Update matching logic: AI scores all candidates, lower threshold, absolute amount, prompt improvements

feedback_logger.py

@@ -0,0 +1,60 @@
+from dataclasses import dataclass
+from datetime import datetime, timedelta
+from typing import List, Optional
+import json
+import os
+
+@dataclass
+class FeedbackLog:
+    transaction_id: str
+    original_match: str
+    correction: str
+    reason: str
+    timestamp: datetime
+    user_id: str
+
+class FeedbackLogger:
+    def __init__(self, log_file: str = "feedback_logs.json"):
+        self.log_file = log_file
+        self.logs: List[FeedbackLog] = self._load_logs()
+    
+    def _load_logs(self) -> List[FeedbackLog]:
+        if not os.path.exists(self.log_file):
+            return []
+        
+        try:
+            with open(self.log_file, 'r') as f:
+                data = json.load(f)
+                return [FeedbackLog(**log) for log in data]
+        except:
+            return []
+    
+    def _save_logs(self):
+        with open(self.log_file, 'w') as f:
+            json.dump([{
+                'transaction_id': log.transaction_id,
+                'original_match': log.original_match,
+                'correction': log.correction,
+                'reason': log.reason,
+                'timestamp': log.timestamp.isoformat(),
+                'user_id': log.user_id
+            } for log in self.logs], f, indent=2)
+    
+    def log_override(self, transaction_id: str, original_match: str, correction: str, reason: str, user_id: str):
+        log = FeedbackLog(
+            transaction_id=transaction_id,
+            original_match=original_match,
+            correction=correction,
+            reason=reason,
+            timestamp=datetime.now(),
+            user_id=user_id
+        )
+        self.logs.append(log)
+        self._save_logs()
+    
+    def get_logs_by_transaction(self, transaction_id: str) -> List[FeedbackLog]:
+        return [log for log in self.logs if log.transaction_id == transaction_id]
+    
+    def get_recent_logs(self, days: int = 30) -> List[FeedbackLog]:
+        cutoff = datetime.now() - timedelta(days=days)
+        return [log for log in self.logs if log.timestamp > cutoff]