feat: 完善 RecordStream 的协议协商、运行观测与文档说明

- 将 RecordStream 出站路径收敛为单 writer loop
  - 支持在 batch header 中 piggyback AckSeq，保留独立 ack 作为兼容回退
  - 增加 record stream 打开阶段能力协商，支持 mixed-version peer 自动降级
  - 补充 RecordSnapshot 与 diagnostics summary 的 record-plane 观测项
  - 增加 batch/ack/error frame、piggyback ack、barrier 等待拆分与 apply backlog 指标
  - 收紧 TransportConn detach 后的 runtime snapshot 语义
  - 补充 README 中的 RecordStream 语义、兼容行为与诊断快照说明
  - 补充相关单测与 race 回归验证

server_stream.go

@@ -33,6 +33,7 @@ func (s *ServerCommon) OpenStreamLogical(ctx context.Context, logical *LogicalCo
 	if resp.DataID != 0 {
 		req.DataID = resp.DataID
 	}
+	req.Metadata = mergeStreamMetadata(req.Metadata, resp.Metadata)
 	transport := logical.CurrentTransportConn()
 	stream := newStreamHandle(logical.stopContextSnapshot(), runtime, scope, req, 0, logical, transport, resp.TransportGeneration, serverStreamCloseSender(s, logical, nil), serverStreamResetSender(s, logical, nil), serverStreamDataSender(s, transport), runtime.configSnapshot())
 	if err := runtime.register(scope, stream); err != nil {
@@ -72,6 +73,7 @@ func (s *ServerCommon) OpenStreamTransport(ctx context.Context, transport *Trans
 	if resp.DataID != 0 {
 		req.DataID = resp.DataID
 	}
+	req.Metadata = mergeStreamMetadata(req.Metadata, resp.Metadata)
 	stream := newStreamHandle(logical.stopContextSnapshot(), runtime, scope, req, 0, logical, transport, resp.TransportGeneration, serverStreamCloseSender(s, logical, transport), serverStreamResetSender(s, logical, transport), serverStreamDataSender(s, transport), runtime.configSnapshot())
 	if err := runtime.register(scope, stream); err != nil {
 		_, _ = sendStreamResetServerTransport(context.Background(), s, transport, StreamResetRequest{