fix: flag to enable and disable last_accessed

alembic/versions/e1ec1dcb50b6_add_last_accessed_to_data.py

@@ -5,6 +5,7 @@ Revises: 211ab850ef3d
 Create Date: 2025-11-04 21:45:52.642322  
   
 """  
+import os  
 from typing import Sequence, Union  
   
 from alembic import op  
@@ -17,6 +18,7 @@ down_revision: Union[str, None] = '211ab850ef3d'
 branch_labels: Union[str, Sequence[str], None] = None  
 depends_on: Union[str, Sequence[str], None] = None  
   
+  
 def _get_column(inspector, table, name, schema=None):    
     for col in inspector.get_columns(table, schema=schema):    
         if col["name"] == name:    
@@ -30,11 +32,15 @@ def upgrade() -> None:
     
     last_accessed_column = _get_column(insp, "data", "last_accessed")     
     if not last_accessed_column:    
+        # Always create the column for schema consistency  
         op.add_column('data',     
             sa.Column('last_accessed', sa.DateTime(timezone=True), nullable=True)    
         )    
-        # Optionally initialize with created_at values for existing records  
+          
-        op.execute("UPDATE data SET last_accessed = CURRENT_TIMESTAMP")  
+        # Only initialize existing records if feature is enabled  
+        enable_last_accessed = os.getenv("ENABLE_LAST_ACCESSED", "false").lower() == "true"  
+        if enable_last_accessed:  
+            op.execute("UPDATE data SET last_accessed = CURRENT_TIMESTAMP")  
     
     
 def downgrade() -> None:    

cognee/modules/retrieval/utils/access_tracking.py

@@ -4,7 +4,7 @@ import json
 from datetime import datetime, timezone  
 from typing import List, Any  
 from uuid import UUID  
-  
+import os 
 from cognee.infrastructure.databases.graph import get_graph_engine  
 from cognee.infrastructure.databases.relational import get_relational_engine  
 from cognee.modules.data.models import Data  
@@ -28,6 +28,9 @@ async def update_node_access_timestamps(items: List[Any]):
     items : List[Any]  
         List of items with payload containing 'id' field (from vector search results)  
     """ 
+    if os.getenv("ENABLE_LAST_ACCESSED", "false").lower() != "true":  
+        return  
+          
     if not items:  
         return  
       

cognee/tasks/cleanup/cleanup_unused_data.py

@@ -10,7 +10,7 @@ import json
 from datetime import datetime, timezone, timedelta    
 from typing import Optional, Dict, Any    
 from uuid import UUID    
-    
+import os    
 from cognee.infrastructure.databases.graph import get_graph_engine    
 from cognee.infrastructure.databases.vector import get_vector_engine    
 from cognee.infrastructure.databases.relational import get_relational_engine  
@@ -48,6 +48,42 @@ async def cleanup_unused_data(
     Dict[str, Any]    
         Cleanup results with status, counts, and timestamp    
     """   
+    # Check 1: Environment variable must be enabled  
+    if os.getenv("ENABLE_LAST_ACCESSED", "false").lower() != "true":  
+        logger.warning(  
+            "Cleanup skipped: ENABLE_LAST_ACCESSED is not enabled."  
+        )  
+        return {  
+            "status": "skipped",  
+            "reason": "ENABLE_LAST_ACCESSED not enabled",  
+            "unused_count": 0,  
+            "deleted_count": {},  
+            "cleanup_date": datetime.now(timezone.utc).isoformat()  
+        }  
+      
+    # Check 2: Verify tracking has actually been running  
+    db_engine = get_relational_engine()  
+    async with db_engine.get_async_session() as session:  
+        # Count records with non-NULL last_accessed  
+        tracked_count = await session.execute(  
+            select(sa.func.count(Data.id)).where(Data.last_accessed.isnot(None))  
+        )  
+        tracked_records = tracked_count.scalar()  
+          
+        if tracked_records == 0:  
+            logger.warning(  
+                "Cleanup skipped: No records have been tracked yet. "  
+                "ENABLE_LAST_ACCESSED may have been recently enabled. "  
+                "Wait for retrievers to update timestamps before running cleanup."  
+            )  
+            return {  
+                "status": "skipped",  
+                "reason": "No tracked records found - tracking may be newly enabled",  
+                "unused_count": 0,  
+                "deleted_count": {},  
+                "cleanup_date": datetime.now(timezone.utc).isoformat()  
+            }  
+      
     logger.info(    
         "Starting cleanup task",    
         days_threshold=days_threshold,