@mastra/core 1.2.0 → 1.2.1-alpha.0

package/dist/docs/{agents/10-adding-voice.md → references/docs-agents-adding-voice.md}

@@ -164,7 +164,7 @@ The following files are created:
 - **hybrid-question.mp3** – Hybrid agent's spoken question.
 - **unified-response.mp3** – Unified agent's spoken response.
 
-```typescript title="src/test-voice-agents.ts"
+```typescript
 import "dotenv/config";
 
 import path from "path";
@@ -323,15 +323,16 @@ const voice = new CompositeVoice({
 ```
 
 For the complete list of supported AI SDK providers and their capabilities:
-* [Transcription](https://ai-sdk.dev/docs/providers/openai/transcription)
-* [Speech](https://ai-sdk.dev/docs/providers/elevenlabs/speech)
+
+- [Transcription](https://ai-sdk.dev/docs/providers/openai/transcription)
+- [Speech](https://ai-sdk.dev/docs/providers/elevenlabs/speech)
 
 ## Supported Voice Providers
 
 Mastra supports multiple voice providers for text-to-speech (TTS) and speech-to-text (STT) capabilities:
 
-| Provider        | Package                         | Features                  | Reference                                         |
-| --------------- | ------------------------------- | ------------------------- | ------------------------------------------------- |
+| Provider        | Package                         | Features                  | Reference                                                          |
+| --------------- | ------------------------------- | ------------------------- | ------------------------------------------------------------------ |
 | OpenAI          | `@mastra/voice-openai`          | TTS, STT                  | [Documentation](https://mastra.ai/reference/voice/openai)          |
 | OpenAI Realtime | `@mastra/voice-openai-realtime` | Realtime speech-to-speech | [Documentation](https://mastra.ai/reference/voice/openai-realtime) |
 | ElevenLabs      | `@mastra/voice-elevenlabs`      | High-quality TTS          | [Documentation](https://mastra.ai/reference/voice/elevenlabs)      |

package/dist/docs/{agents/08-agent-approval.md → references/docs-agents-agent-approval.md}

@@ -1,5 +1,3 @@
-> Learn how to require approvals, suspend tool execution, and automatically resume suspended tools while keeping humans in control of agent workflows.
-
 # Agent Approval
 
 Agents sometimes require the same [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) oversight used in workflows when calling tools that handle sensitive operations, like deleting resources or performing running long processes. With agent approval you can suspend a tool call and provide feedback to the user, or approve or decline a tool call based on targeted application conditions.
@@ -12,7 +10,7 @@ Tool call approval can be enabled at the agent level and apply to every tool the
 
 Agent approval uses a snapshot to capture the state of the request. Ensure you've enabled a storage provider in your main Mastra instance. If storage isn't enabled you'll see an error relating to snapshot not found.
 
-```typescript title="src/mastra/index.ts"
+```typescript
 import { Mastra } from "@mastra/core/mastra";
 import { LibSQLStore } from "@mastra/libsql";
 
@@ -117,13 +115,13 @@ if (output.finishReason === "suspended") {
 
 ### Stream vs Generate comparison
 
-| Aspect | `stream()` | `generate()` |
-|--------|-----------|--------------|
-| Response type | Streaming chunks | Complete response |
-| Approval detection | `tool-call-approval` chunk | `finishReason: 'suspended'` |
-| Approve method | `approveToolCall({ runId })` | `approveToolCallGenerate({ runId, toolCallId })` |
-| Decline method | `declineToolCall({ runId })` | `declineToolCallGenerate({ runId, toolCallId })` |
-| Result | Stream to iterate | Full output object |
+| Aspect             | `stream()`                   | `generate()`                                     |
+| ------------------ | ---------------------------- | ------------------------------------------------ |
+| Response type      | Streaming chunks             | Complete response                                |
+| Approval detection | `tool-call-approval` chunk   | `finishReason: 'suspended'`                      |
+| Approve method     | `approveToolCall({ runId })` | `approveToolCallGenerate({ runId, toolCallId })` |
+| Decline method     | `declineToolCall({ runId })` | `declineToolCallGenerate({ runId, toolCallId })` |
+| Result             | Stream to iterate            | Full output object                               |
 
 ## Tool-level approval
 
@@ -231,7 +229,6 @@ const handleResume = async () => {
   }
   process.stdout.write("\n");
 };
-
 ```
 
 ## Automatic tool resumption
@@ -270,8 +267,11 @@ const stream = await agent.stream("What's the weather?", {
 When `autoResumeSuspendedTools` is enabled:
 
 1. A tool suspends execution by calling `suspend()` with a payload (e.g., requesting more information)
+
 2. The suspension is persisted to memory along with the conversation
+
 3. When the user sends their next message on the same thread, the agent:
+
    - Detects the suspended tool from message history
    - Extracts `resumeData` from the user's message based on the tool's `resumeSchema`
    - Automatically resumes the tool with the extracted data
@@ -341,7 +341,7 @@ const handleResume = async () => {
 
 **Conversation flow:**
 
-```
+```text
 User: "What's the weather like?"
 Agent: "What city do you want to know the weather for?"
 
@@ -361,17 +361,17 @@ For automatic tool resumption to work:
 
 ### Manual vs automatic resumption
 
-| Approach | Use case |
-|----------|----------|
-| Manual (`resumeStream()`) | Programmatic control, webhooks, button clicks, external triggers |
+| Approach                               | Use case                                                                 |
+| -------------------------------------- | ------------------------------------------------------------------------ |
+| Manual (`resumeStream()`)              | Programmatic control, webhooks, button clicks, external triggers         |
 | Automatic (`autoResumeSuspendedTools`) | Conversational flows where users provide resume data in natural language |
 
 Both approaches work with the same tool definitions. Automatic resumption triggers only when suspended tools exist in the message history and the user sends a new message on the same thread.
 
 ## Related
 
-- [Using Tools](./using-tools)
-- [Agent Overview](./overview)
-- [Tools Overview](../mcp/overview)
-- [Agent Memory](./agent-memory)
+- [Using Tools](https://mastra.ai/docs/agents/using-tools)
+- [Agent Overview](https://mastra.ai/docs/agents/overview)
+- [Tools Overview](https://mastra.ai/docs/mcp/overview)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)
 - [Request Context](https://mastra.ai/docs/server/request-context)

package/dist/docs/{agents/03-agent-memory.md → references/docs-agents-agent-memory.md}

@@ -1,10 +1,8 @@
-> Learn how to add memory to agents to store message history and maintain context across interactions.
-
 # Agent memory
 
 Agents use memory to maintain context across interactions. LLMs are stateless and don't retain information between calls, so agents need memory to track message history and recall relevant information.
 
-Mastra agents can be configured to store message history, with optional [working memory](../memory/working-memory) to maintain recent context or [semantic recall](../memory/semantic-recall) to retrieve past messages based on meaning.
+Mastra agents can be configured to store message history, with optional [working memory](https://mastra.ai/docs/memory/working-memory) to maintain recent context or [semantic recall](https://mastra.ai/docs/memory/semantic-recall) to retrieve past messages based on meaning.
 
 ## When to use memory
 
@@ -14,66 +12,74 @@ Use memory when your agent needs to maintain multi-turn conversations that refer
 
 To enable memory in Mastra, install the `@mastra/memory` package along with a storage provider.
 
-```bash npm2yarn
+**npm**:
+
+```bash
 npm install @mastra/memory@latest @mastra/libsql@latest
 ```
 
-## Storage providers
+**pnpm**:
 
-Memory requires a storage provider to persist message history, including user messages and agent responses. For more details on available providers and how storage works in Mastra, see the [Storage](https://mastra.ai/docs/memory/storage) documentation.
-
-## Configuring memory
+```bash
+pnpm add @mastra/memory@latest @mastra/libsql@latest
+```
 
-  ### Step
+**Yarn**:
 
-Enable memory by creating a `Memory` instance and passing it to the agent’s `memory` option.
+```bash
+yarn add @mastra/memory@latest @mastra/libsql@latest
+```
 
-```typescript {7-11} title="src/mastra/agents/memory-agent.ts"
-import { Agent } from "@mastra/core/agent";
-import { Memory } from "@mastra/memory";
+**Bun**:
 
-export const memoryAgent = new Agent({
-  id: 'memory-agent',
-  name: 'Memory Agent',
-  memory: new Memory({
-    options: {
-      lastMessages: 20,
-    },
-  }),
-});
+```bash
+bun add @mastra/memory@latest @mastra/libsql@latest
 ```
 
-> **Note:**
+## Storage providers
 
-Visit [Memory Class](https://mastra.ai/reference/memory/memory-class) for a full list of configuration options.
+Memory requires a storage provider to persist message history, including user messages and agent responses. For more details on available providers and how storage works in Mastra, see the [Storage](https://mastra.ai/docs/memory/storage) documentation.
 
-  
+## Configuring memory
 
-  ### Step
+1. Enable memory by creating a `Memory` instance and passing it to the agent’s `memory` option.
 
-Add a storage provider to your main Mastra instance to enable memory across all configured agents.
+   ```typescript
+   import { Agent } from "@mastra/core/agent";
+   import { Memory } from "@mastra/memory";
 
-```typescript {5-8} title="src/mastra/index.ts"
-import { Mastra } from "@mastra/core";
-import { LibSQLStore } from "@mastra/libsql";
+   export const memoryAgent = new Agent({
+     id: 'memory-agent',
+     name: 'Memory Agent',
+     memory: new Memory({
+       options: {
+         lastMessages: 20,
+       },
+     }),
+   });
+   ```
 
-export const mastra = new Mastra({
-  storage: new LibSQLStore({
-    id: 'mastra-storage',
-    url: ":memory:",
-  }),
-});
-```
+   > **Info:** Visit [Memory Class](https://mastra.ai/reference/memory/memory-class) for a full list of configuration options.
+
+2. Add a storage provider to your main Mastra instance to enable memory across all configured agents.
 
-> **Note:**
+   ```typescript
+   import { Mastra } from "@mastra/core";
+   import { LibSQLStore } from "@mastra/libsql";
 
-Visit [libSQL Storage](https://mastra.ai/reference/storage/libsql) for a full list of configuration options.
+   export const mastra = new Mastra({
+     storage: new LibSQLStore({
+       id: 'mastra-storage',
+       url: ":memory:",
+     }),
+   });
+   ```
 
-  
+   > **Info:** Visit [libSQL Storage](https://mastra.ai/reference/storage/libsql) for a full list of configuration options.
 
 Alternatively, add storage directly to an agent’s memory to keep data separate or use different providers per agent.
 
-```typescript {9-12} title="src/mastra/agents/memory-agent.ts"
+```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
 import { LibSQLStore } from "@mastra/libsql";
@@ -90,8 +96,7 @@ export const memoryAgent = new Agent({
 });
 ```
 
-> **Mastra Cloud Store limitation**
-Agent-level storage is not supported when using [Mastra Cloud Store](https://mastra.ai/docs/mastra-cloud/deployment#using-mastra-cloud-store). If you use Mastra Cloud Store, configure storage on the Mastra instance instead. This limitation does not apply if you bring your own database.
+> **Mastra Cloud Store limitation:** Agent-level storage is not supported when using [Mastra Cloud Store](https://mastra.ai/docs/mastra-cloud/deployment). If you use Mastra Cloud Store, configure storage on the Mastra instance instead. This limitation does not apply if you bring your own database.
 
 ## Message history
 
@@ -102,7 +107,7 @@ Include a `memory` object with both `resource` and `thread` to track message his
 
 These fields tell the agent where to store and retrieve context, enabling persistent, thread-aware memory across a conversation.
 
-```typescript {4-7}
+```typescript
 const response = await memoryAgent.generate(
   "Remember my favorite color is blue.",
   {
@@ -116,7 +121,7 @@ const response = await memoryAgent.generate(
 
 To recall information stored in memory, call the agent with the same `resource` and `thread` values used in the original conversation.
 
-```typescript {2-5}
+```typescript
 const response = await memoryAgent.generate("What's my favorite color?", {
   memory: {
     resource: "user-123",
@@ -125,16 +130,15 @@ const response = await memoryAgent.generate("What's my favorite color?", {
 });
 ```
 
-> **Note:**
-Each thread has an owner (`resourceId`) that cannot be changed after creation. Avoid reusing the same thread ID for threads with different owners, as this will cause errors when querying.
+> **Warning:** Each thread has an owner (`resourceId`) that cannot be changed after creation. Avoid reusing the same thread ID for threads with different owners, as this will cause errors when querying.
 
-To learn more about memory see the [Memory](../memory/overview) documentation.
+To learn more about memory see the [Memory](https://mastra.ai/docs/memory/overview) documentation.
 
 ## Using `RequestContext`
 
 Use [RequestContext](https://mastra.ai/docs/server/request-context) to access request-specific values. This lets you conditionally select different memory or storage configurations based on the context of the request.
 
-```typescript title="src/mastra/agents/memory-agent.ts"
+```typescript
 export type UserTier = {
   "user-tier": "enterprise" | "pro";
 };
@@ -154,13 +158,11 @@ export const memoryAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [Request Context](https://mastra.ai/docs/server/request-context) for more information.
+> **Info:** Visit [Request Context](https://mastra.ai/docs/server/request-context) for more information.
 
 ## Related
 
-- [Working Memory](../memory/working-memory)
-- [Semantic Recall](../memory/semantic-recall)
-- [Storage](../memory/storage)
+- [Working Memory](https://mastra.ai/docs/memory/working-memory)
+- [Semantic Recall](https://mastra.ai/docs/memory/semantic-recall)
+- [Storage](https://mastra.ai/docs/memory/storage)
 - [Request Context](https://mastra.ai/docs/server/request-context)

package/dist/docs/{agents/07-guardrails.md → references/docs-agents-guardrails.md}

@@ -1,5 +1,3 @@
-> Learn how to implement guardrails using input and output processors to secure and control AI interactions.
-
 # Guardrails
 
 Agents use processors to apply guardrails to inputs and outputs. They run before or after each interaction, giving you a way to review, transform, or block information as it passes between the user and the agent.
@@ -19,7 +17,7 @@ Use processors for content moderation, prompt injection prevention, response san
 
 Import and instantiate the relevant processor class, and pass it to your agent’s configuration using either the `inputProcessors` or `outputProcessors` option:
 
-```typescript {2,9-17} title="src/mastra/agents/moderated-agent.ts"
+```typescript
 import { Agent } from "@mastra/core/agent";
 import { ModerationProcessor } from "@mastra/core/processors";
 
@@ -48,7 +46,7 @@ Input processors are applied before user messages reach the language model. They
 
 The `UnicodeNormalizer` is an input processor that cleans and normalizes user input by unifying Unicode characters, standardizing whitespace, and removing problematic symbols, allowing the LLM to better understand user messages.
 
-```typescript {7-10} title="src/mastra/agents/normalized-agent.ts"
+```typescript
 import { UnicodeNormalizer } from "@mastra/core/processors";
 
 export const normalizedAgent = new Agent({
@@ -63,15 +61,13 @@ export const normalizedAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [UnicodeNormalizer](https://mastra.ai/reference/processors/unicode-normalizer) for a full list of configuration options.
+> **Info:** Visit [UnicodeNormalizer](https://mastra.ai/reference/processors/unicode-normalizer) for a full list of configuration options.
 
 ### Preventing prompt injection
 
 The `PromptInjectionDetector` is an input processor that scans user messages for prompt injection, jailbreak attempts, and system override patterns. It uses an LLM to classify risky input and can block or rewrite it before it reaches the model.
 
-```typescript {7-12} title="src/mastra/agents/secure-agent.ts"
+```typescript
 import { PromptInjectionDetector } from "@mastra/core/processors";
 
 export const secureAgent = new Agent({
@@ -88,15 +84,13 @@ export const secureAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [PromptInjectionDetector](https://mastra.ai/reference/processors/prompt-injection-detector) for a full list of configuration options.
+> **Info:** Visit [PromptInjectionDetector](https://mastra.ai/reference/processors/prompt-injection-detector) for a full list of configuration options.
 
 ### Detecting and translating language
 
 The `LanguageDetector` is an input processor that detects and translates user messages into a target language, enabling multilingual support while maintaining consistent interaction. It uses an LLM to identify the language and perform the translation.
 
-```typescript {7-12} title="src/mastra/agents/multilingual-agent.ts"
+```typescript
 import { LanguageDetector } from "@mastra/core/processors";
 
 export const multilingualAgent = new Agent({
@@ -113,9 +107,7 @@ export const multilingualAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [LanguageDetector](https://mastra.ai/reference/processors/language-detector) for a full list of configuration options.
+> **Info:** Visit [LanguageDetector](https://mastra.ai/reference/processors/language-detector) for a full list of configuration options.
 
 ## Output processors
 
@@ -125,7 +117,7 @@ Output processors are applied after the language model generates a response, but
 
 The `BatchPartsProcessor` is an output processor that combines multiple stream parts before emitting them to the client. This reduces network overhead and improves the user experience by consolidating small chunks into larger batches.
 
-```typescript {7-11} title="src/mastra/agents/batched-agent.ts"
+```typescript
 import { BatchPartsProcessor } from "@mastra/core/processors";
 
 export const batchedAgent = new Agent({
@@ -141,15 +133,13 @@ export const batchedAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [BatchPartsProcessor](https://mastra.ai/reference/processors/batch-parts-processor) for a full list of configuration options.
+> **Info:** Visit [BatchPartsProcessor](https://mastra.ai/reference/processors/batch-parts-processor) for a full list of configuration options.
 
 ### Limiting token usage
 
 The `TokenLimiterProcessor` is an output processor that limits the number of tokens in model responses. It helps manage cost and performance by truncating or blocking messages when the limit is exceeded.
 
-```typescript {7-11} title="src/mastra/agents/limited-agent.ts"
+```typescript
 import { TokenLimiterProcessor } from "@mastra/core/processors";
 
 export const limitedAgent = new Agent({
@@ -165,15 +155,13 @@ export const limitedAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [TokenLimiterProcessor](https://mastra.ai/reference/processors/token-limiter-processor) for a full list of configuration options.
+> **Info:** Visit [TokenLimiterProcessor](https://mastra.ai/reference/processors/token-limiter-processor) for a full list of configuration options.
 
 ### Scrubbing system prompts
 
 The `SystemPromptScrubber` is an output processor that detects and redacts system prompts or other internal instructions from model responses. It helps prevent unintended disclosure of prompt content or configuration details that could introduce security risks. It uses an LLM to identify and redact sensitive content based on configured detection types.
 
-```typescript {7-16} title="src/mastra/agents/scrubbed-agent.ts"
+```typescript
 import { SystemPromptScrubber } from "@mastra/core/processors";
 
 const scrubbedAgent = new Agent({
@@ -194,12 +182,9 @@ const scrubbedAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [SystemPromptScrubber](https://mastra.ai/reference/processors/system-prompt-scrubber) for a full list of configuration options.
+> **Info:** Visit [SystemPromptScrubber](https://mastra.ai/reference/processors/system-prompt-scrubber) for a full list of configuration options.
 
-> **Note:**
-When streaming responses over HTTP, Mastra redacts sensitive request data (system prompts, tool definitions, API keys) from stream chunks at the server level by default. See [Stream data redaction](https://mastra.ai/docs/server/mastra-server#stream-data-redaction) for details.
+> **Note:** When streaming responses over HTTP, Mastra redacts sensitive request data (system prompts, tool definitions, API keys) from stream chunks at the server level by default. See [Stream data redaction](https://mastra.ai/docs/server/mastra-server) for details.
 
 ## Hybrid processors
 
@@ -209,7 +194,7 @@ Hybrid processors can be applied either before messages are sent to the language
 
 The `ModerationProcessor` is a hybrid processor that detects inappropriate or harmful content across categories like hate, harassment, and violence. It can be used to moderate either user input or model output, depending on where it's applied. It uses an LLM to classify the message and can block or rewrite it based on your configuration.
 
-```typescript {7-12,15} title="src/mastra/agents/moderated-agent.ts"
+```typescript
 import { ModerationProcessor } from "@mastra/core/processors";
 
 export const moderatedAgent = new Agent({
@@ -229,15 +214,13 @@ export const moderatedAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [ModerationProcessor](https://mastra.ai/reference/processors/moderation-processor) for a full list of configuration options.
+> **Info:** Visit [ModerationProcessor](https://mastra.ai/reference/processors/moderation-processor) for a full list of configuration options.
 
 ### Detecting and redacting PII
 
 The `PIIDetector` is a hybrid processor that detects and removes personally identifiable information such as emails, phone numbers, and credit cards. It can redact either user input or model output, depending on where it's applied. It uses an LLM to identify sensitive content based on configured detection types.
 
-```typescript {7-14,17} title="src/mastra/agents/private-agent.ts"
+```typescript
 import { PIIDetector } from "@mastra/core/processors";
 
 export const privateAgent = new Agent({
@@ -259,9 +242,7 @@ export const privateAgent = new Agent({
 });
 ```
 
-> **Note:**
-
-Visit [PIIDetector](https://mastra.ai/reference/processors/pii-detector) for a full list of configuration options.
+> **Info:** Visit [PIIDetector](https://mastra.ai/reference/processors/pii-detector) for a full list of configuration options.
 
 ## Applying multiple processors
 
@@ -275,7 +256,7 @@ A typical order might be:
 
 The order affects behavior, so arrange processors to suit your goals.
 
-```typescript title="src/mastra/agents/test-agent.ts"
+```typescript
 import {
   UnicodeNormalizer,
   ModerationProcessor,
@@ -301,7 +282,7 @@ Many of the built-in processors support a `strategy` parameter that controls how
 
 Most strategies allow the request to continue without interruption. When `block` is used, the processor calls its internal `abort()` function, which immediately stops the request and prevents any subsequent processors from running.
 
-```typescript {8} title="src/mastra/agents/private-agent.ts"
+```typescript
 import { PIIDetector } from "@mastra/core/processors";
 
 export const privateAgent = new Agent({
@@ -384,6 +365,7 @@ export class QualityChecker implements Processor {
 ```
 
 The `abort()` function accepts an optional second parameter with:
+
 - `retry: true` - Request the LLM retry the step
 - `metadata: unknown` - Attach additional data for debugging/logging
 

package/dist/docs/{agents/09-network-approval.md → references/docs-agents-network-approval.md}

@@ -1,5 +1,3 @@
-> Learn how to require approvals, suspend execution, and resume suspended networks while keeping humans in control of agent network workflows.
-
 # Network Approval
 
 Agent networks can require the same [human-in-the-loop](https://mastra.ai/docs/workflows/human-in-the-loop) oversight used in individual agents and workflows. When a tool, sub-agent, or workflow within a network requires approval or suspends execution, the network pauses and emits events that allow your application to collect user input before resuming.
@@ -8,7 +6,7 @@ Agent networks can require the same [human-in-the-loop](https://mastra.ai/docs/w
 
 Network approval uses snapshots to capture execution state. Ensure you've enabled a storage provider in your Mastra instance. If storage isn't enabled you'll see an error relating to snapshot not found.
 
-```typescript title="src/mastra/index.ts"
+```typescript
 import { Mastra } from "@mastra/core/mastra";
 import { LibSQLStore } from "@mastra/libsql";
 
@@ -37,7 +35,7 @@ let runId: string;
 for await (const chunk of stream) {
   runId = stream.runId;
   // if the requirApproval is in a tool inside a subAgent or the subAgent has requireToolApproval set to true
-  if (chunk.type === "agent-execution-approval") { 
+  if (chunk.type === "agent-execution-approval") {
     console.log("Tool requires approval:", chunk.payload);
   }
 
@@ -199,8 +197,11 @@ const stream = await routingAgent.network("Process this request", {
 When `autoResumeSuspendedTools` is enabled:
 
 1. A primitive suspends execution by calling `suspend()` with a payload
+
 2. The suspension is persisted to memory along with the conversation
+
 3. When the user sends their next message on the same thread, the network:
+
    - Detects the suspended primitive from message history
    - Extracts `resumeData` from the user's message based on the tool's `resumeSchema`
    - Automatically resumes the primitive with the extracted data
@@ -241,7 +242,7 @@ for await (const chunk of resumedStream) {
 
 **Conversation flow:**
 
-```
+```text
 User: "Delete the old records"
 Agent: "Please confirm: delete old records"
 
@@ -259,16 +260,16 @@ For automatic tool resumption to work:
 
 ### Manual vs automatic resumption
 
-| Approach | Use case |
-|----------|----------|
-| Manual (`resumeNetwork()`) | Programmatic control, webhooks, button clicks, external triggers |
+| Approach                               | Use case                                                                 |
+| -------------------------------------- | ------------------------------------------------------------------------ |
+| Manual (`resumeNetwork()`)             | Programmatic control, webhooks, button clicks, external triggers         |
 | Automatic (`autoResumeSuspendedTools`) | Conversational flows where users provide resume data in natural language |
 
 Both approaches work with the same tool definitions. Automatic resumption triggers only when suspended tools exist in the message history and the user sends a new message on the same thread.
 
 ## Related
 
-- [Agent Networks](./networks)
-- [Agent Approval](./agent-approval)
+- [Agent Networks](https://mastra.ai/docs/agents/networks)
+- [Agent Approval](https://mastra.ai/docs/agents/agent-approval)
 - [Human-in-the-Loop](https://mastra.ai/docs/workflows/human-in-the-loop)
-- [Agent Memory](./agent-memory)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)

package/dist/docs/{agents/05-networks.md → references/docs-agents-networks.md}

@@ -1,5 +1,3 @@
-> Learn how to coordinate multiple agents, workflows, and tools using agent networks for complex, non-deterministic task execution.
-
 # Agent Networks
 
 Agent networks in Mastra coordinate multiple agents, workflows, and tools to handle tasks that aren't clearly defined upfront but can be inferred from the user's message or context. A top-level **routing agent** (a Mastra agent with other agents, workflows, and tools configured) uses an LLM to interpret the request and decide which primitives (sub-agents, workflows, or tools) to call, in what order, and with what data.
@@ -20,7 +18,7 @@ Mastra agent networks operate using these principles:
 
 An agent network is built around a top-level routing agent that delegates tasks to agents, workflows, and tools defined in its configuration. Memory is configured on the routing agent using the `memory` option, and `instructions` define the agent's routing behavior.
 
-```typescript {22-23,26,29} title="src/mastra/agents/routing-agent.ts"
+```typescript
 import { Agent } from "@mastra/core/agent";
 import { Memory } from "@mastra/memory";
 import { LibSQLStore } from "@mastra/libsql";
@@ -68,7 +66,7 @@ When configuring a Mastra agent network, each primitive (agent, workflow, or too
 
 Each agent in a network should include a clear `description` that explains what the agent does.
 
-```typescript title="src/mastra/agents/research-agent.ts"
+```typescript
 export const researchAgent = new Agent({
   id: "research-agent",
   name: "Research Agent",
@@ -78,7 +76,7 @@ export const researchAgent = new Agent({
 });
 ```
 
-```typescript title="src/mastra/agents/writing-agent.ts"
+```typescript
 export const writingAgent = new Agent({
   id: "writing-agent",
   name: "Writing Agent",
@@ -92,7 +90,7 @@ export const writingAgent = new Agent({
 
 Workflows in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
 
-```typescript title="src/mastra/workflows/city-workflow.ts"
+```typescript
 export const cityWorkflow = createWorkflow({
   id: "city-workflow",
   description: `This workflow handles city-specific research tasks.
@@ -112,7 +110,7 @@ export const cityWorkflow = createWorkflow({
 
 Tools in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
 
-```typescript title="src/mastra/tools/weather-tool.ts"
+```typescript
 export const weatherTool = createTool({
   id: "weather-tool",
   description: ` Retrieves current weather information using the wttr.in API.
@@ -286,7 +284,7 @@ const final = await stream.object;
 
 ## Related
 
-- [Agent Memory](./agent-memory)
-- [Workflows Overview](../workflows/overview)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)
+- [Workflows Overview](https://mastra.ai/docs/workflows/overview)
 - [Request Context](https://mastra.ai/docs/server/request-context)
 - [Supervisor example](https://github.com/mastra-ai/mastra/tree/main/examples/supervisor-agent)