mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
bcec6c8d39
The restart-routing, systemd-support, and subprocess-HOME tests asserted
branch behavior but left part of the real probe surface unmocked, so they
fail when the suite itself runs inside a container (self-hosted CI) or a
launchd-descended shell:
- /restart routing tests: the handler also consults the real /.dockerenv —
extract the inline probe to gateway.restart.is_container_restart_context()
(patchable seam, no behavior change) and pin it False; scrub ALL four
supervisor env markers (ambient XPC_SERVICE_NAME on macOS flipped one).
- supports_systemd_services tests: pin shutil.which('systemctl') and
is_container() so the test asserts the branch, not the host.
- copilot ACP real-HOME test: pin is_container() (auto mode prefers profile
home in containers) and scrub ambient HERMES_REAL_HOME/TERMINAL_HOME_MODE.
97 tests green on macOS dev box AND inside a docker CI runner container.
Co-authored-by: Kyzcreig <9063726+Kyzcreig@users.noreply.github.com>
66 lines
2.5 KiB
Python
66 lines
2.5 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 is_container_restart_context() -> bool:
|
|
"""Return whether the gateway is running inside a container for restart
|
|
routing purposes (Docker/Podman ⇒ the detached setsid path dies with the
|
|
cgroup; exit-75 service restart is the only viable path).
|
|
|
|
Extracted from the inline probe in the /restart handler so tests can mock
|
|
container detection hermetically — a real ``/.dockerenv`` on a
|
|
containerized CI runner otherwise flips the routing under the test.
|
|
"""
|
|
return os.path.exists("/.dockerenv") or os.path.exists("/run/.containerenv")
|
|
|
|
|
|
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)
|