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/cli/src/index.ts

@@ -81,6 +81,12 @@ export function createProgram(): Command {
       return attachments;
     }
 
+    // --project scoping for servers: show only attached servers
+    if (!nameOrId && resource === 'servers' && projectName) {
+      const projectId = await resolveNameOrId(client, 'projects', projectName);
+      return client.get<unknown[]>(`/api/v1/projects/${projectId}/servers`);
+    }
+
     // --project scoping for prompts and promptrequests
     if (!nameOrId && (resource === 'prompts' || resource === 'promptrequests')) {
       if (projectName) {
@@ -138,6 +144,7 @@ export function createProgram(): Command {
     fetchResource,
     log: (...args) => console.log(...args),
     getProject: () => program.opts().project as string | undefined,
+    mcplocalUrl: config.mcplocalUrl,
   }));
 
   program.addCommand(createDescribeCommand({
@@ -145,6 +152,7 @@ export function createProgram(): Command {
     fetchResource: fetchSingleResource,
     fetchInspect: async (id: string) => client.get(`/api/v1/instances/${id}/inspect`),
     log: (...args) => console.log(...args),
+    mcplocalUrl: config.mcplocalUrl,
   }));
 
   program.addCommand(createDeleteCommand({