t6_mem0_v2/check-store-sync.py

#!/usr/bin/env python3
"""Check synchronization between Supabase and Neo4j stores"""
import asyncio
from mem0 import Memory
from config import mem0_config
from neo4j import GraphDatabase

async def check_stores():
    """Check memory counts in both stores"""
    print("=" * 60)
    print("Memory Store Synchronization Check")
    print("=" * 60)

    # Initialize mem0
    memory = Memory.from_config(mem0_config)

    # Check Supabase (vector store)
    print("\n[1] Checking Supabase (Vector Store)...")
    try:
        # Get all memories - this queries the vector store
        result = memory.get_all()
        supabase_memories = result.get('results', []) if isinstance(result, dict) else result
        print(f"✓ Supabase memories count: {len(supabase_memories)}")

        if supabase_memories:
            print("\nMemories in Supabase:")
            for i, mem in enumerate(supabase_memories[:5], 1):  # Show first 5
                if isinstance(mem, dict):
                    print(f"  {i}. ID: {mem.get('id')}, Memory: {mem.get('memory', 'N/A')[:50]}")
                else:
                    print(f"  {i}. {str(mem)[:50]}")
            if len(supabase_memories) > 5:
                print(f"  ... and {len(supabase_memories) - 5} more")
    except Exception as e:
        print(f"✗ Error checking Supabase: {e}")
        supabase_memories = []

    # Check Neo4j (graph store)
    print("\n[2] Checking Neo4j (Graph Store)...")
    try:
        from config import settings
        driver = GraphDatabase.driver(
            settings.neo4j_uri,
            auth=(settings.neo4j_user, settings.neo4j_password)
        )

        with driver.session() as session:
            # Count all nodes
            result = session.run("MATCH (n) RETURN count(n) as count")
            total_nodes = result.single()['count']
            print(f"✓ Total Neo4j nodes: {total_nodes}")

            # Count by label
            result = session.run("""
                MATCH (n)
                RETURN labels(n) as labels, count(n) as count
                ORDER BY count DESC
            """)
            print("\nNodes by label:")
            for record in result:
                labels = record['labels']
                count = record['count']
                print(f"  • {labels}: {count}")

            # Count relationships
            result = session.run("MATCH ()-[r]->() RETURN count(r) as count")
            total_rels = result.single()['count']
            print(f"\n✓ Total relationships: {total_rels}")

            # Show sample nodes
            result = session.run("""
                MATCH (n)
                RETURN n, labels(n) as labels
                LIMIT 10
            """)
            print("\nSample nodes:")
            for i, record in enumerate(result, 1):
                node = record['n']
                labels = record['labels']
                props = dict(node)
                print(f"  {i}. Labels: {labels}, Properties: {list(props.keys())[:3]}")

        driver.close()

    except Exception as e:
        print(f"✗ Error checking Neo4j: {e}")
        import traceback
        traceback.print_exc()

    # Summary
    print("\n" + "=" * 60)
    print("SUMMARY")
    print("=" * 60)
    print(f"Supabase (Vector Store): {len(supabase_memories)} memories")
    print(f"Neo4j (Graph Store): {total_nodes if 'total_nodes' in locals() else 'ERROR'} nodes, {total_rels if 'total_rels' in locals() else 'ERROR'} relationships")

    if len(supabase_memories) == 0 and total_nodes > 0:
        print("\n⚠️  WARNING: Inconsistency detected!")
        print("   → Supabase has 0 memories but Neo4j has nodes")
        print("   → This suggests orphaned graph data")

if __name__ == "__main__":
    asyncio.run(check_stores())