feat(api): add llama.cpp support as local model provider

- Add llamacpp provider preset to provider-presets.ts
- Add base-llamacpp.settings.json configuration
- Update help-command.ts with ccs llamacpp documentation
- Update UI provider presets for dashboard parity

llama.cpp is a popular C++ inference engine for LLaMA models.
This complements existing Ollama support for local inference.

Usage: ccs llamacpp (requires llama.cpp server on port 8080)

Closes #690

ui/bun.lock

@@ -1,5 +1,6 @@
 {
   "lockfileVersion": 1,
+  "configVersion": 0,
   "workspaces": {
     "": {
       "name": "ui",

ui/src/lib/provider-presets.ts

@@ -60,6 +60,21 @@ export const PROVIDER_PRESETS: ProviderPreset[] = [
     apiKeyHint: 'No API key required for local Ollama',
     category: 'recommended',
   },
+  // Recommended - llama.cpp (Local)
+  {
+    id: 'llamacpp',
+    name: 'llama.cpp (Local)',
+    description: 'Local inference via llama.cpp (LLaMA models)',
+    baseUrl: 'http://127.0.0.1:8080',
+    defaultProfileName: 'llamacpp',
+    badge: 'Local',
+    featured: true,
+    defaultModel: 'llama3-8b',
+    requiresApiKey: false,
+    apiKeyPlaceholder: 'llamacpp',
+    apiKeyHint: 'Run llama.cpp server: ./server --host 0.0.0.0 --port 8080 -m model.gguf',
+    category: 'recommended',
+  },
   // Alternative providers - GLM/GLMT/Kimi
   {
     id: 'glm',