fix: scope gateway stop/restart to current profile, --all for global kill

gateway stop and restart previously called kill_gateway_processes() which
scans ps aux and kills ALL gateway processes across all profiles. Starting
a profile gateway would nuke the main one (and vice versa).

Now:
- hermes gateway stop → only kills the current profile's gateway (PID file)
- hermes -p work gateway stop → only kills the 'work' profile's gateway
- hermes gateway stop --all → kills every gateway process (old behavior)
- hermes gateway restart → profile-scoped for manual fallback path
- hermes update → discovers and restarts ALL profile gateways (systemctl
  list-units hermes-gateway*) since the code update is shared

Added stop_profile_gateway() which uses the HERMES_HOME-scoped PID file
instead of global process scanning.
This commit is contained in:
Teknium
2026-04-03 14:21:25 -07:00
parent 52ddd6bc64
commit 84a875ca02
4 changed files with 229 additions and 172 deletions

View File

@@ -3516,139 +3516,103 @@ def cmd_update(args):
print()
print("✓ Update complete!")
# Auto-restart gateway if it's running.
# Uses the PID file (scoped to HERMES_HOME) to find this
# installation's gateway — safe with multiple installations.
# Auto-restart ALL gateways after update.
# The code update (git pull) is shared across all profiles, so every
# running gateway needs restarting to pick up the new code.
try:
from gateway.status import get_running_pid, remove_pid_file
from hermes_cli.gateway import (
get_service_name, get_launchd_plist_path, is_macos, is_linux,
launchd_restart, _ensure_user_systemd_env,
get_systemd_linger_status,
is_macos, is_linux, _ensure_user_systemd_env,
get_systemd_linger_status, find_gateway_pids,
)
import signal as _signal
_gw_service_name = get_service_name()
existing_pid = get_running_pid()
has_systemd_service = False
has_system_service = False
has_launchd_service = False
restarted_services = []
killed_pids = set()
try:
_ensure_user_systemd_env()
check = subprocess.run(
["systemctl", "--user", "is-active", _gw_service_name],
capture_output=True, text=True, timeout=5,
)
has_systemd_service = check.stdout.strip() == "active"
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
# Also check for a system-level service (hermes gateway install --system).
# This covers gateways running under system systemd where --user
# fails due to missing D-Bus session.
if not has_systemd_service and is_linux():
# --- Systemd services (Linux) ---
# Discover all hermes-gateway* units (default + profiles)
if is_linux():
try:
check = subprocess.run(
["systemctl", "is-active", _gw_service_name],
capture_output=True, text=True, timeout=5,
)
has_system_service = check.stdout.strip() == "active"
except (FileNotFoundError, subprocess.TimeoutExpired):
_ensure_user_systemd_env()
except Exception:
pass
# Check for macOS launchd service
for scope, scope_cmd in [("user", ["systemctl", "--user"]), ("system", ["systemctl"])]:
try:
result = subprocess.run(
scope_cmd + ["list-units", "hermes-gateway*", "--plain", "--no-legend", "--no-pager"],
capture_output=True, text=True, timeout=10,
)
for line in result.stdout.strip().splitlines():
parts = line.split()
if not parts:
continue
unit = parts[0] # e.g. hermes-gateway.service or hermes-gateway-coder.service
if not unit.endswith(".service"):
continue
svc_name = unit.removesuffix(".service")
# Check if active
check = subprocess.run(
scope_cmd + ["is-active", svc_name],
capture_output=True, text=True, timeout=5,
)
if check.stdout.strip() == "active":
restart = subprocess.run(
scope_cmd + ["restart", svc_name],
capture_output=True, text=True, timeout=15,
)
if restart.returncode == 0:
restarted_services.append(svc_name)
else:
print(f" ⚠ Failed to restart {svc_name}: {restart.stderr.strip()}")
except (FileNotFoundError, subprocess.TimeoutExpired):
pass
# --- Launchd services (macOS) ---
if is_macos():
try:
from hermes_cli.gateway import get_launchd_label
from hermes_cli.gateway import launchd_restart, get_launchd_label, get_launchd_plist_path
plist_path = get_launchd_plist_path()
if plist_path.exists():
check = subprocess.run(
["launchctl", "list", get_launchd_label()],
capture_output=True, text=True, timeout=5,
)
has_launchd_service = check.returncode == 0
except (FileNotFoundError, subprocess.TimeoutExpired):
if check.returncode == 0:
try:
launchd_restart()
restarted_services.append(get_launchd_label())
except subprocess.CalledProcessError as e:
stderr = (getattr(e, "stderr", "") or "").strip()
print(f" ⚠ Gateway restart failed: {stderr}")
except (FileNotFoundError, subprocess.TimeoutExpired, ImportError):
pass
if existing_pid or has_systemd_service or has_system_service or has_launchd_service:
print()
# --- Manual (non-service) gateways ---
# Kill any remaining gateway processes not managed by a service
manual_pids = find_gateway_pids()
for pid in manual_pids:
try:
os.kill(pid, _signal.SIGTERM)
killed_pids.add(pid)
except (ProcessLookupError, PermissionError):
pass
if restarted_services or killed_pids:
print()
for svc in restarted_services:
print(f" ✓ Restarted {svc}")
if killed_pids:
print(f" → Stopped {len(killed_pids)} manual gateway process(es)")
print(" Restart manually: hermes gateway run")
# Also restart for each profile if needed
if len(killed_pids) > 1:
print(" (or: hermes -p <profile> gateway run for each profile)")
if not restarted_services and not killed_pids:
# No gateways were running — nothing to do
pass
# When a service manager is handling the gateway, let it
# manage the lifecycle — don't manually SIGTERM the PID
# (launchd KeepAlive would respawn immediately, causing races).
if has_systemd_service:
import time as _time
if existing_pid:
try:
os.kill(existing_pid, _signal.SIGTERM)
print(f"→ Stopped gateway process (PID {existing_pid})")
except ProcessLookupError:
pass
except PermissionError:
print(f"⚠ Permission denied killing gateway PID {existing_pid}")
remove_pid_file()
_time.sleep(1) # Brief pause for port/socket release
print("→ Restarting gateway service...")
restart = subprocess.run(
["systemctl", "--user", "restart", _gw_service_name],
capture_output=True, text=True, timeout=15,
)
if restart.returncode == 0:
print("✓ Gateway restarted.")
else:
print(f"⚠ Gateway restart failed: {restart.stderr.strip()}")
# Check if linger is the issue
if is_linux():
linger_ok, _detail = get_systemd_linger_status()
if linger_ok is not True:
import getpass
_username = getpass.getuser()
print()
print(" Linger must be enabled for the gateway user service to function.")
print(f" Run: sudo loginctl enable-linger {_username}")
print()
print(" Then restart the gateway:")
print(" hermes gateway restart")
else:
print(" Try manually: hermes gateway restart")
elif has_system_service:
# System-level service (hermes gateway install --system).
# No D-Bus session needed — systemctl without --user talks
# directly to the system manager over /run/systemd/private.
print("→ Restarting system gateway service...")
restart = subprocess.run(
["systemctl", "restart", _gw_service_name],
capture_output=True, text=True, timeout=15,
)
if restart.returncode == 0:
print("✓ Gateway restarted (system service).")
else:
print(f"⚠ Gateway restart failed: {restart.stderr.strip()}")
print(" System services may require root. Try:")
print(f" sudo systemctl restart {_gw_service_name}")
elif has_launchd_service:
# Use the shared launchd restart helper so we wait for the
# old gateway process to fully exit before starting the new
# one. This avoids stop/start races during self-update.
print("→ Restarting gateway service...")
try:
launchd_restart()
except subprocess.CalledProcessError as e:
stderr = (getattr(e, "stderr", "") or "").strip()
print(f"⚠ Gateway restart failed: {stderr}")
print(" Try manually: hermes gateway restart")
elif existing_pid:
try:
os.kill(existing_pid, _signal.SIGTERM)
print(f"→ Stopped gateway process (PID {existing_pid})")
except ProcessLookupError:
pass # Already gone
except PermissionError:
print(f"⚠ Permission denied killing gateway PID {existing_pid}")
remove_pid_file()
print(" Gateway was running manually (not as a service).")
print(" Restart it with: hermes gateway run")
except Exception as e:
logger.debug("Gateway restart during update failed: %s", e)
@@ -4214,6 +4178,7 @@ For more help on a command:
# gateway stop
gateway_stop = gateway_subparsers.add_parser("stop", help="Stop gateway service")
gateway_stop.add_argument("--system", action="store_true", help="Target the Linux system-level gateway service")
gateway_stop.add_argument("--all", action="store_true", help="Stop ALL gateway processes across all profiles")
# gateway restart
gateway_restart = gateway_subparsers.add_parser("restart", help="Restart gateway service")