59 lines
1.9 KiB
Markdown
59 lines
1.9 KiB
Markdown
|
# Task ID: 36
|
||
|
|
|
||
|
|
**Title:** End-to-end integration testing
|
||
|
|
|
||
|
|
**Status:** done
|
||
|
|
|
||
|
|
**Dependencies:** 29 ✓, 33 ✓, 34 ✓, 35 ✓
|
||
|
|
|
||
|
|
**Priority:** high
|
||
|
|
|
||
|
|
**Description:** Create comprehensive integration tests that validate the full data flow from mcpctl through mcplocal to mcpd to MCP server containers and back.
|
||
|
|
|
||
|
|
**Details:**
|
||
|
|
|
||
|
|
1. Create test fixtures in `src/mcplocal/test/fixtures/`:
|
||
|
|
- Mock MCP server that returns predictable responses
|
||
|
|
- Test configuration files
|
||
|
|
- Sample tool call payloads
|
||
|
|
2. Create integration test suite in `src/mcplocal/test/integration/`:
|
||
|
|
```typescript
|
||
|
|
describe('End-to-end flow', () => {
|
||
|
|
it('mcpctl -> mcplocal -> mcpd -> mcp_server', async () => {
|
||
|
|
// Start mock MCP server
|
||
|
|
// Start mcpd with test config
|
||
|
|
// Start mcplocal pointing to mcpd
|
||
|
|
// Execute mcpctl command
|
||
|
|
// Verify response flows back correctly
|
||
|
|
});
|
||
|
|
|
||
|
|
it('LLM pre-processing reduces response size', async () => {
|
||
|
|
// Send query that returns large dataset
|
||
|
|
// Verify LLM filtering reduces token count
|
||
|
|
// Verify relevant data is preserved
|
||
|
|
});
|
||
|
|
|
||
|
|
it('credentials never leave mcpd', async () => {
|
||
|
|
// Monitor all traffic from mcplocal
|
||
|
|
// Verify no credentials appear in requests/responses
|
||
|
|
});
|
||
|
|
});
|
||
|
|
```
|
||
|
|
3. Test scenarios:
|
||
|
|
- Management commands (get servers, instances, etc.)
|
||
|
|
- MCP tool calls with LLM preprocessing
|
||
|
|
- MCP tool calls without preprocessing
|
||
|
|
- Error handling (mcpd down, instance down, LLM failure)
|
||
|
|
- Health monitoring accuracy
|
||
|
|
4. Add CI integration test workflow
|
||
|
|
5. Create docker-compose.test.yml for test environment
|
||
|
|
|
||
|
|
**Test Strategy:**
|
||
|
|
|
||
|
|
1. All integration tests pass in CI environment
|
||
|
|
2. Test coverage includes happy path and error scenarios
|
||
|
|
3. Performance benchmarks: measure latency at each tier
|
||
|
|
4. Security test: verify credential isolation
|
||
|
|
5. Load test: multiple concurrent requests
|
||
|
|
6. Chaos test: random component failures
|