> ## Documentation Index
> Fetch the complete documentation index at: https://supermemory-temp-snowcone-command.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Upgrading @supermemory/tools to v2.0.0

> Migrate your code from @supermemory/tools 1.4.x to 2.0.0 — config-object signature, customId, and new defaults

`@supermemory/tools` v2.0.0 unifies the API across all four integrations (Vercel AI SDK, OpenAI, Mastra, VoltAgent) around a single config-object signature and a consistent conversation-grouping concept. This guide walks you through the breaking changes.

<Note>
  This release is **breaking**. Update calls and re-test before bumping in
  production.
</Note>

## What changed at a glance

| Area                  | v1.4.x                                                | v2.0.0                                                      |
| --------------------- | ----------------------------------------------------- | ----------------------------------------------------------- |
| Signature             | `withSupermemory(model, "user-123", { ... })`         | `withSupermemory(model, { containerTag: "user-123", ... })` |
| Conversation grouping | `conversationId` (Vercel/OpenAI), `threadId` (Mastra) | **`customId`** everywhere                                   |
| `customId`            | Optional                                              | **Required** — throws if missing or empty                   |
| `containerTag`        | Positional argument                                   | **Required** field on options object                        |
| `addMemory` default   | `"never"`                                             | `"always"`                                                  |
| VoltAgent `verbose`   | Hardcoded to `false`                                  | Honored from options                                        |

## Install

```bash theme={null}
npm install @supermemory/tools@^2.0.0
```

## 1. Vercel AI SDK

```typescript theme={null}
// v1.4.x
import { withSupermemory } from '@supermemory/tools/ai-sdk';

const model = withSupermemory(openai('gpt-4'), 'user-123', {
  conversationId: 'conv-456',
  mode: 'full',
});
```

```typescript theme={null}
// v2.0.0
import { withSupermemory } from '@supermemory/tools/ai-sdk';

const model = withSupermemory(openai('gpt-4'), {
  containerTag: 'user-123',
  customId: 'conv-456',
  mode: 'full',
});
```

<Warning>
  `customId` is now **required**. Passing an empty string or omitting it throws
  at construction time.
</Warning>

## 2. OpenAI SDK

```typescript theme={null}
// v1.4.x
import { withSupermemory } from '@supermemory/tools/openai';

const client = withSupermemory(openai, 'user-123', {
  conversationId: 'conv-456',
});
```

```typescript theme={null}
// v2.0.0
import { withSupermemory } from '@supermemory/tools/openai';

const client = withSupermemory(openai, {
  containerTag: 'user-123',
  customId: 'conv-456',
});
```

Both `containerTag` and `customId` are validated and throw with explicit error messages if missing.

## 3. Mastra

Processor constructors and factory functions both moved to a single options argument. `threadId` is gone — use `customId` instead.

```typescript theme={null}
// v1.4.x
import {
  SupermemoryInputProcessor,
  createSupermemoryOutputProcessor,
} from '@supermemory/tools/mastra';

const input = new SupermemoryInputProcessor('user-123', {
  mode: 'full',
});

const output = createSupermemoryOutputProcessor('user-123', {
  threadId: 'conv-456',
  addMemory: 'always',
});
```

```typescript theme={null}
// v2.0.0
import {
  SupermemoryInputProcessor,
  createSupermemoryOutputProcessor,
} from '@supermemory/tools/mastra';

const input = new SupermemoryInputProcessor({
  containerTag: 'user-123',
  customId: 'conv-456',
  mode: 'full',
});

const output = createSupermemoryOutputProcessor({
  containerTag: 'user-123',
  customId: 'conv-456',
});
```

<Note>
  In server setups, Mastra's `RequestContext` thread ID still takes precedence
  over the construction-time `customId` — the option now acts as the fallback
  when no per-request thread ID is provided.
</Note>

## 4. VoltAgent

VoltAgent already used a config-object signature, so the call shape is unchanged. Two behavior fixes ship in v2.0.0:

* `verbose: true` is now honored (was hardcoded to `false` in v1.4.x).
* A runtime warning is logged when advanced search params (`threshold`, `limit`, `rerank`, `rewriteQuery`, `filters`, `include`, `searchMode`) are set while `mode: "profile"` — those parameters are ignored in profile mode.

If you were relying on `verbose: false` implicitly while passing `verbose: true`, you will now see logs. Adjust as needed.

## 5. New default: `addMemory: "always"`

Across all four integrations, `addMemory` now defaults to `"always"`. If your v1.4.x code relied on the old default of `"never"`, set it explicitly:

```typescript theme={null}
const model = withSupermemory(openai('gpt-4'), {
  containerTag: 'user-123',
  customId: 'conv-456',
  addMemory: 'never', // preserve v1.4.x behavior
});
```

## Conversation persistence

In v1.4.x the Vercel middleware fell back to `client.add` with a synthesized `customId` when no `conversationId` was passed. In v2.0.0, because `customId` is required, all conversation persistence goes through the `/v4/conversations` endpoint via `addConversation`. There is no fallback path.

## Migration checklist

<Steps>
  <Step title="Bump the dependency">
    `npm install @supermemory/tools@^2.0.0`
  </Step>

  <Step title="Find every withSupermemory / processor call">
    Grep your codebase for `withSupermemory(`, `SupermemoryInputProcessor`,
    `SupermemoryOutputProcessor`, `createSupermemoryProcessor`,
    `createSupermemoryOutputProcessor`.
  </Step>

  <Step title="Move containerTag into the options object">
    Drop the positional `containerTag` argument and add it to the options
    object.
  </Step>

  <Step title="Rename conversationId / threadId to customId">
    Make sure every call site provides a non-empty `customId`.
  </Step>

  <Step title="Audit addMemory">
    If you depended on the old `"never"` default, pass `addMemory: "never"`
    explicitly.
  </Step>

  <Step title="Run your test suite">
    Validation throws happen at construction time, so missing fields surface
    immediately.
  </Step>
</Steps>

## Need help?

* [Vercel AI SDK integration](/integrations/ai-sdk)
* [OpenAI integration](/integrations/openai)
* [Mastra integration](/integrations/mastra)
* [VoltAgent integration](/integrations/voltagent)

If you hit something this guide does not cover, open an issue on [GitHub](https://github.com/supermemoryai/supermemory).