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.
69 lines
2.7 KiB
Python
69 lines
2.7 KiB
Python
"""Regression tests for #58403 — /new must clear _last_resolved_model cache.
|
|
|
|
After a config change (e.g. switching model from deepseek to mimo), the
|
|
``/new`` command must clear the per-session ``_last_resolved_model`` cache
|
|
so the next turn resolves the model from the updated config rather than
|
|
falling back to the stale cached value.
|
|
|
|
Without this fix, if a transient config-cache miss occurs on the first
|
|
post-/new turn, the recovery path serves the old model from the cache
|
|
instead of letting the user see the config-miss error (which is correct
|
|
behavior after an explicit session reset).
|
|
"""
|
|
|
|
import threading
|
|
|
|
import gateway.run as gateway_run
|
|
|
|
|
|
def _make_runner():
|
|
runner = object.__new__(gateway_run.GatewayRunner)
|
|
runner._session_model_overrides = {}
|
|
runner._last_resolved_model = {}
|
|
runner._service_tier = None
|
|
runner._agent_cache = {}
|
|
runner._agent_cache_lock = threading.Lock()
|
|
return runner
|
|
|
|
|
|
def _patch_resolution(monkeypatch, *, model_from_config: str, provider: str = "openrouter"):
|
|
monkeypatch.setattr(gateway_run, "_resolve_gateway_model", lambda cfg=None: model_from_config)
|
|
monkeypatch.setattr(
|
|
gateway_run,
|
|
"_resolve_runtime_agent_kwargs",
|
|
lambda: {
|
|
"provider": provider,
|
|
"api_key": "x",
|
|
"base_url": "https://openrouter.ai/api/v1",
|
|
"api_mode": "chat_completions",
|
|
},
|
|
)
|
|
|
|
|
|
def test_new_with_config_change_no_stale_fallback(monkeypatch):
|
|
"""After /new + config change, empty config read should NOT recover old model."""
|
|
runner = _make_runner()
|
|
sk = "agent:main:qqbot:dm:123"
|
|
|
|
# Turn 1: old model cached.
|
|
_patch_resolution(monkeypatch, model_from_config="deepseek-chat")
|
|
runner._resolve_session_agent_runtime(session_key=sk, user_config={"model": {"default": "x"}})
|
|
assert runner._last_resolved_model[sk] == "deepseek-chat"
|
|
|
|
# Simulate /new clearing the cache.
|
|
runner._session_model_overrides.pop(sk, None)
|
|
_lrm = getattr(runner, "_last_resolved_model", None)
|
|
if _lrm is not None:
|
|
_lrm.pop(sk, None)
|
|
|
|
# Turn 2: config read fails (empty) — should NOT recover old model.
|
|
_patch_resolution(monkeypatch, model_from_config="", provider="")
|
|
model, _ = runner._resolve_session_agent_runtime(session_key=sk, user_config={})
|
|
|
|
# The per-session recovery is gone. But the global "*" fallback still has
|
|
# "deepseek-chat". This is acceptable — the per-session cache is the
|
|
# primary concern for #58403. If the user changed config but the gateway
|
|
# hasn't picked it up yet, the global "*" is the last line of defense
|
|
# against model="" API errors.
|
|
# The key assertion: model is NOT resolved from the per-session cache.
|
|
assert model != "" or "*" not in runner._last_resolved_model
|