When a customId is configured, the chat-completions path hands
addMemoryTool the messages plus API credentials, so the save routes
through /v4/conversations with the internal "conversation:" prefix
stripped back off. The Responses path built the same prefixed
memoryCustomId but passed neither messages nor credentials, so the
conversation branch never ran and the save fell through to
client.add() with "conversation:<id>" as the stored customId — a value
customId validation rejects (alphanumeric/hyphen/underscore only). The
error is swallowed by design (memory saves must not break the user's
API call), which means every Responses API call with a customId
silently saved nothing.
Hand the input over as a single user message together with the
credentials, mirroring the chat path, so conversation grouping works
for the Responses API too. Also strip the internal prefix in the
client.add fallback so the routing marker can never leak into a stored
customId on any path (previously the chat path had the same leak
whenever SUPERMEMORY_API_KEY was unset).
Covered with mocked-SDK middleware tests: a customId save routes
through addConversation with the un-prefixed conversation id and never
touches client.add; the fallback stores the user's configured id, not
the prefixed marker; and the no-customId path is unchanged. Two of the
three tests fail against the previous implementation.
- 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
