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.
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
"""Regression tests for gateway /model support of config.yaml custom_providers."""
|
|
|
|
import yaml
|
|
import pytest
|
|
|
|
from gateway.config import Platform
|
|
from gateway.platforms.base import MessageEvent, MessageType
|
|
from gateway.run import GatewayRunner
|
|
from gateway.session import SessionSource
|
|
|
|
|
|
def _make_runner():
|
|
runner = object.__new__(GatewayRunner)
|
|
runner.adapters = {}
|
|
runner._voice_mode = {}
|
|
runner._session_model_overrides = {}
|
|
return runner
|
|
|
|
|
|
def _make_event(text="/model"):
|
|
return MessageEvent(
|
|
text=text,
|
|
message_type=MessageType.TEXT,
|
|
source=SessionSource(platform=Platform.TELEGRAM, chat_id="12345", chat_type="dm"),
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_direct_model_switch_offloads_to_thread(tmp_path, monkeypatch):
|
|
"""A direct `/model <name>` switch must route switch_model() through
|
|
asyncio.to_thread so the blocking models.dev HTTP fetch can't freeze the
|
|
gateway event loop (#20525)."""
|
|
import asyncio
|
|
|
|
from hermes_cli.model_switch import ModelSwitchResult
|
|
|
|
hermes_home = tmp_path / ".hermes"
|
|
hermes_home.mkdir()
|
|
(hermes_home / "config.yaml").write_text(
|
|
yaml.safe_dump(
|
|
{"model": {"default": "gpt-5.4", "provider": "openrouter"}}
|
|
),
|
|
encoding="utf-8",
|
|
)
|
|
|
|
import gateway.run as gateway_run
|
|
|
|
monkeypatch.setattr(gateway_run, "_hermes_home", hermes_home)
|
|
|
|
# Fail the switch so the handler returns before _finish_switch (which needs
|
|
# full runner state) — we only care that the offload happened.
|
|
def _fake_switch(**kwargs):
|
|
return ModelSwitchResult(success=False, error_message="nope")
|
|
|
|
monkeypatch.setattr("hermes_cli.model_switch.switch_model", _fake_switch)
|
|
|
|
offloaded = []
|
|
real_to_thread = asyncio.to_thread
|
|
|
|
async def _spy_to_thread(func, /, *args, **kwargs):
|
|
offloaded.append(getattr(func, "__name__", repr(func)))
|
|
return await real_to_thread(func, *args, **kwargs)
|
|
|
|
monkeypatch.setattr(asyncio, "to_thread", _spy_to_thread)
|
|
|
|
result = await _make_runner()._handle_model_command(_make_event("/model gpt-5.4"))
|
|
|
|
# switch_model was offloaded to a worker thread, not run on the event loop.
|
|
assert "_fake_switch" in offloaded
|
|
assert result is not None and "nope" in result
|