const shared = Stream.share(source, {
首先，大模型本身无法主动感知，只能对输入被动响应。智能体需要用外部感知组件来主动获取环境信息。对于数字世界的任务，通过智能体工程可以建立基于时间的触发器，定期检查日志、邮件、股价变动等；或基于事件的订阅、监听，接收API推送的事件通知，或当数据库发生变更时自动唤醒记录数据。在物理世界中，智能体还可以通过传感器、摄像头、麦克风等设备采集视觉、听觉、触觉等信号。
，更多细节参见夫子
for t := range c {
That said, it's important to recognize that locking in itself is not bad. It does, in fact, serve an important purpose to ensure that applications properly and orderly consume or produce data. The key challenge is with the original manual implementation of it using APIs like getReader() and releaseLock(). With the arrival of automatic lock and reader management with async iterables, dealing with locks from the users point of view became a lot easier.