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.
57 lines
2.1 KiB
Python
57 lines
2.1 KiB
Python
"""Test that AuthError triggers fallback provider resolution (#7230)."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
|
|
class TestResolveRuntimeAgentKwargsAuthFallback:
|
|
"""_resolve_runtime_agent_kwargs should try fallback on AuthError."""
|
|
|
|
def test_auth_error_tries_fallback(self, tmp_path, monkeypatch):
|
|
"""When primary provider raises AuthError, fallback is attempted."""
|
|
from hermes_cli.auth import AuthError
|
|
|
|
# Create a config with fallback
|
|
config_path = tmp_path / "config.yaml"
|
|
config_path.write_text(
|
|
"model:\n provider: openai-codex\n"
|
|
"fallback_model:\n provider: openrouter\n"
|
|
" model: meta-llama/llama-4-maverick\n"
|
|
)
|
|
|
|
monkeypatch.setattr("gateway.run._hermes_home", tmp_path)
|
|
|
|
call_count = {"n": 0}
|
|
|
|
def _mock_resolve(**kwargs):
|
|
call_count["n"] += 1
|
|
# First call = primary path (gateway reads model.provider from
|
|
# config.yaml internally; we simulate the auth failure here).
|
|
# Second call = fallback path with explicit_api_key + explicit_base_url
|
|
# supplied by gateway from fallback_model config.
|
|
if call_count["n"] == 1:
|
|
raise AuthError("Codex token refresh failed with status 401")
|
|
return {
|
|
"api_key": "fallback-key",
|
|
"base_url": "https://openrouter.ai/api/v1",
|
|
"provider": "openrouter",
|
|
"api_mode": "openai_chat",
|
|
"command": None,
|
|
"args": None,
|
|
"credential_pool": None,
|
|
}
|
|
|
|
with patch(
|
|
"hermes_cli.runtime_provider.resolve_runtime_provider",
|
|
side_effect=_mock_resolve,
|
|
):
|
|
from gateway.run import _resolve_runtime_agent_kwargs
|
|
result = _resolve_runtime_agent_kwargs()
|
|
|
|
assert result["provider"] == "openrouter"
|
|
assert result["api_key"] == "fallback-key"
|
|
# Should have been called at least twice (primary + fallback)
|
|
assert call_count["n"] >= 2
|
|
|
|
|