"""求职助手 Agent 对话 AI 引擎

构造 prompt + 调 LLM + 解析返回。
依赖：LLM 枚举、job_agent/prompts、parse_llm_json
"""

from app.ai.job_agent.prompts import SYSTEM_PROMPT
from app.ai.model_config import JobAgentModel
from app.core.logger import log
from app.tool.json_helper import parse_llm_json


async def agent_chat(resume_text: str, message: str, history: list[dict],
                     job_categories: list[str], regions: list[str],
                     industries: list[str]) -> dict:
    """求职助手对话
    1. 构造 system prompt 2. 拼 messages 3. 调 LLM 4. 解析返回
    """
    # 1. 构造 system prompt
    system_content = SYSTEM_PROMPT.format(
        resume_text=resume_text,
        job_categories="、".join(job_categories) if job_categories else "未设置",
        regions="、".join(regions) if regions else "未设置",
        industries="、".join(industries) if industries else "未设置",
    )

    # 2. 拼 messages
    messages = [("system", system_content)]
    for msg in history:
        messages.append((msg["role"], msg["content"]))
    messages.append(("human", message))

    # 3. 调 LLM
    try:
        result = await JobAgentModel.CHAT.ainvoke(messages)
        raw = result.content
    except Exception as e:
        log.error(f"求职助手AI调用失败: {e}")
        return {"message": "抱歉，我暂时无法回复，请稍后再试。", "tool": None, "toolParams": None}

    # 4. 解析返回
    try:
        parsed = parse_llm_json(raw)
        return {
            "message": parsed.get("message", ""),
            "tool": parsed.get("tool"),
            "toolParams": parsed.get("toolParams"),
        }
    except Exception as e:
        log.warning(f"求职助手AI返回解析失败, raw={raw}, error={e}")
        return {"message": raw.strip() if raw else "抱歉，我暂时无法回复。", "tool": None, "toolParams": None}