mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-28 01:21:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

fix(gateway): close --replace race completely by claiming PID before adapter startup

Browse source 
Follow-up on top of opriz's atomic PID file fix. The prior change caught
the race AFTER runner.start(), so the loser still opened Telegram polling
and Discord gateway sockets before detecting the conflict and exiting.

Hoist the PID-claim block to BEFORE runner.start(). Now the loser of the
O_CREAT|O_EXCL race returns from start_gateway() without ever bringing up
any platform adapter — no Telegram conflict, no Discord duplicate session.

Also add regression tests:
- test_write_pid_file_is_atomic_against_concurrent_writers: second
  write_pid_file() raises FileExistsError rather than clobbering.
- Two existing replace-path tests updated to stateful mocks since the
  real post-kill state (get_running_pid None after remove_pid_file)
  is now exercised by the hoisted re-check.
This commit is contained in:
Teknium 2026-04-21 00:36:25 -07:00 • committed by Teknium
parent 56b99e8239
commit ce9c91c8f7
3 changed files with 64 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

20
tests/gateway/test_runner_startup_failures.py
View file

@ -184,8 +184,15 @@ async def test_start_gateway_replace_force_uses_terminate_pid(monkeypatch, tmp_p
async def stop(self):
return None
monkeypatch.setattr("gateway.status.get_running_pid", lambda: 42)
monkeypatch.setattr("gateway.status.remove_pid_file", lambda: None)
# get_running_pid returns 42 before we kill the old gateway, then None
# after remove_pid_file() clears the record (reflects real behavior).
_pid_state = {"alive": True}
def _mock_get_running_pid():
return 42 if _pid_state["alive"] else None
def _mock_remove_pid_file():
_pid_state["alive"] = False
monkeypatch.setattr("gateway.status.get_running_pid", _mock_get_running_pid)
monkeypatch.setattr("gateway.status.remove_pid_file", _mock_remove_pid_file)
monkeypatch.setattr("gateway.status.release_all_scoped_locks", lambda: 0)
monkeypatch.setattr("gateway.status.terminate_pid", lambda pid, force=False: calls.append((pid, force)))
monkeypatch.setattr("gateway.run.os.getpid", lambda: 100)
@ -253,8 +260,13 @@ async def test_start_gateway_replace_writes_takeover_marker_before_sigterm(
async def stop(self):
return None
monkeypatch.setattr("gateway.status.get_running_pid", lambda: 42)
monkeypatch.setattr("gateway.status.remove_pid_file", lambda: None)
_pid_state = {"alive": True}
def _mock_get_running_pid():
return 42 if _pid_state["alive"] else None
def _mock_remove_pid_file():
_pid_state["alive"] = False
monkeypatch.setattr("gateway.status.get_running_pid", _mock_get_running_pid)
monkeypatch.setattr("gateway.status.remove_pid_file", _mock_remove_pid_file)
monkeypatch.setattr("gateway.status.release_all_scoped_locks", lambda: 0)
monkeypatch.setattr("gateway.status.write_takeover_marker", record_write_marker)
monkeypatch.setattr("gateway.status.terminate_pid", record_terminate)