Files
hermes-agent/scripts/hermes-gateway
Teknium 326b146d68 fix: prevent systemd restart storm on gateway connection failure
Cherry-picked from PR #2319 by @itenev.

When the gateway fails to connect (e.g. PrivilegedIntentsRequired,
missing token), systemd's default RestartSec=10 with no start rate
limit causes rapid reconnect storms flooding logs and triggering
platform-side rate limits.

- StartLimitIntervalSec=600 + StartLimitBurst=5 in [Unit] (max 5
  restarts per 10 min)
- RestartSec: 10 → 30
- Applied to both templates in gateway.py and scripts/hermes-gateway
2026-03-21 09:26:39 -07:00

417 lines
12 KiB
Python
Executable File

#!/usr/bin/env python3
"""
Hermes Gateway - Standalone messaging platform integration.
This is the proper entry point for running the gateway as a service.
NOT tied to the CLI - runs independently.
Usage:
# Run in foreground (for testing)
./scripts/hermes-gateway
# Install as systemd service
./scripts/hermes-gateway install
# Manage the service
./scripts/hermes-gateway start
./scripts/hermes-gateway stop
./scripts/hermes-gateway restart
./scripts/hermes-gateway status
# Uninstall
./scripts/hermes-gateway uninstall
"""
import argparse
import asyncio
import os
import subprocess
import sys
from pathlib import Path
# Add parent directory to path
SCRIPT_DIR = Path(__file__).parent.resolve()
PROJECT_DIR = SCRIPT_DIR.parent
sys.path.insert(0, str(PROJECT_DIR))
# Load .env file
from dotenv import load_dotenv
env_path = PROJECT_DIR / '.env'
if env_path.exists():
load_dotenv(dotenv_path=env_path)
# =============================================================================
# Service Configuration
# =============================================================================
SERVICE_NAME = "hermes-gateway"
SERVICE_DESCRIPTION = "Hermes Agent Gateway - Messaging Platform Integration"
def get_systemd_unit_path() -> Path:
"""Get the path for the systemd user service file."""
return Path.home() / ".config" / "systemd" / "user" / f"{SERVICE_NAME}.service"
def get_launchd_plist_path() -> Path:
"""Get the path for the launchd plist file (macOS)."""
return Path.home() / "Library" / "LaunchAgents" / f"ai.hermes.gateway.plist"
def get_python_path() -> str:
"""Get the path to the Python interpreter."""
# Prefer the venv if it exists
venv_python = PROJECT_DIR / "venv" / "bin" / "python"
if venv_python.exists():
return str(venv_python)
return sys.executable
def get_gateway_script_path() -> str:
"""Get the path to this script."""
return str(Path(__file__).resolve())
# =============================================================================
# Systemd Service (Linux)
# =============================================================================
def generate_systemd_unit() -> str:
"""Generate the systemd unit file content."""
python_path = get_python_path()
script_path = get_gateway_script_path()
working_dir = str(PROJECT_DIR)
return f"""[Unit]
Description={SERVICE_DESCRIPTION}
After=network.target
StartLimitIntervalSec=600
StartLimitBurst=5
[Service]
Type=simple
ExecStart={python_path} {script_path} run
WorkingDirectory={working_dir}
Restart=on-failure
RestartSec=30
StandardOutput=journal
StandardError=journal
# Environment (optional - can also use .env file)
# Environment="TELEGRAM_BOT_TOKEN=your_token"
# Environment="DISCORD_BOT_TOKEN=your_token"
[Install]
WantedBy=default.target
"""
def install_systemd():
"""Install the systemd user service."""
unit_path = get_systemd_unit_path()
unit_path.parent.mkdir(parents=True, exist_ok=True)
print(f"Installing systemd service to: {unit_path}")
unit_path.write_text(generate_systemd_unit())
# Reload systemd
subprocess.run(["systemctl", "--user", "daemon-reload"], check=True)
# Enable the service (start on boot)
subprocess.run(["systemctl", "--user", "enable", SERVICE_NAME], check=True)
print(f"✓ Service installed and enabled")
print(f"")
print(f"To start the service:")
print(f" systemctl --user start {SERVICE_NAME}")
print(f"")
print(f"To view logs:")
print(f" journalctl --user -u {SERVICE_NAME} -f")
print(f"")
print(f"To enable lingering (keeps service running after logout):")
print(f" sudo loginctl enable-linger $USER")
def uninstall_systemd():
"""Uninstall the systemd user service."""
unit_path = get_systemd_unit_path()
# Stop and disable first
subprocess.run(["systemctl", "--user", "stop", SERVICE_NAME], check=False)
subprocess.run(["systemctl", "--user", "disable", SERVICE_NAME], check=False)
# Remove the unit file
if unit_path.exists():
unit_path.unlink()
print(f"✓ Removed {unit_path}")
# Reload systemd
subprocess.run(["systemctl", "--user", "daemon-reload"], check=True)
print(f"✓ Service uninstalled")
def systemd_status():
"""Show systemd service status."""
subprocess.run(["systemctl", "--user", "status", SERVICE_NAME])
def systemd_start():
"""Start the systemd service."""
subprocess.run(["systemctl", "--user", "start", SERVICE_NAME], check=True)
print(f"✓ Service started")
def systemd_stop():
"""Stop the systemd service."""
subprocess.run(["systemctl", "--user", "stop", SERVICE_NAME], check=True)
print(f"✓ Service stopped")
def systemd_restart():
"""Restart the systemd service."""
subprocess.run(["systemctl", "--user", "restart", SERVICE_NAME], check=True)
print(f"✓ Service restarted")
# =============================================================================
# Launchd Service (macOS)
# =============================================================================
def generate_launchd_plist() -> str:
"""Generate the launchd plist file content."""
python_path = get_python_path()
script_path = get_gateway_script_path()
working_dir = str(PROJECT_DIR)
log_dir = Path.home() / ".hermes" / "logs"
return f"""<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>ai.hermes.gateway</string>
<key>ProgramArguments</key>
<array>
<string>{python_path}</string>
<string>{script_path}</string>
<string>run</string>
</array>
<key>WorkingDirectory</key>
<string>{working_dir}</string>
<key>RunAtLoad</key>
<true/>
<key>KeepAlive</key>
<dict>
<key>SuccessfulExit</key>
<false/>
</dict>
<key>StandardOutPath</key>
<string>{log_dir}/gateway.log</string>
<key>StandardErrorPath</key>
<string>{log_dir}/gateway.error.log</string>
<key>EnvironmentVariables</key>
<dict>
<key>PATH</key>
<string>/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin</string>
</dict>
</dict>
</plist>
"""
def install_launchd():
"""Install the launchd service (macOS)."""
plist_path = get_launchd_plist_path()
plist_path.parent.mkdir(parents=True, exist_ok=True)
# Ensure log directory exists
log_dir = Path.home() / ".hermes" / "logs"
log_dir.mkdir(parents=True, exist_ok=True)
print(f"Installing launchd service to: {plist_path}")
plist_path.write_text(generate_launchd_plist())
# Load the service
subprocess.run(["launchctl", "load", str(plist_path)], check=True)
print(f"✓ Service installed and loaded")
print(f"")
print(f"To view logs:")
print(f" tail -f ~/.hermes/logs/gateway.log")
print(f"")
print(f"To manage the service:")
print(f" launchctl start ai.hermes.gateway")
print(f" launchctl stop ai.hermes.gateway")
def uninstall_launchd():
"""Uninstall the launchd service (macOS)."""
plist_path = get_launchd_plist_path()
# Unload first
subprocess.run(["launchctl", "unload", str(plist_path)], check=False)
# Remove the plist file
if plist_path.exists():
plist_path.unlink()
print(f"✓ Removed {plist_path}")
print(f"✓ Service uninstalled")
def launchd_status():
"""Show launchd service status."""
subprocess.run(["launchctl", "list", "ai.hermes.gateway"])
def launchd_start():
"""Start the launchd service."""
subprocess.run(["launchctl", "start", "ai.hermes.gateway"], check=True)
print(f"✓ Service started")
def launchd_stop():
"""Stop the launchd service."""
subprocess.run(["launchctl", "stop", "ai.hermes.gateway"], check=True)
print(f"✓ Service stopped")
def launchd_restart():
"""Restart the launchd service."""
launchd_stop()
launchd_start()
# =============================================================================
# Platform Detection
# =============================================================================
def is_linux() -> bool:
return sys.platform.startswith('linux')
def is_macos() -> bool:
return sys.platform == 'darwin'
def is_windows() -> bool:
return sys.platform == 'win32'
# =============================================================================
# Gateway Runner
# =============================================================================
def run_gateway():
"""Run the gateway in foreground."""
from gateway.run import start_gateway
print("Starting Hermes Gateway...")
print("Press Ctrl+C to stop.")
print()
asyncio.run(start_gateway())
# =============================================================================
# Main CLI
# =============================================================================
def main():
parser = argparse.ArgumentParser(
description="Hermes Gateway - Messaging Platform Integration",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
# Run in foreground (for testing)
./scripts/hermes-gateway run
# Install as system service
./scripts/hermes-gateway install
# Manage the service
./scripts/hermes-gateway start
./scripts/hermes-gateway stop
./scripts/hermes-gateway restart
./scripts/hermes-gateway status
# Uninstall
./scripts/hermes-gateway uninstall
Configuration:
Set environment variables in .env file or system environment:
- TELEGRAM_BOT_TOKEN
- DISCORD_BOT_TOKEN
- WHATSAPP_ENABLED
Or create ~/.hermes/gateway.json for advanced configuration.
"""
)
parser.add_argument(
"command",
choices=["run", "install", "uninstall", "start", "stop", "restart", "status"],
nargs="?",
default="run",
help="Command to execute (default: run)"
)
parser.add_argument(
"--verbose", "-v",
action="store_true",
help="Verbose output"
)
args = parser.parse_args()
# Detect platform and dispatch command
if args.command == "run":
run_gateway()
elif args.command == "install":
if is_linux():
install_systemd()
elif is_macos():
install_launchd()
else:
print("Service installation not supported on this platform.")
print("Please run manually: ./scripts/hermes-gateway run")
sys.exit(1)
elif args.command == "uninstall":
if is_linux():
uninstall_systemd()
elif is_macos():
uninstall_launchd()
else:
print("Service uninstallation not supported on this platform.")
sys.exit(1)
elif args.command == "start":
if is_linux():
systemd_start()
elif is_macos():
launchd_start()
else:
print("Not supported on this platform.")
sys.exit(1)
elif args.command == "stop":
if is_linux():
systemd_stop()
elif is_macos():
launchd_stop()
else:
print("Not supported on this platform.")
sys.exit(1)
elif args.command == "restart":
if is_linux():
systemd_restart()
elif is_macos():
launchd_restart()
else:
print("Not supported on this platform.")
sys.exit(1)
elif args.command == "status":
if is_linux():
systemd_status()
elif is_macos():
launchd_status()
else:
print("Not supported on this platform.")
sys.exit(1)
if __name__ == "__main__":
main()