mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
b61e6c6145
Cycle 2 PR 1 (#14418). Introduces providers/ package with ProviderProfile ABC and auto-discovery registry, then wires ChatCompletionsTransport to delegate to profiles via a clean single-path method. Provider profiles (8 providers): - nvidia: default_max_tokens=16384 - kimi + kimi-cn: OMIT_TEMPERATURE, thinking + top-level reasoning_effort - openrouter: provider_preferences, full reasoning_config passthrough - nous: product tags, reasoning with Nous-specific disabled omission - deepseek: base_url + env_vars - qwen-oauth: vl_high_resolution extra_body, metadata top-level api_kwargs Transport integration: - _build_kwargs_from_profile() replaces the entire legacy flag-based assembly when provider_profile param is passed - Single path: no dual-execution, no overwrites, no legacy fallthrough - build_api_kwargs_extras() returns (extra_body, top_level) tuple to handle Kimi's top-level reasoning_effort vs OpenRouter's extra_body Auth types: api_key | oauth_device_code | oauth_external | copilot | aws (expanded from the lossy 'oauth' to match real Hermes auth modes). 64 new tests: - 30 profile unit tests (registry, all 8 profiles, auth types) - 19 transport parity tests (pin legacy flag-based behavior) - 15 profile wiring tests (verify profile path = legacy path)
250 lines
8.2 KiB
Python
250 lines
8.2 KiB
Python
"""Parity tests: pin the exact current transport behavior per provider.
|
|
|
|
These tests document the flag-based contract between run_agent.py and
|
|
ChatCompletionsTransport.build_kwargs(). When the next PR wires profiles
|
|
to replace flags, every assertion here must still pass — any failure is
|
|
a behavioral regression.
|
|
"""
|
|
|
|
import pytest
|
|
from agent.transports.chat_completions import ChatCompletionsTransport
|
|
|
|
|
|
@pytest.fixture
|
|
def transport():
|
|
return ChatCompletionsTransport()
|
|
|
|
|
|
def _simple_messages():
|
|
return [{"role": "user", "content": "hello"}]
|
|
|
|
|
|
def _max_tokens_fn(n):
|
|
return {"max_completion_tokens": n}
|
|
|
|
|
|
class TestNvidiaParity:
|
|
"""NVIDIA NIM: default max_tokens=16384."""
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_nvidia_nim=True,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 16384
|
|
|
|
def test_user_max_tokens_overrides(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_nvidia_nim=True,
|
|
max_tokens=4096,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 4096 # user overrides default
|
|
|
|
|
|
class TestKimiParity:
|
|
"""Kimi: OMIT temperature, max_tokens=32000, thinking + reasoning_effort."""
|
|
|
|
def test_temperature_omitted(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
omit_temperature=True,
|
|
)
|
|
assert "temperature" not in kw
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 32000
|
|
|
|
def test_thinking_enabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
reasoning_config={"enabled": True, "effort": "high"},
|
|
)
|
|
assert kw["extra_body"]["thinking"] == {"type": "enabled"}
|
|
|
|
def test_thinking_disabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
reasoning_config={"enabled": False},
|
|
)
|
|
assert kw["extra_body"]["thinking"] == {"type": "disabled"}
|
|
|
|
def test_reasoning_effort_top_level(self, transport):
|
|
"""Kimi reasoning_effort is a TOP-LEVEL api_kwargs key, NOT in extra_body."""
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
reasoning_config={"enabled": True, "effort": "high"},
|
|
)
|
|
assert kw.get("reasoning_effort") == "high"
|
|
assert "reasoning_effort" not in kw.get("extra_body", {})
|
|
|
|
def test_reasoning_effort_default_medium(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="kimi-k2",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_kimi=True,
|
|
reasoning_config={"enabled": True},
|
|
)
|
|
assert kw.get("reasoning_effort") == "medium"
|
|
|
|
|
|
class TestOpenRouterParity:
|
|
"""OpenRouter: provider preferences, reasoning in extra_body."""
|
|
|
|
def test_provider_preferences(self, transport):
|
|
prefs = {"allow": ["anthropic"], "sort": "price"}
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_openrouter=True,
|
|
provider_preferences=prefs,
|
|
)
|
|
assert kw["extra_body"]["provider"] == prefs
|
|
|
|
def test_reasoning_passes_full_config(self, transport):
|
|
"""OpenRouter passes the FULL reasoning_config dict, not just effort."""
|
|
rc = {"enabled": True, "effort": "high"}
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_openrouter=True,
|
|
supports_reasoning=True,
|
|
reasoning_config=rc,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == rc
|
|
|
|
def test_default_reasoning_when_no_config(self, transport):
|
|
"""When supports_reasoning=True but no config, adds default."""
|
|
kw = transport.build_kwargs(
|
|
model="anthropic/claude-sonnet-4.6",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_openrouter=True,
|
|
supports_reasoning=True,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == {"enabled": True, "effort": "medium"}
|
|
|
|
|
|
class TestNousParity:
|
|
"""Nous: product tags, reasoning, omit when disabled."""
|
|
|
|
def test_tags(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_nous=True,
|
|
)
|
|
assert kw["extra_body"]["tags"] == ["product=hermes-agent"]
|
|
|
|
def test_reasoning_omitted_when_disabled(self, transport):
|
|
"""Nous special case: reasoning omitted entirely when disabled."""
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_nous=True,
|
|
supports_reasoning=True,
|
|
reasoning_config={"enabled": False},
|
|
)
|
|
assert "reasoning" not in kw.get("extra_body", {})
|
|
|
|
def test_reasoning_enabled(self, transport):
|
|
rc = {"enabled": True, "effort": "high"}
|
|
kw = transport.build_kwargs(
|
|
model="hermes-3-llama-3.1-405b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_nous=True,
|
|
supports_reasoning=True,
|
|
reasoning_config=rc,
|
|
)
|
|
assert kw["extra_body"]["reasoning"] == rc
|
|
|
|
|
|
class TestQwenParity:
|
|
"""Qwen: max_tokens=65536, vl_high_resolution, metadata top-level."""
|
|
|
|
def test_default_max_tokens(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_qwen_portal=True,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
)
|
|
assert kw["max_completion_tokens"] == 65536
|
|
|
|
def test_vl_high_resolution(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_qwen_portal=True,
|
|
)
|
|
assert kw["extra_body"]["vl_high_resolution_images"] is True
|
|
|
|
def test_metadata_top_level(self, transport):
|
|
"""Qwen metadata goes to top-level api_kwargs, NOT extra_body."""
|
|
meta = {"sessionId": "s123", "promptId": "p456"}
|
|
kw = transport.build_kwargs(
|
|
model="qwen3.5-plus",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_qwen_portal=True,
|
|
qwen_session_metadata=meta,
|
|
)
|
|
assert kw["metadata"] == meta
|
|
assert "metadata" not in kw.get("extra_body", {})
|
|
|
|
|
|
class TestCustomOllamaParity:
|
|
"""Custom/Ollama: num_ctx, think=false."""
|
|
|
|
def test_ollama_num_ctx(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="llama3.1",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_custom_provider=True,
|
|
ollama_num_ctx=131072,
|
|
)
|
|
assert kw["extra_body"]["options"]["num_ctx"] == 131072
|
|
|
|
def test_think_false_when_disabled(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="qwen3:72b",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
is_custom_provider=True,
|
|
reasoning_config={"enabled": False, "effort": "none"},
|
|
)
|
|
assert kw["extra_body"]["think"] is False
|