fix: Add database stability monitoring and improve PostgreSQL config

- Add monitor-db-stability.sh for automatic recovery
- Improve PostgreSQL shutdown settings to prevent data loss
- Add checkpoint and WAL settings for better persistence

docker-compose.db.yml

@@ -10,6 +10,8 @@ services:
       POSTGRES_DB: daarion
       POSTGRES_USER: postgres
       POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}
+      # Prevent data loss: ensure proper shutdown
+      POSTGRES_INITDB_ARGS: "-E UTF8 --locale=C"
     ports:
       - "5432:5432"
     volumes:
@@ -24,6 +26,8 @@ services:
       timeout: 5s
       retries: 5
       start_period: 30s
+    # Add command to ensure proper shutdown and prevent data loss
+    command: postgres -c shared_buffers=256MB -c max_connections=200 -c checkpoint_timeout=15min -c wal_level=replica -c max_wal_size=1GB
 
   # Automatic database backups
   db-backup:

scripts/monitor-db-stability.sh

@@ -0,0 +1,88 @@
+#!/bin/bash
+# Monitor database stability and auto-recover if needed
+# Run this periodically (e.g., every 5 minutes via cron)
+
+set -e
+
+LOG_FILE="/var/log/db-stability-monitor.log"
+TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
+
+log() {
+  echo "[$TIMESTAMP] $1" | tee -a "$LOG_FILE"
+}
+
+log "🔍 Starting database stability check..."
+
+# Check if PostgreSQL container is running
+if ! docker ps | grep -q daarion-postgres; then
+  log "❌ PostgreSQL container is not running! Starting..."
+  cd /opt/microdao-daarion
+  docker compose -f docker-compose.db.yml up -d db
+  sleep 10
+fi
+
+# Check if database exists
+if ! docker exec daarion-postgres psql -U postgres -lqt | cut -d \| -f 1 | grep -qw daarion; then
+  log "⚠️  Database 'daarion' does not exist, creating..."
+  docker exec daarion-postgres psql -U postgres -c "CREATE DATABASE daarion;" || {
+    log "❌ Failed to create database"
+    exit 1
+  }
+fi
+
+# Check data integrity
+MICRODAO_COUNT=$(docker exec daarion-postgres psql -U postgres -d daarion -t -c "SELECT COUNT(*) FROM microdaos;" 2>/dev/null | tr -d ' ' || echo "0")
+AGENT_COUNT=$(docker exec daarion-postgres psql -U postgres -d daarion -t -c "SELECT COUNT(*) FROM agents;" 2>/dev/null | tr -d ' ' || echo "0")
+
+log "📊 Data check: MicroDAOs=$MICRODAO_COUNT, Agents=$AGENT_COUNT"
+
+# If data is missing, try to restore
+if [ "$MICRODAO_COUNT" -lt 5 ] || [ "$AGENT_COUNT" -lt 10 ]; then
+  log "⚠️  Data loss detected! Attempting recovery..."
+  
+  # Check for recent backup
+  LATEST_BACKUP=$(ls -t /opt/microdao-daarion/db_backups/*.sql 2>/dev/null | head -1)
+  
+  if [ -n "$LATEST_BACKUP" ]; then
+    log "📦 Found backup: $LATEST_BACKUP"
+    log "🔄 Restoring from backup..."
+    
+    # Drop and recreate database
+    docker exec daarion-postgres psql -U postgres -c "DROP DATABASE IF EXISTS daarion;"
+    docker exec daarion-postgres psql -U postgres -c "CREATE DATABASE daarion;"
+    
+    # Restore from backup
+    docker exec -i daarion-postgres psql -U postgres -d daarion < "$LATEST_BACKUP" 2>&1 | grep -v "already exists\|does not exist" || true
+    
+    # Apply migrations
+    cd /opt/microdao-daarion
+    for f in migrations/*.sql; do
+      docker exec -i daarion-postgres psql -U postgres -d daarion < "$f" 2>&1 | grep -v "already exists\|does not exist" || true
+    done
+    
+    # Sync NODE2 agents
+    python3 scripts/sync-node2-dagi-agents.py 2>&1 | tail -5 || true
+    
+    # Remove test agents
+    bash scripts/remove-test-agents.sh 2>&1 | tail -3 || true
+    
+    log "✅ Recovery complete"
+  else
+    log "❌ No backup found for recovery"
+  fi
+fi
+
+# Check PostgreSQL logs for errors
+ERROR_COUNT=$(docker logs daarion-postgres --since 5m 2>&1 | grep -i "fatal\|error\|panic" | wc -l)
+if [ "$ERROR_COUNT" -gt 0 ]; then
+  log "⚠️  Found $ERROR_COUNT errors in PostgreSQL logs in last 5 minutes"
+fi
+
+# Check container restart count
+RESTART_COUNT=$(docker inspect daarion-postgres --format='{{.RestartCount}}' 2>/dev/null || echo "0")
+if [ "$RESTART_COUNT" -gt 10 ]; then
+  log "⚠️  PostgreSQL has restarted $RESTART_COUNT times - possible stability issue"
+fi
+
+log "✅ Stability check complete"
+