Sourced from ai's releases.

ai@6.0.230

Patch Changes

• 19093fd: fix(ai): call onInputStart before onInputAvailable during non-streaming tool calls
• Updated dependencies [19093fd]
  • @​ai-sdk/provider-utils@​4.0.40
  • @​ai-sdk/gateway@​3.0.153

Sourced from ai's changelog.

7.0.29

Patch Changes

• Updated dependencies [7069785]
• Updated dependencies [4bf9ac2]
  • @​ai-sdk/gateway@​4.0.21

7.0.28

Patch Changes

• 0bc8d4f: Fix chat onFinish handling when overlapping requests clear the active response before a resume stream finishes.

7.0.27

Patch Changes

• ac01b79: Allow validating assistant UI messages with empty parts so persisted errored responses remain loadable.
• 2696562: experimental_streamTranscribe result promises now resolve without consuming fullStream: accessing any result promise consumes the stream internally. Previously await result.text alone deadlocked on transform backpressure. Because live transcription streams can be unbounded, fullStream is explicitly single-consumer (no replay buffering): access it once, before any result promise, when both stream parts and final results are needed.
• Updated dependencies [31c7be8]
• Updated dependencies [4d096f6]
  • @​ai-sdk/provider-utils@​5.0.10
  • @​ai-sdk/gateway@​4.0.20

7.0.26

Patch Changes

• 27d294d: feat(ai): group orphaned tool calls after tool approvals under parent span

7.0.25

Patch Changes

• 7805e4a: Cancelling the experimental_streamTranscribe fullStream now also aborts a still-pending doStream setup, so a model whose doStream has not yet resolved is cancelled instead of leaking.
• f8e82fd: Update the experimental_streamTranscribe unsupported-model error message now that gateway string model IDs can support streaming transcription.
• Updated dependencies [4be62c1]
• Updated dependencies [f8e82fd]
• Updated dependencies [7805e4a]
• Updated dependencies [cd12954]
  • @​ai-sdk/provider-utils@​5.0.9
  • @​ai-sdk/gateway@​4.0.19

7.0.24

Patch Changes

• e193290: Cancel the caller's audio stream when experimental_streamTranscribe fails before or during streaming. Previously, when the model's doStream rejected before a stream existed (e.g. missing API key or other auth failure), the audio stream was never consumed or cancelled, so an upstream producer piping into it would hang forever.
• Updated dependencies [e193290]

... (truncated)

• 6427ca9 Version Packages (#17324)
• 3649694 Version Packages (#17251)
• 0bc8d4f fix: prevent Chat resume-stream onFinish errors when requests overlap (#16620)
• 6976682 Version Packages (#17196)
• 2696562 fix(ai): streamTranscribe result promises resolve without consuming fullStrea...
• ac01b79 fix: UI message validation rejects persisted assistant responses with empty p...
• 2ba5f8a Version Packages (#17181)
• 27d294d feat(ai): group orphaned tool calls after tool approvals under parent span (#...
• cb68fa6 Version Packages (#17175)
• f8e82fd feat(gateway): streaming transcription via GatewayTranscriptionModel.doStream...
• Additional commits viewable in compare view