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.
68 lines
2.6 KiB
Python
68 lines
2.6 KiB
Python
"""Regression tests for the _find_all_skills discovery cache (#58985 salvage).
|
|
|
|
Covers the cache-signature fix layered on the cherry-picked contributor
|
|
commit: the original keyed the cache on the max mtime of only the TOP-LEVEL
|
|
scan dirs, so adding/removing a skill inside a category subdir (which bumps
|
|
the category dir's mtime, not the root's) served a stale list indefinitely.
|
|
The signature now covers roots + immediate children (mirroring
|
|
hermes_cli/profiles.py::_count_skills) plus the disabled-set, with a short
|
|
TTL bounding in-place SKILL.md edit staleness.
|
|
"""
|
|
|
|
import time
|
|
|
|
import pytest
|
|
|
|
import tools.skills_tool as st
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _fresh_cache(monkeypatch, tmp_path):
|
|
"""Isolate every test: clear the module cache and point the scan at
|
|
an empty external-dirs list + a tmp skills root."""
|
|
st._SKILLS_CACHE.clear()
|
|
monkeypatch.setattr(st, "_skills_dir", lambda: tmp_path / "skills")
|
|
monkeypatch.setattr(
|
|
"agent.skill_utils.get_external_skills_dirs", lambda: []
|
|
)
|
|
monkeypatch.setattr(st, "_get_disabled_skill_names", lambda: set())
|
|
yield
|
|
st._SKILLS_CACHE.clear()
|
|
|
|
|
|
def _write_skill(root, category, name, description="a skill"):
|
|
d = root / "skills" / category / name
|
|
d.mkdir(parents=True, exist_ok=True)
|
|
(d / "SKILL.md").write_text(
|
|
f"---\nname: {name}\ndescription: {description}\n---\n# {name}\n",
|
|
encoding="utf-8",
|
|
)
|
|
return d
|
|
|
|
|
|
def test_cache_hit_serves_copies_not_cache_objects(tmp_path):
|
|
"""Callers mutate the returned dicts (web_server annotates
|
|
s['enabled']/s['usage']) — the cache must hand out per-call copies."""
|
|
_write_skill(tmp_path, "cat-a", "skill-one")
|
|
first = st._find_all_skills()
|
|
assert [s["name"] for s in first] == ["skill-one"]
|
|
|
|
# Mutate what the first caller got; the next (cached) call must be clean.
|
|
first[0]["enabled"] = False
|
|
first.append({"name": "junk"})
|
|
|
|
second = st._find_all_skills()
|
|
assert [s["name"] for s in second] == ["skill-one"]
|
|
assert "enabled" not in second[0], "cache poisoned by caller mutation"
|
|
assert second is not first
|
|
|
|
|
|
def test_disabled_and_full_views_cached_separately(tmp_path, monkeypatch):
|
|
_write_skill(tmp_path, "cat-a", "skill-one")
|
|
_write_skill(tmp_path, "cat-a", "skill-two")
|
|
monkeypatch.setattr(st, "_get_disabled_skill_names", lambda: {"skill-two"})
|
|
|
|
filtered = sorted(s["name"] for s in st._find_all_skills())
|
|
everything = sorted(s["name"] for s in st._find_all_skills(skip_disabled=True))
|
|
assert filtered == ["skill-one"]
|
|
assert everything == ["skill-one", "skill-two"]
|