chore(deps): bump @ai-sdk/openai from 3.0.25 to 4.0.50

[dependabot]

Bumps @ai-sdk/openai from 3.0.25 to 4.0.50.

Release notes

Sourced from @​ai-sdk/openai's releases.

@​ai-sdk/openai@​3.0.105

Patch Changes

• Updated dependencies [cc23556]
  • @​ai-sdk/provider-utils@​4.0.50

@​ai-sdk/openai-compatible@​3.0.41

Patch Changes

• 23eb659: Support text and thinking parts in array-based chat completion content while ignoring unknown part types.
• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

Changelog

Sourced from @​ai-sdk/openai's changelog.

4.0.50

Patch Changes

• e6a2992: Fix Responses history serialization for regular functions named tool_search.

4.0.49

Patch Changes

• 2523403: Normalize non-object replayed Chat Completions tool arguments to empty objects.
• Updated dependencies [3e125ba]
  • @​ai-sdk/provider-utils@​5.0.32

4.0.48

Patch Changes

• a9782e1: fix: align batch result parsing, request counts, and lifecycle behavior across providers
• eee6200: Signal schema-invalid known Responses stream events and preserve the error finish reason.
• 35841f5: feat: normalize mid-stream provider error events across supported providers into public StreamProviderError instances and preserve provider-owned type, code, status, retry, and raw payload metadata
• d2f3353: Split OpenAI and Azure OpenAI embedding requests by a conservative UTF-8 byte budget derived from their aggregate token limit, in addition to input count limits.
• Updated dependencies [a9782e1]
• Updated dependencies [35841f5]
• Updated dependencies [d2f3353]
  • @​ai-sdk/provider-utils@​5.0.31

4.0.47

Patch Changes

• 591d25b: feat: add batch completion webhooks. experimental_startTextBatch accepts a webhookUrl, and the gateway provider registers it through the batch callbackUrl contract and exports typed async-job metadata. Direct Anthropic and OpenAI batch providers return an unsupported warning when the option is provided.
• 2214258: Prevent negative text output token counts when providers report reasoning tokens. Perplexity reasoning tokens are now treated as separate from completion tokens.
• Updated dependencies [591d25b]
  • @​ai-sdk/provider@​4.0.8
  • @​ai-sdk/provider-utils@​5.0.30

4.0.46

Patch Changes

• Updated dependencies [b74971f]
  • @​ai-sdk/provider-utils@​5.0.29

4.0.45

Patch Changes

• 6be0f51: fix(openai): expand internal parallel tool call wrappers from the Responses API while preserving stateful continuation and streaming fallbacks

... (truncated)

Commits

• 0379422 Version Packages (#19778)
• e6a2992 fix: replay regular functions named tool_search correctly in OpenAI Responses...
• c93fa8d Version Packages (#19748)
• 2523403 fix: prevent strict Chat Completions backends from rejecting malformed persis...
• a01c481 Version Packages (#19478)
• 35841f5 feat: normalize mid-stream provider error events into public typed errors wit...
• d2f3353 fix: split large embedding batches that exceed provider aggregate token limit...
• a9782e1 fix(batch): align result parsing, request counts, and behavior across provide...
• eee6200 fix: OpenAI Responses streams silently dropping schema-invalid known events a...
• 3d3afac Version Packages (#19362)
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​ai-sdk/openai since your current version.

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
gno	Ready	Preview	Aug 31, 2026 4:03pm

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 22d7b96ea0

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Keep the OpenAI provider on the AI SDK 6 major

When bun scripts/update-eval-scores.ts --include-llm runs with OPENAI_API_KEY, evals/ask.eval.ts passes openai("gpt-5-mini") into generateText from ai. This bump moves only the provider onto the AI SDK 7/provider-v4 line (bun.lock resolves it through @ai-sdk/provider@4.0.4) while the repo still pins ai@6.0.68 and provider v3 at bun.lock:819, so the ask LLM judge hits a provider-spec mismatch and the scorer's catch records score 0 for every case. Please either keep @ai-sdk/openai on 3.x or upgrade the ai/Evalite call sites together.

Useful? React with 👍 / 👎.

[dependabot]

Superseded by #324.