- Added systemd services for system-level persistence (gateway + monitor) - Enhanced agent-monitor.js with auto-healing and Telegram notifications - Created deploy.sh for one-click deployment and management - Updated CORE_INDEX.md with complete architecture documentation - Updated MEMORY.md with implementation details and usage guide - All memory files now tracked in git for version control and rollback Features implemented: ✓ System-Level: Services auto-start on boot, survive logout/reboot ✓ Auto-Healing: Crash detection, auto-restart with rate limiting ✓ Multi-Layer Memory: Core (CORE_INDEX.md) + Long-term (MEMORY.md) + Daily (memory/) ✓ Git Rollback: ./deploy.sh rollback / rollback-to <commit> ✓ Telegram Notifications: Alerts on stop/error/restart eventsmaster
parent
5707edd78a
commit
820530d1ec
7 changed files with 719 additions and 48 deletions
@ -0,0 +1,290 @@ |
|||||||
|
#!/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 rollback - Rollback to previous git commit |
||||||
|
# ./deploy.sh backup - Create backup of current state |
||||||
|
############################################################################### |
||||||
|
|
||||||
|
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..." |
||||||
|
|
||||||
|
# Copy service files |
||||||
|
cp "$WORKSPACE/systemd/openclaw-gateway.service" /etc/systemd/system/ |
||||||
|
cp "$WORKSPACE/systemd/openclaw-agent-monitor.service" /etc/systemd/system/ |
||||||
|
|
||||||
|
# Reload systemd |
||||||
|
systemctl daemon-reload |
||||||
|
|
||||||
|
# Enable services |
||||||
|
systemctl enable openclaw-gateway |
||||||
|
systemctl enable openclaw-agent-monitor |
||||||
|
|
||||||
|
# Start services |
||||||
|
systemctl start openclaw-gateway |
||||||
|
systemctl start openclaw-agent-monitor |
||||||
|
|
||||||
|
log_success "OpenClaw services installed and started!" |
||||||
|
log_info "Gateway: http://localhost:18789" |
||||||
|
log_info "Logs: journalctl -u openclaw-gateway -f" |
||||||
|
} |
||||||
|
|
||||||
|
start_services() { |
||||||
|
log_info "Starting OpenClaw services..." |
||||||
|
systemctl start openclaw-gateway |
||||||
|
systemctl start openclaw-agent-monitor |
||||||
|
log_success "Services started!" |
||||||
|
} |
||||||
|
|
||||||
|
stop_services() { |
||||||
|
log_info "Stopping OpenClaw services..." |
||||||
|
systemctl stop openclaw-gateway |
||||||
|
systemctl stop openclaw-agent-monitor |
||||||
|
log_success "Services stopped!" |
||||||
|
} |
||||||
|
|
||||||
|
restart_services() { |
||||||
|
log_info "Restarting OpenClaw services..." |
||||||
|
systemctl restart openclaw-gateway |
||||||
|
systemctl restart openclaw-agent-monitor |
||||||
|
log_success "Services restarted!" |
||||||
|
} |
||||||
|
|
||||||
|
show_status() { |
||||||
|
echo "" |
||||||
|
log_info "=== OpenClaw Gateway Status ===" |
||||||
|
systemctl status openclaw-gateway --no-pager -l |
||||||
|
echo "" |
||||||
|
log_info "=== Agent Monitor Status ===" |
||||||
|
systemctl status openclaw-agent-monitor --no-pager -l |
||||||
|
echo "" |
||||||
|
log_info "=== Recent Logs ===" |
||||||
|
journalctl -u openclaw-gateway -u openclaw-agent-monitor --no-pager -n 20 |
||||||
|
} |
||||||
|
|
||||||
|
show_logs() { |
||||||
|
log_info "Showing recent logs (last 50 lines)..." |
||||||
|
journalctl -u openclaw-gateway -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..." |
||||||
|
|
||||||
|
local issues=0 |
||||||
|
|
||||||
|
# Check gateway |
||||||
|
if systemctl is-active --quiet openclaw-gateway; then |
||||||
|
log_success "✓ Gateway is running" |
||||||
|
else |
||||||
|
log_error "✗ Gateway is not running" |
||||||
|
((issues++)) |
||||||
|
fi |
||||||
|
|
||||||
|
# Check monitor |
||||||
|
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 |
||||||
|
|
||||||
|
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: $0 <command>" |
||||||
|
echo "" |
||||||
|
echo "Commands:" |
||||||
|
echo " install - Install and start all systemd services" |
||||||
|
echo " start - Start all services" |
||||||
|
echo " stop - Stop all services" |
||||||
|
echo " restart - Restart all services" |
||||||
|
echo " status - Show service status" |
||||||
|
echo " logs - Show recent logs" |
||||||
|
echo " health - Run health check" |
||||||
|
echo " backup - Create backup of current state" |
||||||
|
echo " rollback - Rollback to previous git commit" |
||||||
|
echo " rollback-to <commit> - Rollback to specific commit" |
||||||
|
echo " help - Show this help message" |
||||||
|
echo "" |
||||||
|
} |
||||||
|
|
||||||
|
# Main |
||||||
|
case "${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" |
||||||
|
;; |
||||||
|
help|--help|-h) |
||||||
|
show_help |
||||||
|
;; |
||||||
|
*) |
||||||
|
log_error "Unknown command: $1" |
||||||
|
show_help |
||||||
|
exit 1 |
||||||
|
;; |
||||||
|
esac |
||||||
@ -0,0 +1,4 @@ |
|||||||
|
[2026-02-20T14:25:25.027Z] [INFO] Agent Health Monitor initialized |
||||||
|
[2026-02-20T14:25:25.035Z] [INFO] Agent Health Monitor starting... |
||||||
|
[2026-02-20T14:25:25.036Z] [INFO] Starting OpenClaw Gateway monitoring... |
||||||
|
[2026-02-20T14:25:25.038Z] [INFO] Monitor is now active. Press Ctrl+C to stop. |
||||||
@ -0,0 +1,38 @@ |
|||||||
|
[Unit] |
||||||
|
Description=OpenClaw Agent Health Monitor |
||||||
|
Documentation=https://docs.openclaw.ai |
||||||
|
After=network.target openclaw-gateway.service |
||||||
|
Wants=network-online.target |
||||||
|
|
||||||
|
[Service] |
||||||
|
Type=simple |
||||||
|
User=root |
||||||
|
WorkingDirectory=/root/.openclaw/workspace |
||||||
|
Environment=NODE_ENV=production |
||||||
|
|
||||||
|
# Monitor process |
||||||
|
ExecStart=/usr/bin/node /root/.openclaw/workspace/agent-monitor.js |
||||||
|
|
||||||
|
# Auto-healing configuration |
||||||
|
Restart=always |
||||||
|
RestartSec=5 |
||||||
|
StartLimitInterval=300 |
||||||
|
StartLimitBurst=10 |
||||||
|
|
||||||
|
# Resource limits |
||||||
|
MemoryLimit=512M |
||||||
|
CPUQuota=20% |
||||||
|
|
||||||
|
# Logging |
||||||
|
StandardOutput=journal |
||||||
|
StandardError=journal |
||||||
|
SyslogIdentifier=openclaw-monitor |
||||||
|
|
||||||
|
# Security |
||||||
|
NoNewPrivileges=true |
||||||
|
ProtectSystem=strict |
||||||
|
ProtectHome=read-only |
||||||
|
ReadWritePaths=/root/.openclaw/workspace/logs |
||||||
|
|
||||||
|
[Install] |
||||||
|
WantedBy=multi-user.target |
||||||
@ -0,0 +1,42 @@ |
|||||||
|
[Unit] |
||||||
|
Description=OpenClaw Gateway Service |
||||||
|
Documentation=https://docs.openclaw.ai |
||||||
|
After=network.target |
||||||
|
Wants=network-online.target |
||||||
|
|
||||||
|
[Service] |
||||||
|
Type=simple |
||||||
|
User=root |
||||||
|
WorkingDirectory=/root/.openclaw |
||||||
|
Environment=NODE_ENV=production |
||||||
|
|
||||||
|
# Main gateway process |
||||||
|
ExecStart=/usr/bin/node /www/server/nodejs/v24.13.1/bin/openclaw gateway start |
||||||
|
ExecReload=/bin/kill -HUP $MAINPID |
||||||
|
|
||||||
|
# Auto-healing configuration |
||||||
|
Restart=always |
||||||
|
RestartSec=10 |
||||||
|
StartLimitInterval=300 |
||||||
|
StartLimitBurst=5 |
||||||
|
|
||||||
|
# Resource limits to prevent OOM |
||||||
|
MemoryLimit=2G |
||||||
|
CPUQuota=80% |
||||||
|
|
||||||
|
# Logging |
||||||
|
StandardOutput=journal |
||||||
|
StandardError=journal |
||||||
|
SyslogIdentifier=openclaw-gateway |
||||||
|
|
||||||
|
# Security hardening |
||||||
|
NoNewPrivileges=true |
||||||
|
ProtectSystem=strict |
||||||
|
ProtectHome=read-only |
||||||
|
ReadWritePaths=/root/.openclaw |
||||||
|
|
||||||
|
# Watchdog for health monitoring |
||||||
|
WatchdogSec=30 |
||||||
|
|
||||||
|
[Install] |
||||||
|
WantedBy=multi-user.target |
||||||
Loading…
Reference in new issue