Update app.py

app.py

@@ -546,88 +546,69 @@ def get_recommendation_with_agent(user_id, merchant, category, amount):
 - <60: Suboptimal ❌
 """
         
+        # Extract key points from reasoning (first 3 sentences or bullet points)
+        reasoning_lines = reasoning.split('. ')[:3]
+        reasoning_bullets = '\n'.join([f"- {line.strip()}." for line in reasoning_lines if line.strip()])
+        
         output = f"""
-## 🤖 AI Agent Recommendation
-
-### 💳 Recommended Card: **{card_name}**
-
-**Rewards Earned:** ${rewards_earned:.2f} ({rewards_rate})  
-**Confidence:** {confidence*100:.0f}%
-
----
-
-### 🧠 Agent's Reasoning:
-
-{reasoning}
-
----
-"""
+        ## 🎯 Recommended: **{card_name}**
+        
+        | Metric | Value |
+        |--------|-------|
+        | 💰 **Rewards Earned** | ${rewards_earned:.2f} ({rewards_rate}) |
+        | 📊 **Confidence** | {confidence*100:.0f}% |
+        | 📈 **Annual Potential** | ${net_benefit:.2f}/year |
+        | ⭐ **Optimization Score** | {optimization_score}/100 |
+        
+        ---
+        
+        ### 🧠 Why This Card?
+        
+        {reasoning_bullets}
+        
+        ---
+        """
         
+        # Alternatives in compact table format
         if alternatives:
-            output += "\n### 🔄 Alternative Options:\n\n"
+            output += "\n### 🔄 Alternative Options\n\n"
+            output += "| Card | Rewards | Why? |\n"
+            output += "|------|---------|------|\n"
             for alt in alternatives[:3]:
                 alt_card_id = alt.get('card', '')
                 alt_card_name = card_name_map.get(alt_card_id, alt_card_id.replace('c_', '').replace('_', ' ').title())
-                alt_reason = alt.get('reason', '')
-                output += f"**{alt_card_name}:**\n{alt_reason}\n\n"
+                alt_reason = alt.get('reason', 'Good alternative')
+                # Truncate reason to first sentence
+                alt_reason_short = (lambda x: x[:60] + '...' if len(x) > 60 else x)(alt_reason.split('.')[0])
+                output += f"| {alt_card_name} | ${rec_reward * 0.8:.2f} | {alt_reason_short} |\n"
+            output += "\n---\n"
         
         if warnings:
-            output += "\n### ⚠️ Important Warnings:\n\n"
+            output += "\n### ⚠️ Alerts\n\n"
             for warning in warnings:
-                output += f"- {warning}\n"
+                # Shorten warnings to key info
+                warning_short = warning[:80] + '...' if len(warning) > 80 else warning
+                output += f"- {warning_short}\n"
+            output += "\n---\n"
         
         output += f"""
-### 💰 Annual Impact
-
-- **Potential Savings:** ${net_benefit:.2f}/year
-- **Optimization Score:** {optimization_score}/100
-
 <details>
-<summary>📊 <b>How is this calculated?</b> (Click to expand)</summary>
-
-#### 💡 Calculation Assumptions:
+<summary>📊 <b>Annual Impact Calculation</b> (Click to expand)</summary>
 
-**Step 1: Estimate Annual Spending**
+**Assumptions:**
+- Transaction: ${amount_float:.2f} at {merchant} ({category})
+- Frequency: {frequency_label} → ${annual_spend:.2f}/year
 
-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}**
+**Rewards Breakdown:**
 
 {calc_table}
 
-**Step 3: Compare to Baseline**
-
-{comparison_text}
-
----
+**vs. Baseline (1% card):** ${baseline_rewards:.2f}/year  
+**Net Benefit:** ${net_benefit:+.2f}/year {"🎉" if net_benefit > 0 else "⚠️"}
 
-#### 📈 Optimization Score: {optimization_score}/100
-
-{score_details}
-
----
-
-#### 🔍 Card Details:
-
-- **Reward Rate:** {reward_rate_value}% on {category}
-- **Monthly Cap:** {"$" + str(monthly_cap) if monthly_cap else "None"}
-- **Annual Cap:** {"$" + str(annual_cap) if annual_cap else "None"}
-- **Base Rate:** {base_rate}% (after cap)
-- **Annual Fee:** ${annual_fee}
+**Card Details:** {reward_rate_value}% on {category} | Cap: {"$" + str(monthly_cap or annual_cap) if (monthly_cap or annual_cap) else "None"} | Fee: ${annual_fee}
 
 </details>
-
----
-
-#### 📊 Transaction Details:
-
-- **Amount:** ${amount_float:.2f}
-- **Merchant:** {merchant}
-- **Category:** {category}
-- **MCC Code:** {transaction['mcc']}
 """
         
         chart = create_agent_recommendation_chart_enhanced(result)
@@ -1205,65 +1186,51 @@ def load_user_forecast(user_id: str):
                 {'category': 'Gas', 'predicted': 450.00, 'confidence': 0.85, 'emoji': '⛽'},
             ],
             'recommendations': [
-                "Consider using Amex Gold for groceries to maximize 4x points",
-                "You're approaching your Citi Custom Cash $500 monthly cap",
-                "Travel spending is predicted to increase next month"
+                "Use Amex Gold for groceries (4x points)",
+                "Approaching Citi Custom Cash $500 cap",
+                "Travel spending predicted to increase"
             ],
             'optimization_potential': 45.50
         }
         
         confidence = forecast_data.get('confidence', 0.85)
+        confidence_badge = "High" if confidence > 0.9 else "Medium" if confidence > 0.75 else "Low"
         confidence_color = '#4caf50' if confidence > 0.9 else '#ff9800' if confidence > 0.75 else '#f44336'
         
-        # Return as Markdown instead of HTML
+        # Compact output
         output = f"""
 ## 🔮 Next Month Forecast
 
-**Confidence Score:** {confidence*100:.0f}% <span style="background: {confidence_color}; color: white; padding: 2px 8px; border-radius: 12px; font-size: 12px; font-weight: 600;">High Confidence</span>
-
----
+**Confidence:** {confidence*100:.0f}% ({confidence_badge})
 
-### 📊 Predicted Metrics
+### 📊 Summary
 
 | Metric | Amount |
 |--------|--------|
 | 💰 **Total Spending** | ${forecast_data['next_month_spending']:.2f} |
 | 🎁 **Expected Rewards** | ${forecast_data['predicted_rewards']:.2f} |
-| 📈 **Optimization Potential** | +${forecast_data['optimization_potential']:.2f} |
+| 📈 **Extra with Optimization** | +${forecast_data['optimization_potential']:.2f} |
 
 ---
 
-## 📊 Category Breakdown
+### 📊 Top Categories
 
+| Category | Predicted | Confidence |
+|----------|-----------|------------|
 """
         
         for cat in forecast_data['top_categories']:
-            output += f"""
-### {cat['emoji']} {cat['category']}
-
-- **Predicted Amount:** ${cat['predicted']:.2f} (Confidence: {cat['confidence']*100:.0f}%)
-- **Recommendation:** Use best card for this category
-- **Potential Rewards:** Based on optimal card selection
-
-"""
+            output += f"| {cat['emoji']} {cat['category']} | ${cat['predicted']:.2f} | {cat['confidence']*100:.0f}% |\n"
         
-        output += "\n---\n\n## 💡 Optimization Strategies\n\n"
+        output += "\n---\n\n### 💡 Action Items\n\n"
         for i, rec in enumerate(forecast_data['recommendations'], 1):
             output += f"{i}. {rec}\n"
         
         output += """
-
 ---
 
-### 📈 How to Maximize Rewards
-
-1. **Track your spending caps** - Don't miss out on bonus categories
-2. **Use category-specific cards** - Match each purchase to the best card
-3. **Monitor monthly limits** - Switch cards when you hit caps
-4. **Plan ahead** - Use these predictions to optimize your wallet
-
-"""
-        
+**💡 Tip:** Check the Analytics tab to see your current spending patterns and optimization opportunities.
+"""        
         # Create forecast chart
         fig = go.Figure()
         
@@ -2205,24 +2172,6 @@ with gr.Blocks(
             )
             
             
-            forecast_output = gr.HTML(value="<p><em>Loading forecast...</em></p>")
-            forecast_chart = gr.Plot()
-            
-            def update_forecast(user_id):
-                return load_user_forecast(user_id)
-            
-            forecast_user.change(
-                fn=update_forecast,
-                inputs=[forecast_user],
-                outputs=[forecast_output, forecast_chart]
-            )
-            
-            refresh_forecast_btn.click(
-                fn=update_forecast,
-                inputs=[forecast_user],
-                outputs=[forecast_output, forecast_chart]
-            )
-            
             app.load(
                 fn=update_forecast,
                 inputs=[forecast_user],