feat: include receipt tax amount in match-specific endpoint response

ai_matcher.py

@@ -107,12 +107,17 @@ class AIMatcher:
         Compare this receipt with this transaction and provide a confidence score (0-1) and brief reason.
         
         Receipt: {receipt.vendor}, ${receipt.amount}, {receipt.receipt_date.strftime('%Y-%m-%d')}
+        Receipt Description: {receipt.description}
+        Receipt Category: {receipt.category}
         Transaction: {transaction.vendor}, ${transaction.amount} (absolute: ${transaction_amount_abs}), {transaction.transaction_date.strftime('%Y-%m-%d')}
+        Transaction Notes: {transaction.notes}
         
         Differences:
         - Date difference: {date_diff} days
         - Amount difference: ${amount_diff} ({amount_percent_diff:.1f}%)
         - Vendor comparison: "{receipt.vendor}" vs "{transaction.vendor}"
+        - Description/Notes comparison: "{receipt.description}" vs "{transaction.notes}"
+        - Category: {receipt.category}
         
         Score this potential match based on how likely it is the correct match:
         
@@ -124,6 +129,8 @@ class AIMatcher:
         - Minimal similarity: 0.1-0.19
         - No meaningful similarity: 0.0-0.09
         
+        Consider description and category similarity in your scoring.
+        
         IMPORTANT: Return ONLY the score and reason separated by a pipe character.
         Format: [score]|[reason]
         Example: 0.85|Same vendor, same amount, 2 days apart