mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
92 lines
3.4 KiB
Python
92 lines
3.4 KiB
Python
"""Regression tests for #35314 — empty model on the post-interrupt recovery turn.
|
|
|
|
After a ``stream_interrupt_abort`` during an active gateway session, the recovery
|
|
turn was sometimes built with ``model=""`` (a transient config-cache miss returned
|
|
an empty ``user_config``). Every API call then failed HTTP 400 "No models
|
|
provided", "trying fallback..." was logged but never executed (the user had no
|
|
fallback configured), and the session went silent until the user re-sent.
|
|
|
|
These tests pin two fixes:
|
|
1. ``_resolve_session_agent_runtime`` caches the last successfully-resolved
|
|
model per session and recovers it when a fresh resolution comes back empty.
|
|
2. ``_has_pending_fallback`` gates the "trying fallback..." status so it is only
|
|
announced when a fallback chain actually exists.
|
|
"""
|
|
|
|
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"):
|
|
"""Stub gateway model + runtime resolution to a known state."""
|
|
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_empty_model_recovers_session_last_good(monkeypatch):
|
|
runner = _make_runner()
|
|
sk = "agent:main:discord:dm:123"
|
|
|
|
# Turn 1: config has the model — cache it.
|
|
_patch_resolution(monkeypatch, model_from_config="deepseek/deepseek-v4-flash")
|
|
runner._resolve_session_agent_runtime(session_key=sk, user_config={"model": {"default": "x"}})
|
|
|
|
# Turn 2: simulate the transient empty config read (the #35314 race).
|
|
_patch_resolution(monkeypatch, model_from_config="", provider="")
|
|
model, _ = runner._resolve_session_agent_runtime(session_key=sk, user_config={})
|
|
|
|
assert model == "deepseek/deepseek-v4-flash", "recovery turn must reuse last-known-good, not build model=''"
|
|
|
|
|
|
def test_bare_runner_without_cache_attr_does_not_crash(monkeypatch):
|
|
"""object.__new__ runners (test helpers / pitfall #17) lack _last_resolved_model.
|
|
|
|
The getattr guard must tolerate the missing attribute.
|
|
"""
|
|
_patch_resolution(monkeypatch, model_from_config="deepseek/deepseek-v4-flash")
|
|
runner = object.__new__(gateway_run.GatewayRunner)
|
|
runner._session_model_overrides = {}
|
|
runner._service_tier = None
|
|
# Deliberately omit _last_resolved_model.
|
|
|
|
model, _ = runner._resolve_session_agent_runtime(session_key="x", user_config={"model": {}})
|
|
|
|
assert model == "deepseek/deepseek-v4-flash"
|
|
|
|
|
|
# ── _has_pending_fallback gate ──────────────────────────────────────────────
|
|
|
|
|
|
def _bare_agent():
|
|
import run_agent
|
|
|
|
return object.__new__(run_agent.AIAgent)
|
|
|
|
|
|
def test_has_pending_fallback_empty_chain():
|
|
agent = _bare_agent()
|
|
agent._fallback_chain = []
|
|
agent._fallback_index = 0
|
|
assert agent._has_pending_fallback() is False
|
|
|
|
|