import streamlit as st
from transformers import pipeline
import re

# Load upgraded models
emotion_classifier = pipeline(
    "text-classification",
    model="j-hartmann/emotion-english-distilroberta-base",
    return_all_scores=True
)
intent_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")

# Candidate intents
candidate_tasks = [
    "change mobile plan",
    "top up balance",
    "report service outage",
    "ask for billing support",
    "reactivate service",
    "cancel subscription",
    "check account status",
    "upgrade device"
]

# Emotion categories (updated)
urgent_emotions = {"anger", "frustration", "anxiety", "urgency", "afraid", "annoyed"}
moderate_emotions = {"confused", "sad", "tired", "concerned"}

def get_emotion_label(emotion_result):
    sorted_emotions = sorted(emotion_result[0], key=lambda x: x['score'], reverse=True)
    return sorted_emotions[0]['label']

def get_emotion_score(emotion):
    if emotion.lower() in urgent_emotions:
        return 1.0
    elif emotion.lower() in moderate_emotions:
        return 0.6
    else:
        return 0.2

def get_content_score(text, top_intents):
    score = 0.0
    trigger_words = ["out of service", "urgent", "not working", "stopped", "can't", "immediately"]
    if any(kw in text.lower() for kw in trigger_words):
        score += 0.3
    if any(label in ["top up balance", "reactivate service", "report service outage"] for label in top_intents):
        score += 0.4
    if any(label in ["change mobile plan", "ask for billing support"] for label in top_intents):
        score += 0.2
    return min(score + 0.1, 1.0)

def generate_reply(input_text, intent):
    # Intent-specific suggestion sentences
    intent_solutions = {
        "top up balance": "Your balance is ¥12. Current promo: recharge ¥100 get ¥5 bonus.",
        "reactivate service": "Your service is suspended due to unpaid ¥38. Recharge to restore within 30 mins.",
        "change mobile plan": "You're on Plan Basic (¥68/5GB). Suggest Plan Plus (¥98/20GB).",
        "check account status": "Your data usage is 3.2GB/5GB. Balance: ¥12. Calls left: 22 mins.",
        "ask for billing support": "Last bill was ¥96 for March. Includes data overage ¥16.",
        "cancel subscription": "Your contract ends on 2025-06-30. No penalty after this date.",
        "upgrade device": "You're eligible for upgrade. New iPhone plan starts at ¥399/month.",
        "report service outage": "We're detecting signal issues in your area (ZIP: XXX). Engineers notified."
    }

    # Intent-specific closing question
    intent_closings = {
        "top up balance": "Would you like to proceed with a recharge now?",
        "reactivate service": "Shall I help you restart your service now?",
        "report service outage": "Would you like me to file a service report for you?",
        "change mobile plan": "Would you like to switch to a better plan?",
        "ask for billing support": "Shall I show your last 3 billing records?",
        "cancel subscription": "Shall I guide you through cancellation?",
        "check account status": "Want a summary of your usage and balance?",
        "upgrade device": "Would you like me to show available upgrade options?"
    }

    solution = intent_solutions.get(intent.lower(), "Here's how we can assist you with this issue.")
    closing = intent_closings.get(intent.lower(), "Is there anything else I can help with?")
    opening = "Thank you for contacting us. I understand your concern."

    return f"{opening} {solution} {closing}"

# Streamlit UI
st.set_page_config(page_title="Customer Support Assistant", layout="centered")
st.title("📞 Smart Customer Support Assistant (for Agents Only)")

user_input = st.text_area("Enter customer's message or complaint:", height=150)

if st.button("Analyze Message"):
    if user_input.strip() == "":
        st.warning("Please enter a customer message.")
    else:
        with st.spinner("Processing..."):

            # Emotion detection (updated)
            emotion_result = emotion_classifier(user_input)
            emotion_label = get_emotion_label(emotion_result)
            emotion_score = get_emotion_score(emotion_label)

            # Intent detection
            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]

            # Content score
            content_score = get_content_score(user_input, top_intents)

            # Final decision score
            final_score = (0.5 * emotion_score) + (0.5 * content_score)

            st.subheader("🧾 System Summary")

            if final_score < 0.5:
                st.markdown("### 🟢 This message was handled automatically.")
                if top_intents:
                    auto_intent = top_intents[0]
                    auto_reply = generate_reply(user_input, auto_intent)
                    st.markdown("#### 🤖 Auto-Response Sent to User:")
                    st.success(auto_reply)
                else:
                    st.info("No clear intent detected. A general auto-reply was used.")
            else:
                st.markdown("### 🔴 Human Support Required")

                # Customer Profile Summary
                st.markdown("#### 👤 Customer Status:")
                st.write(f"- **Emotion detected**: {emotion_label.capitalize()}")
                st.write(f"- **Tone**: {'Urgent' if emotion_score > 0.8 else 'Concerned' if emotion_score > 0.5 else 'Calm'}")

                if top_intents:
                    st.markdown("#### 🧩 Detected Customer Needs:")
                    for intent in top_intents:
                        reply = generate_reply(user_input, intent)
                        st.markdown(f"**• {intent.capitalize()}**")
                        st.write(reply)
                else:
                    st.warning("No clear intent detected. Manual review recommended.")