feat: wire up LlamaCppClient to model router

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/daemon/index.ts

@@ -1,7 +1,7 @@
 import { Bot } from 'grammy';
 import { Lifecycle } from './lifecycle.js';
 import type { Config } from '../config/index.js';
-import { AnthropicClient, OpenAIClient, OllamaClient, ModelRouter } from '../models/index.js';
+import { AnthropicClient, OpenAIClient, OllamaClient, LlamaCppClient, ModelRouter } from '../models/index.js';
 import { NativeAgent } from '../backends/index.js';
 import { createTelegramBot } from '../frontends/telegram/index.js';
 import { SessionStore, SessionManager } from '../session/index.js';
@@ -60,6 +60,11 @@ function createModelRouter(config: Config): ModelRouter {
         model: models.local.model,
         host: models.local.endpoint,
       });
+    } else if (models.local.provider === 'llamacpp') {
+      localClient = new LlamaCppClient({
+        endpoint: models.local.endpoint ?? 'http://localhost:8080',
+        authToken: models.local.auth_token,
+      });
     }
   }
 

src/models/index.ts

@@ -1,5 +1,6 @@
 export { AnthropicClient, type AnthropicClientConfig } from './anthropic.js';
 export { OpenAIClient, type OpenAIClientConfig } from './openai.js';
 export { OllamaClient, type OllamaClientConfig } from './local/index.js';
+export { LlamaCppClient, type LlamaCppClientConfig } from './local/index.js';
 export { ModelRouter, type ModelRouterConfig, type ModelTier } from './router.js';
 export type { Message, ChatRequest, ChatResponse, ModelClient } from './types.js';

src/models/local/index.ts

@@ -1 +1,2 @@
 export { OllamaClient, type OllamaClientConfig } from './ollama.js';
+export { LlamaCppClient, type LlamaCppClientConfig } from './llamacpp.js';