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

client.go

@@ -70,6 +70,8 @@ type ClientCommon struct {
 	streamRuntime                 *streamRuntime
 	recordRuntime                 *recordRuntime
 	bulkRuntime                   *bulkRuntime
+	bulkRecovery                  *bulkRecoveryQueue
+	bulkRecoveryMu                sync.Mutex
 	bulkDefaultOpenMode           BulkOpenMode
 	bulkNetworkProfile            BulkNetworkProfile
 	bulkOpenTuning                BulkOpenTuning
@@ -139,6 +141,7 @@ func NewClient() Client {
 	client.streamRuntime = newStreamRuntime("cstrm")
 	client.recordRuntime = newRecordRuntime()
 	client.bulkRuntime = newBulkRuntime("cblk")
+	client.bulkRecovery = newBulkRecoveryQueue(client.reportBulkRecoveryError)
 	client.bulkDedicatedLanes = make(map[uint32]*bulkDedicatedLane)
 	if client.bulkDedicatedAttachLimit > 0 {
 		client.bulkDedicatedAttachSem = make(chan struct{}, client.bulkDedicatedAttachLimit)