run-integration
Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AI_SDK_HOST, AI_SDK_TOKEN) and runs tests that make actual API calls.
소스 정보
- 저장소
- open-metadata/ai-sdk
- 최근 소스 활동
- 2026년 2월 25일 08:44
- 감지된 SKILL.md 언어
- 영어
- 스타
- 13
- 포크
- 4
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
SKILL.md 표시 중
SKILL.md
소스 지침 · 읽기 전용 미리보기- name
- run-integration
- description
- Use when running integration tests against a real Metadata instance. Guides setup of environment variables (AI_SDK_HOST, AI_SDK_TOKEN) and runs tests that make actual API calls.
# Run Integration Tests
Runs integration tests against a real Metadata instance. These tests use actual API calls.
## Usage
```
/run-integration [sdk]
```
Where `[sdk]` is optional: `python`, `typescript`, `java`, `cli`, `n8n`, or `all` (default).
## Prerequisites
Integration tests require environment variables:
- `AI_SDK_HOST` - Base URL of the Metadata instance (e.g., `https://your-instance.getcollate.io`)
- `AI_SDK_TOKEN` - Valid JWT token for authentication
- `AI_SDK_TEST_AGENT` - (Optional) Name of agent to test with
## Commands
### Run All Integration Tests
```bash
AI_SDK_HOST=https://... AI_SDK_TOKEN=... make test-integration
```
### Run Individual SDK Tests
**Python:**
```bash
cd python && AI_SDK_HOST=... AI_SDK_TOKEN=... pytest tests/integration/ -v
```
**TypeScript:**
```bash
cd typescript && AI_SDK_HOST=... AI_SDK_TOKEN=... npm run test:integration
```
**Java:**
```bash
cd java && AI_SDK_HOST=... AI_SDK_TOKEN=... mvn test -Dtest=IntegrationTest
```
**Rust CLI:**
```bash
cd cli && AI_SDK_HOST=... AI_SDK_TOKEN=... cargo test --test integration_test
```
**n8n:**
```bash
cd n8n-nodes-metadata && AI_SDK_HOST=... AI_SDK_TOKEN=... npm run test:integration
```
## What Integration Tests Verify
1. **Authentication** - Token is valid and accepted
2. **Agent Discovery** - Can list available agents
3. **Agent Invocation** - Can invoke an agent and get response
4. **Streaming** - SSE streaming works correctly (if `AI_SDK_RUN_CHAT_TESTS=true`)
5. **Error Handling** - Proper errors for invalid requests
## Troubleshooting
| Error | Cause | Fix |
|-------|-------|-----|
| 401 Unauthorized | Invalid/expired token | Get fresh token from Metadata UI |
| 404 Not Found | Agent doesn't exist | Check `AI_SDK_TEST_AGENT` value |
| Connection refused | Wrong host URL | Verify `AI_SDK_HOST` |
| Timeout | Network/firewall issue | Check connectivity |
## Notes
- Integration tests are **skipped in CI** unless secrets are configured
- Tests use real AI tokens when `AI_SDK_RUN_CHAT_TESTS=true`
- Always test locally before pushing changes that affect API calls
GitHub에서 보기