[JayanthMalladi]

Upgrade to AI SDK 7

This PR moves the project from AI SDK 6 to 7 and keeps its current behavior.

Versions

• @ai-sdk/anthropic: ^3.0.133 → ^4.0.0
• @ai-sdk/azure: ^3.0.141 → ^4.0.0
• @ai-sdk/google: ^3.0.136 → ^4.0.0
• @ai-sdk/openai-compatible: ^2.0.86 → ^3.0.0
• @ai-sdk/openai: ^3.0.10 → ^4.0.0
• @ai-sdk/provider: ^3.0.19 → ^4.0.0
• ai: ^6.0.311 → ^7.0.0

This drops support for AI SDK 6, so users of this package will need AI SDK 7 too. It probably belongs in a new major version.

What changed and why

Fixed: would fail at runtime on v7

• packages/ai-tools/__tests__/ai-tools.test.mts:187, packages/ai-tools/__tests__/ai-tools.test.mts:247: messages/prompt has a system message, which AI SDK 7 rejects at runtime by default. allowSystemInMessages: true keeps the v6 behavior.
• packages/ai-tools/__tests__/ai-tools.test.mts:306, packages/ai-tools/__tests__/ai-tools.test.mts:376: This agent may be called with a system message in messages/prompt (or its calls aren't visible here), which AI SDK 7 rejects by default. Only the constructor accepts the option; .generate()/.stream() don't. allowSystemInMessages: true keeps the v6 behavior.

Other source files changed (codemod renames and fixer edits): packages/ai-tools/src/providers/types.mts.

After the codemod, these checks failed; this PR fixes them: build, typecheck packages/ai-tools.

How it was checked

Check	Before	After
install	pass	pass
build	pass	pass
typecheck .	fail	fail
test .	fail	fail
typecheck packages/ai-tools	pass	pass
test packages/ai-tools	fail	fail

Also ran npx @ai-sdk/codemod v7 (official). Install ran with --ignore-scripts. A second agent reviewed the full diff for behavior changes and unrelated edits.

Rollback

Revert this PR. No data or config migrations are involved.

---

Opened by Shim, which turns API breaking changes into tested PRs. Not useful? Close it and we won't open another on this repo.

[changeset-bot]

🦋 Changeset detected

Latest commit: 24b661f

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
@chainfuse/ai-tools	Major

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has insufficient remaining quota.

[socket-security]

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	@​ai-sdk/​google@​4.0.107
	@​ai-sdk/​openai@​4.0.104
	@​ai-sdk/​provider@​4.0.34
	@​ai-sdk/​azure@​3.0.141 ⏵ 4.0.112	+16		-3
	@​ai-sdk/​openai-compatible@​2.0.86 ⏵ 3.0.80	+14		-16
	@​ai-sdk/​anthropic@​4.0.90
	ai@​7.0.155

View full report

[socket-security]

Caution

Review the following alerts detected in dependencies.

According to your organization's Security Policy, you must resolve all "Block" alerts before proceeding. Learn more about Socket for GitHub.

Priority	Alert  (click "▶" to expand/collapse)	Action
	Potential code anomaly (AI signal): npm undici is 68.0% likely to have a medium risk anomaly Notes: Both alerts describe an in-place re-encoding of a local file from UTF-8 to Latin-1, overwriting the original without backups or validation. This can cause data loss and code corruption, creating a supply-chain tampering risk. The script itself shows no exfiltration or network activity, but its destructive behavior warrants deletion or strict safeguards and auditing. Confidence: 0.68 Severity: 0.60 From: package-lock.json → npm/@ai-sdk/azure@4.0.112 → npm/@ai-sdk/google@4.0.107 → npm/ai@7.0.155 → npm/@ai-sdk/openai-compatible@3.0.80 → npm/@ai-sdk/anthropic@4.0.90 → npm/@ai-sdk/openai@4.0.104 → npm/undici@7.30.1 ℹ Read more on: This package | This alert | What is an AI-detected potential code anomaly? Next steps: Take a moment to review the security alert above. Review the linked package source code to understand the potential risk. Ensure the package is not malicious before proceeding. If you're unsure how to proceed, reach out to your security team or ask the Socket team for help at support@socket.dev. Suggestion: An AI system found a low-risk anomaly in this package. It may still be fine to use, but you should check that it is safe before proceeding. Mark the package as acceptable risk. To ignore this alert only in this pull request, reply with the comment @SocketSecurity ignore npm/undici@7.30.1. You can also ignore all packages with @SocketSecurity ignore-all. To ignore an alert for all future pull requests, use Socket's Dashboard to change the triage state of this alert.	Block

View full report