Update app.py

app.py

@@ -1,11 +1,32 @@
-"""
-Beautiful Gradio interface for credit card recommendations
-"""
+from typing import Dict, Any, Optional, Tuple, List
+import traceback
+import json
+import os
+from datetime import date
+import gradio as gr
+import plotly.graph_objects as go
+import httpx
 
-# Add after imports, before client initialization
-from typing import Dict, Any
-import traceback  
+from config import (
+    APP_TITLE, APP_DESCRIPTION, THEME,
+    MCC_CATEGORIES, SAMPLE_USERS,
+    MERCHANTS_BY_CATEGORY
+)
+from utils.api_client import RewardPilotClient
+from utils.formatters import (
+    format_full_recommendation,
+    format_comparison_table,
+    format_analytics_metrics,
+    create_spending_chart,
+    create_rewards_pie_chart,
+    create_optimization_gauge,
+    create_trend_line_chart,
+    create_card_performance_chart
+)
+from utils.llm_explainer import get_llm_explainer
+import config
 
+CARDS_FILE = os.path.join(os.path.dirname(__file__), "data", "cards.json")
 
 def safe_get(data: Dict, key: str, default: Any = None) -> Any:
     """Safely get value from dictionary with fallback"""
@@ -14,16 +35,13 @@ def safe_get(data: Dict, key: str, default: Any = None) -> Any:
     except:
         return default
 
-
 def normalize_recommendation_data(data: Dict) -> Dict:
     """
     Normalize API response to ensure all required fields exist.
     Handles both orchestrator format and mock data format.
     """
     
-    # Check if this is mock data (simpler format)
     if data.get('mock_data'):
-        # Mock data has simpler structure
         return {
             'recommended_card': safe_get(data, 'recommended_card', 'Unknown Card'),
             'rewards_earned': float(safe_get(data, 'rewards_earned', 0)),
@@ -39,7 +57,6 @@ def normalize_recommendation_data(data: Dict) -> Dict:
             'mock_data': True
         }
     
-    # Handle orchestrator format (recommended_card is a dict)
     recommended_card = safe_get(data, 'recommended_card', {})
     if isinstance(recommended_card, dict):
         card_name = safe_get(recommended_card, 'card_name', 'Unknown Card')
@@ -48,13 +65,11 @@ def normalize_recommendation_data(data: Dict) -> Dict:
         category = safe_get(recommended_card, 'category', 'Unknown')
         reasoning = safe_get(recommended_card, 'reasoning', 'Optimal choice')
         
-        # Format reward rate as string
         if reward_rate > 0:
             rewards_rate_str = f"{reward_rate}x points"
         else:
             rewards_rate_str = "N/A"
     else:
-        # Handle case where it's already a string
         card_name = str(recommended_card) if recommended_card else 'Unknown Card'
         reward_amount = float(safe_get(data, 'rewards_earned', 0))
         reward_rate = 0
@@ -62,18 +77,14 @@ def normalize_recommendation_data(data: Dict) -> Dict:
         category = safe_get(data, 'category', 'Unknown')
         reasoning = safe_get(data, 'reasoning', 'Optimal choice')
     
-    # Get merchant and amount from top level
     merchant = safe_get(data, 'merchant', 'Unknown Merchant')
     amount = float(safe_get(data, 'amount_usd', safe_get(data, 'amount', 0)))
-    
-    # Calculate annual potential
     annual_potential = reward_amount * 12 if reward_amount > 0 else 0
     
-    # Process alternative cards
     alternatives = []
     alt_cards = safe_get(data, 'alternative_cards', safe_get(data, 'alternatives', []))
     
-    for alt in alt_cards[:3]:  # Limit to top 3
+    for alt in alt_cards[:3]:
         if isinstance(alt, dict):
             alt_name = safe_get(alt, 'card_name', safe_get(alt, 'card', 'Unknown'))
             alt_reward = float(safe_get(alt, 'reward_amount', safe_get(alt, 'rewards', 0)))
@@ -90,7 +101,6 @@ def normalize_recommendation_data(data: Dict) -> Dict:
                 'rate': alt_rate_str
             })
     
-    # Extract warnings
     warnings = safe_get(data, 'warnings', [])
     forecast_warning = safe_get(data, 'forecast_warning')
     if forecast_warning and isinstance(forecast_warning, dict):
@@ -98,7 +108,6 @@ def normalize_recommendation_data(data: Dict) -> Dict:
         if warning_msg:
             warnings.append(warning_msg)
     
-    # Build normalized response
     normalized = {
         'recommended_card': card_name,
         'rewards_earned': round(reward_amount, 2),
@@ -120,39 +129,6 @@ def create_loading_state():
     """Create loading indicator message"""
     return "⏳ **Loading...** Please wait while we fetch your recommendation.", None
 
-    
-from datetime import date
-from typing import Optional, Tuple, List, Dict, Any
-import gradio as gr
-from config import (
-    APP_TITLE, APP_DESCRIPTION, THEME,
-    MCC_CATEGORIES, SAMPLE_USERS,
-    MERCHANTS_BY_CATEGORY
-)
-from utils.api_client import RewardPilotClient
-from utils.formatters import (
-    format_full_recommendation,
-    format_comparison_table,
-    format_analytics_metrics,
-    create_spending_chart,
-    create_rewards_pie_chart,
-    create_optimization_gauge,
-    create_trend_line_chart,
-    create_card_performance_chart
-)
-import plotly.graph_objects as go
-import gradio as gr
-from utils.api_client import RewardPilotClient
-from utils.llm_explainer import get_llm_explainer
-import config
-
-# ===================== CARD DATABASE LOADER =====================
-import json
-import os
-
-# Path to cards.json
-CARDS_FILE = os.path.join(os.path.dirname(__file__), "data", "cards.json")
-
 def load_card_database() -> dict:
     """Load card database from local cards.json"""
     try:
@@ -167,7 +143,6 @@ def load_card_database() -> dict:
         print(f"❌ Error parsing cards.json: {e}")
         return {}
 
-# Load at startup
 CARD_DATABASE = load_card_database()
 
 def get_card_details(card_id: str, mcc: str = None) -> dict:
@@ -193,17 +168,14 @@ def get_card_details(card_id: str, mcc: str = None) -> dict:
         }
     
     card = CARD_DATABASE[card_id]
-    
-    # Get reward rate for specific MCC (if provided)
     reward_rate = 1.0
+    
     if mcc and "reward_structure" in card:
         reward_structure = card["reward_structure"]
         
-        # Check exact MCC match
         if mcc in reward_structure:
             reward_rate = reward_structure[mcc]
         else:
-            # Check MCC ranges (e.g., "3001-3999")
             try:
                 mcc_int = int(mcc)
                 for key, rate in reward_structure.items():
@@ -215,11 +187,9 @@ def get_card_details(card_id: str, mcc: str = None) -> dict:
             except (ValueError, AttributeError):
                 pass
         
-        # Use default if no match found
         if reward_rate == 1.0 and "default" in reward_structure:
             reward_rate = reward_structure["default"]
     
-    # Extract spending cap info
     spending_caps = card.get("spending_caps", {})
     cap_info = {}
     
@@ -250,13 +220,8 @@ def get_card_details(card_id: str, mcc: str = None) -> dict:
         "spending_caps": cap_info,
         "benefits": card.get("benefits", [])
     }
-# ===================== END CARD DATABASE =====================
-
 
 def get_recommendation_with_agent(user_id, merchant, category, amount):
-    import httpx
-    import json
-    
     yield "⏳ **Agent is thinking...** Analyzing your transaction and cards...", None
     
     try:
@@ -294,7 +259,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
         
         print(f"🔍 KEYS: {list(result.keys())}")
         
-        # ========== EXTRACT BASIC DATA ==========
         card_id = result.get('recommended_card', 'Unknown')
         rewards_earned = float(result.get('rewards_earned', 0))
         rewards_rate = result.get('rewards_rate', 'N/A')
@@ -303,7 +267,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
         alternatives = result.get('alternative_options', [])
         warnings = result.get('warnings', [])
         
-        # Map card_id to card_name
         card_name_map = {
             'c_citi_custom_cash': 'Citi Custom Cash',
             'c_amex_gold': 'American Express Gold',
@@ -316,67 +279,18 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
         }
         card_name = card_name_map.get(card_id, card_id.replace('c_', '').replace('_', ' ').title())
         
-        # # ========== CARD DATABASE (FALLBACK) ==========
-        # # If API doesn't provide card_details, use this database
-        # CARD_DATABASE = {
-        #     'c_citi_custom_cash': {
-        #         'reward_rate': 5.0,
-        #         'monthly_cap': 500,
-        #         'base_rate': 1.0,
-        #         'annual_fee': 0,
-        #         'cap_type': 'monthly'
-        #     },
-        #     'c_amex_gold': {
-        #         'reward_rate': 4.0,
-        #         'annual_cap': 25000,
-        #         'base_rate': 1.0,
-        #         'annual_fee': 250,
-        #         'cap_type': 'annual'
-        #     },
-        #     'c_chase_sapphire_reserve': {
-        #         'reward_rate': 3.0,
-        #         'monthly_cap': None,
-        #         'base_rate': 3.0,
-        #         'annual_fee': 550,
-        #         'cap_type': 'none'
-        #     },
-        #     'c_chase_freedom_unlimited': {
-        #         'reward_rate': 1.5,
-        #         'monthly_cap': None,
-        #         'base_rate': 1.5,
-        #         'annual_fee': 0,
-        #         'cap_type': 'none'
-        #     },
-        #     'c_chase_sapphire_preferred': {
-        #         'reward_rate': 2.0,
-        #         'monthly_cap': None,
-        #         'base_rate': 2.0,
-        #         'annual_fee': 95,
-        #         'cap_type': 'none'
-        #     }
-        # }
-        
-        # ========== GET CARD DETAILS (FROM cards.json) ==========
-        # Get MCC from transaction
         transaction_mcc = result.get('mcc', MCC_CATEGORIES.get(category, "5999"))
-        
-        # Load card details from our database
         card_details_from_db = get_card_details(card_id, transaction_mcc)
-        
-        # Use API card_details if available, otherwise use our database
         card_details = result.get('card_details', {})
         
         if not card_details or not card_details.get('reward_rate'):
-            # Convert our database format to the format expected by the rest of the code
             reward_structure = CARD_DATABASE.get(card_id, {}).get('reward_structure', {})
             
-            # Get reward rate for this MCC
             if transaction_mcc in reward_structure:
                 reward_rate_value = reward_structure[transaction_mcc]
             else:
                 reward_rate_value = reward_structure.get('default', 1.0)
             
-            # Get spending caps
             spending_caps_db = CARD_DATABASE.get(card_id, {}).get('spending_caps', {})
             
             card_details = {
@@ -400,17 +314,15 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
         
         print(f"✅ CARD DETAILS: {reward_rate_value}%, cap={monthly_cap or annual_cap}, fee=${annual_fee}")
         
-        # ========== CALCULATE ANNUAL PROJECTION ==========
         amount_float = float(amount)
         
-        # Frequency assumptions by category
         frequency_map = {
-            'Groceries': 52,  # Weekly
+            'Groceries': 52,
             'Restaurants': 52,
             'Gas Stations': 52,
             'Fast Food': 52,
-            'Airlines': 4,  # Quarterly
-            'Hotels': 12,  # Monthly
+            'Airlines': 4,
+            'Hotels': 12,
             'Online Shopping': 24,
             'Entertainment': 24,
         }
@@ -425,9 +337,7 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
         
         annual_spend = amount_float * frequency
         
-        # ========== TIERED CALCULATION ==========
         if monthly_cap:
-            # Monthly cap logic (e.g., Citi Custom Cash)
             monthly_cap_annual = monthly_cap * 12
             
             if annual_spend <= monthly_cap_annual:
@@ -450,7 +360,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 | **Net Rewards** | - | - | **${total_rewards - annual_fee:.2f}** |"""
             
         elif annual_cap:
-            # Annual cap logic (e.g., Amex Gold)
             if annual_spend <= annual_cap:
                 high_rate_spend = annual_spend
                 low_rate_spend = 0
@@ -471,7 +380,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 | **Net Rewards** | - | - | **${total_rewards - annual_fee:.2f}** |"""
             
         else:
-            # No cap - flat rate
             total_rewards = annual_spend * (reward_rate_value / 100)
             
             calc_table = f"""| Spending Tier | Annual Amount | Rate | Rewards |
@@ -480,7 +388,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 | Annual fee | - | - | -${annual_fee:.2f} |
 | **Net Rewards** | - | - | **${total_rewards - annual_fee:.2f}** |"""
         
-        # ========== BASELINE COMPARISON ==========
         baseline_rewards = annual_spend * 0.01
         net_rewards = total_rewards - annual_fee
         net_benefit = net_rewards - baseline_rewards
@@ -495,25 +402,21 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 
 **Net Benefit: ${net_benefit:+.2f}/year** {"🎉" if net_benefit > 0 else "⚠️"}"""
         
-        # ========== OPTIMIZATION SCORE ==========
-        # Calculate score based on performance
-        max_possible_rewards = annual_spend * 0.06  # Theoretical max (6%)
+        max_possible_rewards = annual_spend * 0.06
         
         if max_possible_rewards > 0:
             performance_ratio = (net_rewards / max_possible_rewards) * 100
             
-            # Bonus for beating baseline
             if net_rewards > baseline_rewards:
                 improvement = (net_rewards - baseline_rewards) / baseline_rewards
                 baseline_bonus = min(improvement * 20, 20)
             else:
-                baseline_bonus = -10  # Penalty for underperforming
+                baseline_bonus = -10
             
             optimization_score = int(min(performance_ratio + baseline_bonus, 100))
         else:
             optimization_score = 0
         
-        # Score breakdown
         score_breakdown = {
             'reward_rate': min(30, int(optimization_score * 0.30)),
             'cap_availability': min(25, int(optimization_score * 0.25)),
@@ -538,7 +441,6 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 - 60-69: Acceptable ⚠️
 - <60: Suboptimal ❌"""
         
-        # ========== FORMAT OUTPUT ==========
         output = f"""## 🤖 AI Agent Recommendation
 
 ### 💳 Recommended Card: **{card_name}**
@@ -549,12 +451,10 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 ---
 
 ### 🧠 Agent's Reasoning:
-
 {reasoning}
 
 ---"""
         
-        # Add alternatives
         if alternatives:
             output += "\n### 🔄 Alternative Options:\n\n"
             for alt in alternatives[:3]:
@@ -563,16 +463,13 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
                 alt_reason = alt.get('reason', '')
                 output += f"**{alt_card_name}:**\n{alt_reason}\n\n"
         
-        # Add warnings
         if warnings:
             output += "\n### ⚠️ Important Warnings:\n\n"
             for warning in warnings:
                 output += f"- {warning}\n"
         
-        # Add annual impact with expandable details
         output += f"""
 ### 💰 Annual Impact
-
 - **Potential Savings:** ${net_benefit:.2f}/year
 - **Optimization Score:** {optimization_score}/100
 
@@ -582,24 +479,20 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 #### 💡 Calculation Assumptions:
 
 **Step 1: Estimate Annual Spending**
-
 Current transaction: ${amount_float:.2f} at {merchant}  
 Category: {category}  
 Frequency assumption: {frequency_label.capitalize()}  
 Annual estimate: ${amount_float:.2f} × {frequency} = **${annual_spend:.2f}**
 
 **Step 2: Calculate Rewards with {card_name}**
-
 {calc_table}
 
 **Step 3: Compare to Baseline**
-
 {comparison_text}
 
 ---
 
 #### 📈 Optimization Score: {optimization_score}/100
-
 {score_details}
 
 ---
@@ -613,10 +506,9 @@ Annual estimate: ${amount_float:.2f} × {frequency} = **${annual_spend:.2f}**
 
 </details>
 
----"""
-        
-        # Add transaction details
-        output += f"""### 📊 Transaction Details:
+---
+
+#### 📊 Transaction Details:
 - **Amount:** ${amount_float:.2f}
 - **Merchant:** {merchant}
 - **Category:** {category}
@@ -630,13 +522,11 @@ Annual estimate: ${amount_float:.2f} × {frequency} = **${annual_spend:.2f}**
         print("=" * 80)
     
     except Exception as e:
-        import traceback
         print(f"❌ ERROR: {traceback.format_exc()}")
         yield f"❌ **Error:** {str(e)}", None        
         
 def create_agent_recommendation_chart_enhanced(result: Dict) -> go.Figure:
     try:
-        # ✅ FIX: Extract from top level
         rec_name_map = {
             'c_citi_custom_cash': 'Citi Custom Cash',
             'c_amex_gold': 'Amex Gold',
@@ -656,8 +546,7 @@ def create_agent_recommendation_chart_enhanced(result: Dict) -> go.Figure:
         for alt in alternatives[:3]:
             alt_id = alt.get('card', '')
             alt_name = rec_name_map.get(alt_id, alt_id)
-            # Extract reward from reason text if possible
-            alt_reward = rec_reward * 0.8  # Estimate
+            alt_reward = rec_reward * 0.8
             cards.append(alt_name)
             rewards.append(alt_reward)
             colors.append('#cbd5e0')
@@ -689,13 +578,10 @@ def create_agent_recommendation_chart_enhanced(result: Dict) -> go.Figure:
         fig.add_annotation(text="Chart unavailable", xref="paper", yref="paper", x=0.5, y=0.5, showarrow=False)
         fig.update_layout(height=400, template='plotly_white')
         return fig
-        
-# Initialize clients
+
 client = RewardPilotClient(config.ORCHESTRATOR_URL)
 llm = get_llm_explainer()
 
-
-# ===================== Main Recommendation Function =====================
 def get_recommendation(
     user_id: str,
     merchant: str,
@@ -706,7 +592,6 @@ def get_recommendation(
     transaction_date: Optional[str]
 ) -> tuple:
     """Get card recommendation and format response"""
-    # Validate inputs
     if not user_id or not merchant or amount <= 0:
         return (
             "❌ **Error:** Please fill in all required fields.",
@@ -714,17 +599,14 @@ def get_recommendation(
             None,
         )
     
-    # Determine MCC code
     if use_custom_mcc and custom_mcc:
         mcc = custom_mcc
     else:
         mcc = MCC_CATEGORIES.get(category, "5999")
     
-    # Set default date if not provided
     if not transaction_date:
         transaction_date = str(date.today())
     
-    # Call API
     response: Dict[str, Any] = client.get_recommendation_sync(
         user_id=user_id,
         merchant=merchant,
@@ -733,10 +615,8 @@ def get_recommendation(
         transaction_date=transaction_date,
     )
     
-    # Format response
     formatted_text = format_full_recommendation(response)
     
-    # Extract card details for comparison
     comparison_table: Optional[str]
     stats: Optional[str]
     if not response.get("error"):
@@ -745,7 +625,6 @@ def get_recommendation(
         all_cards = [c for c in ([recommended] + alternatives) if c]
         comparison_table = format_comparison_table(all_cards) if all_cards else None
         
-        # Create summary stats
         total_analyzed = response.get("total_cards_analyzed", len(all_cards))
         best_reward = (recommended.get("reward_amount") or 0.0)
         services_used = response.get("services_used", [])
@@ -760,22 +639,18 @@ def get_recommendation(
     
     return formatted_text, comparison_table, stats
 
-
 def get_recommendation_with_ai(user_id, merchant, category, amount):
     """Get card recommendation with LLM-powered explanation"""
     
-    # Validate inputs
     if not merchant or not merchant.strip():
         return "❌ Please enter a merchant name.", None
     
     if amount <= 0:
         return "❌ Please enter a valid amount greater than $0.", None
     
-    # Show loading state
     yield "⏳ **Loading recommendation...** Analyzing your cards and transaction...", None
     
     try:
-        # Get base recommendation from orchestrator
         result = client.get_recommendation(
             user_id=user_id,
             merchant=merchant,
@@ -784,16 +659,13 @@ def get_recommendation_with_ai(user_id, merchant, category, amount):
             mcc=None
         )
         
-        # Check for errors
         if not result.get('success'):
             error_msg = result.get('error', 'Unknown error')
             yield f"❌ Error: {error_msg}", None
             return
         
-        # Normalize the data
         data = normalize_recommendation_data(result.get('data', {}))
         
-        # Generate LLM explanation if enabled
         ai_explanation = ""
         if config.LLM_ENABLED:
             try:
@@ -812,7 +684,6 @@ def get_recommendation_with_ai(user_id, merchant, category, amount):
                 print(f"LLM explanation failed: {e}")
                 ai_explanation = ""
         
-        # Format output
         output = f"""
 ## 🎯 Recommendation for ${amount:.2f} at {merchant}
 
@@ -830,7 +701,6 @@ def get_recommendation_with_ai(user_id, merchant, category, amount):
             output += f"""
 ### 🤖 AI Insight
 {ai_explanation}
-
 ---
 """
         
@@ -853,13 +723,11 @@ def get_recommendation_with_ai(user_id, merchant, category, amount):
             for alt in data['alternatives']:
                 output += f"- **{alt['card']}:** ${alt['rewards']:.2f} ({alt['rate']})\n"
         
-        # Create visualization
         chart = create_rewards_comparison_chart(data)
         
         yield output, chart
         
     except Exception as e:
-        import traceback
         error_details = traceback.format_exc()
         print(f"Recommendation error: {error_details}")
         yield f"❌ Error: {str(e)}\n\nPlease check your API connection or try again.", None        
@@ -868,18 +736,15 @@ def create_rewards_comparison_chart(data: Dict) -> go.Figure:
     """Create rewards comparison chart with proper error handling"""
     
     try:
-        # Prepare data for chart
         cards = [data['recommended_card']]
         rewards = [data['rewards_earned']]
-        colors = ['#667eea']  # Primary color for recommended card
+        colors = ['#667eea']
         
-        # Add alternatives
         for alt in data.get('alternatives', [])[:3]:
             cards.append(alt['card'])
             rewards.append(float(alt['rewards']))
-            colors.append('#a0aec0')  # Gray for alternatives
+            colors.append('#a0aec0')
         
-        # Only create chart if we have valid data
         if not cards or all(r == 0 for r in rewards):
             fig = go.Figure()
             fig.add_annotation(
@@ -894,7 +759,6 @@ def create_rewards_comparison_chart(data: Dict) -> go.Figure:
             )
             return fig
         
-        # Create bar chart
         fig = go.Figure(data=[
             go.Bar(
                 x=cards,
@@ -928,10 +792,8 @@ def create_rewards_comparison_chart(data: Dict) -> go.Figure:
         
     except Exception as e:
         print(f"Chart creation error: {e}")
-        import traceback
         print(traceback.format_exc())
         
-        # Return empty chart with error message
         fig = go.Figure()
         fig.add_annotation(
             text=f"Error creating chart",
@@ -941,12 +803,11 @@ def create_rewards_comparison_chart(data: Dict) -> go.Figure:
         )
         fig.update_layout(height=400, template='plotly_white')
         return fig
-        
+
 def get_analytics_with_insights(user_id):
     """Get analytics with LLM-generated insights"""
     
     try:
-        # Get analytics data
         result = client.get_user_analytics(user_id)
         
         if not result.get('success'):
@@ -954,7 +815,6 @@ def get_analytics_with_insights(user_id):
         
         data = result['data']
         
-        # Generate AI insights if enabled
         ai_insights = ""
         if config.LLM_ENABLED:
             try:
@@ -970,29 +830,23 @@ def get_analytics_with_insights(user_id):
                 print(f"AI insights generation failed: {e}")
                 ai_insights = ""
         
-        # Format metrics
         metrics = f"""
 ## 📊 Your Rewards Analytics
 
 ### Key Metrics
-
 - **💰 Total Rewards:** ${data['total_rewards']:.2f}
 - **📈 Potential Savings:** ${data['potential_savings']:.2f}/year
 - **⭐ Optimization Score:** {data['optimization_score']}/100
 - **✅ Optimized Transactions:** {data.get('optimized_count', 0)}
 """
         
-        # Add AI insights
         if ai_insights:
             metrics += f"""
 ### 🤖 Personalized Insights
-
 {ai_insights}
-
 ---
 """
         
-        # Create charts (your existing chart code)
         spending_chart = create_spending_chart(data)
         rewards_chart = create_rewards_distribution_chart(data)
         optimization_chart = create_optimization_gauge(data['optimization_score'])
@@ -1002,7 +856,6 @@ def get_analytics_with_insights(user_id):
     except Exception as e:
         return f"❌ Error: {str(e)}", None, None, None
 
-# ===================== Sample Transaction Examples =====================
 EXAMPLES = [
     ["u_alice", "Groceries", "Whole Foods", 125.50, False, "", "2025-01-15"],
     ["u_bob", "Restaurants", "Olive Garden", 65.75, False, "", "2025-01-15"],
@@ -1011,7 +864,6 @@ EXAMPLES = [
     ["u_bob", "Gas Stations", "Shell", 45.00, False, "", ""],
 ]
 
-# ===================== Build Gradio Interface =====================
 def _toggle_custom_mcc(use_custom: bool):
     return gr.update(visible=use_custom, value="")
 
@@ -1026,7 +878,6 @@ with gr.Blocks(
         font-size: 16px;
         line-height: 1.6;
     }
-    /* Metric Cards Styling */
     .metric-card {
         background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
         color: white;
@@ -1062,7 +913,6 @@ with gr.Blocks(
     .metric-card-blue {
         background: linear-gradient(135deg, #4facfe 0%, #00f2fe 100%);
     }
-    /* Table styling */
     table {
         width: 100%;
         border-collapse: collapse;
@@ -1091,7 +941,6 @@ with gr.Blocks(
     }
     """,
 ) as app:
-    # Header
     gr.Markdown(
         f"""
 # {APP_TITLE}
@@ -1105,7 +954,7 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
 ---
 """
     )
-    # Agent Status Indicator
+    
     agent_status = """
     🤖 **Autonomous Agent:** ✅ Active (Claude 3.5 Sonnet)  
     📊 **Mode:** Dynamic Planning + Reasoning  
@@ -1113,10 +962,7 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
     """
     gr.Markdown(agent_status)
     
-    
-    # Ensure all tabs are siblings at the same level
     with gr.Tabs():
-        # ========== Tab 1: Get Recommendation ==========
         with gr.Tab("🎯 Get Recommendation"):
             with gr.Row():
                 with gr.Column(scale=1):
@@ -1128,7 +974,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         info="Select a user"
                     )
                     
-                    # CATEGORY FIRST (moved up)
                     category_dropdown = gr.Dropdown(
                         choices=list(MCC_CATEGORIES.keys()),
                         value="Groceries",
@@ -1136,13 +981,12 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         info="Select the category first"
                     )
                     
-                    # MERCHANT DROPDOWN (now dynamic)
                     merchant_dropdown = gr.Dropdown(
                         choices=MERCHANTS_BY_CATEGORY["Groceries"],
                         value="Whole Foods",
                         label="🏪 Merchant Name",
                         info="Select merchant (changes based on category)",
-                        allow_custom_value=True  # Allows typing custom merchants
+                        allow_custom_value=True
                     )
                     
                     amount_input = gr.Number(
@@ -1158,7 +1002,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         value=""
                     )
                     
-                    # Advanced options
                     with gr.Accordion("⚙️ Advanced Options", open=False):
                         use_custom_mcc = gr.Checkbox(
                             label="Use Custom MCC Code",
@@ -1184,7 +1027,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         variant="primary",
                         size="lg"
                     )
-                
                     
                 with gr.Column(scale=2):
                     gr.Markdown("### 💡 Recommendation")
@@ -1193,8 +1035,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         elem_classes=["recommendation-output"]
                     )
                     recommendation_chart = gr.Plot()
-                    
-                    
             
             def update_merchant_choices(category):
                 """Update merchant dropdown based on selected category"""
@@ -1204,14 +1044,12 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     value=merchants[0] if merchants else ""
                 )
             
-            # Connect category change to merchant update
             category_dropdown.change(
                 fn=update_merchant_choices,
                 inputs=[category_dropdown],
                 outputs=[merchant_dropdown]
             )
             
-            # Stats and comparison below
             with gr.Row():
                 with gr.Column():
                     gr.Markdown("### 📊 Quick Stats")
@@ -1221,34 +1059,19 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     gr.Markdown("### 🔄 Card Comparison")
                     comparison_output = gr.Markdown()
             
-            
             recommend_btn.click(
-                                    fn=get_recommendation_with_agent,  
-                                    inputs=[user_dropdown, merchant_dropdown, category_dropdown, amount_input],
-                                    outputs=[recommendation_output, recommendation_chart]
-                                )
-            # def get_recommendation_with_loading(user_id, merchant, category, amount):
-            #     """Wrapper to show loading state"""
-            #     # Show loading first
-            #     yield "⏳ **Loading recommendation...** Please wait...", None
-                
-            #     # Get actual result
-            #     result = get_recommendation_with_ai(user_id, merchant, category, amount)
-            #     yield result
+                fn=get_recommendation_with_agent,  
+                inputs=[user_dropdown, merchant_dropdown, category_dropdown, amount_input],
+                outputs=[recommendation_output, recommendation_chart]
+            )
             
-            # recommend_btn.click(
-            #     fn=get_recommendation_with_loading,
-            #     inputs=[user_dropdown, merchant_dropdown, category_dropdown, amount_input],
-            #     outputs=[recommendation_output, recommendation_chart]
-            # )
-            # Examples
             gr.Markdown("### 📝 Example Transactions")
             gr.Examples(
                 examples=EXAMPLES,
                 inputs=[
                     user_dropdown,
-                    category_dropdown,      # Swapped order
-                    merchant_dropdown,      # Swapped order
+                    category_dropdown,
+                    merchant_dropdown,
                     amount_input,
                     use_custom_mcc,
                     custom_mcc_input,
@@ -1263,11 +1086,9 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 cache_examples=False
             )
         
-        # ========== Tab 2: Analytics with Charts (ENHANCED) ==========
         with gr.Tab("📊 Analytics"):
             gr.Markdown("## 🎯 Your Rewards Optimization Dashboard")
             
-            # User selector for analytics
             with gr.Row():
                 analytics_user = gr.Dropdown(
                     choices=SAMPLE_USERS,
@@ -1281,7 +1102,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     scale=1
                 )
             
-            # Top Metrics Row (Dynamic)
             metrics_display = gr.HTML(
                 value="""
                 <div style="display: flex; gap: 10px; flex-wrap: wrap;">
@@ -1306,34 +1126,26 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
             )
             
             gr.Markdown("---")
-            
-            # ========== CHARTS SECTION (NEW) ==========
             gr.Markdown("## 📊 Visual Analytics")
             
-            # Row 1: Spending Chart + Optimization Gauge
             with gr.Row():
                 with gr.Column(scale=2):
                     spending_chart = gr.Plot(label="Spending vs Rewards")
                 with gr.Column(scale=1):
                     optimization_gauge = gr.Plot(label="Your Score")
             
-            # Row 2: Pie Chart + Card Performance
             with gr.Row():
                 with gr.Column(scale=1):
                     rewards_pie_chart = gr.Plot(label="Rewards Distribution")
                 with gr.Column(scale=1):
                     card_performance_chart = gr.Plot(label="Top Performing Cards")
             
-            # Row 3: Trend Line Chart (Full Width)
             with gr.Row():
                 trend_chart = gr.Plot(label="12-Month Trends")
             
             gr.Markdown("---")
-            
-            # ========== DATA TABLES SECTION ==========
             gr.Markdown("## 📋 Detailed Breakdown")
             
-            # Detailed Analytics (Dynamic)
             with gr.Row():
                 with gr.Column(scale=1):
                     gr.Markdown("### 💰 Category Spending Breakdown")
@@ -1377,7 +1189,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
             
             gr.Markdown("---")
             
-            # Spending Forecast (Dynamic)
             forecast_display = gr.Markdown(
                 value="""
         ### 🔮 Next Month Forecast
@@ -1394,21 +1205,17 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 """
             )
             
-            # Status indicator
             analytics_status = gr.Markdown(
                 value="*Analytics loaded for u_alice*",
                 elem_classes=["status-text"]
             )
         
-        # ===================== Analytics Update Function (ENHANCED) =====================
         def update_analytics_with_charts(user_id: str):
             """Fetch and format analytics with charts for selected user"""
             
             try:
-                # Fetch analytics data from API
                 result = client.get_user_analytics(user_id)
                 
-                # DEBUG: Print what we received
                 print("=" * 60)
                 print(f"DEBUG: Analytics for {user_id}")
                 print(f"Success: {result.get('success')}")
@@ -1418,7 +1225,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     print(f"Total rewards: {result['data'].get('total_rewards')}")
                 print("=" * 60)
                 
-                # Check if request was successful
                 if not result.get('success'):
                     error_msg = result.get('error', 'Unknown error')
                     empty_fig = create_empty_chart(f"Error: {error_msg}")
@@ -1431,10 +1237,8 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         f"*Error: {error_msg}*"
                     )
                 
-                # ✅ Extract the actual data
                 analytics_data = result.get('data', {})
                 
-                # Verify we have data
                 if not analytics_data:
                     empty_fig = create_empty_chart("No analytics data available")
                     return (
@@ -1446,51 +1250,36 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         "*No data available*"
                     )
                 
-                # Import chart functions
-                from utils.formatters import (
-                    format_analytics_metrics,
-                    create_spending_chart,
-                    create_rewards_pie_chart,
-                    create_optimization_gauge,
-                    create_trend_line_chart,
-                    create_card_performance_chart
-                )
-                
-                # Format text data (pass unwrapped data)
                 metrics_html, table_md, insights_md, forecast_md = format_analytics_metrics(analytics_data)
                 
-                # Generate charts (pass unwrapped data)
                 spending_fig = create_spending_chart(analytics_data)
                 pie_fig = create_rewards_pie_chart(analytics_data)
                 gauge_fig = create_optimization_gauge(analytics_data)
                 trend_fig = create_trend_line_chart(analytics_data)
                 performance_fig = create_card_performance_chart(analytics_data)
                 
-                # Status message
                 from datetime import datetime
                 status = f"*Analytics updated for {user_id} at {datetime.now().strftime('%I:%M %p')}*"
                 
                 return (
-                    metrics_html,      # Metric cards
-                    spending_fig,      # Spending bar chart
-                    gauge_fig,         # Optimization gauge
-                    pie_fig,           # Rewards pie chart
-                    performance_fig,   # Card performance chart
-                    trend_fig,         # Trend line chart
-                    table_md,          # Spending table
-                    insights_md,       # Insights text
-                    forecast_md,       # Forecast text
-                    status             # Status message
+                    metrics_html,
+                    spending_fig,
+                    gauge_fig,
+                    pie_fig,
+                    performance_fig,
+                    trend_fig,
+                    table_md,
+                    insights_md,
+                    forecast_md,
+                    status
                 )
                 
             except Exception as e:
-                import traceback
                 error_details = traceback.format_exc()
                 error_msg = f"❌ Error loading analytics: {str(e)}"
                 print(error_msg)
                 print(error_details)
                 
-                # Return empty/error states
                 empty_fig = create_empty_chart("Error loading chart")
                 
                 return (
@@ -1501,7 +1290,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     "Error loading forecast",
                     f"*{error_msg}*"
                 )
-                
         
         def create_empty_chart(message: str) -> go.Figure:
             """Helper to create empty chart with message"""
@@ -1515,7 +1303,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
             fig.update_layout(height=400, template='plotly_white')
             return fig
         
-        # Connect analytics refresh to button and dropdown
         refresh_analytics_btn.click(
             fn=update_analytics_with_charts,
             inputs=[analytics_user],
@@ -1549,8 +1336,7 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 analytics_status
             ]
         )
-        # Tab 3: Chat (NEW!)
-        # Tab 3: Chat (NEW!)
+        
         with gr.Tab("💬 Ask AI"):
             gr.Markdown("## Chat with RewardPilot AI")
             gr.Markdown("*Ask questions about credit cards, rewards, and your spending*")
@@ -1576,7 +1362,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 if not message.strip():
                     return "", chat_history
                 
-                # Get user context
                 user_context = {}
                 try:
                     analytics = client.get_user_analytics(user_id)
@@ -1595,7 +1380,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                         'top_category': 'Groceries'
                     }
                 
-                # Generate AI response
                 try:
                     if config.LLM_ENABLED:
                         bot_response = llm.chat_response(message, user_context, chat_history)
@@ -1611,7 +1395,6 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
             msg.submit(respond, [msg, chatbot, chat_user], [msg, chatbot])
             send_btn.click(respond, [msg, chatbot, chat_user], [msg, chatbot])
             
-            # ✅ RESTORED: Example questions
             gr.Markdown("### 💡 Try asking:")
             gr.Examples(
                 examples=[
@@ -1623,7 +1406,7 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 ],
                 inputs=[msg]
             )
-        # ========== Tab: Agent Insights (NEW) ==========
+        
         with gr.Tab("🤖 Agent Insights"):
             gr.Markdown("""
             ## How the Autonomous Agent Works
@@ -1697,8 +1480,7 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
             
             **Try it out in the "Get Recommendation" tab!** 🚀
             """)
-
-        # ========== Tab 3: About ==========
+        
         with gr.Tab("ℹ️ About"):
             gr.Markdown(
                 """
@@ -1714,7 +1496,6 @@ RewardPilot is an AI-powered credit card recommendation system built using the *
 - 📊 **Interactive visualizations**
 
 ### Features
-
 - Smart card recommendations for every purchase
 - AI-generated personalized insights
 - Visual analytics dashboard
@@ -1722,22 +1503,19 @@ RewardPilot is an AI-powered credit card recommendation system built using the *
 - Real-time cap warnings
 - Multi-card comparison
 
-The system consists of multiple microservices:
-
+The system consists of multiple microservices
 1. **Smart Wallet** - Analyzes transaction context and selects optimal cards
 2. **Rewards-RAG** - Retrieves detailed card benefit information using RAG
 3. **Spend-Forecast** - Predicts spending patterns and warns about cap risks
 4. **Orchestrator** - Coordinates all services for comprehensive recommendations
 
 ### 🎯 How It Works
-
 1. **Enter Transaction Details** - Merchant, amount, category
 2. **AI Analysis** - System analyzes your wallet and transaction context
 3. **Get Recommendation** - Receive the best card with detailed reasoning
 4. **Maximize Rewards** - Earn more points/cashback on every purchase
 
 ### 🔧 Technology Stack
-
 - **Backend:** FastAPI, Python
 - **Frontend:** Gradio
 - **AI/ML:** RAG (Retrieval-Augmented Generation)
@@ -1745,7 +1523,6 @@ The system consists of multiple microservices:
 - **Deployment:** Hugging Face Spaces
 
 ### 📚 MCC Categories Supported
-
 - Groceries (5411)
 - Restaurants (5812)
 - Gas Stations (5541)
@@ -1755,11 +1532,9 @@ The system consists of multiple microservices:
 - And many more...
 
 ### 🎓 Built For
-
 **MCP 1st Birthday Hackathon** - Celebrating one year of the Model Context Protocol
 
 ### 👨‍💻 Developer
-
 Built with ❤️ for the MCP community
 
 ---
@@ -1769,18 +1544,15 @@ Built with ❤️ for the MCP community
 """
             )
         
-        # ========== Tab 4: API Documentation ==========
         with gr.Tab("📖 API Docs"):
             gr.Markdown(
                 """
 ## API Endpoints
 
 ### Orchestrator API
-
 **Base URL:** `https://mcp-1st-birthday-rewardpilot-orchestrator.hf.space`
 
 #### POST `/recommend`
-
 Get comprehensive card recommendation.
 
 **Request:**
@@ -1792,44 +1564,11 @@ Get comprehensive card recommendation.
   "amount_usd": 125.50,
   "transaction_date": "2025-01-15"
 }
-```
-
-**Response:**
-```json
-{
-  "user_id": "u_alice",
-  "merchant": "Whole Foods",
-  "amount_usd": 125.5,
-  "recommended_card": {
-    "card_id": "c_amex_gold",
-    "card_name": "American Express Gold Card",
-    "reward_rate": 4.0,
-    "reward_amount": 502.0,
-    "category": "Groceries",
-    "reasoning": "Earns 4x points on Groceries"
-  },
-  "alternative_cards": ["..."],
-  "rag_insights": { "...": "..." },
-  "forecast_warning": { "...": "..." },
-  "services_used": ["smart_wallet", "rewards_rag", "spend_forecast"],
-  "final_recommendation": "..."
-}
-```
-
-### Other Services
-
-- Smart Wallet: https://mcp-1st-birthday-rewardpilot-smart-wallet.hf.space  
-- Rewards-RAG: https://mcp-1st-birthday-rewardpilot-rewards-rag.hf.space  
-- Spend-Forecast: https://mcp-1st-birthday-rewardpilot-spend-forecast.hf.space  
-
-### Interactive Docs
-
-Visit `/docs` on any service for interactive Swagger UI documentation.
-
-### cURL Examples
-
-```bash
-# Get recommendation
+Other Services
+Smart Wallet: https://mcp-1st-birthday-rewardpilot-smart-wallet.hf.space
+Rewards-RAG: https://mcp-1st-birthday-rewardpilot-rewards-rag.hf.space
+Spend-Forecast: https://mcp-1st-birthday-rewardpilot-spend-forecast.hf.space
+Interactive DocsVisit /docs on any service for interactive Swagger UI documentation.cURL ExamplesbashCopy code[data-radix-scroll-area-viewport]{scrollbar-width:none;-ms-overflow-style:none;-webkit-overflow-scrolling:touch;}[data-radix-scroll-area-viewport]::-webkit-scrollbar{display:none}# Get recommendation
 curl -X POST https://mcp-1st-birthday-rewardpilot-orchestrator.hf.space/recommend \\
   -H "Content-Type: application/json" \\
   -d '{
@@ -1837,10 +1576,8 @@ curl -X POST https://mcp-1st-birthday-rewardpilot-orchestrator.hf.space/recommen
     "merchant": "Whole Foods",
     "mcc": "5411",
     "amount_usd": 125.50
-  }'
-```
-"""
-            )
+  }'"""
+)
 
 # ===================== Launch App =====================
 if __name__ == "__main__":
@@ -1848,4 +1585,4 @@ if __name__ == "__main__":
         server_name="0.0.0.0",
         server_port=7860,
         share=False,
-    )
+    )