[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
@ai-sdk/anthropic (source)	^4.0.44 → ^4.0.46
@ai-sdk/azure (source)	^4.0.52 → ^4.0.54
@ai-sdk/deepseek (source)	^3.0.35 → ^3.0.37
@ai-sdk/google-vertex (source)	^5.0.68 → ^5.0.70
@ai-sdk/mistral (source)	^4.0.35 → ^4.0.37
@ai-sdk/openai (source)	^4.0.50 → ^4.0.52
@ai-sdk/openai-compatible (source)	^3.0.39 → ^3.0.41
@ai-sdk/provider (source)	^4.0.8 → ^4.0.9
@ai-sdk/xai (source)	^4.0.48 → ^4.0.50
ai (source)	^7.0.83 → ^7.0.85

---

Release Notes

vercel/ai (@​ai-sdk/anthropic)

v4.0.46

Compare Source

Patch Changes

• aa45741: fix(provider/anthropic): preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests
• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v4.0.45

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (@​ai-sdk/azure)

v4.0.54

Compare Source

Patch Changes

• Updated dependencies [1c68540]
• Updated dependencies [aa45741]
  • @​ai-sdk/openai@​4.0.52
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/deepseek@​3.0.37
  • @​ai-sdk/provider-utils@​5.0.34

v4.0.53

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33
  • @​ai-sdk/deepseek@​3.0.36
  • @​ai-sdk/openai@​4.0.51

vercel/ai (@​ai-sdk/deepseek)

v3.0.37

Compare Source

Patch Changes

• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v3.0.36

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (@​ai-sdk/google-vertex)

v5.0.70

Compare Source

Patch Changes

• 1d9b13b: fix(google-vertex): advertise the Vertex text embedding batch limit as 250
• Updated dependencies [23eb659]
• Updated dependencies [aa45741]
  • @​ai-sdk/openai-compatible@​3.0.41
  • @​ai-sdk/anthropic@​4.0.46
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/google@​4.0.58
  • @​ai-sdk/provider-utils@​5.0.34

v5.0.69

Compare Source

Patch Changes

• Updated dependencies [949ef93]
• Updated dependencies [90192f1]
  • @​ai-sdk/google@​4.0.57
  • @​ai-sdk/provider-utils@​5.0.33
  • @​ai-sdk/anthropic@​4.0.45
  • @​ai-sdk/openai-compatible@​3.0.40

vercel/ai (@​ai-sdk/mistral)

v4.0.37

Compare Source

Patch Changes

• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v4.0.36

Compare Source

Patch Changes

• e83d6dc: Preserve complete Mistral chat usage objects in raw usage metadata.
• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (@​ai-sdk/openai)

v4.0.52

Compare Source

Patch Changes

• 1c68540: Preserve explicit prompt cache breakpoints on scalar Responses tool results.
• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v4.0.51

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (@​ai-sdk/openai-compatible)

v3.0.41

Compare Source

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

v3.0.40

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (@​ai-sdk/provider)

v4.0.9

Compare Source

Patch Changes

• aa45741: fix(provider/anthropic): preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests

vercel/ai (@​ai-sdk/xai)

v4.0.50

Compare Source

Patch Changes

• Updated dependencies [aa45741]
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v4.0.49

Compare Source

Patch Changes

• Updated dependencies [90192f1]
  • @​ai-sdk/provider-utils@​5.0.33

vercel/ai (ai)

v7.0.85

Compare Source

Patch Changes

• 55a9981: Ensure canonical hashes preserve undefined array element positions.
• dd32de2: fix(ai): sum Gateway image-generation costs across split requests
• aa45741: fix(provider/anthropic): preserve native message batch request counts in provider metadata and support the full language-model option surface in batch requests
• cc29073: feat(ai): expose individual image generation calls
• Updated dependencies [d2507af]
• Updated dependencies [aa45741]
  • @​ai-sdk/gateway@​4.0.69
  • @​ai-sdk/provider@​4.0.9
  • @​ai-sdk/provider-utils@​5.0.34

v7.0.84

Compare Source

Patch Changes

• 6669d69: Expose parsed structured output in streamText end callbacks.
• a6463ca: fix(ai): allow tool approval secrets in ToolLoopAgent settings and prepareCall
• e604532: fix(ai): handle stateful and empty-match regular expressions in smoothStream
• Updated dependencies [805bbfc]
• Updated dependencies [90192f1]
  • @​ai-sdk/gateway@​4.0.68
  • @​ai-sdk/provider-utils@​5.0.33

---

Configuration

📅 Schedule: (in timezone 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.

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.

---

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

---

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

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
lmring-web	Ready	Preview	Aug 30, 2026 9:59am

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!