# Task ID: 111

**Title:** Write Integration Tests for subindex Model

**Status:** done

**Dependencies:** 75 ✓, 76 ✓, 82 ✓, 83 ✗

**Priority:** high

**Description:** Create comprehensive integration tests for the subindex proxymodel processing real content through section-split and summarize-tree.

**Details:**

Create `src/mcplocal/tests/proxymodel/subindex.test.ts`:

```typescript
import { describe, it, expect, beforeAll } from 'vitest';
import { executePipeline } from '../../src/proxymodel/executor';
import { loadProxyModels } from '../../src/proxymodel/loader';
import { createMockProviderRegistry } from '../mocks/providers';

describe('subindex proxymodel', () => {
  let proxyModel;
  let mockRegistry;
  
  beforeAll(async () => {
    const models = await loadProxyModels();
    proxyModel = models.get('subindex');
    mockRegistry = createMockProviderRegistry({
      complete: async (prompt) => 'Mock summary of the content',
    });
  });
  
  it('splits JSON array into sections', async () => {
    const content = JSON.stringify([
      { id: 'flow1', label: 'Thermostat', nodes: [] },
      { id: 'flow2', label: 'Lighting', nodes: [] },
    ]);
    
    const result = await executePipeline({
      content,
      contentType: 'toolResult',
      sourceName: 'test/get_flows',
      projectName: 'test',
      sessionId: 'test-session',
      proxyModel,
      providerRegistry: mockRegistry,
    });
    
    expect(result.sections).toHaveLength(2);
    expect(result.sections[0].id).toBe('flow1');
    expect(result.content).toContain('2 sections');
  });
  
  it('provides drill-down to exact JSON content', async () => {
    // Test that drilling into a section returns exact original JSON
  });
  
  it('uses structural summaries for JSON (no LLM call)', async () => {
    // Verify LLM not called for JSON content
  });
  
  it('uses LLM summaries for prose content', async () => {
    // Verify LLM called for markdown content
  });
  
  it('caches summaries across requests', async () => {
    // Verify cache hit on second request with same content
  });
});
```

**Test Strategy:**

Run with vitest, verify all test cases pass, check LLM call counts are as expected (structural vs prose), verify cache behavior.