@mastra/mcp-docs-server 1.1.25-alpha.7 → 1.1.25-alpha.9

package/.docs/docs/agents/processors.md

@@ -11,6 +11,8 @@ You can use individual [`Processor`](https://mastra.ai/reference/processors/proc
 
 Some processors implement both input and output logic and can be used in either array depending on where the transformation should occur.
 
+Some built-in processors also persist hidden system reminder messages using `<system-reminder>...</system-reminder>` text plus `metadata.systemReminder`. These reminders stay available in raw memory history and retry/prompt reconstruction paths, but standard UI-facing message conversions and default memory recall hide them unless you explicitly opt in.
+
 ## When to use processors
 
 Use processors to:
@@ -536,6 +538,37 @@ The retry mechanism:
 - Tracks retry count via the `retryCount` parameter
 - Respects `maxProcessorRetries` limit on the agent
 
+## API error handling
+
+The `processAPIError` method handles LLM API rejections — errors where the API rejects the request (such as 400 or 422 status codes) rather than network or server failures. This lets you modify the request and retry when the API rejects the message format.
+
+```typescript
+import { APICallError } from '@ai-sdk/provider'
+import type { Processor, ProcessAPIErrorArgs, ProcessAPIErrorResult } from '@mastra/core/processors'
+
+export class ContextLengthHandler implements Processor {
+  id = 'context-length-handler'
+
+  processAPIError({
+    error,
+    messageList,
+    retryCount,
+  }: ProcessAPIErrorArgs): ProcessAPIErrorResult | void {
+    if (retryCount > 0) return
+
+    if (APICallError.isInstance(error) && error.message.includes('context length exceeded')) {
+      const messages = messageList.get.all.db()
+      if (messages.length > 4) {
+        messageList.removeByIds([messages[1]!.id, messages[2]!.id])
+        return { retry: true }
+      }
+    }
+  }
+}
+```
+
+Mastra includes a built-in [`PrefillErrorHandler`](https://mastra.ai/reference/processors/prefill-error-handler) that automatically handles the Anthropic "assistant message prefill" error. This processor is auto-injected and requires no configuration.
+
 ## Related documentation
 
 - [Guardrails](https://mastra.ai/docs/agents/guardrails): Security and validation processors

package/.docs/docs/mcp/overview.md

@@ -89,6 +89,23 @@ export const testAgent = new Agent({
 
 > **Info:** Visit [Agent Class](https://mastra.ai/reference/agents/agent) for a full list of configuration options.
 
+## Tool approval
+
+You can require human approval before MCP tools are executed by setting `requireToolApproval` on a server definition. This integrates with the existing [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) approval flow.
+
+```typescript
+export const mcp = new MCPClient({
+  servers: {
+    github: {
+      url: new URL('http://localhost:3000/mcp'),
+      requireToolApproval: true,
+    },
+  },
+})
+```
+
+You can also pass a function to decide dynamically per-call. See the [MCPClient reference](https://mastra.ai/reference/tools/mcp-client) for the full API.
+
 ## Configuring `MCPServer`
 
 To expose agents, tools, and workflows from your Mastra application to external systems over HTTP(S) use the `MCPServer` class. This makes them accessible to any system or agent that supports the protocol.

package/.docs/docs/memory/message-history.md

@@ -6,6 +6,12 @@ You can also retrieve message history to display past conversations in your UI.
 
 > **Info:** Each message belongs to a thread (the conversation) and a resource (the user or entity it's associated with). See [Threads and resources](https://mastra.ai/docs/memory/storage) for more detail.
 
+> **Warning:** When you use memory with a client application, send **only the new message** from the client instead of the full conversation history.
+>
+> Sending the full history is redundant because Mastra loads messages from storage, and it can cause message ordering bugs when client-side timestamps conflict with stored timestamps.
+>
+> For an AI SDK example, see [Using Mastra Memory](https://mastra.ai/guides/build-your-ui/ai-sdk-ui).
+
 ## Getting started
 
 Install the Mastra memory module along with a [storage adapter](https://mastra.ai/docs/memory/storage) for your database. The examples below use `@mastra/libsql`, which stores data locally in a `mastra.db` file.

package/.docs/docs/memory/observational-memory.md

@@ -38,6 +38,12 @@ const memory = new Memory({
 
 See [configuration options](https://mastra.ai/reference/memory/observational-memory) for full API details.
 
+> **Warning:** When you use OM with a client application, send **only the new message** from the client instead of the full conversation history.
+>
+> Observational memory still relies on stored conversation history. Sending the full history is redundant and can cause message ordering bugs when client-side timestamps conflict with stored timestamps.
+>
+> For an AI SDK example, see [Using Mastra Memory](https://mastra.ai/guides/build-your-ui/ai-sdk-ui).
+
 > **Note:** OM currently only supports `@mastra/pg`, `@mastra/libsql`, and `@mastra/mongodb` storage adapters. It uses background agents for managing memory. When using `observationalMemory: true`, the default model is `google/gemini-2.5-flash`. When passing a config object, a `model` must be explicitly set.
 
 ## Benefits

package/.docs/docs/voice/overview.md

@@ -265,7 +265,7 @@ const { text } = await voiceAgent.generate('What color is the sky?')
 
 // Convert text to speech to an Audio Stream
 const audioStream = await voiceAgent.voice.speak(text, {
-  speaker: 'default', // Optional: specify a speaker
+  speaker: 'shubh', // Optional: specify a bulbul:v3 speaker
 })
 
 playAudio(audioStream)
@@ -760,12 +760,15 @@ Visit the [Speechify Voice Reference](https://mastra.ai/reference/voice/speechif
 // Sarvam Voice Configuration
 const voice = new SarvamVoice({
   speechModel: {
-    name: 'sarvam-voice', // Example model name
+    model: 'bulbul:v3', // TTS model (bulbul:v2 or bulbul:v3)
+    apiKey: process.env.SARVAM_API_KEY,
+    language: 'en-IN', // BCP-47 language code
+  },
+  listeningModel: {
+    model: 'saarika:v2.5', // STT model (saarika:v2.5 or saaras:v3)
     apiKey: process.env.SARVAM_API_KEY,
-    language: 'en-IN', // Language code
-    style: 'conversational', // Style setting
   },
-  // Sarvam may not have a separate listening model
+  speaker: 'shubh', // Default bulbul:v3 speaker
 })
 ```
 

package/.docs/guides/build-your-ui/ai-sdk-ui.md

@@ -238,6 +238,38 @@ export default function Chat() {
 
 Use [`prepareSendMessagesRequest`](https://ai-sdk.dev/docs/reference/ai-sdk-ui/use-chat#transport.default-chat-transport.prepare-send-messages-request) to customize the request sent to the chat route, for example to pass additional configuration to the agent.
 
+## Using Mastra Memory
+
+When your agent has [memory](https://mastra.ai/docs/memory/overview) configured, Mastra loads conversation history from storage on the server. Send only the new message from the client instead of the full conversation history.
+
+Sending the full history is redundant and can cause message ordering bugs because client-side timestamps can conflict with the timestamps stored in your database.
+
+```typescript
+import { useChat } from '@ai-sdk/react'
+import { DefaultChatTransport } from 'ai'
+
+const { messages, sendMessage } = useChat({
+  transport: new DefaultChatTransport({
+    api: 'http://localhost:4111/chat/weatherAgent',
+    prepareSendMessagesRequest({ messages }) {
+      return {
+        body: {
+          messages: [messages[messages.length - 1]],
+          threadId: 'user-thread-123',
+          resourceId: 'user-123',
+        },
+      }
+    },
+  }),
+})
+```
+
+Set `threadId` and `resourceId` from your app's own state, such as URL params, auth context, or your database.
+
+See [Message history](https://mastra.ai/docs/memory/message-history) for more on how Mastra memory loads and stores messages.
+
+[`chatRoute()`](https://mastra.ai/reference/ai-sdk/chat-route) and [`handleChatStream()`](https://mastra.ai/reference/ai-sdk/handle-chat-stream) already work with memory. Configure the client to send only the new message and include the thread and resource identifiers.
+
 ### `useCompletion()`
 
 The `useCompletion()` hook handles single-turn completions between your frontend and a Mastra agent, allowing you to send a prompt and receive a streamed response over HTTP.

package/.docs/guides/deployment/mastra-platform.md

@@ -182,6 +182,8 @@ The CLI reads `organizationId` and `projectId` from `.mastra-project.json` by de
 ## Related
 
 - [CLI reference: `mastra server deploy`](https://mastra.ai/reference/cli/mastra)
+- [CLI reference: `mastra server pause`](https://mastra.ai/reference/cli/mastra)
+- [CLI reference: `mastra server restart`](https://mastra.ai/reference/cli/mastra)
 - [CLI reference: `mastra studio deploy`](https://mastra.ai/reference/cli/mastra)
 - [CLI reference: `mastra auth tokens`](https://mastra.ai/reference/cli/mastra)
 - [Mastra platform overview](https://mastra.ai/docs/mastra-platform/overview)

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 176 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 171 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -46,7 +46,6 @@ ANTHROPIC_API_KEY=ant-...
 | `anthropic/claude-sonnet-4.6`                                   |
 | `arcee-ai/trinity-large-preview:free`                           |
 | `arcee-ai/trinity-large-thinking`                               |
-| `arcee-ai/trinity-mini:free`                                    |
 | `black-forest-labs/flux.2-flex`                                 |
 | `black-forest-labs/flux.2-klein-4b`                             |
 | `black-forest-labs/flux.2-max`                                  |
@@ -117,7 +116,6 @@ ANTHROPIC_API_KEY=ant-...
 | `moonshotai/kimi-k2-0905`                                       |
 | `moonshotai/kimi-k2-0905:exacto`                                |
 | `moonshotai/kimi-k2-thinking`                                   |
-| `moonshotai/kimi-k2:free`                                       |
 | `moonshotai/kimi-k2.5`                                          |
 | `nousresearch/hermes-3-llama-3.1-405b:free`                     |
 | `nousresearch/hermes-4-405b`                                    |
@@ -168,15 +166,12 @@ ANTHROPIC_API_KEY=ant-...
 | `qwen/qwen3-235b-a22b-thinking-2507`                            |
 | `qwen/qwen3-30b-a3b-instruct-2507`                              |
 | `qwen/qwen3-30b-a3b-thinking-2507`                              |
-| `qwen/qwen3-4b:free`                                            |
 | `qwen/qwen3-coder`                                              |
 | `qwen/qwen3-coder-30b-a3b-instruct`                             |
 | `qwen/qwen3-coder-flash`                                        |
 | `qwen/qwen3-coder:exacto`                                       |
-| `qwen/qwen3-coder:free`                                         |
 | `qwen/qwen3-max`                                                |
 | `qwen/qwen3-next-80b-a3b-instruct`                              |
-| `qwen/qwen3-next-80b-a3b-instruct:free`                         |
 | `qwen/qwen3-next-80b-a3b-thinking`                              |
 | `qwen/qwen3.5-397b-a17b`                                        |
 | `qwen/qwen3.5-flash-02-23`                                      |

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 3610 models from 99 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3596 models from 99 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/anthropic.md

@@ -114,13 +114,23 @@ const response = await agent.generate("Hello!", {
 
 **cacheControl** (`{ type: "ephemeral"; ttl?: "5m" | "1h" | undefined; } | undefined`)
 
+**metadata** (`{ userId?: string | undefined; } | undefined`)
+
+**mcpServers** (`{ type: "url"; name: string; url: string; authorizationToken?: string | null | undefined; toolConfiguration?: { enabled?: boolean | null | undefined; allowedTools?: string[] | null | undefined; } | null | undefined; }[] | undefined`)
+
 **container** (`{ id?: string | undefined; skills?: { type: "anthropic" | "custom"; skillId: string; version?: string | undefined; }[] | undefined; } | undefined`)
 
+**toolStreaming** (`boolean | undefined`)
+
 **effort** (`"low" | "medium" | "high" | "max" | undefined`)
 
-**speed** (`"fast" | undefined`)
+**speed** (`"fast" | "standard" | undefined`)
+
+**inferenceGeo** (`"us" | "global" | undefined`)
+
+**anthropicBeta** (`string[] | undefined`)
 
-**contextManagement** (`{ edits: ({ type: "clear_01"; trigger?: { type: "input_tokens"; value: number; } | undefined; keep?: "all" | { type: "thinking_turns"; value: number; } | undefined; } | { type: "compact_20260112"; trigger?: { ...; } | undefined; pauseAfterCompaction?: boolean | undefined; instructions?: string | undefined; })[]; } |...`)
+**contextManagement** (`{ edits: ({ type: "clear_tool_uses_20250919"; trigger?: { type: "input_tokens"; value: number; } | { type: "tool_uses"; value: number; } | undefined; keep?: { type: "tool_uses"; value: number; } | undefined; clearAtLeast?: { ...; } | undefined; clearToolInputs?: boolean | undefined; excludeTools?: string[] | undefin...`)
 
 ## Direct provider installation
 

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

@@ -1,6 +1,6 @@
 # ![Fireworks AI logo](https://models.dev/logos/fireworks-ai.svg)Fireworks AI
 
-Access 16 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
+Access 17 Fireworks AI models through Mastra's model router. Authentication is handled automatically using the `FIREWORKS_API_KEY` environment variable.
 
 Learn more in the [Fireworks AI documentation](https://fireworks.ai/docs/).
 
@@ -48,6 +48,7 @@ for await (const chunk of stream) {
 | `fireworks-ai/accounts/fireworks/models/kimi-k2p5`        | 256K    |       |           |       |       |       | $0.60      | $3          |
 | `fireworks-ai/accounts/fireworks/models/minimax-m2p1`     | 200K    |       |           |       |       |       | $0.30      | $1          |
 | `fireworks-ai/accounts/fireworks/models/minimax-m2p5`     | 197K    |       |           |       |       |       | $0.30      | $1          |
+| `fireworks-ai/accounts/fireworks/models/minimax-m2p7`     | 197K    |       |           |       |       |       | $0.30      | $1          |
 | `fireworks-ai/accounts/fireworks/models/qwen3p6-plus`     | 128K    |       |           |       |       |       | $0.50      | $3          |
 | `fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo` | 256K    |       |           |       |       |       | —          | —           |
 

package/.docs/models/providers/google.md

@@ -137,10 +137,14 @@ const response = await agent.generate("Hello!", {
 
 **mediaResolution** (`"MEDIA_RESOLUTION_UNSPECIFIED" | "MEDIA_RESOLUTION_LOW" | "MEDIA_RESOLUTION_MEDIUM" | "MEDIA_RESOLUTION_HIGH" | undefined`)
 
-**imageConfig** (`{ aspectRatio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | undefined; imageSize?: "1K" | "2K" | "4K" | undefined; } | undefined`)
+**imageConfig** (`{ aspectRatio?: "1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9" | "1:8" | "8:1" | "1:4" | "4:1" | undefined; imageSize?: "1K" | "2K" | "4K" | "512" | undefined; } | undefined`)
 
 **retrievalConfig** (`{ latLng?: { latitude: number; longitude: number; } | undefined; } | undefined`)
 
+**streamFunctionCallArguments** (`boolean | undefined`)
+
+**serviceTier** (`"standard" | "flex" | "priority" | undefined`)
+
 ## Direct provider installation
 
 This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the [package documentation](https://www.npmjs.com/package/@ai-sdk/google) for more details.

package/.docs/models/providers/kilo.md

@@ -1,6 +1,6 @@
 # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
 
-Access 334 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
+Access 335 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
 
 Learn more in the [Kilo Gateway documentation](https://kilo.ai).
 
@@ -268,6 +268,7 @@ for await (const chunk of stream) {
 | `kilo/openai/o4-mini-high`                          | 200K    |       |           |       |       |       | $1         | $4          |
 | `kilo/openrouter/auto`                              | 2.0M    |       |           |       |       |       | —          | —           |
 | `kilo/openrouter/bodybuilder`                       | 128K    |       |           |       |       |       | —          | —           |
+| `kilo/openrouter/elephant-alpha`                    | 262K    |       |           |       |       |       | —          | —           |
 | `kilo/openrouter/free`                              | 200K    |       |           |       |       |       | —          | —           |
 | `kilo/perplexity/sonar`                             | 127K    |       |           |       |       |       | $1         | $1          |
 | `kilo/perplexity/sonar-deep-research`               | 128K    |       |           |       |       |       | $2         | $8          |

package/.docs/models/providers/openai.md

@@ -171,6 +171,10 @@ const response = await agent.generate("Hello!", {
 
 **user** (`string | null | undefined`)
 
+**systemMessageMode** (`"remove" | "system" | "developer" | undefined`)
+
+**forceReasoning** (`boolean | undefined`)
+
 ## Direct provider installation
 
 This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the [package documentation](https://www.npmjs.com/package/@ai-sdk/openai) for more details.

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

@@ -1,6 +1,6 @@
 # ![Poe logo](https://models.dev/logos/poe.svg)Poe
 
-Access 128 Poe models through Mastra's model router. Authentication is handled automatically using the `POE_API_KEY` environment variable.
+Access 117 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).
 
@@ -41,17 +41,12 @@ for await (const chunk of stream) {
 | `poe/anthropic/claude-opus-4.1`        | 197K    |       |           |       |       |       | $13        | $64         |
 | `poe/anthropic/claude-opus-4.5`        | 197K    |       |           |       |       |       | $4         | $21         |
 | `poe/anthropic/claude-opus-4.6`        | 983K    |       |           |       |       |       | $4         | $21         |
-| `poe/anthropic/claude-sonnet-3.5`      | 189K    |       |           |       |       |       | $3         | $13         |
-| `poe/anthropic/claude-sonnet-3.5-june` | 189K    |       |           |       |       |       | $3         | $13         |
 | `poe/anthropic/claude-sonnet-3.7`      | 197K    |       |           |       |       |       | $3         | $13         |
 | `poe/anthropic/claude-sonnet-4`        | 983K    |       |           |       |       |       | $3         | $13         |
 | `poe/anthropic/claude-sonnet-4.5`      | 983K    |       |           |       |       |       | $3         | $13         |
 | `poe/anthropic/claude-sonnet-4.6`      | 983K    |       |           |       |       |       | $3         | $13         |
-| `poe/cerebras/gpt-oss-120b-cs`         | —       |       |           |       |       |       | —          | —           |
-| `poe/cerebras/llama-3.1-8b-cs`         | —       |       |           |       |       |       | —          | —           |
-| `poe/cerebras/llama-3.3-70b-cs`        | —       |       |           |       |       |       | —          | —           |
-| `poe/cerebras/qwen3-235b-2507-cs`      | —       |       |           |       |       |       | —          | —           |
-| `poe/cerebras/qwen3-32b-cs`            | —       |       |           |       |       |       | —          | —           |
+| `poe/cerebras/gpt-oss-120b-cs`         | 128K    |       |           |       |       |       | $0.35      | $0.75       |
+| `poe/cerebras/llama-3.1-8b-cs`         | 128K    |       |           |       |       |       | $0.10      | $0.10       |
 | `poe/elevenlabs/elevenlabs-music`      | 2K      |       |           |       |       |       | —          | —           |
 | `poe/elevenlabs/elevenlabs-v2.5-turbo` | 128K    |       |           |       |       |       | —          | —           |
 | `poe/elevenlabs/elevenlabs-v3`         | 128K    |       |           |       |       |       | —          | —           |
@@ -62,10 +57,8 @@ for await (const chunk of stream) {
 | `poe/google/gemini-2.5-flash-lite`     | 1.0M    |       |           |       |       |       | $0.07      | $0.28       |
 | `poe/google/gemini-2.5-pro`            | 1.1M    |       |           |       |       |       | $0.87      | $7          |
 | `poe/google/gemini-3-flash`            | 1.0M    |       |           |       |       |       | $0.40      | $2          |
-| `poe/google/gemini-3-pro`              | 1.0M    |       |           |       |       |       | $2         | $10         |
 | `poe/google/gemini-3.1-flash-lite`     | 1.0M    |       |           |       |       |       | $0.25      | $2          |
 | `poe/google/gemini-3.1-pro`            | 1.0M    |       |           |       |       |       | $2         | $12         |
-| `poe/google/gemini-deep-research`      | 1.0M    |       |           |       |       |       | $2         | $10         |
 | `poe/google/gemma-4-31b`               | 262K    |       |           |       |       |       | —          | —           |
 | `poe/google/imagen-3`                  | 480     |       |           |       |       |       | —          | —           |
 | `poe/google/imagen-3-fast`             | 480     |       |           |       |       |       | —          | —           |
@@ -88,20 +81,16 @@ for await (const chunk of stream) {
 | `poe/novita/deepseek-v3.2`             | 128K    |       |           |       |       |       | $0.27      | $0.40       |
 | `poe/novita/glm-4.6`                   | —       |       |           |       |       |       | —          | —           |
 | `poe/novita/glm-4.6v`                  | 131K    |       |           |       |       |       | —          | —           |
-| `poe/novita/glm-4.7`                   | 205K    |       |           |       |       |       | —          | —           |
 | `poe/novita/glm-4.7-flash`             | 200K    |       |           |       |       |       | —          | —           |
 | `poe/novita/glm-4.7-n`                 | 205K    |       |           |       |       |       | —          | —           |
-| `poe/novita/glm-5`                     | 205K    |       |           |       |       |       | —          | —           |
+| `poe/novita/glm-5`                     | 205K    |       |           |       |       |       | $1         | $3          |
 | `poe/novita/kimi-k2-thinking`          | 256K    |       |           |       |       |       | —          | —           |
-| `poe/novita/kimi-k2.5`                 | 256K    |       |           |       |       |       | —          | —           |
+| `poe/novita/kimi-k2.5`                 | 128K    |       |           |       |       |       | $0.60      | $3          |
 | `poe/novita/minimax-m2.1`              | 205K    |       |           |       |       |       | —          | —           |
-| `poe/openai/chatgpt-4o-latest`         | 128K    |       |           |       |       |       | $5         | $14         |
 | `poe/openai/dall-e-3`                  | 800     |       |           |       |       |       | —          | —           |
 | `poe/openai/gpt-3.5-turbo`             | 16K     |       |           |       |       |       | $0.45      | $1          |
 | `poe/openai/gpt-3.5-turbo-instruct`    | 4K      |       |           |       |       |       | $1         | $2          |
 | `poe/openai/gpt-3.5-turbo-raw`         | 5K      |       |           |       |       |       | $0.45      | $1          |
-| `poe/openai/gpt-4-classic`             | 8K      |       |           |       |       |       | $27        | $54         |
-| `poe/openai/gpt-4-classic-0314`        | 8K      |       |           |       |       |       | $27        | $54         |
 | `poe/openai/gpt-4-turbo`               | 128K    |       |           |       |       |       | $9         | $27         |
 | `poe/openai/gpt-4.1`                   | 1.0M    |       |           |       |       |       | $2         | $7          |
 | `poe/openai/gpt-4.1-mini`              | 1.0M    |       |           |       |       |       | $0.36      | $1          |

package/.docs/models/providers/xai.md

@@ -109,6 +109,10 @@ const response = await agent.generate("Hello!", {
 
 **reasoningEffort** (`"low" | "high" | undefined`)
 
+**logprobs** (`boolean | undefined`)
+
+**topLogprobs** (`number | undefined`)
+
 **parallel\_function\_calling** (`boolean | undefined`)
 
 **searchParameters** (`{ mode: "off" | "auto" | "on"; returnCitations?: boolean | undefined; fromDate?: string | undefined; toDate?: string | undefined; maxSearchResults?: number | undefined; sources?: ({ ...; } | ... 2 more ... | { ...; })[] | undefined; } | undefined`)

package/.docs/reference/ai-sdk/handle-chat-stream.md

@@ -8,6 +8,23 @@ Framework-agnostic handler for streaming agent chat in AI SDK-compatible format.
 
 Use [`chatRoute()`](https://mastra.ai/reference/ai-sdk/chat-route) if you want to create a chat route inside a Mastra server.
 
+## Structured output in UI streams
+
+When you pass `structuredOutput` to the underlying agent execution, the final structured output object is emitted in the AI SDK-compatible UI stream as a custom data part:
+
+```json
+{
+  "type": "data-structured-output",
+  "data": {
+    "object": {}
+  }
+}
+```
+
+The `object` field contains your full structured output value. Mastra emits this event for the final structured output object only. Partial structured output chunks are not exposed in the UI stream.
+
+Read this event with AI SDK UI's custom data handling, such as `onData`, or render it from message data parts.
+
 ## Usage example
 
 Next.js App Router example:

package/.docs/reference/ai-sdk/to-ai-sdk-stream.md

@@ -6,6 +6,21 @@ This is useful when building custom streaming endpoints outside Mastra's provide
 
 `toAISdkStream()` keeps the existing AI SDK v5/default behavior. If your app is typed against AI SDK v6, pass `version: 'v6'` in the options object.
 
+## Structured output in UI streams
+
+When the source agent stream includes a final structured output object, `toAISdkStream()` emits it as a custom AI SDK UI data part:
+
+```json
+{
+  "type": "data-structured-output",
+  "data": {
+    "object": {}
+  }
+}
+```
+
+The `object` field contains your full structured output value. This maps Mastra's final structured output chunk into the AI SDK UI stream. Partial structured output chunks are not emitted.
+
 ## Usage example
 
 Next.js App Router example:

package/.docs/reference/cli/mastra.md

@@ -217,7 +217,7 @@ Organization ID. Can also be set via the `MASTRA_ORG_ID` environment variable.
 
 #### `--project`
 
-Project ID. Can also be set via the `MASTRA_PROJECT_ID` environment variable.
+Project ID or slug. Can also be set via the `MASTRA_PROJECT_ID` environment variable.
 
 #### `-y, --yes`
 
@@ -231,6 +231,10 @@ Path to the project config file. Defaults to `.mastra-project.json`.
 
 Skip the build step and deploy the existing `.mastra/output` directory.
 
+#### `--debug`
+
+Enable debug logs during the build step.
+
 ### CI/CD usage
 
 Set `MASTRA_API_TOKEN`, `MASTRA_ORG_ID`, and `MASTRA_PROJECT_ID` as environment variables for headless deploys. Interactive prompts are skipped automatically when `MASTRA_API_TOKEN` is set.
@@ -283,6 +287,101 @@ Builds and deploys your project to Server on Mastra platform. Works the same as
 mastra server deploy [dir]
 ```
 
+## `mastra server pause`
+
+Pauses the running server instance for the linked project. Organization and project resolution work the same as [`mastra server deploy`](#mastra-server-deploy).
+
+```bash
+mastra server pause
+```
+
+### Flags
+
+#### `--org`
+
+Organization ID. Can also be set via the `MASTRA_ORG_ID` environment variable.
+
+#### `--project`
+
+Project ID or slug when `MASTRA_PROJECT_ID` is not set. Slugs are resolved against projects in the current organization.
+
+#### `-c, --config`
+
+Path to the project config file. Defaults to `.mastra-project.json`.
+
+Fails if the instance is not running.
+
+## `mastra server restart`
+
+Restarts a paused or stopped server instance for the linked project. After the platform accepts the restart, the CLI resolves the deploy id (from the API response or by polling project and deploy metadata when the response omits an id), then streams build and deploy logs the same way as [`mastra server deploy`](#mastra-server-deploy) until the deploy reaches a terminal state.
+
+### Flags
+
+Same flags as [`mastra server pause`](#mastra-server-pause): **`--org`**, **`--project`**, and **`-c` / `--config`**, with the same defaults and behavior.
+
+```bash
+mastra server restart
+```
+
+Fails if a deployment is still active for this project (running, building, deploying, etc.); that is a platform restriction so you cannot restart while another deploy is in progress.
+
+## `mastra server env`
+
+Manages environment variables for the linked server deployment. Organization and project resolution work the same as [`mastra server deploy`](#mastra-server-deploy).
+
+Every subcommand accepts `-c` / `--config` for the project config file path (defaults to `.mastra-project.json`).
+
+### `mastra server env list`
+
+Lists all environment variables for the linked project. Values are partially masked in the output.
+
+### `mastra server env set`
+
+Sets an environment variable. The CLI reads the current map, applies the change, and uploads the result.
+
+```bash
+mastra server env set <key> <value>
+```
+
+### `mastra server env unset`
+
+Removes an environment variable.
+
+```bash
+mastra server env unset <key>
+```
+
+### `mastra server env import`
+
+Imports variables from a file (for example a `.env` file) and merges them into the existing map. New values override keys that already exist on the server.
+
+```bash
+mastra server env import <file>
+```
+
+### `mastra server env pull`
+
+Downloads environment variables from the linked project and writes them to a local file. This is the inverse of [`mastra server env import`](#mastra-server-env-import).
+
+```bash
+mastra server env pull [file]
+```
+
+The file defaults to `.env` when no argument is given. All values are double-quoted and escaped for safe shell sourcing. Keys that aren't valid shell identifiers are skipped. The output file is created with restrictive permissions (`0600`) since it contains secrets.
+
+#### `--project`
+
+Project ID or slug. Overrides the linked project when `MASTRA_PROJECT_ID` isn't set.
+
+#### CI usage
+
+In a continuous-integration pipeline, authenticate with `MASTRA_API_TOKEN` and pull the environment before running your app:
+
+```bash
+export MASTRA_API_TOKEN="..."
+mastra server env pull .env.production --project my-project
+```
+
 ## `mastra auth`
 
 Manages authentication for Mastra platform. Credentials are stored in `~/.mastra/credentials.json`. You can also set the `MASTRA_API_TOKEN` environment variable as an alternative to interactive login.

package/.docs/reference/index.md

@@ -162,6 +162,7 @@ The Reference section provides documentation of Mastra's API, including paramete
 - [MessageHistory](https://mastra.ai/reference/processors/message-history-processor)
 - [ModerationProcessor](https://mastra.ai/reference/processors/moderation-processor)
 - [PIIDetector](https://mastra.ai/reference/processors/pii-detector)
+- [PrefillErrorHandler](https://mastra.ai/reference/processors/prefill-error-handler)
 - [Processor Interface](https://mastra.ai/reference/processors/processor-interface)
 - [PromptInjectionDetector](https://mastra.ai/reference/processors/prompt-injection-detector)
 - [SemanticRecall](https://mastra.ai/reference/processors/semantic-recall-processor)

package/.docs/reference/processors/prefill-error-handler.md

@@ -0,0 +1,70 @@
+# PrefillErrorHandler
+
+The `PrefillErrorHandler` is an **error processor** that handles the Anthropic "assistant message prefill" error. This error occurs when a conversation ends with an assistant message and the model doesn't support prefilling assistant responses.
+
+When the error is detected, the processor appends a hidden `<system-reminder>continue</system-reminder>` user message to the conversation and signals a retry. The reminder is persisted with `metadata.systemReminder = { type: 'anthropic-prefill-processor-retry' }`, which keeps it available for retry reconstruction and raw history while standard UI-facing message conversions hide it.
+
+Add this processor to `errorProcessors` when you want Mastra to recover from Anthropic assistant message prefill errors.
+
+## How it works
+
+1. The LLM API call fails with a message containing "assistant message prefill"
+2. `PrefillErrorHandler` checks that this is the first retry attempt
+3. It appends a hidden `<system-reminder>continue</system-reminder>` user message to the `messageList`
+4. It returns `{ retry: true }` to signal the LLM call should be retried with the modified messages
+
+The processor now reacts to the API rejection itself instead of re-checking whether the conversation currently ends with an assistant message. This makes it resilient to cases where the provider rejects the request for prefill semantics even if the trailing message shape has already been transformed upstream.
+
+## Usage example
+
+Add `PrefillErrorHandler` to `errorProcessors` for any agent that should retry Anthropic prefill failures:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { PrefillErrorHandler } from '@mastra/core/processors'
+
+export const agent = new Agent({
+  name: 'my-agent',
+  instructions: 'You are a helpful assistant.',
+  model: 'anthropic/claude-opus-4-6',
+  errorProcessors: [new PrefillErrorHandler()],
+})
+```
+
+If you want custom recovery behavior, provide your own error processor with a `processAPIError` method:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import type { Processor } from '@mastra/core/processors'
+
+const customErrorHandler: Processor = {
+  id: 'custom-prefill-error-handler',
+  processAPIError({ error, messageList, retryCount }) {
+    // Your custom logic here
+  },
+}
+
+export const agent = new Agent({
+  name: 'my-agent',
+  instructions: 'You are a helpful assistant.',
+  model: 'anthropic/claude-opus-4-6',
+  errorProcessors: [customErrorHandler],
+})
+```
+
+## Constructor parameters
+
+The `PrefillErrorHandler` takes no constructor parameters.
+
+## Properties
+
+**id** (`'prefill-error-handler'`): Processor identifier.
+
+**name** (`'Prefill Error Handler'`): Processor display name.
+
+**processAPIError** (`(args: ProcessAPIErrorArgs) => ProcessAPIErrorResult | void`): Handles the Anthropic prefill error by appending a hidden system reminder continue message and signaling retry. Only triggers on the first retry attempt.
+
+## Related
+
+- [Processor interface](https://mastra.ai/reference/processors/processor-interface)
+- [Guardrails](https://mastra.ai/docs/agents/guardrails)

package/.docs/reference/processors/processor-interface.md

@@ -4,7 +4,7 @@ The `Processor` interface defines the contract for all processors in Mastra. Pro
 
 ## When processor methods run
 
-The five processor methods run at different points in the agent execution lifecycle:
+The six processor methods run at different points in the agent execution lifecycle:
 
 ```text
 ┌─────────────────────────────────────────────────────────────────┐
@@ -26,10 +26,14 @@ The five processor methods run at different points in the agent execution lifecy
 │  │  └──────────┬──────────┘                                │    │
 │  │             │                                           │    │
 │  │             ▼                                           │    │
-│  │       LLM Execution                                     │    │
-│  │             │                                           │    │
-│  │             ▼                                           │    │
-│  │  ┌──────────────────────┐                               │    │
+│  │       LLM Execution ──── API Error? ──┐                │    │
+│  │             │                          │                │    │
+│  │             │              ┌───────────────────┐        │    │
+│  │             │              │  processAPIError  │        │    │
+│  │             │              └─────────┬─────────┘        │    │
+│  │             │                 retry? └── Loop back ──┐  │    │
+│  │             ▼                                        │  │    │
+│  │  ┌──────────────────────┐                            │  │    │
 │  │  │ processOutputStream  │  ← Runs on EACH stream chunk  │    │
 │  │  └──────────┬───────────┘                               │    │
 │  │             │                                           │    │
@@ -55,13 +59,14 @@ The five processor methods run at different points in the agent execution lifecy
 └─────────────────────────────────────────────────────────────────┘
 ```
 
-| Method                | When it runs                                           | Use case                                                      |
-| --------------------- | ------------------------------------------------------ | ------------------------------------------------------------- |
-| `processInput`        | Once at the start, before the agentic loop             | Validate/transform initial user input, add context            |
-| `processInputStep`    | At each step of the agentic loop, before each LLM call | Transform messages between steps, handle tool results         |
-| `processOutputStream` | On each streaming chunk during LLM response            | Filter/modify streaming content, detect patterns in real-time |
-| `processOutputStep`   | After each LLM response, before tool execution         | Validate output quality, implement guardrails with retry      |
-| `processOutputResult` | Once after generation completes                        | Post-process final response, log results                      |
+| Method                | When it runs                                           | Use case                                                                      |
+| --------------------- | ------------------------------------------------------ | ----------------------------------------------------------------------------- |
+| `processInput`        | Once at the start, before the agentic loop             | Validate/transform initial user input, add context                            |
+| `processInputStep`    | At each step of the agentic loop, before each LLM call | Transform messages between steps, handle tool results                         |
+| `processAPIError`     | When an LLM API call fails                             | Inspect API rejections, optionally mutate state/messages, and request a retry |
+| `processOutputStream` | On each streaming chunk during LLM response            | Filter/modify streaming content, detect patterns in real-time                 |
+| `processOutputStep`   | After each LLM response, before tool execution         | Validate output quality, implement guardrails with retry                      |
+| `processOutputResult` | Once after generation completes                        | Post-process final response, log results                                      |
 
 ## Interface definition
 
@@ -72,6 +77,9 @@ interface Processor<TId extends string = string> {
 
   processInput?(args: ProcessInputArgs): Promise<ProcessInputResult> | ProcessInputResult
   processInputStep?(args: ProcessInputStepArgs): ProcessorMessageResult
+  processAPIError?(
+    args: ProcessAPIErrorArgs,
+  ): Promise<ProcessAPIErrorResult | void> | ProcessAPIErrorResult | void
   processOutputStream?(args: ProcessOutputStreamArgs): Promise<ChunkType | null | undefined>
   processOutputStep?(args: ProcessOutputStepArgs): ProcessorMessageResult
   processOutputResult?(args: ProcessOutputResultArgs): ProcessorMessageResult
@@ -224,6 +232,84 @@ System messages are **reset to their original values** at the start of each step
 
 ***
 
+### `processAPIError`
+
+Handles LLM API rejection errors before they surface as final errors. This runs when the API call fails with a non-retryable error (such as a 400 or 422 status code). Unlike `processOutputStep` which runs after successful responses, this runs when the API rejects the request.
+
+Add processors that implement `processAPIError` to an agent's `errorProcessors` array.
+
+Processors can inspect the error, modify the request (for example, by appending messages to the `messageList`), and return `{ retry: true }` to signal a retry with the modified state.
+
+```typescript
+processAPIError?(args: ProcessAPIErrorArgs): Promise<ProcessAPIErrorResult | void> | ProcessAPIErrorResult | void;
+```
+
+#### `ProcessAPIErrorArgs`
+
+**error** (`unknown`): The error that occurred during the LLM API call.
+
+**messages** (`MastraDBMessage[]`): All messages at the time of the error.
+
+**messageList** (`MessageList`): MessageList instance for managing messages. Modify this to change the request before retry.
+
+**stepNumber** (`number`): Current step number (0-indexed).
+
+**steps** (`StepResult[]`): All completed steps so far.
+
+**state** (`Record<string, unknown>`): Per-processor state that persists across all method calls within this request.
+
+**retryCount** (`number`): The current retry count for error handlers. Use this to limit retry attempts.
+
+**abort** (`(reason?: string, options?: { retry?: boolean; metadata?: unknown }) => never`): Function to abort processing.
+
+**writer** (`ProcessorStreamWriter`): Stream writer for emitting custom data chunks during streaming. Use \`writer.custom()\` to send transient UI signals.
+
+**requestContext** (`RequestContext`): Request context passed through from the agent call.
+
+**abortSignal** (`AbortSignal`): Signal for cancelling the operation.
+
+#### `ProcessAPIErrorResult`
+
+**retry** (`boolean`): Whether to retry the LLM call after applying modifications.
+
+#### Use cases
+
+- Handling API-specific rejections by modifying the request and retrying
+- Converting non-retryable errors into retryable ones with request modifications
+- Implementing model-specific error recovery strategies
+
+#### Example: Custom error recovery
+
+```typescript
+import { APICallError } from '@ai-sdk/provider'
+import type { Processor, ProcessAPIErrorArgs, ProcessAPIErrorResult } from '@mastra/core/processors'
+
+export class ErrorRecoveryProcessor implements Processor {
+  id = 'error-recovery'
+
+  processAPIError({
+    error,
+    messageList,
+    retryCount,
+  }: ProcessAPIErrorArgs): ProcessAPIErrorResult | void {
+    // Only retry once
+    if (retryCount > 0) return
+
+    // Check for a specific API error
+    if (APICallError.isInstance(error) && error.message.includes('context length exceeded')) {
+      // Trim older messages to fit within context
+      const messages = messageList.get.all.db()
+      if (messages.length > 4) {
+        messageList.removeByIds([messages[1]!.id, messages[2]!.id])
+        return { retry: true }
+      }
+    }
+  }
+}
+```
+
+***
+
 ### `processOutputStream`
 
 Processes streaming output chunks with built-in state management. Allows processors to accumulate chunks and make decisions based on larger context.
@@ -368,6 +454,18 @@ type OutputProcessor = Processor &
     | { processOutputStep: required }
     | { processOutputResult: required }
   )
+
+// Must implement processAPIError
+type ErrorProcessor = Processor & { processAPIError: required }
+```
+
+Configure processors that implement `processAPIError` in `errorProcessors`:
+
+```typescript
+const agent = new Agent({
+  // ...
+  errorProcessors: [new PrefillErrorHandler()],
+})
 ```
 
 ## Usage examples

package/.docs/reference/tools/create-tool.md

@@ -27,6 +27,34 @@ export const tool = createTool({
 })
 ```
 
+## Example with strict tool inputs
+
+Set `strict: true` when you want Mastra to ask supported model providers to generate tool arguments that exactly match the tool schema.
+
+```typescript
+import { createTool } from '@mastra/core/tools'
+import { z } from 'zod'
+
+export const weatherTool = createTool({
+  id: 'get-weather',
+  description: 'Get weather for a city',
+  strict: true,
+  inputSchema: z.object({
+    city: z.string(),
+    units: z.enum(['metric', 'imperial']),
+  }),
+  execute: async ({ city, units }) => {
+    return {
+      city,
+      units,
+      forecast: 'sunny',
+    }
+  },
+})
+```
+
+Mastra forwards `strict: true` to model adapters that support strict tool calling. On adapters that do not support strict tool calling, Mastra ignores this option.
+
 ## Example with `toModelOutput`
 
 Use `toModelOutput` when your tool should return rich internal data to your app, but the model should receive either a simplified value or multimodal content.
@@ -120,6 +148,8 @@ export const weatherTool = createTool({
 
 **outputSchema** (`Zod schema`): A Zod schema defining the expected output structure of the tool's \`execute\` function.
 
+**strict** (`boolean`): When true, Mastra enables strict tool input generation on model adapters that support it. This helps supported providers return arguments that match the tool schema more closely.
+
 **toModelOutput** (`(output: TSchemaOut) => unknown`): Optional function that transforms the tool's \`execute\` output before it is sent back to the model. Use this to return \`text\`, \`json\`, or \`content\`-shaped outputs (including multimodal parts like images/files) to the model while still keeping the full raw output in your application code.
 
 **suspendSchema** (`Zod schema`): A Zod schema defining the structure of the payload passed to \`suspend()\`. This payload is returned to the client when the tool suspends execution.

package/.docs/reference/tools/mcp-client.md

@@ -53,6 +53,51 @@ Each server in the `servers` map is configured using the `MastraMCPServerDefinit
 
 **enableServerLogs** (`boolean`): Whether to enable logging for this server. (Default: `true`)
 
+**requireToolApproval** (`boolean | (params: RequireToolApprovalContext) => boolean | Promise<boolean>`): Require human approval before executing tools from this server. When set to \`true\`, all tools require approval. When set to a function, the function is called with the tool name, arguments, and request context to dynamically decide whether approval is needed.
+
+## Tool approval
+
+Use `requireToolApproval` on a server definition to require human approval before any tool from that server is executed. This works with the existing [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) approval flow.
+
+### Require approval for all tools
+
+Set `requireToolApproval` to `true` to require approval for every tool on the server:
+
+```typescript
+const mcp = new MCPClient({
+  servers: {
+    github: {
+      url: new URL('http://localhost:3000/mcp'),
+      requireToolApproval: true,
+    },
+  },
+})
+```
+
+### Dynamic approval with a function
+
+Pass a function to decide per-call whether approval is needed. The function receives the tool name, the arguments the model passed, and any request context from the incoming request:
+
+```typescript
+const mcp = new MCPClient({
+  servers: {
+    github: {
+      url: new URL('http://localhost:3000/mcp'),
+      requireToolApproval: ({ toolName, args, requestContext }) => {
+        // Read-only tools don't need approval
+        if (toolName === 'list_repos') return false
+        // Destructive tools with force flag always need approval
+        if (toolName === 'delete_repo') return args.force === true
+        // Non-admin users need approval for everything else
+        return requestContext?.userRole !== 'admin'
+      },
+    },
+  },
+})
+```
+
+The function can also be async. It receives `requestContext` from the incoming request, which you can use for auth checks or other per-request logic.
+
 ## Methods
 
 ### `listTools()`

package/.docs/reference/voice/sarvam.md

@@ -13,25 +13,23 @@ const voice = new SarvamVoice()
 // Or initialize with specific configuration
 const voiceWithConfig = new SarvamVoice({
   speechModel: {
-    model: 'bulbul:v1',
+    model: 'bulbul:v3',
     apiKey: process.env.SARVAM_API_KEY!,
     language: 'en-IN',
     properties: {
-      pitch: 0,
-      pace: 1.65,
-      loudness: 1.5,
-      speech_sample_rate: 8000,
-      enable_preprocessing: false,
-      eng_interpolation_wt: 123,
+      pace: 1.0,
+      temperature: 0.6,
+      speech_sample_rate: 24000,
+      output_audio_codec: 'wav',
     },
   },
   listeningModel: {
-    model: 'saarika:v2',
+    model: 'saarika:v2.5',
     apiKey: process.env.SARVAM_API_KEY!,
     languageCode: 'en-IN',
     filetype: 'wav',
   },
-  speaker: 'meera', // Default voice
+  speaker: 'shubh', // Default voice for bulbul:v3
 })
 
 // Convert text to speech
@@ -45,46 +43,52 @@ const text = await voice.listen(audioStream, {
 
 ### Sarvam API Docs -
 
-<https://docs.sarvam.ai/api-reference-docs/endpoints/text-to-speech>
+<https://docs.sarvam.ai/api-reference-docs/text-to-speech/convert>
 
 ## Configuration
 
 ### Constructor options
 
-**speechModel** (`SarvamVoiceConfig`): Configuration for text-to-speech synthesis. (Default: `{ model: 'bulbul:v1', language: 'en-IN' }`)
+**speechModel** (`SarvamVoiceConfig`): Configuration for text-to-speech synthesis. (Default: `{ model: 'bulbul:v3', language: 'en-IN' }`)
 
 **speechModel.apiKey** (`string`): Sarvam API key. Falls back to SARVAM\_API\_KEY environment variable.
 
-**speechModel.model** (`SarvamTTSModel`): Specifies the model to use for text-to-speech conversion.
+**speechModel.model** (`SarvamTTSModel`): Specifies the model to use for text-to-speech conversion. Available options: bulbul:v2, bulbul:v3, bulbul:v3-beta. bulbul:v3-beta is a beta variant of bulbul:v3 that shares the same speaker catalog. Note: bulbul:v1 has been deprecated by Sarvam and is no longer supported.
 
 **speechModel.language** (`SarvamTTSLanguage`): Target language for speech synthesis. Available options: hi-IN, bn-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN, en-IN, gu-IN
 
 **speechModel.properties** (`object`): Additional voice properties for customization.
 
-**speechModel.properties.pitch** (`number`): Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75.
+**speechModel.properties.pace** (`number`): Controls the speed of the audio. Supported by both bulbul:v2 (range 0.3–3.0) and bulbul:v3 (range 0.5–2.0).
 
-**speechModel.properties.pace** (`number`): Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0. Required range: 0.3 <= x <= 3
+**speechModel.properties.temperature** (`number`): Sampling temperature that controls the randomness of the generated voice. bulbul:v3 only. Range: 0.01–2.0. Default: 0.6.
 
-**speechModel.properties.loudness** (`number`): Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Required range: 0 <= x <= 3
+**speechModel.properties.dict\_id** (`string`): Pronunciation dictionary ID. bulbul:v3 only.
 
-**speechModel.properties.speech\_sample\_rate** (`8000 | 16000 | 22050`): Audio sample rate in Hz.
+**speechModel.properties.pitch** (`number`): Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. bulbul:v2 only. Range: -0.75 to 0.75.
 
-**speechModel.properties.enable\_preprocessing** (`boolean`): Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false.
+**speechModel.properties.loudness** (`number`): Controls the loudness of the audio. bulbul:v2 only. Range: 0.3 to 3.0.
 
-**speechModel.properties.eng\_interpolation\_wt** (`number`): Weight for interpolating with English speaker at encoder.
+**speechModel.properties.enable\_preprocessing** (`boolean`): Enables normalization of English words and numeric entities (numbers, dates, etc.). bulbul:v2 only. Default is false.
 
-**speaker** (`SarvamVoiceId`): The speaker to be used for the output audio. If not provided, Meera will be used as default. AvailableOptions - meera, pavithra, maitreyi, arvind, amol, amartya, diya, neel, misha, vian, arjun, maya (Default: `'meera'`)
+**speechModel.properties.speech\_sample\_rate** (`8000 | 16000 | 22050 | 24000 | 32000 | 44100 | 48000`): Audio sample rate in Hz.
 
-**listeningModel** (`SarvamListenOptions`): Configuration for speech-to-text recognition. (Default: `{ model: 'saarika:v2', language_code: 'unknown' }`)
+**speechModel.properties.output\_audio\_codec** (`'mp3' | 'wav' | 'linear16' | 'mulaw' | 'alaw' | 'opus' | 'flac' | 'aac'`): Output audio codec.
+
+**speaker** (`SarvamVoiceId`): The speaker to be used for the output audio. Defaults to 'shubh'. bulbul:v3 supports 39 voices (shubh, aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali). bulbul:v2 supports 7 voices (anushka, manisha, vidya, arya, abhilash, karun, hitesh). Speakers are not interchangeable between model versions. (Default: `'shubh'`)
+
+**listeningModel** (`SarvamListenOptions`): Configuration for speech-to-text recognition. (Default: `{ model: 'saarika:v2.5', languageCode: 'unknown' }`)
 
 **listeningModel.apiKey** (`string`): Sarvam API key. Falls back to SARVAM\_API\_KEY environment variable.
 
-**listeningModel.model** (`SarvamSTTModel`): Specifies the model to use for speech-to-text conversion. Note:- Default model is saarika:v2 . Available options: saarika:v1, saarika:v2, saarika:flash
+**listeningModel.model** (`SarvamSTTModel`): Specifies the model to use for speech-to-text conversion. Available options: saarika:v2.5 (transcription), saaras:v3 (multi-mode: transcribe/translate/verbatim/translit/codemix). Note: saarika:v1, saarika:v2, and saarika:flash have been deprecated by Sarvam.
 
-**listeningModel.languageCode** (`SarvamSTTLanguage`): Specifies the language of the input audio. This parameter is required to ensure accurate transcription. For the saarika:v1 model, this parameter is mandatory. For the saarika:v2 model, it is optional. unknown: Use this when the language is not known; the API will detect it automatically. Note:- that the saarika:v1 model does not support unknown language code. Available options: unknown, hi-IN, bn-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN, en-IN, gu-IN
+**listeningModel.languageCode** (`SarvamSTTLanguage`): BCP-47 language code of the input audio. Optional for saarika:v2.5 and saaras:v3 (the API will detect the language automatically when 'unknown' is passed). Available options: unknown, hi-IN, bn-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN, en-IN, gu-IN.
 
 **listeningModel.filetype** (`'mp3' | 'wav'`): Audio format of the input stream.
 
+**listeningModel.mode** (`SarvamSTTMode`): Operation mode. Only valid when using the saaras:v3 model; ignored by saarika:v2.5. Available options: 'transcribe', 'translate', 'verbatim', 'translit', 'codemix'.
+
 ## Methods
 
 ### `speak()`
@@ -121,4 +125,6 @@ Returns: `Promise<Array<{voiceId: SarvamVoiceId}>>`
 - If no API key is provided, the constructor will throw an error
 - The service communicates with the Sarvam AI API at `https://api.sarvam.ai`
 - Audio is returned as a stream containing binary audio data
-- Speech recognition supports mp3 and wav audio formats
+- Speech recognition supports mp3 and wav audio formats
+- `bulbul:v1`, `saarika:v1`, `saarika:v2`, and `saarika:flash` have been deprecated by Sarvam and are no longer supported. Use `bulbul:v3` (or `bulbul:v2`) for TTS and `saarika:v2.5` (or `saaras:v3`) for STT.
+- Speaker names are not interchangeable between `bulbul:v2` and `bulbul:v3` — each model version has its own speaker catalog.

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @mastra/mcp-docs-server
 
+## 1.1.25-alpha.8
+
+### Patch Changes
+
+- Updated dependencies [[`cbdf3e1`](https://github.com/mastra-ai/mastra/commit/cbdf3e12b3d0c30a6e5347be658e2009648c130a), [`8fe46d3`](https://github.com/mastra-ai/mastra/commit/8fe46d354027f3f0f0846e64219772348de106dd), [`18c67db`](https://github.com/mastra-ai/mastra/commit/18c67dbb9c9ebc26f26f65f7d3ff836e5691ef46), [`8dcc77e`](https://github.com/mastra-ai/mastra/commit/8dcc77e78a5340f5848f74b9e9f1b3da3513c1f5), [`aa67fc5`](https://github.com/mastra-ai/mastra/commit/aa67fc59ee8a5eeff1f23eb05970b8d7a536c8ff), [`fa8140b`](https://github.com/mastra-ai/mastra/commit/fa8140bcd4251d2e3ac85fdc5547dfc4f372b5be), [`190f452`](https://github.com/mastra-ai/mastra/commit/190f45258b0640e2adfc8219fa3258cdc5b8f071), [`7e7bf60`](https://github.com/mastra-ai/mastra/commit/7e7bf606886bf374a6f9d4ca9b09dd83d0533372), [`184907d`](https://github.com/mastra-ai/mastra/commit/184907d775d8609c03c26e78ccaf37315f3aa287), [`5f3d4dd`](https://github.com/mastra-ai/mastra/commit/5f3d4ddf237241f4b238ac062ac61eadabed0770), [`0c4cd13`](https://github.com/mastra-ai/mastra/commit/0c4cd131931c04ac5405373c932a242dbe88edd6), [`b16a753`](https://github.com/mastra-ai/mastra/commit/b16a753d5748440248d7df82e29bb987a9c8386c)]:
+  - @mastra/core@1.25.0-alpha.3
+  - @mastra/mcp@1.5.0-alpha.0
+
 ## 1.1.25-alpha.5
 
 ### Patch Changes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/mcp-docs-server",
-  "version": "1.1.25-alpha.7",
+  "version": "1.1.25-alpha.9",
   "description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
   "type": "module",
   "main": "dist/index.js",
@@ -29,8 +29,8 @@
     "jsdom": "^26.1.0",
     "local-pkg": "^1.1.2",
     "zod": "^4.3.6",
-    "@mastra/core": "1.25.0-alpha.2",
-    "@mastra/mcp": "^1.4.2"
+    "@mastra/core": "1.25.0-alpha.3",
+    "@mastra/mcp": "^1.5.0-alpha.0"
   },
   "devDependencies": {
     "@hono/node-server": "^1.19.11",
@@ -48,7 +48,7 @@
     "vitest": "4.0.18",
     "@internal/lint": "0.0.82",
     "@internal/types-builder": "0.0.57",
-    "@mastra/core": "1.25.0-alpha.2"
+    "@mastra/core": "1.25.0-alpha.3"
   },
   "homepage": "https://mastra.ai",
   "repository": {