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.
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
"""E2E tests: verify _build_kwargs_from_profile produces correct output.
|
|
|
|
These tests call _build_kwargs_from_profile on the transport directly,
|
|
without importing run_agent (which would cause xdist worker contamination).
|
|
"""
|
|
|
|
import pytest
|
|
from agent.transports.chat_completions import ChatCompletionsTransport
|
|
from providers import get_provider_profile
|
|
|
|
|
|
@pytest.fixture
|
|
def transport():
|
|
return ChatCompletionsTransport()
|
|
|
|
|
|
def _msgs():
|
|
return [{"role": "user", "content": "hi"}]
|
|
|
|
|
|
class TestNvidiaProfileWiring:
|
|
|
|
|
|
def test_nvidia_model_passed(self, transport):
|
|
profile = get_provider_profile("nvidia")
|
|
kwargs = transport.build_kwargs(
|
|
model="nvidia/test-model",
|
|
messages=_msgs(),
|
|
tools=None,
|
|
provider_profile=profile,
|
|
max_tokens=None,
|
|
max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
|
|
timeout=300,
|
|
reasoning_config=None,
|
|
request_overrides=None,
|
|
session_id="test",
|
|
ollama_num_ctx=None,
|
|
)
|
|
assert kwargs["model"] == "nvidia/test-model"
|
|
|
|
|
|
|
|
class TestDeepSeekProfileWiring:
|
|
def test_deepseek_no_forced_max_tokens(self, transport):
|
|
profile = get_provider_profile("deepseek")
|
|
kwargs = transport.build_kwargs(
|
|
model="deepseek-chat",
|
|
messages=_msgs(),
|
|
tools=None,
|
|
provider_profile=profile,
|
|
max_tokens=None,
|
|
max_tokens_param_fn=lambda x: {"max_tokens": x} if x else {},
|
|
timeout=300,
|
|
reasoning_config=None,
|
|
request_overrides=None,
|
|
session_id="test",
|
|
ollama_num_ctx=None,
|
|
)
|
|
# DeepSeek has no default_max_tokens
|
|
assert kwargs["model"] == "deepseek-chat"
|
|
assert kwargs.get("max_tokens") is None or "max_tokens" not in kwargs
|
|
|