fix: 修复 dedicated bulk attach 竞态并优化 short write 补写路径

- 客户端 dedicated attach 回复改为精确读取单帧，避免 attach reply 与后续 NBR1 数据粘连后被误解析
  - 服务端 accepted attach 改为先 detach transport，再直接回 attach reply，随后立即切入 dedicated bulk read loop
  - transport 读循环在 stop 或 transport ownership 失效后不再继续上推已读数据，避免 handoff 后首包被旧 reader 吃掉
  - dedicated bulk record 写路径改为 full-write，消除 short write 导致的 invalid bulk fast payload
  - 优化 vectored write 补写策略：先尝试一次 writev，未写完时直接顺序补完剩余 buffers，减少重复 WriteTo 开销
  - 放宽 vectored write 能力识别，支持通过 UnwrapConn/WriteBuffers 命中 fast path
  - 修复 dedicated batch 排队路径 payload 复用问题，改为深拷贝 queued items
  - 补齐 dedicated attach、short write、payload clone、transport stop/handoff 等回归测试

client_conn_session_test.go

@@ -332,6 +332,24 @@ func TestLogicalDetachTransportForTransferKeepsHandoffConnAlive(t *testing.T) {
 	}
 }
 
+func TestLogicalHandleTUTransportReadResultWithSessionDropsDataAfterTransportStop(t *testing.T) {
+	server := NewServer().(*ServerCommon)
+	left, right := net.Pipe()
+	defer right.Close()
+
+	stopCtx, stopFn := context.WithCancel(context.Background())
+	logical, _, _ := newRegisteredServerLogicalForTest(t, server, "logical-stop-read-drop", left, stopCtx, stopFn)
+	if logical == nil {
+		t.Fatal("logical should not be nil")
+	}
+	generation := logical.transportGenerationSnapshot()
+	stopFn()
+
+	if logical.handleTUTransportReadResultWithSession(stopCtx, left, generation, len([]byte("late-data")), []byte("late-data"), nil) {
+		t.Fatal("handleTUTransportReadResultWithSession should stop after transport stop")
+	}
+}
+
 func TestClientConnTransportBindingSnapshotUsesRuntimeBinding(t *testing.T) {
 	client := &ClientConn{}
 	left, right := net.Pipe()