chore(deps): bump ai from 6.0.68 to 7.0.83

[dependabot]

Bumps ai from 6.0.68 to 7.0.83.

Release notes

Sourced from ai's releases.

ai@6.0.272

Patch Changes

• e822a1d: Reject generateText responses that do not satisfy a required or specifically selected tool choice, and expose the normalized response content on ToolChoiceViolationError for opt-in recovery.
• 8c51a25: fix(ai): allow tool approval secrets in ToolLoopAgent settings and prepareCall
• Updated dependencies [cc23556]
• Updated dependencies [823cc03]
• Updated dependencies [3f96cf8]
  • @​ai-sdk/provider-utils@​4.0.50
  • @​ai-sdk/gateway@​3.0.185

Changelog

Sourced from ai's changelog.

7.0.83

Patch Changes

• 8dd86a9: Validate persisted typed tool calls against current input and output schemas. Schema-incompatible empty or error inputs and terminal history from unavailable tools remain loadable as dynamic tool parts instead of exposing unvalidated values under current static tool types.
• fda13b3: Allow chats to continue automatically after tool approval denials reach the output-denied state.
• 957146c: add operation-level outcomes to UI message stream end callbacks
• ce6849a: fix(ai): handle stitchable stream cancellation before an inner stream is registered

7.0.82

Patch Changes

• 3e125ba: Allow manual tool approval statuses to include a reason and preserve it across core, model, and UI approval requests. OPA requires-approval decisions now surface their reason to human approvers. UI request chunks serialize the optional reason, while UI messages retain it as approval.requestReason separately from an approver's response reason.
• Updated dependencies [0e7994c]
• Updated dependencies [3e125ba]
  • @​ai-sdk/gateway@​4.0.67
  • @​ai-sdk/provider-utils@​5.0.32

7.0.81

Patch Changes

• Updated dependencies [81bebaf]
  • @​ai-sdk/gateway@​4.0.66

7.0.80

Patch Changes

• 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.
• eed7950: Expose structured output parsing diagnostics from generateText when generation stops because of the output token limit.
• Updated dependencies [80227cf]
• Updated dependencies [a9782e1]
• Updated dependencies [5533946]
• Updated dependencies [35841f5]
• Updated dependencies [d2f3353]
  • @​ai-sdk/gateway@​4.0.65
  • @​ai-sdk/provider-utils@​5.0.31

7.0.79

... (truncated)

Commits

• 0379422 Version Packages (#19778)
• 8dd86a9 fix: reject stale persisted tool inputs without blocking unparsed or unavaila...
• fda13b3 fix: continue chats automatically after denied tool approvals (#19771)
• ce6849a fix(ai): handle stitchable stream cancellation before an inner stream is regi...
• 957146c fix: UI message stream end callbacks cannot distinguish failed responses from...
• c93fa8d Version Packages (#19748)
• 3e125ba fix: human tool approval requests omit policy reasons (#19658)
• 34c4710 Version Packages (#19716)
• 2523403 fix: prevent strict Chat Completions backends from rejecting malformed persis...
• a01c481 Version Packages (#19478)
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for ai 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 30, 2026 8:14pm

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 2e5a5f805b

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]

Align the OpenAI provider with AI SDK 7

When this lands by itself, ai is upgraded to v7 while @ai-sdk/openai stays at 3.0.25, so the eval scorer that calls generateText({ model: openai(...) }) in evals/ask.eval.ts combines AI SDK 7 with the older provider stack. The new lockfile shows ai now resolving @ai-sdk/provider 4.x while the OpenAI provider still resolves 3.x, so bun run eval runs with OPENAI_API_KEY set will fail the LLM judge path and return score 0 from the catch instead of judging answers. Please upgrade the provider package with the core SDK, or keep ai on 6.x.

Useful? React with 👍 / 👎.

[dependabot]

Dependabot tried to update this pull request, but something went wrong. We're looking into it, but in the meantime you can retry the update by commenting @dependabot recreate.

[dependabot]

Superseded by #326.