hermes-agent/tests/gateway/test_systemd_notify.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
Second, deeper pass over tools/gateway/hermes_cli plus first pass over
the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker,
dashboard, conformance, monitoring, secret_sources, hermes_state,
providers). Same rubric as wave 1 (AGENTS.md test policy); security,
alternation/caching invariants, issue-number regressions, and E2E kept.

Real test-quality fixes found and rooted out along the way:
- tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls
  (DEFAULT_CONFIG smart-approval leaked in) — pinned approval
  mode=manual via autouse fixture: 17.4s → 0.4s.
- test_model_switch_custom_providers.py / test_user_providers_model_switch.py
  silently probed live provider catalogs (~2s/test) — stubbed
  cached_provider_model_ids/provider_model_ids/fetch_api_models.
- test_telegram_noise_filter.py: 15-platform copy-paste matrix over
  shared gateway.run logic → 3 representative platforms (55s → 3.9s).
- test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on
  MagicMock agents — interrupt.side_effect now clears _running_agents
  (22s → 1.0s).
- test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x
  (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps
  patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait
  5s → 0.5s.
- test_telegram_init_deadline.py: loop-block margin restored to 1.0s
  with rationale comment — the watchdog-dump assertion needs the loop
  blocked well past deadline+grace under parallel load (flaked once in
  the 40-worker verification run at a 0.2s margin).

Verification: full hermetic suite via scripts/run_tests.sh —
2,438 files, 21,718 tests passed, 0 failed, 293.9s wall.
Suite totals vs original baseline: 46,820 → 19,757 test functions
(−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
2026-07-29 13:39:40 -07:00

81 lines
2.2 KiB
Python

"""Tests for the optional systemd event-loop watchdog protocol."""
from __future__ import annotations
import asyncio
import socket
import pytest
@pytest.mark.skipif(
not hasattr(socket, "AF_UNIX"), reason="Unix datagram sockets are unavailable"
)
def test_notify_supports_systemd_abstract_socket(monkeypatch):
name = "\0hermes-test-notify"
receiver = socket.socket(socket.AF_UNIX, socket.SOCK_DGRAM)
receiver.bind(name)
receiver.settimeout(1.0)
monkeypatch.setenv("NOTIFY_SOCKET", "@hermes-test-notify")
try:
from gateway.systemd_notify import notify
assert notify("WATCHDOG=1") is True
assert receiver.recv(4096) == b"WATCHDOG=1"
finally:
receiver.close()
def test_notify_uses_nonblocking_datagram_send(monkeypatch):
calls: list[object] = []
class _Sender:
def __enter__(self):
return self
def __exit__(self, *_args):
return None
def setblocking(self, value):
calls.append(("setblocking", value))
def connect(self, address):
calls.append(("connect", address))
def send(self, payload):
calls.append(("send", payload))
import gateway.systemd_notify as notify_mod
monkeypatch.setenv("NOTIFY_SOCKET", "/tmp/hermes-test-notify")
monkeypatch.setattr(notify_mod.socket, "socket", lambda *_args: _Sender())
assert notify_mod.notify("READY=1") is True
assert calls[0] == ("setblocking", False)
@pytest.mark.asyncio
async def test_watchdog_sends_ready_heartbeat_and_stopping(monkeypatch):
calls: list[str] = []
monkeypatch.setenv("NOTIFY_SOCKET", "/tmp/hermes-test-notify")
monkeypatch.setenv("WATCHDOG_USEC", "20000")
import gateway.systemd_notify as notify_mod
monkeypatch.setattr(
notify_mod, "notify", lambda message: calls.append(message) or True
)
watchdog = notify_mod.SystemdWatchdog(lag_tolerance_seconds=1.0)
assert watchdog.start() is True
assert watchdog.ready("Gateway running") is True
await asyncio.sleep(0.04)
await watchdog.stop()
assert any(message.startswith("READY=1") for message in calls)
assert "WATCHDOG=1" in calls
assert calls[-1] == "STOPPING=1"
assert watchdog.unhealthy is False