mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
20a4f79ed1
Introduces providers/ package — single source of truth for every inference provider. Adding a simple api-key provider now requires one providers/<name>.py file with zero edits anywhere else. What this PR ships: - providers/ package (ProviderProfile ABC + 33 profiles across 4 api_modes) - ProviderProfile declarative fields: name, api_mode, aliases, display_name, env_vars, base_url, models_url, auth_type, fallback_models, hostname, default_headers, fixed_temperature, default_max_tokens, default_aux_model - 4 overridable hooks: prepare_messages, build_extra_body, build_api_kwargs_extras, fetch_models - chat_completions.build_kwargs: profile path via _build_kwargs_from_profile, legacy flag path retained for lmstudio/tencent-tokenhub (which have session-aware reasoning probing that doesn't map cleanly to hooks yet) - run_agent.py: profile path for all registered providers; legacy path variable scoping fixed (all flags defined before branching) - Auto-wires: auth.PROVIDER_REGISTRY, models.CANONICAL_PROVIDERS, doctor health checks, config.OPTIONAL_ENV_VARS, model_metadata._URL_TO_PROVIDER - GeminiProfile: thinking_config translation (native + openai-compat nested) - New tests/providers/ (79 tests covering profile declarations, transport parity, hook overrides, e2e kwargs assembly) Deltas vs original PR (salvaged onto current main): - Added profiles: alibaba-coding-plan, azure-foundry, minimax-oauth (were added to main since original PR) - Skipped profiles: lmstudio, tencent-tokenhub stay on legacy path (their reasoning_effort probing has no clean hook equivalent yet) - Removed lmstudio alias from custom profile (it's a separate provider now) - Skipped openrouter/custom from PROVIDER_REGISTRY auto-extension (resolve_provider special-cases them; adding breaks runtime resolution) - runtime_provider: profile.api_mode only as fallback when URL detection finds nothing (was breaking minimax /v1 override) - Preserved main's legacy-path improvements: deepseek reasoning_content preserve, gemini Gemma skip, OpenRouter response caching, Anthropic 1M beta recovery, etc. - Kept agent/copilot_acp_client.py in place (rejected PR's relocation — main has 7 fixes landed since; relocation would revert them) - _API_KEY_PROVIDER_AUX_MODELS alias kept for backward compat with existing test imports Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> Closes #14418
258 lines
9.1 KiB
Python
258 lines
9.1 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
|
|
from providers import get_provider_profile
|
|
|
|
|
|
@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):
|
|
"""NVIDIA default max_tokens=16384 comes from profile, not legacy is_nvidia_nim flag."""
|
|
from providers import get_provider_profile
|
|
|
|
profile = get_provider_profile("nvidia")
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
provider_profile=profile,
|
|
)
|
|
assert kw["max_completion_tokens"] == 16384
|
|
|
|
def test_user_max_tokens_overrides(self, transport):
|
|
from providers import get_provider_profile
|
|
|
|
profile = get_provider_profile("nvidia")
|
|
kw = transport.build_kwargs(
|
|
model="nvidia/llama-3.1-nemotron-70b-instruct",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
max_tokens=4096,
|
|
max_tokens_param_fn=_max_tokens_fn,
|
|
provider_profile=profile,
|
|
)
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("kimi-coding"),
|
|
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,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
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,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
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,
|
|
provider_profile=get_provider_profile("openrouter"),
|
|
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,
|
|
provider_profile=get_provider_profile("nous"),
|
|
)
|
|
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,
|
|
provider_profile=get_provider_profile("nous"),
|
|
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,
|
|
provider_profile=get_provider_profile("nous"),
|
|
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,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
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,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
)
|
|
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,
|
|
provider_profile=get_provider_profile("qwen-oauth"),
|
|
qwen_session_metadata=meta,
|
|
)
|
|
assert kw["metadata"] == meta
|
|
assert "metadata" not in kw.get("extra_body", {})
|
|
|
|
|
|
class TestCustomOllamaParity:
|
|
"""Custom/Ollama: num_ctx, think=false — now tested via profile."""
|
|
|
|
def test_ollama_num_ctx(self, transport):
|
|
kw = transport.build_kwargs(
|
|
model="llama3.1",
|
|
messages=_simple_messages(),
|
|
tools=None,
|
|
provider_profile=get_provider_profile("custom"),
|
|
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,
|
|
provider_profile=get_provider_profile("custom"),
|
|
reasoning_config={"enabled": False, "effort": "none"},
|
|
)
|
|
assert kw["extra_body"]["think"] is False
|