mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +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.
62 lines
2 KiB
Python
62 lines
2 KiB
Python
"""Regression tests for numbered fallbacks when the interactive curses menu
|
|
cannot initialize (e.g. non-TTY, curses unavailable, terminal error)."""
|
|
|
|
import subprocess
|
|
from types import SimpleNamespace
|
|
|
|
from hermes_cli.config import load_config, save_config
|
|
|
|
|
|
def _raise_menu(*args, **kwargs):
|
|
# Mimic curses_radiolist hitting an unrecoverable terminal error so the
|
|
# caller's except clause routes to the numbered-input fallback.
|
|
raise subprocess.CalledProcessError(2, ["tput", "clear"])
|
|
|
|
|
|
|
|
|
|
def test_prompt_model_selection_requires_expensive_confirmation(monkeypatch, capsys):
|
|
from hermes_cli.auth import _prompt_model_selection
|
|
|
|
monkeypatch.setattr("hermes_cli.curses_ui.curses_radiolist", _raise_menu)
|
|
monkeypatch.setattr(
|
|
"hermes_cli.model_cost_guard.expensive_model_warning",
|
|
lambda *_args, **_kwargs: SimpleNamespace(message="EXPENSIVE MODEL WARNING"),
|
|
)
|
|
responses = iter(["1", "n"])
|
|
monkeypatch.setattr("builtins.input", lambda _prompt="": next(responses))
|
|
|
|
selected = _prompt_model_selection(
|
|
["openai/gpt-5.5-pro"],
|
|
confirm_provider="nous",
|
|
)
|
|
|
|
out = capsys.readouterr().out
|
|
assert selected is None
|
|
assert "EXPENSIVE MODEL WARNING" in out
|
|
|
|
|
|
def test_remove_custom_provider_falls_back_on_menu_runtime_error(tmp_path, monkeypatch):
|
|
from hermes_cli.main import _remove_custom_provider
|
|
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
monkeypatch.setattr("hermes_cli.curses_ui.curses_radiolist", _raise_menu)
|
|
|
|
cfg = load_config()
|
|
cfg["custom_providers"] = [
|
|
{"name": "Local A", "base_url": "http://localhost:8001/v1"},
|
|
{"name": "Local B", "base_url": "http://localhost:8002/v1"},
|
|
]
|
|
save_config(cfg)
|
|
|
|
responses = iter(["1"])
|
|
monkeypatch.setattr("builtins.input", lambda _prompt="": next(responses))
|
|
|
|
_remove_custom_provider(cfg)
|
|
|
|
reloaded = load_config()
|
|
assert reloaded["custom_providers"] == [
|
|
{"name": "Local B", "base_url": "http://localhost:8002/v1"},
|
|
]
|
|
|
|
|