Patch Changes
- Updated dependencies [31205a4]
- @ai-sdk/provider-utils@4.0.46
- @ai-sdk/gateway@3.0.174
Release activity
| May | Jun | Jul | Aug | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Sunday | No releases on Aug 2, 2026 | No releases on Aug 9, 2026 | No releases on Aug 16, 2026 | |||||||||||||
| Monday | 4 releases on Aug 3, 2026 | 4 releases on Aug 10, 2026 | No releases on Aug 17, 2026 | |||||||||||||
| Tuesday | 3 releases on Aug 4, 2026 | 7 releases on Aug 11, 2026 | ||||||||||||||
| Wednesday | 3 releases on Aug 5, 2026 | 6 releases on Aug 12, 2026 | ||||||||||||||
| Thursday | 3 releases on Aug 6, 2026 | 2 releases on Aug 13, 2026 | ||||||||||||||
| Friday | 6 releases on Jul 31, 2026 | 4 releases on Aug 7, 2026 | 4 releases on Aug 14, 2026 | |||||||||||||
| Saturday | 3 releases on Aug 1, 2026 | No releases on Aug 8, 2026 | No releases on Aug 15, 2026 |
49 releases since Jul 31, 2026, busiest day 7
Changelog
Fixed 2
- Avoid repeatedly cloning accumulated text in readUIMessageStream while preserving independent snapshots for mutable nested values
- Fix declaration emit for exported values that infer an Output type
Patch Changes
- bf11412: Avoid repeatedly cloning accumulated text in
readUIMessageStreamwhile preserving independent snapshots for mutable nested values. - 7ec6b69: Fix declaration emit for exported values that infer an
Outputtype.
Fixed 2
- Keep chat status submitted until response content begins streaming
- Fix declaration emit for exported values that infer an Output type
Patch Changes
- 0782259: Keep chat status submitted until response content begins streaming.
- 2fd1214: Fix declaration emit for exported values that infer an
Outputtype.
Fixed 3
- Keep chat status submitted until response content begins streaming
- Avoid repeatedly cloning accumulated text in readUIMessageStream while preserving independent snapshots for mutable nested values
- Fix declaration emit for exported values that infer an Output type
Patch Changes
- 35a94b0: Keep chat status submitted until response content begins streaming.
- 93d24c6: Avoid repeatedly cloning accumulated text in
readUIMessageStreamwhile preserving independent snapshots for mutable nested values. - 1bd1caf: Fix declaration emit for exported values that infer an
Outputtype.
Fixed 3
- Avoid repeatedly cloning accumulated text in readUIMessageStream while preserving independent snapshots for mutable nested values
- Preserve root-level JSON Schema definitions when wrapping array output schemas
- Propagate errors thrown by the Chat onFinish callback to the initiating request
Patch Changes
- dc8caae: Avoid repeatedly cloning accumulated text in
readUIMessageStreamwhile preserving independent snapshots for mutable nested values. - 72ec74f: Preserve root-level JSON Schema definitions when wrapping array output schemas.
- c5b0515: Propagate errors thrown by the Chat
onFinishcallback to the initiating request. - Updated dependencies [16650e9]
- @ai-sdk/gateway@4.0.52
Changed 1
- Keep chat status submitted until response content begins streaming
Fixed 1
- Propagate errors thrown by chat onFinish callbacks
Patch Changes
- c425210: Propagate errors thrown by chat
onFinishcallbacks. - eb7f2ac: Keep chat status submitted until response content begins streaming.
- Updated dependencies [df0cbe9]
- @ai-sdk/gateway@2.0.134
Changed 1
- Updated @ai-sdk/gateway to version 2.0.133
Patch Changes
- Updated dependencies [91e93fa]
- Updated dependencies [de0921d]
- @ai-sdk/gateway@2.0.133
Fixed 1
- Preserve reasoning block IDs from UI message streams on reasoning UI parts
Patch Changes
- d91d30b: Preserve reasoning block IDs from UI message streams on reasoning UI parts.
- Updated dependencies [0ec239b]
- @ai-sdk/gateway@3.0.172
Changed 1
- @ai-sdk/gateway dependency updated to version 4.0.51
Patch Changes
- Updated dependencies [ea75787]
- Updated dependencies [b20de9e]
- @ai-sdk/gateway@4.0.51
Changed 1
- Allow providers without reranking model support to satisfy the Provider type
Fixed 1
- Propagate errors thrown by the Chat onFinish callback to the initiating request
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
Fixed 1
- Preserve reasoning part IDs when processing UI message streams
Patch Changes
- 412c15e: Preserve reasoning part IDs when processing UI message streams.
- Updated dependencies [1e632f7]
- @ai-sdk/gateway@2.0.132
Changed 1
- Allow providers without reranking model support to be assigned to Provider
Fixed 1
- Preserve reasoning block IDs from UI message streams on reasoning UI parts
Patch Changes
- d0a5807: Preserve reasoning block IDs from UI message streams on reasoning UI parts.
- dcf33e8: Allow providers without reranking model support to be assigned to
Provider. - Updated dependencies [a4d386d]
- @ai-sdk/gateway@4.0.50
Fixed 1
- Prevent resumeStream from copying the previous assistant message into the resumed response
Patch Changes
- 2604cb6: Prevent
resumeStreamfrom copying the previous assistant message into the resumed response.
Added 1
- Add typed custom bodies to Completion APIs
Patch Changes
- e0bcf52: feat(ui): add typed custom bodies to Completion APIs
Fixed 1
- Prevent streaming telemetry spans from ending twice or remaining unfinished when model calls fail
Patch Changes
- 66dd974: Prevent streaming telemetry spans from ending twice or remaining unfinished when model calls fail.
- Updated dependencies [0e51b7b]
- @ai-sdk/provider-utils@3.0.32
- @ai-sdk/gateway@2.0.131
Fixed 2
- Prevent streaming telemetry spans from ending twice when model calls fail
- Prevent resumeStream from copying the previous assistant message into the resumed response
Patch Changes
- a077695: Prevent streaming telemetry spans from ending twice when model calls fail.
- 7ce3b8c: Prevent
resumeStreamfrom copying the previous assistant message into the resumed response. - Updated dependencies [b2a4d5a]
- @ai-sdk/provider-utils@4.0.45
- @ai-sdk/gateway@3.0.170
Fixed 1
- Stop pending and active resumed chat streams after cancellation, and prevent overlapping resumptions from applying stale updates
Patch Changes
- 2709314: Stop pending and active resumed chat streams after cancellation, and prevent overlapping resumptions from applying stale updates.
- Updated dependencies [b474448]
- @ai-sdk/gateway@2.0.130
Fixed 1
- Stop pending and active resumed chat streams after cancellation, and prevent overlapping resumptions from applying stale updates
Patch Changes
- a774b7b: Stop pending and active resumed chat streams after cancellation, and prevent overlapping resumptions from applying stale updates.
- Updated dependencies [b39f987]
- Updated dependencies [d79117b]
- @ai-sdk/gateway@3.0.169
Added 1
- Allow `aspectRatio: 'adaptive'` on `generateVideo` for video models that derive output ratio from input
Patch Changes
-
2171d15: 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, andexperimental_generateVideois now`${number}:${number}` | 'adaptive', so those calls no longer need a type assertion. Support is provider-specific. -
Updated dependencies [2171d15]
- @ai-sdk/provider@3.0.15
- @ai-sdk/gateway@3.0.168
- @ai-sdk/provider-utils@4.0.44
Patch Changes
- Updated dependencies [dab0a08]
- @ai-sdk/provider-utils@4.0.43
- @ai-sdk/gateway@3.0.167
Patch Changes
- Updated dependencies [401a4ba]
- Updated dependencies [7af9646]
- @ai-sdk/provider-utils@5.0.26
- @ai-sdk/gateway@4.0.47
Changed 1
- Updated @ai-sdk/gateway dependency to version 2.0.129
Patch Changes
- Updated dependencies [c524e57]
- @ai-sdk/gateway@2.0.129
Changed 1
- Updated @ai-sdk/gateway to version 2.0.128
Patch Changes
- Updated dependencies [bd09b8e]
- @ai-sdk/gateway@2.0.128
Added 1
- Allow `aspectRatio: 'adaptive'` on `generateVideo` for video models that derive output ratio from input.
Changed 1
- Reduce bundle size by making internal Zod v4 imports tree-shakeable.
Fixed 1
- Respect ToolLoopAgent timeouts configured in agent settings.
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]
- @ai-sdk/gateway@4.0.46
- @ai-sdk/provider@4.0.7
- @ai-sdk/provider-utils@5.0.25
Changed 2
- Updated @ai-sdk/provider-utils to 5.0.24
- Updated @ai-sdk/gateway to 4.0.45
Patch Changes
- Updated dependencies [1937bef]
- @ai-sdk/provider-utils@5.0.24
- @ai-sdk/gateway@4.0.45
Changed 2
- Updated @ai-sdk/provider-utils to 4.0.42
- Updated @ai-sdk/gateway to 3.0.166
Patch Changes
- Updated dependencies [ee2bf30]
- @ai-sdk/provider-utils@4.0.42
- @ai-sdk/gateway@3.0.166
Added 1
- Expose provider metadata on language-model-call end callbacks and telemetry spans
Fixed 2
- Make retried doStart calls idempotent by minting one idempotency token per logical start and forwarding it as an idempotency-key header to prevent duplicate billable generations on retry after lost response
- Stop pending and active resumed chat streams after cancellation and prevent overlapping resumptions from applying stale updates
Patch Changes
-
25c9120: Expose provider metadata on language-model-call end callbacks and telemetry spans.
-
89080c8: fix (ai/gateway): make retried
doStartcalls idempotentgenerateVideoretriesdoStart, 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 Gateway does) sees the same key on every attempt.GatewayVideoModelsimply 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
Added 1
- Add batch APIs
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
Fixed 1
- Preserve preceding assistant messages when regenerating a response
Patch Changes
- 79e58aa: Preserve preceding assistant messages when regenerating a response.
Added 2
- Allow `ToolLoopAgent` `prepareCall` callbacks to read and override the top-level `reasoning` option
- Add `defaultInstructionsMiddleware` for applying default language model instructions while preserving call-level overrides
Fixed 1
- Preserve preceding assistant messages when regenerating a response
Patch Changes
- a6b17a2: Allow
ToolLoopAgentprepareCallcallbacks to read and override the top-levelreasoningoption. - 5615eb7: Add
defaultInstructionsMiddlewarefor applying default language model instructions while preserving call-level overrides. - 36a3ff6: Preserve preceding assistant messages when regenerating a response.
Fixed 1
- Skip re-validating tool input for terminal output-available UI message parts
Patch Changes
- dd5d344: Skip re-validating tool input for terminal output-available UI message parts.
- Updated dependencies [0cd92fa]
- @ai-sdk/gateway@3.0.165
Changed 1
- Updated @ai-sdk/gateway to version 2.0.127
Patch Changes
- Updated dependencies [b74765f]
- @ai-sdk/gateway@2.0.127
Changed 1
- Skip re-validating tool input for terminal output-available UI message parts
Patch Changes
- 212d793: Skip re-validating tool input for terminal output-available UI message parts.
- Updated dependencies [1ce55ef]
- Updated dependencies [f50dc31]
- @ai-sdk/gateway@2.0.126
Fixed 1
- Skip re-validating tool input for terminal output-available UI message parts
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
Changed 1
- Updated @ai-sdk/gateway to version 3.0.164
Patch Changes
- Updated dependencies [f615718]
- Updated dependencies [48d5dff]
- @ai-sdk/gateway@3.0.164
Patch Changes
- Updated dependencies [160ccdb]
- @ai-sdk/provider-utils@5.0.20
- @ai-sdk/gateway@4.0.40
Added 3
- Add asynchronous start/status flow to the experimental video model interface (VideoModelV4) with doStart, doStatus, and handleWebhookOption methods
- Add poll and webhook options to experimental_generateVideo for asynchronous completion orchestration
- Add custom delay implementation support for polling configuration to enable durable workflow compatibility
Changed 1
- Simplify tool caller configuration in code-mode
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 implementdoStart,doStatus, andhandleWebhookOptioninstead of (or in addition to)doGenerate, andexperimental_generateVideoacceptspollandwebhookoptions 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
Patch Changes
- Updated dependencies [7e50c52]
- @ai-sdk/gateway@3.0.163
Changed 1
- Updated @ai-sdk/gateway to 2.0.125
Patch Changes
- Updated dependencies [ecd9c1c]
- @ai-sdk/gateway@2.0.125
Changed 1
- Updated @ai-sdk/gateway to version 4.0.38
Patch Changes
- Updated dependencies [fb6d2f8]
- @ai-sdk/gateway@4.0.38
Changed 1
- @ai-sdk/gateway updated to version 4.0.37
Patch Changes
- Updated dependencies [bdd5e28]
- @ai-sdk/gateway@4.0.37
Patch Changes
- Updated dependencies [b28367e]
- @ai-sdk/gateway@3.0.162
Changed 1
- Updated @ai-sdk/gateway to version 2.0.124
Patch Changes
- Updated dependencies [8ea0ce4]
- @ai-sdk/gateway@2.0.124
Changed 2
- Updated @ai-sdk/provider-utils to version 5.0.18
- Updated @ai-sdk/gateway to version 4.0.36
Patch Changes
- Updated dependencies [5fc7da5]
- Updated dependencies [93b2acd]
- @ai-sdk/provider-utils@5.0.18
- @ai-sdk/gateway@4.0.36
Changed 1
- Updated @ai-sdk/gateway to version 2.0.123
Patch Changes
- Updated dependencies [d27b3c3]
- @ai-sdk/gateway@2.0.123
Changed 1
- Updated @ai-sdk/gateway to version 4.0.35
Patch Changes
- Updated dependencies [4f2e064]
- @ai-sdk/gateway@4.0.35
Patch Changes
- Updated dependencies [d3d9e0b]
- @ai-sdk/gateway@3.0.161
Added 2
- Support experimental_toolCallers in streamText
- Support experimental tool callers in ToolLoopAgent
Fixed 1
- Warn when generateText receives streaming-only firstChunkMs or chunkMs timeout settings
Patch Changes
- d6ce0ee: feat(ai): support experimental_toolCallers in streamText
- fa95504: feat(ai): support experimental tool callers in ToolLoopAgent
- 349afe7: Warn when
generateTextreceives streaming-onlyfirstChunkMsorchunkMstimeout settings. - Updated dependencies [fa95504]
- @ai-sdk/provider-utils@5.0.17
- @ai-sdk/gateway@4.0.34
Fixed 1
- Fix telemetry attribution for language model calls that resolve to a different response model
Patch Changes
- 015acb4: fix telemetry attribution for language model calls that resolve to a different response model
More in AI
View allcodex
codex release notes.
codex
Ollama
Get up and running with large language models locally.
Ollama
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
openclaw
tensorflow
An Open Source Machine Learning Framework for Everyone
tensorflow
superpowers
An agentic skills framework & software development methodology that works.
obra
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
affaan-m
Discussion
If you publish AI SDK, you can claim this product by proving you administer its repository.