Update dependency @ai-sdk/groq to v4 - #70
Open
renovate[bot] wants to merge 1 commit into
Open
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
June 30, 2026 20:08
0422576 to
c67cebe
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 3, 2026 07:48
c67cebe to
43c8628
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 11, 2026 15:52
43c8628 to
e7bceb5
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 12, 2026 15:14
e7bceb5 to
736c6b9
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 15, 2026 00:09
736c6b9 to
7a3aa9c
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 17, 2026 23:25
7a3aa9c to
811dfb9
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 23, 2026 08:05
811dfb9 to
4aaca91
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 24, 2026 00:19
4aaca91 to
958f463
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 30, 2026 20:10
958f463 to
5f4c53f
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
July 30, 2026 23:49
5f4c53f to
1e13897
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 1, 2026 18:58
1e13897 to
233e40f
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 3, 2026 23:43
233e40f to
73d4f1c
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 4, 2026 04:04
73d4f1c to
d66d8cc
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 7, 2026 02:39
d66d8cc to
a41dba4
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 8, 2026 02:36
a41dba4 to
2658770
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 8, 2026 06:30
2658770 to
b29970b
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 11, 2026 00:11
b29970b to
827d515
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 12, 2026 03:18
827d515 to
d8b87d8
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 22, 2026 23:45
d8b87d8 to
4eec723
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 25, 2026 18:42
4eec723 to
0cd8abc
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 28, 2026 09:07
0cd8abc to
37d6179
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 29, 2026 23:30
37d6179 to
ed87ed3
Compare
renovate
Bot
force-pushed
the
renovate/ai-sdk-groq-4.x
branch
from
August 31, 2026 17:30
ed87ed3 to
b37f14a
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains the following updates:
^1.2.5→^4.0.0Release Notes
vercel/ai (@ai-sdk/groq)
v4.0.34Compare Source
Patch Changes
90192f1]v4.0.33Compare Source
Patch Changes
3e125ba]v4.0.31Compare Source
Patch Changes
2214258: Prevent negative text output token counts when providers report reasoning tokens. Perplexity reasoning tokens are now treated as separate from completion tokens.9e9bf11: fix: disable reasoning for supported Groq models when top-level reasoning is set tonone591d25b]v4.0.30Compare Source
Patch Changes
b74971f]v4.0.29Patch Changes
e6087c9: fix: handle empty string tool call IDse6087c9]v4.0.28Patch Changes
7fbfc6d]v4.0.27Compare Source
Patch Changes
401a4ba]v4.0.26Compare Source
Patch Changes
ad6a650]81cd026]v4.0.25Compare Source
Patch Changes
1937bef]v4.0.24Compare Source
Patch Changes
3469d0c]v4.0.23Compare Source
Patch Changes
2b60826]v4.0.22Compare Source
Patch Changes
1bec07d: Fix streamed tool calls with non-zero, non-contiguous, reused, or missing indexes.1bec07d]v4.0.21Compare Source
Patch Changes
160ccdb]v4.0.20Patch Changes
79e133c]v4.0.19Patch Changes
5fc7da5: chore: centralize empty language model usage creation in provider utilities.93b2acd: chore: centralize response metadata conversion5fc7da5]93b2acd]v4.0.18Patch Changes
fa95504]v4.0.17Compare Source
Patch Changes
d2d8744: fix(groq): map word timestamps to transcription segments when segment timestamps are unavailable817910d: Support plain-text responses from Groq transcription models whenresponseFormatis set totext.d8210b6]b192878]v4.0.16Compare Source
Patch Changes
1659cd5]6a5bdff]v4.0.15Compare Source
Patch Changes
0c464d9]c49380c]v4.0.14Compare Source
Patch Changes
1e2f324]v4.0.13Compare Source
Patch Changes
02ffdcb]76cb673]v4.0.12Compare Source
Patch Changes
cd06458]v4.0.11Compare Source
Patch Changes
31c7be8]v4.0.10Compare Source
Patch Changes
4be62c1]7805e4a]cd12954]v4.0.8Compare Source
Patch Changes
23ca4c9: fix (provider/groq): surface prompt cache reads in usageconvertGroqUsageacceptedprompt_tokens_details.cached_tokensbut never read it, so cache hits were reported ascacheRead: undefinedand the entire prompt was counted asnoCache. Groq's implicit prompt caching now surfaces asusage.cachedInputTokens(mapped tocacheRead, subtracted fromnoCache). Groq has no cache-creation charge, socacheWriteremains undefined.v4.0.7Compare Source
Patch Changes
0f93c57]v4.0.6Compare Source
Patch Changes
ac306ed: FixStreamingToolCallTrackerfinalizing streaming tool calls on parsable partial JSON. Tool calls now only finalize during stream flush, restoring the behavior of #13137: a parsable argument buffer can still be the prefix of a longer argument string, so finalizing early could act on truncated tool inputs.ac306ed]v4.0.5Compare Source
Patch Changes
5c5c0f5: Add experimental streaming transcription support for transcription models, including OpenAIgpt-realtime-whisperand xAI WebSocket STT.5c5c0f5]v4.0.4Compare Source
Patch Changes
c6f5e62]v4.0.3Compare Source
Patch Changes
8c616f0]v4.0.2Compare Source
Patch Changes
0274f34]v4.0.1Compare Source
Patch Changes
6a436e3]v4.0.0Compare Source
Major Changes
ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers usingrequire()must switch to ESMimportsyntax.c29a26f: feat(provider): add support for provider references and uploading files as supported per provider8359612: Start v7 pre-release04e9009: chore: make provider implementations code patterns more consistent, including renaming certain exported symbolsFor all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.
Patch Changes
38fc777: Add AI Gateway hint to provider READMEs023550e: DeprecatestreamTextresultfullStreamin favor ofstream.74d520f: feat: migrate providers to support new top-levelreasoningparameter45b3d76: fix(security): prevent streaming tool calls from finalizing on parsable partial JSONStreaming tool call arguments were finalized using
isParsableJson()as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs inflush()after the stream is fully consumed.9f0e36c: trigger release for all packages after provenance setup58a2ad7: fix: more precise default message for tool execution denial7bf717f: feat: Groq support for performance service tierf7295cb: revert incorrect fix #131727fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.f807e45: Extract sharedStreamingToolCallTrackerclass into@ai-sdk/provider-utilsto deduplicate streaming tool call handling across OpenAI-compatible providers. Also adds missinggenerateId()fallback fortoolCallIdin Alibaba'sdoGeneratepath and ensures all providers finalize unfinished tool calls during stream flush.0c4c275: trigger initial canary release6fd51c0: fix(provider): preserve error type prefix in getErrorMessage9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type258c093: chore: ensure consistent import handling and avoid import duplicates or cyclesb8396f0: trigger initial beta release90e2d8a: chore: fix unused vars not being flagged by our lint toolingb3976a2: Add workflow serialization support to all provider models.@ai-sdk/provider-utils: NewserializeModel()helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.All providers:
headersis now optional in provider config types. This is non-breaking — existing code that passesheaderscontinues to work. Custom provider implementations that construct model configs manually can now omitheaders, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.All provider model classes now include
WORKFLOW_SERIALIZEandWORKFLOW_DESERIALIZEstatic methods, enabling them to cross workflow step boundaries without serialization errors.v3.0.64Compare Source
Patch Changes
cc23556]v3.0.63Compare Source
Patch Changes
9a521b9]v3.0.62Compare Source
Patch Changes
313a441: Prevent negative text output token counts when providers report reasoning tokens. Perplexity reasoning tokens are now treated as separate from completion tokens.5642849]v3.0.61Compare Source
Patch Changes
2d172fb]v3.0.60Compare Source
Patch Changes
31205a4]v3.0.59Compare Source
Patch Changes
b2a4d5a]v3.0.58Compare Source
Patch Changes
2171d15]v3.0.57Compare Source
Patch Changes
dab0a08]v3.0.56Compare Source
Patch Changes
ee2bf30]v3.0.55Compare Source
Patch Changes
ae2812a: fix(groq): map word timestamps to transcription segments when segment timestamps are unavailablecc3269f: Support plain-text responses from Groq transcription models whenresponseFormatis set totext.v3.0.54Compare Source
Patch Changes
9ecdefe]v3.0.53Compare Source
Patch Changes
19093fd]v3.0.52Compare Source
Patch Changes
06fb54c]v3.0.51Compare Source
Patch Changes
cee7e45: fix (provider/groq): surface prompt cache reads in usageconvertGroqUsageacceptedprompt_tokens_details.cached_tokensbut never read it, so cache hits were reported ascacheRead: undefinedand the entire prompt was counted asnoCache. Groq's implicit prompt caching now surfaces asusage.cachedInputTokens(mapped tocacheRead, subtracted fromnoCache). Groq has no cache-creation charge, socacheWriteremains undefined.v3.0.50Compare Source
Patch Changes
e1af05f]v3.0.49Compare Source
Patch Changes
bef93ae: fix(security): prevent streaming tool calls from finalizing on parsable partial JSONStreaming tool call arguments were finalized using
isParsableJson()as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs inflush()after the stream is fully consumed.327642b: fix: more precise default message for tool execution denialUpdated dependencies [
d559de9]v3.0.48Compare Source
Patch Changes
0952964]v3.0.47Compare Source
Patch Changes
ea1e95b]v3.0.46Compare Source
Patch Changes
fa850e6]v3.0.45Compare Source
Patch Changes
b30e43a]v3.0.44Compare Source
Patch Changes
f19334d]v3.0.43Compare Source
Patch Changes
1b40ac7: Publish all packages under the@ai-v6dist tag.1b40ac7]v3.0.42Compare Source
Patch Changes
779f5cd]v3.0.41Patch Changes
bfa5864]f42aa79]v3.0.39Compare Source
Patch Changes
f591416]v3.0.38Compare Source
Patch Changes
7beadf0]v3.0.37Compare Source
Patch Changes
a727da4: chore: ensure consistent import handling and avoid import duplicates or cyclesa727da4]v3.0.36Compare Source
Patch Changes
a7f3c72: trigger release for all packages after provenance setupa7f3c72]v3.0.35Compare Source
Patch Changes
d42076d: Add AI Gateway hint to provider READMEsv3.0.34Compare Source
Patch Changes
6247886]v3.0.33Compare Source
Patch Changes
0469aed]v3.0.32Patch Changes
cb3ca8f: feat: Groq support for performance service tierv3.0.29Patch Changes
ad4cfc2]v3.0.28Patch Changes
824b295]v3.0.27Patch Changes
08336f1]v3.0.26Patch Changes
58bc42d]v3.0.25Patch Changes
91f8777: fix(bedrock/groq): pass strict mode for toolsv3.0.24Patch Changes
4024a3a]v3.0.23Patch Changes
99fbed8: feat: normalize provider specific model options type names and ensure they are exportedv3.0.22Patch Changes
7168375]v3.0.21Patch Changes
53f6731]v3.0.20Patch Changes
96936e5]v3.0.19Patch Changes
2810850]v3.0.18Patch Changes
1524271: chore: add skill information to README filesv3.0.17Patch Changes
3988c08: docs: fix incorrect and outdated provider docsv3.0.16Patch Changes
462ad00]v3.0.15Patch Changes
4de5a1d: chore: excluded tests from src folder in npm package4de5a1d]v3.0.14Patch Changes
2b8369d: chore: add docs to package distv3.0.13Patch Changes
8dc54db: chore: add src folders to package bundlev3.0.12Patch Changes
25f5da3: feat(groq): expose reasoningTokens in usage datav3.0.11Patch Changes
7c98577: fix timestamp_granularities handling in groq transcriptionv3.0.10Patch Changes
5c090e7]v3.0.9Patch Changes
46f46e4]v3.0.8Patch Changes
1b11dcb]v3.0.7Patch Changes
bc02a3c: feat(groq,compat): add strictJsonSchema for providersv3.0.6Patch Changes
78fcb18: fix(compat,groq): send reasoning-end before text-start in streamingv3.0.5Patch Changes
34d1c8a]v3.0.4Patch Changes
d937c8f]v3.0.3Patch Changes
0b429d4]v3.0.2Patch Changes
ad4cfc2]v3.0.1Patch Changes
2810850]v3.0.0Major Changes
dee8b05: ai SDK 6 betaMinor Changes
78928cb: release: start 5.1 betaPatch Changes
0c3b58b: fix(provider): add specificationVersion to ProviderV3541abc9: Removed deprecated distil-whisper-large-v3-en model from groq transcription0adc679: feat(provider): shared spec v38d9e8ad: chore(provider): remove generics from EmbeddingModelV3Before
After
2625a04: feat(openai); update spec for mcp approval95f65c2: chore: use import * from zod/v4954c356: feat(openai): allow custom names for provider-defined tools544d4e8: chore(specification): rename v3 provider defined tool to provider toole8109d3: feat: tool execution approvaled329cb: feat:Provider-V33bd2689: feat: extended token usage1cad0ab: feat: add provider version to user-agent header08d5419: fix(groq): remove decomissionedmoonshotai/kimi-k2-instruct, addmoonshotai/kimi-k2-instruct-09058dac895: feat:LanguageModelV3457318b: chore(provider,ai): switch to SharedV3Warning and unified warnings366f50b: chore(provider): add deprecated textEmbeddingModel and textEmbedding aliases4616b86: chore: update zod peer depenedency version0f0fa34: Restrict reasoningEffort to allowed enum values in Groq provider options21e20c0: feat(provider): transcription model v3 speccbf52cd: feat: expose raw finish reason10c1322: fix: moved dependency@ai-sdk/test-serverto devDependencies3f464f4: fix(provider/groq): track cached tokens usageUpdated dependencies
v2.0.52Compare Source
Patch Changes
26165ee]v2.0.51Compare Source
Patch Changes
77d33c0]v2.0.49Compare Source
Patch Changes
9e8e087]v2.0.48Compare Source
Patch Changes
0e51b7b]v2.0.47Compare Source
Patch Changes
3fbb9cc: Support plain-text responses from Groq transcription models whenresponseFormatis set totext.v2.0.46Compare Source
Patch Changes
7a6bdbc]v2.0.45Compare Source
Patch Changes
2fd6076]v2.0.44Compare Source
Patch Changes
c6e1d1a]v2.0.43Compare Source
Patch Changes
b85c4fb]v2.0.42Compare Source
Patch Changes
9169261]v2.0.41Compare Source
Patch Changes
9f67efe]eea9166]v2.0.40Compare Source
Patch Changes
783fa6c: chore: ensure consistent import handling and avoid import duplicates or cycles783fa6c]v2.0.39Compare Source
Patch Changes
0a00b9b: trigger release for all packages after provenance setup0a00b9b]v2.0.38Compare Source
Patch Changes
5543cd1: Add AI Gateway hint to provider READMEsv2.0.37Patch Changes
a27a978]v2.0.35Patch Changes
20565b8]v2.0.34Patch Changes
4953414: fix: trigger new release for@ai-v5dist-tag4953414]Configuration
📅 Schedule: (in timezone Asia/Jerusalem)
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.