ZNJJ-api-server/src/core/fastgpt_client.py

"""FastGPT client and chat backend dependency injection."""
from contextlib import asynccontextmanager
from fastapi import FastAPI
from fastgpt_client import AsyncChatClient
from ..agent.graph import build_graph
from ..backends.chat import ChatBackend
from ..backends.fastgpt import FastGPTBackend
from ..backends.langgraph import LangGraphBackend
from ..services.app_service import AccidentAppService
from ..services.repository import InMemorySessionRepository
from .config import Config


_fastgpt_client: AsyncChatClient | None = None
_chat_backend: ChatBackend | None = None
_langgraph_graph = None
_app_service: AccidentAppService | None = None

# 两后端缺省 60 秒、最多额外重试 3 次，1/2/4 秒退避。
# FastGPT SDK 的 max_retries 实为总尝试数，注入时转换为 1 + 重试次数。
# LLM 关闭 SDK 自动重试；流式发出文本后不再重试。
# LLM 预算按单次模型调用计算，FastGPT timeout 为 HTTP SDK 超时，
# 均不承诺多次模型调用的整个聊天回合具有相同总期限。
FASTGPT_TIMEOUT_SECONDS = 60.0
FASTGPT_MAX_RETRIES = 3


@asynccontextmanager
async def lifespan(app: FastAPI):
    """Manage chat backend resource lifecycle."""
    global _chat_backend, _fastgpt_client
    Config.validate()
    llm = None

    if Config.AGENT_BACKEND == "langgraph":
        # 作业 2：LangGraph fake 模式不要求 FastGPT 密钥。
        # TODO(作业 2): 若语音仍启用，需在此单独初始化并校验 FastGPT 配置。
        from ..agent.llm import build_llm_service

        global _langgraph_graph, _app_service
        _langgraph_graph = build_graph()
        llm = build_llm_service()
        _chat_backend = LangGraphBackend(_langgraph_graph, llm=llm)
        # 作业 6：应用服务 + 内存 repository（作业 7 换 PostgreSQL）。
        _app_service = AccidentAppService(
            _chat_backend, InMemorySessionRepository()
        )
    else:
        _fastgpt_client = AsyncChatClient(
            api_key=Config.FASTGPT_API_KEY,
            base_url=Config.FASTGPT_BASE_URL,
            timeout=FASTGPT_TIMEOUT_SECONDS,
            max_retries=FASTGPT_MAX_RETRIES + 1,
            retry_delay=1.0,
            enable_logging=Config.DEBUG,
        )
        await _fastgpt_client.__aenter__()
        _chat_backend = FastGPTBackend(_fastgpt_client)

    try:
        yield
    finally:
        _chat_backend = None
        _langgraph_graph = None
        _app_service = None
        if llm is not None and hasattr(llm, "aclose"):
            await llm.aclose()
        if _fastgpt_client:
            await _fastgpt_client.__aexit__(None, None, None)
        _fastgpt_client = None


async def delete_chat_session(thread_id: str) -> None:
    """langgraph 模式下删除会话：清理图 checkpoint（对照计划作业 6 的
    完整语义——业务字段、事件、路由持久化清理在接入 repository 后补齐）。
    """
    if _langgraph_graph is None:
        raise RuntimeError("LangGraph backend not initialized")
    checkpointer = getattr(_langgraph_graph, "checkpointer", None)
    if checkpointer is not None and hasattr(checkpointer, "delete_thread"):
        checkpointer.delete_thread(thread_id)


def get_fastgpt_client() -> AsyncChatClient:
    """Get the initialized FastGPT client."""
    if _fastgpt_client is None:
        raise RuntimeError("FastGPT client not initialized")
    return _fastgpt_client


def get_app_service() -> AccidentAppService:
    """Get the initialized application service（langgraph 模式）。"""
    if _app_service is None:
        raise RuntimeError("Application service not initialized")
    return _app_service


def get_chat_backend() -> ChatBackend:
    """Get the backend-neutral chat service."""
    if _chat_backend is None:
        raise RuntimeError("Chat backend not initialized")
    return _chat_backend