feat: print API endpoints and chat UI link on server startup

crates/inference-server/src/main.rs

@@ -65,7 +65,7 @@ async fn main() -> Result<()> {
     let state = AppState {
         engine: Arc::new(Mutex::new(engine)),
         counters: PerfCounters::new(),
-        model_name: Arc::new(model_name),
+        model_name: Arc::new(model_name.clone()),
         server_config,
         start_time: std::time::Instant::now(),
     };
@@ -78,7 +78,29 @@ async fn main() -> Result<()> {
     let router = build_router(state);
     let listener = tokio::net::TcpListener::bind(addr).await?;
 
-    info!(addr = %addr, "LocalLLM server listening");
+    // ── Startup banner ───────────────────────────────────────────────────
+    let display_addr = if addr.ip().is_unspecified() {
+        format!("http://127.0.0.1:{}", addr.port())
+    } else {
+        format!("http://{}", addr)
+    };
+    println!();
+    println!("  ╔══════════════════════════════════════════════════╗");
+    println!("  ║           ForgeLM  •  Local LLM Runtime          ║");
+    println!("  ╚══════════════════════════════════════════════════╝");
+    println!();
+    println!("  Model  : {}", model_name);
+    println!();
+    println!("  API Endpoints:");
+    println!("    GET   {}/health", display_addr);
+    println!("    GET   {}/v1/models", display_addr);
+    println!("    POST  {}/v1/chat/completions", display_addr);
+    println!();
+    println!("  Chat UI:");
+    println!("    file://$(pwd)/ui/chat.html");
+    println!("    (open ui/chat.html in your browser and set server to {})", display_addr);
+    println!();
+
     axum::serve(listener, router).await?;
 
     Ok(())