Skip to content

Support and test Vercel AI SDK 7 #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
x1xhlol merged 1 commit into from
Oct 4, 2026
Merged

Support and test Vercel AI SDK 7 #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,10 @@
# Changelog

## [Unreleased]

- AI SDK 7 support, tested. `shieldLanguageModelMiddleware` works unchanged with AI SDK 7 (`ai@7`, `v4` language models) in `generateText` and `streamText`, and the test suite now runs it against AI SDK 4, 5, 6, and 7, including streaming, tool results, tool call arguments, `throwOnLeak`, and redaction.
- The legacy `shieldMiddleware().wrapParams()` and `wrapParamsAsync()` now also harden AI SDK 7's `instructions` option, which replaces the deprecated `system`. Before, a system prompt passed as `instructions` reached the model unhardened.

## [2.0.0] - 2026-10-02

- Root `detect()` now returns a Promise and calls the hosted Shield API with a dashboard key. `createHostedDetector()` supports the four hosted model IDs, self-hosted moderation endpoints, cancellation, timeouts, and provider wrapper options.
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,7 +200,7 @@ Every wrapper hardens the system prompt, runs its configured detector on user me
| OpenAI | `shieldOpenAI` from `@zeroleaks/shield/openai` | `chat.completions.create`, `responses.create` |
| Anthropic | `shieldAnthropic` from `@zeroleaks/shield/anthropic` | `messages.create` |
| Groq | `shieldGroq` from `@zeroleaks/shield/groq` | `chat.completions.create` |
| Vercel AI SDK 4, 5, 6 | `shieldLanguageModelMiddleware` from `@zeroleaks/shield/ai-sdk` | `generateText`, `streamText` via `wrapLanguageModel` |
| Vercel AI SDK 4, 5, 6, 7 | `shieldLanguageModelMiddleware` from `@zeroleaks/shield/ai-sdk` | `generateText`, `streamText` via `wrapLanguageModel` |
| Google Gen AI | `shieldGoogleGenAI` from `@zeroleaks/shield/google` | `models.generateContent`, `models.generateContentStream`, and chats |
| Mistral | `shieldMistral` from `@zeroleaks/shield/mistral` | `chat.complete`, `chat.stream` |
| LangChain.js | `shieldChatModel`, `ShieldCallbackHandler` from `@zeroleaks/shield/langchain` | `invoke`, `stream`, `batch`, and runnables derived from the model |
Expand Down
29 changes: 22 additions & 7 deletions bun.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 2 additions & 1 deletion package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,9 +173,10 @@
"@modelcontextprotocol/sdk": "^1.30.1",
"@openai/agents": "^0.18.0",
"@types/node": "^26.1.1",
"ai": "^6.0.292",
"ai": "^7.0.127",
"ai-v4": "npm:ai@^4.3.19",
"ai-v5": "npm:ai@^5.0.267",
"ai-v6": "npm:ai@^6.0.292",
"groq-sdk": "^0.37.0",
"openai": "^6.25.0",
"tsup": "^8.5.1",
Expand Down
Loading
Loading