a869f77070
Merges feat/agent-project-membership (task 166/152). An agent can finally join many projects: membership routes, per-membership role and optional brain override, chat resolving context from the membership, and CLI attach-agent / detach-agent / get memberships. The legacy Agent.projectId fallback is kept for this release as the schema comment promises. Conflict resolved in main.ts: that branch added its RBAC case to mapUrlToPermission inline, while this branch had extracted the function to middleware/url-permission.ts so it could be tested. Kept the extraction and ported the case into it — joining a team is `edit:agents:<name>`, not `create:agents`, which is the authority to mint a whole agent. Also fixes something the extraction makes possible. security.test.ts contained a hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes main() and nothing in it was importable. A security test asserting against a copy stops testing the system the moment the real one changes, and this copy had already drifted. It now imports the real function; all 18 assertions still pass, against the code that actually runs. Local: build clean, workspace 2550 passed, lint unchanged at 794 errors. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p
62 lines
2.0 KiB
Markdown
62 lines
2.0 KiB
Markdown
# Task ID: 66
|
|
|
|
**Title:** Add unit tests for LLM prompt selection
|
|
|
|
**Status:** done
|
|
|
|
**Dependencies:** 46 ✓
|
|
|
|
**Priority:** high
|
|
|
|
**Description:** Create unit tests for the LLM-based prompt selection service covering LLM interactions, fallback behavior, and priority 10 handling.
|
|
|
|
**Details:**
|
|
|
|
1. Add tests in `/src/mcplocal/tests/services/llm-prompt-selector.test.ts`:
|
|
```typescript
|
|
describe('LlmPromptSelectorService', () => {
|
|
describe('priority 10 handling', () => {
|
|
it('always includes priority 10 prompts', async () => {
|
|
const result = await selector.selectPrompts(['unrelated'], promptIndex);
|
|
expect(result.priority10).toContain(priority10Prompt);
|
|
});
|
|
});
|
|
|
|
describe('LLM selection', () => {
|
|
it('sends tags and index to heavy LLM', async () => {
|
|
await selector.selectPrompts(['zigbee', 'mqtt'], promptIndex);
|
|
expect(mockLlm.complete).toHaveBeenCalledWith(
|
|
expect.stringContaining('zigbee')
|
|
);
|
|
});
|
|
|
|
it('parses LLM response correctly', async () => {
|
|
mockLlm.complete.mockResolvedValue(
|
|
'[{"name": "prompt1", "reason": "relevant"}]'
|
|
);
|
|
const result = await selector.selectPrompts(['test'], promptIndex);
|
|
expect(result.selected[0].name).toBe('prompt1');
|
|
});
|
|
});
|
|
|
|
describe('fallback behavior', () => {
|
|
it('falls back to tag matcher on LLM error', async () => { ... });
|
|
it('falls back on LLM timeout', async () => { ... });
|
|
it('falls back when no LLM available', async () => { ... });
|
|
});
|
|
|
|
describe('summary generation', () => {
|
|
it('generates missing summaries with fast LLM', async () => { ... });
|
|
});
|
|
});
|
|
```
|
|
|
|
**Test Strategy:**
|
|
|
|
This task IS the test implementation. Verify:
|
|
- Priority 10 tests pass
|
|
- LLM interaction tests use proper mocks
|
|
- Fallback tests cover all error scenarios
|
|
- Summary generation tests pass
|
|
- Response parsing handles edge cases
|