# 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