Update dependency ai to v7.0.58 - autoclosed - #156

v7.0.58

Compare Source

Patch Changes

• 72ad23f: Respect ToolLoopAgent timeouts configured in agent settings.

• ad6a650: feat(video): allow aspectRatio: 'adaptive' on generateVideo

  Some 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. aspectRatio on
  VideoModelV3CallOptions, VideoModelV4CallOptions, and
  experimental_generateVideo is 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]

  • @​ai-sdk/gateway@​4.0.46
  • @​ai-sdk/provider@​4.0.7
  • @​ai-sdk/provider-utils@​5.0.25

v7.0.57

Compare Source

Patch Changes

• Updated dependencies [1937bef]
  • @​ai-sdk/provider-utils@​5.0.24
  • @​ai-sdk/gateway@​4.0.45

v7.0.56

Compare Source

Patch Changes

• 25c9120: Expose provider metadata on language-model-call end callbacks and telemetry spans.

• 89080c8: fix (ai/gateway): make retried doStart calls idempotent

  generateVideo retries doStart, 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 an idempotency-key header, so a provider that deduplicates (the Vercel AI
  Gateway does) sees the same key on every attempt. GatewayVideoModel simply
  forwards the caller's headers rather than inferring retry identity from an
  options object, which would collide across unrelated calls.

• 79d6195: Stop pending and active resumed chat streams after cancellation, and prevent
  overlapping resumptions from applying stale updates.

• Updated dependencies [89080c8]

• Updated dependencies [89080c8]

  • @​ai-sdk/gateway@​4.0.44

v7.0.55

Compare Source

Patch Changes

• 3469d0c: feat: add batch APIs
• Updated dependencies [3469d0c]
  • @​ai-sdk/provider@​4.0.6
  • @​ai-sdk/gateway@​4.0.43
  • @​ai-sdk/provider-utils@​5.0.23

v7.0.54

Compare Source

Patch Changes

• a6b17a2: Allow ToolLoopAgent prepareCall callbacks to read and override the top-level reasoning option.
• 5615eb7: Add defaultInstructionsMiddleware for applying default language model instructions while preserving call-level overrides.
• 36a3ff6: Preserve preceding assistant messages when regenerating a response.

v7.0.52

Compare Source

Patch Changes

• 3836a85: Skip re-validating tool input for terminal output-available UI message parts.
• Updated dependencies [1bec07d]
• Updated dependencies [53c326e]
• Updated dependencies [d765f82]
  • @​ai-sdk/provider-utils@​5.0.21
  • @​ai-sdk/gateway@​4.0.41

v7.0.51

Compare Source

Patch Changes

• Updated dependencies [160ccdb]
  • @​ai-sdk/provider-utils@​5.0.20
  • @​ai-sdk/gateway@​4.0.40

v7.0.50

Compare Source

Patch Changes

• 79e133c: async APIs for generateVideo (poll, webhook)

  Adds an asynchronous start/status flow to the experimental video model
  interface (VideoModelV4): models may now implement doStart, doStatus,
  and handleWebhookOption instead of (or in addition to) doGenerate, and
  experimental_generateVideo accepts poll and webhook options to
  orchestrate completion via polling or webhooks. Polling configuration can use
  a custom delay implementation for durable workflow compatibility.

• da64b51: feat(code-mode): simplify tool caller configuration

• Updated dependencies [79e133c]

  • @​ai-sdk/provider@​4.0.5
  • @​ai-sdk/gateway@​4.0.39
  • @​ai-sdk/provider-utils@​5.0.19

v7.0.49

Compare Source

Patch Changes

• Updated dependencies [fb6d2f8]
  • @​ai-sdk/gateway@​4.0.38

v7.0.48

Compare Source

Patch Changes

• Updated dependencies [bdd5e28]
  • @​ai-sdk/gateway@​4.0.37

v7.0.47

Compare Source

Patch Changes

• Updated dependencies [5fc7da5]
• Updated dependencies [93b2acd]
  • @​ai-sdk/provider-utils@​5.0.18
  • @​ai-sdk/gateway@​4.0.36

v7.0.46

Compare Source

Patch Changes

• Updated dependencies [4f2e064]
  • @​ai-sdk/gateway@​4.0.35

v7.0.45

Compare Source

Patch Changes

• d6ce0ee: feat(ai): support experimental_toolCallers in streamText
• fa95504: feat(ai): support experimental tool callers in ToolLoopAgent
• 349afe7: Warn when generateText receives streaming-only firstChunkMs or chunkMs timeout settings.
• Updated dependencies [fa95504]
  • @​ai-sdk/provider-utils@​5.0.17
  • @​ai-sdk/gateway@​4.0.34

v7.0.44

Compare Source

Patch Changes

• 015acb4: fix telemetry attribution for language model calls that resolve to a different response model

v7.0.43

Compare Source

Patch Changes

• b192878: feat: add experimental_toolCaller routing to generateText for code mode
• Updated dependencies [d8210b6]
• Updated dependencies [af3f400]
• Updated dependencies [b192878]
  • @​ai-sdk/provider-utils@​5.0.16
  • @​ai-sdk/gateway@​4.0.33

v7.0.42

Compare Source

Patch Changes

• 1659cd5: Prevent validated downloads on Node.js from reaching private or internal services through DNS aliases or DNS rebinding by validating and pinning every resolved address at connection time.
• 60f97f6: support overriding model call settings for individual prepareStep invocations
• 6a5bdff: Fix validated Node.js downloads when the HTTP connector requests a single DNS address.
• 6de2ec1: Preserve provider metadata from empty text deltas in streamText.
• Updated dependencies [1659cd5]
• Updated dependencies [6a5bdff]
• Updated dependencies [0012529]
  • @​ai-sdk/provider-utils@​5.0.15
  • @​ai-sdk/gateway@​4.0.32

v7.0.41

Compare Source

Patch Changes

• 2e2224b: Route the warning system information banner to stderr so it does not corrupt application output written to stdout.
• Updated dependencies [bf216b3]
  • @​ai-sdk/gateway@​4.0.31

v7.0.40

Compare Source

Patch Changes

• c3782a6: Deprecate Experimental_GeneratedImage in favor of GeneratedFile.

v7.0.39

Compare Source

Patch Changes

• 09a52cb: Promote the repairText option to stable on generateObject and streamObject, with a deprecated experimental_repairText alias for backwards compatibility.
• Updated dependencies [0c464d9]
• Updated dependencies [c49380c]
  • @​ai-sdk/provider-utils@​5.0.14
  • @​ai-sdk/gateway@​4.0.30

v7.0.38

Compare Source

Patch Changes

• 7bd6bdd: Avoid synthesizing client tool errors for invalid provider-executed tool calls.
• 1e2f324: feat: add experimental speech translation model specification (Experimental_SpeechTranslationModelV4) and experimental_streamTranslate for streaming speech-to-speech translation
• Updated dependencies [d9d2a11]
• Updated dependencies [1e2f324]
  • @​ai-sdk/gateway@​4.0.29
  • @​ai-sdk/provider@​4.0.4
  • @​ai-sdk/provider-utils@​5.0.13

v7.0.37

Compare Source

Patch Changes

• Updated dependencies [0a7c7f4]
  • @​ai-sdk/gateway@​4.0.28

v7.0.36

Compare Source

Patch Changes

• 7fa85b2: fix(ai): use injective serialization for tool approval HMAC payload

  The tool approval signature (experimental_toolApprovalSecret) built its HMAC
  payload by joining fields with \n. Because fields such as toolName and
  toolCallId can themselves contain a newline, distinct field tuples could
  serialize to identical bytes, allowing a signed approval to verify against a
  different tuple. The payload is now serialized with JSON.stringify (with a
  versioned domain-separation prefix), which escapes delimiter/control characters
  and makes the encoding injective.

  Verification remains backwards compatible: a signature in the old format still
  verifies, but only when no field contains the \n delimiter (the condition
  that made the old format ambiguous), so a pending approval that straddles an
  upgrade is not rejected while the collision stays closed.

v7.0.35

Compare Source

Patch Changes

• 7f6650b: Return response piping promises so callers can catch stream read and write errors.
• 106ea59: feat(ai): add per-step first content timeout for streaming generations
• Updated dependencies [2112ff1]
  • @​ai-sdk/gateway@​4.0.27

v7.0.34

Compare Source

Patch Changes

• Updated dependencies [7c16f21]
  • @​ai-sdk/gateway@​4.0.26

v7.0.33

Compare Source

Patch Changes

• 76cb673: fix: detect MP4 audio from its ftyp box during transcription
• e808fa5: fix(ai): preserve tool parts when tool call IDs repeat across steps
• 33647d7: Preserve provider options when combining consecutive tool messages.
• Updated dependencies [02ffdcb]
• Updated dependencies [76cb673]
  • @​ai-sdk/provider-utils@​5.0.12
  • @​ai-sdk/gateway@​4.0.25

v7.0.32

Compare Source

Patch Changes

• 6cd7c74: fix: correct the onToolCall callback result documentation
• e35bcae: Allow UI message chunks to include fields added by newer server versions.
• a4eb3f3: Propagate abort reasons when generation is cancelled during tool execution.
• Updated dependencies [cefa3b1]
• Updated dependencies [8fbb89c]
  • @​ai-sdk/gateway@​4.0.24

v7.0.31

Compare Source

Patch Changes

• 70f18c3: fix(ai): emit denied tool output state for client-rejected approvals
• cd06458: fix(ai): call onInputStart before onInputAvailable during non-streaming tool calls
• Updated dependencies [cd06458]
  • @​ai-sdk/provider-utils@​5.0.11
  • @​ai-sdk/gateway@​4.0.23

v7.0.30

Compare Source

Patch Changes

• Updated dependencies [341616a]
• Updated dependencies [70fc45c]
  • @​ai-sdk/gateway@​4.0.22

v7.0.29

Compare Source

Patch Changes

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

v7.0.28

Compare Source

Patch Changes

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

v7.0.27

Compare Source

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

v7.0.26

Compare Source

Patch Changes

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

v7.0.25

Compare Source

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

v7.0.23

Compare Source

Patch Changes

• 930f949: feat(ai): wrap embedMany in tracing channel context
• Updated dependencies [867f80a]
  • @​ai-sdk/gateway@​4.0.17

v7.0.22

Compare Source

Patch Changes

• 8f89c25: Add the Cartesia provider with Sonic 3.5 speech generation, Ink-Whisper batch transcription, and Ink 2 realtime transcription support.

v7.0.21

Compare Source

Patch Changes

• 308a519: chore: enforce consistent imports from zod/v4 instead of zod
• Updated dependencies [308a519]
• Updated dependencies [7fe53d2]
  • @​ai-sdk/gateway@​4.0.16

v7.0.20

Compare Source

Patch Changes

• b9ac19f: Flush compressed Node.js response chunks as they are piped so UI message and text streams remain incremental in Express and Next.js.
• a4186d6: Promote the repairToolCall option to stable, with a deprecated experimental_repairToolCall alias for backwards compatibility.