FrameworksOfficial

assistant-ui makes aborts, rate limits, persistence failures and composer origins observable

assistant-ui's October 22 package set distinguishes rate limits, validation failures, server errors, aborts, incomplete runs and persistence failures in Cloud telemetry, while attaching origins to composer text changes.

Why it matters

If a generative interface collapses “no reply,” “storage failed” and “the user stopped” into one empty state, product and audit systems cannot decide whether to recover, retry, explain or stop. Draft recovery likewise depends on why the text changed.

A closer look

assistant-cloud 0.2.8 maps HTTP 429, 400/422 and 5xx to rate_limited, validation_failed and server_error. Stops before the first token report aborted, and output-free completion reports incomplete. Failed history appends or updates are no longer skipped or reported completed; they become persistence_error. React/Vue 0.15.31/0.0.6 also tag composer.textChange as user, recall, send, return, reset or external, and disable unarchive controls when an adapter cannot restore a thread.

Who this is for

Frontend and platform teams building multi-turn agent UI, draft recovery, run monitoring and failure audit

Original sources

Revisions & corrections (1)

— The October 22 official package releases combine distinct but related runtime observability and recovery-boundary changes; linked merged PRs provide scope and known omissions.

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.