Skip to content

deps: bump ai from 5.0.228 to 7.0.84 - #140

Closed
dependabot[bot] wants to merge 1 commit into
devfrom
dependabot/npm_and_yarn/ai-7.0.84
Closed

deps: bump ai from 5.0.228 to 7.0.84#140
dependabot[bot] wants to merge 1 commit into
devfrom
dependabot/npm_and_yarn/ai-7.0.84

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Sep 1, 2026

Copy link
Copy Markdown
Contributor

Bumps ai from 5.0.228 to 7.0.84.

Release notes

Sourced from ai's releases.

ai@6.0.273

Patch Changes

  • 6e632b8: Expose parsed structured output in streamText end callbacks.
  • Updated dependencies [5ab6f63]
    • @​ai-sdk/gateway@​3.0.186

ai@5.0.250

Patch Changes

  • 4e3f54b: Validate persisted typed tool calls against current input and output schemas. Schema-incompatible empty or error inputs and completed or failed history from unavailable tools remain loadable as dynamic tool parts instead of exposing unvalidated values under current static tool types.
  • 26165ee: Mark transient network errors that occur while reading successful response bodies as retryable, including AI Gateway responses.
  • Updated dependencies [810dc70]
  • Updated dependencies [7a926ba]
  • Updated dependencies [25c1956]
  • Updated dependencies [26165ee]
    • @​ai-sdk/gateway@​2.0.144
    • @​ai-sdk/provider-utils@​3.0.36
Changelog

Sourced from ai's changelog.

7.0.84

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

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

... (truncated)

Commits
  • 0a0f271 Version Packages (#19857)
  • e604532 fix: prevent smoothStream custom RegExp chunking from merging chunks or loopi...
  • 6669d69 fix: include parsed structured output in streamText end callbacks (#17717)
  • a6463ca fix: ToolLoopAgent types reject supported tool approval secrets (#19883)
  • 9a68261 feat(open-responses): support experimental extension codecs (#18900)
  • 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...
  • Additional commits viewable in compare view

Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

  • @dependabot rebase will rebase this PR
  • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
  • @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
  • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

Bumps [ai](https://github.com/vercel/ai/tree/HEAD/packages/ai) from 5.0.228 to 7.0.84.
- [Release notes](https://github.com/vercel/ai/releases)
- [Changelog](https://github.com/vercel/ai/blob/main/packages/ai/CHANGELOG.md)
- [Commits](https://github.com/vercel/ai/commits/ai@7.0.84/packages/ai)

---
updated-dependencies:
- dependency-name: ai
  dependency-version: 7.0.84
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot added the dependencies Dependency updates (Dependabot) label Sep 1, 2026
DeDuva added a commit that referenced this pull request Sep 1, 2026
Supersedes the three separate Dependabot PRs for `ai`, `@ai-sdk/anthropic` and
`@ai-sdk/google`. They cannot land one at a time: `ai` v7 speaks
LanguageModelV4 and the v2 providers do not, so each PR alone fails while all
three together pass.

    ai                  ^5.0.228 -> ^7.0.88   (#140)
    @ai-sdk/anthropic    ^2.0.93 -> ^4.0.46   (#142)
    @ai-sdk/google       ^2.0.86 -> ^4.0.60   (#143)

Four breaking changes, in two layers.

The harness reads usage. v7 moved the cache breakdown into `inputTokenDetails`
and redefined `inputTokens` as the *total* prompt count, cached reads included.
TokenUsage documents inputTokens and cachedInputTokens as disjoint and
priceUsage adds them, so a mechanical rename would have billed every cache read
twice — quietly, in a tool whose output is cost. `noCacheTokens` is the figure
v5's `inputTokens` used to carry; where a provider omits it we fall back to
total-minus-cached rather than to zero, so the invariant holds either way.

The test's scripted model needed three: MockLanguageModelV2 is now
MockLanguageModelV4 (the providers implement V4, so the mock should exercise the
same path), usage is two nested breakdowns rather than flat counters, and
finishReason is `{ unified, raw }` rather than a bare string. That last one is
why the first fix attempt still failed with no error: the model returned
successfully, the string finish reason simply meant no tool calls were seen, and
every conformance clause about tool calls went quiet rather than red.

`npm run check` passes: 290 files, 7554 tests.
@DeDuva

DeDuva commented Sep 1, 2026

Copy link
Copy Markdown
Owner

Superseded by #144 — closing.

This upgrade could not land on its own. ai v7 speaks LanguageModelV4 and the v2 providers do not, so ai, @ai-sdk/anthropic and @ai-sdk/google had to move together; #144 does all three, plus the four breaking changes they require in packages/squad-lab.

The one worth knowing about: v7 redefined usage.inputTokens as the total prompt count including cache reads, while this repo's TokenUsage documents it as disjoint from cachedInputTokens and priceUsage adds the two. Carrying the field across unchanged would have double-billed every cache read — silently, in the tool whose output is cost.

npm run check passes on the combined change: 290 files, 7554 tests.

@DeDuva DeDuva closed this Sep 1, 2026
@dependabot @github

dependabot Bot commented on behalf of github Sep 1, 2026

Copy link
Copy Markdown
Contributor Author

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.

@dependabot
dependabot Bot deleted the dependabot/npm_and_yarn/ai-7.0.84 branch September 1, 2026 18:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

dependencies Dependency updates (Dependabot)

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant