Add comprehensive debug logging to sample data loading

backend/database/__init__.py

@@ -81,35 +81,44 @@ def test_database_connection():
 
 def add_sample_data_for_hf():
     """Add simple sample data for HF Spaces using direct SQL."""
+    print("🚀 add_sample_data_for_hf() started")
+    
     if not os.getenv("SPACE_ID"):
+        print("❌ Not in HF Spaces environment, skipping sample data")
         return  # Only run on HF Spaces
         
-    print(f"🔍 HF Spaces environment check:")
+    print(f"🔍 HF Spaces environment confirmed:")
     print(f"   • SPACE_ID: {os.getenv('SPACE_ID')}")
     print(f"   • Database URL: {DATABASE_URL}")
+    print(f"   • Engine: {engine}")
     
     try:
+        print("🔧 Creating database connection...")
         # Use direct connection to avoid session issues
         with engine.connect() as conn:
+            print("✅ Database connection successful")
+            
             # Begin transaction for atomic operations
+            print("🔄 Starting transaction...")
             trans = conn.begin()
             
             try:
+                print("🔍 Checking existing data...")
                 # Check if data already exists
                 result = conn.execute("SELECT COUNT(*) FROM traces").fetchone()
                 existing_traces = result[0] if result else 0
+                print(f"   • Found {existing_traces} existing traces")
                 
                 result = conn.execute("SELECT COUNT(*) FROM knowledge_graphs").fetchone()  
                 existing_kgs = result[0] if result else 0
-                
-                print(f"   • Existing traces: {existing_traces}")
-                print(f"   • Existing KGs: {existing_kgs}")
+                print(f"   • Found {existing_kgs} existing knowledge graphs")
                 
                 if existing_traces > 0 or existing_kgs > 0:
-                    print("📊 Sample data already exists, skipping...")
+                    print("📊 Sample data already exists, skipping insertion...")
                     return
                 
-                print("🎯 Adding sample data using direct SQL...")
+                print("🎯 No existing data found. Adding sample data using direct SQL...")
+                print("📝 Preparing sample trace data...")
                 
                 import json
                 import uuid
@@ -126,11 +135,16 @@ def add_sample_data_for_hf():
     {"role": "user", "content": "Thank you for the quick resolution!", "timestamp": "2024-08-31T10:04:00Z", "sentiment": "satisfied"}
 ]'''
                 
+                print("🔑 Generating unique identifiers...")
                 # Generate IDs
                 trace_id = str(uuid.uuid4())
                 content_hash = hashlib.sha256(sample_trace_content.encode()).hexdigest()
                 now = datetime.utcnow()
+                print(f"   • Trace ID: {trace_id}")
+                print(f"   • Content hash: {content_hash[:16]}...")
+                print(f"   • Timestamp: {now}")
                 
+                print("💾 Inserting sample trace...")
                 # Insert trace
                 conn.execute(
                     """INSERT INTO traces (trace_id, filename, title, description, content, content_hash, 
@@ -143,7 +157,9 @@ def add_sample_data_for_hf():
                      "processed", '["demo", "customer_service", "multi_agent"]', 
                      '{"scenario": "customer_service", "agents": ["RouterAgent", "OrderAgent", "CompensationAgent", "SupervisorAgent"]}')
                 )
+                print("✅ Trace inserted successfully")
                 
+                print("📊 Inserting knowledge graph...")
                 # Insert knowledge graph with correct field names
                 conn.execute(
                     """INSERT INTO knowledge_graphs (filename, entity_count, relation_count,
@@ -151,10 +167,16 @@ def add_sample_data_for_hf():
                        VALUES (?, ?, ?, ?, ?, ?, ?, ?)""",
                     ("demo_kg.json", 5, 4, "completed", trace_id, 0, 1, "demo_run")
                 )
+                print("✅ Knowledge graph inserted successfully")
                 
+                print("🔍 Retrieving knowledge graph ID...")
                 # Get KG ID
                 kg_result = conn.execute("SELECT id FROM knowledge_graphs WHERE trace_id = ?", (trace_id,))
-                kg_id = kg_result.fetchone()[0]
+                kg_row = kg_result.fetchone()
+                if not kg_row:
+                    raise Exception("Failed to retrieve knowledge graph ID")
+                kg_id = kg_row[0]
+                print(f"   • Knowledge graph ID: {kg_id}")
                 
                 # Insert sample entities with correct field names
                 entities = [
@@ -165,9 +187,11 @@ def add_sample_data_for_hf():
                     ("issue_1", "issue", "PaymentSystemFailure", '{"severity": "high", "impact": "service_disruption"}')
                 ]
                 
+                print("👥 Inserting sample entities...")
                 # Insert entities and store their database IDs
                 entity_db_ids = {}
-                for entity_id, entity_type, name, properties in entities:
+                for i, (entity_id, entity_type, name, properties) in enumerate(entities, 1):
+                    print(f"   • Inserting entity {i}/5: {name} ({entity_type})")
                     conn.execute(
                         """INSERT INTO entities (graph_id, entity_id, type, name, properties)
                            VALUES (?, ?, ?, ?, ?)""",
@@ -175,8 +199,14 @@ def add_sample_data_for_hf():
                     )
                     # Get the database ID for this entity
                     result = conn.execute("SELECT id FROM entities WHERE graph_id = ? AND entity_id = ?", (kg_id, entity_id))
-                    entity_db_ids[entity_id] = result.fetchone()[0]
+                    row = result.fetchone()
+                    if not row:
+                        raise Exception(f"Failed to retrieve database ID for entity: {entity_id}")
+                    entity_db_ids[entity_id] = row[0]
+                    print(f"     → Entity DB ID: {entity_db_ids[entity_id]}")
+                print("✅ All entities inserted successfully")
                 
+                print("🔗 Inserting sample relations...")
                 # Insert sample relations using database IDs as foreign keys
                 relations = [
                     ("rel_1", "agent_1", "routes_to", "agent_2", '{"priority": "high", "success": true}'),
@@ -185,32 +215,48 @@ def add_sample_data_for_hf():
                     ("rel_4", "agent_4", "resolves", "issue_1", '{"method": "manual_override"}')
                 ]
                 
-                for relation_id, from_entity, relation_type, to_entity, properties in relations:
+                for i, (relation_id, from_entity, relation_type, to_entity, properties) in enumerate(relations, 1):
                     source_db_id = entity_db_ids[from_entity]
                     target_db_id = entity_db_ids[to_entity]
+                    print(f"   • Inserting relation {i}/4: {from_entity} --{relation_type}--> {to_entity}")
+                    print(f"     → Source DB ID: {source_db_id}, Target DB ID: {target_db_id}")
                     conn.execute(
                         """INSERT INTO relations (graph_id, relation_id, type, source_id, target_id, properties) 
                            VALUES (?, ?, ?, ?, ?, ?)""",
                         (kg_id, relation_id, relation_type, source_db_id, target_db_id, properties)
                     )
+                print("✅ All relations inserted successfully")
                 
+                print("💾 Committing transaction...")
                 # Commit transaction
                 trans.commit()
+                print("✅ Transaction committed successfully")
                 
+                print("🔍 Verifying final data counts...")
                 # Verify data
                 final_traces = conn.execute("SELECT COUNT(*) FROM traces").fetchone()[0]
                 final_kgs = conn.execute("SELECT COUNT(*) FROM knowledge_graphs").fetchone()[0]
                 final_entities = conn.execute("SELECT COUNT(*) FROM entities").fetchone()[0]
                 final_relations = conn.execute("SELECT COUNT(*) FROM relations").fetchone()[0]
                 
-                print("✅ Sample data added successfully!")
+                print("🎉 Sample data insertion completed successfully!")
+                print(f"   📊 Final counts:")
                 print(f"   • Traces: {final_traces}")
                 print(f"   • Knowledge graphs: {final_kgs}")
                 print(f"   • Entities: {final_entities}")
                 print(f"   • Relations: {final_relations}")
+                print(f"   🎯 Expected: 1 trace, 1 KG, 5 entities, 4 relations")
+                
+                # Additional verification
+                if final_traces == 1 and final_kgs == 1 and final_entities == 5 and final_relations == 4:
+                    print("✅ All counts match expected values!")
+                else:
+                    print("⚠️  Counts don't match expected values")
                 
             except Exception as e:
+                print(f"❌ Error during transaction: {e}")
                 trans.rollback()
+                print("🔄 Transaction rolled back")
                 raise e
                 
     except Exception as e:
@@ -218,6 +264,7 @@ def add_sample_data_for_hf():
         import traceback
         print("Full error traceback:")
         traceback.print_exc()
+        print("🚨 Sample data loading failed completely")
 
 __all__ = [
     'get_db',