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.
191 lines
5.4 KiB
Python
191 lines
5.4 KiB
Python
"""Tests for the provider module registry and profiles."""
|
|
|
|
from providers import get_provider_profile, _REGISTRY
|
|
from providers.base import ProviderProfile, OMIT_TEMPERATURE
|
|
|
|
|
|
class TestRegistry:
|
|
def test_discovery_populates_registry(self):
|
|
p = get_provider_profile("nvidia")
|
|
assert p is not None
|
|
assert p.name == "nvidia"
|
|
|
|
|
|
|
|
|
|
|
|
class TestNvidiaProfile:
|
|
def test_max_tokens(self):
|
|
p = get_provider_profile("nvidia")
|
|
assert p.default_max_tokens == 16384
|
|
|
|
|
|
def test_base_url(self):
|
|
p = get_provider_profile("nvidia")
|
|
assert "nvidia.com" in p.base_url
|
|
|
|
|
|
|
|
class TestKimiProfile:
|
|
def test_temperature_omit(self):
|
|
p = get_provider_profile("kimi")
|
|
assert p.fixed_temperature is OMIT_TEMPERATURE
|
|
|
|
|
|
|
|
|
|
def test_thinking_enabled(self):
|
|
# xor contract (fix ce4e74b3): an explicit recognized effort sends
|
|
# reasoning_effort ONLY — never paired with extra_body.thinking.
|
|
p = get_provider_profile("kimi")
|
|
eb, tl = p.build_api_kwargs_extras(reasoning_config={"enabled": True, "effort": "high"})
|
|
assert tl["reasoning_effort"] == "high"
|
|
assert "thinking" not in eb
|
|
|
|
|
|
|
|
|
|
|
|
class TestOpenRouterProfile:
|
|
def test_extra_body_with_prefs(self):
|
|
p = get_provider_profile("openrouter")
|
|
body = p.build_extra_body(provider_preferences={"allow": ["anthropic"]})
|
|
assert body["provider"] == {"allow": ["anthropic"]}
|
|
|
|
|
|
|
|
|
|
|
|
def test_pareto_min_coding_score_emitted_for_pareto_model(self):
|
|
"""min_coding_score → plugins block when model is openrouter/pareto-code."""
|
|
p = get_provider_profile("openrouter")
|
|
body = p.build_extra_body(
|
|
model="openrouter/pareto-code",
|
|
openrouter_min_coding_score=0.65,
|
|
)
|
|
assert body["plugins"] == [
|
|
{"id": "pareto-router", "min_coding_score": 0.65}
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_grok_session_id_sets_cache_affinity_header(self):
|
|
"""OpenRouter + Grok model + session_id => x-grok-conv-id header."""
|
|
p = get_provider_profile("openrouter")
|
|
_, tl = p.build_api_kwargs_extras(
|
|
model="x-ai/grok-4",
|
|
session_id="sess-abc123",
|
|
)
|
|
assert tl["extra_headers"]["x-grok-conv-id"] == "sess-abc123"
|
|
|
|
|
|
|
|
|
|
|
|
# --- reasoning-mandatory Anthropic effort → top-level verbosity (#43432) ---
|
|
#
|
|
# These models (Claude 4.6+ / fable / mythos-class) ignore
|
|
# ``reasoning.effort`` and use adaptive thinking. OpenRouter honors the
|
|
# requested effort on the top-level ``verbosity`` field instead (maps to
|
|
# Anthropic ``output_config.effort``). The profile must route the existing
|
|
# ``reasoning_config["effort"]`` there while still NEVER emitting a
|
|
# ``reasoning`` field (which would 400 — see #42991). Gate every fixture on
|
|
# the real predicate so this stays a behavior contract, not a name snapshot.
|
|
|
|
@staticmethod
|
|
def _is_mandatory(model):
|
|
import inspect
|
|
p = get_provider_profile("openrouter")
|
|
mod = inspect.getmodule(type(p))
|
|
return mod._anthropic_reasoning_is_mandatory(model)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_mandatory_anthropic_verbosity_coexists_with_grok_header(self):
|
|
"""A reasoning-mandatory Anthropic model is never a Grok model, but the
|
|
top-level dict must remain a single merged dict — verify the verbosity
|
|
path doesn't clobber the extra_headers slot used by Grok affinity."""
|
|
p = get_provider_profile("openrouter")
|
|
# mandatory anthropic + effort → verbosity, no extra_headers
|
|
_, tl = p.build_api_kwargs_extras(
|
|
reasoning_config={"enabled": True, "effort": "high"},
|
|
supports_reasoning=True,
|
|
model="anthropic/claude-fable-5",
|
|
)
|
|
assert tl == {"verbosity": "high"}
|
|
|
|
|
|
class TestNousProfile:
|
|
def test_tags(self):
|
|
from agent.portal_tags import nous_portal_tags
|
|
p = get_provider_profile("nous")
|
|
body = p.build_extra_body()
|
|
assert body["tags"] == nous_portal_tags()
|
|
|
|
|
|
|
|
|
|
|
|
def test_auth_type(self):
|
|
p = get_provider_profile("nous")
|
|
assert p.auth_type == "oauth_device_code"
|
|
|
|
|
|
|
|
|
|
class TestQwenProfile:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_prepare_messages_protects_nested_image_url_retry_mutation(self):
|
|
qwen = get_provider_profile("qwen-oauth")
|
|
image_url = {"url": "data:image/png;base64,original"}
|
|
msgs = [
|
|
{"role": "system", "content": "Be helpful"},
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": "see image"},
|
|
{"type": "image_url", "image_url": image_url},
|
|
],
|
|
},
|
|
]
|
|
|
|
qwen_result = qwen.prepare_messages(msgs)
|
|
|
|
assert qwen_result[1] is not msgs[1]
|
|
assert qwen_result[1]["content"] is not msgs[1]["content"]
|
|
assert qwen_result[1]["content"][1] is not msgs[1]["content"][1]
|
|
assert qwen_result[1]["content"][1]["image_url"] is not image_url
|
|
|
|
qwen_result[1]["content"][1]["image_url"]["url"] = (
|
|
"data:image/png;base64,shrunk"
|
|
)
|
|
assert msgs[1]["content"][1]["image_url"]["url"] == (
|
|
"data:image/png;base64,original"
|
|
)
|
|
|
|
def test_metadata_top_level(self):
|
|
p = get_provider_profile("qwen-oauth")
|
|
meta = {"sessionId": "s123", "promptId": "p456"}
|
|
eb, tl = p.build_api_kwargs_extras(qwen_session_metadata=meta)
|
|
assert tl["metadata"] == meta
|
|
assert "metadata" not in eb
|
|
|
|
|
|
|
|
|