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.
81 lines
3.1 KiB
Python
81 lines
3.1 KiB
Python
"""Tests for the static-catalog fallback in validate_requested_model.
|
|
|
|
OpenCode Go and OpenCode Zen publish an OpenAI-compatible API at paths that do
|
|
NOT expose ``/models`` (the path returns the marketing site's HTML 404). This
|
|
caused ``validate_requested_model`` to return ``accepted=False`` for every
|
|
model on those providers, which in turn made ``switch_model()`` fail and the
|
|
gateway's ``/model <name> --provider opencode-go`` command never write to
|
|
``_session_model_overrides``.
|
|
|
|
These tests cover the catalog-fallback path: when ``fetch_api_models`` returns
|
|
``None``, the validator must consult ``provider_model_ids()`` for the provider
|
|
(populated from ``_PROVIDER_MODELS``) rather than rejecting outright.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
from hermes_cli.models import validate_requested_model
|
|
|
|
|
|
_UNREACHABLE_PROBE = {
|
|
"models": None,
|
|
"probed_url": "https://opencode.ai/zen/go/v1/models",
|
|
"resolved_base_url": "https://opencode.ai/zen/go/v1",
|
|
"suggested_base_url": None,
|
|
"used_fallback": False,
|
|
}
|
|
|
|
|
|
def _patched(func):
|
|
"""Decorator: force fetch_api_models / probe_api_models to simulate an
|
|
unreachable /models endpoint, proving the catalog path is used."""
|
|
def wrapper(*args, **kwargs):
|
|
with patch("hermes_cli.models.fetch_api_models", return_value=None), \
|
|
patch("hermes_cli.models.probe_api_models", return_value=_UNREACHABLE_PROBE):
|
|
return func(*args, **kwargs)
|
|
wrapper.__name__ = func.__name__
|
|
return wrapper
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# opencode-go: curated catalog in _PROVIDER_MODELS
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@_patched
|
|
def test_opencode_go_known_model_accepted():
|
|
"""A model present in the opencode-go curated catalog must be accepted
|
|
even when /models is unreachable."""
|
|
result = validate_requested_model("kimi-k2.6", "opencode-go")
|
|
assert result["accepted"] is True
|
|
assert result["persist"] is True
|
|
assert result["recognized"] is True
|
|
assert result["message"] is None
|
|
|
|
|
|
@_patched
|
|
def test_opencode_go_totally_unknown_model_still_accepted():
|
|
"""A model with zero similarity to the catalog is still accepted (no
|
|
suggestion line) so the user can try a model that hasn't made it into the
|
|
curated list yet."""
|
|
result = validate_requested_model("some-brand-new-model", "opencode-go")
|
|
assert result["accepted"] is True
|
|
assert result["persist"] is True
|
|
assert result["recognized"] is False
|
|
# No suggestion text (no close matches)
|
|
assert "Similar models" not in result["message"]
|
|
assert "opencode" in result["message"].lower() or "opencode go" in result["message"].lower()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# opencode-zen: same pattern as opencode-go
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Unknown provider with no catalog: soft-accept (honors the comment's intent)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|