mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
80 lines
2 KiB
Python
80 lines
2 KiB
Python
"""Tests for `hermes chat --safe-mode` isolation."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import sys
|
|
import types
|
|
|
|
import pytest
|
|
|
|
|
|
_VARS = ("HERMES_SAFE_MODE", "HERMES_IGNORE_USER_CONFIG", "HERMES_IGNORE_RULES")
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_env(monkeypatch):
|
|
for var in _VARS:
|
|
monkeypatch.delenv(var, raising=False)
|
|
yield
|
|
for var in _VARS:
|
|
os.environ.pop(var, None)
|
|
|
|
|
|
def test_cmd_chat_safe_mode_sets_env_before_startup(monkeypatch):
|
|
import hermes_cli.main as main_mod
|
|
from hermes_cli._parser import build_top_level_parser
|
|
|
|
parser, _subparsers, chat_parser = build_top_level_parser()
|
|
chat_parser.set_defaults(func=main_mod.cmd_chat)
|
|
args = parser.parse_args(["chat", "--safe-mode"])
|
|
captured: dict[str, object] = {}
|
|
fake_cli = types.ModuleType("cli")
|
|
|
|
def fake_has_provider() -> bool:
|
|
assert os.environ["HERMES_SAFE_MODE"] == "1"
|
|
assert os.environ["HERMES_IGNORE_USER_CONFIG"] == "1"
|
|
assert os.environ["HERMES_IGNORE_RULES"] == "1"
|
|
return True
|
|
|
|
def fake_main(**kwargs):
|
|
captured.update(kwargs)
|
|
|
|
monkeypatch.setattr(main_mod, "_has_any_provider_configured", fake_has_provider)
|
|
monkeypatch.setattr(main_mod, "_pin_kanban_board_env", lambda: None)
|
|
monkeypatch.setattr(main_mod, "_sync_bundled_skills_for_startup", lambda: None)
|
|
monkeypatch.setattr(main_mod, "_termux_should_prefetch_update_check", lambda: False)
|
|
setattr(fake_cli, "main", fake_main)
|
|
monkeypatch.setitem(sys.modules, "cli", fake_cli)
|
|
|
|
main_mod.cmd_chat(args)
|
|
|
|
assert captured["ignore_user_config"] is True
|
|
assert captured["ignore_rules"] is True
|
|
|
|
|
|
|
|
|
|
def test_plugin_discovery_skipped(monkeypatch):
|
|
monkeypatch.setenv("HERMES_SAFE_MODE", "1")
|
|
from hermes_cli.plugins import PluginManager
|
|
|
|
mgr = PluginManager()
|
|
called = []
|
|
monkeypatch.setattr(mgr, "_discover_and_load_inner", lambda: called.append(True))
|
|
|
|
mgr.discover_and_load()
|
|
|
|
assert called == []
|
|
assert mgr._discovered is True
|
|
assert mgr._plugins == {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|