Update app.py

app.py

@@ -5,14 +5,10 @@ from huggingface_hub import login
 
 login(os.environ["HF_TOKEN"])
 
-
-# Load models
 emotion_classifier = pipeline("text-classification", model="shengqizhao0124/emotion_trainer", return_all_scores=True)
 intent_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 text_generator = pipeline("text2text-generation", model="declare-lab/flan-alpaca-base")
 
-
-# Intent categories
 candidate_tasks = [
     "change mobile plan", "top up balance", "report service outage",
     "ask for billing support", "reactivate service", "cancel subscription",
@@ -48,7 +44,6 @@ def get_emotion_score(emotion):
     else:
         return 0.2
 
-# ✅ Simplified fixed-format auto-reply
 def generate_response(intent, human=True):
     if human:
         prompt = (
@@ -60,7 +55,6 @@ def generate_response(intent, human=True):
     else:
         return f"[Below is a link to the service you need：{intent} → https://support.example.com/{intent.replace(' ', '_')}]\\n[If your problem still can not be solved, welcome to continue to consult, we will continue to serve you!]"
 
-# Streamlit App
 st.set_page_config(page_title="Smart Customer Support Assistant", layout="wide")
 st.sidebar.title("📁 Customer Selector")
 
@@ -80,25 +74,28 @@ if selected_customer not in st.session_state.chat_sessions:
 session = st.session_state.chat_sessions[selected_customer]
 st.title("Smart Customer Support Assistant (for Agents Only)")
 
-# 💬 Conversation
+# Conversation UI
 st.markdown("### Conversation")
 for msg in session["chat"]:
     avatar = "👤" if msg['role'] == 'user' else ("🤖" if msg.get("auto") else "👨‍💼")
     with st.chat_message(msg['role'], avatar=avatar):
+        if msg["role"] == "user" and "emotion" in msg:
+            st.markdown(f"<div style='text-align:right;font-size:0.9em;color:gray;'>Emotion: {msg['emotion'].capitalize()}</div>", unsafe_allow_html=True)
         st.markdown(msg['content'])
 
-# 🔍 Analyze input
+# Input & Analyze
 col1, col2 = st.columns([6, 1])
 with col1:
     user_input = st.text_input("Enter customer message:", key="customer_input")
 with col2:
     if st.button("Analyze"):
         if user_input.strip():
-            session["chat"].append({"role": "user", "content": user_input})
             emotion_result = emotion_classifier(user_input)
             emotion_label = get_emotion_label(emotion_result, user_input)
             emotion_score = get_emotion_score(emotion_label)
 
+            session["chat"].append({"role": "user", "content": user_input, "emotion": emotion_label})
+
             intent_result = intent_classifier(user_input, candidate_tasks)
             top_intents = [label for label, score in zip(intent_result['labels'], intent_result['scores']) if score > 0.15][:3]
 
@@ -126,7 +123,7 @@ with col2:
                 session["agent_reply"] = ""
             st.rerun()
 
-# 🧠 Agent reply
+# Agent panel
 if session["support_required"]:
     st.markdown(f"### {session['support_required']}")
 
@@ -140,7 +137,7 @@ if st.button("Send Reply"):
         session["support_required"] = ""
         st.rerun()
 
-# 🔍 If human required
+# Show customer analysis
 if session["system_result"] is not None:
     st.markdown("#### Customer Status")
     st.markdown(f"- **Emotion:** {session['system_result']['emotion'].capitalize()}")
@@ -159,4 +156,3 @@ if st.button("End Conversation"):
     session["user_input"] = ""
     st.success("Conversation ended and cleared.")
     st.rerun()
-