mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-07 02:51:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

fix: refresh systemd unit on gateway boot (not just start/restart) (#19684)

Browse source 
The resilient restart settings from PR #18639 only took effect when
the gateway was started via `hermes gateway start` or `hermes gateway
restart` — both of which call refresh_systemd_unit_if_needed() which
writes the new unit and runs daemon-reload.

However, when the gateway self-restarts via exit-code-75 (stale-code
detection after `hermes update`, or the /restart command), systemd
respawns the process directly without going through any CLI function.
The unit file on disk stays stale, and systemd keeps using the old
cached settings (StartLimitBurst=5, RestartSec=30) until someone
manually runs `hermes gateway restart`.

This meant that after PR #18639 was deployed, users who never ran
`hermes gateway restart` manually were still vulnerable to the
permanent-death-on-network-outage bug.

Fix: call refresh_systemd_unit_if_needed() at the top of run_gateway()
(the foreground entry point that systemd's ExecStart invokes). This
ensures that on every boot — whether triggered by systemd restart,
exit-75 respawn, or manual foreground run — the unit definition and
daemon state are current. The call is best-effort (exceptions caught)
and a no-op when the unit is already current (one stat + string compare).
This commit is contained in:
Siddharth Balyan 2026-05-04 16:27:51 +05:30 • committed by GitHub
parent 33f554d83c
commit af6f9bc2a1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 48 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

34
tests/hermes_cli/test_gateway_service.py
View file

@ -107,6 +107,40 @@ class TestSystemdServiceRefresh:
]
def test_run_gateway_refreshes_outdated_unit_on_boot(self, tmp_path, monkeypatch):
"""run_gateway() should refresh the systemd unit on boot so that
restart settings take effect even when the process was respawned
via exit-code-75 (bypassing `hermes gateway restart`)."""
unit_path = tmp_path / "hermes-gateway.service"
unit_path.write_text("old unit\n", encoding="utf-8")
monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit_path)
monkeypatch.setattr(gateway_cli, "generate_systemd_unit", lambda system=False, run_as_user=None: "new unit\n")
monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
calls = []
def fake_run(cmd, check=True, **kwargs):
calls.append(cmd)
return SimpleNamespace(returncode=0, stdout="", stderr="")
monkeypatch.setattr(gateway_cli.subprocess, "run", fake_run)
# Prevent run_gateway from actually starting the gateway
def fake_start_gateway(**kwargs):
import asyncio
f = asyncio.Future()
f.set_result(True)
return f
monkeypatch.setattr("gateway.run.start_gateway", fake_start_gateway)
gateway_cli.run_gateway()
assert unit_path.read_text(encoding="utf-8") == "new unit\n"
assert ["systemctl", "--user", "daemon-reload"] in calls
class TestGeneratedSystemdUnits:
def test_user_unit_avoids_recursive_execstop_and_uses_extended_stop_timeout(self):
unit = gateway_cli.generate_systemd_unit(system=False)