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.
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
"""Regression tests for gateway runtime config env-var expansion."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
import gateway.run as gateway_run
|
|
|
|
|
|
def _write_config(home, body: str) -> None:
|
|
(home / "config.yaml").write_text(body, encoding="utf-8")
|
|
|
|
|
|
@pytest.fixture
|
|
def gateway_home(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(gateway_run, "_hermes_home", tmp_path)
|
|
monkeypatch.delenv("HERMES_PREFILL_MESSAGES_FILE", raising=False)
|
|
monkeypatch.delenv("HERMES_EPHEMERAL_SYSTEM_PROMPT", raising=False)
|
|
monkeypatch.delenv("HERMES_GATEWAY_BUSY_INPUT_MODE", raising=False)
|
|
monkeypatch.delenv("HERMES_RESTART_DRAIN_TIMEOUT", raising=False)
|
|
monkeypatch.delenv("HERMES_BACKGROUND_NOTIFICATIONS", raising=False)
|
|
return tmp_path
|
|
|
|
|
|
def test_load_prefill_messages_prefers_top_level_over_legacy(monkeypatch, gateway_home):
|
|
top_level = [{"role": "system", "content": "top-level"}]
|
|
legacy = [{"role": "system", "content": "legacy"}]
|
|
(gateway_home / "top.json").write_text(json.dumps(top_level), encoding="utf-8")
|
|
(gateway_home / "legacy.json").write_text(json.dumps(legacy), encoding="utf-8")
|
|
_write_config(
|
|
gateway_home,
|
|
"prefill_messages_file: top.json\n"
|
|
"agent:\n"
|
|
" prefill_messages_file: legacy.json\n",
|
|
)
|
|
|
|
assert gateway_run.GatewayRunner._load_prefill_messages() == top_level
|
|
|
|
|