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.
75 lines
2.4 KiB
Python
75 lines
2.4 KiB
Python
"""Tests for tools.daemon_pool.DaemonThreadPoolExecutor.
|
|
|
|
The daemon pool exists so abandoned workers (interrupted/timed-out tool
|
|
batches, wedged memory-provider syncs) can never block interpreter exit:
|
|
stdlib ThreadPoolExecutor workers are non-daemon AND registered in
|
|
concurrent.futures.thread._threads_queues, whose atexit hook joins every
|
|
worker unconditionally — even after shutdown(wait=False).
|
|
"""
|
|
|
|
import subprocess
|
|
import sys
|
|
import threading
|
|
import time
|
|
|
|
from concurrent.futures.thread import _threads_queues
|
|
|
|
from tools.daemon_pool import DaemonThreadPoolExecutor
|
|
|
|
|
|
def test_workers_are_daemon_threads():
|
|
pool = DaemonThreadPoolExecutor(max_workers=2)
|
|
try:
|
|
info = pool.submit(
|
|
lambda: (threading.current_thread().daemon, threading.current_thread())
|
|
).result(timeout=10)
|
|
is_daemon, worker = info
|
|
assert is_daemon is True
|
|
# Not registered with concurrent.futures' atexit join hook.
|
|
assert worker not in _threads_queues
|
|
finally:
|
|
pool.shutdown(wait=True)
|
|
|
|
|
|
def test_idle_worker_reuse():
|
|
pool = DaemonThreadPoolExecutor(max_workers=4)
|
|
try:
|
|
tid1 = pool.submit(threading.get_ident).result(timeout=10)
|
|
time.sleep(0.05) # let the worker park on the idle semaphore
|
|
tid2 = pool.submit(threading.get_ident).result(timeout=10)
|
|
assert tid1 == tid2
|
|
finally:
|
|
pool.shutdown(wait=True)
|
|
|
|
|
|
def test_wedged_worker_does_not_block_interpreter_exit():
|
|
"""A worker stuck in a long sleep must not hold the process open.
|
|
|
|
With stdlib ThreadPoolExecutor this subprocess hangs until the sleep
|
|
finishes (the atexit hook joins the worker); with the daemon pool it
|
|
exits as soon as the main thread returns.
|
|
"""
|
|
script = (
|
|
"import sys; sys.path.insert(0, %r)\n"
|
|
"from tools.daemon_pool import DaemonThreadPoolExecutor\n"
|
|
"import time\n"
|
|
"pool = DaemonThreadPoolExecutor(max_workers=1)\n"
|
|
"pool.submit(time.sleep, 120)\n"
|
|
"time.sleep(0.3)\n"
|
|
"pool.shutdown(wait=False)\n"
|
|
"print('main-done', flush=True)\n"
|
|
) % (str(_repo_root()),)
|
|
proc = subprocess.run(
|
|
[sys.executable, "-c", script],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=30,
|
|
)
|
|
assert proc.returncode == 0
|
|
assert "main-done" in proc.stdout
|
|
|
|
|
|
def _repo_root():
|
|
import pathlib
|
|
|
|
return pathlib.Path(__file__).resolve().parents[2]
|