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.
48 lines
1.3 KiB
Python
48 lines
1.3 KiB
Python
"""Behavior contracts for computer_use latency knobs."""
|
|
|
|
from unittest.mock import patch
|
|
|
|
from tools.computer_use import cua_backend
|
|
from tools.computer_use import tool as cu_tool
|
|
|
|
|
|
def test_max_image_dimension_default():
|
|
with patch("hermes_cli.config.load_config", return_value={}):
|
|
assert cua_backend._computer_use_max_image_dimension() == 1456
|
|
|
|
|
|
|
|
|
|
def test_capture_after_mode_default_som():
|
|
with patch("hermes_cli.config.load_config", return_value={}):
|
|
assert cu_tool._capture_after_mode() == "som"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_aux_vision_route_caches_per_provider_model(monkeypatch):
|
|
cu_tool._AUX_VISION_ROUTE_CACHE.clear()
|
|
calls = {"n": 0}
|
|
|
|
monkeypatch.setattr(
|
|
"agent.auxiliary_client._read_main_provider", lambda: "openai"
|
|
)
|
|
monkeypatch.setattr(
|
|
"agent.auxiliary_client._read_main_model", lambda: "gpt-test"
|
|
)
|
|
|
|
def fake_load():
|
|
calls["n"] += 1
|
|
return {"auxiliary": {"vision": {}}}
|
|
|
|
monkeypatch.setattr("hermes_cli.config.load_config", fake_load)
|
|
monkeypatch.setattr(
|
|
"tools.computer_use.vision_routing.should_route_capture_to_aux_vision",
|
|
lambda *a, **k: True,
|
|
)
|
|
|
|
assert cu_tool._should_route_through_aux_vision() is True
|
|
assert cu_tool._should_route_through_aux_vision() is True
|
|
assert calls["n"] == 1
|