fix(deps): update dependency @ai-sdk/openai to v2.0.103#8541
Open
renovate[bot] wants to merge 1 commit intolatestfrom
Open
fix(deps): update dependency @ai-sdk/openai to v2.0.103#8541renovate[bot] wants to merge 1 commit intolatestfrom
renovate[bot] wants to merge 1 commit intolatestfrom
Conversation
2bccd98 to
66fa230
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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:
2.0.24→2.0.103Release Notes
vercel/ai (@ai-sdk/openai)
v2.0.103Compare Source
Patch Changes
v2.0.102Compare Source
Patch Changes
a27a978]v2.0.101Compare Source
Patch Changes
316517c: Addgpt-5.4-mini,gpt-5.4-mini-2026-03-17,gpt-5.4-nano, andgpt-5.4-nano-2026-03-17models.v2.0.100Compare Source
Patch Changes
216151a: fix(provider/openai): drop reasoning parts without encrypted content when store: falsev2.0.99Patch Changes
15cfac8]v2.0.98Patch Changes
392dc94: feat(provider/openai): add GPT-5.4 model supportv2.0.97Patch Changes
6a2f01b]17d64e3]v2.0.96Compare Source
Patch Changes
e867b5c: Supportphaseparameter on Responses API message items. Thephasefield ('commentary'or'final_answer') is returned by models likegpt-5.3-codexon assistant message output items and must be preserved when sending follow-up requests. The phase value is available inproviderMetadata.openai.phaseon text parts and is automatically included on assistant messages sent back to the API.v2.0.95Compare Source
Patch Changes
b08351e: fix(openai): allow null/undefined type in streaming tool call deltasAzure AI Foundry and Mistral deployed on Azure omit the
typefield instreaming tool_calls deltas. The chat stream parser now accepts a missing
typefield (treating it as"function") instead of throwingInvalidResponseDataError: Expected 'function' type.Fixes #12770
v2.0.94Compare Source
Patch Changes
42815ac: feat(provider/openai): addgpt-5.3-codexv2.0.93Compare Source
Patch Changes
fa64d70: fix(openai): change web search tool action to be optionalv2.0.92Compare Source
Patch Changes
c680a01: fix(openai): add changeset and tests for per-image usage metadatav2.0.91Compare Source
Patch Changes
6a0adb7: feat: differentiate text vs image input tokensv2.0.90Compare Source
Patch Changes
20565b8]v2.0.89Compare Source
Patch Changes
4953414: fix: trigger new release for@ai-v5dist-tag4953414]v2.0.88Compare Source
Patch Changes
v2.0.87Compare Source
Patch Changes
51aa5de: backport: test server51aa5de]v2.0.86Compare Source
Patch Changes
a909bcf: fix(openai); fix url_citation schema in chat apiv2.0.85Compare Source
Patch Changes
e79430b: fix(openai): change find action type to find_in_page action typev2.0.84Compare Source
Patch Changes
041a4fc: feat(openai): add gpt-5.2 modelsv2.0.83Compare Source
Patch Changes
edc807f: feat(provider/openai): add GPT 5.1 Codex Max to OpenAI Responses model IDs listv2.0.82Compare Source
Patch Changes
e31dfa4: feat(provider/openai): add support for OpenAI xhigh reasoning effortv2.0.81Compare Source
Patch Changes
ef6d784]v2.0.80Compare Source
Patch Changes
707a163: feat(openai): additional settings for file search toolv2.0.79Compare Source
Patch Changes
5b6aa88: fix(openai): fix parameter exclusion logicv2.0.78Compare Source
Patch Changes
e245b61: fix(openai): allow temperature etc setting when reasoning effort is none for gpt-5.1v2.0.77Compare Source
Patch Changes
31f6c20: fix(openai): allow open_page action type url to be nullishv2.0.76Compare Source
Patch Changes
61545c4: feat (provider/openai): include more image generation response metadatav2.0.75Compare Source
Patch Changes
1c7ff4a: distinguish between OpenAI and Azure in Responses API providerMetadatav2.0.74Compare Source
Patch Changes
a27a978]v2.0.73Compare Source
Patch Changes
42bc840: fix(anthropic): move claude-haiku-4-5 to the 4-5 model group in getModelCapabilitiesMoves
claude-haiku-4-5from theclaude-sonnet-4-/claude-3-7-sonnetgroup (structured output: false) to theclaude-sonnet-4-5/claude-opus-4-5group (structured output: true), aligning with main and release-v6.0.v2.0.72Compare Source
Patch Changes
98bd0e2: feat(provider/anthropic): support new code_execution toolv2.0.71Compare Source
Patch Changes
b0a0821: feat (provider/anthropic): support passing metadata.user_idv2.0.70Compare Source
Patch Changes
a9a7f73: feat(anthropic): support eagerInputStreaming option for fine-grained tool streamingv2.0.69Compare Source
Patch Changes
6a2f01b]17d64e3]v2.0.68Compare Source
Patch Changes
63bf188: feat(anthropic): expose anthropic.anthropicBeta to downstream providersv2.0.67Compare Source
Patch Changes
3735f5a: feat(openai): Add support for 'promptCacheRetention: 24h' for gpt5.1 seriesv2.0.66Compare Source
Patch Changes
73f9178: feat(openai): add 'gpt-5.1' modelIDv2.0.65Compare Source
Patch Changes
056c471]v2.0.64Compare Source
Patch Changes
d251e53: feat(openai): addo3-deep-researchando4-mini-deep-researchmodelsv2.0.63Compare Source
Patch Changes
3b62c49: fix(openai): extract meta data from first chunk that contains anyv2.0.62Compare Source
Patch Changes
51aa5de: backport: test server51aa5de]v2.0.61Compare Source
Patch Changes
3399b61: feat(provider/google): support multimodal content parts in embedding provider optionsv2.0.60Compare Source
Patch Changes
3f0102b: fix(provider/google): makesegmentoptional ingroundingSupportsschemaBackport of #12002. When using image search grounding, the Google API returns
groundingSupportsentries without asegmentfield, causing schema validation to fail with "Invalid JSON response".v2.0.59Compare Source
Patch Changes
8cf6b86: fix(provider/google): preserve groundingMetadata and urlContextMetadata when they arrive in a stream chunk before the finishReason chunkv2.0.58Compare Source
Patch Changes
v2.0.57Compare Source
Patch Changes
c319849]v2.0.56Compare Source
Patch Changes
b82d23b: feat(openai): preserve file_id when converting file citationsv2.0.55Compare Source
Patch Changes
2f4a59a: feat(openai): add sources in web-search actionsv2.0.54Compare Source
Patch Changes
1e05490]v2.0.53Compare Source
Patch Changes
5464bf0: fix(provider/openai): add truncation parameter support for Responses APIv2.0.52Compare Source
Patch Changes
8de8de5: fix(provider/openai): end reasoning parts earlierv2.0.51Compare Source
Patch Changes
cad5c1d: fix(provider/openai): fix web search tool input typesv2.0.50Compare Source
Patch Changes
c336b43: feat(provider/openai): send assistant text and tool call parts as reference ids when store: truev2.0.49Compare Source
Patch Changes
f4287d0: feat(provider/openai): automatically add reasoning.encrypted_content include when store = falsev2.0.48Compare Source
Patch Changes
17f9872]v2.0.47Compare Source
Patch Changes
99e2a2a: feat(provider/openai): support file and image tool resultsv2.0.46Compare Source
Patch Changes
66f69e7: Add 'default' as service tierv2.0.45Compare Source
Patch Changes
6f0644c: chore: use import * from zod/v46f0644c: chore: load zod schemas lazily6f0644c]6f0644c]v2.0.44Compare Source
Patch Changes
28215ca: fix(provider/openai): add providerExecuted flag to tool start chunksv2.0.43Patch Changes
fd46da1: feat(provider/openai): add new model IDsgpt-image-1-mini,gpt-5-pro,gpt-5-pro-2025-10-06v2.0.42Patch Changes
3c6f4e1: fix(provider/xai): correct sources format in searchParametersv2.0.41Compare Source
Patch Changes
110c735: support OPENAI_BASE_URL envv2.0.40Compare Source
Patch Changes
8c74f47: feat(provider/openai): add gpt-5-codex model idadca087: feat(provider/openai): local shell toolv2.0.39Compare Source
Patch Changes
5428a0d: The built in Code Interpreter tool input code is streamed intool-input-<start/delta/end>chunks.v2.0.38Compare Source
Patch Changes
0bda600: enables code_interpreter and file_search capabilities in the Azure provider through the Responses APIv2.0.37Compare Source
Patch Changes
6075c91: feat(provider/openai): only send item references for reasoning when store: truev2.0.36Compare Source
Patch Changes
bc5ed71: chore: update zod peer depenedency versionbc5ed71]v2.0.35Compare Source
Patch Changes
1cfc209: feat(provider/openai):OpenAIChatLanguageModelOptionstypev2.0.34Compare Source
Patch Changes
322901b: feat: add provider version to user-agent headerv2.0.33Compare Source
Patch Changes
a617948: fix the "incomplete_details" key from nullable to nullish for openai compatibilityv2.0.32Compare Source
Patch Changes
1cf857d: fix(provider/openai): remove provider-executed tools from chat completions model01de47f: feat(provider/openai): rework file search toolv2.0.31Compare Source
Patch Changes
b73ba90: feat(provider/anthropic): default and limit maxTokens based on modelv2.0.30Compare Source
Patch Changes
0294b58]v2.0.29Compare Source
Patch Changes
056c471]v2.0.28Compare Source
Patch Changes
9a999c4: fix(@ai-sdk/google): Make title field optional in grounding metadata schemav2.0.27Compare Source
Patch Changes
51aa5de: backport: test server51aa5de]v2.0.26Compare Source
Patch Changes
5819aec: fix (provider/openai): only send tool calls finish reason for tools that are not provider-executedaf8c6bb: feat (provider/openai): add web_search toolv2.0.25Compare Source
Patch Changes
f6b46d2: feat (provider/gateway): add provider-defined perplexity searchConfiguration
📅 Schedule: (UTC)
🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR becomes conflicted, 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.