mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
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.
156 lines
6 KiB
Python
156 lines
6 KiB
Python
"""Tests for the models.dev-preferred merge behavior in provider_model_ids
|
|
and list_authenticated_providers.
|
|
|
|
These guard the contract:
|
|
|
|
* For providers in ``_MODELS_DEV_PREFERRED`` (opencode-go, opencode-zen,
|
|
xiaomi, deepseek, smaller inference providers), both the CLI model
|
|
picker path (``provider_model_ids``) and the gateway ``/model`` picker
|
|
path (``list_authenticated_providers``) merge fresh models.dev entries
|
|
on top of the curated static list.
|
|
* OpenRouter and Nous Portal are NEVER merged — they keep their curated
|
|
(OpenRouter) or live-Portal (Nous) semantics.
|
|
* If models.dev is unreachable (offline / CI), the curated list is the
|
|
fallback — no crash, no empty list.
|
|
|
|
Merging is what lets new models (e.g. ``mimo-v2.5-pro`` on opencode-go)
|
|
appear in ``/model`` without a Hermes release.
|
|
"""
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
from hermes_cli.models import (
|
|
_MODELS_DEV_PREFERRED,
|
|
_PROVIDER_MODELS,
|
|
_merge_with_models_dev,
|
|
provider_model_ids,
|
|
)
|
|
|
|
|
|
class TestMergeHelper:
|
|
def test_merge_empty_mdev_returns_curated(self):
|
|
"""When models.dev returns nothing, curated list is preserved verbatim."""
|
|
with patch("agent.models_dev.list_agentic_models", return_value=[]):
|
|
out = _merge_with_models_dev("opencode-go", ["mimo-v2-pro", "kimi-k2.6"])
|
|
assert out == ["mimo-v2-pro", "kimi-k2.6"]
|
|
|
|
|
|
def test_merge_case_insensitive_dedup(self):
|
|
"""Dedup is case-insensitive but preserves the first occurrence's casing."""
|
|
mdev = ["MiniMax-M2.7"]
|
|
curated = ["minimax-m2.7", "minimax-m2.5"]
|
|
with patch("agent.models_dev.list_agentic_models", return_value=mdev):
|
|
out = _merge_with_models_dev("minimax", curated)
|
|
# models.dev casing wins since it came first
|
|
assert out == ["MiniMax-M2.7", "minimax-m2.5"]
|
|
|
|
|
|
class TestProviderModelIdsPreferred:
|
|
|
|
|
|
|
|
|
|
|
|
def test_k3_live_discovery_is_scoped_to_kimi_coding_endpoint(self):
|
|
"""Coding keys discover K3; legacy Moonshot keys must not advertise it."""
|
|
|
|
class Response:
|
|
def __init__(self, body: bytes):
|
|
self._body = body
|
|
|
|
def read(self):
|
|
return self._body
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *_args):
|
|
return False
|
|
|
|
def fake_open(req, **_kwargs):
|
|
if req.full_url == "https://api.kimi.com/coding/v1/models":
|
|
return Response(b'{"data":[{"id":"k3"}]}')
|
|
if req.full_url == "https://api.moonshot.ai/v1/models":
|
|
return Response(b'{"data":[{"id":"K3"},{"id":"kimi-k2.6"}]}')
|
|
if req.full_url == "https://example.invalid/v1/models":
|
|
return Response(b'{"data":[{"id":"k3"},{"id":"kimi-k2.6"}]}')
|
|
raise AssertionError(f"unexpected Kimi models URL: {req.full_url}")
|
|
|
|
with patch("hermes_cli.urllib_security.open_credentialed_url", side_effect=fake_open):
|
|
with patch(
|
|
"hermes_cli.auth.resolve_api_key_provider_credentials",
|
|
return_value={
|
|
"api_key": "sk-kimi-test",
|
|
"base_url": "https://api.kimi.com/coding",
|
|
},
|
|
):
|
|
coding_models = provider_model_ids("kimi-coding")
|
|
|
|
with patch(
|
|
"hermes_cli.auth.resolve_api_key_provider_credentials",
|
|
return_value={
|
|
"api_key": "legacy-test",
|
|
"base_url": "https://api.moonshot.ai/v1",
|
|
},
|
|
):
|
|
legacy_models = provider_model_ids("kimi-coding")
|
|
|
|
with patch(
|
|
"hermes_cli.auth.resolve_api_key_provider_credentials",
|
|
return_value={
|
|
"api_key": "custom-test",
|
|
"base_url": "https://example.invalid/v1",
|
|
},
|
|
):
|
|
custom_models = provider_model_ids("kimi-coding")
|
|
|
|
# The live bare wire id ``k3`` folds into the curated public slug
|
|
# ``kimi-k3`` (picker alias dedup) — one row, curated slug leads.
|
|
assert coding_models[0] == "kimi-k3"
|
|
assert all(model.lower() != "k3" for model in coding_models)
|
|
assert all(model.lower() != "k3" for model in legacy_models)
|
|
assert all(model.lower() != "k3" for model in custom_models)
|
|
# Legacy / custom endpoints never advertise the k3 family at all
|
|
# via live discovery (their curated floor may still carry kimi-k3).
|
|
|
|
def test_kimi_setup_flow_uses_same_coding_plan_catalog(self):
|
|
"""The setup wizard must not carry a stale duplicate Kimi model list."""
|
|
from hermes_cli.model_setup_flows import _model_flow_kimi
|
|
|
|
captured = {}
|
|
|
|
def fake_select(model_list, **_kwargs):
|
|
captured["models"] = model_list
|
|
return None
|
|
|
|
with (
|
|
patch("hermes_cli.main._prompt_api_key", return_value=("sk-kimi-test", False)),
|
|
patch("hermes_cli.auth._prompt_model_selection", side_effect=fake_select),
|
|
patch("hermes_cli.config.get_env_value", return_value=""),
|
|
patch("hermes_cli.config.save_env_value"),
|
|
):
|
|
_model_flow_kimi({}, current_model="")
|
|
|
|
assert captured["models"] == _PROVIDER_MODELS["kimi-coding"]
|
|
assert captured["models"][0] == "kimi-k3"
|
|
|
|
|
|
class TestOpenRouterAndNousUnchanged:
|
|
"""Per Teknium: openrouter and nous are NEVER merged with models.dev."""
|
|
|
|
|
|
def test_openrouter_does_not_call_merge(self):
|
|
"""openrouter takes its own live path — merge helper must NOT run."""
|
|
with patch(
|
|
"hermes_cli.models._merge_with_models_dev",
|
|
side_effect=AssertionError("merge should not be called for openrouter"),
|
|
):
|
|
# Even if model_ids() fails for some other reason, we just care
|
|
# that the merge path isn't invoked.
|
|
try:
|
|
provider_model_ids("openrouter")
|
|
except AssertionError:
|
|
raise
|
|
except Exception:
|
|
pass # model_ids() may fail in the hermetic test env — that's fine.
|