hermes-agent/tests/hermes_cli/test_lmstudio_context_policy.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

91 lines
2.2 KiB
Python

import json
import pytest
from hermes_cli import models
MODEL = "publisher/model"
BASE_URL = "http://127.0.0.1:1234/v1"
class _JsonResponse:
def __init__(self, payload):
self._body = json.dumps(payload).encode()
def __enter__(self):
return self
def __exit__(self, *_args):
return False
def read(self):
return self._body
def _catalog(*, loaded_context=None, maximum=262_144):
loaded_instances = []
if loaded_context is not None:
loaded_instances.append({
"id": f"{MODEL}:active",
"config": {"context_length": loaded_context},
})
return [{
"key": MODEL,
"max_context_length": maximum,
"loaded_instances": loaded_instances,
}]
def _capture_load(monkeypatch, response_payload):
requests = []
def fake_open(request, *, timeout):
requests.append((request, timeout, json.loads(request.data.decode())))
return _JsonResponse(response_payload)
monkeypatch.setattr(models, "_urlopen_model_catalog_request", fake_open)
return requests
def test_missing_echo_refreshes_loaded_state(monkeypatch):
catalogs = iter([_catalog(), _catalog(loaded_context=88_000)])
monkeypatch.setattr(
models, "_lmstudio_fetch_raw_models", lambda **_kwargs: next(catalogs)
)
_capture_load(monkeypatch, {"status": "loaded"})
result = models.ensure_lmstudio_model_loaded(
MODEL, BASE_URL, api_key="", target_context_length=100_000
)
assert result == 88_000
def test_explicit_override_above_known_maximum_rejects_even_when_loaded(monkeypatch):
monkeypatch.setattr(
models,
"_lmstudio_fetch_raw_models",
lambda **_kwargs: _catalog(loaded_context=64_000, maximum=128_000),
)
monkeypatch.setattr(
models,
"_urlopen_model_catalog_request",
lambda *_args, **_kwargs: pytest.fail("invalid override must not be posted"),
)
result = models.ensure_lmstudio_model_loaded(
MODEL,
BASE_URL,
api_key="",
target_context_length=256_000,
return_load_result=True,
)
assert result.context_length is None
assert result.load_attempted is False
assert result.rejected is True