mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-29 01:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(gateway): recover stale pid and planned restart state

Browse source
This commit is contained in:
helix4u 2026-04-22 17:17:16 -06:00 • committed by Teknium
parent 284e084bcc
commit b52123eb15
7 changed files with 646 additions and 79 deletions
Download patch file Download diff file Expand all files Collapse all files

85
tests/gateway/test_status.py
View file

@ -65,7 +65,11 @@ class TestGatewayPidState:
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
assert status.get_running_pid() == os.getpid()
assert status.acquire_gateway_runtime_lock() is True
try:
assert status.get_running_pid() == os.getpid()
finally:
status.release_gateway_runtime_lock()
def test_get_running_pid_accepts_script_style_gateway_cmdline(self, tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
@ -85,7 +89,11 @@ class TestGatewayPidState:
lambda pid: "/venv/bin/python /repo/hermes_cli/main.py gateway run --replace",
)
assert status.get_running_pid() == os.getpid()
assert status.acquire_gateway_runtime_lock() is True
try:
assert status.get_running_pid() == os.getpid()
finally:
status.release_gateway_runtime_lock()
def test_get_running_pid_accepts_explicit_pid_path_without_cleanup(self, tmp_path, monkeypatch):
other_home = tmp_path / "profile-home"
@ -102,9 +110,82 @@ class TestGatewayPidState:
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
lock_path = other_home / "gateway.lock"
lock_path.write_text(json.dumps({
"pid": os.getpid(),
"kind": "hermes-gateway",
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
"start_time": 123,
}))
monkeypatch.setattr(status, "is_gateway_runtime_lock_active", lambda lock_path=None: True)
assert status.get_running_pid(pid_path, cleanup_stale=False) == os.getpid()
assert pid_path.exists()
def test_runtime_lock_claims_and_releases_liveness(self, tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
assert status.is_gateway_runtime_lock_active() is False
assert status.acquire_gateway_runtime_lock() is True
assert status.is_gateway_runtime_lock_active() is True
status.release_gateway_runtime_lock()
assert status.is_gateway_runtime_lock_active() is False
def test_get_running_pid_treats_pid_file_as_stale_without_runtime_lock(self, tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
pid_path = tmp_path / "gateway.pid"
pid_path.write_text(json.dumps({
"pid": os.getpid(),
"kind": "hermes-gateway",
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
"start_time": 123,
}))
monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
assert status.get_running_pid() is None
assert not pid_path.exists()
def test_get_running_pid_falls_back_to_live_lock_record(self, tmp_path, monkeypatch):
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
pid_path = tmp_path / "gateway.pid"
pid_path.write_text(json.dumps({
"pid": 99999,
"kind": "hermes-gateway",
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
"start_time": 123,
}))
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
monkeypatch.setattr(
status,
"_build_pid_record",
lambda: {
"pid": os.getpid(),
"kind": "hermes-gateway",
"argv": ["python", "-m", "hermes_cli.main", "gateway"],
"start_time": 123,
},
)
assert status.acquire_gateway_runtime_lock() is True
def fake_kill(pid, sig):
if pid == 99999:
raise ProcessLookupError
return None
monkeypatch.setattr(status.os, "kill", fake_kill)
try:
assert status.get_running_pid() == os.getpid()
finally:
status.release_gateway_runtime_lock()
class TestGatewayRuntimeStatus:
def test_write_runtime_status_overwrites_stale_pid_on_restart(self, tmp_path, monkeypatch):