feat: add DeepSeek official API support and capture reasoning content

- Add DeepSeek provider routing: deepseek-chat/deepseek-reasoner use
  api.deepseek.com, other models use SiliconFlow
- Add stream_with_reasoning() using raw OpenAI SDK to capture
  reasoning_content (langchain_openai strips this field)
- RAG chain and conversation chain both use stream_with_reasoning
  for proper reasoning display in thinking models
- Frontend model selector: grouped by provider (DeepSeek official +
  SiliconFlow), default changed to deepseek-chat
- Regenerate message converted to streaming with reasoning capture
- Minor UI: globals.css additions, chat store refactoring

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/src/rag/conversation_chains.py

@@ -24,7 +24,9 @@ class ConversationChain:
             system_prompt: 系统提示词
             model: 可选的模型名称，如 deepseek-ai/DeepSeek-V3, Qwen/QwQ-32B
         """
-        self.llm = get_llm_client(model=model).llm
+        _sf_client = get_llm_client(model=model)
+        self.llm = _sf_client.llm
+        self.client = _sf_client
         self.system_prompt = system_prompt or "你是一个专业的国土空间规划知识问答助手。请基于你的知识回答用户的问题。"
         
         # 创建带历史的Prompt模板
@@ -94,24 +96,18 @@ class ConversationChain:
 
         yield {"type": "thinking", "stage": "generating", "message": "正在生成回答..."}
 
-        # 直接流式调用 LLM 以捕获推理内容
-        prompt_messages = await self.prompt.ainvoke({
+        # 直接使用原始 OpenAI SDK 捕获推理内容
+        prompt_value = await self.prompt.ainvoke({
             "question": question,
             "chat_history": history_messages
         })
+        prompt_messages = prompt_value.to_messages()
 
         content_started = False
-        async for chunk in self.llm.astream(prompt_messages):
-            # 捕获推理内容（DeepSeek-R1/QwQ 等推理模型）
-            if hasattr(chunk, 'additional_kwargs') and 'reasoning_content' in chunk.additional_kwargs:
-                reasoning_text = chunk.additional_kwargs['reasoning_content']
-                if reasoning_text:
-                    yield {"type": "thinking", "stage": "reasoning", "message": reasoning_text}
-            elif hasattr(chunk, 'reasoning_content') and chunk.reasoning_content:
-                yield {"type": "thinking", "stage": "reasoning", "message": chunk.reasoning_content}
-
-            content = chunk.content if hasattr(chunk, 'content') else str(chunk)
-            if content:
+        async for event_type, content in self.client.stream_with_reasoning(prompt_messages):
+            if event_type == "reasoning":
+                yield {"type": "thinking", "stage": "reasoning", "message": content}
+            elif event_type == "content":
                 if not content_started:
                     content_started = True
                 yield {"type": "chunk", "content": content}