[mchesterbot]

This PR contains the following updates:

Package	Type	Update	Change
@ai-sdk/openai (source)	dependencies	patch	4.0.104 → 4.0.108

---

Release Notes

vercel/ai (@​ai-sdk/openai)

v4.0.108

Compare Source

Patch Changes

• Updated dependencies [fa15312]
  • @​ai-sdk/provider-utils@5.0.74

v4.0.107

Compare Source

Patch Changes

• 4ae6986: fix(openai): preserve valid JSON string tool arguments and serialize BigInt and cycles in tool calls and results, retaining malformed argument replay fallbacks
• 226b7da: Forward languages and keywords transcription hints as repeated multipart fields instead of silently dropping them. Warn when these REST-only options are supplied to streaming transcription.
• Updated dependencies [51ca5b7]
• Updated dependencies [dc6f1c3]
• Updated dependencies [4ae6986]
  • @​ai-sdk/provider-utils@5.0.73

v4.0.106

Compare Source

Patch Changes

• 7716e18: Support promises and synchronous or asynchronous callbacks in provider API key and token settings. Resolve credentials per authenticated request while preserving existing authentication behavior and synchronous credential serialization.

  The experimental OpenAI Live getServerWebSocketConfig() method can now resolve asynchronously. Await its result before using the connection settings.

• dcd2f8d: Introduce a model entry contract with named capability sections and request configuration. Consolidate the OpenAI and Anthropic model catalogs so existing request behavior and generated capability documentation use the same source of truth. Catalogs also declare the provider options each provider accepts and which models support them.

• Updated dependencies [7716e18]

• Updated dependencies [5c247e9]

• Updated dependencies [dcd2f8d]

  • @​ai-sdk/provider-utils@5.0.72
  • @​ai-sdk/provider@4.0.35

v4.0.105

Compare Source

Patch Changes

• 47b1d8b: feat(openai): send native JSON input and prompt cache keys to Decisions

• d07b475: fix(openai): map top-level reasoning to efforts supported by GPT-5.x models instead of sending unsupported values that OpenAI rejects with a 400. max is now only sent on the Responses API, and GPT-5.6 on Chat Completions sends reasoning_effort: 'none' when function tools are used, since it rejects function tools with reasoning. A warning is emitted when a reasoning level was requested.

• 61a315e: fix: map the top-level reasoning option consistently across providers

  Providers now resolve reasoning the same way:

  1. A provider-specific reasoning setting in providerOptions is sent unchanged. OpenAI no longer drops providerOptions.openai.reasoningEffort values that are not in its list for the model, and Fireworks no longer rewrites providerOptions.fireworks.reasoningEffort. Fireworks also sends top-level reasoning values directly instead of rounding them to 'high' at most, except for model families known to reject 'none' (GPT-OSS, GLM-5.3, Muse Spark) or 'minimal' (Nemotron, Inkling).
  2. Otherwise, reasoning maps to the closest level the model supports, rounding down, and rounds up only when there is no lower level. For example, 'xhigh' now maps to 'high' instead of 'max' on Anthropic and Bedrock models without xhigh effort, and 'medium' maps to 'low' instead of 'high' on DeepSeek, Kimi K3, and Mistral GLM-5.3 models.
  3. 'none' on a model that cannot disable reasoning maps to the model's lowest level with a compatibility warning, instead of being dropped or sending a request the API rejects. This affects GPT-6 models without 'none', xAI grok-4.5 and later, Groq GPT-OSS, Kimi K3, Perplexity, QuiverAI, Bedrock OpenAI gpt-oss models, and Gemini 2.5 Pro (minimum thinking budget). Gemini 3 and Anthropic and Bedrock between_tools mappings now emit the compatibility warning too.

  mapReasoningToProviderEffort now accepts any reasoning value, returns an optional providerOptionsEffort unchanged, and rounds levels that are missing from the effort map to the closest supported level. mapReasoningToProviderBudget maps 'none' to the minimum reasoning budget, always returns a budget, and uses the default percentage for levels missing from budgetPercentages. OpenAICompatibleChatConfig adds an optional mapReasoning function for mapping the top-level reasoning option.

• Updated dependencies [61a315e]

  • @​ai-sdk/provider-utils@5.0.71

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ 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 has been generated by Mend Renovate CLI.

[claude]

Claude finished @mchesterbot[bot]'s task in 16s —— View job

---

Review: @ai-sdk/openai 4.0.104 → 4.0.108

The branch now pins 4.0.108, so the PR title and description (4.0.107) are out of date. The diff is only package.json and package-lock.json. I did not run the test suite.

What changed

• package.json pins @ai-sdk/openai at 4.0.108, which matches the repo's exact-pin convention.
• The lockfile adds nested copies under node_modules/@ai-sdk/openai/node_modules/: @ai-sdk/provider 4.0.35, @ai-sdk/provider-utils 5.0.74 and undici 7.30.1.

Points to check

1. Duplicate provider packages. The hoisted @ai-sdk/provider is 4.0.34 and @ai-sdk/provider-utils is 5.0.70. The OpenAI provider now carries its own newer copies, so two versions of these packages are installed. The other @ai-sdk/* packages and ai@7.0.159 stay on the older ones. This is usually harmless because the packages share structural types, but npm run typecheck is the check that would catch a type mismatch in lib/llm/. It's worth confirming CI shows Typecheck and Unit Tests green.
2. Behaviour changes in the changelog (4.0.105–4.0.108).
   • The top-level reasoning option now maps to the efforts each GPT-5.x model supports. GPT-5.6 on Chat Completions sends reasoning_effort: 'none' when function tools are used. If the chat or wrapped purposes pass effort and tools to an OpenAI model, check that nothing depends on the old mapping.
   • Tool-call argument and BigInt/cycle serialisation was changed in 4.0.107.
   • These are fixes, and I found no breaking API changes.
3. Peer versions. The other AI SDK packages are not bumped. That's fine for patch releases, but if Renovate opens matching PRs for @ai-sdk/google and @ai-sdk/anthropic, merging them together would remove the duplicates.

Verdict: safe to merge once Typecheck, Unit Tests and Build pass. I found no security issues. A changelog fragment isn't needed, since no migrations, env, Docker or deploy files are touched.