NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #1793 most downloaded on npm
Latest stable
5.0.79
Last release 11 days ago
10 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Most releases are documented
notes for 46 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
436 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
61753c3: ### @ai-sdk/openai: remove redundant name argument from openai.tools.customTool()
61753c3: ### @ai-sdk/openai: remove redundant name argument from openai.tools.customTool()
openai.tools.customTool() no longer accepts a name field. the tool name is now derived from the sdk tool key (the object key in the tools object).
migration: remove the name property from customTool() calls. the object key is now used as the tool name sent to the openai api.
before:
tools: {
write_sql: openai.tools.customTool({
name: 'write_sql',
description: '...',
}),
}
after:
tools: {
write_sql: openai.tools.customTool({
description: '...',
}),
}
@ai-sdk/provider-utils: createToolNameMapping() no longer accepts the resolveProviderToolName parameterbefore: tool name can be set dynamically
const toolNameMapping = createToolNameMapping({
tools,
providerToolNames: {
"openai.code_interpreter": "code_interpreter",
"openai.file_search": "file_search",
"openai.image_generation": "image_generation",
"openai.local_shell": "local_shell",
"openai.shell": "shell",
"openai.web_search": "web_search",
"openai.web_search_preview": "web_search_preview",
"openai.mcp": "mcp",
"openai.apply_patch": "apply_patch",
},
resolveProviderToolName: (tool) =>
tool.id === "openai.custom"
? (tool.args as { name?: string }).name
: undefined,
});
after: tool name is static based on tools keys
const toolNameMapping = createToolNameMapping({
tools,
providerToolNames: {
'openai.code_interpreter': 'code_interpreter',
'openai.file_search': 'file_search',
'openai.image_generation': 'image_generation',
'openai.local_shell': 'local_shell',
'openai.shell': 'shell',
'openai.web_search': 'web_search',
'openai.web_search_preview': 'web_search_preview',
'openai.mcp': 'mcp',
'openai.apply_patch': 'apply_patch',
}
});
Your coding agent can read these notes before it upgrades. Set up the MCP server →
f7d4f01: feat(provider): add support for reasoning-file type for files that are part of reasoning
reasoning-file type for files that are part of reasoning### Patch Changes - Updated dependencies [5c2a5a2] - @ai-sdk/provider@4.0.0-beta.1
531251e: fix(security): validate redirect targets in download functions to prevent SSRF bypass
531251e: fix(security): validate redirect targets in download functions to prevent SSRF bypass
Both downloadBlob and download now validate the final URL after following HTTP redirects, preventing attackers from bypassing SSRF protections via open redirects to internal/private addresses.
### Major Changes - 8359612: Start v7 pre-release ### Patch Changes - Updated dependencies [8359612] - @ai-sdk/provider@4.0.0-beta.0
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
a9cea74: Keep default Node.js downloads protected by DNS validation and connection pinning when frameworks or instrumentation wrap global fetch before
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
c636bb4: fix(mistral): map provider error finish reasons to error
ede5b89: chore: migrate package builds from tsup to tsdown
ede5b89: chore: migrate package builds from tsup to tsdown
Nothing published for this version
Nothing published for this version
Nothing published for this version
Updated dependencies [ 90192f1 ]
Nothing published for this version
Updated dependencies [ 3e125ba ]
31205a4: chore(provider-utils): upgrade undici to a maintained release
Nothing published for this version
16650e9: feat(google): add gemini-3.7-flash model
gemini-3.7-flash model8e90283: Preserve forced tool calls when strict function tools are configured.
### Patch Changes - Updated dependencies [59d6def] - @ai-sdk/openai@4.0.41
59d6def: Reconstruct provider-executed shell calls when continuing OpenAI Responses with storage disabled.
1ffa1d2: feat(xai): speech timestamps, pronunciation replacements, provider metadata, and error parsing
1ffa1d2: feat(xai): speech timestamps, pronunciation replacements, provider metadata, and error parsing
withTimestamps and replace provider options for text to speech. With
withTimestamps, the JSON envelope is decoded and the audio returned as
usual, while duration, content type, and character-level alignment are
exposed via providerMetadata.xai.providerMetadata.xai.traceId (from the x-trace-id response
header) on every speech response.{"error":"..."}) so APICallError
messages carry xAI's real error detail instead of the HTTP reason phrase.646c86e: fix(provider/xai): report video moderation blocks and missing URLs as an error status instead of throwing
484293f: feat(xai): support the priority service tier on chat and responses
a4d386d: feat(xai): add the Grok 4.6 model IDs and support its xhigh reasoning effort
xhigh reasoning effort8edc775: feat (provider/xai): support Grok Imagine Video 1.5. Adds the grok-imagine-video-1.5 model id and native 1080p for text-to-video and image-to
grok-imagine-video-1.5 model id and native 1080p for text-to-video and image-to-video (the standard resolution: '1920x1080' now maps to 1080p). Reference-to-video remains capped at 720p, so a 1080p request in that mode is downgraded with a warning. Also fixes reference routing: previously any non-empty inputReferences array selected reference-to-video, so an array holding only a non-image reference sent reference_images: [] with no usable references.referenceVoiceIds for reference-to-video reference audio. Pass up to 3 xAI preset voice ids (e.g. ['eve']) and reference them from the prompt with <AUDIO_0>–<AUDIO_2>; they are sent as reference_audios: [{ voice_id }] on POST /v1/videos/generations.Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
8c65988: feat(ai): add telemetry to speech generation and transcription, including provider usage propagation and experimental streaming lifecycle cal
ede5b89: chore: migrate package builds from tsup to tsdown
ad4cfc2: Add URL validation to downloadBlob and download to prevent blind SSRF attacks. Private/internal IP addresses, localhost, and non-HTTP protoco
downloadBlob and download to prevent blind SSRF attacks. Private/internal IP addresses, localhost, and non-HTTP protocols are now rejected before fetching.824b295: fix(provider-utils): prevent unicode escape bypass in secureJsonParse
08336f1: fix(bedrock): strip file extensions from filename
58bc42d: feat(provider/openai): support custom tools with alias mapping
4024a3a: security: prevent unbounded memory growth in download functions
4024a3a: security: prevent unbounded memory growth in download functions
The download() and downloadBlob() functions now enforce a default 2 GiB size limit when downloading from user-provided URLs. Downloads that exceed this limit are aborted with a DownloadError instead of consuming unbounded memory and crashing the process. The abortSignal parameter is now passed through to fetch() in all download call sites.
Added download option to transcribe() and experimental_generateVideo() for providing a custom download function. Use the new createDownload({ maxBytes }) factory to configure download size limits.
### Patch Changes - Updated dependencies [7168375] - @ai-sdk/provider@3.0.8
### Patch Changes - Updated dependencies [53f6731] - @ai-sdk/provider@3.0.7
96936e5: fix(provider-utils): export only types from standard-schema package
One column per month.