FrameworksOfficial

AI SDK moves experimental low-memory streaming to a dedicated API

The October 16 low-memory option moved on October 19 to experimental_streamTextLowMemory to repair reusable-option and ReturnType typing.

Why it matters

Experimental stream API names and type boundaries directly affect upgrade cost and recovery logic in generative interfaces.

A closer look

Version 7.0.143 introduced single-consumer execution without replay buffering or retained final-content results. Version 7.0.144 then replaced the experimental_lowMemory option with experimental_streamTextLowMemory(options). Lazy default chat IDs remain part of 7.0.143.

Who this is for

Streaming chat and generative UI developers

Original sources

Revisions & corrections (3)

— 更正2026-10-20中文限制中的次日:原版为10月16日,后续7.0.144为10月19日,相隔三天。保留真实事件日期、索引时间和修订历史;英文next-patch无需更改。

— Merge the official 7.0.144 follow-up into the existing low-memory streaming event; preserve the original event date while documenting the next-patch API migration.

— Verified distinct dated original release; limitations preserved.

Related events

Frameworks

assistant-ui's October 28 release tightens prompt review, tool-result ownership and configuration writes

assistant-ui released a coordinated package set on October 28. Generative Frame 0.0.9 fills the composer with widget and MCP App prompts for review before sending; assistant-stream 0.3.55 fixes stale model content surviving a later tool response and pending results moving when tool-call IDs are reused; the CLI also narrows configuration paths and plan-revision boundaries.

Frameworks

AI SDK 7.0.155 removes runtime checks already guaranteed by static types

Released October 27, AI SDK 7.0.155 stops revalidating message history against the ModelMessage schema in text and object generation and removes several shape checks covered by TypeScript, reducing a linear cost in long conversations and multi-step runs.