chore(deps): bump @ai-sdk/openai from 3.0.84 to 4.0.11

[dependabot]

Bumps @ai-sdk/openai from 3.0.84 to 4.0.11.

Changelog

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

4.0.11

Patch Changes

• b2b1bb9: feat(provider/openai): add GPT-5.6 reasoning and prompt cache controls

4.0.10

Patch Changes

• fdb6d5d: feat(provider/openai,provider/gateway): add gpt-5.6 model ids
• Updated dependencies [0f93c57]
  • @​ai-sdk/provider@​4.0.3
  • @​ai-sdk/provider-utils@​5.0.7

4.0.9

Patch Changes

• ac306ed: Fix StreamingToolCallTracker finalizing streaming tool calls on parsable partial JSON. Tool calls now only finalize during stream flush, restoring the behavior of #13137: a parsable argument buffer can still be the prefix of a longer argument string, so finalizing early could act on truncated tool inputs.
• Updated dependencies [ac306ed]
  • @​ai-sdk/provider-utils@​5.0.6

4.0.8

Patch Changes

• b51ed36: Send inline image file parts in OpenAI chat requests as data URLs instead of bare base64 strings.

4.0.7

Patch Changes

• 5c5c0f5: Add experimental streaming transcription support for transcription models, including OpenAI gpt-realtime-whisper and xAI WebSocket STT.
• Updated dependencies [5c5c0f5]
  • @​ai-sdk/provider@​4.0.2
  • @​ai-sdk/provider-utils@​5.0.5

4.0.6

Patch Changes

• Updated dependencies [c6f5e62]
  • @​ai-sdk/provider-utils@​5.0.4

4.0.5

Patch Changes

• Updated dependencies [8c616f0]

... (truncated)

Commits

• 703e0bf Version Packages (#17031)
• b2b1bb9 feat(provider/openai): support GPT-5.6 reasoning and prompt caching controls ...
• 405116e Version Packages (#16937)
• fdb6d5d feat(provider/openai,provider/gateway): add gpt-5.6 model id (#17021)
• f0d9a6c Version Packages (#16898)
• ac306ed fix(provider-utils): do not finalize streaming tool calls on parsable partial...
• a9953d2 Version Packages (#16700)
• b51ed36 fix: send OpenAI chat image data as data URLs (#16655)
• c73f2ef Version Packages (#16651)
• 5c5c0f5 Add experimental streaming transcription support (#16338)
• Additional commits viewable in compare view

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)

[chatgpt-codex-connector]

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

[krishagel]

🤖 pr-fix routine: blocked by environment network policy

Diagnosed the two real CI failures on this PR:

1. Test, Lint, and Type Check and Validate CDK Infrastructure both fail identically:

   error: lockfile had changes, but lockfile is frozen
   note: try re-running without --frozen-lockfile and commit the updated lockfile
   

   Root cause: Dependabot's commit only bumped @ai-sdk/openai in package.json (~3.0.74 → ~4.0.11) but did not update bun.lock to match. The fix is a simple bun install && git add bun.lock && git commit.

2. claude-review fails for an unrelated reason: Workflow initiated by non-human actor: dependabot (type: Bot). Add bot to allowed_bots list or use '*' to allow all bots. Fixing this requires editing the allowed_bots config inside .github/workflows/**, which is a protected path this autonomous routine cannot touch.

Why I couldn't push the lockfile fix myself: this routine's execution sandbox blocks outbound network access to registry.npmjs.org (Host not in allowlist: registry.npmjs.org. Add this host to your network egress settings to allow access.) — confirmed with both a direct request and one routed through the egress proxy. bun install needs registry access to resolve the new @ai-sdk/openai version and regenerate bun.lock, so it fails here even though GitHub Actions' own runner (which has full npm access) gets past dependency resolution just fine.

Also worth flagging: because I never got past bun install, I couldn't confirm whether the 3.0.84 → 4.0.11 major version bump needs any code changes beyond the lockfile (e.g. in the OpenAI provider factory). That should be checked once the lockfile is regenerated.

To unblock:

• A human (or an environment with npm registry egress) can run bun install, commit the updated bun.lock, and push — then remove pr-fix-stuck so this routine verifies and re-checks the claude-review/protected-workflow item separately.
• Alternatively, allow registry.npmjs.org in this routine's environment network egress policy so future runs can fix Bun/npm lockfile drift autonomously.

No commits were pushed by this routine. The routine will not pick this PR up again until pr-fix-stuck is removed.

---

Generated by Claude Code

[krishagel]

🔬 Deferred as part of the AI SDK v7 cluster — see the full triage and migration plan on #1214. These majors are interdependent (shared provider-spec version) and can only land via one consolidated migration branch, which requires live-provider E2E verification not available in the current environment. Labeled pr-fix-skip; do not hand back to the pr-fix routine.

[dependabot]

Superseded by #1574.