openClaw_agent_dm/deploy.sh

#!/bin/bash

###############################################################################
# OpenClaw System Deployment & Management Script
# 
# Features:
# - One-click deployment of OpenClaw with systemd services
# - Auto-healing configuration
# - Health monitoring
# - Rollback support via git
# - Telegram notifications
#
# Usage:
#   ./deploy.sh install      - Install and start all services
#   ./deploy.sh start        - Start all services
#   ./deploy.sh stop         - Stop all services
#   ./deploy.sh restart      - Restart all services
#   ./deploy.sh status       - Show service status
#   ./deploy.sh logs         - Show recent logs
#   ./deploy.sh health       - Run health check
#   ./deploy.sh rollback     - Rollback to previous git commit
#   ./deploy.sh backup       - Create backup of current state
#   ./deploy.sh debug-stop   - Stop ALL services (including monitor) for debugging
#   ./deploy.sh debug-start  - Start ALL services after debugging
#   ./deploy.sh fix-service  - Re-inject EnvironmentFile= after OpenClaw UI upgrade
###############################################################################

set -e

WORKSPACE="/root/.openclaw/workspace"
LOG_DIR="/root/.openclaw/workspace/logs/system"
TIMESTAMP=$(date +%Y%m%d-%H%M%S)

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

log_info() {
    echo -e "${BLUE}[INFO]${NC} $1"
}

log_success() {
    echo -e "${GREEN}[SUCCESS]${NC} $1"
}

log_warning() {
    echo -e "${YELLOW}[WARNING]${NC} $1"
}

log_error() {
    echo -e "${RED}[ERROR]${NC} $1"
}

ensure_log_dir() {
    mkdir -p "$LOG_DIR"
}

install_services() {
    log_info "Installing OpenClaw systemd services..."
    
    # Step 1: Enable linger for user-level systemd (CRITICAL for VPS/server deployments)
    log_info "Enabling user linger for persistent user-level services..."
    loginctl enable-linger $(whoami)
    
    # Step 2: Export required environment variables
    setup_user_env
    
    if [ ! -d "$XDG_RUNTIME_DIR" ]; then
        log_error "XDG_RUNTIME_DIR not found: $XDG_RUNTIME_DIR"
        log_warning "Creating runtime directory..."
        mkdir -p "$XDG_RUNTIME_DIR"
        chmod 700 "$XDG_RUNTIME_DIR"
    fi
    
    # Step 3: Install user-level gateway services
    log_info "Installing user-level gateway services..."
    mkdir -p ~/.config/systemd/user/
    cp "$WORKSPACE/systemd/openclaw-gateway-user.service" ~/.config/systemd/user/openclaw-gateway.service
    cp "$WORKSPACE/systemd/agent-life.service" ~/.config/systemd/user/openclaw-gateway-life.service
    
    systemctl --user daemon-reload
    systemctl --user enable openclaw-gateway
    systemctl --user enable openclaw-gateway-life
    
    # Step 4: Install system-level agent monitor
    log_info "Installing system-level agent monitor..."
    cp "$WORKSPACE/systemd/openclaw-agent-monitor.service" /etc/systemd/system/
    systemctl daemon-reload
    systemctl enable openclaw-agent-monitor
    
    # Step 5: Inject EnvironmentFile references
    fix_service_files
    
    # Step 6: Start services
    log_info "Starting services..."
    systemctl --user start openclaw-gateway
    systemctl --user start openclaw-gateway-life
    systemctl start openclaw-agent-monitor
    
    sleep 3
    
    log_success "OpenClaw services installed and started!"
    log_info "Gateway: ws://localhost:18789"
    log_info "Life Agent: openclaw-gateway-life.service"
    log_info "User service logs: journalctl --user -u openclaw-gateway -f"
    log_info "Life agent logs:   journalctl --user -u openclaw-gateway-life -f"
    log_info "Monitor logs:      journalctl -u openclaw-agent-monitor -f"
}

setup_user_env() {
    export XDG_RUNTIME_DIR=/run/user/$(id -u)
    export DBUS_SESSION_BUS_ADDRESS="unix:path=/run/user/$(id -u)/bus"
}

start_services() {
    log_info "Starting OpenClaw services..."
    setup_user_env
    
    systemctl --user start openclaw-gateway
    systemctl --user start openclaw-gateway-life
    systemctl start openclaw-agent-monitor
    log_success "All services started (gateway + life + monitor)"
}

stop_services() {
    log_info "Stopping OpenClaw services..."
    setup_user_env
    
    systemctl --user stop openclaw-gateway
    systemctl --user stop openclaw-gateway-life
    systemctl stop openclaw-agent-monitor
    log_success "All services stopped"
}

restart_services() {
    log_info "Restarting OpenClaw services..."
    setup_user_env
    
    systemctl --user restart openclaw-gateway
    systemctl --user restart openclaw-gateway-life
    systemctl restart openclaw-agent-monitor
    log_success "All services restarted (gateway + life + monitor)"
}

debug_stop() {
    log_warning "=== DEBUG MODE: Stopping ALL services ==="
    log_warning "Monitor will NOT auto-restart gateway while in debug mode."
    log_warning "Run './deploy.sh debug-start' when done debugging."
    setup_user_env
    
    systemctl stop openclaw-agent-monitor 2>/dev/null || true
    systemctl --user stop openclaw-gateway 2>/dev/null || true
    systemctl --user stop openclaw-gateway-life 2>/dev/null || true
    
    log_success "All services stopped. Safe to debug."
    echo ""
    log_info "Useful debug commands:"
    log_info "  openclaw gateway start          # start gateway in foreground"
    log_info "  journalctl --user -u openclaw-gateway -n 100"
    log_info "  journalctl --user -u openclaw-gateway-life -n 100"
}

debug_start() {
    log_info "=== Exiting DEBUG MODE: Restarting ALL services ==="
    setup_user_env
    
    systemctl --user start openclaw-gateway
    systemctl --user start openclaw-gateway-life
    systemctl start openclaw-agent-monitor
    
    sleep 2
    log_success "All services restored. Monitor is active again."
    health_check
}

fix_service_files() {
    log_info "Ensuring EnvironmentFile= is present in installed service files..."
    setup_user_env
    
    local gateway_svc="$HOME/.config/systemd/user/openclaw-gateway.service"
    local life_svc="$HOME/.config/systemd/user/openclaw-gateway-life.service"
    local gateway_env="$WORKSPACE/systemd/gateway.env"
    local life_env="$WORKSPACE/systemd/life-gateway.env"
    local changed=0
    
    if [ -f "$gateway_svc" ]; then
        if ! grep -q "EnvironmentFile=.*gateway.env" "$gateway_svc" 2>/dev/null; then
            sed -i "/^\[Service\]/a EnvironmentFile=-${gateway_env}" "$gateway_svc"
            log_info "Injected EnvironmentFile into openclaw-gateway.service"
            changed=1
        else
            log_info "openclaw-gateway.service already has EnvironmentFile"
        fi
    fi
    
    if [ -f "$life_svc" ]; then
        if ! grep -q "EnvironmentFile=.*life-gateway.env" "$life_svc" 2>/dev/null; then
            sed -i "/^\[Service\]/a EnvironmentFile=-${life_env}" "$life_svc"
            log_info "Injected EnvironmentFile into openclaw-gateway-life.service"
            changed=1
        else
            log_info "openclaw-gateway-life.service already has EnvironmentFile"
        fi
    fi
    
    if [ $changed -eq 1 ]; then
        systemctl --user daemon-reload
        log_success "Service files updated. Run './deploy.sh restart' to apply."
    else
        log_success "All service files are up to date."
    fi
}

show_status() {
    setup_user_env
    
    echo ""
    log_info "=== OpenClaw Gateway (User Service) ==="
    systemctl --user status openclaw-gateway --no-pager -l 2>&1 || true
    echo ""
    log_info "=== Life Agent (User Service) ==="
    systemctl --user status openclaw-gateway-life --no-pager -l 2>&1 || true
    echo ""
    log_info "=== Agent Monitor (System Service) ==="
    systemctl status openclaw-agent-monitor --no-pager -l 2>&1 || true
    echo ""
    log_info "=== Recent Gateway Logs ==="
    journalctl --user -u openclaw-gateway --no-pager -n 10
    echo ""
    log_info "=== Recent Life Agent Logs ==="
    journalctl --user -u openclaw-gateway-life --no-pager -n 10
    echo ""
    log_info "=== Recent Monitor Logs ==="
    journalctl -u openclaw-agent-monitor --no-pager -n 10
}

show_logs() {
    setup_user_env
    
    log_info "Showing recent gateway logs (last 50 lines)..."
    journalctl --user -u openclaw-gateway --no-pager -n 50
    echo ""
    log_info "Showing recent life agent logs (last 50 lines)..."
    journalctl --user -u openclaw-gateway-life --no-pager -n 50
    echo ""
    log_info "Showing recent monitor logs (last 50 lines)..."
    journalctl -u openclaw-agent-monitor --no-pager -n 50
}

rollback() {
    log_warning "This will rollback the workspace to the previous git commit!"
    read -p "Are you sure? (y/N): " confirm
    
    if [[ $confirm =~ ^[Yy]$ ]]; then
        cd "$WORKSPACE"
        
        # Create backup before rollback
        backup
        
        # Show current commit
        log_info "Current commit:"
        git log -1 --oneline
        
        # Rollback
        git reset --hard HEAD~1
        
        log_success "Rolled back to previous commit!"
        log_info "Restarting services to apply changes..."
        restart_services
    else
        log_info "Rollback cancelled."
    fi
}

rollback_to() {
    if [ -z "$1" ]; then
        log_error "Please specify a commit hash or tag"
        exit 1
    fi
    
    log_warning "This will rollback the workspace to commit: $1"
    read -p "Are you sure? (y/N): " confirm
    
    if [[ $confirm =~ ^[Yy]$ ]]; then
        cd "$WORKSPACE"
        backup
        git reset --hard "$1"
        log_success "Rolled back to commit: $1"
        restart_services
    else
        log_info "Rollback cancelled."
    fi
}

backup() {
    local backup_dir="/root/.openclaw/backups"
    mkdir -p "$backup_dir"
    
    log_info "Creating backup..."
    
    # Backup workspace
    tar -czf "$backup_dir/workspace-$TIMESTAMP.tar.gz" \
        --exclude='.git' \
        --exclude='logs' \
        -C /root/.openclaw workspace
    
    # Backup config
    cp /root/.openclaw/openclaw.json "$backup_dir/openclaw-config-$TIMESTAMP.json" 2>/dev/null || true
    
    log_success "Backup created: $backup_dir/workspace-$TIMESTAMP.tar.gz"
}

health_check() {
    log_info "Running health check..."
    setup_user_env
    
    local issues=0
    
    if systemctl --user is-active --quiet openclaw-gateway 2>/dev/null; then
        log_success "✓ Gateway is running"
    else
        log_error "✗ Gateway is not running"
        ((issues++))
    fi
    
    if systemctl --user is-active --quiet openclaw-gateway-life 2>/dev/null; then
        log_success "✓ Life Agent is running"
    else
        log_error "✗ Life Agent is not running"
        ((issues++))
    fi
    
    if systemctl is-active --quiet openclaw-agent-monitor; then
        log_success "✓ Agent Monitor is running"
    else
        log_error "✗ Agent Monitor is not running"
        ((issues++))
    fi
    
    # Check disk space
    local disk_usage=$(df -h /root | tail -1 | awk '{print $5}' | sed 's/%//')
    if [ "$disk_usage" -lt 80 ]; then
        log_success "✓ Disk usage: ${disk_usage}%"
    else
        log_warning "⚠ Disk usage: ${disk_usage}%"
        ((issues++))
    fi
    
    # Check memory
    local mem_usage=$(free | grep Mem | awk '{printf("%.0f", $3/$2 * 100.0)}')
    if [ "$mem_usage" -lt 80 ]; then
        log_success "✓ Memory usage: ${mem_usage}%"
    else
        log_warning "⚠ Memory usage: ${mem_usage}%"
        ((issues++))
    fi
    
    # Check XDG_RUNTIME_DIR
    if [ -d "$XDG_RUNTIME_DIR" ]; then
        log_success "✓ XDG_RUNTIME_DIR exists: $XDG_RUNTIME_DIR"
    else
        log_warning "⚠ XDG_RUNTIME_DIR not found"
        ((issues++))
    fi
    
    # Check linger status
    if loginctl show-user $(whoami) -p Linger | grep -q "yes"; then
        log_success "✓ User linger is enabled"
    else
        log_warning "⚠ User linger is NOT enabled (run: loginctl enable-linger)"
        ((issues++))
    fi
    
    echo ""
    if [ $issues -eq 0 ]; then
        log_success "All health checks passed!"
        return 0
    else
        log_error "$issues health check(s) failed!"
        return 1
    fi
}

show_help() {
    echo "OpenClaw System Management Script"
    echo ""
    echo "Usage: $0 <command>"
    echo ""
    echo "Commands:"
    echo "  install       - Install and start all systemd services"
    echo "  start         - Start all services (gateway + life + monitor)"
    echo "  stop          - Stop all services"
    echo "  restart       - Restart all services"
    echo "  status        - Show service status"
    echo "  logs          - Show recent logs"
    echo "  health        - Run health check"
    echo "  backup        - Create backup of current state"
    echo "  rollback      - Rollback to previous git commit"
    echo "  rollback-to   - Rollback to specific commit"
    echo "  debug-stop    - Stop ALL services including monitor (safe for debugging)"
    echo "  debug-start   - Restart all services after debugging"
    echo "  fix-service   - Re-inject EnvironmentFile after OpenClaw UI upgrade"
    echo "  help          - Show this help message"
    echo ""
}

# Main
case "${1:-help}" in
    install)
        install_services
        ;;
    start)
        start_services
        ;;
    stop)
        stop_services
        ;;
    restart)
        restart_services
        ;;
    status)
        show_status
        ;;
    logs)
        show_logs
        ;;
    health)
        health_check
        ;;
    backup)
        backup
        ;;
    rollback)
        rollback
        ;;
    rollback-to)
        rollback_to "$2"
        ;;
    debug-stop)
        debug_stop
        ;;
    debug-start)
        debug_start
        ;;
    fix-service)
        fix_service_files
        ;;
    help|--help|-h)
        show_help
        ;;
    *)
        log_error "Unknown command: $1"
        show_help
        exit 1
        ;;
esac