Sourced from ai's releases.
ai@6.0.253
Patch Changes
- d91d30b: Preserve reasoning block IDs from UI message streams on reasoning UI parts.
- Updated dependencies [0ec239b]
@ai-sdk/gateway@3.0.172ai@6.0.252
Patch Changes
- 2f96d3f: Allow providers without reranking model support to satisfy the
Providertype.- afb1965: Propagate errors thrown by the Chat
onFinishcallback to the initiating request.- Updated dependencies [18b0965]
- Updated dependencies [451d2c3]
@ai-sdk/gateway@3.0.171
Sourced from ai's changelog.
7.0.59
Patch Changes
- Updated dependencies [401a4ba]
- Updated dependencies [7af9646]
7.0.58
Patch Changes
72ad23f: Respect ToolLoopAgent timeouts configured in agent settings.
ad6a650: feat(video): allow
aspectRatio: 'adaptive'ongenerateVideoSome video models derive the output ratio from the input and reject explicit
{width}:{height}values — BytePlus Seedance 2.5 does this for first-frame, first-and-last-frame, editing, and extension tasks.aspectRatioonVideoModelV3CallOptions,VideoModelV4CallOptions, andexperimental_generateVideois now`${number}:${number}` | 'adaptive', so those calls no longer need a type assertion. Support is provider-specific.81cd026: Reduce bundle size by making internal Zod v4 imports tree-shakeable.
Updated dependencies [c477556]
Updated dependencies [ad6a650]
Updated dependencies [81cd026]
7.0.57
Patch Changes
7.0.56
Patch Changes
25c9120: Expose provider metadata on language-model-call end callbacks and telemetry spans.
89080c8: fix (ai/gateway): make retried
doStartcalls idempotent
generateVideoretriesdoStart, which creates a billable generation, so a retry after a lost response could start a second one. It now mints one idempotency token per logical start — outside the retry closure — and forwards it as anidempotency-keyheader, so a provider that deduplicates (the Vercel AI
... (truncated)
cbdbeee
Version Packages (#18645)63db193
Version Packages (#18587)72ad23f
fix: ToolLoopAgent settings-level timeouts being ignored by generate and
stre...81cd026
perf: make zod imports tree-shakeable (#18304)ad6a650
feat(video): allow aspectRatio: 'adaptive' on generateVideo
(#18586)ae26160
Version Packages (#18566)2f04a5e
Version Packages (#18560)89080c8
feat (provider/gateway): support async video operations
(doStart/doStatus) on...25c9120
feat: expose provider metadata in language model call end callbacks (#18100)79d6195
fix: resumed chat streams updating state after cancellation or a newer
resume...This version was pushed to npm by GitHub Actions, a new releaser for ai since your current version.