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.
54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
"""Tests for tools/debug_helpers.py — DebugSession class."""
|
|
|
|
import json
|
|
import os
|
|
from unittest.mock import patch
|
|
|
|
from tools.debug_helpers import DebugSession
|
|
|
|
|
|
class TestDebugSessionDisabled:
|
|
"""When the env var is not set, DebugSession should be a cheap no-op."""
|
|
|
|
def test_not_active_by_default(self):
|
|
ds = DebugSession("test_tool", env_var="FAKE_DEBUG_VAR_XYZ")
|
|
assert ds.active is False
|
|
assert ds.enabled is False
|
|
|
|
|
|
def test_get_session_info_disabled(self):
|
|
ds = DebugSession("test_tool", env_var="FAKE_DEBUG_VAR_XYZ")
|
|
info = ds.get_session_info()
|
|
assert info["enabled"] is False
|
|
assert info["session_id"] is None
|
|
assert info["log_path"] is None
|
|
assert info["total_calls"] == 0
|
|
|
|
|
|
class TestDebugSessionEnabled:
|
|
"""When the env var is set to 'true', DebugSession records and saves."""
|
|
|
|
def _make_enabled(self, tmp_path):
|
|
with patch.dict(os.environ, {"TEST_DEBUG": "true"}):
|
|
ds = DebugSession("test_tool", env_var="TEST_DEBUG")
|
|
ds.log_dir = tmp_path
|
|
return ds
|
|
|
|
def test_active_when_env_set(self, tmp_path):
|
|
ds = self._make_enabled(tmp_path)
|
|
assert ds.active is True
|
|
assert ds.enabled is True
|
|
|
|
def test_session_id_generated(self, tmp_path):
|
|
ds = self._make_enabled(tmp_path)
|
|
assert len(ds.session_id) > 0
|
|
|
|
|
|
def test_save_empty_log(self, tmp_path):
|
|
ds = self._make_enabled(tmp_path)
|
|
ds.save()
|
|
files = list(tmp_path.glob("*.json"))
|
|
assert len(files) == 1
|
|
data = json.loads(files[0].read_text())
|
|
assert data["total_calls"] == 0
|
|
assert data["tool_calls"] == []
|