@mastra/libsql 1.11.1-alpha.0 → 1.12.0-alpha.0

package/CHANGELOG.md

@@ -1,5 +1,73 @@
 # @mastra/libsql
 
+## 1.12.0-alpha.0
+
+### Minor Changes
+
+- Added the `tool_provider_connections` storage domain. Stored agents can now persist per-agent ToolProvider config that round-trips on read/write/create. Runtime connection resolution (per-author, shared, caller-supplied) ships in a follow-up PR. ([#17247](https://github.com/mastra-ai/mastra/pull/17247))
+
+  **What you can do**
+  - Pin a connection on a stored agent's config and have it round-trip on read/write/create.
+  - Persist multiple connections per toolkit so a follow-up runtime PR can fan-out to the right one at execution time.
+
+  **Example**
+
+  ```ts
+  import { LibSQLStore } from '@mastra/libsql';
+
+  const storage = new LibSQLStore({ url: process.env.DATABASE_URL });
+
+  // Persist an OAuth connection that an agent can pin later
+  await storage.toolProviders.upsertConnection({
+    authorId: 'user-123',
+    providerId: 'composio',
+    connectionId: 'auth_abc',
+    toolkit: 'gmail',
+    label: 'Work inbox',
+    scope: 'per-author',
+  });
+
+  // List a user's own connections (admin can omit authorId to list across users)
+  const { items } = await storage.toolProviders.listConnectionsByAuthor({
+    authorId: 'user-123',
+    providerId: 'composio',
+  });
+  ```
+
+  Additive — existing stored agents continue to work unchanged. The runtime that consumes this domain ships in a follow-up PR.
+
+  PR 1 of 3 split from #17224.
+
+### Patch Changes
+
+- Added a public `close()` method to `LibSQLStore` that releases SQLite file handles and cleans up the WAL/shm sidecar files. Previously these handles stayed open until the process exited, which on Windows caused `EBUSY` errors when removing the storage directory after shutdown. `Mastra.shutdown()` now calls `close()` automatically, so you no longer need to reach into private fields. ([#17306](https://github.com/mastra-ai/mastra/pull/17306))
+
+  ```typescript
+  const storage = new LibSQLStore({ id: 'my-store', url: 'file:./dev.db' });
+
+  // Release all file handles, including WAL/shm sidecar files
+  await storage.close();
+
+  // Now safe to remove the storage directory on all platforms, including Windows
+  await fs.rm('./dev.db', { recursive: true, force: true });
+  ```
+
+- Updated dependencies [[`8ace89d`](https://github.com/mastra-ai/mastra/commit/8ace89df77f762e622d3b9f7f65ad7524350d050), [`fa63872`](https://github.com/mastra-ai/mastra/commit/fa6387280954e6b667bec5714b55ba082bc627ff), [`f07b646`](https://github.com/mastra-ai/mastra/commit/f07b64604ab7d25391179790b7fd4823df9e2dff), [`d8838ae`](https://github.com/mastra-ai/mastra/commit/d8838ae80b69780361693d27098f7f6684af12fe), [`40f9297`](https://github.com/mastra-ai/mastra/commit/40f9297003b921c62373d3e8d3a4bda76c9f6de3), [`0f0d1ba`](https://github.com/mastra-ai/mastra/commit/0f0d1ba67bfcb2204e571401662f1eceefc03357), [`8c31bcd`](https://github.com/mastra-ai/mastra/commit/8c31bcdb00e597880d5939b1b7d7566fbe5dacae), [`95b14cd`](https://github.com/mastra-ai/mastra/commit/95b14cdd820e86d97ac05fe568424c513a252e31), [`aa36be2`](https://github.com/mastra-ai/mastra/commit/aa36be23aa513b7dc53cb8ca16b7fab8f20e43ad), [`212c635`](https://github.com/mastra-ai/mastra/commit/212c635203e61d036ab41db8ff86c3893dc795b3), [`d8838ae`](https://github.com/mastra-ai/mastra/commit/d8838ae80b69780361693d27098f7f6684af12fe), [`9aa5a73`](https://github.com/mastra-ai/mastra/commit/9aa5a73e7e110f6e9365eec69364a33d5f03bb56), [`f73c789`](https://github.com/mastra-ai/mastra/commit/f73c789e8ef21561580395d2c410119cab5848c8), [`8bd16da`](https://github.com/mastra-ai/mastra/commit/8bd16da73a4cb874d739373643dbd6a6e7f88684), [`c8630f8`](https://github.com/mastra-ai/mastra/commit/c8630f80d4f40cb5d22e60ab162b618b1907167a), [`47f71dc`](https://github.com/mastra-ai/mastra/commit/47f71dc6fbcbd12d71e21a979e676e20a02bd77d), [`50ceae2`](https://github.com/mastra-ai/mastra/commit/50ceae270878e2f8fb2b2c6c2faab09df0007c8a), [`8cdde58`](https://github.com/mastra-ai/mastra/commit/8cdde5875bbba6702d9df226f2b20232b8d75d6c), [`847ff1e`](https://github.com/mastra-ai/mastra/commit/847ff1e0d94368d94b2e173e4e0908e115568ef3), [`259d409`](https://github.com/mastra-ai/mastra/commit/259d409a514174299dbde1ff5e1121209b3ba850), [`9e16c68`](https://github.com/mastra-ai/mastra/commit/9e16c6818b6485ccb43df28aba6f3a2219d28662), [`cefca33`](https://github.com/mastra-ai/mastra/commit/cefca33ae666e69810c935fedf95a929c173d1d7), [`d00e8c5`](https://github.com/mastra-ai/mastra/commit/d00e8c50daebe5bce5bf2f48bde39c86fc3d2fe4), [`36fa7e2`](https://github.com/mastra-ai/mastra/commit/36fa7e24d14e58a1eb46147097b32f583e5b8775), [`87e9774`](https://github.com/mastra-ai/mastra/commit/87e97741c1e493cd6d62f478eb810b49bda4d57c), [`65a72e7`](https://github.com/mastra-ai/mastra/commit/65a72e70c25eedea8ff985a6624b96be2850236b), [`0f77241`](https://github.com/mastra-ai/mastra/commit/0f7724108806703799a8ba80ad0f09414afd5066), [`92ff509`](https://github.com/mastra-ai/mastra/commit/92ff5098ef8a990438ca038077021a5f7541ec1d), [`3fce5e7`](https://github.com/mastra-ai/mastra/commit/3fce5e70d011d289043e75003ef3336ed4aa43c3), [`a763592`](https://github.com/mastra-ai/mastra/commit/a763592c3db46963ef1011cfe16fe372816e775e), [`80c7737`](https://github.com/mastra-ai/mastra/commit/80c7737e32d7917b5f356957d67c169d01744fd3), [`3f1cf47`](https://github.com/mastra-ai/mastra/commit/3f1cf476f74c1e4cc2df908837e05853a5347e31)]:
+  - @mastra/core@1.38.0-alpha.3
+
+## 1.11.1
+
+### Patch Changes
+
+- Fixed scheduler performance and correctness issues that could cause excessive Postgres CPU and noisy failed runs. ([#16805](https://github.com/mastra-ai/mastra/pull/16805))
+  - Added missing indexes on the schedules tables that the tick loop polls every 10 seconds: `(status, next_fire_at)` on `mastra_schedules` and `(schedule_id, actual_fire_at)` on `mastra_schedule_triggers`. Without these the scheduler performed a full sequential scan on every tick.
+  - The scheduler tick loop is now only started when at least one workflow declares a schedule (or `scheduler.enabled` is set explicitly), so deployments without scheduled workflows no longer poll the database at all.
+  - The scheduler now validates that a schedule's target workflow is still registered before firing it. Schedules whose target workflow has been removed from the Mastra config are skipped for a short grace window and then deleted, so stale rows stop producing failed workflow runs forever.
+  - The scheduler is now lazily initialized inside `startWorkers()`. Accessing `mastra.scheduler` before `startWorkers()` runs throws a descriptive error instead of returning a half-initialized instance.
+
+- Updated dependencies [[`452036a`](https://github.com/mastra-ai/mastra/commit/452036a0d965b4f4c1efd93606e4f03b50b807a5), [`c272d50`](https://github.com/mastra-ai/mastra/commit/c272d50610a54496b6b6d92ccd4d37b333a2613a), [`27fd1b7`](https://github.com/mastra-ai/mastra/commit/27fd1b79ac62eb7694f92587eb7d1be05b59be01), [`5ba7253`](https://github.com/mastra-ai/mastra/commit/5ba7253745c85e8df8012a76d954c640ffa336f7), [`5556cc1`](https://github.com/mastra-ai/mastra/commit/5556cc1befec71518d84f826b3bfe3a079a9daf7), [`f73980d`](https://github.com/mastra-ai/mastra/commit/f73980d651eb5f7f1ab20582de4615a1b6f10fce), [`5499303`](https://github.com/mastra-ai/mastra/commit/54993032c1ebc09642625b78d2014e0cf84a3cae), [`a702009`](https://github.com/mastra-ai/mastra/commit/a702009d3cfaa745120f501e21c783ed4d6a3072), [`9aee493`](https://github.com/mastra-ai/mastra/commit/9aee493ed6089b5133472623dcce49934bf2d509), [`d8692af`](https://github.com/mastra-ai/mastra/commit/d8692afa253028e39cdce2aafa0ac414071a762e), [`1a9cc60`](https://github.com/mastra-ai/mastra/commit/1a9cc6069f9910fc3d59e4953ac8cd95d89ad6f5), [`8cdb86c`](https://github.com/mastra-ai/mastra/commit/8cdb86ceed1137bc2768e147dce85a0692b9fb26), [`8534d79`](https://github.com/mastra-ai/mastra/commit/8534d791fa1cb70fe1c19e2604c4b63cc10dd051), [`eda90c5`](https://github.com/mastra-ai/mastra/commit/eda90c5bfd7de11805ecc9f4552716c895fbaf78), [`a935b0a`](https://github.com/mastra-ai/mastra/commit/a935b0a0977ae3f196b33ec7621f528069c82db0), [`9c88701`](https://github.com/mastra-ai/mastra/commit/9c8870195b41a38dc40b6ba2aa55eda04df8fa69), [`c78f8cd`](https://github.com/mastra-ai/mastra/commit/c78f8cd6222a86e6c60ae5210b6929ad5221b6fb), [`e146aad`](https://github.com/mastra-ai/mastra/commit/e146aadbba66c410ba0e74bac4c50135495cb8dd), [`ac79462`](https://github.com/mastra-ai/mastra/commit/ac79462b98f1062394c45093aa515b0766f27ee2), [`1a0ec78`](https://github.com/mastra-ai/mastra/commit/1a0ec789a26cae443744e9abbd62ed6ee676af39), [`e47bca7`](https://github.com/mastra-ai/mastra/commit/e47bca7b72866d3abd173b9f530ac4318113a8ff), [`afc004f`](https://github.com/mastra-ai/mastra/commit/afc004f5cc7e30697809e7021820b9f5881e6719), [`0031d0f`](https://github.com/mastra-ai/mastra/commit/0031d0f13831d7843ac5d498734a7d92862e2ce3), [`841a222`](https://github.com/mastra-ai/mastra/commit/841a222560d8c19238f8213713f30535cdd82284), [`64c1e0b`](https://github.com/mastra-ai/mastra/commit/64c1e0b35165c96b659818bd0177aa18794ef11f), [`40d83a9`](https://github.com/mastra-ai/mastra/commit/40d83a90d9be31a1b83e04649edb703eb7753e33), [`4e88dc6`](https://github.com/mastra-ai/mastra/commit/4e88dc6b89f154c0eae37221c8126be0c23c569f), [`19018f0`](https://github.com/mastra-ai/mastra/commit/19018f05722af74a5978781a7731a654b26f7f2a), [`19281c7`](https://github.com/mastra-ai/mastra/commit/19281c70424f757219782de16c2699743c5e04d0), [`3498b49`](https://github.com/mastra-ai/mastra/commit/3498b4946be94f4313cd817733589680dcda5278), [`d52b6fe`](https://github.com/mastra-ai/mastra/commit/d52b6fe1c56853eb38864baae0bbfa75cc739ccb), [`408be73`](https://github.com/mastra-ai/mastra/commit/408be73449dfab92b51eab8c6623b6c443debc25), [`359439b`](https://github.com/mastra-ai/mastra/commit/359439bb8c635e048176306828195f8297f50021), [`71a820b`](https://github.com/mastra-ai/mastra/commit/71a820b2353fa1406772c50760a3732058a8b337), [`1698f5e`](https://github.com/mastra-ai/mastra/commit/1698f5ec141d34f22a873efdb145ce3cdf848a5e)]:
+  - @mastra/core@1.36.0
+
 ## 1.11.1-alpha.0
 
 ### Patch Changes

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-libsql
 description: Documentation for @mastra/libsql. Use when working with @mastra/libsql APIs, configuration, or implementation.
 metadata:
   package: "@mastra/libsql"
-  version: "1.11.1-alpha.0"
+  version: "1.12.0-alpha.0"
 ---
 
 ## When to use
@@ -16,6 +16,8 @@ Read the individual reference documents for detailed explanations and code examp
 
 ### Docs
 
+- [Deploying](references/docs-agent-builder-deploying.md) - Swap local Agent Builder primitives for cloud-backed storage, filesystems, sandboxes, an EE license, auth, and a public channel URL for production.
+- [Agent Builder overview](references/docs-agent-builder-overview.md) - Let teammates create, configure, and operate Mastra agents from a browser, with admin-pinned defaults, RBAC, and channel integrations.
 - [Agent approval](references/docs-agents-agent-approval.md) - Learn how to require approvals, suspend tool execution, and automatically resume suspended tools while keeping humans in control of agent workflows.
 - [Agent networks](references/docs-agents-networks.md) - Coordinate multiple agents, workflows, and tools using agent networks for complex, non-deterministic task execution.
 - [Memory processors](references/docs-memory-memory-processors.md) - Learn how to use memory processors in Mastra to filter, trim, and transform messages before they're sent to the language model to manage context window limits.

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.11.1-alpha.0",
+  "version": "1.12.0-alpha.0",
   "package": "@mastra/libsql",
   "exports": {},
   "modules": {}

package/dist/docs/references/docs-agent-builder-deploying.md

@@ -0,0 +1,121 @@
+# Deploying
+
+> **Note:** The Agent Builder is part of the Mastra Enterprise Edition. Production deployments require a valid EE license. [Contact sales](https://mastra.ai/contact) for more information.
+
+Production deployments swap the local primitives in the Quickstart for cloud-backed equivalents. The shape of the `Mastra` and `MastraEditor` config doesn't change — only the providers behind it.
+
+## What a production deployment needs
+
+1. **EE license** — a valid `MASTRA_EE_LICENSE` so the server will start with the Builder enabled.
+2. **Hosted storage** — a shared store for agents, skills, runs, and memory.
+3. **Shared workspace filesystem** — survives across instances; `local` is single-node only.
+4. **Cloud sandbox** — runs agent commands safely; `local` is unsafe in shared environments.
+5. **Auth and RBAC** — gates the Builder UI and `/agent-builder/*` routes.
+6. **Public base URL for channels** — Slack and other channel providers need a reachable URL.
+
+## EE license
+
+Set `MASTRA_EE_LICENSE` in the deployment environment. The server refuses to start when `builder.enabled` is truthy without a valid license. Treat the license key as a secret.
+
+## Storage
+
+Replace the file-backed LibSQL store with a hosted backend. LibSQL Cloud, PostgreSQL, and any other Mastra storage adapter all work.
+
+```typescript
+import { Mastra } from '@mastra/core/mastra'
+import { LibSQLStore } from '@mastra/libsql'
+
+new Mastra({
+  storage: new LibSQLStore({
+    url: process.env.DATABASE_URL!,
+    authToken: process.env.DATABASE_AUTH_TOKEN,
+  }),
+})
+```
+
+## Workspace filesystem and sandbox
+
+`local` filesystem works only on the node that owns the directory. For multi-instance deployments, register cloud filesystem and sandbox providers on `MastraEditor` and reference them by id in the inline workspace config.
+
+**npm**:
+
+```bash
+npm install @mastra/s3 @mastra/e2b
+```
+
+**pnpm**:
+
+```bash
+pnpm add @mastra/s3 @mastra/e2b
+```
+
+**Yarn**:
+
+```bash
+yarn add @mastra/s3 @mastra/e2b
+```
+
+**Bun**:
+
+```bash
+bun add @mastra/s3 @mastra/e2b
+```
+
+```typescript
+import { Mastra } from '@mastra/core/mastra'
+import { MastraEditor } from '@mastra/editor'
+import { s3FilesystemProvider } from '@mastra/s3'
+import { e2bSandboxProvider } from '@mastra/e2b'
+
+new Mastra({
+  editor: new MastraEditor({
+    filesystems: { [s3FilesystemProvider.id]: s3FilesystemProvider },
+    sandboxes: { [e2bSandboxProvider.id]: e2bSandboxProvider },
+    builder: {
+      enabled: true,
+      configuration: {
+        agent: {
+          workspace: {
+            type: 'inline',
+            config: {
+              name: 'builder-workspace',
+              filesystem: {
+                provider: s3FilesystemProvider.id,
+                config: {
+                  bucket: process.env.S3_BUCKET!,
+                  region: process.env.S3_REGION!,
+                },
+              },
+              sandbox: {
+                provider: e2bSandboxProvider.id,
+                config: { apiKey: process.env.E2B_API_KEY! },
+              },
+            },
+          },
+        },
+      },
+    },
+  }),
+})
+```
+
+`S3Filesystem` uses the default AWS credential chain (environment variables, `~/.aws` config, IAM roles, EC2 instance profile). For long-running deployments, use a credential provider function so credentials refresh automatically.
+
+`DockerSandbox` and `VercelSandbox` are alternative cloud sandbox providers — pick whichever matches your runtime.
+
+> **Warning:** A local sandbox can't run commands safely in a shared environment. Always register a cloud sandbox provider and reference it in the workspace config before deploying.
+
+## Auth and RBAC
+
+A production deployment without authentication exposes the Builder to the public internet. Register a `Mastra.server.auth` provider (for example, WorkOS or your own provider) and a `Mastra.server.rbac` provider to gate access.
+
+See [Access control](https://mastra.ai/docs/agent-builder/access-control) for the required role permissions and a WorkOS quickstart.
+
+## Public URL for channels
+
+Slack needs to reach your server through a public URL. Pass `baseUrl` to `SlackProvider` with the deployed URL (no trailing slash). See [Channels](https://mastra.ai/docs/agent-builder/channels) for the full setup.
+
+## Related
+
+- [Access control](https://mastra.ai/docs/agent-builder/access-control) — auth and RBAC setup.
+- [Channels](https://mastra.ai/docs/agent-builder/channels) — Slack `baseUrl` and channel-specific setup.

package/dist/docs/references/docs-agent-builder-overview.md

@@ -0,0 +1,97 @@
+# Agent Builder overview
+
+> **Note:** The Agent Builder is part of the Mastra Enterprise Edition. Production deployments require a valid EE license. [Contact sales](https://mastra.ai/contact) for more information.
+
+The Agent Builder lets you build, configure, and operate Mastra agents all within the UI. It runs inside your Mastra server, persists everything to `Mastra.storage`, and supports multi-tenant agent workflows with RBAC and channel integrations.
+
+- [**Configuration**](https://mastra.ai/docs/agent-builder/configuration): Toggle UI sections and pin admin-controlled defaults for every new agent.
+- [**Model policy**](https://mastra.ai/docs/agent-builder/model-policy): Restrict which providers and models the Builder exposes, and pin a default.
+- [**Memory**](https://mastra.ai/docs/agent-builder/memory): Configure the default memory shape for every Builder-created agent.
+- [**Access control**](https://mastra.ai/docs/agent-builder/access-control): Gate the Builder behind Mastra RBAC roles and permissions.
+- [**Channels**](https://mastra.ai/docs/agent-builder/channels): Connect Builder-created agents to Slack and other channels.
+- [**Skill registries**](https://mastra.ai/docs/agent-builder/skill-registries): Browse and install community skills from opt-in registries.
+- [**Deploying**](https://mastra.ai/docs/agent-builder/deploying): Swap local primitives for cloud-backed storage, filesystems, and sandboxes.
+
+For building agents entirely in code, see the [Agents overview](https://mastra.ai/docs/agents/overview). For editing code-defined agents through Studio, see the [Editor overview](https://mastra.ai/docs/editor/overview).
+
+## Get started
+
+Install `@mastra/editor` alongside a storage adapter:
+
+**npm**:
+
+```bash
+npm install @mastra/editor @mastra/libsql
+```
+
+**pnpm**:
+
+```bash
+pnpm add @mastra/editor @mastra/libsql
+```
+
+**Yarn**:
+
+```bash
+yarn add @mastra/editor @mastra/libsql
+```
+
+**Bun**:
+
+```bash
+bun add @mastra/editor @mastra/libsql
+```
+
+Wire the Agent Builder onto a `Mastra` instance:
+
+```typescript
+import { Mastra } from '@mastra/core/mastra'
+import { MastraEditor } from '@mastra/editor'
+import { createBuilderAgent } from '@mastra/editor/ee'
+import { LibSQLStore } from '@mastra/libsql'
+
+export const mastra = new Mastra({
+  storage: new LibSQLStore({ url: 'file:./mastra.db' }),
+  agents: { builderAgent: createBuilderAgent() },
+  editor: new MastraEditor({
+    builder: {
+      enabled: true,
+      configuration: {
+        agent: {
+          memory: { observationalMemory: true },
+        },
+      },
+    },
+  }),
+})
+```
+
+Start the dev server:
+
+```bash
+npx mastra dev
+```
+
+The Agent Builder is mounted at `http://localhost:4111/agent-builder`.
+
+## Prerequisites
+
+The Agent Builder requires:
+
+- **Storage**: An `@mastra/core` storage adapter on the `Mastra` instance. Agents, memory, and workspace state all persist through `Mastra.storage`.
+- **The Builder agent**: Register a Builder agent created with the `createBuilderAgent()` factory from `@mastra/editor/ee` on `Mastra.agents`. The chat-based editor invokes it through the same `Mastra.getAgent(id)` lookup as any other agent. Without this registration, the chat-based editor returns 404.
+- **`OPENAI_API_KEY`**: The Builder agent created by `createBuilderAgent()` runs on an OpenAI model, so an `OPENAI_API_KEY` environment variable is required.
+
+## Disabling the Builder
+
+Set `enabled: false` to keep the config in place but turn the surface off:
+
+```typescript
+new MastraEditor({
+  builder: {
+    enabled: false,
+  },
+})
+```
+
+Omitting the `builder` field has the same effect.

package/dist/docs/references/docs-agents-agent-approval.md

@@ -86,6 +86,20 @@ for await (const chunk of stream.fullStream) {
 }
 ```
 
+#### Conditional approval with a function
+
+Instead of a boolean, `requireToolApproval` accepts a function that decides per tool call. It receives the `toolName`, the `args` the model passed, the `requestContext`, and the `workspace`. Return `true` to require approval for that call, or `false` to allow it. This lets you gate approval dynamically — for example, only for tools whose name matches a pattern:
+
+```typescript
+const stream = await agent.stream('Clean up old records', {
+  requireToolApproval: ({ toolName }) => /^delete_/.test(toolName),
+})
+```
+
+A tool's own `requireApproval` setting still takes precedence: if a tool defines its own approval rule, that rule decides for that tool and the function above does not override it. If the function throws, the call requires approval (fail-safe).
+
+> **Note:** Function-based `requireToolApproval` is only available on regular `stream()` / `generate()` calls. Durable agents and stored agents persist their options, and a function can't be serialized, so they accept only a boolean. If you pass a function in those contexts it falls back to requiring approval for every tool call.
+
 ### Runtime suspension with `suspend()`
 
 A tool can also pause _during_ its `execute` function by calling `suspend()`. This is useful when the tool starts running and then discovers it needs additional user input or confirmation before it can finish.

package/dist/docs/references/docs-memory-multi-user-threads.md

@@ -65,7 +65,7 @@ const memory = new Memory({
 export const collabAgent = new Agent({
   id: 'collab',
   name: 'CollabAgent',
-  model: 'openai/gpt-5.4-mini',
+  model: '__OPENAI_MODEL_MINI__',
   memory,
   instructions: `
 You are a collaborative document assistant. Multiple users talk to you in the SAME thread.

package/dist/docs/references/docs-memory-semantic-recall.md

@@ -247,7 +247,7 @@ const agent = new Agent({
 })
 ```
 
-The model router automatically handles API key detection from environment variables (`OPENAI_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`, `OPENROUTER_API_KEY`).
+The model router automatically handles API key detection from environment variables (`OPENAI_API_KEY`, `GOOGLE_API_KEY`, `OPENROUTER_API_KEY`). Google models also fall back to `GOOGLE_GENERATIVE_AI_API_KEY`.
 
 ### Using AI SDK Packages
 

package/dist/docs/references/docs-memory-storage.md

@@ -179,7 +179,7 @@ export const agent = new Agent({
   memory: new Memory({
     options: {
       generateTitle: {
-        model: 'openai/gpt-5-mini',
+        model: '__OPENAI_MODEL_MINI__',
         instructions: 'Generate a 1 word title',
       },
     },

package/dist/docs/references/docs-rag-retrieval.md

@@ -472,7 +472,10 @@ const initialResults = await pgVector.query({
 })
 
 // Create a relevance scorer
-const relevanceProvider = new MastraAgentRelevanceScorer('relevance-scorer', 'openai/gpt-5.4')
+const relevanceProvider = new MastraAgentRelevanceScorer(
+  'relevance-scorer',
+  'openai/gpt-5.4',
+)
 
 // Re-rank the results
 const rerankedResults = await rerank({