hermes-agent/gateway/restart.py

54 lines
1.9 KiB
Python

"""Shared gateway restart constants and supervisor detection helpers."""
import os
from collections.abc import Mapping
from hermes_cli.config import DEFAULT_CONFIG
# EX_TEMPFAIL from sysexits.h — used to ask the service manager to restart
# the gateway after a graceful drain/reload path completes.
GATEWAY_SERVICE_RESTART_EXIT_CODE = 75
# EX_CONFIG from sysexits.h — fatal configuration error (e.g. token
# collision, no messaging platforms). The s6 finish script translates
# this into exit 125 (permanent failure) so the supervisor stops
# restarting the gateway. See #51228.
GATEWAY_FATAL_CONFIG_EXIT_CODE = 78
# Set by ``hermes gateway run --external-supervisor``. Unlike systemd's
# INVOCATION_ID and launchd's XPC_SERVICE_NAME, this survives wrappers that
# intentionally replace the child environment (for example ``sudo env -i``).
EXTERNAL_GATEWAY_SUPERVISOR_ENV = "HERMES_GATEWAY_EXTERNAL_SUPERVISOR"
DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT = float(
DEFAULT_CONFIG["agent"]["restart_drain_timeout"]
)
def is_gateway_supervisor_process(
environ: Mapping[str, str] | None = None,
) -> bool:
"""Return whether this gateway process is owned by a supervisor."""
env = os.environ if environ is None else environ
if env.get("INVOCATION_ID"):
return True
if env.get("HERMES_S6_SUPERVISED_CHILD"):
return True
xpc_service = env.get("XPC_SERVICE_NAME", "")
if xpc_service and xpc_service != "0":
return True
return str(env.get(EXTERNAL_GATEWAY_SUPERVISOR_ENV, "")).strip().lower() in {
"1",
"true",
"yes",
"on",
}
def parse_restart_drain_timeout(raw: object) -> float:
"""Parse a configured drain timeout, falling back to the shared default."""
try:
value = float(raw) if str(raw or "").strip() else DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
except (TypeError, ValueError):
return DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
return max(0.0, value)