mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
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.
68 lines
2 KiB
Python
68 lines
2 KiB
Python
"""Shutdown watchdog + loop heartbeat coverage for #66892.
|
|
|
|
The drain path is asyncio-based; a frozen loop makes every asyncio timeout
|
|
structurally unable to fire. These tests pin the out-of-loop backstop
|
|
(thread watchdog) and the loop-liveness heartbeat file contract.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import json
|
|
import threading
|
|
import time
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from gateway.shutdown_watchdog import (
|
|
DEFAULT_SHUTDOWN_WATCHDOG_GRACE_S,
|
|
arm_shutdown_watchdog,
|
|
get_loop_heartbeat_path,
|
|
get_shutdown_watchdog_dump_path,
|
|
loop_heartbeat_forever,
|
|
resolve_shutdown_watchdog_delay,
|
|
write_loop_heartbeat,
|
|
)
|
|
|
|
def test_resolve_shutdown_watchdog_delay_adds_grace():
|
|
assert resolve_shutdown_watchdog_delay(180) == 180 + DEFAULT_SHUTDOWN_WATCHDOG_GRACE_S
|
|
assert resolve_shutdown_watchdog_delay(0) == DEFAULT_SHUTDOWN_WATCHDOG_GRACE_S
|
|
assert resolve_shutdown_watchdog_delay("bad") == DEFAULT_SHUTDOWN_WATCHDOG_GRACE_S
|
|
assert resolve_shutdown_watchdog_delay(10, grace_s=5) == 15.0
|
|
|
|
|
|
def test_arm_shutdown_watchdog_fires_with_dump_and_exit(tmp_path):
|
|
done = threading.Event()
|
|
fired = threading.Event()
|
|
dump = tmp_path / "logs" / "watchdog.log"
|
|
snapshot_calls = []
|
|
exit_codes = []
|
|
|
|
def snapshot():
|
|
snapshot_calls.append(1)
|
|
return {"active_agents": 1, "draining": True}
|
|
|
|
def fake_exit(code):
|
|
exit_codes.append(code)
|
|
fired.set()
|
|
|
|
with patch("gateway.shutdown_watchdog.os._exit", side_effect=fake_exit):
|
|
arm_shutdown_watchdog(
|
|
0.15,
|
|
done_event=done,
|
|
snapshot_fn=snapshot,
|
|
dump_path=dump,
|
|
exit_code=9,
|
|
)
|
|
assert fired.wait(timeout=5.0), "watchdog did not fire"
|
|
|
|
assert exit_codes == [9]
|
|
assert snapshot_calls == [1]
|
|
assert dump.is_file()
|
|
text = dump.read_text(encoding="utf-8")
|
|
assert "shutdown_watchdog_fired" in text
|
|
assert "faulthandler dump" in text
|
|
assert get_shutdown_watchdog_dump_path(tmp_path).name == "gateway-shutdown-watchdog.log"
|
|
|
|
|