wehub-resource-sync
236 lines
8.1 KiB
Python
236 lines
8.1 KiB
Python
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
from free_claude_code.application.errors import UnknownProviderError
|
|
from free_claude_code.application.routing import ModelRouter
|
|
from free_claude_code.config.provider_catalog import PROVIDER_CATALOG
|
|
from free_claude_code.config.settings import Settings
|
|
from free_claude_code.core.anthropic.models import (
|
|
Message,
|
|
MessagesRequest,
|
|
TokenCountRequest,
|
|
)
|
|
|
|
|
|
@pytest.fixture
|
|
def settings():
|
|
settings = Settings()
|
|
settings.model = "nvidia_nim/fallback-model"
|
|
settings.model_opus = None
|
|
settings.model_sonnet = None
|
|
settings.model_haiku = None
|
|
settings.enable_model_thinking = True
|
|
settings.enable_opus_thinking = None
|
|
settings.enable_sonnet_thinking = None
|
|
settings.enable_haiku_thinking = None
|
|
return settings
|
|
|
|
|
|
def test_model_router_resolves_default_model(settings):
|
|
resolved = ModelRouter(settings).resolve("claude-3-opus")
|
|
|
|
assert resolved.original_model == "claude-3-opus"
|
|
assert resolved.provider_id == "nvidia_nim"
|
|
assert resolved.provider_model == "fallback-model"
|
|
assert resolved.provider_model_ref == "nvidia_nim/fallback-model"
|
|
assert resolved.thinking_enabled is True
|
|
|
|
|
|
def test_model_router_applies_opus_override(settings):
|
|
settings.model_opus = "open_router/deepseek/deepseek-r1"
|
|
|
|
request = MessagesRequest(
|
|
model="claude-opus-4-20250514",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
routed = ModelRouter(settings).resolve_messages_request(request)
|
|
|
|
assert routed.request.model == "deepseek/deepseek-r1"
|
|
assert routed.resolved.provider_model_ref == "open_router/deepseek/deepseek-r1"
|
|
assert routed.resolved.original_model == "claude-opus-4-20250514"
|
|
assert routed.resolved.thinking_enabled is True
|
|
assert request.model == "claude-opus-4-20250514"
|
|
|
|
|
|
def test_model_router_resolves_per_model_thinking(settings):
|
|
settings.enable_model_thinking = False
|
|
settings.enable_opus_thinking = True
|
|
settings.enable_haiku_thinking = False
|
|
|
|
router = ModelRouter(settings)
|
|
|
|
assert router.resolve("claude-opus-4-20250514").thinking_enabled is True
|
|
assert router.resolve("claude-sonnet-4-20250514").thinking_enabled is False
|
|
assert router.resolve("claude-3-haiku-20240307").thinking_enabled is False
|
|
assert router.resolve("claude-2.1").thinking_enabled is False
|
|
|
|
|
|
def test_model_router_applies_haiku_override(settings):
|
|
settings.model_haiku = "lmstudio/qwen2.5-7b"
|
|
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="claude-3-haiku-20240307",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "qwen2.5-7b"
|
|
assert routed.resolved.provider_model_ref == "lmstudio/qwen2.5-7b"
|
|
|
|
|
|
def test_model_router_applies_sonnet_override(settings):
|
|
settings.model_sonnet = "nvidia_nim/meta/llama-3.3-70b-instruct"
|
|
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="claude-sonnet-4-20250514",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "meta/llama-3.3-70b-instruct"
|
|
assert (
|
|
routed.resolved.provider_model_ref == "nvidia_nim/meta/llama-3.3-70b-instruct"
|
|
)
|
|
|
|
|
|
def test_model_router_routes_prefixed_provider_model_directly(settings):
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="deepseek/deepseek-chat",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "deepseek-chat"
|
|
assert routed.resolved.original_model == "deepseek/deepseek-chat"
|
|
assert routed.resolved.provider_id == "deepseek"
|
|
assert routed.resolved.provider_model == "deepseek-chat"
|
|
assert routed.resolved.provider_model_ref == "deepseek/deepseek-chat"
|
|
|
|
|
|
def test_model_router_routes_wafer_provider_model_directly(settings):
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="wafer/DeepSeek-V4-Pro",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "DeepSeek-V4-Pro"
|
|
assert routed.resolved.provider_id == "wafer"
|
|
assert routed.resolved.provider_model == "DeepSeek-V4-Pro"
|
|
assert routed.resolved.provider_model_ref == "wafer/DeepSeek-V4-Pro"
|
|
|
|
|
|
def test_model_router_routes_minimax_provider_model_directly(settings):
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="minimax/MiniMax-M3",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "MiniMax-M3"
|
|
assert routed.resolved.provider_id == "minimax"
|
|
assert routed.resolved.provider_model == "MiniMax-M3"
|
|
assert routed.resolved.provider_model_ref == "minimax/MiniMax-M3"
|
|
|
|
|
|
def test_model_router_routes_gateway_encoded_provider_model_directly(settings):
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="anthropic/nvidia_nim/deepseek-ai/deepseek-v4-pro",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "deepseek-ai/deepseek-v4-pro"
|
|
assert (
|
|
routed.resolved.original_model
|
|
== "anthropic/nvidia_nim/deepseek-ai/deepseek-v4-pro"
|
|
)
|
|
assert routed.resolved.provider_id == "nvidia_nim"
|
|
assert routed.resolved.provider_model == "deepseek-ai/deepseek-v4-pro"
|
|
assert (
|
|
routed.resolved.provider_model_ref
|
|
== "anthropic/nvidia_nim/deepseek-ai/deepseek-v4-pro"
|
|
)
|
|
|
|
|
|
def test_model_router_routes_no_thinking_gateway_model_directly(settings):
|
|
settings.enable_model_thinking = True
|
|
|
|
routed = ModelRouter(settings).resolve_messages_request(
|
|
MessagesRequest(
|
|
model="claude-3-freecc-no-thinking/nvidia_nim/deepseek-ai/deepseek-v4-pro",
|
|
max_tokens=100,
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
)
|
|
|
|
assert routed.request.model == "deepseek-ai/deepseek-v4-pro"
|
|
assert (
|
|
routed.resolved.original_model
|
|
== "claude-3-freecc-no-thinking/nvidia_nim/deepseek-ai/deepseek-v4-pro"
|
|
)
|
|
assert routed.resolved.provider_id == "nvidia_nim"
|
|
assert routed.resolved.provider_model == "deepseek-ai/deepseek-v4-pro"
|
|
assert routed.resolved.thinking_enabled is False
|
|
|
|
|
|
def test_model_router_direct_prefixed_model_uses_provider_model_for_thinking(settings):
|
|
settings.enable_model_thinking = False
|
|
settings.enable_opus_thinking = True
|
|
|
|
resolved = ModelRouter(settings).resolve("open_router/anthropic/claude-opus-4")
|
|
|
|
assert resolved.provider_id == "open_router"
|
|
assert resolved.provider_model == "anthropic/claude-opus-4"
|
|
assert resolved.thinking_enabled is True
|
|
|
|
|
|
def test_model_router_routes_token_count_request(settings):
|
|
settings.model_haiku = "lmstudio/qwen2.5-7b"
|
|
|
|
request = TokenCountRequest(
|
|
model="claude-3-haiku-20240307",
|
|
messages=[Message(role="user", content="hello")],
|
|
)
|
|
routed = ModelRouter(settings).resolve_token_count_request(request)
|
|
|
|
assert routed.request.model == "qwen2.5-7b"
|
|
assert request.model == "claude-3-haiku-20240307"
|
|
|
|
|
|
def test_model_router_logs_mapping(settings):
|
|
with patch("free_claude_code.application.routing.logger.debug") as mock_log:
|
|
ModelRouter(settings).resolve("claude-2.1")
|
|
|
|
mock_log.assert_called()
|
|
args = mock_log.call_args[0]
|
|
assert "MODEL MAPPING" in args[0]
|
|
assert args[1] == "claude-2.1"
|
|
assert args[2] == "fallback-model"
|
|
|
|
|
|
def test_model_router_preserves_typed_error_for_unknown_mapped_provider(settings):
|
|
settings.model = "unknown/model"
|
|
|
|
with pytest.raises(UnknownProviderError) as exc_info:
|
|
ModelRouter(settings).resolve("claude-2.1")
|
|
|
|
supported = "', '".join(PROVIDER_CATALOG)
|
|
assert str(exc_info.value) == (
|
|
f"Unknown provider_type: 'unknown'. Supported: '{supported}'"
|
|
)
|