mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-13 03:52:00 +00:00
feat: provider modules — ProviderProfile ABC, 33 providers, fetch_models, transport single-path
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
This commit is contained in:
kshitijk4poor
Teknium
parent
2b500ed68a
commit
20a4f79ed1
57 changed files with 3149 additions and 177 deletions
|
|
@ -71,17 +71,17 @@ class TestMinimaxThinkingSupport:
|
|||
|
||||
|
||||
class TestMinimaxAuxModel:
|
||||
"""Verify auxiliary model is standard (not highspeed)."""
|
||||
"""Verify auxiliary model is standard (not highspeed) — now reads from profiles."""
|
||||
|
||||
def test_minimax_aux_is_standard(self):
|
||||
from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
|
||||
assert _API_KEY_PROVIDER_AUX_MODELS["minimax"] == "MiniMax-M2.7"
|
||||
assert _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"] == "MiniMax-M2.7"
|
||||
from agent.auxiliary_client import _get_aux_model_for_provider
|
||||
assert _get_aux_model_for_provider("minimax") == "MiniMax-M2.7"
|
||||
assert _get_aux_model_for_provider("minimax-cn") == "MiniMax-M2.7"
|
||||
|
||||
def test_minimax_aux_not_highspeed(self):
|
||||
from agent.auxiliary_client import _API_KEY_PROVIDER_AUX_MODELS
|
||||
assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax"]
|
||||
assert "highspeed" not in _API_KEY_PROVIDER_AUX_MODELS["minimax-cn"]
|
||||
from agent.auxiliary_client import _get_aux_model_for_provider
|
||||
assert "highspeed" not in _get_aux_model_for_provider("minimax")
|
||||
assert "highspeed" not in _get_aux_model_for_provider("minimax-cn")
|
||||
|
||||
|
||||
class TestMinimaxBetaHeaders:
|
||||
|
|
|
|||
|
|
@ -73,17 +73,21 @@ class TestChatCompletionsBuildKwargs:
|
|||
assert kw["tools"] == tools
|
||||
|
||||
def test_openrouter_provider_prefs(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("openrouter")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="gpt-4o", messages=msgs,
|
||||
is_openrouter=True,
|
||||
provider_profile=profile,
|
||||
provider_preferences={"only": ["openai"]},
|
||||
)
|
||||
assert kw["extra_body"]["provider"] == {"only": ["openai"]}
|
||||
|
||||
def test_nous_tags(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("nous")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(model="gpt-4o", messages=msgs, is_nous=True)
|
||||
kw = transport.build_kwargs(model="gpt-4o", messages=msgs, provider_profile=profile)
|
||||
assert kw["extra_body"]["tags"] == ["product=hermes-agent"]
|
||||
|
||||
def test_reasoning_default(self, transport):
|
||||
|
|
@ -95,29 +99,36 @@ class TestChatCompletionsBuildKwargs:
|
|||
assert kw["extra_body"]["reasoning"] == {"enabled": True, "effort": "medium"}
|
||||
|
||||
def test_nous_omits_disabled_reasoning(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("nous")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="gpt-4o", messages=msgs,
|
||||
provider_profile=profile,
|
||||
supports_reasoning=True,
|
||||
is_nous=True,
|
||||
reasoning_config={"enabled": False},
|
||||
)
|
||||
# Nous rejects enabled=false; reasoning omitted entirely
|
||||
assert "reasoning" not in kw.get("extra_body", {})
|
||||
|
||||
def test_ollama_num_ctx(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("custom")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="llama3", messages=msgs,
|
||||
provider_profile=profile,
|
||||
ollama_num_ctx=32768,
|
||||
)
|
||||
assert kw["extra_body"]["options"]["num_ctx"] == 32768
|
||||
|
||||
def test_custom_think_false(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("custom")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="qwen3", messages=msgs,
|
||||
is_custom_provider=True,
|
||||
provider_profile=profile,
|
||||
reasoning_config={"effort": "none"},
|
||||
)
|
||||
assert kw["extra_body"]["think"] is False
|
||||
|
|
@ -304,23 +315,29 @@ class TestChatCompletionsBuildKwargs:
|
|||
assert kw["max_tokens"] == 2048
|
||||
|
||||
def test_nvidia_default_max_tokens(self, transport):
|
||||
"""NVIDIA max_tokens=16384 is now set via ProviderProfile, not legacy flag."""
|
||||
from providers import get_provider_profile
|
||||
|
||||
profile = get_provider_profile("nvidia")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="glm-4.7", messages=msgs,
|
||||
is_nvidia_nim=True,
|
||||
model="nvidia/llama-3.1-405b-instruct",
|
||||
messages=msgs,
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
provider_profile=profile,
|
||||
)
|
||||
# NVIDIA default: 16384
|
||||
assert kw["max_tokens"] == 16384
|
||||
|
||||
def test_qwen_default_max_tokens(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("qwen-oauth")
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(
|
||||
model="qwen3-coder-plus", messages=msgs,
|
||||
is_qwen_portal=True,
|
||||
provider_profile=profile,
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
)
|
||||
# Qwen default: 65536
|
||||
# Qwen default: 65536 from profile.default_max_tokens
|
||||
assert kw["max_tokens"] == 65536
|
||||
|
||||
def test_anthropic_max_output_for_claude_on_aggregator(self, transport):
|
||||
|
|
@ -343,14 +360,23 @@ class TestChatCompletionsBuildKwargs:
|
|||
assert kw["service_tier"] == "priority"
|
||||
|
||||
def test_fixed_temperature(self, transport):
|
||||
"""Fixed temperature is now set via ProviderProfile.fixed_temperature."""
|
||||
from providers.base import ProviderProfile
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(model="gpt-4o", messages=msgs, fixed_temperature=0.6)
|
||||
kw = transport.build_kwargs(
|
||||
model="gpt-4o", messages=msgs,
|
||||
provider_profile=ProviderProfile(name="_t", fixed_temperature=0.6),
|
||||
)
|
||||
assert kw["temperature"] == 0.6
|
||||
|
||||
def test_omit_temperature(self, transport):
|
||||
"""Omit temperature is set via ProviderProfile with OMIT_TEMPERATURE sentinel."""
|
||||
from providers.base import ProviderProfile, OMIT_TEMPERATURE
|
||||
msgs = [{"role": "user", "content": "Hi"}]
|
||||
kw = transport.build_kwargs(model="gpt-4o", messages=msgs, omit_temperature=True, fixed_temperature=0.5)
|
||||
# omit wins
|
||||
kw = transport.build_kwargs(
|
||||
model="gpt-4o", messages=msgs,
|
||||
provider_profile=ProviderProfile(name="_t", fixed_temperature=OMIT_TEMPERATURE),
|
||||
)
|
||||
assert "temperature" not in kw
|
||||
|
||||
|
||||
|
|
@ -358,18 +384,22 @@ class TestChatCompletionsKimi:
|
|||
"""Regression tests for the Kimi/Moonshot quirks migrated into the transport."""
|
||||
|
||||
def test_kimi_max_tokens_default(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("kimi-coding")
|
||||
kw = transport.build_kwargs(
|
||||
model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
|
||||
is_kimi=True,
|
||||
provider_profile=profile,
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
)
|
||||
# Kimi CLI default: 32000
|
||||
# Kimi CLI default: 32000 from KimiProfile.default_max_tokens
|
||||
assert kw["max_tokens"] == 32000
|
||||
|
||||
def test_kimi_reasoning_effort_top_level(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("kimi-coding")
|
||||
kw = transport.build_kwargs(
|
||||
model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
|
||||
is_kimi=True,
|
||||
provider_profile=profile,
|
||||
reasoning_config={"effort": "high"},
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
)
|
||||
|
|
@ -387,17 +417,21 @@ class TestChatCompletionsKimi:
|
|||
assert "reasoning_effort" not in kw
|
||||
|
||||
def test_kimi_thinking_enabled_extra_body(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("kimi-coding")
|
||||
kw = transport.build_kwargs(
|
||||
model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
|
||||
is_kimi=True,
|
||||
provider_profile=profile,
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
)
|
||||
assert kw["extra_body"]["thinking"] == {"type": "enabled"}
|
||||
|
||||
def test_kimi_thinking_disabled_extra_body(self, transport):
|
||||
from providers import get_provider_profile
|
||||
profile = get_provider_profile("kimi-coding")
|
||||
kw = transport.build_kwargs(
|
||||
model="kimi-k2", messages=[{"role": "user", "content": "Hi"}],
|
||||
is_kimi=True,
|
||||
provider_profile=profile,
|
||||
reasoning_config={"enabled": False},
|
||||
max_tokens_param_fn=lambda n: {"max_tokens": n},
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue