AI SDK 7 wraps file data as { type: "data" | "url" } and allows a bare "image" media type. The middleware only read the old shape, so image-only turns were not saved and mixed turns lost their images.
@ai-sdk/provider was a required peer, so npm installed provider 4 (Node 22 only) in AI SDK 5 and 6 apps. It is now optional, so apps keep the provider their ai version uses.
test:compat now checks that both image turns are saved and that the installed provider major matches the one ai depends on.
Every integration (AI SDK, OpenAI, Mastra, VoltAgent, Claude memory) now calls v5 through `supermemory@5`. The config takes one `namespace` instead of `containerTags` or `projectId`, and `withSupermemory` takes `namespace` and `id` instead of `containerTag` and `customId`. No aliases. With no config the tools still use `sm_project_default`.
Conversations are stored as one document per conversation keyed by `id` instead of `/v4/conversations`. `memoryForget` drops `reason`; forgetting by text previews with `forgetMatching` and then forgets exact matches by id. Claude memory marks its files with `metadata.source` instead of a second tag. Search keeps the 2.x defaults so results do not shift.
`packages/ai-sdk` is removed: npm already deprecates it in favor of `@supermemory/tools/ai-sdk`, so its CI steps and playground wiring go too. `apps/sdk-playground` moves to the new tools API and v5 routes, including its Python server.
Tested against production: add, search, profile, list and delete. 112 unit tests pass; type errors drop from 148 to 141, none new. The `supermemory` dependency pins the rc until 5.0.0 is published.
## Stack Context
This stack moves memory deduplication **out of the playground UI and into the SDKs themselves**, so every integration injects a single, deduplicated, self-replacing memory block. Three PRs:
1. **`sdk-dedup/tools-ts`** (this PR) — TypeScript SDK core + integrations
2. `sdk-dedup/python` — Python SDKs
3. `sdk-dedup/playground` — playground debug view reflects the SDK-owned block
## What?
Move profile deduplication into the SDK middleware for the TypeScript tools package.
- Facts are normalized (strip leading `[YYYY-MM-DD]`, trim, collapse whitespace, casefold) and deduplicated in **`static > dynamic > search`** priority within a single request.
- The result is injected as one **owned `<supermemory>` block** that *replaces* the previous block instead of accumulating a new one each turn.
- Dedup is **mode-aware**: in query mode, search results are not dropped against a profile that isn't being injected.
- Deduplication is **request-local** — no global/browser `Set`. Safe for multiple users, concurrent requests, and Cloudflare Worker isolates.
Covers AI SDK, OpenAI (Chat + Responses), Mastra, and VoltAgent. New `shared/memory-context.ts` owns the block-replacement logic.
## Why?
The earlier "conversation-scoped deduplication" was only a playground browser `Set` — a UI debug affordance that did not change what the SDK sent to the model, and would have been unsafe as server-side global state. Real cross-source dedup belongs in the SDK, applied fresh per stateless model request.
## Testing
- `bun run test` in `packages/tools`: 145 passed (the one failing suite, `claude-memory.test.ts`, is a pre-existing broken import unrelated to this change).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> **Medium Risk**
> Changes how system prompts and instructions are built across all TypeScript integrations; behavior is well-covered by unit tests but incorrect strip/replace logic could drop or duplicate context in production prompts.
>
> **Overview**
> Moves **cross-source memory deduplication** and **owned prompt injection** into `@supermemory/tools` so every integration sends one deduplicated memory block per request instead of growing context each turn.
>
> **Deduplication:** Facts are normalized via `normalizeMemoryFact` (strip `[YYYY-MM-DD]`, trim, collapse whitespace, lowercase) and deduplicated with **static → dynamic → search** priority. `deduplicateMemoriesForMode` keeps search hits in **query** mode when the profile is not injected.
>
> **Owned `<supermemory>` block:** New `shared/memory-context.ts` wraps memories in `<supermemory context="user-memories" readonly>`, strips stale blocks, and **replaces** prior SDK context while preserving caller system instructions. Applied in AI SDK (`injectMemoriesIntoParams`), OpenAI Chat/Responses middleware, Mastra input processor (`wrapMemoryContext`), and VoltAgent hooks.
>
> **Tests:** Unit coverage for block replacement (with-supermemory, OpenAI, VoltAgent), Mastra wrapper tag assertion, normalized dedup variants, and concurrent `containerTag` isolation.
>
> <sup>Reviewed by [Cursor Bugbot](https://cursor.com/bugbot) for commit 2fa2e0d85c. Bugbot is set up for automated code reviews on this repo. Configure [here](https://www.cursor.com/dashboard/bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
## Summary
- Refresh canonical tool descriptions in `tools-shared.ts`
- Align OpenAI and AI SDK tool bindings with 7-tool surface
- Export `TOOL_DESCRIPTIONS` / `PARAMETER_DESCRIPTIONS` from package index
Stacked on #1431
## Test plan
- [ ] `bun run test:unit` in `packages/tools`
Made with [Cursor](https://cursor.com)
Cherry-picks four contributor PRs for `@supermemory/tools` onto one branch, and bumps the package to 2.2.0.
- #1244 (@rajarshidattapy): `withSupermemory` accepts `options.apiKey` instead of only reading `SUPERMEMORY_API_KEY`, matching the Vercel, Mastra and Voltagent integrations. Unblocks secrets managers, edge runtimes and per-request keys.
- #1574 (@Agnik47): re-exports `PromptTemplate`, `MemoryPromptData` and `WithSupermemoryOptions` from `ai-sdk`. `./vercel` is not a published subpath, so the documented custom-template example did not compile.
- #1488 (@abhinav7x94): malformed tool-call JSON returns an error result instead of throwing out of the request.
- #1507 (@abhinav7x94): VoltAgent `onEnd` awaits the conversation save, which was fire-and-forget and could be dropped when a serverless runtime tore down.
Dropped the `middleware.test.ts` added by #1244. Note that editing `packages/tools/package.json` triggers the npm publish workflow on merge.
Co-Authored-By: rajarshidattapy <138959719+rajarshidattapy@users.noreply.github.com>
Co-Authored-By: Agnik47 <140933190+Agnik47@users.noreply.github.com>
Co-Authored-By: abhinav7x94 <204053250+abhinav7x94@users.noreply.github.com>
- Published the v2.0.0 docs and a 1.4 → 2.0 migration guide so existing users have a clear upgrade path.
- Updated the four integration pages (AI SDK, OpenAI, Mastra, VoltAgent) to reflect v2 defaults and link to the migration guide.
- Added a short explainer on the two required fields (containerTag, customId) so new users aren't blocked at first integration.
**`withSupermemory`** **(AI SDK)**
- **`skipMemoryOnError`** **defaults to** **`true`**. memory errors/timeouts log and the model runs on the **original** prompt unless you set `skipMemoryOnError: false`.
- **Pre-LLM** **`/v4/profile`** **is aborted after 5s** via `AbortSigna`
**Docs**
- `packages/tools/README.md`, **`apps/docs/integrations/ai-sdk.md`**
adds withSupermemory wrapper and input/output processors for
mastra agents:
- input processor fetches and injects memories into system prompt
before llm calls
- output processor saves conversations to supermemory after
responses
- supports profile, query, and full memory search modes
- includes custom prompt templates and requestcontext support
const agent = new Agent(withSupermemory(
{ id: "my-assistant", model: openai("gpt-4o"), instructions:
"..." },
"user-123",
{ mode: "full", addMemory: "always", threadId: "conv-456" }
))
includes docs as well
this pr also reworks how the tools package works into shared modules
## Add customizable prompt templates for memory injection
**Changes:**
- Add `promptTemplate` option to `withSupermemory()` for full control over injected memory format (XML, custom branding, etc.)
- New `MemoryPromptData` interface with `userMemories` and `generalSearchMemories` fields
- Exclude `system` messages from persistence to avoid storing injected prompts
- Add JSDoc comments to all public interfaces for better DevEx
**Usage:**
```typescript
const customPrompt = (data: MemoryPromptData) => `
<user_memories>
${data.userMemories}
${data.generalSearchMemories}
</user_memories>
`.trim()
const model = withSupermemory(openai("gpt-4"), "user-123", {
promptTemplate: customPrompt,
})
```
### Added streaming support to the Supermemory middleware and improved memory handling in the AI SDK integration.
### What changed?
- Refactored the middleware architecture to support both streaming and non-streaming responses
- Extracted memory prompt functionality into a separate module (`memory-prompt.ts`)
- Added memory saving capability for streaming responses
- Improved the formatting of memory content with a "User Supermemories:" prefix
- Added utility function to filter out supermemories from content
- Created a new streaming example in the test app with a dedicated route and page
- Updated version from 1.3.0 to 1.3.1 in package.json
- Simplified installation instructions in [README.m](http://README.md)d
### TL;DR
Added OpenAI SDK middleware support for SuperMemory integration, allowing direct memory injection without AI SDK dependency.
### What changed?
- Added `withSupermemory` middleware for OpenAI SDK that automatically injects relevant memories into chat completions
- Implemented memory search and injection functionality for OpenAI clients
- Restructured the OpenAI module to separate tools and middleware functionality
- Updated README with comprehensive documentation and examples for the new OpenAI middleware
- Added test implementation with a Next.js API route example
- Reorganized package exports to support the new structure
### TL;DR
Added support for automatically saving user messages to Supermemory.
### What changed?
- Added a new `addMemory` option to `wrapVercelLanguageModel` that accepts either "always" or "never" (defaults to "never")
- Implemented the `addMemoryTool` function to save user messages to Supermemory
- Modified the middleware to check the `addMemory` setting and save the last user message when appropriate
- Initialized the Supermemory client in the middleware to enable memory storage
### How to test?
1. Set the `SUPERMEMORY_API_KEY` environment variable
2. Use the `wrapVercelLanguageModel` function with the new `addMemory: "always"` option
3. Send a user message through the model
4. Verify that the message is saved to Supermemory with the specified container tag
### Why make this change?
This change enables automatic memory creation from user messages, which improves the system's ability to build a knowledge base without requiring explicit memory creation calls. This is particularly useful for applications that want to automatically capture and store user interactions for future reference.
