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.
50 lines
1.4 KiB
Python
50 lines
1.4 KiB
Python
"""Tests for hermes_cli/bundles.py — the `hermes bundles` CLI subcommand."""
|
|
|
|
import argparse
|
|
|
|
import pytest
|
|
|
|
from hermes_cli.bundles import (
|
|
bundles_command,
|
|
register_cli,
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def bundles_env(tmp_path, monkeypatch):
|
|
bundles_dir = tmp_path / "skill-bundles"
|
|
monkeypatch.setenv("HERMES_BUNDLES_DIR", str(bundles_dir))
|
|
# Reset module-level cache between tests.
|
|
import agent.skill_bundles as mod
|
|
mod._bundles_cache = {}
|
|
mod._bundles_cache_mtime = None
|
|
return bundles_dir
|
|
|
|
|
|
def _parse(argv):
|
|
parser = argparse.ArgumentParser()
|
|
register_cli(parser)
|
|
return parser.parse_args(argv)
|
|
|
|
|
|
class TestBundlesCli:
|
|
|
|
|
|
|
|
def test_create_refuses_overwrite(self, bundles_env, capsys):
|
|
bundles_command(_parse(["create", "dup", "--skill", "s1"]))
|
|
capsys.readouterr()
|
|
with pytest.raises(SystemExit) as ei:
|
|
bundles_command(_parse(["create", "dup", "--skill", "s2"]))
|
|
assert ei.value.code == 1
|
|
out = capsys.readouterr().out
|
|
assert "already exists" in out.lower() or "--force" in out.lower()
|
|
|
|
|
|
def test_create_requires_skills(self, bundles_env, capsys, monkeypatch):
|
|
# Simulate user pressing Ctrl-D immediately at the interactive prompt.
|
|
monkeypatch.setattr("builtins.input", lambda *_a, **_kw: (_ for _ in ()).throw(EOFError()))
|
|
with pytest.raises(SystemExit):
|
|
bundles_command(_parse(["create", "empty"]))
|
|
|
|
|