fix: 更新聊天代理处理逻辑，增强敏感内容检测和中断提示

- 在 chat_agent 函数中，优化了敏感内容检测后的响应，添加了时间成本的记录。
- 修改了前端 AgentChatComponent 和 AgentMessageComponent，以正确处理和显示敏感内容中断的提示信息。
- 移除了不必要的代码注释和冗余逻辑，提升了代码可读性。

server/routers/chat_router.py

@@ -375,7 +375,6 @@ async def get_agent(current_user: User = Depends(get_required_user)):
     return {"agents": agents}
 
 
-# TODO:[未完成]这个thread_id在前端是直接生成的1234，最好传入thread_id时做校验只允许uuid4
 @chat.post("/agent/{agent_id}")
 async def chat_agent(
     agent_id: str,
@@ -472,7 +471,8 @@ async def chat_agent(
                     if conf.enable_content_guard and await content_guard.check_with_keywords(full_msg.content[-20:]):
                         logger.warning("Sensitive content detected in stream")
                         await save_partial_message(conv_manager, thread_id, full_msg, "content_guard_blocked")
-                        yield make_chunk(message="检测到敏感内容，已中断输出", status="error")
+                        meta["time_cost"] = asyncio.get_event_loop().time() - start_time
+                        yield make_chunk(status="interrupted", message="检测到敏感内容，已中断输出", meta=meta)
                         return
 
                     yield make_chunk(content=msg.content, msg=msg.model_dump(), metadata=metadata, status="loading")
@@ -487,7 +487,8 @@ async def chat_agent(
             ):
                 logger.warning("Sensitive content detected in final message")
                 await save_partial_message(conv_manager, thread_id, full_msg, "content_guard_blocked")
-                yield make_chunk(message="检测到敏感内容，已中断输出", status="error")
+                meta["time_cost"] = asyncio.get_event_loop().time() - start_time
+                yield make_chunk(status="interrupted", message="检测到敏感内容，已中断输出", meta=meta)
                 return
 
             # After streaming finished, check for interrupts and save messages
@@ -512,16 +513,6 @@ async def chat_agent(
             # 客户端主动中断连接，检查中断并保存已生成的部分内容
             logger.warning(f"Client disconnected, cancelling stream: {e}")
 
-            # 断开连接时不检查中断，直接保存部分消息
-            langgraph_config = {"configurable": input_context}
-
-            # 尝试从 LangGraph state 保存消息（可能没有，因为中断了）
-            await save_messages_from_langgraph_state(
-                agent_instance=agent,
-                thread_id=thread_id,
-                conv_mgr=conv_manager,
-                config_dict=langgraph_config,
-            )
 
             # 如果有手动维护的 full_msg，直接保存到数据库
             if full_msg:
@@ -539,16 +530,6 @@ async def chat_agent(
         except Exception as e:
             logger.error(f"Error streaming messages: {e}, {traceback.format_exc()}")
 
-            # 异常情况下也不检查中断，直接保存部分消息
-            langgraph_config = {"configurable": input_context}
-
-            # 尝试从 LangGraph state 保存消息（可能没有，因为异常了）
-            await save_messages_from_langgraph_state(
-                agent_instance=agent,
-                thread_id=thread_id,
-                conv_mgr=conv_manager,
-                config_dict=langgraph_config,
-            )
 
             # 如果有手动维护的 full_msg，直接保存到数据库
             if full_msg:

src/agents/common/middlewares/attachment_middleware.py

@@ -64,7 +64,7 @@ class AttachmentMiddleware(AgentMiddleware[AttachmentState]):
         self, request: ModelRequest, handler: Callable[[ModelRequest], ModelResponse]
     ) -> ModelResponse:
         # Read from State: get uploaded files metadata
-        logger.debug(f"inject_attachment_context: request.state = {request.state}")
+        # logger.debug(f"inject_attachment_context: request.state = {request.state}")
         attachments = request.state.get("attachments", [])
 
         if attachments:

web/src/components/AgentChatComponent.vue

@@ -470,7 +470,7 @@ const resetOnGoingConv = (threadId = null, preserveMessages = false) => {
 };
 
 const _processStreamChunk = (chunk, threadId) => {
-  const { status, msg, request_id, message } = chunk;
+  const { status, msg, request_id, message: chunkMessage } = chunk;
   const threadState = getThreadState(threadId);
   // console.log('Processing stream chunk:', chunk, 'for thread:', threadId);
 
@@ -489,7 +489,7 @@ const _processStreamChunk = (chunk, threadId) => {
       }
         return false;
     case 'error':
-      handleChatError({ message }, 'stream');
+      handleChatError({ message: chunkMessage }, 'stream');
       // Stop the loading indicator
       if (threadState) {
         threadState.isStreaming = false;
@@ -525,6 +525,10 @@ const _processStreamChunk = (chunk, threadId) => {
       if (threadState) {
         threadState.isStreaming = false;
       }
+      // 如果有 message 字段，显示提示（例如：敏感内容检测）
+      if (chunkMessage) {
+        message.info(chunkMessage);
+      }
       fetchThreadMessages({ agentId: currentAgentId.value, threadId: threadId })
         .finally(() => {
           resetOnGoingConv(threadId, true);

web/src/components/AgentMessageComponent.vue

@@ -30,9 +30,10 @@
       <div v-else-if="parsedData.reasoning_content"  class="empty-block"></div>
 
       <!-- 错误提示块 -->
-      <div v-if="message.error_type" class="error-hint" :class="{ 'error-interrupted': message.error_type === 'interrupted', 'error-unexpect': message.error_type === 'unexpect' }">
+      <div v-if="message.error_type" class="error-hint">
         <span v-if="message.error_type === 'interrupted'">回答生成已中断</span>
         <span v-else-if="message.error_type === 'unexpect'">生成过程中出现异常</span>
+        <span v-else-if="message.error_type === 'content_guard_blocked'">检测到敏感内容，已中断输出</span>
       </div>
 
       <div v-if="validToolCalls && validToolCalls.length > 0" class="tool-calls-container">
@@ -365,19 +366,9 @@ const toggleToolCall = (toolCallId) => {
     display: flex;
     align-items: center;
     gap: 8px;
-
-    &.error-interrupted {
-      background-color: #fffbeb;
-      // border: 1px solid #fbbf24;
-      color: #92400e;
-    }
-
-    &.error-unexpect {
     background-color: #fef2f2;
     // border: 1px solid #f87171;
     color: #991b1b;
-    }
-
     span {
       line-height: 1.5;
     }