mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
58 lines
2.3 KiB
Python
58 lines
2.3 KiB
Python
"""Regression tests for the _get_command_timeout cache race (#14331).
|
|
|
|
Before the fix:
|
|
``_command_timeout_resolved`` was set to ``True`` *before*
|
|
``_cached_command_timeout`` was assigned. If the body raised between those
|
|
two statements (e.g. inside ``read_raw_config``), or a re-entrant/concurrent
|
|
reader hit the cache between them, the function returned ``None``. Callers
|
|
then evaluated ``max(None, 60)`` and crashed with::
|
|
|
|
TypeError: '>' not supported between instances of 'int' and 'NoneType'
|
|
|
|
The fix:
|
|
1. assign cache before flipping the resolved flag,
|
|
2. flip the resolved flag *off* before nulling the cache in
|
|
``cleanup_all_browsers()``,
|
|
3. expose ``_safe_command_timeout()`` as defense in depth.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
class TestGetCommandTimeoutRace:
|
|
def setup_method(self):
|
|
from tools import browser_tool
|
|
|
|
self.bt = browser_tool
|
|
self._orig_cache = browser_tool._cached_command_timeout
|
|
self._orig_resolved = browser_tool._command_timeout_resolved
|
|
browser_tool._cached_command_timeout = None
|
|
browser_tool._command_timeout_resolved = False
|
|
|
|
def teardown_method(self):
|
|
self.bt._cached_command_timeout = self._orig_cache
|
|
self.bt._command_timeout_resolved = self._orig_resolved
|
|
|
|
def test_returns_default_when_config_read_raises(self):
|
|
"""If config reading blows up, we still return an int (not None)."""
|
|
with patch(
|
|
"hermes_cli.config.read_raw_config", side_effect=RuntimeError("boom")
|
|
):
|
|
result = self.bt._get_command_timeout()
|
|
|
|
assert isinstance(result, int)
|
|
assert result == self.bt.DEFAULT_COMMAND_TIMEOUT
|
|
# Cache must be populated (not left as None) once resolved is True.
|
|
assert self.bt._cached_command_timeout is not None
|
|
assert self.bt._command_timeout_resolved is True
|
|
|
|
|
|
def test_max_call_site_pattern_never_raises(self):
|
|
"""The exact expression from browser_navigate must not raise TypeError."""
|
|
# Force the corrupted state the bug used to produce.
|
|
self.bt._command_timeout_resolved = True
|
|
self.bt._cached_command_timeout = None
|
|
|
|
# This is the literal line from browser_navigate() after the fix.
|
|
timeout = max(self.bt._safe_command_timeout(), 60)
|
|
assert timeout == 60
|