deerflow-code/offline-backend-20260512/backend/app/gateway/routers/models.py

from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel, Field

from app.gateway.deps import get_config
from deerflow.config.app_config import AppConfig
from deerflow.config.model_config import ModelConfig

router = APIRouter(prefix="/api", tags=["models"])

_PROVIDER_KEYWORDS: list[tuple[str, str]] = [
    ("langchain_openai", "openai"),
    ("langchain_anthropic", "anthropic"),
    ("langchain_google", "google"),
    ("langchain_groq", "groq"),
    ("langchain_mistralai", "mistral"),
    ("langchain_cohere", "cohere"),
    ("ollama", "ollama"),
    ("vllm", "vllm"),
]

_LOCAL_PROVIDERS = {"ollama", "vllm"}


def _derive_provider(use: str) -> str | None:
    use_lower = use.lower()
    for keyword, provider in _PROVIDER_KEYWORDS:
        if keyword in use_lower:
            return provider
    return None


def _build_model_response(model: ModelConfig) -> "ModelResponse":
    extra = model.model_extra or {}
    provider = str(extra["provider"]) if "provider" in extra else _derive_provider(model.use)
    is_local = bool(extra["is_local"]) if "is_local" in extra else (provider in _LOCAL_PROVIDERS)
    supports_tool_calling = bool(extra["supports_tool_calling"]) if "supports_tool_calling" in extra else True
    return ModelResponse(
        name=model.name,
        model=model.model,
        display_name=model.display_name,
        description=model.description,
        supports_thinking=model.supports_thinking,
        supports_reasoning_effort=model.supports_reasoning_effort,
        supports_vision=model.supports_vision,
        supports_tool_calling=supports_tool_calling,
        is_local=is_local,
        provider=provider,
    )


class ModelResponse(BaseModel):
    """Response model for model information."""

    name: str = Field(..., description="Unique identifier for the model")
    model: str = Field(..., description="Actual provider model identifier")
    display_name: str | None = Field(None, description="Human-readable name")
    description: str | None = Field(None, description="Model description")
    supports_thinking: bool = Field(default=False, description="Whether model supports thinking mode")
    supports_reasoning_effort: bool = Field(default=False, description="Whether model supports reasoning effort")
    supports_vision: bool = Field(default=False, description="Whether model supports image inputs")
    supports_tool_calling: bool = Field(default=True, description="Whether model supports tool/function calling")
    is_local: bool = Field(default=False, description="Whether this is a locally-hosted model")
    provider: str | None = Field(None, description="Model provider name (openai, anthropic, ollama, etc.)")


class TokenUsageResponse(BaseModel):
    """Token usage display configuration."""

    enabled: bool = Field(default=False, description="Whether token usage display is enabled")


class ModelsListResponse(BaseModel):
    """Response model for listing all models."""

    models: list[ModelResponse]
    token_usage: TokenUsageResponse


@router.get(
    "/models",
    response_model=ModelsListResponse,
    summary="List All Models",
    description="Retrieve a list of all available AI models configured in the system.",
)
async def list_models(config: AppConfig = Depends(get_config)) -> ModelsListResponse:
    """List all available models from configuration.

    Returns model information suitable for frontend display,
    excluding sensitive fields like API keys and internal configuration.

    Returns:
        A list of all configured models with their metadata and token usage display settings.

    Example Response:
        ```json
        {
            "models": [
                {
                    "name": "gpt-4",
                    "model": "gpt-4",
                    "display_name": "GPT-4",
                    "description": "OpenAI GPT-4 model",
                    "supports_thinking": false,
                    "supports_reasoning_effort": false
                },
                {
                    "name": "claude-3-opus",
                    "model": "claude-3-opus",
                    "display_name": "Claude 3 Opus",
                    "description": "Anthropic Claude 3 Opus model",
                    "supports_thinking": true,
                    "supports_reasoning_effort": false
                }
            ],
            "token_usage": {
                "enabled": true
            }
        }
        ```
    """
    models = [_build_model_response(model) for model in config.models]
    return ModelsListResponse(
        models=models,
        token_usage=TokenUsageResponse(enabled=config.token_usage.enabled),
    )


@router.get(
    "/models/{model_name}",
    response_model=ModelResponse,
    summary="Get Model Details",
    description="Retrieve detailed information about a specific AI model by its name.",
)
async def get_model(model_name: str, config: AppConfig = Depends(get_config)) -> ModelResponse:
    """Get a specific model by name.

    Args:
        model_name: The unique name of the model to retrieve.

    Returns:
        Model information if found.

    Raises:
        HTTPException: 404 if model not found.

    Example Response:
        ```json
        {
            "name": "gpt-4",
            "display_name": "GPT-4",
            "description": "OpenAI GPT-4 model",
            "supports_thinking": false
        }
        ```
    """
    model = config.get_model_config(model_name)
    if model is None:
        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")

    return _build_model_response(model)