Improve check_user_has_category_data to comprehensively search budgets collection and fix logic to prioritize historical data over budget_amount

app/main.py

@@ -207,32 +207,23 @@ async def check_and_get_recommendations(request: RecommendationRequest, month: O
     # Check if user has previous data for this category
     has_data = recommender.check_user_has_category_data(request.user_id, request.category_id)
     
-    if has_data or request.budget_amount:
-        # Get recommendations for this specific category
-        # Pass budget_amount if provided
+    if has_data:
+        # User has previous data - use it for recommendations (ignore budget_amount if provided)
+        print(f"✅ User {request.user_id} has previous data for category {request.category_id} - using historical data")
         recommendations = recommender.get_recommendation_for_category(
             request.user_id, 
             request.category_id, 
             month, 
             year,
-            request.budget_amount
+            budget_amount=None  # Don't use budget_amount if user has historical data
         )
         
         if recommendations:
-            # Check if this is based on budget_amount only (no real historical data)
-            # If user doesn't have data but provided budget_amount, set has_previous_data=False
-            if not has_data and request.budget_amount:
-                return RecommendationResponse(
-                    has_previous_data=False,
-                    recommendations=recommendations,
-                    message="Recommendation generated based on provided budget amount. User does not have previous spending data for this category."
-                )
-            else:
-                return RecommendationResponse(
-                    has_previous_data=True,
-                    recommendations=recommendations,
-                    message=None
-                )
+            return RecommendationResponse(
+                has_previous_data=True,
+                recommendations=recommendations,
+                message=None
+            )
         else:
             # User has data but no recommendations generated (edge case)
             return RecommendationResponse(
@@ -240,24 +231,30 @@ async def check_and_get_recommendations(request: RecommendationRequest, month: O
                 recommendations=[],
                 message="User has previous data but no recommendations could be generated for this category."
             )
-    else:
-        # User doesn't have previous data, but if budget_amount is provided, generate recommendation anyway
-        if request.budget_amount and request.budget_amount > 0:
-            recommendations = recommender.get_recommendation_for_category(
-                request.user_id, 
-                request.category_id, 
-                month, 
-                year,
-                request.budget_amount
-            )
-            
-            if recommendations:
-                return RecommendationResponse(
-                    has_previous_data=False,
-                    recommendations=recommendations,
-                    message=f"Recommendation generated based on provided budget amount. User does not have previous data for this category."
-                )
+    elif request.budget_amount and request.budget_amount > 0:
+        # User doesn't have previous data, but provided budget_amount - generate recommendation based on it
+        print(f"ℹ️ User {request.user_id} does not have previous data for category {request.category_id} - using provided budget_amount")
+        recommendations = recommender.get_recommendation_for_category(
+            request.user_id, 
+            request.category_id, 
+            month, 
+            year,
+            request.budget_amount
+        )
         
+        if recommendations:
+            return RecommendationResponse(
+                has_previous_data=False,
+                recommendations=recommendations,
+                message="Recommendation generated based on provided budget amount. User does not have previous spending data for this category."
+            )
+        else:
+            return RecommendationResponse(
+                has_previous_data=False,
+                recommendations=None,
+                message="Could not generate recommendations even with provided budget amount."
+            )
+    else:
         # User doesn't have previous data and no budget_amount provided
         return RecommendationResponse(
             has_previous_data=False,

app/smart_recommendation.py

@@ -125,79 +125,106 @@ class SmartBudgetRecommender:
         Returns:
             True if user has previous data for this category, False otherwise
         """
-        # Check if user has budgets with this category_id
+        print(f"🔍 check_user_has_category_data: Checking for user_id={user_id}, category_id={category_id}")
+        
+        # Build comprehensive user query
+        user_conditions = []
+        try:
+            user_objid = ObjectId(user_id)
+            user_conditions = [
+                {"createdBy": user_objid},
+                {"createdBy": user_id},
+                {"user_id": user_objid},
+                {"user_id": user_id}
+            ]
+        except (ValueError, TypeError):
+            user_conditions = [
+                {"createdBy": user_id},
+                {"user_id": user_id}
+            ]
+        
+        # Build comprehensive category query - check all possible fields
+        category_conditions = []
+        try:
+            category_objid = ObjectId(category_id)
+            # Try as ObjectId
+            category_conditions = [
+                {"category": category_objid},
+                {"categoryId": category_objid},
+                {"headCategory": category_objid},
+                {"headCategories.headCategory": category_objid},
+                {"headCategories.categories.category": category_objid},
+                # Also try as string
+                {"category": category_id},
+                {"categoryId": category_id},
+                {"headCategory": category_id},
+                {"headCategories.headCategory": category_id},
+                {"headCategories.categories.category": category_id},
+            ]
+        except (ValueError, TypeError):
+            # category_id is not a valid ObjectId, try as string only
+            category_conditions = [
+                {"category": category_id},
+                {"categoryId": category_id},
+                {"headCategory": category_id},
+                {"headCategories.headCategory": category_id},
+                {"headCategories.categories.category": category_id},
+            ]
+        
+        # Combine user and category conditions
+        for user_cond in user_conditions:
+            for cat_cond in category_conditions:
+                budget_query = {**user_cond, **cat_cond}
+                budget_count = self.db.budgets.count_documents(budget_query)
+                if budget_count > 0:
+                    print(f"✅ Found {budget_count} budget(s) for user {user_id} with category_id {category_id}")
+                    print(f"   Query that matched: {budget_query}")
+                    return True
+        
+        # Also try a more comprehensive query using $and and $or
+        try:
+            comprehensive_query = {
+                "$and": [
+                    {"$or": user_conditions},
+                    {"$or": category_conditions}
+                ]
+            }
+            budget_count = self.db.budgets.count_documents(comprehensive_query)
+            if budget_count > 0:
+                print(f"✅ Found {budget_count} budget(s) using comprehensive query for user {user_id} with category_id {category_id}")
+                return True
+        except Exception as e:
+            print(f"⚠️ Error with comprehensive query: {e}")
+        
+        # Check expenses collection as fallback
         try:
-            # Try ObjectId format
             try:
                 category_objid = ObjectId(category_id)
-                budget_query = {
+                expense_query = {
                     "$or": [
-                        {"createdBy": ObjectId(user_id), "category": category_objid},
-                        {"createdBy": ObjectId(user_id), "categoryId": category_objid},
-                        {"createdBy": ObjectId(user_id), "headCategory": category_objid},
-                        {"createdBy": user_id, "category": category_objid},
-                        {"createdBy": user_id, "categoryId": category_objid},
-                        {"createdBy": user_id, "headCategory": category_objid},
                         {"user_id": ObjectId(user_id), "category": category_objid},
-                        {"user_id": user_id, "category": category_objid},
-                    ]
-                }
-            except (ValueError, TypeError):
-                # category_id is not a valid ObjectId, try as string
-                budget_query = {
-                    "$or": [
-                        {"createdBy": ObjectId(user_id), "category": category_id},
-                        {"createdBy": ObjectId(user_id), "categoryId": category_id},
-                        {"createdBy": ObjectId(user_id), "headCategory": category_id},
-                        {"createdBy": user_id, "category": category_id},
-                        {"createdBy": user_id, "categoryId": category_id},
-                        {"createdBy": user_id, "headCategory": category_id},
                         {"user_id": ObjectId(user_id), "category": category_id},
+                        {"user_id": user_id, "category": category_objid},
                         {"user_id": user_id, "category": category_id},
                     ]
                 }
-            
-            # Check budgets collection
-            budget_count = self.db.budgets.count_documents(budget_query)
-            if budget_count > 0:
-                print(f"✅ Found {budget_count} budget(s) for user {user_id} with category_id {category_id}")
-                return True
-            
-            # Also check if category_id is in headCategories array
-            head_cat_query = {
-                "$or": [
-                    {"createdBy": ObjectId(user_id), "headCategories.category": category_id},
-                    {"createdBy": user_id, "headCategories.category": category_id},
-                    {"user_id": ObjectId(user_id), "headCategories.category": category_id},
-                    {"user_id": user_id, "headCategories.category": category_id},
-                ]
-            }
-            head_cat_count = self.db.budgets.count_documents(head_cat_query)
-            if head_cat_count > 0:
-                print(f"✅ Found {head_cat_count} budget(s) with category_id {category_id} in headCategories for user {user_id}")
-                return True
-            
-            # Check expenses collection
-            try:
+            except (ValueError, TypeError):
                 expense_query = {
                     "$or": [
                         {"user_id": ObjectId(user_id), "category": category_id},
                         {"user_id": user_id, "category": category_id},
                     ]
                 }
-                expense_count = self.db.expenses.count_documents(expense_query)
-                if expense_count > 0:
-                    print(f"✅ Found {expense_count} expense(s) for user {user_id} with category_id {category_id}")
-                    return True
-            except Exception as e:
-                print(f"Error checking expenses: {e}")
-            
-            print(f"❌ No previous data found for user {user_id} with category_id {category_id}")
-            return False
             
+            expense_count = self.db.expenses.count_documents(expense_query)
+            if expense_count > 0:
+                print(f"✅ Found {expense_count} expense(s) for user {user_id} with category_id {category_id}")
+                return True
         except Exception as e:
-            print(f"Error checking user category data: {e}")
-            return False
+            print(f"Error checking expenses: {e}")
+        
+        print(f"❌ No previous data found for user {user_id} with category_id {category_id}")
+        return False
     
     def get_recommendation_for_category(self, user_id: str, category_id: str, month: int, year: int, budget_amount: Optional[float] = None) -> List[BudgetRecommendation]:
         """