"""
LangGraph StateGraph 构建

构建 assistant + ToolNode 的 ReAct 图，接入 Dashscope Qwen。
"""

from typing import Optional

from langgraph.graph import StateGraph, START, END
from langgraph.prebuilt import ToolNode, tools_condition
from langgraph.checkpoint.memory import MemorySaver
from langchain_openai import ChatOpenAI

from app.config import settings
from app.utils.logger import logger
from .state import AgentState
from .tools import all_tools
from .prompts import SYSTEM_PROMPT


def _create_llm():
    """创建 LLM 客户端（通过 Dashscope OpenAI 兼容接口对接 Qwen）"""
    return ChatOpenAI(
        model=settings.agent.model,
        base_url=settings.agent.vlm_base_url,
        api_key=settings.agent.vlm_api_key,
        timeout=settings.agent.timeout,
        temperature=0.1,
    )


def build_agent_graph(checkpointer=None):
    """构建并编译 Agent 图

    Args:
        checkpointer: LangGraph checkpointer 实例（None=不持久化）

    Returns:
        编译后的 CompiledGraph
    """
    llm = _create_llm()
    llm_with_tools = llm.bind_tools(all_tools)

    def assistant(state: AgentState):
        """LLM 推理节点：接收消息 + 系统提示，返回回复或工具调用"""
        system_msg = {"role": "system", "content": SYSTEM_PROMPT}
        response = llm_with_tools.invoke([system_msg] + state["messages"])
        return {"messages": [response]}

    # 构建图
    builder = StateGraph(AgentState)

    # 两个核心节点
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(all_tools))

    # 边：START → assistant → (条件) → tools 或 END
    builder.add_edge(START, "assistant")
    builder.add_conditional_edges("assistant", tools_condition)
    builder.add_edge("tools", "assistant")

    # 编译
    graph = builder.compile(checkpointer=checkpointer)
    logger.info("LangGraph Agent 图已编译")
    return graph


def create_default_graph():
    """创建带内存 checkpoint 的默认图（开发用）"""
    checkpointer = MemorySaver()
    return build_agent_graph(checkpointer=checkpointer)