ai-video-fullstack/backend/services/realtime/launcher.py

"""Resolve and validate an assistant before creating a media connection."""

from __future__ import annotations

from typing import Any

from db.session import SessionLocal
from models import AssistantConfig
from services.config_resolver import resolve_runtime_config
from services.node_specs import graph_references
from services.runtime_variables import prepare_dynamic_config
from services.workflow_engine import WorkflowEngine


async def resolve_assistant_config(
    assistant_id: str,
    *,
    dynamic_variables: dict[str, Any] | None = None,
) -> AssistantConfig:
    async with SessionLocal() as session:
        config = await resolve_runtime_config(session, assistant_id)
    return prepare_dynamic_config(
        config,
        dynamic_variables or {},
        assistant_id=assistant_id,
    )


def validate_visual_runtime(config: AssistantConfig) -> bool:
    """Return the authoritative video-input permission or fail before connect."""

    if config.type == "workflow":
        return WorkflowEngine(config.graph).uses_vision()

    vision_enabled = config.vision_enabled
    if not vision_enabled:
        return False
    has_native_vision = (
        not config.vision_model_resource_id and config.llm_support_image_input
    )
    has_aux_vision_model = (
        bool(config.vision_model_resource_id)
        and config.vision_llm_support_image_input
    )
    if not (has_native_vision or has_aux_vision_model):
        raise ValueError(
            "当前模型不支持图片输入,请在模型资源中选择支持图片输入的视觉模型"
        )
    return True


def _require_values(labels: list[tuple[str, Any]]) -> None:
    missing = [label for label, value in labels if not value]
    if missing:
        raise ValueError(f"助手运行配置不完整: {', '.join(missing)}")


def _validate_voice_resource(
    capability: str,
    *,
    interface_type: str,
    values: dict[str, Any],
    secrets: dict[str, Any],
) -> None:
    labels: list[tuple[str, Any]] = []
    if capability == "ASR":
        if interface_type not in {"openai-asr", "dashscope-asr", "xfyun-asr"}:
            raise ValueError(f"不支持的 ASR 接口类型: {interface_type}")
        if interface_type == "xfyun-asr":
            labels.extend(
                (f"ASR {key}", secrets.get(key))
                for key in ("appId", "apiKey", "apiSecret")
            )
        else:
            labels.extend(
                [
                    ("ASR modelId", values.get("modelId")),
                    ("ASR apiUrl", values.get("apiUrl")),
                    ("ASR apiKey", secrets.get("apiKey")),
                ]
            )
    elif capability == "TTS":
        if interface_type not in {
            "openai-tts",
            "dashscope-tts",
            "xfyun-tts",
            "xfyun-super-tts",
        }:
            raise ValueError(f"不支持的 TTS 接口类型: {interface_type}")
        labels.append(("TTS voice", values.get("voice")))
        if interface_type in {"xfyun-tts", "xfyun-super-tts"}:
            labels.extend(
                (f"TTS {key}", secrets.get(key))
                for key in ("appId", "apiKey", "apiSecret")
            )
        else:
            labels.extend(
                [
                    ("TTS modelId", values.get("modelId")),
                    ("TTS apiUrl", values.get("apiUrl")),
                    ("TTS apiKey", secrets.get("apiKey")),
                ]
            )
    elif capability == "LLM":
        if interface_type not in {"openai-llm", "dashscope-llm"}:
            raise ValueError(f"不支持的 LLM 接口类型: {interface_type}")
        labels.extend(
            [
                ("LLM modelId", values.get("modelId")),
                ("LLM apiUrl", values.get("apiUrl")),
                ("LLM apiKey", secrets.get("apiKey")),
            ]
        )
    _require_values(labels)


def validate_runtime_requirements(config: AssistantConfig) -> None:
    """Reject structurally incomplete assistants before media negotiation."""

    if config.type not in {"prompt", "workflow", "dify", "fastgpt"}:
        raise ValueError(f"当前助手类型不支持 Realtime API: {config.type}")
    if config.runtimeMode == "realtime":
        if config.type not in {"prompt", "workflow"}:
            raise ValueError(f"助手类型 {config.type} 不支持 realtime 运行模式")
        if config.realtime_interface_type not in {
            "qwen-audio-realtime",
            "stepfun-realtime",
        }:
            raise ValueError(
                f"不支持的 Realtime 接口类型: {config.realtime_interface_type}"
            )
        _require_values(
            [
                ("Realtime interfaceType", config.realtime_interface_type),
                ("Realtime modelId", config.realtimeModel),
                ("Realtime apiUrl", config.realtime_base_url),
                ("Realtime apiKey", config.realtime_api_key),
            ],
        )
        return

    _validate_voice_resource(
        "ASR",
        interface_type=config.stt_interface_type,
        values=config.stt_values,
        secrets=config.stt_secrets,
    )
    _validate_voice_resource(
        "TTS",
        interface_type=config.tts_interface_type,
        values=config.tts_values,
        secrets=config.tts_secrets,
    )
    if config.type == "prompt":
        _validate_voice_resource(
            "LLM",
            interface_type=config.llm_interface_type,
            values=config.llm_values,
            secrets=config.llm_secrets,
        )
    elif config.type == "dify":
        _require_values(
            [
                ("Dify apiUrl", config.dify_api_url),
                ("Dify apiKey", config.dify_api_key),
            ],
        )
    elif config.type == "fastgpt":
        _require_values(
            [
                ("FastGPT apiUrl", config.fastgpt_api_url),
                ("FastGPT apiKey", config.fastgpt_api_key),
            ],
        )

    if config.type != "workflow":
        return
    references = graph_references(config.graph)
    missing_models = references["model_resources"] - set(
        config.workflow_model_resources
    )
    missing_knowledge = references["knowledge_bases"] - set(
        config.workflow_knowledge_bases
    )
    if missing_models or missing_knowledge:
        missing = sorted([*missing_models, *missing_knowledge])
        raise ValueError(f"Workflow 引用了不可用资源: {', '.join(missing)}")
    for resource in config.workflow_model_resources.values():
        if resource.capability in {"ASR", "TTS", "LLM"}:
            _validate_voice_resource(
                resource.capability,
                interface_type=resource.interface_type,
                values=resource.values,
                secrets=resource.secrets,
            )