Spaces:
Running
Running
File size: 3,421 Bytes
6687173 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
#!/usr/bin/env python3
"""
NUCLEAR CLEANUP: Delete corrupted conversations and fix the index
"""
import asyncio
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent.parent))
from app.database import connect_db, disconnect_db, get_db
import logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
async def nuclear_cleanup():
"""Aggressively fix all conversation issues"""
try:
await connect_db()
db = await get_db()
logger.info("Step 1: Finding ALL conversations...")
all_convs = await db.conversations.find({}).to_list(length=None)
logger.info(f"Total conversations in DB: {len(all_convs)}")
# Check each conversation
corrupted_ids = []
for conv in all_convs:
participants = conv.get("participants")
conv_id = conv["_id"]
# Check if corrupted (not a proper list of 2 strings)
is_corrupted = False
if isinstance(participants, str):
logger.info(f" ❌ CORRUPTED (string): {conv_id} -> '{participants}'")
is_corrupted = True
elif not isinstance(participants, list):
logger.info(f" ❌ CORRUPTED (not list): {conv_id} -> {type(participants)}")
is_corrupted = True
elif len(participants) != 2:
logger.info(f" ❌ CORRUPTED (wrong length): {conv_id} -> {participants}")
is_corrupted = True
else:
# Verify each participant is a string
for p in participants:
if not isinstance(p, str):
logger.info(f" ❌ CORRUPTED (bad participant type): {conv_id}")
is_corrupted = True
break
if is_corrupted:
corrupted_ids.append(conv_id)
logger.info(f"\nFound {len(corrupted_ids)} corrupted conversations")
# Delete corrupted conversations and their messages
for conv_id in corrupted_ids:
await db.messages.delete_many({"conversation_id": str(conv_id)})
await db.conversations.delete_one({"_id": conv_id})
logger.info(f" ✅ Deleted: {conv_id}")
# Step 2: Drop and recreate the index
logger.info("\nStep 2: Fixing participants index...")
try:
await db.conversations.drop_index("participants_1")
logger.info(" Dropped old participants_1 index")
except Exception as e:
logger.info(f" No existing index to drop: {e}")
# Recreate with proper unique index
await db.conversations.create_index("participants", unique=True)
logger.info(" ✅ Created new unique index on participants")
logger.info(f"\n{'='*60}")
logger.info(f"✅ NUCLEAR CLEANUP COMPLETE!")
logger.info(f"Deleted {len(corrupted_ids)} corrupted conversations")
logger.info(f"Index recreated")
logger.info(f"{'='*60}\n")
except Exception as e:
logger.error(f"Cleanup failed: {e}")
raise
finally:
await disconnect_db()
if __name__ == "__main__":
logger.info("🔥 NUCLEAR CLEANUP - Fixing all conversation issues...")
asyncio.run(nuclear_cleanup())
|