@mastra/mcp-docs-server 1.1.29-alpha.6 → 1.1.29-alpha.9

package/.docs/docs/agents/channels.md

@@ -72,7 +72,7 @@ Platform webhooks need a public URL to reach your local server. Use a tunnel to
 ngrok http 4111
 
 # cloudflared
-cloudflared tunnel --url http://localhost:4111
+npx cloudflared tunnel --url http://localhost:4111
 ```
 
 Copy the generated URL and use it as the base for your webhook paths (e.g. `https://abc123.ngrok.io/api/agents/support-agent/channels/slack/webhook`).
@@ -164,6 +164,7 @@ By default, only images are sent inline (`inlineMedia: ['image/*']`). Unsupporte
 
 ## Related
 
+- [Guide: Building a Slack assistant](https://mastra.ai/guides/guide/slack-assistant)
 - [Agent overview](https://mastra.ai/docs/agents/overview)
 - [Tool approval](https://mastra.ai/docs/agents/agent-approval)
 - [Channels reference](https://mastra.ai/reference/agents/channels)

package/.docs/docs/evals/custom-scorers.md

@@ -270,6 +270,66 @@ const glutenCheckerScorer = createScorer({...})
 })
 ```
 
+## Input filtering
+
+Agent conversations can contain hundreds of messages with tool calls, data parts, and system metadata. Most scorers only need a subset of this data. The `prepareRun` option transforms the run data before the scorer pipeline executes, reducing noise and keeping scorers focused.
+
+### Declarative filtering with `filterRun()`
+
+The [`filterRun()`](https://mastra.ai/reference/evals/filter-run) utility creates a `prepareRun` function from declarative options:
+
+```typescript
+import { createScorer, filterRun } from '@mastra/core/evals'
+
+const toolScorer = createScorer({
+  id: 'tool-quality',
+  description: 'Evaluates tool usage quality',
+  type: 'agent',
+  prepareRun: filterRun({
+    partTypes: ['tool-invocation', 'text'],
+    maxRememberedMessages: 20,
+  }),
+}).generateScore(({ run }) => {
+  // run.input.rememberedMessages has only tool and text messages, max 20
+  return 1
+})
+```
+
+Common options include:
+
+- `partTypes`: Keep only messages with matching part types (e.g., `'tool-invocation'`, `'text'`, `'reasoning'`)
+- `toolNames`: Keep only messages involving specific tools (e.g., `['write_file', 'execute_command']`)
+- `maxRememberedMessages`: Limit context window size
+- `dropRequestContext`, `dropGroundTruth`, `dropExpectedTrajectory`: Remove unused fields
+
+See the [`filterRun()` reference](https://mastra.ai/reference/evals/filter-run) for the full list of options.
+
+### Custom `prepareRun` functions
+
+For logic that `filterRun()` doesn't cover, write a `prepareRun` function directly:
+
+```typescript
+import { createScorer } from '@mastra/core/evals'
+
+const customScorer = createScorer({
+  id: 'recent-output',
+  description: 'Scores only the last response',
+  type: 'agent',
+  prepareRun: (run) => ({
+    ...run,
+    output: run.output.slice(-1), // Keep only the last message
+    requestContext: undefined,
+  }),
+})
+.generateScore(({ run }) => {
+  return run.output.length > 0 ? 1 : 0
+})
+```
+
+The `prepareRun` function can also be async.
+
+> **System messages are always preserved:** `filterRun()` never filters `systemMessages` or `taggedSystemMessages`. These contain agent instructions and are critical context for scoring.
+
 ## Example: Create a custom scorer
 
 A custom scorer in Mastra uses `createScorer` with four core components:

package/.docs/docs/workspace/filesystem.md

@@ -21,9 +21,10 @@ Available providers:
 - [`LocalFilesystem`](https://mastra.ai/reference/workspace/local-filesystem): Stores files in a directory on disk
 - [`S3Filesystem`](https://mastra.ai/reference/workspace/s3-filesystem): Stores files in Amazon S3 or S3-compatible storage (R2, MinIO)
 - [`GCSFilesystem`](https://mastra.ai/reference/workspace/gcs-filesystem): Stores files in Google Cloud Storage
+- [`AzureBlobFilesystem`](https://mastra.ai/reference/workspace/azure-blob-filesystem): Stores files in Azure Blob Storage
 - [`AgentFSFilesystem`](https://mastra.ai/reference/workspace/agentfs-filesystem): Stores files in a Turso/SQLite database via AgentFS
 
-> **Tip:** `LocalFilesystem` is the simplest way to get started as it requires no external services. For cloud storage, use `S3Filesystem` or `GCSFilesystem`. For database-backed storage without external services, use `AgentFSFilesystem`.
+> **Tip:** `LocalFilesystem` is the simplest way to get started as it requires no external services. For cloud storage, use `S3Filesystem`, `GCSFilesystem`, or `AzureBlobFilesystem`. For database-backed storage without external services, use `AgentFSFilesystem`.
 
 ## Basic usage
 
@@ -219,6 +220,7 @@ When you configure a filesystem on a workspace, agents receive tools for reading
 - [LocalFilesystem reference](https://mastra.ai/reference/workspace/local-filesystem)
 - [S3Filesystem reference](https://mastra.ai/reference/workspace/s3-filesystem)
 - [GCSFilesystem reference](https://mastra.ai/reference/workspace/gcs-filesystem)
+- [AzureBlobFilesystem reference](https://mastra.ai/reference/workspace/azure-blob-filesystem)
 - [AgentFSFilesystem reference](https://mastra.ai/reference/workspace/agentfs-filesystem)
 - [Workspace overview](https://mastra.ai/docs/workspace/overview)
 - [Sandbox](https://mastra.ai/docs/workspace/sandbox)

package/.docs/guides/guide/slack-assistant.md

@@ -0,0 +1,191 @@
+# Building a Slack assistant
+
+In this guide, you'll build a Mastra agent that responds to messages and mentions on Slack. You'll learn how to configure a channel adapter, set up a Slack app with the right permissions, connect it to your agent via a webhook, and test the interaction.
+
+## Prerequisites
+
+- Node.js `v22.13.0` or later installed
+- An API key from a supported [Model Provider](https://mastra.ai/models)
+- An existing Mastra project. Follow the [installation guide](https://mastra.ai/guides/getting-started/quickstart) if needed.
+- A [Slack workspace](https://slack.com/) where you can create apps
+
+## Create the agent
+
+Install the Slack adapter:
+
+**npm**:
+
+```bash
+npm install @chat-adapter/slack
+```
+
+**pnpm**:
+
+```bash
+pnpm add @chat-adapter/slack
+```
+
+**Yarn**:
+
+```bash
+yarn add @chat-adapter/slack
+```
+
+**Bun**:
+
+```bash
+bun add @chat-adapter/slack
+```
+
+Create a new file `src/mastra/agents/slack-agent.ts` and define your agent:
+
+```ts
+import { Agent } from '@mastra/core/agent'
+import { createSlackAdapter } from '@chat-adapter/slack'
+
+export const slackAgent = new Agent({
+  id: 'slack-agent',
+  name: 'Slack Agent',
+  instructions:
+    'You are a helpful assistant. Answer questions, help with tasks, and have natural conversations.',
+  model: 'anthropic/claude-opus-4-6',
+  channels: {
+    adapters: {
+      slack: createSlackAdapter(),
+    },
+  },
+})
+```
+
+The `channels` property tells Mastra to generate a webhook endpoint for each adapter. In this case, the Slack adapter handles event verification, signature validation, and message formatting automatically.
+
+Register the agent in your `src/mastra/index.ts` file:
+
+```ts
+import { Mastra } from '@mastra/core'
+import { slackAgent } from './agents/slack-agent'
+
+export const mastra = new Mastra({
+  agents: { slackAgent },
+})
+```
+
+## Create a Slack app
+
+You need a Slack app to connect your agent to a workspace.
+
+Go to <https://api.slack.com/apps> and select **Create New App** > **From scratch**. Give it a name and select your workspace.
+
+Navigate to **OAuth & Permissions** and scroll to **Bot Token Scopes**. Add the following scopes:
+
+- `app_mentions:read`
+- `channels:history`
+- `channels:read`
+- `chat:write`
+- `users:read`
+
+At the top of **OAuth & Permissions**, select **Install to Workspace**. Copy the **Bot User OAuth Token** (`xoxb-...`).
+
+Go to **Basic Information** > **App Credentials** and copy the **Signing Secret** (e.g. `c3a4...`).
+
+Ensure **Socket Mode** is turned **off** under **Settings** > **Socket Mode**.
+
+Add the credentials to your `.env` file:
+
+```bash
+SLACK_SIGNING_SECRET=your-signing-secret
+SLACK_BOT_TOKEN=xoxb-your-bot-token
+```
+
+The adapter reads these environment variables by default. See the [Chat SDK Slack adapter docs](https://chat-sdk.dev/adapters/slack) for more details.
+
+## Connect the webhook
+
+Slack delivers events to your agent via a webhook. Mastra generates this endpoint automatically for each channel adapter.
+
+Start the dev server:
+
+**npm**:
+
+```bash
+npm run dev
+```
+
+**pnpm**:
+
+```bash
+pnpm run dev
+```
+
+**Yarn**:
+
+```bash
+yarn dev
+```
+
+**Bun**:
+
+```bash
+bun run dev
+```
+
+During local development, Slack needs a public URL to reach your local server. Open a new terminal and start a tunnel:
+
+```bash
+npx cloudflared tunnel --url http://localhost:4111
+```
+
+This outputs a temporary public URL like `https://triple-arms-solutions-kit.trycloudflare.com`. The URL changes each time you restart the tunnel.
+
+In your Slack app settings, go to **Event Subscriptions** and toggle **Enable Events** to **On**.
+
+Set the **Request URL** to your tunnel URL with the agent webhook path:
+
+```text
+https://<your-tunnel-url>/api/agents/slack-agent/channels/slack/webhook
+```
+
+Slack sends a verification request. If your dev server is running, it responds with a green checkmark.
+
+Under **Subscribe to bot events**, add:
+
+- `app_mention`
+- `message.channels`
+
+Select **Save Changes**. Slack requires you to reinstall the app after changing event subscriptions. Go to **OAuth & Permissions** and select **Reinstall to Workspace** to apply the updated permissions.
+
+> **Note:** The tunnel URL is for local development only. When you [deploy your application](https://mastra.ai/docs/deployment/overview), update the **Request URL** in your Slack app's **Event Subscriptions** to your production URL (e.g. `https://your-app.example.com/api/agents/slack-agent/channels/slack/webhook`).
+
+## Test the agent
+
+Before testing with Slack, you can refine your agent's behavior in [Studio](https://mastra.ai/docs/studio/overview). Open <http://localhost:4111/> to chat with your agent directly, adjust its instructions, and inspect traces to see how responses are generated.
+
+Once you're happy with the agent's responses, test the Slack integration. Invite the bot to a channel in Slack:
+
+```text
+/invite @your-bot-name
+```
+
+Mention the bot in the channel:
+
+```text
+@your-bot-name What can you help me with?
+```
+
+The agent responds in the thread. Output may vary depending on the model and instructions.
+
+## Next steps
+
+You can extend this agent to:
+
+- [Deploy your application](https://mastra.ai/docs/deployment/overview) and update the Slack **Request URL** to your production endpoint
+- Add more adapters (Discord, Telegram) to the same agent so it responds on multiple platforms
+- Configure [multimodal content](https://mastra.ai/docs/agents/channels) to let your agent process images, video, and audio shared in chat
+- Add [tools](https://mastra.ai/docs/agents/using-tools) to give the agent access to external APIs and data
+
+Learn more:
+
+- [Channels overview](https://mastra.ai/docs/agents/channels)
+- [Studio](https://mastra.ai/docs/studio/overview)
+- [Deployment overview](https://mastra.ai/docs/deployment/overview)
+- [Chat SDK adapter docs](https://chat-sdk.dev)

package/.docs/models/gateways/openrouter.md

@@ -1,6 +1,6 @@
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 178 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 179 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -73,6 +73,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-2.5-pro-preview-06-05`                           |
 | `google/gemini-3-flash-preview`                                 |
 | `google/gemini-3-pro-preview`                                   |
+| `google/gemini-3.1-flash-image-preview`                         |
 | `google/gemini-3.1-flash-lite-preview`                          |
 | `google/gemini-3.1-pro-preview`                                 |
 | `google/gemini-3.1-pro-preview-customtools`                     |

package/.docs/models/index.md

@@ -1,6 +1,6 @@
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3743 models from 105 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3757 models from 106 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/abliteration-ai.md

@@ -0,0 +1,71 @@
+# ![abliteration.ai logo](https://models.dev/logos/abliteration-ai.svg)abliteration.ai
+
+Access 1 abliteration.ai model through Mastra's model router. Authentication is handled automatically using the `ABLIT_KEY` environment variable.
+
+Learn more in the [abliteration.ai documentation](https://docs.abliteration.ai/models).
+
+```bash
+ABLIT_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "abliteration-ai/abliterated-model"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [abliteration.ai documentation](https://docs.abliteration.ai/models) for details.
+
+## Models
+
+| Model                               | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ----------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `abliteration-ai/abliterated-model` | 150K    |       |           |       |       |       | $3         | $3          |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.abliteration.ai/v1",
+    id: "abliteration-ai/abliterated-model",
+    apiKey: process.env.ABLIT_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic model selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "abliteration-ai/abliterated-model"
+      : "abliteration-ai/abliterated-model";
+  }
+});
+```

package/.docs/models/providers/alibaba-cn.md

@@ -1,6 +1,6 @@
 # ![Alibaba (China) logo](https://models.dev/logos/alibaba-cn.svg)Alibaba (China)
 
-Access 78 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
+Access 80 Alibaba (China) models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
 
 Learn more in the [Alibaba (China) documentation](https://www.alibabacloud.com/help/en/model-studio/models).
 
@@ -45,6 +45,8 @@ for await (const chunk of stream) {
 | `alibaba-cn/deepseek-v3`                        | 66K     |       |           |       |       |       | $0.29      | $1          |
 | `alibaba-cn/deepseek-v3-1`                      | 131K    |       |           |       |       |       | $0.57      | $2          |
 | `alibaba-cn/deepseek-v3-2-exp`                  | 131K    |       |           |       |       |       | $0.29      | $0.43       |
+| `alibaba-cn/deepseek-v4-flash`                  | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
+| `alibaba-cn/deepseek-v4-pro`                    | 1.0M    |       |           |       |       |       | $2         | $3          |
 | `alibaba-cn/glm-5`                              | 203K    |       |           |       |       |       | $0.86      | $3          |
 | `alibaba-cn/glm-5.1`                            | 203K    |       |           |       |       |       | $0.87      | $3          |
 | `alibaba-cn/kimi-k2-thinking`                   | 262K    |       |           |       |       |       | $0.57      | $2          |

package/.docs/models/providers/alibaba.md

@@ -1,6 +1,6 @@
 # ![Alibaba logo](https://models.dev/logos/alibaba.svg)Alibaba
 
-Access 42 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
+Access 47 Alibaba models through Mastra's model router. Authentication is handled automatically using the `DASHSCOPE_API_KEY` environment variable.
 
 Learn more in the [Alibaba documentation](https://www.alibabacloud.com/help/en/model-studio/models).
 
@@ -72,8 +72,13 @@ for await (const chunk of stream) {
 | `alibaba/qwen3-vl-235b-a22b`                 | 131K    |       |           |       |       |       | $0.70      | $3          |
 | `alibaba/qwen3-vl-30b-a3b`                   | 131K    |       |           |       |       |       | $0.20      | $0.80       |
 | `alibaba/qwen3-vl-plus`                      | 262K    |       |           |       |       |       | $0.20      | $2          |
+| `alibaba/qwen3.5-122b-a10b`                  | 262K    |       |           |       |       |       | $0.40      | $3          |
+| `alibaba/qwen3.5-27b`                        | 262K    |       |           |       |       |       | $0.30      | $2          |
+| `alibaba/qwen3.5-35b-a3b`                    | 262K    |       |           |       |       |       | $0.25      | $2          |
 | `alibaba/qwen3.5-397b-a17b`                  | 262K    |       |           |       |       |       | $0.60      | $4          |
 | `alibaba/qwen3.5-plus`                       | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `alibaba/qwen3.6-27b`                        | 262K    |       |           |       |       |       | $0.60      | $4          |
+| `alibaba/qwen3.6-35b-a3b`                    | 262K    |       |           |       |       |       | $0.25      | $1          |
 | `alibaba/qwen3.6-plus`                       | 1.0M    |       |           |       |       |       | $0.28      | $2          |
 | `alibaba/qwq-plus`                           | 131K    |       |           |       |       |       | $0.80      | $2          |
 

package/.docs/models/providers/huggingface.md

@@ -1,6 +1,6 @@
 # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
 
-Access 23 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
+Access 24 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
 
 Learn more in the [Hugging Face documentation](https://huggingface.co).
 
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
 | ------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `huggingface/deepseek-ai/DeepSeek-R1-0528`        | 164K    |       |           |       |       |       | $3         | $5          |
 | `huggingface/deepseek-ai/DeepSeek-V3.2`           | 164K    |       |           |       |       |       | $0.28      | $0.40       |
+| `huggingface/deepseek-ai/DeepSeek-V4-Pro`         | 1.0M    |       |           |       |       |       | $2         | $3          |
 | `huggingface/MiniMaxAI/MiniMax-M2.1`              | 205K    |       |           |       |       |       | $0.30      | $1          |
 | `huggingface/MiniMaxAI/MiniMax-M2.5`              | 205K    |       |           |       |       |       | $0.30      | $1          |
 | `huggingface/MiniMaxAI/MiniMax-M2.7`              | 205K    |       |           |       |       |       | $0.30      | $1          |

package/.docs/models/providers/ollama-cloud.md

@@ -1,6 +1,6 @@
 # ![Ollama Cloud logo](https://models.dev/logos/ollama-cloud.svg)Ollama Cloud
 
-Access 37 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
+Access 39 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the `OLLAMA_API_KEY` environment variable.
 
 Learn more in the [Ollama Cloud documentation](https://docs.ollama.com/cloud).
 
@@ -37,6 +37,8 @@ for await (const chunk of stream) {
 | `ollama-cloud/cogito-2.1:671b`        | 164K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/deepseek-v3.1:671b`     | 164K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/deepseek-v3.2`          | 164K    |       |           |       |       |       | —          | —           |
+| `ollama-cloud/deepseek-v4-flash`      | 1.0M    |       |           |       |       |       | —          | —           |
+| `ollama-cloud/deepseek-v4-pro`        | 1.0M    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/devstral-2:123b`        | 262K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/devstral-small-2:24b`   | 262K    |       |           |       |       |       | —          | —           |
 | `ollama-cloud/gemini-3-flash-preview` | 1.0M    |       |           |       |       |       | —          | —           |

package/.docs/models/providers/opencode-go.md

@@ -36,8 +36,8 @@ for await (const chunk of stream) {
 | ------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `opencode-go/deepseek-v4-flash` | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `opencode-go/deepseek-v4-pro`   | 1.0M    |       |           |       |       |       | $2         | $3          |
-| `opencode-go/glm-5`             | 205K    |       |           |       |       |       | $1         | $3          |
-| `opencode-go/glm-5.1`           | 205K    |       |           |       |       |       | $1         | $4          |
+| `opencode-go/glm-5`             | 203K    |       |           |       |       |       | $1         | $3          |
+| `opencode-go/glm-5.1`           | 203K    |       |           |       |       |       | $1         | $4          |
 | `opencode-go/kimi-k2.5`         | 262K    |       |           |       |       |       | $0.60      | $3          |
 | `opencode-go/kimi-k2.6`         | 262K    |       |           |       |       |       | $0.32      | $1          |
 | `opencode-go/mimo-v2-omni`      | 262K    |       |           |       |       |       | $0.40      | $2          |

package/.docs/models/providers/poe.md

@@ -1,6 +1,6 @@
 # ![Poe logo](https://models.dev/logos/poe.svg)Poe
 
-Access 119 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
+Access 121 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
 
 Learn more in the [Poe documentation](https://creator.poe.com/docs/external-applications/openai-compatible-api).
 
@@ -123,6 +123,8 @@ for await (const chunk of stream) {
 | `poe/openai/gpt-5.4-mini`              | 400K    |       |           |       |       |       | $0.68      | $4          |
 | `poe/openai/gpt-5.4-nano`              | 400K    |       |           |       |       |       | $0.18      | $1          |
 | `poe/openai/gpt-5.4-pro`               | 1.1M    |       |           |       |       |       | $27        | $160        |
+| `poe/openai/gpt-5.5`                   | 400K    |       |           |       |       |       | $5         | $27         |
+| `poe/openai/gpt-5.5-pro`               | 400K    |       |           |       |       |       | $27        | $164        |
 | `poe/openai/gpt-image-1`               | 128K    |       |           |       |       |       | —          | —           |
 | `poe/openai/gpt-image-1-mini`          | —       |       |           |       |       |       | —          | —           |
 | `poe/openai/gpt-image-1.5`             | 128K    |       |           |       |       |       | —          | —           |

package/.docs/models/providers.md

@@ -11,6 +11,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
 - [xAI](https://mastra.ai/models/providers/xai)
 - [302.AI](https://mastra.ai/models/providers/302ai)
 - [Abacus](https://mastra.ai/models/providers/abacus)
+- [abliteration.ai](https://mastra.ai/models/providers/abliteration-ai)
 - [Alibaba](https://mastra.ai/models/providers/alibaba)
 - [Alibaba (China)](https://mastra.ai/models/providers/alibaba-cn)
 - [Alibaba Coding Plan](https://mastra.ai/models/providers/alibaba-coding-plan)

package/.docs/reference/evals/create-scorer.md

@@ -51,6 +51,8 @@ const scorer = createScorer({
 
 **type** (`string`): Type specification for input/output. Use 'agent' for automatic agent types. For custom types, use the generic approach instead.
 
+**prepareRun** (`(run: ScorerRun) => ScorerRun | Promise<ScorerRun>`): Transform the scorer run data before the pipeline executes. Use this to filter messages, limit context size, or drop fields the scorer doesn't need. The \[\`filterRun()\`]\(/reference/evals/filter-run) utility creates this function from declarative options. Can be async.
+
 This function returns a scorer builder that you can chain step methods onto. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
 
 The judge only runs for steps defined as **prompt objects** (`preprocess`, `analyze`, `generateScore`, `generateReason` in prompt mode). If you use function steps only, the judge is never called and there is no LLM output to inspect. In that case, any score/reason must be produced by your functions.

package/.docs/reference/evals/filter-run.md

@@ -0,0 +1,117 @@
+# filterRun()
+
+Creates a `prepareRun` function from declarative options. Pass the result to `createScorer()` to filter messages, limit context size, and drop unnecessary fields before the scorer pipeline runs.
+
+Use [`filterRun()`](#usage-example) for declarative filtering. Write a custom `prepareRun` function directly when you need imperative logic that `filterRun()` doesn't cover. See [Custom scorers: input filtering](https://mastra.ai/docs/evals/custom-scorers) for more.
+
+## Usage example
+
+The following example creates a scorer that only sees tool invocations and text messages, limited to the 20 most recent context messages:
+
+```typescript
+import { createScorer, filterRun } from '@mastra/core/evals'
+
+const toolScorer = createScorer({
+  id: 'tool-usage',
+  description: 'Evaluates tool usage patterns',
+  type: 'agent',
+  prepareRun: filterRun({
+    partTypes: ['tool-invocation', 'text'],
+    maxRememberedMessages: 20,
+  }),
+}).generateScore(({ run }) => {
+  // run.input.rememberedMessages contains only tool and text messages
+  // run.output contains only tool and text messages
+  return 1
+})
+```
+
+### Filter by tool name
+
+Keep only messages involving specific tools:
+
+```typescript
+import { createScorer, filterRun } from '@mastra/core/evals'
+
+const fileEditScorer = createScorer({
+  id: 'file-edit-quality',
+  description: 'Evaluates file editing patterns',
+  type: 'agent',
+  prepareRun: filterRun({
+    toolNames: ['write_file', 'string_replace_lsp', 'view'],
+  }),
+}).generateScore(({ run }) => {
+  // Only messages with these tool calls remain
+  return 1
+})
+```
+
+### Drop fields
+
+Remove fields the scorer doesn't need:
+
+```typescript
+import { createScorer, filterRun } from '@mastra/core/evals'
+
+const simpleScorer = createScorer({
+  id: 'response-length',
+  description: 'Checks response length',
+  type: 'agent',
+  prepareRun: filterRun({
+    dropRequestContext: true,
+    dropExpectedTrajectory: true,
+    dropGroundTruth: true,
+    maxOutputMessages: 5,
+  }),
+}).generateScore(({ run }) => {
+  return run.output.length > 0 ? 1 : 0
+})
+```
+
+## Parameters
+
+**options** (`FilterRunOptions`): Configuration object that controls what data the scorer receives.
+
+**options.partTypes** (`MastraPartType[]`): Keep only messages whose parts match these types. Each entry is prefix-matched against the message part's type. Plain text messages (no tool invocations) are always kept unless explicitly excluded. System messages and tagged system messages are never filtered.
+
+**options.toolNames** (`string[]`): Keep only tool-invocation messages for these specific tools. Each entry is prefix-matched against the tool name. Non-tool messages (text, data) are unaffected.
+
+**options.maxRememberedMessages** (`number`): Maximum number of messages to keep in remembered messages (context). Takes from the end (most recent). Applied after type and tool filtering.
+
+**options.maxOutputMessages** (`number`): Maximum number of messages to keep in the output. Takes from the end. Applied after type and tool filtering.
+
+**options.dropRequestContext** (`boolean`): Remove request context from the run entirely.
+
+**options.dropExpectedTrajectory** (`boolean`): Remove expected trajectory from the run.
+
+**options.dropGroundTruth** (`boolean`): Remove ground truth from the run.
+
+**Returns:** `(run: ScorerRun) => ScorerRun` — A function suitable for the `prepareRun` option on [`createScorer()`](https://mastra.ai/reference/evals/create-scorer).
+
+## Part types
+
+The `partTypes` option accepts `MastraPartType` values. Each value is prefix-matched, so `'data-'` matches all data part types.
+
+| Type                | Description                                  |
+| ------------------- | -------------------------------------------- |
+| `'text'`            | Text content parts                           |
+| `'tool-invocation'` | Tool call and result parts                   |
+| `'reasoning'`       | Chain-of-thought reasoning parts             |
+| `'step-start'`      | Step marker parts                            |
+| `'image'`           | Image parts                                  |
+| `'file'`            | File parts                                   |
+| `'source'`          | Source reference parts                       |
+| `'source-document'` | Source document parts                        |
+| `'data-'`           | All data parts (matches any `data-*` prefix) |
+| `'data-om-'`        | Observational memory data parts              |
+| `'data-workspace-'` | Workspace data parts                         |
+| `'data-sandbox-'`   | Sandbox data parts                           |
+| `'data-tool-'`      | Tool-related data parts                      |
+
+## Filtering behavior
+
+- **Part type filtering** applies to both `input.rememberedMessages` and `output` when they contain agent message arrays.
+- **Tool name filtering** only affects messages that contain tool invocations. Text-only messages pass through.
+- **System messages** (`systemMessages`, `taggedSystemMessages`) are never filtered, regardless of `partTypes` or `toolNames`.
+- **Message limits** (`maxRememberedMessages`, `maxOutputMessages`) apply after type and tool filtering, taking the most recent messages.
+- When both `partTypes` and `toolNames` are set, a message must satisfy both filters to be kept.

package/.docs/reference/index.md

@@ -96,6 +96,7 @@ The Reference section provides documentation of Mastra's API, including paramete
 - [MastraEditor Class](https://mastra.ai/reference/editor/mastra-editor)
 - [ToolProvider](https://mastra.ai/reference/editor/tool-provider)
 - [createScorer()](https://mastra.ai/reference/evals/create-scorer)
+- [filterRun()](https://mastra.ai/reference/evals/filter-run)
 - [MastraScorer](https://mastra.ai/reference/evals/mastra-scorer)
 - [runEvals()](https://mastra.ai/reference/evals/run-evals)
 - [Scorer Utils](https://mastra.ai/reference/evals/scorer-utils)
@@ -285,6 +286,7 @@ The Reference section provides documentation of Mastra's API, including paramete
 - [.startAsync()](https://mastra.ai/reference/workflows/run-methods/startAsync)
 - [.timeTravel()](https://mastra.ai/reference/workflows/run-methods/timeTravel)
 - [AgentFSFilesystem](https://mastra.ai/reference/workspace/agentfs-filesystem)
+- [AzureBlobFilesystem](https://mastra.ai/reference/workspace/azure-blob-filesystem)
 - [BlaxelSandbox](https://mastra.ai/reference/workspace/blaxel-sandbox)
 - [DaytonaSandbox](https://mastra.ai/reference/workspace/daytona-sandbox)
 - [DockerSandbox](https://mastra.ai/reference/workspace/docker-sandbox)

package/.docs/reference/workspace/azure-blob-filesystem.md

@@ -0,0 +1,219 @@
+# AzureBlobFilesystem
+
+Stores files in Azure Blob Storage containers.
+
+> **Info:** For interface details, see [WorkspaceFilesystem Interface](https://mastra.ai/reference/workspace/filesystem).
+
+## Installation
+
+**npm**:
+
+```bash
+npm install @mastra/azure
+```
+
+**pnpm**:
+
+```bash
+pnpm add @mastra/azure
+```
+
+**Yarn**:
+
+```bash
+yarn add @mastra/azure
+```
+
+**Bun**:
+
+```bash
+bun add @mastra/azure
+```
+
+## Usage
+
+Add an `AzureBlobFilesystem` to a workspace and assign it to an agent:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { Workspace } from '@mastra/core/workspace'
+import { AzureBlobFilesystem } from '@mastra/azure/blob'
+
+const workspace = new Workspace({
+  filesystem: new AzureBlobFilesystem({
+    container: 'my-container',
+    connectionString: process.env.AZURE_STORAGE_CONNECTION_STRING,
+  }),
+})
+
+const agent = new Agent({
+  name: 'file-agent',
+  model: 'anthropic/claude-opus-4-6',
+  workspace,
+})
+```
+
+### Account key
+
+Use an account name and account key when you do not want to pass a full connection string:
+
+```typescript
+import { AzureBlobFilesystem } from '@mastra/azure/blob'
+
+const filesystem = new AzureBlobFilesystem({
+  container: 'my-container',
+  accountName: process.env.AZURE_STORAGE_ACCOUNT_NAME,
+  accountKey: process.env.AZURE_STORAGE_ACCOUNT_KEY,
+})
+```
+
+### Shared access signature token
+
+Use a shared access signature (SAS) token with either `accountName` or `endpoint`:
+
+```typescript
+import { AzureBlobFilesystem } from '@mastra/azure/blob'
+
+const filesystem = new AzureBlobFilesystem({
+  container: 'my-container',
+  accountName: process.env.AZURE_STORAGE_ACCOUNT_NAME,
+  sasToken: process.env.AZURE_STORAGE_SAS_TOKEN,
+})
+```
+
+### DefaultAzureCredential
+
+Use `DefaultAzureCredential` when your environment provides Azure identity credentials:
+
+```typescript
+import { AzureBlobFilesystem } from '@mastra/azure/blob'
+
+const filesystem = new AzureBlobFilesystem({
+  container: 'my-container',
+  accountName: process.env.AZURE_STORAGE_ACCOUNT_NAME,
+  useDefaultCredential: true,
+})
+```
+
+Install `@azure/identity` when you use `DefaultAzureCredential`:
+
+**npm**:
+
+```bash
+npm install @azure/identity
+```
+
+**pnpm**:
+
+```bash
+pnpm add @azure/identity
+```
+
+**Yarn**:
+
+```bash
+yarn add @azure/identity
+```
+
+**Bun**:
+
+```bash
+bun add @azure/identity
+```
+
+## Constructor parameters
+
+**container** (`string`): Azure Blob Storage container name
+
+**connectionString** (`string`): Full Azure Storage connection string. Takes priority over other authentication options.
+
+**accountName** (`string`): Azure Storage account name. Required unless you use connectionString or endpoint.
+
+**accountKey** (`string`): Azure Storage account key.
+
+**sasToken** (`string`): Shared access signature token. Requires accountName or endpoint.
+
+**useDefaultCredential** (`boolean`): Use DefaultAzureCredential from @azure/identity. (Default: `false`)
+
+**endpoint** (`string`): Custom Blob service endpoint URL. Used for local development with Azurite.
+
+**prefix** (`string`): Optional prefix for all keys (acts like a subdirectory).
+
+**id** (`string`): Unique identifier for this filesystem instance. (Default: `Auto-generated`)
+
+**displayName** (`string`): Human-friendly display name for the UI.
+
+**icon** (`FilesystemIcon`): Icon identifier for the UI.
+
+**description** (`string`): Short description of this filesystem for the UI.
+
+**readOnly** (`boolean`): When true, all write operations are blocked. (Default: `false`)
+
+## Properties
+
+**id** (`string`): Filesystem instance identifier.
+
+**name** (`string`): Provider name ('AzureBlobFilesystem').
+
+**provider** (`string`): Provider identifier ('azure-blob').
+
+**readOnly** (`boolean | undefined`): Whether the filesystem is in read-only mode.
+
+## Methods
+
+AzureBlobFilesystem implements the [WorkspaceFilesystem interface](https://mastra.ai/reference/workspace/filesystem), providing all standard filesystem methods:
+
+- `readFile(path, options?)` - Read file contents
+- `writeFile(path, content, options?)` - Write content to a file
+- `appendFile(path, content)` - Append content to a file
+- `deleteFile(path, options?)` - Delete a file
+- `copyFile(src, dest, options?)` - Copy a file
+- `moveFile(src, dest, options?)` - Move or rename a file
+- `mkdir(path, options?)` - Create a directory
+- `rmdir(path, options?)` - Remove a directory
+- `readdir(path, options?)` - List directory contents
+- `exists(path)` - Check if a path exists
+- `stat(path)` - Get file or directory metadata
+
+### `init()`
+
+Initialize the filesystem. Verifies container access and credentials.
+
+```typescript
+await filesystem.init()
+```
+
+### `getInfo()`
+
+Returns metadata about this filesystem instance.
+
+```typescript
+const info = filesystem.getInfo()
+// { id: '...', name: 'AzureBlobFilesystem', provider: 'azure-blob', status: 'ready' }
+```
+
+### `getContainer()`
+
+Returns the underlying Azure Blob Storage `ContainerClient`.
+
+```typescript
+const container = await filesystem.getContainer()
+```
+
+### `getMountConfig()`
+
+Returns the mount configuration for sandbox providers that support Azure Blob filesystem mounts.
+
+```typescript
+const config = filesystem.getMountConfig()
+// { type: 'azure-blob', container: 'my-container', ... }
+```
+
+> **Note:** Azure Blob sandbox mounting depends on sandbox support for `azure-blob` mount configs. Use `filesystem` for direct workspace file operations when your sandbox provider does not support Azure Blob mounts.
+
+## Related
+
+- [WorkspaceFilesystem interface](https://mastra.ai/reference/workspace/filesystem)
+- [S3Filesystem reference](https://mastra.ai/reference/workspace/s3-filesystem)
+- [GCSFilesystem reference](https://mastra.ai/reference/workspace/gcs-filesystem)
+- [Workspace overview](https://mastra.ai/docs/workspace/overview)

package/.docs/reference/workspace/gcs-filesystem.md

@@ -190,5 +190,6 @@ See [E2BSandbox reference](https://mastra.ai/reference/workspace/e2b-sandbox) fo
 
 - [WorkspaceFilesystem interface](https://mastra.ai/reference/workspace/filesystem)
 - [S3Filesystem reference](https://mastra.ai/reference/workspace/s3-filesystem)
+- [AzureBlobFilesystem reference](https://mastra.ai/reference/workspace/azure-blob-filesystem)
 - [E2BSandbox reference](https://mastra.ai/reference/workspace/e2b-sandbox)
 - [Workspace overview](https://mastra.ai/docs/workspace/overview)

package/.docs/reference/workspace/s3-filesystem.md

@@ -193,5 +193,6 @@ See [E2BSandbox reference](https://mastra.ai/reference/workspace/e2b-sandbox) fo
 
 - [WorkspaceFilesystem interface](https://mastra.ai/reference/workspace/filesystem)
 - [GCSFilesystem reference](https://mastra.ai/reference/workspace/gcs-filesystem)
+- [AzureBlobFilesystem reference](https://mastra.ai/reference/workspace/azure-blob-filesystem)
 - [E2BSandbox reference](https://mastra.ai/reference/workspace/e2b-sandbox)
 - [Workspace overview](https://mastra.ai/docs/workspace/overview)

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @mastra/mcp-docs-server
 
+## 1.1.29-alpha.9
+
+### Patch Changes
+
+- Updated dependencies [[`8a71261`](https://github.com/mastra-ai/mastra/commit/8a71261e3954ae617c6f8e25767b951f99438ab2), [`021a60f`](https://github.com/mastra-ai/mastra/commit/021a60f1f3e0135a70ef23c58be7a9b3aaffe6b4)]:
+  - @mastra/core@1.29.0-alpha.4
+
+## 1.1.29-alpha.7
+
+### Patch Changes
+
+- Updated dependencies [[`c04417b`](https://github.com/mastra-ai/mastra/commit/c04417ba0a2e4ded66da4352331ef29cd4bd1d79), [`cf25a03`](https://github.com/mastra-ai/mastra/commit/cf25a03132164b9dc1e5dccf7394824e33007c51), [`ba6b0c5`](https://github.com/mastra-ai/mastra/commit/ba6b0c51bfce358554fd33c7f2bcd5593633f2ff)]:
+  - @mastra/core@1.29.0-alpha.3
+
 ## 1.1.29-alpha.5
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.29-alpha.6",
+  "version": "1.1.29-alpha.9",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -29,7 +29,7 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.3.6",
-    "@mastra/core": "1.29.0-alpha.2",
+    "@mastra/core": "1.29.0-alpha.4",
     "@mastra/mcp": "^1.5.2"
   },
   "devDependencies": {
@@ -47,8 +47,8 @@
     "typescript": "^5.9.3",
     "vitest": "4.1.5",
     "@internal/lint": "0.0.86",
-    "@mastra/core": "1.29.0-alpha.2",
-    "@internal/types-builder": "0.0.61"
+    "@internal/types-builder": "0.0.61",
+    "@mastra/core": "1.29.0-alpha.4"
   },
   "homepage": "https://mastra.ai",
   "repository": {