
- [x] Type definitions added (TypeScript)
- [x] Admin UI implemented
- [x] Configuration validation
- [x] Health checks implemented
- [x] Error handling with structured results
- [x] Breaking changes documented
- [x] Configuration scripts created
- [x] gVisor requirements documented

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

---------

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-28 13:28:21 +08:00

7.4 KiB
Raw Blame History

Aliyun Code Interpreter Provider - 使用官方 SDK

重要变更

官方资源

使用官方 SDK 的优势

从手动 HTTP 请求迁移到官方 SDK (agentrun-sdk) 有以下优势:

1. 自动签名认证

  • SDK 自动处理 Aliyun API 签名(无需手动实现 Authorization 头)
  • 支持多种认证方式AccessKey、STS Token
  • 自动读取环境变量

2. 简化的 API

# 旧实现(手动 HTTP 请求)
response = requests.post(
    f"{DATA_ENDPOINT}/sandboxes/{sandbox_id}/execute",
    headers={"X-Acs-Parent-Id": account_id},
    json={"code": code, "language": "python"}
)

# 新实现(使用 SDK
sandbox = CodeInterpreterSandbox(template_name="python-sandbox", config=config)
result = sandbox.context.execute(code="print('hello')")

3. 更好的错误处理

  • 结构化的异常类型 (ServerError)
  • 自动重试机制
  • 详细的错误信息

主要变更

1. 文件重命名

旧文件名 新文件名 说明
aliyun_opensandbox.py aliyun_codeinterpreter.py 提供商实现
test_aliyun_provider.py test_aliyun_codeinterpreter.py 单元测试
test_aliyun_integration.py test_aliyun_codeinterpreter_integration.py 集成测试

2. 配置字段变更

旧配置OpenSandbox

{
  "access_key_id": "LTAI5t...",
  "access_key_secret": "...",
  "region": "cn-hangzhou",
  "workspace_id": "ws-xxxxx"
}

新配置Code Interpreter

{
  "access_key_id": "LTAI5t...",
  "access_key_secret": "...",
  "account_id": "1234567890...",  // 新增阿里云主账号ID必需
  "region": "cn-hangzhou",
  "template_name": "python-sandbox",  // 新增:沙箱模板名称
  "timeout": 30  // 最大 30 秒(硬限制)
}

3. 关键差异

特性 OpenSandbox Code Interpreter
API 端点 opensandbox.{region}.aliyuncs.com agentrun.{region}.aliyuncs.com (控制面)
API 版本 2024-01-01 2025-09-10
认证 需要 AccessKey 需要 AccessKey + 主账号ID
请求头 标准签名 需要 X-Acs-Parent-Id
超时限制 可配置 最大 30 秒(硬限制)
上下文 不支持 支持上下文Jupyter kernel

4. API 调用方式变更

旧实现(假设的 OpenSandbox

# 单一端点
API_ENDPOINT = "https://opensandbox.cn-hangzhou.aliyuncs.com"

# 简单的请求/响应
response = requests.post(
    f"{API_ENDPOINT}/execute",
    json={"code": "print('hello')", "language": "python"}
)

新实现Code Interpreter

# 控制面 API - 管理沙箱生命周期
CONTROL_ENDPOINT = "https://agentrun.cn-hangzhou.aliyuncs.com/2025-09-10"

# 数据面 API - 执行代码
DATA_ENDPOINT = "https://{account_id}.agentrun-data.cn-hangzhou.aliyuncs.com"

# 创建沙箱(控制面)
response = requests.post(
    f"{CONTROL_ENDPOINT}/sandboxes",
    headers={"X-Acs-Parent-Id": account_id},
    json={"templateName": "python-sandbox"}
)

# 执行代码(数据面)
response = requests.post(
    f"{DATA_ENDPOINT}/sandboxes/{sandbox_id}/execute",
    headers={"X-Acs-Parent-Id": account_id},
    json={"code": "print('hello')", "language": "python", "timeout": 30}
)

5. 迁移步骤

步骤 1: 更新配置

如果您之前使用的是 aliyun_opensandbox

旧配置:

{
  "name": "sandbox.provider_type",
  "value": "aliyun_opensandbox"
}

新配置:

{
  "name": "sandbox.provider_type",
  "value": "aliyun_codeinterpreter"
}

步骤 2: 添加必需的 account_id

在 Aliyun 控制台右上角点击头像,获取主账号 ID

  1. 登录 阿里云控制台
  2. 点击右上角头像
  3. 复制主账号 ID16 位数字)

步骤 3: 更新环境变量

# 新增必需的环境变量
export ALIYUN_ACCOUNT_ID="1234567890123456"

# 其他环境变量保持不变
export ALIYUN_ACCESS_KEY_ID="LTAI5t..."
export ALIYUN_ACCESS_KEY_SECRET="..."
export ALIYUN_REGION="cn-hangzhou"

步骤 4: 运行测试

# 单元测试(不需要真实凭据)
pytest agent/sandbox/tests/test_aliyun_codeinterpreter.py -v

# 集成测试(需要真实凭据)
pytest agent/sandbox/tests/test_aliyun_codeinterpreter_integration.py -v -m integration

文件变更清单

已完成

  • 创建 aliyun_codeinterpreter.py - 新的提供商实现
  • 更新 sandbox_spec.md - 规范文档
  • 更新 admin/services.py - 服务管理器
  • 更新 providers/__init__.py - 包导出
  • 创建 test_aliyun_codeinterpreter.py - 单元测试
  • 创建 test_aliyun_codeinterpreter_integration.py - 集成测试

📝 可选清理

如果您想删除旧的 OpenSandbox 实现:

# 删除旧文件(可选)
rm agent/sandbox/providers/aliyun_opensandbox.py
rm agent/sandbox/tests/test_aliyun_provider.py
rm agent/sandbox/tests/test_aliyun_integration.py

注意: 保留旧文件不会影响新功能,只是代码冗余。

API 参考

控制面 API沙箱管理

端点 方法 说明
/sandboxes POST 创建沙箱实例
/sandboxes/{id}/stop POST 停止实例
/sandboxes/{id} DELETE 删除实例
/templates GET 列出模板

数据面 API代码执行

端点 方法 说明
/sandboxes/{id}/execute POST 执行代码(简化版)
/sandboxes/{id}/contexts POST 创建上下文
/sandboxes/{id}/contexts/{ctx_id}/execute POST 在上下文中执行
/sandboxes/{id}/health GET 健康检查
/sandboxes/{id}/files GET/POST 文件读写
/sandboxes/{id}/processes/cmd POST 执行 Shell 命令

常见问题

Q: 为什么要添加 account_id

A: Code Interpreter API 需要在请求头中提供 X-Acs-Parent-Id阿里云主账号ID进行身份验证。这是 Aliyun Code Interpreter API 的必需参数。

Q: 30 秒超时限制可以绕过吗?

A: 不可以。这是 Aliyun Code Interpreter 的硬限制,无法通过配置或请求参数绕过。如果代码执行时间超过 30 秒,请考虑:

  1. 优化代码逻辑
  2. 分批处理数据
  3. 使用上下文保持状态

Q: 旧的 OpenSandbox 配置还能用吗?

A: 不能。OpenSandbox 和 Code Interpreter 是两个不同的服务API 不兼容。必须迁移到新的配置格式。

Q: 如何获取阿里云主账号 ID

A:

  1. 登录阿里云控制台
  2. 点击右上角的头像
  3. 在弹出的信息中可以看到"主账号ID"

Q: 迁移后会影响现有功能吗?

A:

  • 自我管理提供商self_managed: 不受影响
  • E2B 提供商: 不受影响
  • Aliyun 提供商: 需要更新配置并重新测试

相关文档

技术支持

如有问题,请:

  1. 查看官方文档
  2. 检查配置是否正确
  3. 查看测试输出中的错误信息
  4. 联系 RAGFlow 团队