feat: eager vLLM warmup and smart page titles in paginate stage

- Add warmup() to LlmProvider interface for eager subprocess startup
- ManagedVllmProvider.warmup() starts vLLM in background on project load
- ProviderRegistry.warmupAll() triggers all managed providers
- NamedProvider proxies warmup() to inner provider
- paginate stage generates LLM-powered descriptive page titles when
  available, cached by content hash, falls back to generic "Page N"
- project-mcp-endpoint calls warmupAll() on router creation so vLLM
  is loading while the session initializes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/mcpd/tests/backup.test.ts

@@ -34,7 +34,7 @@ const mockSecrets = [
 
 const mockProjects = [
   {
-    id: 'proj1', name: 'my-project', description: 'Test project', proxyMode: 'direct', llmProvider: null, llmModel: null,
+    id: 'proj1', name: 'my-project', description: 'Test project', proxyMode: 'direct', proxyModel: '', llmProvider: null, llmModel: null,
     ownerId: 'user1', version: 1, createdAt: new Date(), updatedAt: new Date(),
     servers: [{ id: 'ps1', server: { id: 's1', name: 'github' } }],
   },