Agent streaming has outgrown token deltas.
Real apps need to render tools, state, subagents, media, interrupts, and reconnects without parsing a firehose of raw events.
The new @LangChain streaming protocol turn agent runs into typed projections apps can subscribe to.
http://x.com/i/article/2057502554934607872
Users praise LangChain's new streaming primitives because they make subagent streams first-class and support content-block handling for messages, reasoning, and tool calls beyond just text.
No Digg Deeper questions have been answered for this story yet.
streaming from modern agents is pretty complex!
especially with - parallel tools / subagents - multimodal content - human in the loop events
our new streaming primitives make all of this ergonomic!
Agent streaming has outgrown token deltas.
Real apps need to render tools, state, subagents, media, interrupts, and reconnects without parsing a firehose of raw events.
The new @LangChain streaming protocol turn agent runs into typed projections apps can subscribe to.
One of my favorite parts of the new @LangChain streaming primitives: subagent streams are first-class 🥇
Instead of flattening every worker into one transcript, UIs can discover subagents, show their status, and subscribe only to the messages/tool calls they render
Code: https://github.com/langchain-ai/streaming-cookbook/blob/main/typescript/streaming/src/subagents/remote.ts
Streaming is no longer just text 📚
The new primitives are content-block based, so the same architecture can handle messages, reasoning, tool calls, images, audio, video, and custom app data 📁 🎵🎥
The multimodal storybook demo shows where agent UIs are heading 😊
Code: https://github.com/langchain-ai/streaming-cookbook/tree/main/typescript/multimodal
