feat: integrate Langfuse for LLM observability

- Add instrumentation.ts with Langfuse OpenTelemetry exporter
- Enable experimental telemetry on streamText calls
- Add instrumentationHook to Next.js config
- Install required dependencies (@vercel/otel, langfuse-vercel, etc.)

next.config.ts

@@ -3,6 +3,9 @@ import type { NextConfig } from "next";
 const nextConfig: NextConfig = {
   /* config options here */
   output: 'standalone',
+  experimental: {
+    instrumentationHook: true,
+  },
 };
 
 export default nextConfig;