[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
@ai-sdk/openai (source)	2.0.24 → 2.0.139

---

Release Notes

vercel/ai (@​ai-sdk/openai)

v2.0.139

Compare Source

Patch Changes

• Updated dependencies [a1a772f]
  • @​ai-sdk/provider-utils@3.0.43

v2.0.138

Compare Source

Patch Changes

• 1ff7951: fix(openai): report unfinished web searches as tool errors
• 1ff7951: Report failed and incomplete web searches as tool errors instead of successful tool results in OpenAI Responses API calls.

v2.0.137

Compare Source

Patch Changes

• 6a87db5: Fix gpt-transcribe REST transcription. Requests with OpenAI provider options now use response_format: 'json' for gpt-transcribe and dated gpt-4o-mini-transcribe snapshots, which reject verbose_json. durationInSeconds is read from usage.seconds when a duration-billed response has no top-level duration.

v2.0.136

Compare Source

Patch Changes

• 2d22edb: Defer validation schema construction until first use to reduce provider import time.
• Updated dependencies [d7b0ffa]
• Updated dependencies [4146790]
  • @​ai-sdk/provider-utils@3.0.42

v2.0.135

Compare Source

Patch Changes

• c883c47: fix(openai): send assistant text and function calls with content instead of an item reference when their reasoning was removed

  With reasoning models, pruning reasoning (e.g. pruneMessages({ reasoning: 'all' })) caused follow-up requests to fail with "Item 'msg*...' of type 'message' was provided without its required 'reasoning' item" or "Item 'fc*...' of type 'function_call' was provided without its required 'reasoning' item". Assistant text and function call parts are now only sent as item references, or with their item id, when they are preceded by reasoning in the same assistant message.

v2.0.134

Patch Changes

• b399a1d: fix(openai): replay web search results, including tools with custom names, when response storage is disabled

v2.0.133

Patch Changes

• Updated dependencies [2b1c2df]
• Updated dependencies [2b1c2df]
• Updated dependencies [2b1c2df]
  • @​ai-sdk/provider-utils@3.0.41

v2.0.132

Patch Changes

• 07e394b: feat(openai): add GPT-6.1 Sol model support

v2.0.131

Patch Changes

• 14810cb: fix(provider-utils): preserve streamed tool calls with unreliable IDs and indices
• Updated dependencies [14810cb]
  • @​ai-sdk/provider-utils@3.0.40

v2.0.130

Patch Changes

• f912d4a: The OpenAI Responses provider now accepts providerOptions.openai.reasoningEffortUpdate on empty system messages and sends each update at its position in the conversation. This lets applications change reasoning effort during a conversation while preserving the prompt prefix for caching.

v2.0.129

Patch Changes

• 1c05ff4: fix(openai): expose Chat Completions audio transcripts as generated text
• bf29419: chore: enable dead code lint rules
• Updated dependencies [bf29419]
  • @​ai-sdk/provider-utils@3.0.39

v2.0.128

Compare Source

Patch Changes

• 0f8e4fe: fix(openai): accept incomplete function_call items on the Responses stream, so a call truncated by max_output_tokens finishes with length instead of a TypeValidationError
• 391ad4a: feat: GPT-6 Sol and Luna model IDs
• Updated dependencies [594787e]
  • @​ai-sdk/provider@2.0.5
  • @​ai-sdk/provider-utils@3.0.38

v2.0.127

Compare Source

Patch Changes

• fd889a3: fix(openai): return an AI SDK error for empty chat completion choices
• Updated dependencies [c2089a9]
• Updated dependencies [ab3990f]
  • @​ai-sdk/provider@2.0.4
  • @​ai-sdk/provider-utils@3.0.37

v2.0.126

Compare Source

Patch Changes

• 022f24b: Include explicit message item types in Azure AI Foundry Responses requests.
• a15b75a: Add async function tool calling support for OpenAI Responses models.

v2.0.125

Compare Source

Patch Changes

• e0d0bd1: feat(openai): add GPT-6 reasoning configuration updates

v2.0.124

Compare Source

Patch Changes

• 7bebd57: feat(openai): add support for the gpt-6-astra

v2.0.123

Compare Source

Patch Changes

• Updated dependencies [26165ee]
  • @​ai-sdk/provider-utils@3.0.36

v2.0.122

Compare Source

Patch Changes

• f70d0a3: Normalize non-object replayed Chat Completions tool arguments to empty objects.

v2.0.119

Compare Source

Patch Changes

• Updated dependencies [9e8e087]
  • @​ai-sdk/provider-utils@3.0.33

v2.0.118

Compare Source

Patch Changes

• Updated dependencies [0e51b7b]
  • @​ai-sdk/provider-utils@3.0.32

v2.0.117

Compare Source

Patch Changes

• Updated dependencies [7a6bdbc]
  • @​ai-sdk/provider-utils@3.0.31

v2.0.116

Compare Source

Patch Changes

• 8591016: Add blocked domain filters to the OpenAI and Azure Responses API web search tools.

v2.0.115

Compare Source

Patch Changes

• 11a02d9: Apply reasoning, service tier, and image defaults to recognizable future OpenAI model family versions.

v2.0.114

Compare Source

Patch Changes

• Updated dependencies [2fd6076]
  • @​ai-sdk/provider-utils@3.0.30

v2.0.113

Compare Source

Patch Changes

• 21eef03: Send null content for tool-call-only assistant messages.

v2.0.112

Compare Source

Patch Changes

• Updated dependencies [c6e1d1a]
  • @​ai-sdk/provider-utils@3.0.29

v2.0.111

Compare Source

Patch Changes

• b4f8362: feat(provider/openai): add GPT-5.6 reasoning and prompt cache controls
• 8549807: feat(provider/openai,provider/gateway): add gpt-5.6 model ids

v2.0.110

Patch Changes

• Updated dependencies [b85c4fb]
  • @​ai-sdk/provider-utils@3.0.28

v2.0.32

Patch Changes

• 1cf857d: fix(provider/openai): remove provider-executed tools from chat completions model
• 01de47f: feat(provider/openai): rework file search tool

v2.0.31

Patch Changes

• bb94467: feat(provider/openai): add maxToolCalls provider option
• 4a2b70e: feat(provider/openai): send item references for provider-executed tool results
• 643711d: feat (provider/openai): provider defined image generation tool support

v2.0.30

Patch Changes

• Updated dependencies [0294b58]
  • @​ai-sdk/provider-utils@3.0.9

v2.0.29

Patch Changes

• 4235eb3: feat(provider/openai): code interpreter tool calls and results

v2.0.28

Patch Changes

• 4c2bb77: fix (provider/openai): send sources action as include
• 561e8b0: fix (provider/openai): fix code interpreter tool in doGenerate

v2.0.27

Patch Changes

• 2338c79: feat (provider/openai): add jsdoc for openai tools

v2.0.26

Patch Changes

• 5819aec: fix (provider/openai): only send tool calls finish reason for tools that are not provider-executed
• af8c6bb: feat (provider/openai): add web_search tool

v2.0.25

Patch Changes

• fb45ade: fix timestamp granularities support for openai transcription

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • "before 8am every weekday,every weekend"
• Automerge
  • At any time (no schedule defined)

🚦 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.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

Run configuration

• Source mode: Auto
• Repository: prisma/prisma-examples
• Branch: latest
• File: .coderabbit.yaml
• Commit: 684faae
• Layers: Repository YAML
• Review profile: CHILL
• Plan: Advanced
• Run ID: 2d35d2d7-6515-4a18-8891-306caa4a5dc9

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

• Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

_{Comment @coderabbitai help to get the list of available commands.}