fix(notify): 修复传输生命周期竞态，完善背压与协议边界

- 完善 stream/bulk DataID 分配、预留和双向命名空间，修复并发打开及 dedicated/shared 回退时的 ID 冲突
- 将收发、回复、恢复任务和 sidecar 绑定原始会话与物理连接，防止重连后的旧消息误操作新连接
- 加强 close/reset 身份校验及实例移除检查，修复 dedicated attach 失败、通道引用和资源回收竞态
- 收紧批量发送器停止准入，确保在途入队完成后统一清理请求、缓冲区和等待者
- 修复 record 满队列死锁、取消时序号消耗及关闭竞态，确保关闭有界并返回真实错误
- 增加协商式 record 逻辑半关闭，保留反向 ACK；通过 reset 传递 RecordFailure，避免背压掩盖原始失败原因
- 补齐帧长度、批次数量、序号溢出和未确认窗口校验，提前拒绝超限数据并按字节预算拆批
- 为入站分发增加全局及单连接的条数、字节预算和阻塞背压，关闭时唤醒等待者，消除正常断连日志噪音
- 完善 bulk 窗口释放失败处理与传输诊断，补充并发、重连、背压、协议边界及真实 TCP 回归覆盖

msg.go

@@ -44,6 +44,7 @@ type Message struct {
 	TransportConn           *TransportConn
 	ServerConn              Client
 	inboundTransportProfile *transportProtectionProfile
+	clientRoute             clientSessionRoute
 	TransferMsg
 	Time        time.Time
 	inboundConn net.Conn
@@ -73,6 +74,10 @@ type messageClientTransferSender interface {
 	sendWithContextTimeout(context.Context, TransferMsg, time.Duration) (WaitMsg, error)
 }
 
+type messageClientRouteTransferSender interface {
+	sendWithContextTimeoutAtRoute(context.Context, clientSessionRoute, TransferMsg, time.Duration) (WaitMsg, error)
+}
+
 type messageReplyWriteTimeoutProvider interface {
 	ReplyWriteTimeout() time.Duration
 }
@@ -140,6 +145,12 @@ func (m *Message) replyContext(ctx context.Context, value MsgVal) (err error) {
 		if m.ServerConn == nil {
 			return net.ErrClosed
 		}
+		if m.clientRoute.bound() {
+			if sender, ok := m.ServerConn.(messageClientRouteTransferSender); ok {
+				_, err = sender.sendWithContextTimeoutAtRoute(ctx, m.clientRoute, reply, writeTimeout)
+				return err
+			}
+		}
 		if sender, ok := m.ServerConn.(messageClientTransferSender); ok {
 			_, err = sender.sendWithContextTimeout(ctx, reply, writeTimeout)
 		} else {