Stop model during graceful shutdown (#7042)

js/global_scope_js.js

@@ -95,6 +95,12 @@ function startEditing(messageElement, messageBody, isUserMessage) {
   editingInterface.textarea.focus();
   editingInterface.textarea.setSelectionRange(rawText.length, rawText.length);
 
+  // Scroll the textarea into view
+  editingInterface.textarea.scrollIntoView({
+    behavior: "smooth",
+    block: "center"
+  });
+
   // Setup event handlers
   setupEditingHandlers(editingInterface.textarea, messageElement, originalHTML, messageBody, isUserMessage);
 }

js/main.js

@@ -217,7 +217,7 @@ function isElementVisibleOnScreen(element) {
 }
 
 function doSyntaxHighlighting() {
-  const messageBodies = document.querySelectorAll(".message-body");
+  const messageBodies = document.getElementById("chat").querySelectorAll(".message-body");
 
   if (messageBodies.length > 0) {
     observer.disconnect();
@@ -229,6 +229,7 @@ function doSyntaxHighlighting() {
         codeBlocks.forEach((codeBlock) => {
           hljs.highlightElement(codeBlock);
           codeBlock.setAttribute("data-highlighted", "true");
+          codeBlock.classList.add("pretty_scrollbar");
         });
 
         renderMathInElement(messageBody, {

server.py

@@ -60,6 +60,14 @@ from modules.utils import gradio
 
 def signal_handler(sig, frame):
     logger.info("Received Ctrl+C. Shutting down Text generation web UI gracefully.")
+
+    # Explicitly stop LlamaServer to avoid __del__ cleanup issues during shutdown
+    if shared.model and shared.model.__class__.__name__ == 'LlamaServer':
+        try:
+            shared.model.stop()
+        except:
+            pass
+
     sys.exit(0)