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.
44 lines
1.3 KiB
Python
44 lines
1.3 KiB
Python
from decimal import Decimal
|
|
|
|
from agent.models_dev import ModelInfo
|
|
from agent.usage_pricing import PricingEntry
|
|
from hermes_cli.model_cost_guard import expensive_model_warning
|
|
|
|
|
|
def test_no_warning_when_known_prices_are_at_threshold():
|
|
info = ModelInfo(
|
|
id="edge/model",
|
|
name="edge/model",
|
|
family="",
|
|
provider_id="test",
|
|
cost_input=20.0,
|
|
cost_output=100.0,
|
|
)
|
|
|
|
assert expensive_model_warning("edge/model", provider="test", model_info=info) is None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_openai_gpt55_pro_warns_for_nous_portal_pricing(monkeypatch):
|
|
monkeypatch.setattr("agent.models_dev.get_model_info", lambda *_args, **_kwargs: None)
|
|
monkeypatch.setattr(
|
|
"agent.usage_pricing.fetch_endpoint_model_metadata",
|
|
lambda base_url, api_key="": {
|
|
"openai/gpt-5.5-pro": {
|
|
"pricing": {
|
|
"prompt": "0.000025",
|
|
"completion": "0.000125",
|
|
}
|
|
}
|
|
},
|
|
)
|
|
|
|
warning = expensive_model_warning("openai/gpt-5.5-pro", provider="nous")
|
|
|
|
assert warning is not None
|
|
assert warning.input_cost_per_million == Decimal("25.000000")
|
|
assert warning.output_cost_per_million == Decimal("125.000000")
|
|
assert "did you mean to select openai/gpt-5.5?" in warning.message
|