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.
108 lines
2.6 KiB
Python
108 lines
2.6 KiB
Python
"""Tests for _ThreadedProcessHandle — the adapter for SDK backends."""
|
|
|
|
import threading
|
|
import time
|
|
|
|
from tools.environments.base import _ThreadedProcessHandle
|
|
|
|
|
|
class TestBasicExecution:
|
|
def test_successful_execution(self):
|
|
def exec_fn():
|
|
return ("hello world", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
handle.wait(timeout=5)
|
|
|
|
assert handle.returncode == 0
|
|
output = handle.stdout.read()
|
|
assert "hello world" in output
|
|
|
|
|
|
def test_empty_output(self):
|
|
def exec_fn():
|
|
return ("", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
handle.wait(timeout=5)
|
|
|
|
assert handle.returncode == 0
|
|
output = handle.stdout.read()
|
|
assert output == ""
|
|
|
|
|
|
class TestPolling:
|
|
def test_poll_returns_none_while_running(self):
|
|
event = threading.Event()
|
|
|
|
def exec_fn():
|
|
event.wait(timeout=5)
|
|
return ("done", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
assert handle.poll() is None
|
|
|
|
event.set()
|
|
handle.wait(timeout=5)
|
|
assert handle.poll() == 0
|
|
|
|
def test_poll_returns_returncode_when_done(self):
|
|
def exec_fn():
|
|
return ("ok", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
handle.wait(timeout=5)
|
|
assert handle.poll() == 0
|
|
|
|
|
|
class TestCancelFn:
|
|
def test_cancel_fn_called_on_kill(self):
|
|
called = threading.Event()
|
|
|
|
def cancel():
|
|
called.set()
|
|
|
|
def exec_fn():
|
|
time.sleep(10)
|
|
return ("", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn, cancel_fn=cancel)
|
|
handle.kill()
|
|
assert called.is_set()
|
|
|
|
|
|
def test_cancel_fn_exception_swallowed(self):
|
|
def cancel():
|
|
raise RuntimeError("cancel failed")
|
|
|
|
def exec_fn():
|
|
return ("ok", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn, cancel_fn=cancel)
|
|
handle.kill() # should not raise despite cancel raising
|
|
handle.wait(timeout=5)
|
|
|
|
|
|
class TestStdoutPipe:
|
|
def test_stdout_is_readable(self):
|
|
def exec_fn():
|
|
return ("line1\nline2\nline3\n", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
handle.wait(timeout=5)
|
|
|
|
lines = handle.stdout.readlines()
|
|
assert len(lines) == 3
|
|
assert lines[0] == "line1\n"
|
|
|
|
|
|
def test_unicode_output(self):
|
|
def exec_fn():
|
|
return ("hello 世界 🌍\n", 0)
|
|
|
|
handle = _ThreadedProcessHandle(exec_fn)
|
|
handle.wait(timeout=5)
|
|
|
|
output = handle.stdout.read()
|
|
assert "世界" in output
|
|
assert "🌍" in output
|