fix error : ValueError: Conversation roles must alternate user/assistant/user/assistant

app.py

@@ -131,34 +131,38 @@ st.caption(f"Powered by `llama.cpp` | Model: {selected_model['filename']}")
 user_input = st.chat_input("Ask something...")
 
 if user_input:
-    st.session_state.chat_history.append({"role": "user", "content": user_input})
-
-    with st.chat_message("user"):
-        st.markdown(user_input)
-
-    # Trim conversation history to max 8 turns (user+assistant)
-    MAX_TURNS = 8
-    trimmed_history = st.session_state.chat_history[-MAX_TURNS * 2:]
-    messages = [{"role": "system", "content": system_prompt}] + trimmed_history
-
-    with st.chat_message("assistant"):
-        full_response = ""
-        response_area = st.empty()
-
-        stream = llm.create_chat_completion(
-            messages=messages,
-            max_tokens=max_tokens,
-            temperature=temperature,
-            top_k=top_k,
-            top_p=top_p,
-            repeat_penalty=repeat_penalty,
-            stream=True,
-        )
-
-        for chunk in stream:
-            if "choices" in chunk:
-                delta = chunk["choices"][0]["delta"].get("content", "")
-                full_response += delta
-                response_area.markdown(full_response)
-
-        st.session_state.chat_history.append({"role": "assistant", "content": full_response})
+    # Prevent appending user message if assistant hasn't replied yet
+    if len(st.session_state.chat_history) % 2 == 1:
+        st.warning("Please wait for the assistant to respond before sending another message.")
+    else:
+        st.session_state.chat_history.append({"role": "user", "content": user_input})
+
+        with st.chat_message("user"):
+            st.markdown(user_input)
+
+        # Trim conversation history to max 8 turns (user+assistant)
+        MAX_TURNS = 8
+        trimmed_history = st.session_state.chat_history[-MAX_TURNS * 2:]
+        messages = [{"role": "system", "content": system_prompt}] + trimmed_history
+
+        with st.chat_message("assistant"):
+            full_response = ""
+            response_area = st.empty()
+
+            stream = llm.create_chat_completion(
+                messages=messages,
+                max_tokens=max_tokens,
+                temperature=temperature,
+                top_k=top_k,
+                top_p=top_p,
+                repeat_penalty=repeat_penalty,
+                stream=True,
+            )
+
+            for chunk in stream:
+                if "choices" in chunk:
+                    delta = chunk["choices"][0]["delta"].get("content", "")
+                    full_response += delta
+                    response_area.markdown(full_response)
+
+            st.session_state.chat_history.append({"role": "assistant", "content": full_response})