feat：1.通过请求数量区分刷新(num=1)和正常推荐(num>1)

2.回调信息简化 \ stylist_agent_server.py中 一部分逻辑更新

.env

@@ -1,2 +0,0 @@
-GEMINI_API_KEY=AIzaSyAO4zXFke1bqyrXd9-RGfKJTLerwLSFKww
-GOOGLE_APPLICATION_CREDENTIALS="/app/request.json"

.env_local

@@ -1,2 +0,0 @@
-GEMINI_API_KEY=AIzaSyAO4zXFke1bqyrXd9-RGfKJTLerwLSFKww
-GOOGLE_APPLICATION_CREDENTIALS="/workspace/lc_stylist_agent/app/request.json"

.gitignore

@@ -1,12 +1,10 @@
-.env
+/.env
 .vscode/
-app/core/__pycache__/
-data/db
-data/image_data
-app/core/data/
+__pycache__/
+data/
 .idea/
-*.sqlite3
 *.log
-db
-*.sqlite
-*.png
+*.toml
+.prod_env
+google_application_credentials.json
+*.bash

Dockerfile

@@ -40,8 +40,7 @@ COPY . /app
 # Install litserve and requirements
 RUN pip install --upgrade pip setuptools wheel
 RUN pip install --no-cache-dir litserve==0.2.16 -r requirements.txt
-RUN pip install torch torchvision
-
+RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
 EXPOSE 8000
 CMD ["python", "-m","app.main"]
 #CMD ["tail", "-f","/dev/null"]

app/config.py

@@ -3,8 +3,8 @@ import os
 from pydantic_settings import BaseSettings, SettingsConfigDict
 from pydantic import Field
 
+
 # ⚠️ 注意: 您需要安装 pydantic-settings: pip install pydantic-settings
-DEBUG = os.environ.get("DEBUG", 1)
 
 
 class Settings(BaseSettings):
@@ -16,6 +16,8 @@ class Settings(BaseSettings):
         env_file_encoding='utf-8',
         extra='ignore'  # 忽略环境变量中多余的键
     )
+    # 调试配饰
+    LOCAL: int = Field(default=0, description="是否在本地运行，1表示本地运行，0表示生产环境运行")
 
     # Redis 配置
     REDIS_HOST: str = Field(default='10.1.1.240', description="Redis服务器地址")
@@ -28,19 +30,22 @@ class Settings(BaseSettings):
     LLM_MODEL_NAME: str = Field(default="gemini-2.5-flash", description="使用的 LLM 模型名称")
 
     # 路径配置参数
-    DATA_ROOT: str = Field(default="/workspace/lc_stylist_agent/app/core/data", description="数据根目录")
-    IMAGE_DIR: str = Field(default="/workspace/lc_stylist_agent/app/core/data/image_data", description="图片数据目录")
-    OUTFIT_OUTPUT_DIR: str = Field(default="/workspace/lc_stylist_agent/app/core/data/outfit_output", description="生成的搭配图片输出目录")
-    STYLIST_GUIDE_DIR: str = Field(default="/workspace/lc_stylist_agent/app/core/data/stylist_guide", description="风格指南文本目录")
+    DATA_ROOT: str = Field(default="/workspace/lc_stylist_agent/data", description="数据根目录")
+    OUTFIT_OUTPUT_DIR: str = Field(default="/workspace/lc_stylist_agent/data/outfit_output", description="生成的搭配图片输出目录")
+    STYLIST_GUIDE_DIR: str = Field(default="/workspace/lc_stylist_agent/data/stylist_guide", description="风格指南文本目录")
 
     # 向量数据库配置参数
-    if DEBUG == 1:
-        VECTOR_DB_DIR: str = Field(default="/workspace/lc_stylist_agent/db", description="向量数据库目录")
-    else:
-        VECTOR_DB_DIR: str = Field(default="/db", description="向量数据库目录")
+    VECTOR_DB_DIR: str = Field(default="/db", description="向量数据库目录")
     COLLECTION_NAME: str = Field(default="lc_clothing_embedding", description="向量数据库集合名称")
     EMBEDDING_MODEL_NAME: str = Field(default="openai/clip-vit-base-patch32", description="CLIP嵌入模型名称")
 
+    # minio配置
+    MINIO_URL: str = Field(default="", description="URL")
+    MINIO_ACCESS: str = Field(default="", description="ACCESS")
+    MINIO_SECRET: str = Field(default="", description="SECRET")
+    MINIO_SECURE: bool = Field(default=True, description="SECRET")
+    MINIO_LC_DATA_PATH: str = Field(default="", description="图片数据路径")
+
 
 # 创建配置实例，供应用其他部分使用
 settings = Settings()

app/core/chatbot_agent.py

@@ -1,139 +0,0 @@
-import time
-from typing import Dict, List
-import asyncio
-
-from app.core.data_structure import Message, Role
-from app.core.llm_interface import AsyncLLMInterface, AsyncGeminiLLM
-from app.core.redis_manager import RedisManager
-from app.core.system_prompt import BASIC_PROMPT, SUMMARY_PROMPT
-from app.core.stylist_agent import AsyncStylistAgent
-from app.core.vector_database import VectorDatabase
-from app.core.config import settings
-
-
-class ChatbotAgent:
-    def __init__(self, llm_model: AsyncLLMInterface = None):
-        self.llm = llm_model if llm_model else AsyncGeminiLLM(model_name=settings.LLM_MODEL_NAME)
-        self.redis = RedisManager(
-            host=settings.REDIS_HOST,
-            port=settings.REDIS_PORT,
-            db=settings.REDIS_DB,
-            key_prefix=settings.REDIS_HISTORY_KEY_PREFIX
-        )
-        self.vector_db = VectorDatabase(
-            vector_db_dir=settings.VECTOR_DB_DIR,
-            collection_name=settings.COLLECTION_NAME,
-            embedding_model_name=settings.EMBEDDING_MODEL_NAME
-        )
-        self.stylist_agent_kwages = {
-            'local_db': self.vector_db,
-            'max_len': 5,
-            'outfits_root': settings.OUTFIT_OUTPUT_DIR,
-            'image_dir': settings.IMAGE_DIR,
-            'stylist_guide_dir': settings.STYLIST_GUIDE_DIR,
-            'gemini_model_name': settings.LLM_MODEL_NAME
-        }
-
-    async def process_query(self, user_id: str, user_message: str) -> str:
-        """
-        处理用户的最新输入，调用 LLM, 并更新历史记录。
-        """
-
-        # 添加用户消息到历史
-        user_msg = Message(role=Role.USER, content=user_message)
-        chat_history = self.redis.get_history(user_id)
-        chat_history.append(user_msg)
-
-        # 生成 LLM 回复
-        try:
-            response_text = await self.llm.generate_response(chat_history, system_prompt=BASIC_PROMPT)
-        except Exception as e:
-            print(f"LLM 调用失败: {e}")
-            response_text = "抱歉，系统暂时无法响应，请稍后再试。"
-
-        # 添加助手消息到历史
-        if response_text:
-            assistant_msg = Message(role=Role.ASSISTANT, content=response_text)
-        else:
-            assistant_msg = Message(role=Role.ASSISTANT, content="No response generated. Try again later.")
-
-        self.redis.save_message(user_id, user_msg)
-        self.redis.save_message(user_id, assistant_msg)
-
-        return response_text
-
-    async def get_conversation_summary(self, user_id: str) -> str:
-        """
-        分析用户的完整会话历史，并打包成一个简洁的需求总结。
-        
-        这个总结可以直接作为输入 Prompt 传递给 Stylist Agent。`
-        """
-        history_messages = self.redis.get_history(user_id)
-        input_message = "\n".join([f"{msg.role.value}: {msg.content}" for msg in history_messages])
-
-        # 临时调用 LLM 或使用本地逻辑生成总结
-        summary = await self.llm.generate_response(history=[Message(role=Role.USER, content=input_message)], system_prompt=SUMMARY_PROMPT)
-
-        return summary
-
-    async def recommend_outfit(self, request_summary: str, stylist_name: str, start_outfit: List[Dict[str, str]] = [], num_outfits: int = 1):
-        """
-        基于用户的对话历史和需求，推荐一套搭配。
-        
-        Args:
-            request_summary: 用户的request
-            start_outfit: 可选的初始搭配列表，每个元素包含 'item_id' 和 'category'。
-        """
-        tasks = []
-        for _ in range(num_outfits):
-            agent = AsyncStylistAgent(**self.stylist_agent_kwages)
-            task = agent.run_styling_process(request_summary, stylist_name, start_outfit)
-            tasks.append(task)
-        print(f"--- Starting {num_outfits} concurrent outfit generation tasks. ---")
-
-        try:
-            results = await asyncio.gather(*tasks, return_exceptions=True)
-
-            successful_outfits = []
-            failed_outfits = []
-            for result in results:
-                if isinstance(result, Exception):
-                    # 任务执行中发生异常
-                    failed_outfits.append(f"Failed: {result}")
-                else:
-                    # 任务成功，result 是 run_styling_process 返回的图片路径
-                    successful_outfits.append(result)
-
-            return {
-                "successful_outfits": successful_outfits,
-                "failed_outfits": failed_outfits
-            }
-
-        except Exception as e:
-            print(f"An unexpected error occurred during concurrent recommendation: {e}")
-            return {"error": str(e)}
-
-
-if __name__ == "__main__":
-    async def run():
-        start_time = time.time()
-        agent = ChatbotAgent()
-        user_id = "string"
-        # agent.redis.clear_history(user_id)  # 清除历史，便于测试
-        # print(await agent.process_query(user_id, "I want a chic outfit for a summer party."))
-        # print(await agent.process_query(user_id, "I prefer something floral and light."))
-        request_summary = await agent.get_conversation_summary(user_id)
-        print(f"Conversation Summary:\n{request_summary}")
-
-        recommendation_results = await agent.recommend_outfit(request_summary, stylist_name="crystal", start_outfit=[], num_outfits=4)
-
-        print("\n--- Final Recommendation Results ---")
-        for i, path in enumerate(recommendation_results.get("successful_outfits", [])):
-            print(f"✅ Outfit {i + 1} saved to: {path}")
-
-        for error in recommendation_results.get("failed_outfits", []):
-            print(f"❌ {error}")
-        print(time.time() - start_time)
-
-
-    asyncio.run(run())

app/core/chatbot_agent_stream.py

@@ -1,163 +0,0 @@
-from google.genai import types
-from typing import Dict, List
-import asyncio
-
-from google import genai
-
-from app.core import system_prompt
-from app.core.data_structure import Message, Role
-from app.core.llm_interface_stream import AsyncLLMInterface, AsyncGeminiLLM
-from app.core.redis_manager import RedisManager
-from app.core.system_prompt import BASIC_PROMPT, SUMMARY_PROMPT
-from app.core.stylist_agent import AsyncStylistAgent
-from app.core.vector_database import VectorDatabase
-from app.core.config import settings
-
-
-class ChatbotAgent:
-    def __init__(self, llm_model: AsyncLLMInterface = None):
-        self.llm = llm_model if llm_model else AsyncGeminiLLM(model_name=settings.LLM_MODEL_NAME)
-        self.redis = RedisManager(
-            host=settings.REDIS_HOST,
-            port=settings.REDIS_PORT,
-            db=settings.REDIS_DB,
-            key_prefix=settings.REDIS_HISTORY_KEY_PREFIX
-        )
-        self.vector_db = VectorDatabase(
-            vector_db_dir=settings.VECTOR_DB_DIR,
-            collection_name=settings.COLLECTION_NAME,
-            embedding_model_name=settings.EMBEDDING_MODEL_NAME
-        )
-        self.stylist_agent_kwages = {
-            'local_db': self.vector_db,
-            'max_len': 5,
-            'outfits_root': settings.OUTFIT_OUTPUT_DIR,
-            'image_dir': settings.IMAGE_DIR,
-            'stylist_guide_dir': settings.STYLIST_GUIDE_DIR,
-            'gemini_model_name': settings.LLM_MODEL_NAME
-        }
-        self.gemini_client = genai.Client(
-            vertexai=True, project='aida-461108', location='us-central1'
-        )
-
-    async def process_query(self, user_id: str, user_message: str) -> str:
-        """
-        处理用户的最新输入，调用 LLM, 并更新历史记录。
-        """
-
-        # 添加用户消息到历史
-        user_msg = Message(role=Role.USER, content=user_message)
-        chat_history = self.redis.get_history(user_id)
-        chat_history.append(user_msg)
-
-        contents = []
-
-        for msg in chat_history:
-            gemini_role = "user" if msg.role == Role.USER else "model"
-            content = types.Content(
-                role=gemini_role,
-                parts=[types.Part.from_text(text=msg.content)]
-            )
-            contents.append(content)
-
-        response_parts = []
-        response_stream = await self.gemini_client.aio.models.generate_content_stream(
-            model='gemini-2.5-flash',
-            contents=contents,
-            config=types.GenerateContentConfig(
-                system_instruction=BASIC_PROMPT,
-                # temperature=0.3,
-            )
-        )
-        async for chunk in response_stream:
-            # 您可以在这里处理每一个文本块，例如发送给前端
-            print(chunk.text, end="", flush=True)
-            response_parts.append(chunk.text)
-            # 3. 将所有文本块合并成最终的字符串
-        response_text = "".join(response_parts)
-
-        # 添加助手消息到历史
-        if response_text:
-            assistant_msg = Message(role=Role.ASSISTANT, content=response_text)
-        else:
-            assistant_msg = Message(role=Role.ASSISTANT, content="No response generated. Try again later.")
-
-        self.redis.save_message(user_id, user_msg)
-        self.redis.save_message(user_id, assistant_msg)
-
-        return response_text
-
-    async def get_conversation_summary(self, user_id: str) -> str:
-        """
-        分析用户的完整会话历史，并打包成一个简洁的需求总结。
-        
-        这个总结可以直接作为输入 Prompt 传递给 Stylist Agent。`
-        """
-        history_messages = self.redis.get_history(user_id)
-        input_message = "\n".join([f"{msg.role.value}: {msg.content}" for msg in history_messages])
-
-        # 临时调用 LLM 或使用本地逻辑生成总结
-        summary = await self.llm.generate_response(history=[Message(role=Role.USER, content=input_message)], system_prompt=SUMMARY_PROMPT)
-
-        return summary
-
-    async def recommend_outfit(self, request_summary: str, stylist_name: str, start_outfit: List[Dict[str, str]] = [], num_outfits: int = 1):
-        """
-        基于用户的对话历史和需求，推荐一套搭配。
-        
-        Args:
-            request_summary: 用户的request
-            start_outfit: 可选的初始搭配列表，每个元素包含 'item_id' 和 'category'。
-        """
-        tasks = []
-        for _ in range(num_outfits):
-            agent = AsyncStylistAgent(**self.stylist_agent_kwages)
-            task = agent.run_styling_process(request_summary, stylist_name, start_outfit)
-            tasks.append(task)
-        print(f"--- Starting {num_outfits} concurrent outfit generation tasks. ---")
-
-        try:
-            results = await asyncio.gather(*tasks, return_exceptions=True)
-
-            successful_outfits = []
-            failed_outfits = []
-            for result in results:
-                if isinstance(result, Exception):
-                    # 任务执行中发生异常
-                    failed_outfits.append(f"Failed: {result}")
-                else:
-                    # 任务成功，result 是 run_styling_process 返回的图片路径
-                    successful_outfits.append(result)
-
-            return {
-                "successful_outfits": successful_outfits,
-                "failed_outfits": failed_outfits
-            }
-
-        except Exception as e:
-            print(f"An unexpected error occurred during concurrent recommendation: {e}")
-            return {"error": str(e)}
-
-
-if __name__ == "__main__":
-    async def run():
-        # 阶段一：用户对话
-        agent = ChatbotAgent()
-        user_id = "string"
-        # agent.redis.clear_history(user_id)  # 清除历史，便于测试
-        # await agent.process_query(user_id, "I want a chic outfit for a summer party.")
-        # print(await agent.process_query(user_id, "I prefer something floral and light."))
-
-        # 阶段二：读取聊天记录，生成推荐搭配
-        request_summary = await agent.get_conversation_summary(user_id)
-        print(f"Conversation Summary:\n{request_summary}")
-
-        recommendation_results = await agent.recommend_outfit(request_summary, stylist_name="crystal", start_outfit=[], num_outfits=1)
-
-        print("\n--- Final Recommendation Results ---")
-        for i, path in enumerate(recommendation_results.get("successful_outfits", [])):
-            print(f"✅ Outfit {i + 1} saved to: {path}")
-
-        for error in recommendation_results.get("failed_outfits", []):
-            print(f"❌ {error}")
-    asyncio.run(run())

app/core/data_structure.py

@@ -1,16 +0,0 @@
-from typing import List, Dict, Any
-from enum import Enum
-from pydantic import BaseModel, Field
-import datetime
-
-# 角色枚举，用于区分用户和系统的消息
-class Role(str, Enum):
-    USER = "user"
-    ASSISTANT = "assistant"
-    SYSTEM = "system"
-
-# 单条消息的数据模型
-class Message(BaseModel):
-    role: Role = Field(..., description="Role of message sender")
-    content: str = Field(..., description="Content of the message")
-    # timestamp: str = Field(default_factory=lambda: datetime.datetime.now().isoformat()) # 记录时间戳

app/core/llm_interface.py

@@ -1,56 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List
-
-from google import genai
-from google.genai import types
-
-from app.core.data_structure import Message, Role
-
-class AsyncLLMInterface(ABC):
-    @abstractmethod
-    async def generate_response(self, history: List[Message], system_prompt: str) -> str:
-        """
-        根据对话历史和系统指令生成回复.
-        
-        Args:
-            history: 包含多条 Message 的列表。
-            
-        Returns:
-            LLM 生成的回复字符串。
-        """
-        raise NotImplementedError("Subclasses must implement this method")
-
-class AsyncGeminiLLM(AsyncLLMInterface):
-    def __init__(self, model_name: str = "gemini-2.5-flash"):
-        self.model_name = model_name
-        try:
-            self.gemini_client = genai.Client(
-                vertexai=True, project='aida-461108', location='us-central1'
-            )
-        except Exception as e:
-            raise type(e)(f"Failed to initialize Gemini Client. Check if GEMINI_API_KEY is set. Original error: {e}")
-
-    async def generate_response(self, history: List[Message], system_prompt: str) -> str:
-        contents = []
-
-        for msg in history:
-            gemini_role = "user" if msg.role == Role.USER else "model"
-            content = types.Content(
-                role=gemini_role,
-                parts=[types.Part.from_text(text=msg.content)]
-            )
-            contents.append(content)
-
-        try:
-            response = await self.gemini_client.aio.models.generate_content(
-                model=self.model_name,
-                contents=contents,
-                config=types.GenerateContentConfig(
-                    system_instruction=system_prompt,
-                    # temperature=0.3,
-                )
-            )
-            return response.text
-        except Exception as e:
-            raise type(e)(f"Gemini API call failed: {e}")
-

app/core/llm_interface_stream.py

@@ -1,61 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List
-
-from google import genai
-from google.genai import types
-
-from app.core.data_structure import Message, Role
-
-
-class AsyncLLMInterface(ABC):
-    @abstractmethod
-    async def generate_response(self, history: List[Message], system_prompt: str) -> str:
-        """
-        根据对话历史和系统指令生成回复.
-
-        Args:
-            history: 包含多条 Message 的列表。
-
-        Returns:
-            LLM 生成的回复字符串。
-        """
-        raise NotImplementedError("Subclasses must implement this method")
-
-
-class AsyncGeminiLLM(AsyncLLMInterface):
-    def __init__(self, model_name: str = "gemini-2.5-flash"):
-        self.model_name = model_name
-        try:
-            self.gemini_client = genai.Client(
-                vertexai=True, project='aida-461108', location='us-central1'
-            )
-        except Exception as e:
-            raise type(e)(f"Failed to initialize Gemini Client. Check if GEMINI_API_KEY is set. Original error: {e}")
-
-    async def generate_response(self, history: List[Message], system_prompt: str):
-        contents = []
-
-        for msg in history:
-            gemini_role = "user" if msg.role == Role.USER else "model"
-            content = types.Content(
-                role=gemini_role,
-                parts=[types.Part.from_text(text=msg.content)]
-            )
-            contents.append(content)
-
-        return contents
-            # response_stream = await self.gemini_client.aio.models.generate_content_stream(
-            #     model=self.model_name,
-            #     contents=contents,
-            #     config=types.GenerateContentConfig(
-            #         system_instruction=system_prompt,
-            #         # temperature=0.3,
-            #     )
-            # )
-            #
-            # # 3. 异步迭代流，并 yield 每个块的文本
-            # async for chunk in response_stream:
-            #     # 确保 chunk 中有可用的文本
-            #     if chunk.text:
-            #         print(chunk.text)
-            #         yield chunk.text

app/core/redis_manager.py

@@ -1,68 +0,0 @@
-import logging
-
-import redis
-from typing import List, Optional
-from app.core.data_structure import Message, Role
-
-logger = logging.getLogger(__name__)
-
-
-# 这是一个同步 Redis 客户端，用于演示如何替换内存存储。
-# 在生产环境和异步 Web 框架中，应替换为 aioredis 等异步客户端。
-class RedisManager:
-    """同步管理器，用于在 Redis 中存储和检索对话历史。"""
-
-    def __init__(self, host: str = 'localhost', port: int = 6379, db: int = 0, key_prefix: str = "chat:history:"):
-        self.r: Optional[redis.Redis] = None
-        self.key_prefix = key_prefix
-        try:
-            # 尝试连接 Redis
-            self.r = redis.Redis(host=host, port=port, db=db, decode_responses=True)
-            self.r.ping()
-            logger.info("Successfully connected to Redis at {}:{}".format(host, port))
-        except Exception as e:
-            logger.error(f"⚠️ Failed to connect to Redis: {e}. Falling back to No-Op.")
-            self.r = None  # 连接失败时设置为 None，避免后续操作报错
-
-    def _get_key(self, user_id: str) -> str:
-        """生成用户历史记录的 Redis 键名。"""
-        return f"{self.key_prefix}{user_id}"
-
-    def _message_to_json(self, message: Message) -> str:
-        """将 Message 对象序列化为 JSON 字符串以便存储。"""
-        return message.model_dump_json()
-
-    def _json_to_message(self, data: str) -> Message:
-        """将 JSON 字符串反序列化回 Message 对象。"""
-        try:
-            return Message.model_validate_json(data)
-        except Exception as e:
-            logger.error(f"Error deserializing message data: {data[:50]}... Error: {e}")
-            return Message(role=Role.ASSISTANT, content="[Deserialization Error]")
-
-    def save_message(self, user_id: str, message: Message):
-        """将单条消息保存到用户历史记录列表的末尾。"""
-        if not self.r:
-            return
-
-        message_json = self._message_to_json(message)
-        # RPUSH：将元素添加到列表的尾部
-        self.r.rpush(self._get_key(user_id), message_json)
-
-    def get_history(self, user_id: str) -> List[Message]:
-        """检索用户的完整会话历史记录。"""
-        if not self.r:
-            return []
-
-        # LRANGE：获取列表的所有元素 (0 到 -1)
-        raw_history = self.r.lrange(self._get_key(user_id), 0, -1)
-
-        # 将 JSON 字符串列表转换为 Message 对象列表
-        messages = [self._json_to_message(data) for data in raw_history]
-        return messages
-
-    def clear_history(self, user_id: str):
-        """删除用户的完整历史记录。"""
-        if self.r:
-            self.r.delete(self._get_key(user_id))
-            logger.info(f"History cleared for {user_id}")

app/core/stylist_agent.py

@@ -1,302 +0,0 @@
-import json
-import os
-import random
-import uuid
-from typing import List, Dict, Any, Optional
-
-from google import genai
-
-from app.core.utils import merge_images_to_square
-
-
-class AsyncStylistAgent:
-    CATEGORY_SET = {'Activewear', 'Watches', 'Shopping Totes', 'Underwear', 'Sunglasses', 'Dresses', 'Outerwear', 'Handbags', 'Backpacks', 'Belts', 'Hats', 'Skirts', 'Swimwear', 'Jewelry', 'Briefcases', 'Socks', 'Neckties', 'Pants', 'Suits', 'Shoes', 'Shirts & Tops', 'Scarves & Shawls'}
-
-    def __init__(self, local_db, max_len: int, outfits_root: str, image_dir: str, stylist_guide_dir: str, gemini_model_name: str):
-        # self.outfit_items: List[Dict[str, str]] = []
-        self.outfit_id = str(uuid.uuid4())
-        self.gemini_client = genai.Client(
-            vertexai=True, project='aida-461108', location='us-central1'
-        )
-        self.local_db = local_db
-        self.max_len = max_len
-        self.output_outfit_path = os.path.join(outfits_root, f"{self.outfit_id}.jpg")
-        self.output_json_path = os.path.join(outfits_root, f"{self.outfit_id}_items.json")
-        self.image_dir = image_dir
-        self.stylist_guide_dir = stylist_guide_dir
-        self.gemini_model_name = gemini_model_name
-        self.stop_reason = ""
-        
-    def _load_style_guide(self, path: str) -> str:
-        """加载 markdown 风格指南内容。"""
-        try:
-            with open(path, 'r', encoding='utf-8') as f:
-                return f.read()
-        except Exception as e:
-            raise FileNotFoundError(f"Failed to load style guide from {path}: {e}")
-
-    def _build_system_prompt(self, request_summary: str = "") -> str:
-        """Constructs the complete System Prompt."""
-        # Insert the style_guide content into the template
-        template = f"""
-        You are a professional fashion stylist Agent, specialized in creating complete outfits for the user.
-
-        Your task is to **create a cohesive and complete outfit**, strictly adhering to **BOTH** the user's explicit **Request Summary** and the **Outfit Style Guide**. You must decide the next logical item to add to the outfit based on the currently selected items (if any).
-
-        ---
-
-        ## Request from the User:
-
-        {request_summary}
-
-        ## Core Guidance Document: Outfit Style Guide
-
-        {self.style_guide}
-
-        ---
-
-        ## Your Workflow and Constraints
-
-        1.  **Style Adherence**: You must strictly observe all rules in the Style Guide concerning **color palette, fit, layering principles, pattern restrictions, accessory stacking, and shoe/bag coordination**.
-        2.  **Step Planning**: The styling sequence must follow a **top-down, inside-out** approach: First major garments (tops/outerwear/bottoms/dresses), then shoes and bags, and finally accessories.
-        3.  **Structured Output**: Every response must recommend the **next single item**. You must strictly use the **JSON format** for your output, as follows:
-
-        ```json
-        {{
-        "action": "recommend_item",
-        "category": "YOUR_ITEM_CATEGORY",
-        "description": "YOUR_DETAILED_DESCRIPTION"
-        }}
-        ```
-
-        * `action`: Must always be `"recommend_item"` until the outfit is complete.
-        * `category`: Must be the category of the item you are recommending, strictly selected from the following list: {list(self.CATEGORY_SET)}.
-        * `description`: This must be an **extremely detailed and precise** description of the item. This description is used for **high-accuracy vector search** in the database and must include:
-            * **Color** (e.g., milk tea, pure white, dark gray)
-            * **Fit/Silhouette** (e.g., Oversize, loose, slim-fit)
-            * **Material/Detail** (e.g., 100% cotton, linen, gold clasp, thin stripe, checkered pattern)
-            * **Role in the Outfit** (e.g., serves as the innermost base layer for layering; acts as the crucial tie accent for the smart casual look)
-            * **[CRITICAL FOR JEWELRY] If recommending 'Jewelry' (especially Necklaces), the description must specify its distinction (length, thickness, pendant style) from all previously selected necklaces to ensure layered variety.**
-
-        4.  **Termination Condition**: Only when you deem the entire outfit complete and **all mandatory elements stipulated in the Style Guide are met**, you must output the following JSON format to terminate the process:
-
-        ```json
-        {{
-        "action": "stop",
-        "reason": "OUTFIT_COMPLETE_AND_MEETS_ALL_MINI_GUIDELINES"
-        }}
-        ```
-        Normally, five or six items are totally enough for an outfit.
-
-        5.  **Context Dependency**: The user's next input (if not `Start`) will contain the **image and description of the selected item**. When recommending the next item, you must consider the coordination between the **already selected items** and the Style Guide.
-
-        **Now, please start building an outfit and output the JSON for the first item.**
-        """
-        return template.strip()
-    
-    def _clear_uploaded_files(self):
-        for f in self.gemini_client.files.list():
-            self.gemini_client.files.delete(name=f.name)
-    
-    async def _call_gemini(self, user_input: str) -> str:
-        """
-        实际调用 Gemini API 的函数，接受文本和可选的图片路径列表。
-        
-        Args:
-            user_input: 发送给模型的主文本内容。
-            image_paths: 待发送图片的本地路径列表。
-            
-        Returns:
-            模型的响应文本（预期为 JSON 字符串）。
-        """
-        content_parts = []
-        # self._clear_uploaded_files()
-        # 1. 添加图片内容
-        # if self.outfit_items:
-        #     merged_image_path = merge_images_to_square(self.outfit_items, max_len=self.max_len, output_path=self.output_outfit_path)
-        #     try:
-        #         myfile = await self.gemini_client.aio.files.upload(file=merged_image_path)
-        #         content_parts.append(myfile)
-        #     except Exception as e:
-        #         print(f"Error loading image {merged_image_path}: {e}")
-        
-        # 2. 添加文本内容
-        content_parts.append(user_input)
-        
-        # print(f"\n--- Calling Gemini with {len(self.outfit_items) if self.outfit_items else 0} images and query:\n{user_input}")
-
-        try:
-            # 3. 实际 API 调用
-            response = await self.gemini_client.aio.models.generate_content(
-                model=self.gemini_model_name,
-                contents=content_parts,
-                config={
-                    "system_instruction": self.system_prompt,
-                    # 确保模型返回 JSON 格式
-                    "response_mime_type": "application/json",
-                    "response_schema": {
-                        "type": "object",
-                        "properties": {
-                            "action": {"type": "string", "enum": ["recommend_item", "stop"]},
-                            "category": {"type": "string"},
-                            "description": {"type": "string"},
-                            "reason": {"type": "string"}
-                        },
-                        "required": ["action"]
-                    }
-                }
-            )
-            
-            # response.text 将包含一个 JSON 字符串
-            return response.text
-        
-        except Exception as e:
-            print(f"Gemini API Call failed: {e}")
-            # 返回一个停止信号以防止循环继续
-            return json.dumps({"action": "stop", "reason": f"API_ERROR: {str(e)}"})
-
-    def _parse_gemini_response(self, response_text: str) -> Optional[Dict[str, Any]]:
-        """安全解析 Gemini 的 JSON 响应。"""
-        try:
-            # 有时 Gemini 可能会在 JSON 外面添加文字,尝试清理
-            response_text = response_text.strip().replace('```json', '').replace('```', '')
-            data = json.loads(response_text)
-            print(f"The agent response is: {data}")
-            return data
-        except json.JSONDecodeError as e:
-            print(f"Error parsing JSON from Gemini: {e}")
-            print(f"Raw response: {response_text}")
-            return None
-
-    def _get_next_item(self, item_description: str, category: str) -> Optional[Dict[str, str]]:
-        """
-        1. 根据描述生成嵌入。
-        2. 查询本地数据库以找到最佳匹配项。
-        3. 模拟 Agent 审核匹配项(这里简化为总是通过)。
-        """
-        try:
-            # 1. 生成查询嵌入
-            query_embedding = self.local_db.get_clip_embedding(item_description, is_image=False)
-            
-            # 2. 执行查询,并过滤类别
-            results = self.local_db.query_local_db(query_embedding, category, n_results=1)
-            
-            if not results:
-                print(f"❌ 数据库中未找到符合 '{category}' 和描述的单品。")
-                return None
-            
-            # 3. 模拟 Agent 审核(实际应用中,你需要将图片发回给 Agent进行审核)
-            best_meta = results['metadatas'][0][0] # 第一个 batch 的第一个 metadata
-            return {
-                "item_id": best_meta['item_id'], # 从 metadata 字典中安全获取
-                "category": category,
-                "gpt_description": item_description,
-                'description': best_meta['description'],
-                # 假设 'item_path' 存储在 metadata 中，或从 'item_id' 推导
-                # 这里假设 item_id 就是文件名的一部分
-                "image_path": os.path.join(self.image_dir, f"{best_meta['item_id']}.jpg") 
-            }
-
-        except Exception as e:
-            print(f"An error occurred during item retrieval: {e}")
-            return None
-
-    def _build_user_input(self) -> str:
-        """构建发送给 Gemini 的用户输入,包含已选单品信息。"""
-        if not self.outfit_items:
-            return "Start"
-        
-        # 将已选单品的信息作为上下文发回给 Agent
-        context = "Selected fashion items:\n"
-        for ii, item in enumerate(self.outfit_items):
-            context += f"{ii + 1}. Category: {item['category']}. Description: {item['description']}\n"
-        context += "\nPlease recommend the next single item based on the selected items, user's request, and style guide."
-        return context
-
-    async def run_styling_process(self, request_summary, stylist_name, start_outfit=[]):
-        self.outfit_items = start_outfit if start_outfit else []
-        """主流程控制循环。"""
-        print(f"--- Starting Agent (Outfit ID: {self.outfit_id}) ---")
-
-        self.style_guide = self._load_style_guide(os.path.join(self.stylist_guide_dir, f"{stylist_name}_en.md"))
-        self.system_prompt = self._build_system_prompt(request_summary)
-
-        while True:
-            # 1. 准备用户输入(上下文)
-            user_input = self._build_user_input()
-            
-            # 2. 调用 Gemini Agent
-            gemini_response_text = await self._call_gemini(user_input)
-            gemini_data = self._parse_gemini_response(gemini_response_text)
-
-            if not gemini_data:
-                print("🚨 Agent 返回无效响应,终止流程。")
-                self.stop_reason = "Agent failed to return response"
-                break
-
-            # 3. 检查终止条件
-            if gemini_data.get('action') == 'stop':
-                print(f"🛑 搭配完成,终止原因: {gemini_data.get('reason')}")
-                self.stop_reason = "Finish reason: " + gemini_data.get('reason', 'No reason provided')
-                break
-
-            # 4. 处理推荐单品
-            if gemini_data.get('action') == 'recommend_item':
-                category = gemini_data.get('category')
-                description = gemini_data.get('description')
-
-                # 4a. 检查类别是否有效 (重要步骤)
-                if category not in self.CATEGORY_SET:
-                    print(f"❌ Agent 推荐了无效类别: {category}。要求 Agent 重新输出。")
-                    # 在实际应用中,这里需要将错误信息发回给 Agent,要求它更正
-                    # 这里简化为跳过本次循环
-                    continue
-                
-                # 4b. 在本地 DB 中查询单品
-                new_item = self._get_next_item(description, category)
-
-                if new_item:
-                    # 4c. (实际步骤) 将选中的单品图片和描述发回给 Agent 进行最终审核
-                    # 这里的代码框架省略了图片回传和二次审核的步骤,直接视为通过
-                    # 实际你需要： new_user_input = f"Check this item: {new_item['description']}, path: {new_item['image_path']}"
-                    #              call_gemini_agent(...) -> 如果返回"pass",则添加到outfit_items
-
-                    if new_item['item_id'] in [x['item_id'] for x in self.outfit_items]:
-                        print("This item exists. Stop here.")
-                        self.stop_reason = "Finish reason: Duplicate item selected."
-                        break
-
-                    if new_item['item_id'] == "ELG383":
-                        if random.random() < 0.70:
-                            self.stop_reason = "Finish reason: ELG383 is seleced repeatly."
-                            break
-                    
-                    self.outfit_items.append(new_item)
-                    print(f"➕ 成功添加单品: {new_item['category']} ({new_item['item_id']}). 当前搭配数量: {len(self.outfit_items)}")
-                    
-                else:
-                    print("⚠️ 未找到匹配单品,无法继续搭配。终止。")
-                    self.stop_reason = "Finish reason: No matching item found in local database."
-                    break
-
-            if len(self.outfit_items) >= self.max_len: # 设置一个最大循环限制,防止无限循环
-                 print("🚨 达到最大搭配数量限制,强制终止。")
-                 self.stop_reason = "Finish reason: Reached max outfit length."
-                 break
-
-        # 5. 流程结束后保存结果
-        self._save_outfit_results()
-        return self.output_outfit_path
-        
-    def _save_outfit_results(self):
-        """保存最终的 JSON 列表和图片到指定文件夹。"""
-        if not self.outfit_items:
-            raise ValueError("No outfit items to save.")
-        
-        # 1. 保存 JSON 文件
-        results_list = [{'item_id': item['item_id'], 'category': item['category'], 'description': item['description'], 'gpt_description': item['gpt_description']} for item in self.outfit_items]
-        results_list.append({'stop_reason': self.stop_reason})
-        with open(self.output_json_path, 'w', encoding='utf-8') as f:
-            json.dump(results_list, f, ensure_ascii=False, indent=4)
-
-        merge_images_to_square(self.outfit_items, max_len=self.max_len, output_path=self.output_outfit_path, add_text=False)

app/core/stylist_agent_server.py

@@ -1,435 +0,0 @@
-import asyncio
-import io
-import json
-import logging
-import os
-import random
-import uuid
-from typing import List, Dict, Any, Optional
-
-from google import genai
-from google.cloud import storage
-from google.oauth2 import service_account
-
-from app.core.utils_litserve import merge_images_to_square
-from app.server.utils.minio_client import minio_client, oss_upload_image
-from app.server.utils.request_post import post_request
-
-logger = logging.getLogger(__name__)
-
-
-class AsyncStylistAgent:
-    CATEGORY_SET = {'Activewear', 'Watches', 'Shopping Totes', 'Underwear', 'Sunglasses', 'Dresses', 'Outerwear', 'Handbags', 'Backpacks', 'Belts', 'Hats', 'Skirts', 'Swimwear', 'Jewelry', 'Briefcases', 'Socks', 'Neckties', 'Pants', 'Suits', 'Shoes', 'Shirts & Tops', 'Scarves & Shawls'}
-
-    def __init__(self, local_db, max_len: int, gemini_model_name: str, outfit_id=str):
-        # self.outfit_items: List[Dict[str, str]] = []
-        self.outfit_id = outfit_id
-        self.gemini_client = genai.Client(
-            vertexai=True, project='aida-461108', location='us-central1'
-        )
-        self.local_db = local_db
-        self.max_len = max_len
-        self.gemini_model_name = gemini_model_name
-        self.stop_reason = ""
-
-        # 存储桶配置
-        try:
-            # TODO 目前写死路径 生产环境切换路径
-            self.credentials = service_account.Credentials.from_service_account_file(os.getenv("GOOGLE_APPLICATION_CREDENTIALS"))
-        except Exception as e:
-            # 这里的异常处理应根据实际情况调整
-            raise RuntimeError(f"Failed to load credentials from file {os.getenv('GOOGLE_APPLICATION_CREDENTIALS')}: {e}")
-
-        self.gcs_client = storage.Client(
-            project=self.credentials.project_id,
-            credentials=self.credentials
-        )
-        self.gcs_bucket = "lc_stylist_agent_outfit_items"
-        self.minio_bucket = "lanecarford"
-
-    def _load_style_guide(self, path: str) -> str:
-        """加载 markdown 风格指南内容。"""
-        parts = path.split('/', 1)
-        if len(parts) != 2:
-            raise ValueError("MinIO path must be in 'bucket_name/object_name' format.")
-
-        bucket_name, object_name = parts
-        try:
-            # 1. 获取对象
-            response = minio_client.get_object(bucket_name, object_name)
-
-            # 2. 读取内容
-            content_bytes = response.read()
-
-            # 3. 关闭连接
-            response.close()
-            response.release_conn()
-
-            # 4. 解码并返回
-            return content_bytes.decode('utf-8')
-
-        except Exception as e:
-            raise Exception(f"Failed to load style guide from {path}: {e}")
-
-    def _build_system_prompt(self, request_summary: str = "") -> str:
-        """Constructs the complete System Prompt."""
-        # Insert the style_guide content into the template
-        template = f"""
-        You are a professional fashion stylist Agent, specialized in creating complete outfits for the user.
-
-        Your task is to **create a cohesive and complete outfit**, strictly adhering to **BOTH** the user's explicit **Request Summary** and the **Outfit Style Guide**. You must decide the next logical item to add to the outfit based on the currently selected items (if any).
-
-        ---
-
-        ## Request from the User:
-
-        {request_summary}
-
-        ## Core Guidance Document: Outfit Style Guide
-
-        {self.style_guide}
-
-        ---
-
-        ## Your Workflow and Constraints
-
-        1.  **Style Adherence**: You must strictly observe all rules in the Style Guide concerning **color palette, fit, layering principles, pattern restrictions, accessory stacking, and shoe/bag coordination**.
-        2.  **Step Planning**: The styling sequence must follow a **top-down, inside-out** approach: First major garments (tops/outerwear/bottoms/dresses), then shoes and bags, and finally accessories.
-        3.  **Structured Output**: Every response must recommend the **next single item**. You must strictly use the **JSON format** for your output, as follows:
-
-        ```json
-        {{
-        "action": "recommend_item",
-        "category": "YOUR_ITEM_CATEGORY",
-        "description": "YOUR_DETAILED_DESCRIPTION"
-        }}
-        ```
-
-        * `action`: Must always be `"recommend_item"` until the outfit is complete.
-        * `category`: Must be the category of the item you are recommending, strictly selected from the following list: {list(self.CATEGORY_SET)}.
-        * `description`: This must be an **extremely detailed and precise** description of the item. This description is used for **high-accuracy vector search** in the database and must include:
-            * **Color** (e.g., milk tea, pure white, dark gray)
-            * **Fit/Silhouette** (e.g., Oversize, loose, slim-fit)
-            * **Material/Detail** (e.g., 100% cotton, linen, gold clasp, thin stripe, checkered pattern)
-            * **Role in the Outfit** (e.g., serves as the innermost base layer for layering; acts as the crucial tie accent for the smart casual look)
-            * **[CRITICAL FOR JEWELRY] If recommending 'Jewelry' (especially Necklaces), the description must specify its distinction (length, thickness, pendant style) from all previously selected necklaces to ensure layered variety.**
-
-        4.  **Termination Condition**: Only when you deem the entire outfit complete and **all mandatory elements stipulated in the Style Guide are met**, you must output the following JSON format to terminate the process:
-
-        ```json
-        {{
-        "action": "stop",
-        "reason": "OUTFIT_COMPLETE_AND_MEETS_ALL_MINI_GUIDELINES"
-        }}
-        ```
-        Normally, five or six items are totally enough for an outfit.
-
-        5.  **Context Dependency**: The user's next input (if not `Start`) will contain the **image and description of the selected item**. When recommending the next item, you must consider the coordination between the **already selected items** and the Style Guide.
-
-        **Now, please start building an outfit and output the JSON for the first item.**
-        """
-        return template.strip()
-
-    def _clear_uploaded_files(self):
-        for f in self.gemini_client.files.list():
-            self.gemini_client.files.delete(name=f.name)
-
-    async def _call_gemini(self, user_input: str, user_id: str):
-        """
-        实际调用 Gemini API 的函数，接受文本和可选的图片路径列表。
-        
-        Args:
-            user_input: 发送给模型的主文本内容。
-            image_paths: 待发送图片的本地路径列表。
-            
-        Returns:
-            模型的响应文本（预期为 JSON 字符串）。
-        """
-        minio_path = ""
-        content_parts = []
-        # self._clear_uploaded_files()
-        # 1. 添加图片内容
-        if self.outfit_items:
-            merged_image = merge_images_to_square(self.outfit_items, max_len=self.max_len, add_text=False)
-            image_bytes_io = io.BytesIO()
-            image_format = 'JPEG'
-            mime_type = 'image/jpeg'
-
-            merged_image.save(image_bytes_io, format=image_format)
-            image_bytes = image_bytes_io.getvalue()
-
-            file_name = uuid.uuid4()
-            blob_name = f"lc_stylist_agent_outfit_items/{user_id}/{file_name}.jpg"
-            gcs_path = self._upload_to_gcs(bucket_name=self.gcs_bucket, blob_name=blob_name, mime_type=mime_type, image_bytes=image_bytes)
-            responses = oss_upload_image(oss_client=minio_client, bucket=self.minio_bucket, object_name=blob_name, image_bytes=image_bytes)
-            minio_path = f"{responses.bucket_name}/{responses.object_name}"
-            content_parts.append(gcs_path)
-
-        # 2. 添加文本内容
-        content_parts.append(user_input)
-
-        # print(f"\n--- Calling Gemini with {len(self.outfit_items) if self.outfit_items else 0} images and query:\n{user_input}")
-
-        try:
-            # 3. 实际 API 调用
-            response = await self.gemini_client.aio.models.generate_content(
-                model=self.gemini_model_name,
-                contents=content_parts,
-                config={
-                    "system_instruction": self.system_prompt,
-                    # 确保模型返回 JSON 格式
-                    "response_mime_type": "application/json",
-                    "response_schema": {
-                        "type": "object",
-                        "properties": {
-                            "action": {"type": "string", "enum": ["recommend_item", "stop"]},
-                            "category": {"type": "string"},
-                            "description": {"type": "string"},
-                            "reason": {"type": "string"}
-                        },
-                        "required": ["action"]
-                    }
-                }
-            )
-
-            # response.text 将包含一个 JSON 字符串
-            return response.text, minio_path
-
-        except Exception as e:
-            print(f"Gemini API Call failed: {e}")
-            # 返回一个停止信号以防止循环继续
-            return json.dumps({"action": "stop", "reason": f"API_ERROR: {str(e)}"})
-
-    def _parse_gemini_response(self, response_text: str) -> Optional[Dict[str, Any]]:
-        """安全解析 Gemini 的 JSON 响应。"""
-        try:
-            # 有时 Gemini 可能会在 JSON 外面添加文字,尝试清理
-            response_text = response_text.strip().replace('```json', '').replace('```', '')
-            data = json.loads(response_text)
-            # print(f"The agent response is: {data}")
-            return data
-        except json.JSONDecodeError as e:
-            print(f"Error parsing JSON from Gemini: {e}")
-            print(f"Raw response: {response_text}")
-            return None
-
-    def _get_next_item(self, item_description: str, category: str) -> Optional[Dict[str, str]]:
-        """
-        1. 根据描述生成嵌入。
-        2. 查询本地数据库以找到最佳匹配项。
-        3. 模拟 Agent 审核匹配项(这里简化为总是通过)。
-        """
-        try:
-            # 1. 生成查询嵌入
-            query_embedding = self.local_db.get_clip_embedding(item_description, is_image=False)
-
-            # 2. 执行查询,并过滤类别
-            results = self.local_db.query_local_db(query_embedding, category, n_results=1)
-
-            if not results:
-                print(f"❌ 数据库中未找到符合 '{category}' 和描述的单品。")
-                return None
-
-            # 3. 模拟 Agent 审核(实际应用中,你需要将图片发回给 Agent进行审核)
-            best_meta = results['metadatas'][0][0]  # 第一个 batch 的第一个 metadata
-            return {
-                "item_id": best_meta['item_id'],  # 从 metadata 字典中安全获取
-                "category": category,
-                "gpt_description": item_description,
-                'description': best_meta['description'],
-                # 假设 'item_path' 存储在 metadata 中，或从 'item_id' 推导
-                # 这里假设 item_id 就是文件名的一部分
-                "image_path": os.path.join(f"{best_meta['item_id']}.jpg")
-            }
-
-        except Exception as e:
-            print(f"An error occurred during item retrieval: {e}")
-            return None
-
-    def _build_user_input(self) -> str:
-        """构建发送给 Gemini 的用户输入,包含已选单品信息。"""
-        if not self.outfit_items:
-            return "Start"
-
-        # 将已选单品的信息作为上下文发回给 Agent
-        context = "Selected fashion items:\n"
-        for ii, item in enumerate(self.outfit_items):
-            context += f"{ii + 1}. Category: {item['category']}. Description: {item['description']}\n"
-        context += "\nPlease recommend the next single item based on the selected items, user's request, and style guide."
-        return context
-
-    async def run_styling_process(self, request_summary, stylist_path, start_outfit=None, user_id="test", callback_url=""):
-        if start_outfit is None:
-            start_outfit = []
-        self.outfit_items = start_outfit if start_outfit else []
-        """主流程控制循环。"""
-        print(f"--- Starting Agent (Outfit ID: {self.outfit_id}) ---")
-
-        self.style_guide = self._load_style_guide(stylist_path)
-        self.system_prompt = self._build_system_prompt(request_summary)
-        response_data = {"status": "",
-                         "message": "",
-                         "path": "",
-                         "outfit_id": self.outfit_id,
-                         "items": []
-                         }
-        logger.info(response_data)
-        item_id = ""
-        item_category = ""
-        while True:
-            # 1. 准备用户输入(上下文)
-            user_input = self._build_user_input()
-
-            # 2. 调用 Gemini Agent
-            gemini_response_text, minio_path = await self._call_gemini(user_input, user_id)
-            gemini_data = self._parse_gemini_response(gemini_response_text)
-            response_data['path'] = minio_path
-            if item_id:
-                response_data['items'].append({"item_id": item_id, "category": item_category})
-            if not gemini_data:
-                print("🚨 Agent 返回无效响应,终止流程。")
-                self.stop_reason = "Agent failed to return response"
-                response_data['status'] = "failed"
-                response_data['message'] = self.stop_reason
-                break
-
-            # 3. 检查终止条件
-            if gemini_data.get('action') == 'stop':
-                print(f"🛑 搭配完成,终止原因: {gemini_data.get('reason')}")
-                self.stop_reason = "Finish reason: " + gemini_data.get('reason', 'No reason provided')
-                response_data['status'] = "stop"
-                response_data['message'] = self.stop_reason
-
-            # 4. 处理推荐单品
-            if gemini_data.get('action') == 'recommend_item':
-                category = gemini_data.get('category')
-                description = gemini_data.get('description')
-
-                # 4a. 检查类别是否有效 (重要步骤)
-                if category not in self.CATEGORY_SET:
-                    print(f"❌ Agent 推荐了无效类别: {category}。要求 Agent 重新输出。")
-                    # 在实际应用中,这里需要将错误信息发回给 Agent,要求它更正
-                    # 这里简化为跳过本次循环
-                    response_data['status'] = "continue"
-                    response_data['message'] = f"❌ Agent 推荐了无效类别: {category}。要求 Agent 重新输出。",
-                    continue
-
-                # 4b. 在本地 DB 中查询单品
-                new_item = self._get_next_item(description, category)
-                item_id = new_item.get('item_id')
-                item_category = new_item.get('category')
-
-                if new_item:
-                    # 4c. (实际步骤) 将选中的单品图片和描述发回给 Agent 进行最终审核
-                    # 这里的代码框架省略了图片回传和二次审核的步骤,直接视为通过
-                    # 实际你需要： new_user_input = f"Check this item: {new_item['description']}, path: {new_item['image_path']}"
-                    #              call_gemini_agent(...) -> 如果返回"pass",则添加到outfit_items
-
-                    if new_item['item_id'] in [x['item_id'] for x in self.outfit_items]:
-                        print("This item exists. Stop here.")
-                        self.stop_reason = "Finish reason: Duplicate item selected."
-                        response_data['status'] = "stop"
-                        response_data['message'] = self.stop_reason
-                        break
-
-                    if new_item['item_id'] == "ELG383":
-                        if random.random() < 0.70:
-                            self.stop_reason = "Finish reason: ELG383 is seleced repeatly."
-                            response_data['status'] = "stop"
-                            response_data['message'] = self.stop_reason
-                            break
-
-                    self.outfit_items.append(new_item)
-                    # print(f"➕ 成功添加单品: {new_item['category']} ({new_item['item_id']}). 当前搭配数量: {len(self.outfit_items)}")
-                    response_data['status'] = "ok"
-                    response_data['message'] = self.stop_reason
-                else:
-                    print("⚠️ 未找到匹配单品,无法继续搭配。终止。")
-                    self.stop_reason = "Finish reason: No matching item found in local database."
-                    response_data['status'] = "stop"
-                    response_data['message'] = self.stop_reason
-                    break
-
-            if len(self.outfit_items) >= self.max_len:  # 设置一个最大循环限制,防止无限循环
-                logger.info("🚨 达到最大搭配数量限制,强制终止。")
-                self.stop_reason = "Finish reason: Reached max outfit length."
-                response_data['status'] = "stop"
-                response_data['message'] = self.stop_reason
-
-            logger.info(f"request data ：{response_data}")
-            headers = {
-                'Accept': "*/*",
-                'Accept-Encoding': "gzip, deflate, br",
-                'User-Agent': "PostmanRuntime-ApipostRuntime/1.1.0",
-                'Connection': "keep-alive",
-                'Content-Type': "application/json"
-            }
-            url = f'{callback_url}/api/style/callback'
-            response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-            logger.info(response.text)
-        return response_data
-
-    # def _save_outfit_results(self, user_id):
-    #     """保存最终的 JSON 列表和图片到指定文件夹。"""
-    #     if not self.outfit_items:
-    #         raise ValueError("No outfit items to save.")
-    #
-    #     # 1. 保存 JSON 文件
-    #     results_list = [{'item_id': item['item_id'], 'category': item['category'], 'description': item['description'], 'gpt_description': item['gpt_description']} for item in self.outfit_items]
-    #     results_list.append({'stop_reason': self.stop_reason})
-    #
-    #     return upload_json_to_minio_sync(
-    #         minio_client=minio_client,
-    #         bucket_name=f"lanecarford",
-    #         object_name=f"lc_stylist_agent_outfit_items/{user_id}/{uuid.uuid4()}.json",
-    #         data=results_list
-    #     )
-
-    def _upload_to_gcs(self, bucket_name: str, blob_name: str, mime_type, image_bytes) -> str:
-        """同步方法：将文件上传到 GCS 并返回 GCS URI。"""
-        bucket = self.gcs_client.bucket(bucket_name)
-        blob = bucket.blob(blob_name)
-        blob.upload_from_string(
-            data=image_bytes,
-            content_type=mime_type
-        )
-
-        gcs_uri = f"gs://{bucket_name}/{blob_name}"
-        return gcs_uri
-
-    async def recommend_outfit(self, request_summary: str, stylist_name: str, start_outfit: List[Dict[str, str]] = [], num_outfits: int = 1):
-        """
-                基于用户的对话历史和需求，推荐一套搭配。
-
-                Args:
-                    request_summary: 用户的request
-                    start_outfit: 可选的初始搭配列表，每个元素包含 'item_id' 和 'category'。
-                """
-        tasks = []
-        for _ in range(num_outfits):
-            agent = AsyncStylistAgent(**self.stylist_agent_kwages)
-            task = agent.run_styling_process(request_summary, stylist_name, start_outfit)
-            tasks.append(task)
-        print(f"--- Starting {num_outfits} concurrent outfit generation tasks. ---")
-
-        try:
-            results = await asyncio.gather(*tasks, return_exceptions=True)
-
-            successful_outfits = []
-            failed_outfits = []
-            for result in results:
-                if isinstance(result, Exception):
-                    # 任务执行中发生异常
-                    failed_outfits.append(f"Failed: {result}")
-                else:
-                    # 任务成功，result 是 run_styling_process 返回的图片路径
-                    successful_outfits.append(result)
-
-            return {
-                "successful_outfits": successful_outfits,
-                "failed_outfits": failed_outfits
-            }
-
-        except Exception as e:
-            print(f"An unexpected error occurred during concurrent recommendation: {e}")
-            return {"error": str(e)}

app/core/system_prompt.py

@@ -1,56 +0,0 @@
-BASIC_PROMPT = """"""
-WOMEN_BASIC_PROMPT = """You are a professional, friendly, and insightful AI women's styling assistant.
-
-Your primary mission is to engage in a multi-turn conversation with the user to fully understand their dressing intent. You must adopt a professional yet approachable tone.
-
-CONVERSATION GOALS:
-1.  **Occasion:** Determine the specific event (e.g., romantic dinner, summer wedding, business meeting).
-2.  **Style:** Pinpoint the desired aesthetic (e.g., classic elegance, edgy, minimalist, bohemian).
-3.  **Vibe/Details:** Gather any mood or specific constraints (e.g., needs to be comfortable, requires light colors, no bare shoulders).
-4.  **Item Preference:** Ask the user if they have any specific preferences for an item type or silhouette (e.g., preference for a dress, skirt, tailored pants, or a particular neckline/length).
-
-GUIDANCE FOR RESPONSE GENERATION:
--   After the user's initial request (e.g., "I want a chic outfit for dinner."), immediately reply with a friendly, targeted follow-up question to elicit the most crucial missing information (usually a combination of **Occasion** and **Style**).
--   Be concise. Ask only 1 to 2 essential questions per turn.
--   You must gather sufficient, clear intent before proceeding to actual clothing recommendations.
-
-OUTPUT FORMAT INSTRUCTION:
--   **DO NOT** use any Markdown formatting whatsoever (e.g., do not use asterisks (*), bold text (**), lists, or code blocks).
--   **ONLY** output the plain text response spoken by the AI Assistant.
-
-Example Follow-up (mimicking a conversational flow):
-User: I want a chic outfit for dinner.
-Your Response: Hey there! A chic dinner outfit, I love that! To give you the perfect recommendations, tell me: is this a romantic date, business dinner, or celebration with friends? And what's your go-to style vibe: classic elegance or something with more edge?"""
-MEN_BASIC_PROMPT = """You are a professional, friendly, and insightful AI men's styling assistant.
-
-Your primary mission is to engage in a multi-turn conversation with the user to fully understand their dressing intent. You must adopt a professional yet approachable tone.
-
-CONVERSATION GOALS:
-1.  **Occasion:** Determine the specific event (e.g., romantic dinner, summer wedding, business meeting).
-2.  **Style:** Pinpoint the desired aesthetic (e.g., classic elegance, edgy, minimalist, bohemian).
-3.  **Vibe/Details:** Gather any mood or specific constraints (e.g., needs to be comfortable, requires light colors, no bare shoulders).
-4.  **Item Preference:** Ask the user if they have any specific preferences for an item type or silhouette (e.g., preference for a dress, skirt, tailored pants, or a particular neckline/length).
-
-GUIDANCE FOR RESPONSE GENERATION:
--   After the user's initial request (e.g., "I want a chic outfit for dinner."), immediately reply with a friendly, targeted follow-up question to elicit the most crucial missing information (usually a combination of **Occasion** and **Style**).
--   Be concise. Ask only 1 to 2 essential questions per turn.
--   You must gather sufficient, clear intent before proceeding to actual clothing recommendations.
-
-OUTPUT FORMAT INSTRUCTION:
--   **DO NOT** use any Markdown formatting whatsoever (e.g., do not use asterisks (*), bold text (**), lists, or code blocks).
--   **ONLY** output the plain text response spoken by the AI Assistant.
-
-Example Follow-up (mimicking a conversational flow):
-User: I want a chic outfit for dinner.
-Your Response: Hey there! A chic dinner outfit, I love that! To give you the perfect recommendations, tell me: is this a romantic date, business dinner, or celebration with friends? And what's your go-to style vibe: classic elegance or something with more edge?"""
-
-SUMMARY_PROMPT = """Analyze the following chat history. Your task is to extract all user intentions, scenarios, style preferences, and constraints expressed during the conversation, and distill them into a concise, structured JSON object.
-
-**YOUR OUTPUT MUST BE A JSON OBJECT ONLY, WITH NO SURROUNDING TEXT, MARKDOWN, OR EXPLANATION.**
-
-JSON FIELD REQUIREMENTS:
--   **occasion (string):** The specific event and purpose (e.g., "Romantic date dinner", "Summer outdoor wedding", "Casual Friday at office").
--   **style (string):** The overall aesthetic description (e.g., "Classic elegance", "Modern minimalist", "Bohemian vibe", "Edgy and contemporary").
--   **color_preference (string or list):** User's preferred or excluded colors/tones (e.g., "Light colors only", "Avoid deep shades", "['Cream', 'Pale Blue']", "No preference").
--   **clothing_type (string):** User's preference for specific garment types, material, or silhouette (e.g., "Lightweight maxi dress", "Skirt with silk blouse", "Tailored wide-leg pants", "Floral print").
--   **vibe_or_details (string):** Any other details, mood requirements, or specific constraints (e.g., "Needs to be comfortable and breathable", "Accent on accessories", "Must cover shoulders")."""

app/core/utils.py

@@ -1,160 +0,0 @@
-from typing import List, Dict
-import shutil
-
-from PIL import Image, ImageDraw, ImageFont
-
-# 9个 341x341 左右的单元格 (ALL_9_CELLS)
-# 布局顺序: 从上到下，从左到右 (1 -> 9)
-ALL_9_CELLS = [
-    # Top Row (Y=0, H=341)
-    (0, 0, 341, 341),  # 1. Top-Left (341x341)
-    (341, 0, 341, 341),  # 2. Top-Middle (341x341)
-    (682, 0, 342, 341),  # 3. Top-Right (342x341)
-    # Middle Row (Y=341, H=341)
-    (0, 341, 341, 341),  # 4. Mid-Left (341x341)
-    (341, 341, 341, 341),  # 5. Center (341x341)
-    (682, 341, 342, 341),  # 6. Mid-Right (342x341)
-    # Bottom Row (Y=682, H=342)
-    (0, 682, 341, 342),  # 7. Bottom-Left (341x342)
-    (341, 682, 341, 342),  # 8. Bottom-Middle (341x342)
-    (682, 682, 342, 342)  # 9. Bottom-Right (342x342)
-]
-
-
-def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, output_path="temp.jpg", add_text=True):
-    """
-    Loads up to 4 images from the given paths, resizes them while maintaining 
-    aspect ratio, and merges them onto a 1024x1024 white background JPG.
-    
-    The layout depends on the number of images:
-    1: Center the single image on the 1024x1024 canvas.
-    2: Place side-by-side, each scaled to fit a 512x1024 half.
-    3: Place in top-left (512x512), top-right (512x512), and bottom-left (512x512).
-    4: Place in all four 512x512 quadrants.
-
-    Args:
-        outfit_items: A list of item metadata (max length 9).
-
-    Returns:
-        The file path of the temporary merged JPG image.
-    """
-
-    # Define the final canvas size
-    CANVAS_SIZE = 1024
-
-    # 1. Create the final white canvas
-    # Using 'RGB' mode for JPG output
-    canvas = Image.new('RGB', (CANVAS_SIZE, CANVAS_SIZE), 'white')
-    draw = ImageDraw.Draw(canvas)
-    font = ImageFont.load_default()
-
-    # 2. Define the quadrants/target areas (x, y, w, h)
-    # The positions are based on a 512x512 quadrant size
-    quadrants = {
-        1: [(0, 0, CANVAS_SIZE, CANVAS_SIZE)],  # Single full-size placement
-        2: [(0, 0, 512, CANVAS_SIZE), (512, 0, 512, CANVAS_SIZE)],  # Left, Right
-        3: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512)],  # Top-Left, Top-Right, Bottom-Left
-        4: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512), (512, 512, 512, 512)],  # All Four
-        5: ALL_9_CELLS[:5],  # 布局前5个单元格 (1-5)
-        6: ALL_9_CELLS[:6],  # 布局前6个单元格 (1-6)
-        7: ALL_9_CELLS[:7],  # 布局前7个单元格 (1-7)
-        8: ALL_9_CELLS[:8],  # 布局前8个单元格 (1-8)
-        9: ALL_9_CELLS[:9]  # 布局全部9个单元格 (1-9)
-    }
-
-    # 3. Load and Filter Images
-    valid_images = []
-    image_paths = [item['image_path'] for item in outfit_items]
-    for path in image_paths:
-        try:
-            # We use Image.open() and convert to 'RGB' to handle potential transparency (RGBA)
-            # and ensure compatibility with the final 'RGB' canvas and JPG output.
-            img = Image.open(path).convert('RGB')
-            valid_images.append(img)
-        except Exception as e:
-            print(f"Error loading image {path}. Skipping: {e}")
-
-    num_images = len(valid_images)
-
-    if num_images == 0:
-        raise ValueError("No valid images were loaded.")
-
-    if num_images > max_len:
-        raise ValueError(f"Valid item number {num_images} exceed max limit {max_len}")
-
-    # Get the correct list of target areas based on the number of valid images
-    target_areas = quadrants.get(num_images, [])
-
-    # 4. Resize and Paste
-    for i, (img, item) in enumerate(zip(valid_images, outfit_items)):
-        item_id = item['item_id']
-        category = item['category']
-        if i >= len(target_areas):
-            # This should not happen if num_images <= 4
-            break
-
-        # Target area dimensions (x_start, y_start, width, height)
-        x_start, y_start, target_w, target_h = target_areas[i]
-
-        # Calculate new size while maintaining aspect ratio
-        original_w, original_h = img.size
-
-        # Calculate the ratio needed to fit within the target area
-        ratio_w = target_w / original_w
-        ratio_h = target_h / original_h
-
-        # Use the *smaller* of the two ratios to ensure the image fits entirely
-        resize_ratio = min(ratio_w, ratio_h)
-
-        # Calculate the new dimensions
-        new_w = int(original_w * resize_ratio)
-        new_h = int(original_h * resize_ratio)
-
-        # Resize the image. Image.Resampling.LANCZOS provides high-quality scaling.
-        # Pillow documentation recommends ANTIALIAS or BICUBIC for downscaling, 
-        # but LANCZOS is a good general high-quality filter.
-        # Note: In Pillow versions > 9.0.0, Image.LANCZOS is now Image.Resampling.LANCZOS
-        resized_img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
-
-        # Calculate the paste position to center the resized image within its target area
-        # Center X: (Target Width - New Width) / 2 + X Start
-        paste_x = (target_w - new_w) // 2 + x_start
-        # Center Y: (Target Height - New Height) / 2 + Y Start
-        # paste_y = (target_h - new_h) // 2 + y_start
-
-        TEXT_RESERVE_HEIGHT = 30
-        paste_y = (target_h - new_h - TEXT_RESERVE_HEIGHT) // 2 + y_start
-        paste_y = max(paste_y, y_start)
-
-        # Paste the resized image onto the canvas
-        canvas.paste(resized_img, (paste_x, paste_y))
-
-        full_text = f"ID: {item_id}, Category: {category}"
-        try:
-            # 推荐使用：计算文本的实际尺寸 (width, height)
-            bbox = draw.textbbox((0, 0), full_text, font=font)
-            text_w = bbox[2] - bbox[0]
-            text_h = bbox[3] - bbox[1]
-        except AttributeError:
-            # 兼容旧版本 Pillow
-            text_w, text_h = draw.textsize(full_text, font=font)
-
-        # 计算 X 轴起始位置：使其在目标区域 (target_w) 中居中
-        text_x_center = x_start + target_w // 2
-        text_x_start = text_x_center - text_w // 2
-
-        # 计算 Y 轴起始位置：将其放在目标区域的底部
-        # (目标区域的起始Y + 目标区域的高度 - 文本行的高度)
-        text_y_start = y_start + target_h - text_h - 5  # 减去 5 像素作为边距
-
-        # 3. 绘制合并后的文本
-        if add_text:
-            draw.text((text_x_start, text_y_start),
-                      full_text,
-                      fill='black',
-                      font=font)
-
-    # Save as a high-quality JPG (quality=90 is a good balance)
-    # canvas.save(output_path, 'JPEG', quality=90)
-
-    return canvas

app/core/utils_litserve.py

@@ -1,320 +0,0 @@
-import logging
-from typing import List, Dict
-from PIL import Image, ImageDraw, ImageFont
-from app.server.utils.minio_client import oss_get_image, minio_client
-from app.server.utils.minio_config import MINIO_LC_DATA_PATH
-
-logger = logging.getLogger(__name__)
-# 9个 341x341 左右的单元格 (ALL_9_CELLS)
-# 布局顺序: 从上到下，从左到右 (1 -> 9)
-ALL_9_CELLS = [
-    # Top Row (Y=0, H=341)
-    (0, 0, 341, 341),  # 1. Top-Left (341x341)
-    (341, 0, 341, 341),  # 2. Top-Middle (341x341)
-    (682, 0, 342, 341),  # 3. Top-Right (342x341)
-    # Middle Row (Y=341, H=341)
-    (0, 341, 341, 341),  # 4. Mid-Left (341x341)
-    (341, 341, 341, 341),  # 5. Center (341x341)
-    (682, 341, 342, 341),  # 6. Mid-Right (342x341)
-    # Bottom Row (Y=682, H=342)
-    (0, 682, 341, 342),  # 7. Bottom-Left (341x342)
-    (341, 682, 341, 342),  # 8. Bottom-Middle (341x342)
-    (682, 682, 342, 342)  # 9. Bottom-Right (342x342)
-]
-
-
-def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_text=True):
-    """
-    Loads up to 4 images from the given paths, resizes them while maintaining 
-    aspect ratio, and merges them onto a 1024x1024 white background JPG.
-    
-    The layout depends on the number of images:
-    1: Center the single image on the 1024x1024 canvas.
-    2: Place side-by-side, each scaled to fit a 512x1024 half.
-    3: Place in top-left (512x512), top-right (512x512), and bottom-left (512x512).
-    4: Place in all four 512x512 quadrants.
-
-    Args:
-        outfit_items: A list of item metadata (max length 9).
-
-    Returns:
-        The file path of the temporary merged JPG image.
-    """
-
-    # Define the final canvas size
-    CANVAS_SIZE = 1024
-
-    # 定义每个 item 的外边距
-    MARGIN = 5  # 5像素外边距
-
-    # 1. Create the final white canvas
-    # Using 'RGB' mode for JPG output
-    canvas = Image.new('RGB', (CANVAS_SIZE, CANVAS_SIZE), 'white')
-    draw = ImageDraw.Draw(canvas)
-    font = ImageFont.load_default()
-
-    # 2. Define the quadrants/target areas (x, y, w, h)
-    # The positions are based on a 512x512 quadrant size
-    quadrants = {
-        1: [(0, 0, CANVAS_SIZE, CANVAS_SIZE)],  # Single full-size placement
-        2: [(0, 0, 512, CANVAS_SIZE), (512, 0, 512, CANVAS_SIZE)],  # Left, Right
-        3: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512)],  # Top-Left, Top-Right, Bottom-Left
-        4: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512), (512, 512, 512, 512)],  # All Four
-        5: ALL_9_CELLS[:5],  # 布局前5个单元格 (1-5)
-        6: ALL_9_CELLS[:6],  # 布局前6个单元格 (1-6)
-        7: ALL_9_CELLS[:7],  # 布局前7个单元格 (1-7)
-        8: ALL_9_CELLS[:8],  # 布局前8个单元格 (1-8)
-        9: ALL_9_CELLS[:9]  # 布局全部9个单元格 (1-9)
-    }
-
-    # 3. Load and Filter Images
-    valid_images = []
-    image_paths = [item['image_path'] for item in outfit_items]
-    for path in image_paths:
-        try:
-            # We use Image.open() and convert to 'RGB' to handle potential transparency (RGBA)
-            # and ensure compatibility with the final 'RGB' canvas and JPG output.
-            img = oss_get_image(oss_client=minio_client, path=f"{MINIO_LC_DATA_PATH}/{path}", data_type="PIL").convert('RGB')
-            # img = Image.open(path).convert('RGB')
-            valid_images.append(img)
-        except Exception as e:
-            logger.error(f"Error loading image {path}. Skipping: {e}")
-
-    num_images = len(valid_images)
-
-    if num_images == 0:
-        raise ValueError("No valid images were loaded.")
-
-    if num_images > max_len:
-        raise ValueError(f"Valid item number {num_images} exceed max limit {max_len}")
-
-    # Get the correct list of target areas based on the number of valid images
-    target_areas = quadrants.get(num_images, [])
-
-    if not target_areas:
-        raise ValueError(f"No layout defined for {num_images} images.")
-
-    # 4. Resize and Paste
-    for i, (img, item) in enumerate(zip(valid_images, outfit_items)):
-        item_id = item['item_id']
-        category = item['category']
-        if i >= len(target_areas):
-            # This should not happen if num_images <= 4
-            break
-
-        # 原始目标区域 (x_start, y_start, width, height)
-        orig_x_start, orig_y_start, orig_w, orig_h = target_areas[i]
-
-        # 📢 应用边距：实际用于图像和文本的区域
-        # 新的起始点：向内移动 MARGIN
-        x_start = orig_x_start + MARGIN
-        y_start = orig_y_start + MARGIN
-
-        # 新的宽高：减去两倍的 MARGIN (左右/上下)
-        target_w = orig_w - 2 * MARGIN
-        target_h = orig_h - 2 * MARGIN
-
-        # --- 图像缩放与居中 ---
-
-        # Calculate new size while maintaining aspect ratio
-        original_w, original_h = img.size
-
-        # Calculate the ratio needed to fit within the *带边距的* 目标区域
-        ratio_w = target_w / original_w
-        ratio_h = target_h / original_h
-
-        # Use the *smaller* of the two ratios to ensure the image fits entirely
-        resize_ratio = min(ratio_w, ratio_h)
-
-        # Calculate the new dimensions
-        new_w = int(original_w * resize_ratio)
-        new_h = int(original_h * resize_ratio)
-
-        # Resize the image.
-        resized_img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
-
-        # Calculate the paste position to center the resized image within its target area
-        # Center X: (Target Width - New Width) / 2 + X Start (带边距的 X_start)
-        paste_x = (target_w - new_w) // 2 + x_start
-
-        # 预留文本高度 ( TEXT_RESERVE_HEIGHT )
-        TEXT_RESERVE_HEIGHT = 30
-
-        # Center Y: (Target Height - New Height - 预留文本高度) / 2 + Y Start (带边距的 Y_start)
-        paste_y = (target_h - new_h - TEXT_RESERVE_HEIGHT) // 2 + y_start
-        # 确保图片顶部不超出目标区域的 Y_start
-        paste_y = max(paste_y, y_start)
-
-        # Paste the resized image onto the canvas
-        canvas.paste(resized_img, (paste_x, paste_y))
-
-        # --- 文本居中与定位 ---
-
-        full_text = f"ID: {item_id}, Category: {category}"
-        if add_text:
-            try:
-                # 推荐使用：计算文本的实际尺寸 (width, height)
-                bbox = draw.textbbox((0, 0), full_text, font=font)
-                text_w = bbox[2] - bbox[0]
-                text_h = bbox[3] - bbox[1]
-            except AttributeError:
-                # 兼容旧版本 Pillow
-                text_w, text_h = draw.textsize(full_text, font=font)
-
-            # 计算 X 轴起始位置：使其在 *带边距的目标区域* (target_w) 中居中
-            text_x_center = x_start + target_w // 2
-            text_x_start = text_x_center - text_w // 2
-
-            # 计算 Y 轴起始位置：将其放在 *带边距的目标区域* 的底部
-            # (带边距的起始Y + 带边距的高度 - 文本行的高度)
-            # 📢 在带边距的目标区域底部再减去 5 像素作为与底部的边距
-            text_y_start = y_start + target_h - text_h
-
-            draw.text((text_x_start, text_y_start),
-                      full_text,
-                      fill='black',
-                      font=font)
-
-    # Save as a high-quality JPG (quality=90 is a good balance)
-    # canvas.save(output_path, 'JPEG', quality=90)
-
-    return canvas
-
-# def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_text=True):
-#     """
-#     Loads up to 4 images from the given paths, resizes them while maintaining
-#     aspect ratio, and merges them onto a 1024x1024 white background JPG.
-#
-#     The layout depends on the number of images:
-#     1: Center the single image on the 1024x1024 canvas.
-#     2: Place side-by-side, each scaled to fit a 512x1024 half.
-#     3: Place in top-left (512x512), top-right (512x512), and bottom-left (512x512).
-#     4: Place in all four 512x512 quadrants.
-#
-#     Args:
-#         outfit_items: A list of item metadata (max length 9).
-#
-#     Returns:
-#         The file path of the temporary merged JPG image.
-#     """
-#
-#     # Define the final canvas size
-#     CANVAS_SIZE = 1024
-#
-#     # 1. Create the final white canvas
-#     # Using 'RGB' mode for JPG output
-#     canvas = Image.new('RGB', (CANVAS_SIZE, CANVAS_SIZE), 'white')
-#     draw = ImageDraw.Draw(canvas)
-#     font = ImageFont.load_default()
-#
-#     # 2. Define the quadrants/target areas (x, y, w, h)
-#     # The positions are based on a 512x512 quadrant size
-#     quadrants = {
-#         1: [(0, 0, CANVAS_SIZE, CANVAS_SIZE)],  # Single full-size placement
-#         2: [(0, 0, 512, CANVAS_SIZE), (512, 0, 512, CANVAS_SIZE)],  # Left, Right
-#         3: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512)],  # Top-Left, Top-Right, Bottom-Left
-#         4: [(0, 0, 512, 512), (512, 0, 512, 512), (0, 512, 512, 512), (512, 512, 512, 512)],  # All Four
-#         5: ALL_9_CELLS[:5],  # 布局前5个单元格 (1-5)
-#         6: ALL_9_CELLS[:6],  # 布局前6个单元格 (1-6)
-#         7: ALL_9_CELLS[:7],  # 布局前7个单元格 (1-7)
-#         8: ALL_9_CELLS[:8],  # 布局前8个单元格 (1-8)
-#         9: ALL_9_CELLS[:9]  # 布局全部9个单元格 (1-9)
-#     }
-#
-#     # 3. Load and Filter Images
-#     valid_images = []
-#     image_paths = [item['image_path'] for item in outfit_items]
-#     for path in image_paths:
-#         try:
-#             # We use Image.open() and convert to 'RGB' to handle potential transparency (RGBA)
-#             # and ensure compatibility with the final 'RGB' canvas and JPG output.
-#             img = oss_get_image(oss_client=minio_client, path=f"{MINIO_LC_DATA_PATH}/{path}", data_type="PIL").convert('RGB')
-#             # img = Image.open(path).convert('RGB')
-#             valid_images.append(img)
-#         except Exception as e:
-#             logger.error(f"Error loading image {path}. Skipping: {e}")
-#
-#     num_images = len(valid_images)
-#
-#     if num_images == 0:
-#         raise ValueError("No valid images were loaded.")
-#
-#     if num_images > max_len:
-#         raise ValueError(f"Valid item number {num_images} exceed max limit {max_len}")
-#
-#     # Get the correct list of target areas based on the number of valid images
-#     target_areas = quadrants.get(num_images, [])
-#
-#     # 4. Resize and Paste
-#     for i, (img, item) in enumerate(zip(valid_images, outfit_items)):
-#         item_id = item['item_id']
-#         category = item['category']
-#         if i >= len(target_areas):
-#             # This should not happen if num_images <= 4
-#             break
-#
-#         # Target area dimensions (x_start, y_start, width, height)
-#         x_start, y_start, target_w, target_h = target_areas[i]
-#
-#         # Calculate new size while maintaining aspect ratio
-#         original_w, original_h = img.size
-#
-#         # Calculate the ratio needed to fit within the target area
-#         ratio_w = target_w / original_w
-#         ratio_h = target_h / original_h
-#
-#         # Use the *smaller* of the two ratios to ensure the image fits entirely
-#         resize_ratio = min(ratio_w, ratio_h)
-#
-#         # Calculate the new dimensions
-#         new_w = int(original_w * resize_ratio)
-#         new_h = int(original_h * resize_ratio)
-#
-#         # Resize the image. Image.Resampling.LANCZOS provides high-quality scaling.
-#         # Pillow documentation recommends ANTIALIAS or BICUBIC for downscaling,
-#         # but LANCZOS is a good general high-quality filter.
-#         # Note: In Pillow versions > 9.0.0, Image.LANCZOS is now Image.Resampling.LANCZOS
-#         resized_img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
-#
-#         # Calculate the paste position to center the resized image within its target area
-#         # Center X: (Target Width - New Width) / 2 + X Start
-#         paste_x = (target_w - new_w) // 2 + x_start
-#         # Center Y: (Target Height - New Height) / 2 + Y Start
-#         # paste_y = (target_h - new_h) // 2 + y_start
-#
-#         TEXT_RESERVE_HEIGHT = 30
-#         paste_y = (target_h - new_h - TEXT_RESERVE_HEIGHT) // 2 + y_start
-#         paste_y = max(paste_y, y_start)
-#
-#         # Paste the resized image onto the canvas
-#         canvas.paste(resized_img, (paste_x, paste_y))
-#
-#         full_text = f"ID: {item_id}, Category: {category}"
-#         try:
-#             # 推荐使用：计算文本的实际尺寸 (width, height)
-#             bbox = draw.textbbox((0, 0), full_text, font=font)
-#             text_w = bbox[2] - bbox[0]
-#             text_h = bbox[3] - bbox[1]
-#         except AttributeError:
-#             # 兼容旧版本 Pillow
-#             text_w, text_h = draw.textsize(full_text, font=font)
-#
-#         # 计算 X 轴起始位置：使其在目标区域 (target_w) 中居中
-#         text_x_center = x_start + target_w // 2
-#         text_x_start = text_x_center - text_w // 2
-#
-#         # 计算 Y 轴起始位置：将其放在目标区域的底部
-#         # (目标区域的起始Y + 目标区域的高度 - 文本行的高度)
-#         text_y_start = y_start + target_h - text_h - 5  # 减去 5 像素作为边距
-#
-#         # 3. 绘制合并后的文本
-#         if add_text:
-#             draw.text((text_x_start, text_y_start),
-#                       full_text,
-#                       fill='black',
-#                       font=font)
-#
-#     # Save as a high-quality JPG (quality=90 is a good balance)
-#     # canvas.save(output_path, 'JPEG', quality=90)
-#
-#     return canvas

app/core/vector_database.py

@@ -1,62 +0,0 @@
-import os
-from typing import List, Dict, Any, Optional
-
-import torch
-import chromadb
-from transformers import CLIPProcessor, CLIPModel
-from PIL import Image
-
-
-class VectorDatabase():
-    def __init__(self, vector_db_dir: str, collection_name: str, embedding_model_name: str):
-        self.client = chromadb.PersistentClient(path=vector_db_dir)
-
-        self.collection = self.client.get_or_create_collection(name=collection_name)
-
-        self.device = "cuda" if torch.cuda.is_available() else "cpu"
-
-        self.model = CLIPModel.from_pretrained(embedding_model_name).to(self.device)
-        self.processor = CLIPProcessor.from_pretrained(embedding_model_name)
-
-    def get_clip_embedding(self, data: str | Image.Image, is_image: bool) -> List[float]:
-        """生成图像或文本的 CLIP 嵌入，并进行 L2 归一化。"""
-
-        if is_image:
-            inputs = self.processor(images=data, return_tensors="pt").to(self.device)
-            with torch.no_grad():
-                features = self.model.get_image_features(**inputs)
-        else:
-            # 强制截断，解决序列长度问题
-            inputs = self.processor(
-                text=[data],
-                return_tensors="pt",
-                padding=True,
-                truncation=True
-            ).to(self.device)
-            with torch.no_grad():
-                features = self.model.get_text_features(**inputs)
-
-        # L2 归一化
-        features = features / features.norm(p=2, dim=-1, keepdim=True)
-
-        return features.cpu().numpy().flatten().tolist()
-
-    def query_local_db(self, embedding: List[float], category: str, n_results: int = 3) -> List[Dict[str, Any]]:
-        """
-        基于嵌入向量在本地数据库中查询相似单品。
-        实际应执行 ChromaDB 查询,并根据 category 进行过滤(metadatas)。
-        """
-        # 实际应执行向量查询
-        # 为了演示流程,返回一个模拟结果
-        results = self.collection.query(
-            query_embeddings=[embedding],
-            n_results=n_results,
-            where={
-                "$and": [
-                    {"category": category},
-                    {"modality": "image"},
-                ]
-            },
-            include=['documents', 'metadatas', 'distances']
-        )
-        return results

app/main.py

@@ -1,7 +1,7 @@
 import logging.config
 import os
 import litserve as ls
-from app.core.config import DEBUG, settings
+from app.config import settings
 from app.server.ChatbotAgent.agent_server import LCAgent
 from app.server.ChatbotAgent.chatbot_server import LCChatBot
 from app.server.ReFace.server import ReFace
@@ -21,7 +21,7 @@ logging.config.dictConfig(LOGGER_CONFIG_DICT)
 
 # STEP 2: START THE SERVER
 if __name__ == "__main__":
-    logger.info(f"DEBUG -> :{DEBUG}")
+    logger.info(f"运行环境 1表示本地运行，0表示生产环境运行 ： -> :{settings.LOCAL}")
     logger.info(f"VECTOR_DB_DIR -> :{settings.VECTOR_DB_DIR}")
     chat_boot_api = LCChatBot(enable_async=True, stream=True, api_path='/api/v1/chatbot')
     agent_api = LCAgent(enable_async=True, api_path='/api/v1/agent')

app/request.json

@@ -1,13 +0,0 @@
-{
-  "type": "service_account",
-  "project_id": "aida-461108",
-  "private_key_id": "b4afaabebb84da24502b318a5fa175f1dc5c096a",
-  "private_key": "-----BEGIN PRIVATE KEY-----\nMIIEvAIBADANBgkqhkiG9w0BAQEFAASCBKYwggSiAgEAAoIBAQCmk7LKrp8g9yD1\nWmF+mY2qHCEZ/5aIx6QRh0QoVPBL7Yi7ce009QxaE8fu8+QMgg8l3xMreXvgpt56\noFnVwpFusLjSdjgoFluElM2hYxXlO9q8cbBoU2nehOBLLJzGzkodT7xu/BOjNvKC\n//aTbjtJyk8Kj+ENa0/dPaUZs/PCtQqpAu8ag5nXrordVWfO0K25EjeYyoba35zk\nPp2fBi8KALZZI5Xfd2z9++K0K2mWWIMJic30idHvquj0WxlTRK2Pq8BmJXCQpJIi\nQ5E4egue16BfKjrF0Kxkpqd1RmdlEmaSKbbkZXe2z4jg0qknESRFOmRy8C3LnaB2\nHHJWLYM3AgMBAAECggEACUdroOQJSTTQSS/iWRhZ+S0yoC10nTnsZxg527qfiBs7\nOqB7WNqC+Ew8dDsca6CdvLuoaGDkCFJDTQwRn66u8JOM4sG4bxiPuzBEJBv45EQT\n8zCsuvhVNWgBdoPjAnq19jFdixvPnDqQrRYaY4FdxsaA5f24c57pW/xLGMYawLBt\n9RJZSuWmJdzKG1i5W8a8+4f/seNtuo2MtXU3mPJZPqRWPXTAZeaQPM/57ZQ+kzig\nOkAbQZNRmt1yPCjPCQD8vc8yCBMmjus/rlHXD/L7okYUlVZkob5I3FBrLl+ZyIXS\nqxEsBLBwRW3w8WbX+ZSVciQ72JK68W7LnOHSAENmAQKBgQDgBTCqp87KGLWVPb8w\nK+s1Sfh+nM3M4AlbLdcGBs1JCoddF6pAeY4wpf/ow1Tm4rqEuCYzMClPwxvkue+D\nY7lCQgy2FK3ahUzn8oVmvEPD/YPAojDSY3bH0lquHuS6oVKk834JUykButaAU3XY\nvUGNQuKdLKAeQRT8Q6um4m+EYQKBgQC+Wz6nYESKH6GiNnuFTH8hIkThPlbi4wua\nU1kGnPKe3ouE4zRLfPwQ6RRf1slQ/2hFLOatiTLYUgZWZQeBPSWp2EjYcOSzob+7\n11+KqeIRCD5DKxgf0cjJdihK9AM639OKlH2NvZ2507TksdeTPDzdaOMLwLWKexP5\nlYrdob0ulwKBgD81t7Gvf83Ogw4FSjkRa2Cx6ofvPrKcVIeBu7ZbnPkLG37M+qEO\nq2xWqorG8uHi/7YLL9wprr5u0yQKwuZT8SYc9PE7jIKoMjcQW0vNu2FF2zMzkIsM\nvatMU4Hl/awbcPJSMjH3YQ635WZ4Jjxtyl1NjhvDR7rBqmYzwe9o3QaBAoGANhPB\n1tbYYczepDCKIrI6o3US0FJfaJFLqInpDqHjoxJh3FyXbKKTEVLFwPxJsML+IjjB\nR6dkVGPo/P4yhZqTao7REvvvXMCksX5b3A6q9F+9IGPLtK5qNiFlDPYJPN59QC8z\nA+NMPZBRIW8MaP2B5Px5E8upRy/z2sGK86+RCP0CgYATGs75F97q+Zf8q+Pe3Nsb\ngqmhLoI3PZUSWgBcQgNF4nyCZceUrEl72wKO/NWLgxqQPtlra187ce69g7qARHLb\ntHq80nb0f7lil74B6+OlyNNO1htWA90fmGR2s16Mt0BwJRT+/EFuNqbJIUSLxKiW\nqlXBUbmHHzamo5DPYL8S/w==\n-----END PRIVATE KEY-----\n",
-  "client_email": "aida-239@aida-461108.iam.gserviceaccount.com",
-  "client_id": "103102077955178349079",
-  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
-  "token_uri": "https://oauth2.googleapis.com/token",
-  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
-  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/aida-239%40aida-461108.iam.gserviceaccount.com",
-  "universe_domain": "googleapis.com"
-}

app/server/ChatbotAgent/agent_server.py

@@ -1,28 +1,61 @@
 import asyncio
 import logging
 import uuid
+from enum import Enum
+from typing import List
+from pydantic import Field
+import time
 
 import litserve as ls
 from pydantic import BaseModel
-from app.core.config import settings
+from app.config import settings
 from app.server.ChatbotAgent.core.data_structure import Message, Role
 from app.server.ChatbotAgent.core.llm_interface import AsyncGeminiLLM
 from app.server.ChatbotAgent.core.redis_manager import RedisManager
 from app.server.ChatbotAgent.core.stylist_agent_server import AsyncStylistAgent
-from app.server.ChatbotAgent.core.system_prompt import SUMMARY_PROMPT
+from app.server.ChatbotAgent.core.prompt import SUMMARY_PROMPT
 from app.server.ChatbotAgent.core.vector_database import VectorDatabase
 
 logger = logging.getLogger(__name__)
 
 
+class OccasionEnum(str, Enum):
+    CASUAL = "Casual"
+    FORMAL = "Formal"
+    ACTIVEWEAR = "Activewear"
+    RESORT = "Resort"
+    EVENING = "Evening"
+    OUTDOOR = "Outdoor"
+    BUSINESS_WORKWEAR = "Business / workwear"
+    COCKTAIL_SEMI_FORMAL = "Cocktail / Semi-Formal"
+    BLACK_TIE_WHITE_TIE = "Black Tie / White Tie"
+    BRIDAL_WEDDING = "Bridal / Wedding"
+    FESTIVAL_CONCERT = "Festival / Concert"
+    PARTY_CLUBBING = "Party / Clubbing"
+    TRAVEL_TRANSIT = "Travel / Transit"
+    ATHLEISURE = "Athleisure"
+    BEACH_SWIM = "Beach / Swim"
+    SKI_SNOW_MOUNTAIN = "Ski / Snow / Mountain"
+    GARDEN_PARTY_DAYTIME = "Garden Party / Daytime Event"
+
+
+class StylistResponse(BaseModel):
+    occasions: List[OccasionEnum] = Field(
+        description="A list of **applicable** occasions that are most strongly implied or explicitly requested by the user's conversation history. These occasions are used later in item retrieval for filtering and must strictly match the predefined OccasionEnum list."
+    )
+    summary: str = Field(
+        description="A detailed summary of the user's styling requirements, preferences, constraints, and specific item requests."
+    )
+
+
 class AgentRequestModel(BaseModel):
     user_id: str
     session_id: str
     num_outfits: int
     stylist_path: str
+    batch_sources: List[str]
     callback_url: str
     gender: str
-    max_len: int = 9
 
 
 class LCAgent(ls.LitAPI):
@@ -41,10 +74,8 @@ class LCAgent(ls.LitAPI):
         )
         self.stylist_agent_kwages = {
             'local_db': self.vector_db,
-            'max_len': 9,
             'gemini_model_name': settings.LLM_MODEL_NAME
         }
-        self.outfit_ids = []
 
     async def decode_request(self, request: AgentRequestModel):
         """
@@ -62,49 +93,87 @@ class LCAgent(ls.LitAPI):
 
     async def predict(self, request):
 
-        self.outfit_ids = [str(uuid.uuid4()) for _ in range(request.num_outfits)]
+        outfit_ids = [str(uuid.uuid4()) for _ in range(request.num_outfits)]
 
-        asyncio.create_task(self.background_run(request))
-        return {"status": "Task initiated in background.", "outfit_ids": self.outfit_ids}
+        asyncio.create_task(self.background_run(request, outfit_ids))
+
+        logger.info({"status": "Task initiated in background.", "outfit_ids": outfit_ids})
+        return {"status": "Task initiated in background.", "outfit_ids": outfit_ids}
 
     async def encode_response(self, output):
         return output
 
-    async def background_run(self, request: AgentRequestModel):
+    async def background_run(self, request: AgentRequestModel, outfit_ids):
         # 1. 根据用户ID查询对话历史，总结对话内容
-        request_summary = await self.get_conversation_summary(request.session_id)
+        request_summary, occasions = await self.get_conversation_summary(request.session_id)
         logger.info(f"request_summary: {request_summary}")
 
         # 2.根据对话总结推荐搭配
-        recommendation_results = await self.recommend_outfit(request_summary=request_summary,
-                                                             stylist_name=request.stylist_path,
-                                                             start_outfit=[],
-                                                             num_outfits=request.num_outfits,
-                                                             user_id=request.user_id,
-                                                             gender=request.gender,
-                                                             callback_url=request.callback_url,
-                                                             max_len=request.max_len)
+        recommendation_results = await self.recommend_outfit(
+            request_summary=request_summary,
+            occasions=occasions,
+            stylist_name=request.stylist_path,
+            start_outfit=[],
+            batch_sources=request.batch_sources,
+            num_outfits=request.num_outfits,
+            user_id=request.user_id,
+            gender=request.gender,
+            callback_url=request.callback_url,
+            outfit_ids=outfit_ids
+        )
         logger.info("--- Final Recommendation Results ---")
         for i, path in enumerate(recommendation_results.get("successful_outfits", [])):
             logger.info(f"✅ Outfit {i + 1} saved to: {path}")
         for failed in recommendation_results.get("failed_outfits", []):
             logger.error(f"❌ {failed}")
 
-    async def get_conversation_summary(self, session_id: str) -> str:
+    async def get_conversation_summary(self, session_id: str) -> dict:
         """
-        分析用户的完整会话历史，并打包成一个简洁的需求总结。
-
-        这个总结可以直接作为输入 Prompt 传递给 Stylist Agent。`
+        分析用户的完整会话历史，并返回结构化的需求数据。
+        
+        Returns:
+            occasions: List[str], # 用于 Vector DB 筛选
+            summary: str          # 用于 recommendation 的输入
         """
         history_messages = self.redis.get_history(session_id)
-        input_message = "\n".join([f"{msg.role.value}: {msg.content}" for msg in history_messages])
-        # 临时调用 LLM 或使用本地逻辑生成总结
-        summary = await self.llm.generate_response(history=[Message(role=Role.USER, content=input_message)],
-                                                   system_prompt=SUMMARY_PROMPT)
-        return summary
+        if not history_messages:
+            # 处理无历史记录的情况
+            return {"occasions": [], "summary": "User has no history provided."}
 
-    async def recommend_outfit(self, request_summary: str, stylist_name: str, start_outfit=None, num_outfits: int = 1,
-                               user_id: str = "test", gender: str = "male", callback_url: str = None, max_len: int = 9):
+        input_message = "\n".join([f"{msg.role.value}: {msg.content}" for msg in history_messages])
+        json_schema = StylistResponse.model_json_schema()
+
+        raw_response = await self.llm.generate_response(
+            history=[Message(role=Role.USER, content=input_message)],
+            system_prompt=SUMMARY_PROMPT,
+            json_schema=json_schema
+        )
+
+        try:
+            # 验证并解析 JSON
+            parsed_result = StylistResponse.model_validate_json(raw_response)
+
+            print(f"Occasions: {[occ.value for occ in parsed_result.occasions]}")
+            print(f"Summary: {parsed_result.summary}")  # 这是一个 string
+
+        except Exception as e:
+            logger.error(f"Schema validation failed: {e}")
+
+        return str(parsed_result.summary), [occ.value for occ in parsed_result.occasions]
+
+    async def recommend_outfit(
+            self,
+            request_summary: str,
+            occasions: List[str],
+            stylist_name: str,
+            start_outfit: List = [],
+            batch_sources: List[str] = [],
+            num_outfits: int = 1,
+            user_id: str = "test",
+            gender: str = "male",
+            callback_url: str = None,
+            outfit_ids=None
+    ):
         """
         基于用户的对话历史和需求，推荐一套搭配。
 
@@ -112,24 +181,58 @@ class LCAgent(ls.LitAPI):
             request_summary: 用户的request
             start_outfit: 可选的初始搭配列表，每个元素包含 'item_id' 和 'category'。
         """
-        if start_outfit is None:
-            start_outfit = []
+        if outfit_ids is None:
+            outfit_ids = []
         tasks = []
         task_map = {}
-        for i in range(num_outfits):
-            self.stylist_agent_kwages['outfit_id'] = self.outfit_ids[i]
-            self.stylist_agent_kwages['max_len'] = max_len
-            agent = AsyncStylistAgent(**self.stylist_agent_kwages)
-            task = agent.run_styling_process(
+
+        stylist_agent_kwages = self.stylist_agent_kwages.copy()
+        if num_outfits == 1:
+            # 通过请求数量判断 num == 1 单个outfit刷新
+            stylist_agent_kwages['outfit_id'] = outfit_ids[0]
+            stylist_agent_kwages['stylist_name'] = stylist_name
+            stylist_agent_kwages['gender'] = gender
+            agent = AsyncStylistAgent(**stylist_agent_kwages)
+            task = agent.run_iterative_styling(
                 request_summary=request_summary,
-                stylist_path=stylist_name,
+                occasions=occasions,
                 start_outfit=start_outfit,
+                batch_sources=batch_sources,
                 user_id=user_id,
                 callback_url=callback_url,
-                gender=gender,
             )
             tasks.append(task)
-            task_map[task] = {"outfit_id": self.outfit_ids[i], "retries": 0}
+            task_map[task] = {"outfit_id": outfit_ids[0], "retries": 0}
+        elif num_outfits > 1:
+            # 通过请求数量判断 num > 1 四套搭配推荐 (1快 , num-1慢)
+            for i in range(num_outfits):
+                stylist_agent_kwages['outfit_id'] = outfit_ids[i]
+                stylist_agent_kwages['stylist_name'] = stylist_name
+                stylist_agent_kwages['gender'] = gender
+                agent = AsyncStylistAgent(**stylist_agent_kwages)
+                if i == 0:
+                    # 第一套搭配使用快速方法 一次跑出所有单品
+                    logger.info(f"fast request outfit_id is : {outfit_ids[i]}")
+                    task = agent.run_quick_batch_styling(
+                        request_summary=request_summary,
+                        occasions=occasions,
+                        start_outfit=start_outfit,
+                        batch_sources=batch_sources,
+                        user_id=user_id,
+                        callback_url=callback_url,
+                    )
+                else:
+                    # 后续
+                    task = agent.run_iterative_styling(
+                        request_summary=request_summary,
+                        occasions=occasions,
+                        start_outfit=start_outfit,
+                        batch_sources=batch_sources,
+                        user_id=user_id,
+                        callback_url=callback_url,
+                    )
+                tasks.append(task)
+                task_map[task] = {"outfit_id": outfit_ids[i], "retries": 0}
         logger.info(f"--- Starting {num_outfits} concurrent outfit generation tasks. ---")
 
         # 2. 任务执行与重试循环
@@ -157,12 +260,15 @@ class LCAgent(ls.LitAPI):
                             logger.info(f"--- Retrying outfit {outfit_id} (Attempt {current_retries + 1}/{retry_limit}). ---")
 
                             # 重新创建任务 (可能需要短暂延迟，例如 time.sleep(1)，但在此异步环境中，我们会通过重新创建 agent/task 来实现)
-                            self.stylist_agent_kwages['outfit_id'] = outfit_id
-                            agent = AsyncStylistAgent(**self.stylist_agent_kwages)
-                            new_task = agent.run_styling_process(
+                            stylist_agent_kwages['outfit_id'] = outfit_id
+                            stylist_agent_kwages['stylist_name'] = stylist_name
+                            stylist_agent_kwages['gender'] = gender
+                            agent = AsyncStylistAgent(**stylist_agent_kwages)
+                            new_task = agent.run_quick_batch_styling(
                                 request_summary=request_summary,
-                                stylist_path=stylist_name,
+                                occasions=occasions,
                                 start_outfit=start_outfit,
+                                batch_sources=batch_sources,
                                 user_id=user_id,
                                 callback_url=callback_url
                             )
@@ -203,3 +309,63 @@ class LCAgent(ls.LitAPI):
             "failed_outfits": failed_outfits,
             "error": ""
         }
+
+
+if __name__ == "__main__":
+    async def test():
+        # 1. 准备测试实例
+        agent_api = LCAgent()
+        agent_api.setup(device='cpu')
+
+        # 2. 准备请求数据
+        import json
+        stylist_agent_kwages = agent_api.stylist_agent_kwages.copy()
+        with open("/mnt/data/workspace/Code/lc_stylist_agent/data/2025_q4/request_test.json", "r") as f:
+            request_data = json.load(f)
+
+        tasks_with_metadata = []
+        for test_content in request_data[20:25]:
+            occasions = test_content['occasions']
+            request_summary = test_content['request_summary']
+            for stylist_name in ["edi", "vera"]:
+                stylist_agent_kwages['outfit_id'] = test_content['test_case_id'] + "_" + "_".join(occasions) + f"_{stylist_name}"
+                stylist_agent_kwages['stylist_name'] = stylist_name
+                stylist_agent_kwages['gender'] = "female"
+                agent = AsyncStylistAgent(**stylist_agent_kwages)
+                # coro = agent.run_iterative_styling(
+                coro = agent.run_quick_batch_styling(
+                    request_summary=request_summary,
+                    occasions=occasions,
+                    start_outfit=[],
+                    batch_sources=["2025_q4"],
+                    user_id=test_content['test_case_id'],
+                    callback_url="http://18.167.251.121:10095",
+                )
+                # 记录任务开始前的单调时间，并将元数据添加到列表中
+                description = f"Batch mode - Case {test_content['test_case_id']} - Stylist {stylist_name}"
+
+                tasks_with_metadata.append((coro, description))
+
+        tasks_only = [coro for coro, _ in tasks_with_metadata]
+        print(f"--- Launching {len(tasks_only)} concurrent styling tasks... ---")
+        results = await asyncio.gather(*tasks_only, return_exceptions=True)
+
+        time_samples = []
+        for i, result in enumerate(results):
+            coro, description = tasks_with_metadata[i]
+            if isinstance(result, Exception):
+                print(f"❌ 任务失败: {type(result).__name__} - {str(result)}")
+                continue
+            else:
+                response, duration = result
+                time_samples.append(duration)
+                print(f"✅ 任务成功 ({description}) [Time: {duration:.2f}s].")
+
+        print(f"Average time consumption is {sum(time_samples) / len(time_samples)}")
+
+
+    try:
+        # 使用 asyncio.run() 来执行顶层异步函数
+        asyncio.run(test())
+    except Exception as e:
+        logger.error(f"Test failed due to an unexpected error: {e}")

app/server/ChatbotAgent/chatbot_server.py

@@ -4,14 +4,12 @@ import litserve as ls
 from typing import AsyncGenerator
 from google import genai
 from pydantic import BaseModel
-from app.core.config import settings
+from app.config import settings
 from google.genai import types
 
 from app.server.ChatbotAgent.core.data_structure import Message, Role
-from app.server.ChatbotAgent.core.llm_interface import AsyncGeminiLLM
 from app.server.ChatbotAgent.core.redis_manager import RedisManager
-from app.server.ChatbotAgent.core.system_prompt import MEN_BASIC_PROMPT, WOMEN_BASIC_PROMPT
-from app.server.ChatbotAgent.core.vector_database import VectorDatabase
+from app.server.ChatbotAgent.core.prompt import BASIC_PROMPT
 
 logger = logging.getLogger(__name__)
 
@@ -25,26 +23,12 @@ class PredictRequest(BaseModel):
 
 class LCChatBot(ls.LitAPI):
     def setup(self, device):
-        self.llm = AsyncGeminiLLM(model_name=settings.LLM_MODEL_NAME)
         self.redis = RedisManager(
             host=settings.REDIS_HOST,
             port=settings.REDIS_PORT,
             db=settings.REDIS_DB,
             key_prefix=settings.REDIS_HISTORY_KEY_PREFIX
         )
-        self.vector_db = VectorDatabase(
-            vector_db_dir=settings.VECTOR_DB_DIR,
-            collection_name=settings.COLLECTION_NAME,
-            embedding_model_name=settings.EMBEDDING_MODEL_NAME
-        )
-        self.stylist_agent_kwages = {
-            'local_db': self.vector_db,
-            'max_len': 5,
-            'outfits_root': settings.OUTFIT_OUTPUT_DIR,
-            'image_dir': settings.IMAGE_DIR,
-            'stylist_guide_dir': settings.STYLIST_GUIDE_DIR,
-            'gemini_model_name': settings.LLM_MODEL_NAME
-        }
         self.gemini_client = genai.Client(
             vertexai=True, project='aida-461108', location='us-central1'
         )
@@ -62,9 +46,9 @@ class LCChatBot(ls.LitAPI):
         chat_history = self.redis.get_history(session_id)
         chat_history.append(user_msg)
         if request.gender == 'male':
-            BASIC_PROMPT = MEN_BASIC_PROMPT
+            prompt = BASIC_PROMPT.format(gender='men')
         else:
-            BASIC_PROMPT = WOMEN_BASIC_PROMPT
+            prompt = BASIC_PROMPT.format(gender='women')
 
         contents = []
 
@@ -80,7 +64,7 @@ class LCChatBot(ls.LitAPI):
             model='gemini-2.5-flash',
             contents=contents,
             config=types.GenerateContentConfig(
-                system_instruction=BASIC_PROMPT,
+                system_instruction=prompt,
                 # temperature=0.3,
             )
         )
@@ -108,3 +92,45 @@ class LCChatBot(ls.LitAPI):
         # The for-loop must have async keyword here since output is an AsyncGenerator
         async for out in output:
             yield {"output": out}
+
+
+if __name__ == "__main__":
+    import asyncio
+    async def run_simple_test():
+        """
+        一个简单的异步测试用例，用于测试 LCChatBot 的流式输出。
+        """
+        print("\n" + "=" * 50)
+        print("--- 🔬 开始 LCChatBot 简单流式测试 ---")
+        
+        # 1. 初始化 LitAPI 和其依赖
+        chatbot_api = LCChatBot()
+        chatbot_api.setup(device="cpu") 
+        print("✅ Setup complete. Mock services initialized.")
+
+        # 2. 构造请求数据
+        request_data = PredictRequest(
+            user_id="simple_user",
+            session_id="simple_session",
+            user_message="I want an outfit. I am going to a evening party with friends. Suggest something stylish yet comfortable.",
+            gender="female"
+        )
+        chatbot_api.redis.clear_history(request_data.session_id)
+
+        print(f"-> 正在发送查询: {request_data.user_message}")
+        
+        # 3. 调用 predict 方法并处理流
+        response_generator = chatbot_api.predict(request_data)
+        
+        print("\n<- 接收流式响应:")
+
+        # 4. 异步迭代生成器，实时打印输出
+        async for chunk in response_generator:
+            print(chunk, end="", flush=True)
+
+    print("\n" + "=" * 50)
+    # 启动异步事件循环
+    try:
+        asyncio.run(run_simple_test())
+    except Exception as e:
+        print(f"\n发生致命错误: {e}")

app/server/ChatbotAgent/core/llm_interface.py

@@ -32,7 +32,7 @@ class AsyncGeminiLLM(AsyncLLMInterface):
         except Exception as e:
             raise type(e)(f"Failed to initialize Gemini Client. Check if GEMINI_API_KEY is set. Original error: {e}")
 
-    async def generate_response(self, history: List[Message], system_prompt: str) -> str:
+    async def generate_response(self, history: List[Message], system_prompt: str, json_schema=None) -> str:
         contents = []
 
         for msg in history:
@@ -44,14 +44,27 @@ class AsyncGeminiLLM(AsyncLLMInterface):
             contents.append(content)
 
         try:
-            response = await self.gemini_client.aio.models.generate_content(
-                model=self.model_name,
-                contents=contents,
-                config=types.GenerateContentConfig(
-                    system_instruction=system_prompt,
-                    # temperature=0.3,
+            if json_schema:
+                response = await self.gemini_client.aio.models.generate_content(
+                    model=self.model_name,
+                    contents=contents,
+                    config=types.GenerateContentConfig(
+                        system_instruction=system_prompt,
+                        response_mime_type="application/json",
+                        response_schema=json_schema
+                    )
                 )
-            )
-            return response.text
+                return response.text
+            else:
+                response = await self.gemini_client.aio.models.generate_content(
+                    model=self.model_name,
+                    contents=contents,
+                    config=types.GenerateContentConfig(
+                        system_instruction=system_prompt,
+                        # temperature=0.3,
+                    )
+                )
+                return response.text
         except Exception as e:
             raise type(e)(f"Gemini API call failed: {e}")
+        

app/server/ChatbotAgent/core/prompt.py

@@ -0,0 +1,219 @@
+BASIC_PROMPT = """You are a professional, friendly, and insightful AI {gender}'s styling assistant.
+
+Your primary mission is to engage in a multi-turn conversation with the user to fully understand their dressing intent. You must adopt a professional yet approachable tone.
+
+CONVERSATION GOALS:
+1.  **Occasion:** Determine the specific event (e.g., romantic dinner, summer wedding, business meeting).
+2.  **Style:** Pinpoint the desired aesthetic (e.g., classic elegance, edgy, minimalist, bohemian).
+3.  **Vibe/Details:** Gather any mood or specific constraints (e.g., needs to be comfortable, requires light colors, no bare shoulders).
+4.  **Item Preference:** Ask the user if they have any specific preferences for an item type or silhouette (e.g., preference for a dress, skirt, tailored pants, or a particular neckline/length).
+
+GUIDANCE FOR RESPONSE GENERATION:
+-   After the user's initial request (e.g., "I want a chic outfit for dinner."), immediately reply with a friendly, targeted follow-up question to elicit the most crucial missing information (usually a combination of **Occasion** and **Style**).
+-   Be concise. Ask only 1 to 2 essential questions per turn.
+-   You must gather sufficient, clear intent before proceeding to actual clothing recommendations.
+
+OUTPUT FORMAT INSTRUCTION:
+-   **DO NOT** use any Markdown formatting whatsoever (e.g., do not use asterisks (*), bold text (**), lists, or code blocks).
+-   **ONLY** output the plain text response spoken by the AI Assistant.
+
+Example Follow-up (mimicking a conversational flow):
+User: I want a chic outfit for dinner.
+Your Response: Hey there! A chic dinner outfit, I love that! To give you the perfect recommendations, tell me: is this a romantic date, business dinner, or celebration with friends? And what's your go-to style vibe: classic elegance or something with more edge?"""
+
+SUMMARY_PROMPT = """
+You are an expert fashion request analyzer. Analyze the conversation history provided by the user.
+Your task is to:
+
+1. Identify the most appropriate occasions from the allowed list based on the user's intent.
+2. Write a detailed summary string that captures the user's style preferences, specific item requests, disliked items, body concerns, and color preferences. This summary will be used by a stylist to recommend outfits.
+
+Extract this information accurately from the chat history.
+"""
+
+
+from app.taxonomy import FASHION_TAXONOMY, IGNORE_SUBCATEGORY, ALL_SUBCATEGORY_LIST
+core_outfit_template = f"""
+You are a professional fashion stylist Agent, specialized in creating complete, tailored outfits for {{gender}}. Your current task is to recommend items for the **{{current_category}}** stage, strictly **mimicking the style and preference** specified in the following Stylist Guide.
+
+Your task is to **create a cohesive and complete outfit**, strictly adhering to **BOTH** the user's explicit **Request Summary** and the **Outfit Style Guide**. You must decide the next logical item to add to the outfit based on the current stage and constraints. Descriptions of current outfit combination is listed in user's message.
+
+---
+## Request from the User:
+{{request_summary}}
+
+## Core Guidance Document: Outfit Style Guide
+{{stylist_guide}}
+---
+
+## Your Workflow and Constraints
+
+1.  **Style Adherence**: You must strictly observe all rules in the Style Guide concerning **color palette, fit, layering principles, pattern restrictions , shoe coordination**.
+2.  **Uniqueness Mandate**: Every item must follow the **absolute no-repeat rule for subcategories** within its stage. Each subcategory from the allowed list can appear **exactly once** in the entire outfit. Furthermore, the categories 'dresses' and 'pants' and 'skirts' are mutually exclusive; they NORMALLY cannot be included in the same outfit.
+3.  **Step Planning**: The styling sequence must follow a logical approach (e.g., top-down, inside-out for clothing). Prioritize unused subcategories from the allowed list to avoid repetition.
+4.  **Structured Output**: Your output MUST be a valid JSON object. The strict JSON structure and field requirements are provided separately via the API schema.
+
+You must only output one of two actions: "recommend_item" or "stop".
+4.1. **recommend_item**: Use this action to suggest the next single item.
+   * **subcategory**: Must be strictly no repeats, and drawn from the allowed list.
+   * **description**: This must be an **extremely detailed and precise** description for the vector search. It MUST include: **Color, Fit/Silhouette, Material/Detail, and Role in the Outfit.**
+You must strictly use the **JSON format** for your output, as follows:
+```json
+{{{{
+"action": "recommend_item",
+"subcategory": "YOUR_ITEM_SUBCATEGORY",
+"description": "YOUR_DETAILED_DESCRIPTION",
+"reason": "YOUR_RECOMMENDATION_REASON"
+}}}}
+
+4.2. **stop**: Use this action when the Termination Condition is met.
+   * **reason**: This field is mandatory when stopping, and must clearly state why the outfit is complete.
+You must strictly use the **JSON format** for your output, as follows:
+{{{{
+"action": "stop",
+"subcategory": "",
+"description": "",
+"reason": "CORE_OUTFIT_COMPLETE"
+}}}}
+
+5.  **Termination Condition**: Terminate when the below condition is fully met：
+    5.1. **CLOTHING Stage**: The core clothing part of the outfit is complete, meaning the combination of items effectively achieves **full body coverage** (e.g., includes both a top/upper garment and a bottom/lower garment, or a single full-body piece like a dress/jumpsuit). Additionally, **all mandatory elements** stipulated in the Style Guide are satisfied. *(Note: Typically, {{max_len}} items are sufficient for this stage.)*
+    5.2. **SHOES Stage**: **Exactly one (1) item** has been successfully recommended, as shoes are a **mandatory component** for any complete outfit.
+    5.3. **BAGS Stage**: **Exactly one (1) item** has been successfully recommended, **OR** the recommendation is skipped if the Style Guide or the User Request **does not mandate** a bag for the specific occasion (i.e., the bag is considered optional).
+
+6.  **Context Dependency**: The user's next input (if not Start) will contain the **image and description of the selected item**. When recommending the next item:
+    a) First verify the subcategories of all already selected items to ensure no duplicates;
+    b) Select an unused subcategory from the allowed list as the priority;
+    c) Ensure the recommended item coordinates with the already selected items and complies with all rules in the Style Guide.
+Now, please start building an outfit (with strictly unique categories for all items) and output the JSON for the first item.
+"""
+
+
+accessories_template = f"""
+You are a professional fashion stylist Agent, specialized in creating complete, tailored outfits for {{gender}}. Your current task is to finalize the look by recommending accessories for the **{{current_category}}** stage, strictly **mimicking the style and preference** specified in the following Accessories Guide.
+
+Your final task is to **select the perfect set of accessories** to complete the given outfit. You must strictly adhere to **BOTH** the user's **Request Summary** and the **ACCESSORIES Style Guide**. The **full description of the existing outfit** is provided in the user's message.
+
+---
+## CONTEXT
+[User Request]: {{request_summary}}
+
+[Accessories Style Guide]:
+{{stylist_guide}}
+
+---
+## ACCESSORIES GENERATION RULES
+
+1. **Batch Recommendation**: You must output the **COMPLETE LIST of accessories** in a single response using the 'recommended_accessories' list defined in the schema. Do not recommend items one by one.
+2. **Quantity Constraint**: The total number of accessories recommended in the list must not exceed **{{max_len}}** items. Typically, 1 to {{max_len}} distinct items are required to complete a look.
+3. **Harmony & Guide Compliance**: 
+    - Assess the existing outfit (provided in the user's message) and ensure all accessories complement its style, color palette, and occasion.
+    - **Strictly follow the [Accessories Style Guide]** regarding material types (e.g., metals like gold/silver), total numbers allowed, and specific layering requirements (e.g., mandated watch or jewelry layering).
+4. **Exclusion List**: Subcategories in the following list are strictly excluded from recommendation: ({IGNORE_SUBCATEGORY}).
+5. **Description Quality**: The 'description' field for each accessory must be **extremely detailed and precise** for high-accuracy vector search, including: **Color, Material/Detail, and the specific Role in the Outfit.**
+
+Generate the final, complete accessories list now.
+"""
+
+all_items_template = f"""
+You are a professional fashion stylist Agent, specialized in creating complete, tailored outfits for {{gender}}. Your task is to **generate a Complete, Head-to-Toe Outfit** in a **Single Batch**, strictly **mimicking the style and preference** specified in the Stylist Guide.
+
+You must create a cohesive look that includes **Clothing, Shoes, Bags, and Accessories**. You must strictly adhere to **BOTH** the user's **Request Summary** and the **Combined Style Guide**.
+
+---
+## Request from the User:
+{{request_summary}}
+
+## Core Guidance Document: Combined Style Guide
+{{stylist_guide}}
+---
+
+## GENERATION WORKFLOW & RULES
+
+1.  **Holistic Styling**: You are NOT recommending items step-by-step. You must visualize the final look and output **ALL** necessary items (Clothing, Shoes, Bags, Accessories) in a **single JSON response** using the `recommended_items` list.
+
+2.  **Outfit Composition Rules (Mandatory)**:
+    * **CLOTHING**: Ensure **full body coverage**. You must include either [Top + Bottom] OR [One-piece (e.g., Dress/Jumpsuit)]. 'Dresses' and 'Skirts/Pants' are mutually exclusive.
+    * **SHOES**: **Exactly one (1) pair** of shoes is MANDATORY.
+    * **BAGS**: Recommend **0 or 1 bag**. Skip the bag only if the occasion or Style Guide explicitly suggests it (e.g., home wear, yoga).
+    * **ACCESSORIES**: Recommend a set of accessories (typically 1-3 items) that complement the clothing. Follow metal/material constraints in the guide.
+    Number of items in outfit must not exceed {{max_len}}.
+
+3.  **Uniqueness Mandate**: 
+    * Each **subcategory** belonging to CLOTHING (e.g., 't-shirts', 'sweaters', 'jacket') can appear **EXACTLY ONCE** in the entire list. 
+    * But **subcategory** belonging to ACCESSORIES can repeat.
+
+4.  **Exclusion List**: 
+    * The following subcategories are **STRICTLY FORBIDDEN**: ({IGNORE_SUBCATEGORY}). Do not include them in your recommendation.
+
+5.  **Style Adherence**: 
+    * Ensure all items coordinate in **color, fit, and material**.
+    * Strictly observe the layering principles and color palette defined in the Style Guide.
+
+6.  **Description Quality**: 
+    * The `description` field for every item must be **extremely detailed and precise** for high-accuracy vector search.
+    * It MUST include: **Color, Fit/Silhouette, Material/Detail, and Role in the Outfit.**
+
+## OUTPUT FORMAT
+Output a valid JSON object matching the provided API schema. The `recommended_items` array must contain all the items for this outfit.
+
+Generate the complete outfit list now.
+"""
+
+
+def build_iterative_schema(current_category):
+    schema = {
+        "type": "object",
+        "properties": {
+            "action": {"type": "string", "enum": ["recommend_item", "stop"]},
+            "subcategory": {
+                "type": "string",
+                "description": "The subcategory this single item. Only present if action is 'recommend_item'",
+                "enum": FASHION_TAXONOMY[current_category]
+            },
+            "description": {
+                "type": "string", 
+                "description": "an **extremely detailed and precise** description of the item. This description is used for **high-accuracy vector search** in the database. It should include Color, Fit/Silhouette, Material/Detail, Role in the Outfit."
+            },
+            "reason": {"type": "string", "description": "The reason for the current action. Required if action is 'stop' (to summarize the final outfit)."}
+        },
+        "required": ["action", "subcategory", "description", "reason"]
+    }
+    return schema
+
+
+def build_batch_schema(specified_category: str=""):
+    assert(specified_category in FASHION_TAXONOMY.keys() or specified_category == "")
+    if not specified_category:
+        category_range_desc = "the complete final outfit (including all categories)"
+        subcategory_list = ALL_SUBCATEGORY_LIST
+    else:
+        category_range_desc = specified_category
+        subcategory_list = FASHION_TAXONOMY[specified_category]
+    schema = {
+        "type": "object",
+        "properties": {
+            "reason": {
+                "type": "string",
+                "description": f"The justification for the selection of {category_range_desc}. This summary must explain how the recommended items meet the user's request and style requirements."
+            },
+            "recommended_items": {
+                "type": "array",
+                "description": "A list of descriptions of recommended items.",
+                "items": {
+                    "type": "object",
+                    "properties": {
+                        "description": {"type": "string", "description": f"The detailed description for this {specified_category} item."},
+                        "subcategory": {
+                            "type": "string",
+                            "description": "The subcategory of the recommended item.",
+                            "enum": subcategory_list
+                        },
+                    },
+                    "required": ["subcategory", "description"]
+                }
+            }
+        },
+        "required": ["recommended_items", "reason"]
+    }
+    return schema

app/server/ChatbotAgent/core/stylist_agent_server.py

@@ -1,36 +1,50 @@
-import asyncio
 import io
 import json
 import logging
 import os
-import random
-import uuid
 from typing import List, Dict, Any, Optional
+from copy import deepcopy
+import time
 
 from google import genai
 from google.cloud import storage
 from google.oauth2 import service_account
 
-from app.core.utils_litserve import merge_images_to_square
+from app.server.utils.img_operation import merge_images_to_square
 from app.server.utils.minio_client import minio_client, oss_upload_image
 from app.server.utils.request_post import post_request
+from app.config import settings
+from app.server.ChatbotAgent.core.prompt import (
+    core_outfit_template,
+    accessories_template,
+    all_items_template,
+    build_iterative_schema,
+    build_batch_schema
+)
+from app.taxonomy import FASHION_TAXONOMY, ALL_SUBCATEGORY_LIST
 
 logger = logging.getLogger(__name__)
 
 
 class AsyncStylistAgent:
-    CATEGORY_SET = {'Activewear', 'Watches', 'Shopping Totes', 'Underwear', 'Sunglasses', 'Dresses', 'Outerwear', 'Handbags', 'Backpacks', 'Belts', 'Hats', 'Skirts', 'Swimwear', 'Jewelry', 'Briefcases', 'Socks', 'Neckties', 'Pants', 'Suits', 'Shoes', 'Shirts & Tops', 'Scarves & Shawls'}
-
-    def __init__(self, local_db, max_len: int, gemini_model_name: str, outfit_id=str):
+    def __init__(self, local_db: str, gemini_model_name: str, outfit_id: str, stylist_name: str, gender: str):
         # self.outfit_items: List[Dict[str, str]] = []
         self.outfit_id = outfit_id
+        self.stylist_name = stylist_name
+        self.gender = gender
         self.gemini_client = genai.Client(
             vertexai=True, project='aida-461108', location='us-central1'
         )
         self.local_db = local_db
-        self.max_len = max_len
         self.gemini_model_name = gemini_model_name
         self.stop_reason = ""
+        self.headers = {
+            'Accept': "*/*",
+            'Accept-Encoding': "gzip, deflate, br",
+            'User-Agent': "PostmanRuntime-ApipostRuntime/1.1.0",
+            'Connection': "keep-alive",
+            'Content-Type': "application/json"
+        }
 
         # 存储桶配置
         try:
@@ -46,166 +60,97 @@ class AsyncStylistAgent:
         self.gcs_bucket = "lc_stylist_agent_outfit_items"
         self.minio_bucket = "lanecarford"
 
-    def _load_style_guide(self, path: str) -> str:
+    def _load_style_guide(self, stylist_name: str):
         """加载 markdown 风格指南内容。"""
-        parts = path.split('/', 1)
-        if len(parts) != 2:
-            raise ValueError("MinIO path must be in 'bucket_name/object_name' format.")
-
-        bucket_name, object_name = parts
+        guide_path = os.path.join(settings.STYLIST_GUIDE_DIR, f"{stylist_name}_en.md")
+        acc_guide_path = os.path.join(settings.STYLIST_GUIDE_DIR, f"{stylist_name}_acc.md")
         try:
-            # 1. 获取对象
-            response = minio_client.get_object(bucket_name, object_name)
-
-            # 2. 读取内容
-            content_bytes = response.read()
-
-            # 3. 关闭连接
-            response.close()
-            response.release_conn()
-
-            # 4. 解码并返回
-            return content_bytes.decode('utf-8')
-
+            with open(guide_path, 'r', encoding='utf-8') as file:
+                stylist_guide = file.read()
+            with open(acc_guide_path, 'r', encoding='utf-8') as file:
+                accessories_guide = file.read()
+            return stylist_guide, accessories_guide
         except Exception as e:
-            raise Exception(f"Failed to load style guide from {path}: {e}")
+            raise Exception(f"Failed to load style guide from {guide_path}, {acc_guide_path}: {e}")
 
-    def _build_system_prompt(self, request_summary: str = "", gender: str = "male") -> str:
-        """Constructs the complete System Prompt."""
-
-        clothing_gender = "women's clothing"
-        if gender == "male":
-            clothing_gender = "men's clothing"
-        elif gender == "female":
-            clothing_gender = "women's clothing"
-
-        # Insert the style_guide content into the template
-        template = f"""
-        You are a professional fashion stylist Agent, specialized in creating complete, tailored outfits exclusively for {clothing_gender}.
-
-        Your task is to **create a cohesive and complete outfit**, strictly adhering to **BOTH** the user's explicit **Request Summary** and the **Outfit Style Guide**. You must decide the next logical item to add to the outfit based on the currently selected items (if any).
-
-        ---
-
-        ## Request from the User:
-
-        {request_summary}
-
-        ## Core Guidance Document: Outfit Style Guide
-
-        {self.style_guide}
-
-        ---
-
-        ## Your Workflow and Constraints
-
-        1.  **Style Adherence**: You must strictly observe all rules in the Style Guide concerning **color palette, fit, layering principles, pattern restrictions, accessory stacking, and shoe/bag coordination**.
-        2.  **Step Planning**: The styling sequence must follow a **top-down, inside-out** approach: First major garments (tops/outerwear/bottoms/dresses), then shoes and bags, and finally accessories.
-        3.  **Structured Output**: Every response must recommend the **next single item**. You must strictly use the **JSON format** for your output, as follows:
-
-        ```json
-        {{
-        "action": "recommend_item",
-        "category": "YOUR_ITEM_CATEGORY",
-        "description": "YOUR_DETAILED_DESCRIPTION"
-        }}
-        ```
-
-        * `action`: Must always be `"recommend_item"` until the outfit is complete.
-        * `category`: Must be the category of the item you are recommending, strictly selected from the following list: {list(self.CATEGORY_SET)}.
-        * `description`: This must be an **extremely detailed and precise** description of the item. This description is used for **high-accuracy vector search** in the database and must include:
-            * **Color** (e.g., milk tea, pure white, dark gray)
-            * **Fit/Silhouette** (e.g., Oversize, loose, slim-fit)
-            * **Material/Detail** (e.g., 100% cotton, linen, gold clasp, thin stripe, checkered pattern)
-            * **Role in the Outfit** (e.g., serves as the innermost base layer for layering; acts as the crucial tie accent for the smart casual look)
-            * **[CRITICAL FOR JEWELRY] If recommending 'Jewelry' (especially Necklaces), the description must specify its distinction (length, thickness, pendant style) from all previously selected necklaces to ensure layered variety.**
-
-        4.  **Termination Condition**: Only when you deem the entire outfit complete and **all mandatory elements stipulated in the Style Guide are met**, you must output the following JSON format to terminate the process:
-
-        ```json
-        {{
-        "action": "stop",
-        "reason": "OUTFIT_COMPLETE_AND_MEETS_ALL_MINI_GUIDELINES"
-        }}
-        ```
-        Normally, five or six items are totally enough for an outfit.
-
-        5.  **Context Dependency**: The user's next input (if not `Start`) will contain the **image and description of the selected item**. When recommending the next item, you must consider the coordination between the **already selected items** and the Style Guide.
-
-        **Now, please start building an outfit and output the JSON for the first item.**
+    async def _call_gemini(self, user_input: str, user_id: str, file_name: str, output_schema: Dict[str, Any], image_bytes: bytes = None, system_prompt: str = "") -> str:
         """
-        return template.strip()
-
-    def _clear_uploaded_files(self):
-        for f in self.gemini_client.files.list():
-            self.gemini_client.files.delete(name=f.name)
-
-    async def _call_gemini(self, user_input: str, user_id: str):
-        """
-        实际调用 Gemini API 的函数，接受文本和可选的图片路径列表。
+        实际调用 Gemini API 的函数，接受文本和用户的id。
+        会在这个函数中merge图片，然后上传到google cloud，供gemini参考。
         
         Args:
             user_input: 发送给模型的主文本内容。
-            image_paths: 待发送图片的本地路径列表。
+            user_id: 用户id。
+            file_name: 用于存储图片的文件名。
+            image_bytes: 可选的图片字节数据。
             
         Returns:
             模型的响应文本（预期为 JSON 字符串）。
         """
-        minio_path = ""
         content_parts = []
-        # self._clear_uploaded_files()
         # 1. 添加图片内容
-        if self.outfit_items:
-            merged_image = merge_images_to_square(self.outfit_items, max_len=self.max_len, add_text=False)
-            image_bytes_io = io.BytesIO()
-            image_format = 'JPEG'
-            mime_type = 'image/jpeg'
-
-            merged_image.save(image_bytes_io, format=image_format)
-            image_bytes = image_bytes_io.getvalue()
-
-            file_name = uuid.uuid4()
+        if image_bytes:
             blob_name = f"lc_stylist_agent_outfit_items/{user_id}/{file_name}.jpg"
-            gcs_path = self._upload_to_gcs(bucket_name=self.gcs_bucket, blob_name=blob_name, mime_type=mime_type, image_bytes=image_bytes)
-            responses = oss_upload_image(oss_client=minio_client, bucket=self.minio_bucket, object_name=blob_name, image_bytes=image_bytes)
-            minio_path = f"{responses.bucket_name}/{responses.object_name}"
+            gcs_path = self._upload_to_gcs(bucket_name=self.gcs_bucket, blob_name=blob_name, mime_type='image/jpeg', image_bytes=image_bytes)
             content_parts.append(gcs_path)
 
         # 2. 添加文本内容
         content_parts.append(user_input)
 
-        # print(f"\n--- Calling Gemini with {len(self.outfit_items) if self.outfit_items else 0} images and query:\n{user_input}")
-
         try:
             # 3. 实际 API 调用
             response = await self.gemini_client.aio.models.generate_content(
                 model=self.gemini_model_name,
                 contents=content_parts,
                 config={
-                    "system_instruction": self.system_prompt,
+                    "system_instruction": system_prompt,
                     # 确保模型返回 JSON 格式
                     "response_mime_type": "application/json",
-                    "response_schema": {
-                        "type": "object",
-                        "properties": {
-                            "action": {"type": "string", "enum": ["recommend_item", "stop"]},
-                            "category": {"type": "string"},
-                            "description": {"type": "string"},
-                            "reason": {"type": "string"}
-                        },
-                        "required": ["action"]
-                    }
+                    "response_schema": output_schema
                 }
             )
 
             # response.text 将包含一个 JSON 字符串
-            return response.text, minio_path
+            return response.text
 
         except Exception as e:
             print(f"Gemini API Call failed: {e}")
             # 返回一个停止信号以防止循环继续
             return json.dumps({"action": "stop", "reason": f"API_ERROR: {str(e)}"})
 
+    async def _merge_images(self, file_name: str, user_id: str, stylist_name: str):
+        """
+        把所有的item图片组成一张图片并保存到jpg文件
+
+        Args:
+            user_id: 用户的id
+            stylist_name: 造型师的name
+
+        Returns:
+            (存储的路径, 内存图片数据)
+        """
+        if not self.outfit_items:
+            return "", None
+        merged_image = merge_images_to_square(self.outfit_items, max_len=9, add_text=False)
+        image_bytes_io = io.BytesIO()
+        image_format = 'JPEG'
+        merged_image.save(image_bytes_io, format=image_format)
+        image_bytes = image_bytes_io.getvalue()
+        if settings.LOCAL == 1:
+            local_dir = os.path.join(settings.OUTFIT_OUTPUT_DIR, stylist_name)
+            os.makedirs(local_dir, exist_ok=True)
+            local_file_path = os.path.join(local_dir, f"{file_name}.jpg")
+
+            with open(local_file_path, 'wb') as f:
+                f.write(image_bytes)
+            return local_file_path, image_bytes
+        else:
+            # minio文件地址需保持变动，否则前端缓存导致无法更新图片
+            blob_name = f"lc_stylist_agent_outfit_items/{user_id}/{file_name}-{len(self.outfit_items)}.jpg"
+            responses = oss_upload_image(oss_client=minio_client, bucket=self.minio_bucket, object_name=blob_name, image_bytes=image_bytes)
+            minio_path = f"{responses.bucket_name}/{responses.object_name}"
+            return minio_path, image_bytes
+
     def _parse_gemini_response(self, response_text: str) -> Optional[Dict[str, Any]]:
         """安全解析 Gemini 的 JSON 响应。"""
         try:
@@ -219,177 +164,360 @@ class AsyncStylistAgent:
             print(f"Raw response: {response_text}")
             return None
 
-    def _get_next_item(self, item_description: str, category: str) -> Optional[Dict[str, str]]:
+    def _get_next_item(self, item_description: str, category: str, subcategory: str, occasions: List[str], batch_sources: List[str] = [], gender: str = "female") -> Optional[Dict[str, str]]:
         """
         1. 根据描述生成嵌入。
         2. 查询本地数据库以找到最佳匹配项。
         3. 模拟 Agent 审核匹配项(这里简化为总是通过)。
         """
+        # 1. 生成查询嵌入
+        query_embedding = self.local_db.get_clip_embedding(item_description, is_image=False)
+
+        # 2. 执行查询,并过滤类别
         try:
-            # 1. 生成查询嵌入
-            query_embedding = self.local_db.get_clip_embedding(item_description, is_image=False)
+            results = self.local_db.get_matched_item(
+                query_embedding,
+                category,
+                occasions=occasions,
+                batch_sources=batch_sources,
+                gender=gender,
+                n_results=1
+            )
+        except ValueError as e:
+            print(f"检测到无效参数错误：{e}")
+            results = []
 
-            # 2. 执行查询,并过滤类别
-            results = self.local_db.query_local_db(query_embedding, category, n_results=1)
-
-            if not results:
-                print(f"❌ 数据库中未找到符合 '{category}' 和描述的单品。")
-                return None
-
-            # 3. 模拟 Agent 审核(实际应用中,你需要将图片发回给 Agent进行审核)
-            best_meta = results['metadatas'][0][0]  # 第一个 batch 的第一个 metadata
-            return {
-                "item_id": best_meta['item_id'],  # 从 metadata 字典中安全获取
-                "category": category,
-                "gpt_description": item_description,
-                'description': best_meta['description'],
-                # 假设 'item_path' 存储在 metadata 中，或从 'item_id' 推导
-                # 这里假设 item_id 就是文件名的一部分
-                "image_path": os.path.join(f"{best_meta['item_id']}.jpg")
-            }
-
-        except Exception as e:
-            print(f"An error occurred during item retrieval: {e}")
+        if not results:
+            print(f"数据库中未找到符合 '{category}' 和描述的单品。")
             return None
 
-    def _build_user_input(self) -> str:
+        # 3. 模拟 Agent 审核(实际应用中,你需要将图片发回给 Agent进行审核)
+        best_meta = results[0]  # 第一个 batch 的第一个 metadata
+        item_id = best_meta['item_id'].replace("_img", "")
+        batch_source = best_meta['batch_source']
+        return {
+            "item_id": item_id,  # 从 metadata 字典中安全获取
+            "category": best_meta['category'],
+            'description': best_meta['description'],
+            "subcategory": best_meta['subcategory'],
+            "gpt_description": item_description,
+            "gpt_subcategory": subcategory,
+            # 假设 'item_path' 存储在 metadata 中，或从 'item_id' 推导
+            # 这里假设 item_id 就是文件名的一部分
+            "image_path": os.path.join(settings.DATA_ROOT, batch_source, 'image_data', f"{item_id}.jpg")
+        }
+
+    def _build_system_prompt(self, template: str, request_summary: str = "", stylist_guide: str = "", current_category: str = "clothing", max_len: int = 4) -> str:
+        # Insert the style_guide content into the template
+        sys_template = template.format(
+            gender=self.gender,
+            current_category=current_category.upper(),
+            request_summary=request_summary,
+            stylist_guide=stylist_guide,
+            max_len=max_len
+        )
+        return sys_template.strip()
+
+    def _build_user_input(self, current_category: str, existing_subcategories: str) -> str:
         """构建发送给 Gemini 的用户输入,包含已选单品信息。"""
         if not self.outfit_items:
-            return "Start"
+            context = ""
+        else:
+            context = "Selected fashion items:\n"
 
         # 将已选单品的信息作为上下文发回给 Agent
-        context = "Selected fashion items:\n"
         for ii, item in enumerate(self.outfit_items):
-            context += f"{ii + 1}. Category: {item['category']}. Description: {item['description']}\n"
-        context += "\nPlease recommend the next single item based on the selected items, user's request, and style guide."
+            context += f"{ii + 1}. Category: {item['category']}. Subcategory: {item['subcategory']}. Description: {item['description']}\n"
+
+        if current_category == 'clothing':
+            context += f"\nRecommend the next single item based on the selected items, user's request, and style guide. 【CRITICAL CONSTRAINT】You MUST strictly **maintain uniqueness**; do not recommend any clothing whose **Subcategory** is already present in this exclusion list: {existing_subcategories}."
+        elif current_category in ['shoes', 'bags']:
+            context += f"\nRecommend the next {current_category} based on the selected items, user's request, and style guide."
+        elif current_category == 'accessories':
+            context += f"\nRecommend a complete list of accessories to complement the selected outfit based on the user's request and accessories style guide. 【CRITICAL CONSTRAINT】You MUST strictly **maintain uniqueness**; do not recommend any accessories whose **Subcategory** is already present in this exclusion list: {existing_subcategories}."
+        elif current_category == 'all':
+            context += "\nRecommend a **complete, full outfit**, including all items (clothing, shoes, bags, and accessories), strictly following the Request Summary and Style Guide. Output the **complete list** of items in a single JSON response."
         return context
 
-    async def run_styling_process(self, request_summary, stylist_path, start_outfit=None, user_id="test", callback_url="", gender: str = "male"):
-        if start_outfit is None:
-            start_outfit = []
-        self.outfit_items = start_outfit if start_outfit else []
-        """主流程控制循环。"""
-        print(f"--- Starting Agent (Outfit ID: {self.outfit_id}) ---")
+    def post_operation(self, status: str, message: str, callback_url: str, img_path: str):
+        """处理完成后的回调操作。"""
+        if settings.LOCAL == 0:
+            # 生产回调请求数据处理
+            items = []
+            for item in self.outfit_items:
+                items.append(
+                    {
+                        "item_id": item['item_id'],
+                        "category": item['subcategory']
+                    }
+                )
+            response_data = {
+                'items': items,
+                'status': status,
+                # 'message': message,
+                'path': img_path,
+                'outfit_id': self.outfit_id
+            }
+            response = post_request(url=callback_url, data=json.dumps(response_data), headers=self.headers)
+            logger.info(f"request data ：{json.dumps(response_data, ensure_ascii=False, indent=2)} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
+            return response_data
+        else:
+            return {}
 
-        self.style_guide = self._load_style_guide(stylist_path)
-        self.system_prompt = self._build_system_prompt(request_summary, gender)
-        response_data = {"status": "",
-                         "message": "",
-                         "path": "",
-                         "outfit_id": self.outfit_id,
-                         "items": []
-                         }
-        logger.info(response_data)
-        item_id = ""
-        item_category = ""
-        headers = {
-            'Accept': "*/*",
-            'Accept-Encoding': "gzip, deflate, br",
-            'User-Agent': "PostmanRuntime-ApipostRuntime/1.1.0",
-            'Connection': "keep-alive",
-            'Content-Type': "application/json"
-        }
-        url = f'{callback_url}/api/style/callback'
-        while True:
+    async def _execute_iterative_recommendation(
+            self,
+            current_category: str,
+            system_prompt: str,
+            schema: Dict,
+            max_len: int,
+            occasions: List[str],
+            batch_sources: List[str],
+            user_id: str,
+            url: str
+    ):
+        recommend_timestep = 0
+        gemini_data = {'action': 'start'}
+        existing_subcategories = []
+        while recommend_timestep < max_len and gemini_data.get('action') != 'stop':
+            recommend_timestep += 1
             # 1. 准备用户输入(上下文)
-            user_input = self._build_user_input()
+            user_input = self._build_user_input(current_category, ", ".join(existing_subcategories))
 
-            # 2. 调用 Gemini Agent
-            gemini_response_text, minio_path = await self._call_gemini(user_input, user_id)
+            # 2. 把图片组装起来供api调用
+            merged_image_path, image_bytes = await self._merge_images(self.outfit_id, user_id, self.stylist_name)
+
+            # 3. 调用 Gemini Agent
+            gemini_response_text = await self._call_gemini(
+                user_input,
+                user_id,
+                self.outfit_id,
+                schema,
+                image_bytes,
+                system_prompt
+            )
             gemini_data = self._parse_gemini_response(gemini_response_text)
-            response_data['path'] = minio_path
-            if item_id:
-                response_data['items'].append({"item_id": item_id, "category": item_category})
 
             if not gemini_data:
-                # if gemini_data:
-                print("🚨 Agent 返回无效响应,终止流程。")
-                self.stop_reason = "Agent failed to return response"
-                response_data['status'] = "failed"
-                response_data['message'] = self.stop_reason
-                response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
+                print("Agent 返回无效响应,终止流程。")
+                self.post_operation(
+                    status="failed",
+                    message="Agent returned invalid response, terminating process.",
+                    callback_url=url,
+                    img_path=merged_image_path,
+                )
                 break
 
-            # 3. 检查终止条件
-            if gemini_data.get('action') == 'stop':
-                print(f"🛑 搭配完成,终止原因: {gemini_data.get('reason')}")
-                self.stop_reason = "Finish reason: " + gemini_data.get('reason', 'No reason provided')
-                response_data['status'] = "stop"
-                response_data['message'] = self.stop_reason
-                response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
-                break
-
-            # 4. 处理推荐单品
+            # 处理推荐单品
             if gemini_data.get('action') == 'recommend_item':
-                category = gemini_data.get('category')
+                subcategory = gemini_data.get('subcategory')
                 description = gemini_data.get('description')
 
                 # 4a. 检查类别是否有效 (重要步骤)
-                if category not in self.CATEGORY_SET:
-                    print(f"❌ Agent 推荐了无效类别: {category}。要求 Agent 重新输出。")
-                    # 在实际应用中,这里需要将错误信息发回给 Agent,要求它更正
-                    # 这里简化为跳过本次循环
-                    response_data['status'] = "continue"
-                    response_data['message'] = f"❌ Agent 推荐了无效类别: {category}。要求 Agent 重新输出。",
-                    response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                    logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
+                if subcategory not in FASHION_TAXONOMY[current_category]:
+                    self.post_operation(
+                        status="continue",
+                        message=f"Invalid subcategory recommended by Agent: {subcategory}. Requesting Agent to re-output.",
+                        callback_url=url,
+                        img_path=merged_image_path,
+                    )
                     continue
 
                 # 4b. 在本地 DB 中查询单品
-                new_item = self._get_next_item(description, category)
-                item_id = new_item.get('item_id')
-                item_category = new_item.get('category')
-
-                if new_item:
-                    # 4c. (实际步骤) 将选中的单品图片和描述发回给 Agent 进行最终审核
-                    # 这里的代码框架省略了图片回传和二次审核的步骤,直接视为通过
-                    # 实际你需要： new_user_input = f"Check this item: {new_item['description']}, path: {new_item['image_path']}"
-                    #              call_gemini_agent(...) -> 如果返回"pass",则添加到outfit_items
-
-                    if new_item['item_id'] in [x['item_id'] for x in self.outfit_items]:
-                        print("This item exists. Stop here.")
-                        self.stop_reason = "Finish reason: Duplicate item selected."
-                        response_data['status'] = "stop"
-                        response_data['message'] = self.stop_reason
-                        response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                        logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
-                        break
-
-                    if new_item['item_id'] == "ELG383":
-                        if random.random() < 0.70:
-                            self.stop_reason = "Finish reason: ELG383 is seleced repeatly."
-                            response_data['status'] = "stop"
-                            response_data['message'] = self.stop_reason
-                            response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                            logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
-                            break
-
-                    self.outfit_items.append(new_item)
-                    # print(f"➕ 成功添加单品: {new_item['category']} ({new_item['item_id']}). 当前搭配数量: {len(self.outfit_items)}")
-                    response_data['status'] = "ok"
-                    response_data['message'] = self.stop_reason
-                    response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                    logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
+                new_item = self._get_next_item(description, current_category, subcategory, occasions, batch_sources, self.gender)
+                if not new_item:
+                    self.post_operation(
+                        status="continue",
+                        message=f"No matching item is found. Ask Gemini to re-output.",
+                        callback_url=url,
+                        img_path=merged_image_path,
+                    )
+                    continue
+                elif new_item['subcategory'] in [x['subcategory'] for x in self.outfit_items]:
+                    self.post_operation(
+                        status="continue",
+                        message=f"{new_item['item_id']}'s subcategory {new_item['subcategory']} duplicated. Ask Gemini to re-output.",
+                        callback_url=url,
+                        img_path=merged_image_path,
+                    )
+                    continue
+                elif new_item['item_id'] in [x['item_id'] for x in self.outfit_items]:
+                    self.post_operation(
+                        status="continue",
+                        message=f"Item {new_item['item_id']} duplicated. Ask Gemini to re-output.",
+                        callback_url=url,
+                        img_path=merged_image_path,
+                    )
+                    continue
                 else:
-                    print("⚠️ 未找到匹配单品,无法继续搭配。终止。")
-                    self.stop_reason = "Finish reason: No matching item found in local database."
-                    response_data['status'] = "stop"
-                    response_data['message'] = self.stop_reason
-                    response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                    logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
-                    break
+                    self.outfit_items.append(new_item)
+                    existing_subcategories.append(new_item["subcategory"])
+                    self.post_operation(
+                        status="ok",
+                        message=f"Add new item {new_item['item_id']} in category {new_item['category']} successfully.",
+                        callback_url=url,
+                        img_path=merged_image_path,
+                    )
+                    print(f"Stage {current_category.upper()}, Step {recommend_timestep}: {gemini_data}, found item: {new_item['item_id']}")
 
-            if len(self.outfit_items) >= self.max_len:  # 设置一个最大循环限制,防止无限循环
-                logger.info("🚨 达到最大搭配数量限制,强制终止。")
-                self.stop_reason = "Finish reason: Reached max outfit length."
-                response_data['status'] = "stop"
-                response_data['message'] = self.stop_reason
-                response = post_request(url=url, data=json.dumps(response_data), headers=headers)
-                logger.info(f"request data ：{response_data} | JAVA callback info -> status:{response.status_code} | message:{response.text}")
-                break
-        return response_data
+    async def _execute_batch_recommendation(
+            self,
+            current_category: str,  # this can be any category or all
+            system_prompt: str,
+            schema: Dict,
+            occasions: List[str],
+            batch_sources: List[str],
+            user_id: str,
+            url: str
+    ):
+        user_input = self._build_user_input(current_category, existing_subcategories=", ".join([x['subcategory'] for x in self.outfit_items]))
+        # 合并图片
+        merged_image_path, image_bytes = await self._merge_images(self.outfit_id, user_id, self.stylist_name)
+        # 调用Gemini API
+        gemini_response_text = await self._call_gemini(
+            user_input,
+            user_id,
+            self.outfit_id,
+            schema,
+            image_bytes,
+            system_prompt
+        )
+        # 解析响应
+        gemini_data = self._parse_gemini_response(gemini_response_text)
+        recommended_items = gemini_data.get('recommended_items', [])
+        reason = gemini_data.get('reason', '')
+
+        if not recommended_items or not isinstance(recommended_items, List):
+            print("No recommended item from Gemini, terminating process.")
+            self.post_operation(
+                status="failed",
+                message="Agent returned invalid response, terminating process.",
+                callback_url=url,
+                img_path=merged_image_path
+            )
+        else:
+            for idx, rec_item in enumerate(recommended_items):
+                subcategory = rec_item.get('subcategory')
+                description = rec_item.get('description')
+
+                # 4a. 检查类别是否有效 (重要步骤)
+                if subcategory not in ALL_SUBCATEGORY_LIST:
+                    continue
+
+                # 4b. 在本地 DB 中查询单品
+                # we need first determine the category if current category is 'all'
+                if current_category == "all":
+                    for category, subcategories_list in FASHION_TAXONOMY.items():
+                        # 将子类别列表转换为集合 (set) 可以提高查找效率，
+                        # 特别是当列表很长时。
+                        if subcategory in subcategories_list:
+                            break
+                else:
+                    category = current_category
+
+                new_item = self._get_next_item(description, category, subcategory, occasions, batch_sources, self.gender)
+                if not new_item or new_item['item_id'] in [x['item_id'] for x in self.outfit_items]:
+                    continue
+                else:
+                    self.outfit_items.append(new_item)
+                    print(f"Item {idx + 1}: ({subcategory}) {rec_item}, found item: {new_item}")
+        return reason
+
+    async def run_iterative_styling(self, request_summary, occasions, start_outfit: Optional[List] = None, batch_sources: List = [], user_id="test", callback_url=""):
+        start_time = time.monotonic()
+        STAGES = ['clothing', 'shoes', 'bags']
+        # 深拷贝start_outfit 避免实例之间的参数泄漏 确保每个实例都有自己的 start_outfit 副本
+        if start_outfit is None:
+            self.outfit_items = []
+        else:
+            self.outfit_items = deepcopy(start_outfit)
+        stylist_guide, accessories_guide = self._load_style_guide(self.stylist_name)
+        url = f'{callback_url}/api/style/callback'
+
+        """主流程控制循环。"""
+        print(f"--- Starting Agent (Outfit ID: {self.outfit_id}) ---")
+        for current_category in STAGES:
+            max_len = 4 if current_category == 'clothing' else 1
+            system_prompt = self._build_system_prompt(core_outfit_template, request_summary, stylist_guide, current_category, max_len)
+
+            await self._execute_iterative_recommendation(
+                current_category,
+                system_prompt,
+                build_iterative_schema(current_category),
+                max_len,
+                occasions,
+                batch_sources,
+                user_id,
+                url
+            )
+
+        # 根据stylist要求增加配饰 3-4个配饰
+        MAX_LEN_ACC = 3
+        acc_system_prompt = self._build_system_prompt(accessories_template, request_summary, accessories_guide, 'accessories', MAX_LEN_ACC)
+        reason = await self._execute_batch_recommendation(
+            'accessories',  # can be 'accessories' or 'all'
+            acc_system_prompt,
+            build_batch_schema(current_category),
+            occasions,
+            batch_sources,
+            user_id,
+            url
+        )
+
+        final_image_path, _ = await self._merge_images(self.outfit_id, user_id, self.stylist_name)
+        response_data = self.post_operation(
+            status="stop",
+            message=reason,
+            callback_url=url,
+            img_path=final_image_path
+        )
+        if settings.LOCAL == 1:
+            with open(os.path.join(settings.OUTFIT_OUTPUT_DIR, self.stylist_name, f'{self.outfit_id}.json'), 'w') as f:
+                json.dump({"request_summary": request_summary, "occasions": occasions, "items": self.outfit_items}, f, indent=2)
+
+        end_time = time.monotonic()
+        total_duration = end_time - start_time
+
+        return response_data, total_duration
+
+    async def run_quick_batch_styling(self, request_summary, occasions, start_outfit: Optional[List] = None, batch_sources: List = [], user_id="test", callback_url=""):
+        start_time = time.monotonic()
+        # 深拷贝start_outfit 避免实例之间的参数泄漏 确保每个实例都有自己的 start_outfit 副本
+        if start_outfit is None:
+            self.outfit_items = []
+        else:
+            self.outfit_items = deepcopy(start_outfit)
+        stylist_guide, accessories_guide = self._load_style_guide(self.stylist_name)
+        url = f'{callback_url}/api/style/callback'
+
+        print(f"--- Starting Agent (Outfit ID: {self.outfit_id}) ---")
+
+        MAX_LEN = 9
+        system_prompt = self._build_system_prompt(all_items_template, request_summary, stylist_guide + accessories_guide, "", MAX_LEN)
+        reason = await self._execute_batch_recommendation(
+            'all',  # can be 'accessories' or 'all'
+            system_prompt,
+            build_batch_schema(),
+            occasions,
+            batch_sources,
+            user_id,
+            url
+        )
+
+        final_image_path, _ = await self._merge_images(self.outfit_id, user_id, self.stylist_name)
+        response_data = self.post_operation(
+            status="stop",
+            message=reason,
+            callback_url=url,
+            img_path=final_image_path
+        )
+        if settings.LOCAL == 1:
+            with open(os.path.join(settings.OUTFIT_OUTPUT_DIR, self.stylist_name, f'{self.outfit_id}.json'), 'w') as f:
+                json.dump({"request_summary": request_summary, "occasions": occasions, "items": self.outfit_items}, f, indent=2)
+
+        end_time = time.monotonic()
+        total_duration = end_time - start_time
+
+        return response_data, total_duration
 
     def _upload_to_gcs(self, bucket_name: str, blob_name: str, mime_type, image_bytes) -> str:
         """同步方法：将文件上传到 GCS 并返回 GCS URI。"""

app/server/ChatbotAgent/core/system_prompt.py

@@ -1,56 +0,0 @@
-BASIC_PROMPT = """"""
-WOMEN_BASIC_PROMPT = """You are a professional, friendly, and insightful AI women's styling assistant.
-
-Your primary mission is to engage in a multi-turn conversation with the user to fully understand their dressing intent. You must adopt a professional yet approachable tone.
-
-CONVERSATION GOALS:
-1.  **Occasion:** Determine the specific event (e.g., romantic dinner, summer wedding, business meeting).
-2.  **Style:** Pinpoint the desired aesthetic (e.g., classic elegance, edgy, minimalist, bohemian).
-3.  **Vibe/Details:** Gather any mood or specific constraints (e.g., needs to be comfortable, requires light colors, no bare shoulders).
-4.  **Item Preference:** Ask the user if they have any specific preferences for an item type or silhouette (e.g., preference for a dress, skirt, tailored pants, or a particular neckline/length).
-
-GUIDANCE FOR RESPONSE GENERATION:
--   After the user's initial request (e.g., "I want a chic outfit for dinner."), immediately reply with a friendly, targeted follow-up question to elicit the most crucial missing information (usually a combination of **Occasion** and **Style**).
--   Be concise. Ask only 1 to 2 essential questions per turn.
--   You must gather sufficient, clear intent before proceeding to actual clothing recommendations.
-
-OUTPUT FORMAT INSTRUCTION:
--   **DO NOT** use any Markdown formatting whatsoever (e.g., do not use asterisks (*), bold text (**), lists, or code blocks).
--   **ONLY** output the plain text response spoken by the AI Assistant.
-
-Example Follow-up (mimicking a conversational flow):
-User: I want a chic outfit for dinner.
-Your Response: Hey there! A chic dinner outfit, I love that! To give you the perfect recommendations, tell me: is this a romantic date, business dinner, or celebration with friends? And what's your go-to style vibe: classic elegance or something with more edge?"""
-MEN_BASIC_PROMPT = """You are a professional, friendly, and insightful AI men's styling assistant.
-
-Your primary mission is to engage in a multi-turn conversation with the user to fully understand their dressing intent. You must adopt a professional yet approachable tone.
-
-CONVERSATION GOALS:
-1.  **Occasion:** Determine the specific event (e.g., romantic dinner, summer wedding, business meeting).
-2.  **Style:** Pinpoint the desired aesthetic (e.g., classic elegance, edgy, minimalist, bohemian).
-3.  **Vibe/Details:** Gather any mood or specific constraints (e.g., needs to be comfortable, requires light colors, no bare shoulders).
-4.  **Item Preference:** Ask the user if they have any specific preferences for an item type or silhouette (e.g., preference for a dress, skirt, tailored pants, or a particular neckline/length).
-
-GUIDANCE FOR RESPONSE GENERATION:
--   After the user's initial request (e.g., "I want a chic outfit for dinner."), immediately reply with a friendly, targeted follow-up question to elicit the most crucial missing information (usually a combination of **Occasion** and **Style**).
--   Be concise. Ask only 1 to 2 essential questions per turn.
--   You must gather sufficient, clear intent before proceeding to actual clothing recommendations.
-
-OUTPUT FORMAT INSTRUCTION:
--   **DO NOT** use any Markdown formatting whatsoever (e.g., do not use asterisks (*), bold text (**), lists, or code blocks).
--   **ONLY** output the plain text response spoken by the AI Assistant.
-
-Example Follow-up (mimicking a conversational flow):
-User: I want a chic outfit for dinner.
-Your Response: Hey there! A chic dinner outfit, I love that! To give you the perfect recommendations, tell me: is this a romantic date, business dinner, or celebration with friends? And what's your go-to style vibe: classic elegance or something with more edge?"""
-
-SUMMARY_PROMPT = """Analyze the following chat history. Your task is to extract all user intentions, scenarios, style preferences, and constraints expressed during the conversation, and distill them into a concise, structured JSON object.
-
-**YOUR OUTPUT MUST BE A JSON OBJECT ONLY, WITH NO SURROUNDING TEXT, MARKDOWN, OR EXPLANATION.**
-
-JSON FIELD REQUIREMENTS:
--   **occasion (string):** The specific event and purpose (e.g., "Romantic date dinner", "Summer outdoor wedding", "Casual Friday at office").
--   **style (string):** The overall aesthetic description (e.g., "Classic elegance", "Modern minimalist", "Bohemian vibe", "Edgy and contemporary").
--   **color_preference (string or list):** User's preferred or excluded colors/tones (e.g., "Light colors only", "Avoid deep shades", "['Cream', 'Pale Blue']", "No preference").
--   **clothing_type (string):** User's preference for specific garment types, material, or silhouette (e.g., "Lightweight maxi dress", "Skirt with silk blouse", "Tailored wide-leg pants", "Floral print").
--   **vibe_or_details (string):** Any other details, mood requirements, or specific constraints (e.g., "Needs to be comfortable and breathable", "Accent on accessories", "Must cover shoulders")."""

app/server/ChatbotAgent/core/vector_database.py

@@ -1,18 +1,25 @@
+import numpy as np
 import torch
 import chromadb
 from PIL import Image
 from typing import List, Dict, Any
 from transformers import CLIPProcessor, CLIPModel
 
+from app.taxonomy import OCCASION, CATEGORY_LIST, IGNORE_SUBCATEGORY
+
 
 class VectorDatabase():
     def __init__(self, vector_db_dir: str, collection_name: str, embedding_model_name: str):
         self.client = chromadb.PersistentClient(path=vector_db_dir)
-
-        self.collection = self.client.get_or_create_collection(name=collection_name)
-
+        self.collection = self.client.get_or_create_collection(
+            name=collection_name, 
+            configuration={
+                "hnsw": {
+                    "space": "cosine",
+                }
+            }
+        )
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
-
         self.model = CLIPModel.from_pretrained(embedding_model_name).to(self.device)
         self.processor = CLIPProcessor.from_pretrained(embedding_model_name)
 
@@ -38,23 +45,75 @@ class VectorDatabase():
         features = features / features.norm(p=2, dim=-1, keepdim=True)
 
         return features.cpu().numpy().flatten().tolist()
+        
+    def get_matched_item(self, embedding: List[float], category: str, occasions: List[str] = [], batch_sources: List[str] = [], gender: str = 'female', n_results: int = 1) -> List[Dict[str, Any]]:
+        if category not in CATEGORY_LIST:
+            raise ValueError(f"Recommended {category} is not valid.")
+        
+        and_conditions = [
+            {"category": category},
+            {"modality": "image"},
+            {"$or": [
+                {"gender": gender},
+                {"gender": "unisex"},
+            ]},
+            {"subcategory": {"$nin": IGNORE_SUBCATEGORY}}
+        ]
+        if batch_sources and len(batch_sources) > 0:
+            if len(batch_sources) == 1:
+                and_conditions.append({"batch_source": batch_sources[0]})
+            else:
+                source_conditions = []
+                for source in batch_sources:
+                    source_conditions.append({"batch_source": source})
+
+                # 将 Batch Source 的 OR 子句添加到主 AND 条件中
+                and_conditions.append({"$or": source_conditions})
 
-    def query_local_db(self, embedding: List[float], category: str, n_results: int = 3) -> List[Dict[str, Any]]:
-        """
-        基于嵌入向量在本地数据库中查询相似单品。
-        实际应执行 ChromaDB 查询,并根据 category 进行过滤(metadatas)。
-        """
-        # 实际应执行向量查询
-        # 为了演示流程,返回一个模拟结果
         results = self.collection.query(
             query_embeddings=[embedding],
-            n_results=n_results,
-            where={
-                "$and": [
-                    {"category": category},
-                    {"modality": "image"},
-                ]
-            },
-            include=['documents', 'metadatas', 'distances']
+            n_results=500,
+            where={"$and": and_conditions},
+            include=['metadatas', 'distances'],
         )
-        return results
+        if not results['ids'][0]:
+            return []
+        
+        metadatas = results['metadatas'][0]  # List[Dict[str, Any]]
+        final_scores = []
+        for idx, metadata in enumerate(metadatas):
+            dist_img = results['distances'][0][idx]
+            score_vec = 1 - dist_img  # cosine similarity range: [-1, 1]
+
+            score_occ = 0.0
+            if occasions:
+                count = 0
+                for occ in occasions:
+                    if occ not in OCCASION:
+                        continue
+                    count += 1
+                    status_val = metadata.get(occ, -1)
+                    if status_val == 1:
+                        score_occ += 1.0
+                    elif status_val == 0:
+                        score_occ += 0.0
+                    else:
+                        score_occ -= 100.0
+
+                score_occ = score_occ / count if count else 0.0
+
+            final_score = 0.6 * score_vec + 0.4 * score_occ
+            final_scores.append(final_score)
+
+        scores_arr = np.array(final_scores)
+        temperature = 0.5
+        scores_arr = scores_arr / temperature
+        
+        # Softmax: 将分数转换为概率
+        exp_scores = np.exp(scores_arr - np.max(scores_arr))
+        probabilities = exp_scores / np.sum(exp_scores)
+        
+        # 采样 (或直接取 Top 1)
+        sampled_index = np.random.choice(a=len(results['ids'][0]), p=probabilities, size=n_results, replace=False)  # 不重复采样
+        sampled_items = [metadatas[i] for i in sampled_index]
+        return sampled_items

app/server/utils/img_operation.py

@@ -1,8 +1,9 @@
 import logging
+import os
 from typing import List, Dict
 from PIL import Image, ImageDraw, ImageFont
 from app.server.utils.minio_client import oss_get_image, minio_client
-from app.server.utils.minio_config import MINIO_LC_DATA_PATH
+from app.config import settings
 
 logger = logging.getLogger(__name__)
 # 9个 341x341 左右的单元格 (ALL_9_CELLS)
@@ -44,6 +45,9 @@ def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_te
     # Define the final canvas size
     CANVAS_SIZE = 1024
 
+    # 定义每个 item 的外边距
+    MARGIN = 5  # 5像素外边距
+
     # 1. Create the final white canvas
     # Using 'RGB' mode for JPG output
     canvas = Image.new('RGB', (CANVAS_SIZE, CANVAS_SIZE), 'white')
@@ -71,7 +75,11 @@ def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_te
         try:
             # We use Image.open() and convert to 'RGB' to handle potential transparency (RGBA)
             # and ensure compatibility with the final 'RGB' canvas and JPG output.
-            img = oss_get_image(oss_client=minio_client, path=f"{MINIO_LC_DATA_PATH}/{path}", data_type="PIL").convert('RGB')
+            if settings.LOCAL == 1:
+                img = Image.open(path).convert('RGB')
+            else:
+                img_name = path.rsplit('/', 1)[-1]
+                img = oss_get_image(oss_client=minio_client, path=f"{settings.MINIO_LC_DATA_PATH}/{img_name}", data_type="PIL").convert('RGB')
             # img = Image.open(path).convert('RGB')
             valid_images.append(img)
         except Exception as e:
@@ -88,6 +96,9 @@ def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_te
     # Get the correct list of target areas based on the number of valid images
     target_areas = quadrants.get(num_images, [])
 
+    if not target_areas:
+        raise ValueError(f"No layout defined for {num_images} images.")
+
     # 4. Resize and Paste
     for i, (img, item) in enumerate(zip(valid_images, outfit_items)):
         item_id = item['item_id']
@@ -96,13 +107,24 @@ def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_te
             # This should not happen if num_images <= 4
             break
 
-        # Target area dimensions (x_start, y_start, width, height)
-        x_start, y_start, target_w, target_h = target_areas[i]
+        # 原始目标区域 (x_start, y_start, width, height)
+        orig_x_start, orig_y_start, orig_w, orig_h = target_areas[i]
+
+        # 📢 应用边距：实际用于图像和文本的区域
+        # 新的起始点：向内移动 MARGIN
+        x_start = orig_x_start + MARGIN
+        y_start = orig_y_start + MARGIN
+
+        # 新的宽高：减去两倍的 MARGIN (左右/上下)
+        target_w = orig_w - 2 * MARGIN
+        target_h = orig_h - 2 * MARGIN
+
+        # --- 图像缩放与居中 ---
 
         # Calculate new size while maintaining aspect ratio
         original_w, original_h = img.size
 
-        # Calculate the ratio needed to fit within the target area
+        # Calculate the ratio needed to fit within the *带边距的* 目标区域
         ratio_w = target_w / original_w
         ratio_h = target_h / original_h
 
@@ -113,45 +135,46 @@ def merge_images_to_square(outfit_items: List[Dict[str, str]], max_len=9, add_te
         new_w = int(original_w * resize_ratio)
         new_h = int(original_h * resize_ratio)
 
-        # Resize the image. Image.Resampling.LANCZOS provides high-quality scaling.
-        # Pillow documentation recommends ANTIALIAS or BICUBIC for downscaling, 
-        # but LANCZOS is a good general high-quality filter.
-        # Note: In Pillow versions > 9.0.0, Image.LANCZOS is now Image.Resampling.LANCZOS
+        # Resize the image.
         resized_img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
 
         # Calculate the paste position to center the resized image within its target area
-        # Center X: (Target Width - New Width) / 2 + X Start
+        # Center X: (Target Width - New Width) / 2 + X Start (带边距的 X_start)
         paste_x = (target_w - new_w) // 2 + x_start
-        # Center Y: (Target Height - New Height) / 2 + Y Start
-        # paste_y = (target_h - new_h) // 2 + y_start
 
+        # 预留文本高度 ( TEXT_RESERVE_HEIGHT )
         TEXT_RESERVE_HEIGHT = 30
+
+        # Center Y: (Target Height - New Height - 预留文本高度) / 2 + Y Start (带边距的 Y_start)
         paste_y = (target_h - new_h - TEXT_RESERVE_HEIGHT) // 2 + y_start
+        # 确保图片顶部不超出目标区域的 Y_start
         paste_y = max(paste_y, y_start)
 
         # Paste the resized image onto the canvas
         canvas.paste(resized_img, (paste_x, paste_y))
 
+        # --- 文本居中与定位 ---
+
         full_text = f"ID: {item_id}, Category: {category}"
-        try:
-            # 推荐使用：计算文本的实际尺寸 (width, height)
-            bbox = draw.textbbox((0, 0), full_text, font=font)
-            text_w = bbox[2] - bbox[0]
-            text_h = bbox[3] - bbox[1]
-        except AttributeError:
-            # 兼容旧版本 Pillow
-            text_w, text_h = draw.textsize(full_text, font=font)
-
-        # 计算 X 轴起始位置：使其在目标区域 (target_w) 中居中
-        text_x_center = x_start + target_w // 2
-        text_x_start = text_x_center - text_w // 2
-
-        # 计算 Y 轴起始位置：将其放在目标区域的底部
-        # (目标区域的起始Y + 目标区域的高度 - 文本行的高度)
-        text_y_start = y_start + target_h - text_h - 5  # 减去 5 像素作为边距
-
-        # 3. 绘制合并后的文本
         if add_text:
+            try:
+                # 推荐使用：计算文本的实际尺寸 (width, height)
+                bbox = draw.textbbox((0, 0), full_text, font=font)
+                text_w = bbox[2] - bbox[0]
+                text_h = bbox[3] - bbox[1]
+            except AttributeError:
+                # 兼容旧版本 Pillow
+                text_w, text_h = draw.textsize(full_text, font=font)
+
+            # 计算 X 轴起始位置：使其在 *带边距的目标区域* (target_w) 中居中
+            text_x_center = x_start + target_w // 2
+            text_x_start = text_x_center - text_w // 2
+
+            # 计算 Y 轴起始位置：将其放在 *带边距的目标区域* 的底部
+            # (带边距的起始Y + 带边距的高度 - 文本行的高度)
+            # 📢 在带边距的目标区域底部再减去 5 像素作为与底部的边距
+            text_y_start = y_start + target_h - text_h
+
             draw.text((text_x_start, text_y_start),
                       full_text,
                       fill='black',

app/server/utils/minio_client.py

@@ -1,6 +1,7 @@
 import io
 import json
 import logging
+import time
 from io import BytesIO
 
 import cv2
@@ -9,9 +10,9 @@ import urllib3
 from PIL import Image
 from minio import Minio
 
-from app.server.utils.minio_config import MINIO_ACCESS, MINIO_SECRET, MINIO_URL, MINIO_SECURE
+from app.config import settings
 
-minio_client = Minio(MINIO_URL, access_key=MINIO_ACCESS, secret_key=MINIO_SECRET, secure=MINIO_SECURE)
+minio_client = Minio(settings.MINIO_URL, access_key=settings.MINIO_ACCESS, secret_key=settings.MINIO_SECRET, secure=settings.MINIO_SECURE)
 
 
 # 自定义 Retry 类
@@ -114,12 +115,19 @@ if __name__ == '__main__':
     # url = "lanecarford/lc_stylist_agent_outfit_items/string/7fed1c7b-9efd-41fa-a335-182c310ea611.jpg"
     # url = "lanecarford/lc_stylist_agent_outfit_items/string/5de155d0-56a6-43e8-a2f1-7538fce86220.jpg"
     # url = "lanecarford/lc_stylist_agent_outfit_items/string/1cd1803c-5f51-4961-a4f2-2acd3e0d8294.jpg"
-    url = 'lanecarford/lc_stylist_agent_outfit_items/string/99cd8cc0-856a-487d-bb21-5684855ef48f.jpg'
+    url = [
+        'lanecarford/lc_stylist_agent_outfit_items/zhhtest20251121/4b595d3b-5d3d-4617-ae09-5fca92d935f7.jpg',
+        'lanecarford/lc_stylist_agent_outfit_items/zhhtest20251121/6d0d7540-5b61-45f2-a1fa-5cb1c7a3d0fa.jpg',
+        'lanecarford/lc_stylist_agent_outfit_items/zhhtest20251121/a4e51ccb-9b95-4718-8153-92ee0a39d0c8.jpg',
+        'lanecarford/lc_stylist_agent_outfit_items/zhhtest20251121/cbebbcf6-cca2-4460-9f9f-d0b1000dc2cd.jpg'
+    ]
     read_type = "1"
-    img = oss_get_image(oss_client=minio_client, path=url, data_type=read_type)
-    if read_type == "cv2":
-        cv2.imshow("", img)
-        cv2.waitKey(0)
-    else:
-        img.show()
-        img.save("4.png")
+    for id, i in enumerate(url):
+        img = oss_get_image(minio_client, i, read_type)
+        img = oss_get_image(oss_client=minio_client, path=i, data_type=read_type)
+        if read_type == "cv2":
+            cv2.imshow("", img)
+            cv2.waitKey(0)
+        else:
+            img.show()
+            img.save(f"{time.time()}.png")

app/server/utils/minio_config.py

@@ -1,6 +0,0 @@
-# minio 配置
-MINIO_URL = "www.minio-api.aida.com.hk"
-MINIO_ACCESS = 'vXKFLSJkYeEq2DrSZvkB'
-MINIO_SECRET = 'uKTZT3x7C43WvPN9QTc99DiRkwddWZrG9Uh3JVlR'
-MINIO_SECURE = True
-MINIO_LC_DATA_PATH = "lanecarford/lc_image_data"

app/taxonomy.py

@@ -0,0 +1,94 @@
+# 这个文件用来储存所有的category和occasion，这是标准文件。
+OCCASION = [
+    "Casual", "Formal", "Activewear", "Resort", "Evening", "Outdoor", 
+    "Business / workwear", "Cocktail / Semi-Formal", "Black Tie / White Tie", 
+    "Bridal / Wedding", "Festival / Concert", "Party / Clubbing", 
+    "Travel / Transit", "Athleisure", "Beach / Swim", "Ski / Snow / Mountain", 
+    "Garden Party / Daytime Event"
+]
+
+FASHION_TAXONOMY = {
+    'clothing': [
+        # --- Tops ---
+        't-shirts',          # T恤
+        'shirts',            # 衬衫 (泛指梭织)
+        'blouses',           # 女式衬衫
+        'polo shirts',       # Polo衫
+        'tank tops',         # 背心/坎肩
+        'camisoles',         # 吊带背心
+        # --- Knits/Sweaters ---
+        'sweaters',          # 毛衣 (泛指)
+        'cardigans',         # 开衫
+        'pullovers',         # 套头衫
+        'hoodies',           # 连帽衫
+        'sweatshirts',       # 圆领卫衣
+        'vests',             # 马甲/背心 (外穿)
+        # --- Outerwear ---
+        'coats',             # 大衣 (长款)
+        'jackets',           # 夹克 (短款)
+        'blazers',           # 西装外套
+        # --- Bottoms ---
+        'jeans',             # 牛仔裤 (虽是材质，但在时尚界视为独立大类)
+        'trousers',          # 西裤/正装长裤
+        'pants',             # 长裤 (泛指休闲)
+        'joggers',           # 束脚裤
+        'leggings',          # 打底裤/紧身裤
+        'shorts',            # 短裤
+        'skirts',            # 半身裙
+        'skorts',            # 裙裤
+        # --- One-Piece ---
+        'dresses',           # 连衣裙
+        'jumpsuits',         # 连体长裤
+        'bodysuits',         # 连体紧身衣
+        'suits',             # 套装 (西装套)
+        # --- Intimates/Swim ---
+        'bras',              # 文胸
+        'underwear',         # 内衣
+        'lingerie',          # 性感内衣
+        'pajamas',           # 睡衣套装
+        'swimwear',          # 泳装
+    ],
+    'shoes': [
+        'sneakers',
+        'formal shoes',
+        'heels',
+        'flats',
+        'sandals',
+        'slides',
+        'boots',
+    ],
+    'bags': [
+        'shoulder bags',
+        'crossbody',
+        'bucket bags',
+        'tote bags',
+        'clutch bags',
+        'backpacks',
+        'travel bags',
+        'luggage',
+    ],
+    'accessories': [
+        # --- Jewelry & Watches ---
+        'necklaces',
+        'earrings',
+        'bracelets',
+        'rings',
+        'cufflinks',
+        'watches',
+        # --- Head/Face ---
+        'hats',
+        'eyewear',
+        # --- Body/Textile ---
+        'belts',
+        'scarves',
+        'gloves',
+        'ties',
+        'bow ties',
+        'pocket squares',
+        'socks',
+    ]
+}
+CATEGORY_LIST = list(FASHION_TAXONOMY.keys())
+ALL_SUBCATEGORY_LIST = sum(FASHION_TAXONOMY.values(), [])
+
+IGNORE_SUBCATEGORY = ['socks']

app/test/chromadb/embedding_query.py

@@ -0,0 +1,90 @@
+import random
+
+import chromadb
+from typing import Set, List, Dict, Union, Any
+
+import torch
+from PIL import Image
+from torch import no_grad
+from transformers import CLIPModel, CLIPProcessor
+
+from app.server.utils.minio_client import oss_get_image, minio_client
+from app.server.utils.minio_config import MINIO_LC_DATA_PATH
+
+# --- 你的配置 ---
+DB_PATH = "/workspace/lc_stylist_agent/db"
+COLLECTION_NAME = 'lc_clothing_embedding'
+# 设置一个足够大的限制来获取所有记录，或者使用分页（如果记录数非常庞大）
+MAX_LIMIT = 1000000
+
+client = chromadb.PersistentClient(path=DB_PATH)
+try:
+    collection = client.get_collection(name=COLLECTION_NAME)
+    print(f"✅ 连接到 Collection: {COLLECTION_NAME}")
+except ValueError:
+    print(f"⚠️ Collection '{COLLECTION_NAME}' 不存在。")
+    # 如果 collection 不存在，我们将跳过后续操作
+    collection = None
+
+from transformers import CLIPModel, CLIPProcessor
+
+
+def get_clip_embedding(data: str | Image.Image) -> List[float]:
+    """生成图像或文本的 CLIP 嵌入，并进行 L2 归一化。"""
+
+    embedding_model_name = "openai/clip-vit-base-patch32"
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = CLIPModel.from_pretrained(embedding_model_name).to(device)
+    processor = CLIPProcessor.from_pretrained(embedding_model_name)
+
+    # 强制截断，解决序列长度问题
+    inputs = processor(
+        text=[data],
+        return_tensors="pt",
+        padding=True,
+        truncation=True
+    ).to(device)
+    with no_grad():
+        features = model.get_text_features(**inputs)
+
+    # L2 归一化
+    features = features / features.norm(p=2, dim=-1, keepdim=True)
+
+    return features.cpu().numpy().flatten().tolist()
+
+
+def query_local_db(embedding: List[float], category: str, n_results: int = 3) -> List[Dict[str, Any]]:
+    """
+    基于嵌入向量在本地数据库中查询相似单品。
+    实际应执行 ChromaDB 查询,并根据 category 进行过滤(metadatas)。
+    """
+    # 实际应执行向量查询
+    # 为了演示流程,返回一个模拟结果
+    results = collection.query(
+        query_embeddings=[embedding],
+        n_results=n_results,
+        where={
+            "$and": [
+                {"category": category},
+                {"modality": "image"},
+            ]
+        },
+        include=['documents', 'metadatas', 'distances']
+    )
+    return results
+
+
+if __name__ == '__main__':
+    embedding = get_clip_embedding("watch")
+    print(embedding)
+    result = query_local_db(embedding, "Watches", 20)
+    print(result)
+    ids = result['ids'][0]
+
+    random_single_id = random.choices(ids, k=2)
+    print(random_single_id)
+
+    # for id in ids:
+    #     path = id.replace("_img", ".jpg")
+    #     img = oss_get_image(oss_client=minio_client, path=f"{MINIO_LC_DATA_PATH}/{path}", data_type="PIL").convert('RGB')
+    #     img.save(path)

app/test/chromadb/random_accessories.py

@@ -0,0 +1,107 @@
+import time
+
+import chromadb
+import random
+from typing import Dict, Any, List
+
+# --- 你的配置 ---
+DB_PATH = "/workspace/lc_stylist_agent/db"
+COLLECTION_NAME = 'lc_clothing_embedding'
+FILTER_CRITERIA = {
+    "$and": [
+        {"item_group_id": {"$ne": "Clothing"}},
+        {"item_group_id": {"$ne": "Shoes"}},  # 新增：过滤 Shoes
+        {"modality": "image"},
+    ]
+}
+MAX_LIMIT = 1000000  # 用于第一次获取所有ID的限制
+
+client = chromadb.PersistentClient(path=DB_PATH)
+try:
+    collection = client.get_collection(name=COLLECTION_NAME)
+    print(f"✅ 连接到 Collection: {COLLECTION_NAME}")
+except ValueError:
+    print(f"⚠️ Collection '{COLLECTION_NAME}' 不存在。")
+    exit()
+
+
+# -----------------------------------------------
+# 步骤 1: 应用程序启动时/初始化时执行（只执行一次）
+# -----------------------------------------------
+def load_filtered_ids(coll: chromadb.api.models.Collection.Collection, filter_criteria: Dict[str, Any]) -> List[str]:
+    """
+    加载并缓存所有符合条件的记录ID。
+    """
+    print("\n--- 初始化阶段：加载所有符合条件的 ID ---")
+
+    try:
+        # 获取所有符合条件的 ID
+        all_ids_results = coll.get(
+            where=filter_criteria,
+            limit=MAX_LIMIT,
+            include=[]
+        )
+        all_matched_ids = all_ids_results['ids']
+        print(f"🎉 成功加载 {len(all_matched_ids)} 个 ID 到缓存。")
+        return all_matched_ids
+
+    except Exception as e:
+        print(f"❌ 初始化失败：获取 ID 列表时发生错误: {e}")
+        return []
+
+
+# 存储所有符合条件的 ID 的全局变量 (缓存)
+start_time = time.time()
+CACHED_FILTERED_IDS = load_filtered_ids(collection, FILTER_CRITERIA)
+print(time.time() - start_time)
+
+
+# -----------------------------------------------
+# 步骤 2: 每次需要随机记录时调用 (高效重复执行)
+# -----------------------------------------------
+def get_random_record_from_cache(coll: chromadb.api.models.Collection.Collection, cached_ids: List[str]) -> Dict[str, Any] | None:
+    """
+    从缓存的 ID 列表中随机选择一个 ID，然后查询其详细信息。
+    """
+    total_count = len(cached_ids)
+
+    if total_count == 0:
+        return None
+
+    # 1. 纯 Python 内存操作：从缓存中随机选择一个 ID
+    random_single_id = random.choice(cached_ids)
+
+    # 2. 调用 ChromaDB：只查询这一个 ID 的详细信息
+    try:
+        final_results = coll.get(
+            ids=[random_single_id],
+        )
+
+        # 提取结果
+        if final_results['ids']:
+            return {
+                "id": final_results['ids'][0],
+                "metadata": final_results['metadatas'][0]
+            }
+        else:
+            return None
+
+    except Exception as e:
+        print(f"❌ 获取最终记录时发生错误: {e}")
+        return None
+
+
+# --- 执行并打印结果 (可以多次调用，每次都很快) ---
+print("\n--- 随机获取 1 ---")
+start_time = time.time()
+random_data_1 = get_random_record_from_cache(collection, CACHED_FILTERED_IDS)
+print(time.time() - start_time)
+if random_data_1:
+    print(f"  ID: {random_data_1}")
+
+print("\n--- 随机获取 2 ---")
+start_time = time.time()
+random_data_2 = get_random_record_from_cache(collection, CACHED_FILTERED_IDS)
+print(time.time() - start_time)
+if random_data_2:
+    print(f"  ID: {random_data_2}")

app/test/chromadb/type_list.py

@@ -0,0 +1,101 @@
+import chromadb
+from typing import Set, List, Dict, Union, Any
+
+# --- 你的配置 ---
+DB_PATH = "/workspace/lc_stylist_agent/db"
+COLLECTION_NAME = 'lc_clothing_embedding'
+# 设置一个足够大的限制来获取所有记录，或者使用分页（如果记录数非常庞大）
+MAX_LIMIT = 1000000
+
+client = chromadb.PersistentClient(path=DB_PATH)
+try:
+    collection = client.get_collection(name=COLLECTION_NAME)
+    print(f"✅ 连接到 Collection: {COLLECTION_NAME}")
+except ValueError:
+    print(f"⚠️ Collection '{COLLECTION_NAME}' 不存在。")
+    # 如果 collection 不存在，我们将跳过后续操作
+    collection = None
+
+
+def get_category_item_group_map(
+        coll: chromadb.api.models.Collection.Collection
+) -> Dict[str, Set[str]]:
+    """
+    获取 Collection 中所有记录的 'category' 和 'item_group_id' 字段，
+    并返回一个 Category 到其所有唯一 Item Group ID 集合的映射。
+    """
+    print("\n--- 正在获取所有记录的元数据 (category 和 item_group_id)... ---")
+
+    # 1. 获取所有记录的元数据
+    try:
+        # 使用 .get() 方法获取所有 metadatas，不包含 embeddings 和 documents
+        results = coll.get(
+            limit=MAX_LIMIT,
+            include=["metadatas"]
+        )
+
+        all_metadatas: List[Dict[str, Any]] = results.get('metadatas', [])
+
+    except Exception as e:
+        print(f"❌ 获取元数据时发生错误: {e}")
+        return {}
+
+    if not all_metadatas:
+        print("❌ 集合中没有元数据记录。")
+        return {}
+
+    # 2. 构建 Category 到 Item Group ID 集合的映射
+    # 结构: { 'CategoryA': {'group_id_1', 'group_id_2'}, 'CategoryB': {'group_id_3'} }
+    category_item_group_map: Dict[str, Set[str]] = {}
+
+    for metadata in all_metadatas:
+        category_value: Union[str, None] = metadata.get('category')
+        item_group_id_value: Union[str, None] = metadata.get('item_group_id')
+
+        # 确保两个元数据字段都存在
+        if category_value is not None and item_group_id_value is not None:
+            category = str(category_value)
+            item_group_id = str(item_group_id_value)
+
+            # 使用 setdefault 来确保 category 键存在，并初始化为一个空的 set
+            # 然后将 item_group_id 添加到对应的 set 中
+            category_item_group_map.setdefault(category, set()).add(item_group_id)
+
+    return category_item_group_map
+
+
+# --- 执行并打印结果 ---
+if collection:
+    category_item_group_mapping = get_category_item_group_map(collection)
+
+    if category_item_group_mapping:
+
+        # 统计总共发现多少种唯一 Category
+        print(f"\n🎉 发现 {len(category_item_group_mapping)} 种唯一 Category 及其对应的 Item Group IDs:")
+
+        # 对类别名称进行排序，便于查看
+        sorted_categories = sorted(category_item_group_mapping.keys())
+
+        # 打印详细结果
+        for category in sorted_categories:
+            item_group_ids = category_item_group_mapping[category]
+
+            # 打印类别名称和唯一的 Item Group ID 数量
+            print(f"\n--- 👕 Category: **{category}** ---")
+            print(f"**Item Group 总数:** {len(item_group_ids)} 个唯一 Item Group ID")
+
+            # 将 Item Group ID 转换为列表并排序，以便展示
+            sorted_item_group_ids = sorted(list(item_group_ids))
+
+            # 打印前 10 个 Item Group ID 作为示例
+            print(f"**部分 Item Group IDs (示例):**")
+
+            # 使用列表展示
+            for i, item_group_id in enumerate(sorted_item_group_ids[:10]):
+                print(f"* {item_group_id}")
+
+            if len(sorted_item_group_ids) > 10:
+                print(f"* ... (还有 {len(sorted_item_group_ids) - 10} 个 Item Group ID 未列出)")
+
+    else:
+        print("没有找到任何 Category 或 Item Group ID 数据。请检查元数据字段名称是否正确。")

data/stylist_guide/mini_en.md

@@ -1,43 +0,0 @@
-# Outfit Style Guide
-
-This guide summarizes the stylist's latest preferences, prohibitions, and styling patterns.
-
-## I. Core Preferences and Prohibitions
-
-| Category | Preference | Prohibition |
-| :--- | :--- | :--- |
-| **Primary Colors** | **Black, White, Gray, Earth Tones** (Solid colors preferred) | Avoid **Yellow** |
-| **Accent Colors** | Added via **bags, scarves** (Max 2 accent colors) | Avoid **Bright/Vivid** colors dominating |
-| **Patterns** | **Plaid/Checkered, Stripes** (Used as accents) | Strictly avoid **Floral/Small Prints** |
-| **Fit/Silhouette** | **Loose, Comfortable, Oversize**; **Clean and Sharp** tailoring | Tight-fitting or complicated silhouettes |
-| **Pants Requirement** | Must be **Floor-Length/Puddle Pants** | **Cropped/Ankle-Length, Flare/Bootcut Pants** |
-| **Footwear** | **White Sneakers**, **Flats/Single Shoes**, **Loafers** | **Heels, Tall Boots** |
-| **Leather Bags** | Must be **Black or White** pure colors; Preference for **Small, Neat Black Top-Handle Bags** | Bulky/Large volume bags |
-| **Accessories** | **Multiple Gold Accessories layered** (Necklace, Bracelet/Bangle, Earrings mandatory); **Watch** (Mandatory) | **Large/Bulky Earrings or Vector-style** accessories |
-
----
-
-## II. Styling Pattern: Layering and Balance
-
-The stylist's outfits emphasize **comfort** and **layering** (creating depth). The common structure is: **3 Upper Body Items + 1 Lower Body Item**. Primary colors are solid, with subtle patterns and accessories adding polish. A **Black Floor-Length Slip Dress** is a key base layer option.
-
-### 1. Classic Outfit Examples
-
-| Style | Structure | Keywords |
-| :--- | :--- | :--- |
-| **Smart Casual** | Milk Tea Oversize Blazer + White Shirt + **Loose Black Floor-Length Pants** + Tie + White Sneakers | Polished, Layered, Puddle Pants |
-| **Short Jacket Look** | **Short Jacket/Blazer** + **Short Skirt/Shorts** + White Socks + **Black Loafers** + Small Black Top-Handle Bag | Short-Jacket Rule, Sharp, Black Accents |
-| **Layered Base** | Loose Striped Knitwear + **Black Floor-Length Slip Dress (Inner)** + **Layered Gold Accessories** + Loafers | Dress Base, Longline, Gold Jewelry |
-| **Sporty Chic** | Milk Tea Oversize Blazer + Black Sleeveless Activewear + **Black Floor-Length Legging** + White Sneakers + Black Fanny Pack | Mixed Style, Dynamic, Balanced |
-
-### 2. Outfit Extended Rules Summary
-
-1.  **Color Palette**: Main garments limited to Black, White, Gray, and Earth Tones; accent colors in accessories max 2. Avoid yellow or vivid dominance.
-2.  **Layering Principle**: Min 2-3 layers on the upper body, with visible subtle patterns (collar/scarf). **Key:** The **Black Floor-Length Slip Dress** is a favored base.
-3.  **Fit Requirements**: All items favor loose/oversize for comfort; tailoring must be clean, avoiding tight or complex silhouettes.
-4.  **Pattern Restriction**: Only Plaid/Stripes as accents; strictly no florals.
-5.  **Pant Length**: All pants **must be floor-length**, prohibiting cropped and flare styles.
-6.  **Short Outerwear Rule**: Short outerwear must be paired with **short skirts or shorts**, and **Black Loafers** are mandatory for footwear.
-7.  **Shoe/Bag Coordination**: Footwear is flat and casual (Loafers, White Sneakers preferred). Leather bags are pure black/white, with a preference for a **small, neat black top-handle bag**.
-8.  **Accessory Stacking**: **Gold necklace, bracelet/bangle, and earrings should ideally all be present and layered**; watch is mandatory; rings are minimal.
-9.  **Overall Balance**: Simple bottoms when the top is layered/complex; overall style is neutral and polished.

data_ingestion/README.md

@@ -0,0 +1,93 @@
+## Steps
+1. Prepare products-all.json and image_data (folder) using javascript to download. These files should be saved in `./data/BATCH_SOURCE` which is a new folder. Give a new batch_source id to each new incoming data.
+1. Run `process_item.py` to categorize category, gender and occasions for each data. Output to `./data/{BATCH_SOURCE}/metadata_extraction.json`. This should be running on H200 device.
+3. Organize all data and then embed them into db locally using `run_ingestion.py`
+
+## Raw Data Structure
+```json
+## products-all.json
+{
+    "id": "BUL808",
+    "name": "SARAH ZHUANG - 'Click & Link' diamond 18k gold earrings",
+    "brand": "SARAH ZHUANG",
+    "category": "Fine Jewellery And Watches",
+    "subcategory": "General",
+    "price": 17500,
+    "currency": "HKD",
+    "description": "Sarah Zhuang's Click & Link earrings embrace the allure of geometry. Forged into elegant rectangles with one side encrusted with diamonds, this gold pair will certainly elevate your cocktail ensembles.",
+    "tags": [
+    "sarah zhuang",
+    "fine jewellery and watches",
+    "in-stock",
+    "new",
+    "sarah",
+    "zhuang",
+    "'click",
+    "link'",
+    "diamond"
+    ],
+    "imageUrl": "https://media.lanecrawford.com/B/U/L/BUL808_in_xl.jpg",
+    "url": "https://www.lanecrawford.com.hk/product/sarah-zhuang/-click-link-diamond-18k-gold-earrings/_/BUL808/product.lc?utm_medium=embed&utm_source=ai-recommended&utm_campaign=2025-christmas_lc_ai-recommended",
+    "color": "YELLOW GOLD",
+    "groupName": "Fine Jewellery",
+    "deptName": "Women's  Fine Jewellery",
+    "onlineBU": "Fine Jewellery",
+    "stockAvailability": true
+}
+```
+
+
+## Example in `metadata_extraction.json`
+```json
+"EOJ367": {
+    "subcategory": "necklaces",
+    "gender": "female",
+    "applicable_occasions": [
+        "Casual",
+        "Outdoor",
+        "Travel / Transit"
+    ],
+    "inappropriate_occasions": [
+        "Formal",
+        "Black Tie / White Tie",
+        "Bridal / Wedding",
+        "Business / workwear",
+        "Cocktail / Semi-Formal"
+    ]
+}
+```
+
+## Metadata in Vector Database
+```json
+{
+    "item_id": "EOJ128",
+    "category": "accessories",
+    "subcategory": "eyewear",
+    "gender": "unisex", 
+    "modality": "image",
+    "brand": "CELINE",
+    "color": "BROWN", 
+    "description": "Immerse yourself in the depth of classic style with CELINE's Tortoiseshell Logo Sunglasses. Featuring a rich, tortoiseshell acetate frame and adorned with the iconic CELINE logo in gold, these sunglasses are a testament to timeless elegance and luxury. Perfect for those who appreciate a sophisticated aesthetic, they offer optimal UV protection while ensuring you remain at the forefront of fashion.",
+    "tags": "celine,accessories,in-stock,new,maxi,triomphe,acetate,round", 
+    "price": 4500, 
+    "url": "https://www.lanecrawford.com.hk/product/celine/maxi-triomphe-acetate-round-sunglasses/_/EOJ128/product.lc?utm_medium=embed&utm_source=ai-recommended&utm_campaign=2025-christmas_lc_ai-recommended",
+    "batch_source": "2025_q4",
+    "Outdoor": 0, 
+    "Ski / Snow / Mountain": 0, 
+    "Festival / Concert": 0, 
+    "Activewear": 0, 
+    "Casual": 1, 
+    "Cocktail / Semi-Formal": -1, 
+    "Formal": -1, 
+    "Party / Clubbing": 0, 
+    "Evening": 0, 
+    "Travel / Transit": 0, 
+    "Beach / Swim": 0, 
+    "Garden Party / Daytime Event": 1, 
+    "Black Tie / White Tie": -1, 
+    "Resort": 1, 
+    "Athleisure": 0, 
+    "Business / workwear": -1, 
+    "Bridal / Wedding": -1, 
+}
+```

data_ingestion/process_item.py

@@ -0,0 +1,283 @@
+import torch
+import os
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from PIL import Image
+import json
+from tqdm import tqdm
+
+from app.taxonomy import OCCASION, FASHION_TAXONOMY, ALL_SUBCATEGORY_LIST
+
+
+# data config
+BATCH_SOURCE = '2025_q4'
+RAW_DATA_PATH = f'./data/{BATCH_SOURCE}/products-all.json'
+IMAGE_DIR = f'./data/{BATCH_SOURCE}/image_data'
+
+# MLLM config
+MODEL_NAME = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+DEVICE = "cuda:0" # 确保设备设置正确，与您的 Traceback 匹配
+BATCH_SIZE = 50
+OUTPUT_FILE = f'./data/{BATCH_SOURCE}/metadata_extraction.json'
+
+
+# Load Model
+processor = AutoProcessor.from_pretrained(MODEL_NAME)
+if processor.tokenizer.padding_side != 'left':
+    processor.tokenizer.padding_side = 'left'
+    print(f"Set tokenizer padding_side to '{processor.tokenizer.padding_side}' for correct generation.")
+model = AutoModelForVision2Seq.from_pretrained(MODEL_NAME, torch_dtype=torch.bfloat16).to(DEVICE) 
+model.eval()
+
+
+# Load Data
+with open(RAW_DATA_PATH, 'r', encoding='utf-8') as file:
+    data = json.load(file)
+
+
+EXAMPLE_1_INFO = """
+Product Name: ARMARIUM - Loren Wool Blend Tube Skirt
+Category: Clothing / Bottoms
+Color: RED
+Description: Cut from cardinal-red virgin wool, Armarium's Loren skirt wields tailoring's exactitude in a column of colour. The low-slung waist and clean tube line are punctuated by a razor back slit—stride from boardroom to candlelit bar with modern hauteur.
+Tags: armarium, clothing, in-stock, new, loren, wool, blend, tube
+"""
+EXAMPLE_1_JSON = json.dumps({
+    "subcategory": "skirts",
+    "gender": "female",
+    "applicable_occasions": [
+        "Business/workwear", "Evening", "Cocktail / Semi-Formal", "Party / Clubbing", "Formal"
+    ],
+    "inappropriate_occasions": [
+        "Activewear", "Beach / Swim", "Athleisure", "Ski / Snow / Mountain", "Casual"
+    ]
+}, indent=4)
+
+# 示例 2：胸针 (Pin)
+EXAMPLE_2_INFO = """
+Product Name: TATEOSSIAN - Mayfair 18K Yellow Gold Rhodium Plated Sterling Silver Peg Pin
+Category: Accessories / Accessories
+Color: MULTI
+Description: Crafted from 18k yellow gold and rhodium-plated sterling silver, this unique pins has been artfully finished with Tateossian's signature diamond engraving pattern.
+Tags: tateossian, accessories, in-stock, new, mayfair, yellow, gold, rhodium
+"""
+EXAMPLE_2_JSON = json.dumps({
+    "subcategory": "jewelry",
+    "gender": "female",
+    "applicable_occasions": [
+        "Formal", "Black Tie / White Tie", "Bridal / Wedding", "Business/workwear", "Cocktail / Semi-Formal"
+    ],
+    "inappropriate_occasions": [
+        "Casual", "Activewear", "Beach / Swim", "Outdoor", "Athleisure", "Ski / Snow / Mountain"
+    ]
+}, indent=4)
+
+
+# --- 2. 构造对话格式 Prompt ---
+BOS_TOKEN = "<|begin_of_text|>"
+EOS_TOKEN = "<|eot_id|>"
+SYSTEM_HEADER = "<|start_header_id|>system<|end_header_id|>\n"
+USER_HEADER = "<|start_header_id|>user<|end_header_id|>\n"
+ASSISTANT_HEADER = "<|start_header_id|>assistant<|end_header_id|>\n"
+IMAGE_TOKEN = "<|image|>"
+
+def format_product_info(product):
+    tags_str = ", ".join(product.get('tags', []))
+    info = (
+        f"Product Name: {product.get('name', 'N/A')}\n"
+        f"Category: {product.get('category', 'N/A')} / {product.get('deptName', 'N/A')}\n"
+        f"Color: {product.get('color', 'N/A')}\n"
+        f"Description: {product.get('description', '')}\n"
+        f"Tags: {tags_str}",
+        f"groupName: {product.get('groupName', 'N/A')}\n"
+        f"onlineBU: {product.get('onlineBU', 'N/A')}\n"
+    )
+    return info
+
+
+def raw_category_mapping(raw_category: str) -> str:
+    if raw_category == 'Fine Jewellery And Watches':
+        return 'accessories'
+    else:
+        return raw_category.lower()
+
+
+def generate_full_prompt(product_info, raw_category):
+    category = raw_category_mapping(raw_category)
+    subcategory_list = FASHION_TAXONOMY.get(category)
+
+    SYSTEM_PROMPT = f"""You are an expert fashion AI assistant. Your task is to analyze the provided product image and product details to: 
+    1. determine the suitable occasions for wearing or using the item. You must choose occasions ONLY from the following strict list: {json.dumps(OCCASION, indent=4)}. Only relevant suitable or inappropriate occasions should be selected.
+    2. categorize it into suitable subcategory in strict list: {json.dumps(subcategory_list)}.
+    3. categorize it into appropriate gender in ["female", "male", "unisex"]
+
+    Output Format:
+    Return ONLY a valid JSON object with four keys: "subcategory", "gender", "applicable_occasions" and "inappropriate_occasions". Do not include any analysis or extra text outside of the final JSON object.
+    """
+
+    # 组合对话序列
+    dialogue_prompt = (
+        # 1. System Instruction
+        f"{BOS_TOKEN}{SYSTEM_HEADER}{SYSTEM_PROMPT}{EOS_TOKEN}"
+        
+        # 2. Example 1 (Few-Shot Round 1)
+        # 格式: <|start_header_id|>user<|end_header_id|>\n<|image|>\n{Text Instruction}<|eot_id|>
+        f"{USER_HEADER}\n{EXAMPLE_1_INFO}{EOS_TOKEN}"
+        f"{ASSISTANT_HEADER}{EXAMPLE_1_JSON}{EOS_TOKEN}"
+        
+        # 3. Example 2 (Few-Shot Round 2)
+        f"{USER_HEADER}\n{EXAMPLE_2_INFO}{EOS_TOKEN}"
+        f"{ASSISTANT_HEADER}{EXAMPLE_2_JSON}{EOS_TOKEN}"
+
+        # 4. Target Item (Target Query)
+        f"{USER_HEADER}{IMAGE_TOKEN}\nInput Data:\n{product_info}{EOS_TOKEN}"
+        f"{ASSISTANT_HEADER}" # 最后的 Assistant Header 告诉模型从这里开始生成
+    )
+    return dialogue_prompt
+
+
+# 2. 加载数据
+products = data['products']
+product_list = [
+    product for product in products 
+    if product.get('category') in ['Clothing', 'Accessories', 'Shoes', 'Bags', 'Fine Jewellery And Watches'] 
+    and os.path.exists(os.path.join(IMAGE_DIR, f"{product.get('id')}.jpg"))
+]
+
+
+def validate_result(result_dict):
+    subcategory = result_dict.get("subcategory")
+    gender = result_dict.get("gender")
+
+    if not subcategory or not gender:
+        return False
+    
+    if subcategory not in ALL_SUBCATEGORY_LIST:
+        return False
+
+    if gender not in ['female', 'male', 'unisex']:
+        return False
+    
+    return True
+
+
+if os.path.exists(OUTPUT_FILE):
+    with open(OUTPUT_FILE, 'r') as f:
+        final_results = json.load(f)
+else:
+    final_results = {}
+
+
+attemps = 0
+while attemps < 3:
+    unfinished_products = [product for product in product_list if product.get('id') not in final_results.keys()]
+    attemps += 1
+    completion_ratio = len(final_results) / len(product_list)
+    if (completion_ratio > 0.85):
+        print("valid results surpass 85%. Finish Now.")
+        break
+    else:
+        print(f"Start {attemps} categorization process. Current ratio: {completion_ratio * 100}%")
+
+    try:
+        # 按照 BATCH_SIZE 进行切片迭代
+        for i in tqdm(range(0, len(unfinished_products), BATCH_SIZE)):
+            batch_samples = unfinished_products[i:i + BATCH_SIZE]
+            
+            target_images = []
+            target_prompts = []
+            target_products_in_batch = []
+
+            # 准备当前批次的输入数据
+            for product in batch_samples:
+                product_id = product['id']
+                raw_category = product.get('category')
+                image_path = os.path.join(IMAGE_DIR, f"{product_id}.jpg")
+
+                try:
+                    # 收集图片、Prompt 和产品数据
+                    image = Image.open(image_path).convert("RGB")
+                    product_info = format_product_info(product)
+                    full_prompt = generate_full_prompt(product_info, raw_category)
+                    
+                    target_images.append(image)
+                    target_prompts.append(full_prompt)
+                    target_products_in_batch.append(product)
+                except Exception as e:
+                    # 跳过任何加载失败的单个样本
+                    print(f"Skipping product {product_id} due to loading error: {e}")
+                    continue
+
+            if not target_images:
+                continue # 如果整个批次都没有有效图片，跳过
+
+            # 4. 批量推理
+            print(f"\nProcessing batch {i//BATCH_SIZE + 1}/{int(len(unfinished_products)/BATCH_SIZE)+1} (Size: {len(target_images)})...")
+            
+            # 处理器输入：使用嵌套列表 [[img1], [img2], ...]
+            inputs = processor(
+                images=[[img] for img in target_images], 
+                text=target_prompts, 
+                return_tensors="pt",
+                padding=True, 
+                truncation=True
+            ).to(model.device)
+
+            with torch.no_grad():
+                outputs = model.generate(
+                    **inputs, 
+                    max_new_tokens=150, 
+                    do_sample=False
+                )
+
+            # 5. 批量解码和解析结果
+            input_lengths = inputs.input_ids.size(1) 
+            
+            for j in range(len(target_products_in_batch)):
+                product = target_products_in_batch[j]
+                product_id = product['id']
+                
+                # 提取当前 item 的生成结果
+                # 注意: outputs 是 [batch_size, sequence_length]
+                newly_generated_tokens = outputs[j, input_lengths:] 
+                generated_text = processor.decode(newly_generated_tokens, skip_special_tokens=True)
+                
+                # 清理和解析
+                if generated_text.endswith(processor.tokenizer.eos_token):
+                    generated_text = generated_text[:-len(processor.tokenizer.eos_token)]
+                    
+                try:
+                    start_idx = generated_text.find('{')
+                    end_idx = generated_text.rfind('}') + 1
+                    
+                    if start_idx == -1 or end_idx == -1:
+                        raise ValueError("JSON start or end delimiter not found.")
+                        
+                    json_str = generated_text[start_idx:end_idx]
+                    result_dict = json.loads(json_str)
+                    
+                    if validate_result(result_dict):
+                        final_results[product_id] = result_dict
+                    
+                except Exception as e:
+                    print(f"ID {product_id}: FAILED to parse JSON. Raw Output: {generated_text.strip()}")
+            
+            # 显存清理（可选，但在长任务中推荐）
+            del inputs, outputs
+            torch.cuda.empty_cache()
+
+            with open(OUTPUT_FILE, 'w', encoding='utf-8') as f:
+                json.dump(final_results, f, indent=4, ensure_ascii=False)
+
+        # 6. 保存最终结果    
+        print("\n\n=== ALL BATCHES COMPLETE ===")
+
+        # 保存最终结果到 JSON 文件
+        with open(OUTPUT_FILE, 'w', encoding='utf-8') as f:
+            json.dump(final_results, f, indent=4, ensure_ascii=False)
+            
+        print(f"Results saved to {OUTPUT_FILE}")
+
+
+    except Exception as e:
+        print(f"\n--- Execution Error ---")
+        print(f"An unexpected error occurred: {e}")

data_ingestion/run_ingestion.py

@@ -0,0 +1,182 @@
+import chromadb
+import os
+import json
+from copy import deepcopy
+
+import torch
+from tqdm import tqdm
+from PIL import Image
+from transformers import CLIPProcessor, CLIPModel
+
+from app.taxonomy import ALL_SUBCATEGORY_LIST, OCCASION
+
+
+BATCH_SOURCE = '2025_q4'
+DATA_DIR = f'./data/{BATCH_SOURCE}'
+IMAGE_DIR = f'./data/{BATCH_SOURCE}/image_data'
+
+RAW_DATA_PATH = f'{DATA_DIR}/products-all.json'
+CATEGORIZED_METADATA_PATH = f'{DATA_DIR}/metadata_extraction.json'
+ADD_TEXT_EMBEDDING = False
+
+## Load data
+with open(RAW_DATA_PATH, 'r', encoding='utf-8') as file:
+    raw_data = json.load(file)
+
+with open(CATEGORIZED_METADATA_PATH, 'r', encoding='utf-8') as file:
+    categorized_data = json.load(file)
+
+
+# Create Collection
+client = chromadb.PersistentClient(path='./data/db')
+collection = client.get_or_create_collection(
+    name="lc_clothing_embedding"
+)
+
+# if you wish to delete some item, uncomment following
+results = collection.delete(
+    where={
+        "batch_source": BATCH_SOURCE
+    }
+)
+
+# Load model
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+def format_product_info(product):
+    tags_str = ", ".join(product.get('tags', []))
+    info = (
+        f"Product Name: {product.get('name', 'N/A')}\n"
+        f"Brand: {product.get('brand', 'N/A')}\n"
+        f"Category: {product.get('category', 'N/A')} / {product.get('deptName', 'N/A')}\n"
+        f"Color: {product.get('color', 'N/A')}\n"
+        f"Description: {product.get('description', '')}\n"
+        f"Tags: {tags_str}"
+        f"GroupName: {product.get('groupName', 'N/A')}\n"
+        f"DetpName: {product.get('deptName', 'N/A')}\n"
+        f"OnlineBU: {product.get('onlineBU', 'N/A')}\n"
+    )
+    return info
+
+def raw_category_mapping(raw_category: str) -> str:
+    if raw_category == 'Fine Jewellery And Watches':
+        return 'accessories'
+    else:
+        return raw_category.lower()
+
+# Combine all data together
+valid_count = 0
+all_count = 0
+for raw_item in tqdm(raw_data['products']):
+    item_id = raw_item.get('id')
+    if not item_id:
+        print(f"This item {raw_item} did not have a valid item_id")
+        continue
+
+    raw_category = raw_item.get("category")
+    if raw_category not in ['Clothing', 'Accessories', 'Shoes', 'Bags', 'Fine Jewellery And Watches']:
+        continue
+
+    image_path = os.path.join(IMAGE_DIR, f"{item_id}.jpg")
+    if not os.path.exists(image_path):
+        print(f"Image not found: {image_path}")
+        continue
+
+    # All above is raw data error, it's not our business.
+    all_count += 1
+
+    processed_item = categorized_data.get(item_id, {})
+    if not processed_item:
+        print(f"{item_id} has not been categorized. It does not exist in {CATEGORIZED_METADATA_PATH}")
+        continue
+
+    category = raw_category_mapping(raw_category)
+    subcategory = processed_item.get("subcategory")
+    gender = processed_item.get("gender")
+    applicable_occasions = processed_item.get("applicable_occasions", [])
+    inappropriate_occasions = processed_item.get("inappropriate_occasions", [])
+
+    if subcategory not in ALL_SUBCATEGORY_LIST:
+        print(f"{item_id}'s category, {category}, does not valid.")
+
+    if gender not in ['female', 'male', 'unisex']:
+        print(f"{item_id}'s gender is not valid in {['female', 'male', 'unisex']}")
+        continue
+
+    occasions = applicable_occasions + inappropriate_occasions
+    if not set(occasions).issubset(set(OCCASION)):
+        # print(f"{item_id}'s some occasions is not vaild. \n Invalid occasion is {set(occasions).difference(set(OCCASION))}")
+        applicable_occasions = [o for o in applicable_occasions if o in OCCASION]
+        inappropriate_occasions = [o for o in inappropriate_occasions if o in OCCASION]
+
+    description = raw_item.get('description', "")
+    if not description:
+        f"{item_id}'s description is lost."
+        continue
+
+    url = raw_item.get('url', '')
+    if not url:
+        f"{item_id}'s url is lost."
+        continue
+
+    valid_count += 1
+    # Prepare metadata for db
+    item_img_metadata = {
+        "item_id": item_id,
+        "category": category,
+        "subcategory": subcategory,
+        "description": description,
+        "gender": gender,
+        'brand': raw_item.get('brand', ''),
+        'color': raw_item.get('color', ''),
+        'price': raw_item.get('price', ''),
+        'tags': ",".join(raw_item.get('tags', [])),
+        'url': url,
+        "modality": "image",
+        "batch_source": BATCH_SOURCE
+    }
+    for occasion in OCCASION:
+        item_img_metadata[occasion] = 0
+    for occasion in applicable_occasions:
+        item_img_metadata[occasion] = 1
+    for occasion in inappropriate_occasions:
+        item_img_metadata[occasion] = -1
+
+    # Get image feature
+    image = Image.open(image_path).convert("RGB")
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    with torch.no_grad():
+        img_features = model.get_image_features(**inputs)
+        img_features = img_features / img_features.norm(p=2, dim=-1, keepdim=True)
+        img_embedding = img_features.cpu().numpy().flatten().tolist()
+
+    product_info = format_product_info(raw_item)
+    # 插入到 ChromaDB
+    collection.add(
+        ids=[f'{item_id}_img'],
+        documents=[product_info],
+        embeddings=[img_embedding],
+        metadatas=[item_img_metadata],
+    )
+
+    if ADD_TEXT_EMBEDDING:
+        item_txt_metadata = deepcopy(item_img_metadata)
+        item_txt_metadata["modality"] = "text"
+
+        # Get text feature
+        inputs = processor(text=[description], return_tensors="pt", padding=True, truncation=True).to(device)
+        with torch.no_grad():
+            txt_features = model.get_text_features(**inputs)
+            txt_features = txt_features / txt_features.norm(p=2, dim=-1, keepdim=True)
+            txt_embedding = txt_features.cpu().numpy().flatten().tolist()
+            collection.add(
+                ids=[f'{item_id}_txt'],
+                documents=[product_info],
+                embeddings=[txt_embedding],
+                metadatas=[item_txt_metadata],
+            )
+
+print(f"Final valid ratio is {valid_count / all_count * 100}%. Total number is {all_count}, Valid number is {valid_count}")

docker-compose.yml

@@ -5,12 +5,21 @@ services:
       dockerfile: Dockerfile
     working_dir: /app
     environment:
-      GOOGLE_APPLICATION_CREDENTIALS: /app/app/request.json
+      GOOGLE_APPLICATION_CREDENTIALS: /google_application_credentials.json
       DEBUG: 0
     volumes:
       - ./app:/app/app
-      - ./.env:/app/.env
-      - ./db:/db
+      - ./.prod_env:/app/.env
+      - ./data:/data
+      - ./google_application_credentials.json:/google_application_credentials.json
       - /etc/localtime:/etc/localtime:ro
     ports:
-      - "10070:8000"
+      - "10070:8000"
+    deploy:
+      resources:
+        reservations:
+          devices:
+            # 告诉 Docker 使用所有可用的 NVIDIA GPU
+            - driver: nvidia
+              device_ids: [ '0' ]
+              capabilities: [ gpu ]

new_.json

@@ -1,13 +0,0 @@
-{
-  "type": "service_account",
-  "project_id": "aida-461108",
-  "private_key_id": "e0fa4eb8743342ee0d9af77296ec71101bf09706",
-  "private_key": "-----BEGIN PRIVATE KEY-----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\nxJjMu9TnfDjmd2gG5GkWVqM=\n-----END PRIVATE KEY-----\n",
-  "client_email": "aida-gcs-test@aida-461108.iam.gserviceaccount.com",
-  "client_id": "117280364971550320059",
-  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
-  "token_uri": "https://oauth2.googleapis.com/token",
-  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
-  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/aida-gcs-test%40aida-461108.iam.gserviceaccount.com",
-  "universe_domain": "googleapis.com"
-}

requirements.txt

@@ -16,4 +16,5 @@ pytorch-fid==0.3.0
 open-clip-torch==2.24.0
 pytorch-fid==0.3.0
 litserve
-# pip install git+https://github.com/openai/CLIP.git
+# pip install git+https://github.com/openai/CLIP.git
+# pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128

stylist_guide/crystal_acc.md

@@ -0,0 +1,17 @@
+# Crystal's Accessory Guide: Pure Balance
+This guide strictly outlines accessory selection, emphasizing Gold Tones and pure, solid colors to stabilize the outfit's primary focus on bold pattern clashing.
+
+## I. Color, Pattern, and Material Constraints
+Color & Tone: All jewelry must be in Gold Tones. Vector-style accessories are prohibited.
+
+Accessory Pattern: Bags and shoes must be Solid Color only. Patterned or printed bags and shoes are strictly prohibited.
+
+
+## II. Mandatory & Stacking Requirements
+The use of accessories is essential to complete the look, focusing on stacking and specific shapes:
+
+Mandatory Jewelry: A Necklace is mandatory (minimum one piece). A Watch must be included as part of the wrist stack.
+
+Earrings: Must be Hoop Earrings.
+
+Stacking: Encourage stacking of Bracelets and Rings alongside the mandatory watch.

stylist_guide/crystal_en.md

@@ -1,25 +1,23 @@
 # Outfit Style Guide
 
-This guide outlines the preferred styling logic, brand affinities, patterns, and structure for Crystal's outfits, emphasizing **bold pattern mixing** balanced by **pure accessories**.
+This guide outlines the preferred styling logic, brand affinities, patterns, and structure for Crystal's outfits, emphasizing **bold pattern mixing** balanced by .
 
 ## I. Core Preferences and Prohibitions
 
-| Category | Preference | Prohibition |
+| Category | Preference (✔️) | Prohibition (❌) |
 | :--- | :--- | :--- |
 | **Brands/Material** | **Sacai** brand; **Denim** items | - |
-| **Patterns** | **Plaid, Stripes, Floral, Leopard Print**; Active pattern clashing (min 2, **with specific restrictions**) | Monochromatic or single-pattern outfits; **Mixing different Animal Prints** (e.g., Leopard + Snake) |
+| **Patterns** | **Plaid, Stripes, Floral, Leopard Print**; Active pattern clashing (min 2) | Monochromatic or single-pattern outfits |
 | **Layering** | Max **2 items** on the upper body; Pattern mixing replaces layering | Excessive layering (叠穿) |
 | **Fit/Silhouette** | Accepts **Oversize**; Flexible (can mix with slim-fit/leggings) | Tight-fitting or complicated silhouettes |
 | **Shoe Styles** | **Boots, Platform Shoes, Pointed Low Heels, Mesh Shoes, Ballet Flats, White Sneakers** | Full High Heels (高跟鞋), Tall Boots |
-| **Bags/Shoes (Pattern)** | **Solid Color** only for bags and shoes | **Patterned/Printed** Bags or Shoes |
-| **Bags (Material)** | Must be **Leather** (or natural elements like Rattan/Wicker) | Non-leather materials (except rattan/wicker) |
-| **Accessories** | **Gold Tones**; **Necklace** (Mandatory); Rings, **Hoop Earrings**, Bracelet, **Watch** | Vector-style accessories |
+| **Shoes (Pattern)** | **Solid Color** only for shoes | **Patterned/Printed** Shoes |
 
 ---
 
-## II. Styling Pattern: Pattern Clash and Pure Balance
+## I. Styling Pattern: Pattern Clash and Pure Balance
 
-This stylist's style prioritizes visual impact through **clashing prints** rather than layering. Outfits are usually based on a bold print or denim, balanced by pure, solid-colored accessories.
+This stylist's style prioritizes visual impact through **clashing prints** rather than layering. Outfits are usually based on a bold print or denim, balanced by pure.
 
 ### 1. Classic Outfit Examples
 
@@ -28,15 +26,14 @@ This stylist's style prioritizes visual impact through **clashing prints** rathe
 | **Edgy Casual** | Milk Tea Oversize Blazer + Beige Shirt + Olive Green Cargo Pants + Black Pointed Low Heels | Utility, Sharp Contrast, Subtle Prints |
 | **Elegant Flow** | Milk Tea Oversize Blazer + Beige Shirt + Dark Brown Slim-fit Pants + White Mesh Shoes or Ballet Flats | Mixed Fit, Comfort Contrast |
 | **Sporty Mix** | Milk Tea Oversize Blazer + Dark Brown or Leopard Print Yoga Set + White Sneakers | Athleisure, Pattern Pop |
-| **Heavy Print** | Floral Dress + Denim Pants + Rattan Bag + Wrist Cord + Layered Beaded Necklaces | Pattern Clash (Floral + Denim), Natural Accent |
+| **Heavy Print** | Floral Dress + Denim Pants | Pattern Clash (Floral + Denim), Natural Accent |
 
 ### 2. Outfit Extended Rules Summary
 
-1.  **Pattern Clash**: Actively mix patterns (Plaid/Stripe/Leopard) in one outfit, aiming for at least two non-forbidden prints. **CRITICAL RESTRICTIONS:** A) If a **Floral** print item is chosen, all other clothing items must be solid colors (no mixing floral with other prints). B) **Do not mix different animal prints** (e.g., Leopard and Snakeskin cannot be combined).
+1.  **Pattern Clash**: Actively mix **at least two** patterns (Plaid/Stripe/Floral/Leopard) in one outfit to maximize visual interest.
 2.  **Layering Limit**: Do not rely on multi-layering for depth; use print complexity instead. The upper body is limited to **max 2 pieces**.
 3.  **Fit Flexibility**: Oversize is welcome, but tight-fitting items (e.g., leggings) can be mixed. Prioritize durable fabrics like **Denim** for texture.
-4.  **Color Base**: No strict color restrictions on garments, but all major accessories (**bags and shoes**) must be **pure, solid colors**.
-5.  **Shoe/Bag Principle**: Shoes should provide height (low heel, platform, boots). Bags should be **leather and solid-colored**, with rattan/wicker bags accepted as natural accents.
-6.  **Accessory Requirements**: **Gold** jewelry is preferred for unified tone. **Necklace** is mandatory (min 1). Earrings must be **hoops**. Stack **bracelet/ring/watch**.
-7.  **Overall Balance**: If clothing patterns are complex, shoes/bags must be **simple and pure** to ground the look. Style leans toward **mixed-casual and energetic**, avoiding blandness.
+4.  **Color Base**: No strict color restrictions on garments, but shoes must be **pure, solid colors**.
+5.  **Shoe Principle**: Shoes should provide height (low heel, platform, boots).
+6.  **Overall Balance**: If clothing patterns are complex, shoes must be **simple and pure** to ground the look. Style leans toward **mixed-casual and energetic**, avoiding blandness.
 8.  **Scene Adaptability**: Add **cargo pants/low heels** for casual settings; **yoga sets** for sportier looks; use **denim** to balance out heavy prints.

stylist_guide/edi_acc.md

@@ -0,0 +1,10 @@
+# Accessory Style Guide
+This guide strictly outlines accessory selection, emphasizing a flexible approach to metal tones and highlighting the aesthetic of long-worn items.
+
+# I. Color and Material Constraints
+Metal Tones: Both Gold and Silver metals are preferred and should be mixed and matched together.
+
+Aesthetic Preference: Items that show wear, such as Silver items that have changed color over time, are acceptable as they present a unique personal preference.
+
+# II. Mandatory & Stacking Requirements
+Mandatory Items: No specific jewelry piece is listed as mandatory, but the style encourages mixing both gold and silver jewelry.

stylist_guide/edi_en.md

@@ -0,0 +1,20 @@
+# Outfit Style Guide
+This guide summarizes the preferred styling logic, colors, patterns, and structure for Edi's outfits, emphasizing functionality and a flexible approach to color and print mixing.
+
+## I. Core Preferences and Prohibitions
+Primary Colors: Black is preferred as a mixing base.
+
+Dominant Colors: Maximum of 2 dominant colors per outfit (excluding Black and White).
+
+Print Mixing: Prints are mixed, specifically by using the same pattern (e.g., stripes, plaid) but in different sizes (e.g., thin stripe mixed with wide stripe, large check with small check).
+
+Prohibited Prints: None. All prints are acceptable, depending on the combination.
+
+Shoes: Sneakers are worn most often for comfort and versatility.
+
+Bags: Functional bags that can hold "everything" are preferred over mini bags. A specific favorite is the Lemaire croissant leather bag in a big size.
+
+Color Mixing: All color tones are acceptable for mixing together, including highly varied tones (e.g., rainbow colors), as long as they create a mutual harmony.
+
+## II. Styling Pattern: Functional and Harmonious
+This stylist prioritizes practical, comfortable items (functional bag, sneakers) while embracing complex color and print compositions that lean on Black as a foundational element. The style aims for a unique, harmonious look achieved through flexible mixing.

stylist_guide/mini_acc.md

@@ -0,0 +1,12 @@
+Stylist Accessories Guide
+I. Gold Jewelry
+Preference: Necklace, Bracelet, and Earrings must all be present and layered.
+Prohibition: Avoid Large/Bulky Earrings or Vector-style accessories.
+
+II. Watch
+Preference: Mandatory item.
+Prohibition: N/A.
+
+III. Accent Colors
+Preference: Added via accessories (e.g., scarves); Max 2 accent colors in total.
+Prohibition: Avoid Bright/Vivid colors dominating the outfit.

stylist_guide/mini_en.md

@@ -0,0 +1,37 @@
+# Outfit Style Guide
+
+This guide summarizes the preferred styling logic, colors, silhouettes, accessories, and layering patterns favored by the stylist.
+
+## I. Core Preferences and Prohibitions
+
+| Category | Preference (✔️) | Prohibition (❌) |
+| :--- | :--- | :--- |
+| **Primary Colors** | **Black, White, Gray, Earth Tones** (Solid colors preferred) | Avoid **Yellow** |
+| **Accent Colors** |                                                              | Avoid **Bright/Vivid** colors dominating |
+| **Patterns** | **Plaid/Checkered, Stripes** (Used as accents) | Strictly avoid **Floral/Small Prints (碎花)** |
+| **Style/Fit** | **Loose, Comfortable, Oversize**; **Clean and Sharp** tailoring | Tight-fitting or complicated silhouettes |
+| **Footwear** | **White Sneakers**, **Flats/Single Shoes**, **Loafers** | **Heels, Tall Boots** |
+
+---
+
+## II. Styling Pattern: Layering and Balance
+
+This stylist's outfits emphasize **comfort** and **layering** (creating depth). The common structure is: **3 Upper Body Items + 1 Lower Body Item**. The pattern mainly uses solid primary colors, mixed with subtle patterns, aiming for a look that is **relaxed and casual yet polished**.
+
+### 1. Classic Outfit Examples
+
+| Style | Structure | Keywords |
+| :--- | :--- | :--- |
+| **Smart Casual** | Milk Tea Oversize Blazer + White Shirt + Loose Black Pants  + White Sneakers | Neutral, Polished, Clean |
+| **Everyday Casual** | Milk Tea Oversize Blazer + Dark Blue Jeans or Dark Gray Shorts + **Loafers**+ Detailed Vest/Tank Top | Relaxed, Comfortable, Detailed |
+| **Sporty Chic** | Milk Tea Oversize Blazer + Black/Blue & White Striped Sleeveless Top + Black Leggings + White Sneakers | Mixed Style, Dynamic, Balanced |
+| **Dress Base** | Floral Dress (**Exception**) + White Sneakers | Comfortable, Accents, Exception Handling |
+
+### 2. Outfit Extended Rules Summary
+
+1.  **Color Palette**: Main garment colors are limited to **Black, White, Gray, and Earth Tones** to ensure a minimalist foundation. 
+2.  **Layering Principle**: A minimum of **2-3 layers** on the upper body, with patterned edges (e.g., shirt collar) visible to add depth without complexity.
+3.  **Fit Requirements**: All items should lean toward a **loose/oversize** fit to prioritize comfort; tailoring must be **clean and sharp**.
+4.  **Pattern Restriction**: Only **plaid/checkered or stripes** are acceptable as subtle accents; **strictly no florals**, unless an extremely minimal exception is made.
+5.  **Shoe/Bag Coordination**: Footwear must be **flat and casual** (white sneakers are preferred).
+6.  **Overall Balance**: When the upper body is complex (layered), the lower body should remain **simple**; the overall style is **neutral and polished**, avoiding highly feminine heels or boots.

stylist_guide/vera_acc.md

@@ -0,0 +1,9 @@
+# Accessory Style Guide
+This guide outlines accessory selection based on the desired overall aesthetic, emphasizing a balanced approach to metal tones.
+
+# I. Metal Tone and Aesthetic Constraints
+Jewelry Tone: Prefers Gold for a vintage and nostalgic feel.
+
+Jewelry Tone: Prefers Silver for grungier looks.
+
+Wear Preference: Wears both Gold and Silver, depending on the outfit's desired aesthetic.

stylist_guide/vera_en.md

@@ -0,0 +1,24 @@
+# Outfit Style Guide
+This guide summarizes the preferred styling logic, colors, patterns, and structure for Vera's outfits, emphasizing harmony in color mixing and the use of statement bags.
+
+# I. Core Preferences and Prohibitions
+Primary Colors: Most often wears Khakis, Black, Creams, and sometimes Burgundies.
+
+Dominant Colors: Maximum of two dominant colors per outfit, handled with care.
+
+Print Mixing: Prints are mixed. Acceptable combinations include big polka dots with small polka dots or different floral prints.
+
+Print Rule: Prints must be mixed only as long as the colors and shapes are harmonized.
+
+Prohibited Prints: None. Most prints are considered wearable.
+
+Color Mixing Prohibition: Avoid mixing warms and colds, and brights with muted tones.
+
+Shoes: Wears loafers most often.
+
+Bags: Prefers Bigger bags and bags that make a statement. Specific examples include The Row Margaux and Saint Laurent Icare.
+
+Prohibited Bags: Not a fan of crossbody or micro mini bags.
+
+# II. Styling Pattern: Harmonious Statement
+This stylist prioritizes a core color palette of neutrals and deep tones (Khakis, Black, Creams, Burgundies) and uses print mixing (e.g., different sized polka dots or florals) only when colors and shapes are harmonized. The overall look is anchored by comfortable shoes (loafers) and a large, functional, statement bag.