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.
68 lines
2.1 KiB
Python
68 lines
2.1 KiB
Python
"""Tests for read_raw_config_readonly() — the no-deepcopy raw config read.
|
|
|
|
The readonly variant exists for per-turn policy checks (e.g. the
|
|
shared-metrics gate) that were paying a full config deepcopy on every call.
|
|
Contract under test:
|
|
|
|
1. identity invariant — repeat calls return the SAME cached object,
|
|
including across the very first (cache-miss) call;
|
|
2. freshness — an edited config.yaml (mtime/size change) is picked up;
|
|
3. parity — content equals read_raw_config()'s result;
|
|
4. missing/broken config degrades to {} exactly like read_raw_config().
|
|
"""
|
|
|
|
import os
|
|
import time
|
|
|
|
import pytest
|
|
import yaml
|
|
|
|
|
|
@pytest.fixture()
|
|
def isolated_hermes_home():
|
|
"""Per-test HERMES_HOME dir (already redirected by the autouse conftest
|
|
fixture) as a Path, with the raw-config cache cleared around the test."""
|
|
from pathlib import Path
|
|
|
|
import hermes_cli.config as config_mod
|
|
|
|
home = Path(os.environ["HERMES_HOME"])
|
|
home.mkdir(parents=True, exist_ok=True)
|
|
config_mod._RAW_CONFIG_CACHE.clear()
|
|
yield home
|
|
config_mod._RAW_CONFIG_CACHE.clear()
|
|
|
|
|
|
def _write_config(home, data):
|
|
cfg = home / "config.yaml"
|
|
cfg.write_text(yaml.safe_dump(data), encoding="utf-8")
|
|
return cfg
|
|
|
|
|
|
|
|
|
|
def test_freshness_after_config_edit(isolated_hermes_home):
|
|
from hermes_cli.config import read_raw_config_readonly
|
|
|
|
cfg = _write_config(isolated_hermes_home, {"display": {"ephemeral_system_ttl": 1}})
|
|
first = read_raw_config_readonly()
|
|
assert first["display"]["ephemeral_system_ttl"] == 1
|
|
|
|
_write_config(isolated_hermes_home, {"display": {"ephemeral_system_ttl": 7}})
|
|
# Force a distinct mtime_ns even on coarse-timestamp filesystems.
|
|
st = cfg.stat()
|
|
os.utime(cfg, ns=(st.st_atime_ns, st.st_mtime_ns + 1_000_000))
|
|
|
|
second = read_raw_config_readonly()
|
|
assert second["display"]["ephemeral_system_ttl"] == 7
|
|
|
|
|
|
def test_missing_config_returns_empty(isolated_hermes_home):
|
|
from hermes_cli.config import read_raw_config_readonly
|
|
|
|
cfg = isolated_hermes_home / "config.yaml"
|
|
if cfg.exists():
|
|
cfg.unlink()
|
|
assert read_raw_config_readonly() == {}
|
|
|
|
|