fix: Transition to cumulative yielding in Python backend and replacement rendering in JS frontend to prevent token duplication

app.py

@@ -49,9 +49,11 @@ async def chat(messages_json: str, temperature: float = 0.7, max_tokens: int = 1
             stream=True,
         )
         
+        bot_response = ""
         async for chunk in stream:
             if chunk.choices and chunk.choices[0].delta.content is not None:
-                yield chunk.choices[0].delta.content
+                bot_response += chunk.choices[0].delta.content
+                yield bot_response
                 
     except Exception as e:
         yield f"Error calling Hugging Face Router: {str(e)}"

index.html

@@ -1668,7 +1668,7 @@
                         }
 
                         const chunk = message.data[0];
-                        botResponse += chunk;
+                        botResponse = chunk;
                         
                         if (botBubble) {
                             botBubble.innerHTML = parseMarkdown(botResponse);