assistant/agent/agents/order.py

"""
Order Agent - Handles order-related queries and operations
"""
import json
from typing import Any

from core.state import AgentState, ConversationState, add_tool_call, set_response, update_context
from core.llm import get_llm_client, Message
from utils.logger import get_logger

logger = get_logger(__name__)


ORDER_AGENT_PROMPT = """你是一个专业的 B2B 订单服务助手。
你的职责是帮助用户处理订单相关的问题，包括：
- 订单查询
- 物流跟踪
- 订单修改
- 订单取消
- 发票获取

## 可用工具

1. **get_mall_order** - 从商城 API 查询订单（推荐使用）
   - order_id: 订单号（必需）
   - 说明：此工具会自动使用用户的身份 token 查询商城订单详情

2. **get_logistics** - 从商城 API 查询物流信息
   - order_id: 订单号（必需）
   - 说明：查询订单的物流轨迹和配送状态

3. **query_order** - 查询历史订单
   - user_id: 用户 ID（自动注入）
   - account_id: 账户 ID（自动注入）
   - order_id: 订单号（可选，不填则查询最近订单）
   - date_start: 开始日期（可选）
   - date_end: 结束日期（可选）
   - status: 订单状态（可选）

4. **modify_order** - 修改订单
   - order_id: 订单号
   - user_id: 用户 ID（自动注入）
   - modifications: 修改内容（address/items/quantity 等）

5. **cancel_order** - 取消订单
   - order_id: 订单号
   - user_id: 用户 ID（自动注入）
   - reason: 取消原因

6. **get_invoice** - 获取发票
   - order_id: 订单号
   - invoice_type: 发票类型（normal/vat）

## 回复格式要求

**重要**：你必须始终返回完整的 JSON 对象，不要包含任何其他文本或解释。

### 格式 1：调用工具
当需要使用工具查询信息时，返回：
```json
{
  "action": "call_tool",
  "tool_name": "get_mall_order",
  "arguments": {
    "order_id": "202071324"
  }
}
```

### 格式 2：询问信息
当需要向用户询问更多信息时，返回：
```json
{
  "action": "ask_info",
  "question": "请提供您的订单号"
}
```

### 格式 3：直接回复
当可以直接回答时，返回：
```json
{
  "action": "respond",
  "response": "您的订单已发货，预计3天内到达"
}
```

## 示例对话

用户: "查询订单 202071324"
回复:
```json
{
  "action": "call_tool",
  "tool_name": "get_mall_order",
  "arguments": {
    "order_id": "202071324"
  }
}
```

用户: "我的订单发货了吗？"
回复:
```json
{
  "action": "ask_info",
  "question": "请提供您的订单号，以便查询订单状态"
}
```

用户: "帮我查一下订单 202071324 的物流"
回复:
```json
{
  "action": "call_tool",
  "tool_name": "get_logistics",
  "arguments": {
    "order_id": "202071324"
  }
}
```

## 重要约束
- **必须返回完整的 JSON 对象**，不要只返回部分内容
- **不要添加任何 markdown 代码块标记**（如 \`\`\`json）
- **不要添加任何解释性文字**，只返回 JSON
- user_id 和 account_id 会自动注入到 arguments 中，无需手动添加
- 如果用户提供了订单号，优先使用 get_mall_order 工具
- 如果用户想查询物流状态，使用 get_logistics 工具
- 对于敏感操作（取消、修改），确保有明确的订单号
"""


async def order_agent(state: AgentState) -> AgentState:
    """Order agent node
    
    Handles order queries, tracking, modifications, and cancellations.
    
    Args:
        state: Current agent state
        
    Returns:
        Updated state with tool calls or response
    """
    logger.info(
        "Order agent processing",
        conversation_id=state["conversation_id"],
        sub_intent=state.get("sub_intent")
    )
    
    state["current_agent"] = "order"
    state["agent_history"].append("order")
    state["state"] = ConversationState.PROCESSING.value
    
    # Check if we have tool results to process
    if state["tool_results"]:
        return await _generate_order_response(state)
    
    # Build messages for LLM
    messages = [
        Message(role="system", content=ORDER_AGENT_PROMPT),
    ]
    
    # Add conversation history
    for msg in state["messages"][-6:]:
        messages.append(Message(role=msg["role"], content=msg["content"]))
    
    # Build context info
    context_info = f"用户ID: {state['user_id']}\n账户ID: {state['account_id']}\n"
    
    # Add entities if available
    if state["entities"]:
        context_info += f"已提取的信息: {json.dumps(state['entities'], ensure_ascii=False)}\n"
    
    # Add existing context
    if state["context"].get("order_id"):
        context_info += f"当前讨论的订单号: {state['context']['order_id']}\n"
    
    user_content = f"{context_info}\n用户消息: {state['current_message']}"
    messages.append(Message(role="user", content=user_content))
    
    try:
        llm = get_llm_client()
        response = await llm.chat(messages, temperature=0.5)

        # Parse response
        content = response.content.strip()
        logger.info(
            "LLM response received",
            conversation_id=state["conversation_id"],
            response_length=len(content),
            response_preview=content[:300]
        )

        # 检查是否是简化的工具调用格式：工具名称\n{参数}
        # 例如：get_mall_order\n{"order_id": "202071324"}
        if "\n" in content and "{" in content:
            lines = content.split("\n")
            if len(lines) >= 2:
                tool_name_line = lines[0].strip()
                json_line = "\n".join(lines[1:]).strip()

                # 如果第一行看起来像工具名称（不包含 {），且第二行是 JSON
                if "{" not in tool_name_line and "{" in json_line:
                    logger.info(
                        "Detected simplified tool call format",
                        tool_name=tool_name_line,
                        json_preview=json_line[:200]
                    )

                    try:
                        arguments = json.loads(json_line)
                        # 直接构建工具调用
                        arguments["user_id"] = state["user_id"]
                        arguments["account_id"] = state["account_id"]

                        # Inject user_token if available
                        if state.get("user_token"):
                            arguments["user_token"] = state["user_token"]
                            logger.info(
                                "Injected user_token into tool call",
                                token_prefix=state["user_token"][:20] if state["user_token"] else None
                            )
                        else:
                            logger.warning(
                                "No user_token available in state, MCP will use default token",
                                conversation_id=state["conversation_id"]
                            )

                        # Use entity if available
                        if "order_id" not in arguments and state["entities"].get("order_id"):
                            arguments["order_id"] = state["entities"]["order_id"]

                        state = add_tool_call(
                            state,
                            tool_name=tool_name_line,
                            arguments=arguments,
                            server="order"
                        )
                        state["state"] = ConversationState.TOOL_CALLING.value

                        logger.info(
                            "Tool call added from simplified format",
                            tool_name=tool_name_line,
                            arguments_keys=list(arguments.keys())
                        )

                        return state
                    except json.JSONDecodeError as e:
                        logger.warning(
                            "Failed to parse simplified format",
                            error=str(e),
                            json_line=json_line[:200]
                        )

        # 清理内容，去除可能的 markdown 代码块标记
        # 例如：```json\n{...}\n``` 或 ```\n{...}\n```
        if "```" in content:
            # 找到第一个 ``` 后的内容
            parts = content.split("```")
            if len(parts) >= 2:
                content = parts[1].strip()
                # 去掉可能的 "json" 标记
                if content.startswith("json"):
                    content = content[4:].strip()
                # 去掉结尾的 ``` 标记
                if content.endswith("```"):
                    content = content[:-3].strip()

        # 尝试提取 JSON 对象（处理周围可能有文本的情况）
        json_start = content.find("{")
        json_end = content.rfind("}")
        if json_start != -1 and json_end != -1 and json_end > json_start:
            content = content[json_start:json_end + 1]

        logger.info(
            "Cleaned content for JSON parsing",
            conversation_id=state["conversation_id"],
            content_length=len(content),
            content_preview=content[:500]
        )

        try:
            result = json.loads(content)
        except json.JSONDecodeError as e:
            logger.error(
                "Failed to parse LLM response as JSON",
                conversation_id=state["conversation_id"],
                error=str(e),
                content_preview=content[:500]
            )
            # 如果解析失败，尝试将原始内容作为直接回复
            state = set_response(state, response.content)
            return state

        action = result.get("action")

        logger.info(
            "LLM action parsed",
            conversation_id=state["conversation_id"],
            action=action,
            tool_name=result.get("tool_name")
        )

        if action == "call_tool":
            # Inject user context into arguments
            arguments = result.get("arguments", {})
            arguments["user_id"] = state["user_id"]
            arguments["account_id"] = state["account_id"]

            # Inject user_token if available (for Mall API calls)
            if state.get("user_token"):
                arguments["user_token"] = state["user_token"]
                logger.debug(
                    "Injected user_token into tool call",
                    token_prefix=state["user_token"][:20] if state["user_token"] else None
                )
            else:
                logger.warning(
                    "No user_token available in state, MCP will use default token",
                    conversation_id=state["conversation_id"]
                )

            # Use entity if available
            if "order_id" not in arguments and state["entities"].get("order_id"):
                arguments["order_id"] = state["entities"]["order_id"]

            state = add_tool_call(
                state,
                tool_name=result["tool_name"],
                arguments=arguments,
                server="order"
            )
            state["state"] = ConversationState.TOOL_CALLING.value

            logger.info(
                "Tool call added",
                tool_name=result["tool_name"],
                arguments_keys=list(arguments.keys())
            )
            
        elif action == "ask_info":
            state = set_response(state, result["question"])
            state["state"] = ConversationState.AWAITING_INFO.value
            
        elif action == "respond":
            state = set_response(state, result["response"])
            state["state"] = ConversationState.GENERATING.value
            
        elif action == "handoff":
            state["requires_human"] = True
            state["handoff_reason"] = result.get("reason", "Complex order operation")

        return state

    except Exception as e:
        logger.error("Order agent failed", error=str(e))
        state["error"] = str(e)
        return state


async def _generate_order_response(state: AgentState) -> AgentState:
    """Generate response based on order tool results"""
    
    # Build context from tool results
    tool_context = []
    for result in state["tool_results"]:
        if result["success"]:
            data = result["data"]
            tool_context.append(f"工具 {result['tool_name']} 返回:\n{json.dumps(data, ensure_ascii=False, indent=2)}")
            
            # Extract order_id for context
            if isinstance(data, dict):
                if data.get("order_id"):
                    state = update_context(state, {"order_id": data["order_id"]})
                elif data.get("orders") and len(data["orders"]) > 0:
                    state = update_context(state, {"order_id": data["orders"][0].get("order_id")})
        else:
            tool_context.append(f"工具 {result['tool_name']} 执行失败: {result['error']}")
    
    prompt = f"""基于以下订单系统返回的信息，生成对用户的回复。

用户问题: {state["current_message"]}

系统返回信息:
{chr(10).join(tool_context)}

请生成一个清晰、友好的回复，包含订单的关键信息（订单号、状态、金额、物流等）。
如果是物流信息，请按时间线整理展示。
只返回回复内容，不要返回 JSON。"""
    
    messages = [
        Message(role="system", content="你是一个专业的订单客服助手，请根据系统返回的信息回答用户的订单问题。"),
        Message(role="user", content=prompt)
    ]
    
    try:
        llm = get_llm_client()
        response = await llm.chat(messages, temperature=0.7)
        state = set_response(state, response.content)
        return state
        
    except Exception as e:
        logger.error("Order response generation failed", error=str(e))
        state = set_response(state, "抱歉，处理订单信息时遇到问题。请稍后重试或联系人工客服。")
        return state