[dependabot]

Bumps @ai-sdk/openai from 4.0.96 to 4.0.101.

Changelog

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

4.0.101

Patch Changes

• Updated dependencies [8202f5b]
• Updated dependencies [85d84a1]
  • @​ai-sdk/provider-utils@​5.0.67
  • @​ai-sdk/provider@​4.0.33

4.0.100

Patch Changes

• 43ad966: Report interrupted when a stream ends cleanly without its provider completion signal, preserving partial output without emitting an error solely for the interruption.

  This applies to OpenAI (Chat, Responses, and Completions), Anthropic, Google (Generate Content and Interactions), Alibaba, Amazon Bedrock Converse, Cohere, DeepSeek, Groq, Hugging Face Responses, Mistral Chat, Moonshot AI, Open Responses, Perplexity, and xAI Responses. It also covers cutoffs in later Anthropic messages and Google automatic continuations.

  Compatibility notice: These streams previously fell back to other or omitted the finish part. Applications must now handle interrupted in finish-reason switches, mappings, and custom validation. Check finishReason === 'interrupted' to detect incomplete responses; interruption alone does not trigger error handling.

  Explicit unknown completion reasons still map to other. Actual provider, parsing, and transport errors retain their error paths; affected error paths that previously left the finish reason as other now report error. OpenAI-compatible remains unchanged.

• Updated dependencies [10026d1]

  • @​ai-sdk/provider@​4.0.32
  • @​ai-sdk/provider-utils@​5.0.66

4.0.99

Patch Changes

• 39a776b: Add a shared encodePathSegment helper and use it to encode provider-returned identifiers in credentialed follow-up request paths.
• c787919: Defer construction of provider validation schemas until first use to reduce package import time.
• 0257b47: feat(openai): support 12h prompt cache writes and cache prewarming
• Updated dependencies [b089ce8]
• Updated dependencies [39a776b]
  • @​ai-sdk/provider-utils@​5.0.65

4.0.98

Patch Changes

• 0c2a9de: Add maxOutputTokens and reasoning to experimental decision calls and forward them to language-model-backed decisions. Language-model adapters keep reasoning disabled when omitted. Native decision providers warn when either setting is unsupported.
• 8b728ec: fix(openai): preserve detected language codes in transcription responses
• 3cb1dae: fix(openai): forward shell_call timeout_ms and max_output_length to the shell tool and round-trip max_output_length
• Updated dependencies [0c2a9de]
• Updated dependencies [200c47f]
  • @​ai-sdk/provider@​4.0.31
  • @​ai-sdk/provider-utils@​5.0.64

4.0.97

... (truncated)

Commits

• 594495a Version Packages (#23857)
• 401cadc Version Packages (#23785)
• 43ad966 fix: report interrupted streams without completion signals (#23814)
• e6230e4 Version Packages (#23638)
• 0257b47 feat(openai): support 12h prompt cache writes and cache prewarming (#23635)
• c787919 perf(openai): defer schema construction until first use (#23667)
• 39a776b fix: share URL path segment encoding (#23679)
• 0a5c786 Version Packages (#23572)
• 0c2a9de feat: add maxOutputTokens and reasoning to decide (#23590)
• 8b728ec fix(openai): preserve detected language codes in transcription responses (#23...
• Additional commits viewable in compare view

[vercel]

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

Project	Deployment	Actions	Updated
fate	Ready	Preview	Oct 26, 2026 3:08am UTC