refactor: 统一 Packet 通信协议 + 后端配置管理 + UI 清理

- 合并 server.py 到 core/__init__.py，使用统一 Packet 协议
- 后端管理配置持久化 (~/.trulymem/config.json)
- 前端移除 ConfigService，通过 BackendClient 与后端通信
- 删除 UI 中冗余的 AI 推理逻辑 (chat_service, tool_service, message_handler)
- 删除 core/tools 重复文件 (tool_executor, tool_limiter)
- 提示词管理器支持用户自定义 (~/.trulyemem/system_prompt.md)
- 启动入口优化配置路径逻辑
- 更新测试覆盖 (42 tests)
- 更新文档

core/graph_client.py

@@ -303,12 +303,12 @@ class Neo4jGraph:
 class GraphMemoryClient:
     """图记忆客户端"""
     
-    def __init__(self, api_key: str, base_url: str, graph):
+    def __init__(self, api_key: str, base_url: str, graph, model: str = "deepseek-chat"):
         self.client = OpenAI(api_key=api_key, base_url=base_url)
         self.graph = graph
         self.tools = TOOLS
+        self.model = model
         
-        # 使用新的提示词管理器
         prompt_manager = PromptManager()
         self.system_prompt = prompt_manager.get_system_prompt()
     
@@ -330,7 +330,7 @@ class GraphMemoryClient:
             messages.extend(tool_results)
         
         response = self.client.chat.completions.create(
-            model=MODEL_NAME,
+            model=self.model,
             messages=messages,
             tools=self.tools,
             tool_choice="auto"
@@ -347,7 +347,7 @@ class GraphMemoryClient:
         messages.extend(messages_history)
         
         response = self.client.chat.completions.create(
-            model=MODEL_NAME,
+            model=self.model,
             messages=messages,
             tools=self.tools,
             tool_choice="auto"
@@ -373,7 +373,7 @@ class GraphMemoryClient:
             messages.extend(tool_results)
 
         stream = self.client.chat.completions.create(
-            model=MODEL_NAME,
+            model=self.model,
             messages=messages,
             tools=self.tools,
             tool_choice="auto",