vercel-ai-v3.0.0

mem0ai/mem0vercel-ai-v3.0.0Jun 10, 2026by whysosaket

AI Summary

Major Vercel AI SDK provider release migrating to v6 and Mem0 v3 API.

Key Highlights

Migrated to Vercel AI SDK v6 (LanguageModelV3) and Mem0 v3 API endpoints.
Added `source` field to responses containing attached memories.
Removed Graph Memory support and deprecated config parameters.

Breaking Changes

Upgraded from AI SDK v5 to v6 (requires `ai` ^6.0.199 and provider packages ^3.x).
Migrated API endpoints: `/v1/memories/` → `/v3/memories/add/` and `/v2/memories/search` → `/v3/memories/search/`.
Entity IDs (`user_id`, `agent_id`, `run_id`) must now be provided inside the `filters` object.
Removed Graph Memory support, prompts, and relation extraction code.
Removed deprecated config fields: `org_id`, `project_id`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version`.

New Features

V3 Provider Contract with `specificationVersion: "v3"` and `supportedUrls`.
Mem0 source in responses accessible via `providerMetadata.mem0.memories`.

Full Release Notes

## Vercel AI SDK Provider (v3.0.0)

### Major Release

Migrated to **Vercel AI SDK v6 (LanguageModelV3 / ProviderV3)** and the **Mem0 v3 API**.

### Breaking Changes

#### AI SDK v6

* Upgraded from **AI SDK v5 (LanguageModelV2)** to **AI SDK v6 (LanguageModelV3)**.
* Users must upgrade:

  * `ai` → `^6.0.199`
  * All `@ai-sdk/*` provider packages → `^3.x`

#### Mem0 v3 API

* Memory endpoints migrated:

  * `/v1/memories/` → `/v3/memories/add/`
  * `/v2/memories/search` → `/v3/memories/search/`
* Entity IDs (`user_id`, `agent_id`, `run_id`) must now be provided inside the `filters` object for search requests.

#### Graph Memory Removed

* Removed:

  * `enable_graph`
  * Graph prompts
  * Relation extraction code
* Graph memory is now configured as a project-level setting in the Platform.

#### Deprecated Parameters Removed

The following fields have been removed from `Mem0ConfigSettings`:

* `org_id`
* `project_id`
* `org_name`
* `project_name`
* `output_format`
* `filter_memories`
* `async_mode`
* `enable_graph`
* `version`
* `api_version`

### New Features

#### V3 Provider Contract

* `specificationVersion: "v3"`
* `supportedUrls` property
* V3 content arrays in `doGenerate`
* V3 stream lifecycle events in `doStream`

#### Mem0 Source in Responses

* Memories are attached as a `source` in `generateText` and `streamText` responses.
* Programmatic access is available via:

  * `providerMetadata.mem0.memories`

### Bug Fixes

#### Async Memory Storage

* `addMemories` is now properly awaited.
* Memories no longer silently fail to store.

#### Prompt Mutation

* Prompt arrays are now cloned before memory context injection.
* Prevents side effects on the caller's array.

#### Null Guard on Content

* `doGenerate` now guards against `null` `content` values returned by upstream providers.

#### Stream Response

* `doStream` now returns the complete `LanguageModelV3StreamResult` object.
* Preserves all V3 fields.

#### Response Normalization

* `getMemories` and `retrieveMemories` now support both response formats:

  * `[...]`
  * `{ results: [...] }`