## 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>
Sandbox Provider Tests
This directory contains tests for the RAGFlow sandbox provider system.
Test Structure
tests/
├── pytest.ini # Pytest configuration
├── test_providers.py # Unit tests for all providers (mocked)
├── test_aliyun_provider.py # Unit tests for Aliyun provider (mocked)
├── test_aliyun_integration.py # Integration tests for Aliyun (real API)
└── sandbox_security_tests_full.py # Security tests for self-managed provider
Test Types
1. Unit Tests (No Credentials Required)
Unit tests use mocks and don't require any external services or credentials.
Files:
test_providers.py- Tests for base provider interface and managertest_aliyun_provider.py- Tests for Aliyun provider with mocked API calls
Run unit tests:
# Run all unit tests
pytest agent/sandbox/tests/test_providers.py -v
pytest agent/sandbox/tests/test_aliyun_provider.py -v
# Run specific test
pytest agent/sandbox/tests/test_aliyun_provider.py::TestAliyunOpenSandboxProvider::test_initialize_success -v
# Run all unit tests (skip integration)
pytest agent/sandbox/tests/ -v -m "not integration"
2. Integration Tests (Real Credentials Required)
Integration tests make real API calls to Aliyun OpenSandbox service.
Files:
test_aliyun_integration.py- Tests with real Aliyun API calls
Setup environment variables:
export ALIYUN_ACCESS_KEY_ID="LTAI5t..."
export ALIYUN_ACCESS_KEY_SECRET="..."
export ALIYUN_REGION="cn-hangzhou" # Optional, defaults to cn-hangzhou
export ALIYUN_WORKSPACE_ID="ws-..." # Optional
Run integration tests:
# Run only integration tests
pytest agent/sandbox/tests/test_aliyun_integration.py -v -m integration
# Run all tests including integration
pytest agent/sandbox/tests/ -v
# Run specific integration test
pytest agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_health_check -v
3. Security Tests
Security tests validate the security features of the self-managed sandbox provider.
Files:
sandbox_security_tests_full.py- Comprehensive security tests
Run security tests:
# Run all security tests
pytest agent/sandbox/tests/sandbox_security_tests_full.py -v
# Run specific security test
pytest agent/sandbox/tests/sandbox_security_tests_full.py -k "test_dangerous_imports" -v
Test Commands
Quick Test Commands
# Run all sandbox tests (unit only, fast)
pytest agent/sandbox/tests/ -v -m "not integration" --tb=short
# Run tests with coverage
pytest agent/sandbox/tests/ -v --cov=agent.sandbox --cov-report=term-missing -m "not integration"
# Run tests and stop on first failure
pytest agent/sandbox/tests/ -v -x -m "not integration"
# Run tests in parallel (requires pytest-xdist)
pytest agent/sandbox/tests/ -v -n auto -m "not integration"
Aliyun Provider Testing
# 1. Run unit tests (no credentials needed)
pytest agent/sandbox/tests/test_aliyun_provider.py -v
# 2. Set up credentials for integration tests
export ALIYUN_ACCESS_KEY_ID="your-key-id"
export ALIYUN_ACCESS_KEY_SECRET="your-secret"
export ALIYUN_REGION="cn-hangzhou"
# 3. Run integration tests (makes real API calls)
pytest agent/sandbox/tests/test_aliyun_integration.py -v
# 4. Test specific scenarios
pytest agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_execute_python_code -v
pytest agent/sandbox/tests/test_aliyun_integration.py::TestAliyunRealWorldScenarios -v
Understanding Test Results
Unit Test Output
agent/sandbox/tests/test_aliyun_provider.py::TestAliyunOpenSandboxProvider::test_initialize_success PASSED
agent/sandbox/tests/test_aliyun_provider.py::TestAliyunOpenSandboxProvider::test_create_instance_python PASSED
...
========================== 48 passed in 2.34s ===========================
Integration Test Output
agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_health_check PASSED
agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_create_python_instance PASSED
agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_execute_python_code PASSED
...
========================== 10 passed in 15.67s ===========================
Note: Integration tests will be skipped if credentials are not set:
agent/sandbox/tests/test_aliyun_integration.py::TestAliyunOpenSandboxIntegration::test_health_check SKIPPED
...
========================== 48 skipped, 10 passed in 0.12s ===========================
Troubleshooting
Integration Tests Fail
-
Check credentials:
echo $ALIYUN_ACCESS_KEY_ID echo $ALIYUN_ACCESS_KEY_SECRET -
Check network connectivity:
curl -I https://opensandbox.cn-hangzhou.aliyuncs.com -
Verify permissions:
- Make sure your Aliyun account has OpenSandbox service enabled
- Check that your AccessKey has the required permissions
-
Check region:
- Verify the region is correct for your account
- Try different regions: cn-hangzhou, cn-beijing, cn-shanghai, etc.
Tests Timeout
If tests timeout, increase the timeout in the test configuration or run with a longer timeout:
pytest agent/sandbox/tests/test_aliyun_integration.py -v --timeout=60
Mock Tests Fail
If unit tests fail, it's likely a code issue, not a credentials issue:
- Check the test error message
- Review the code changes
- Run with verbose output:
pytest -vv
Contributing
When adding new providers:
- Create unit tests in
test_{provider}_provider.pywith mocks - Create integration tests in
test_{provider}_integration.pywith real API calls - Add markers to distinguish test types
- Update this README with provider-specific testing instructions
Example:
@pytest.mark.integration
def test_new_provider_real_api():
"""Test with real API calls."""
# Your test here
Continuous Integration
In CI/CD pipelines:
# Run unit tests only (fast, no credentials)
pytest agent/sandbox/tests/ -v -m "not integration"
# Run integration tests if credentials available
if [ -n "$ALIYUN_ACCESS_KEY_ID" ]; then
pytest agent/sandbox/tests/test_aliyun_integration.py -v -m integration
fi