@mastra/core 1.7.0 → 1.8.0

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

@@ -0,0 +1,275 @@
+# 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, subagent, 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.
+
+## Storage
+
+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
+import { Mastra } from '@mastra/core/mastra'
+import { LibSQLStore } from '@mastra/libsql'
+
+export const mastra = new Mastra({
+  storage: new LibSQLStore({
+    id: 'mastra-storage',
+    url: ':memory:',
+  }),
+})
+```
+
+## Approving network tool calls
+
+When a tool within a network has `requireApproval: true`, the network stream emits an `agent-execution-approval` chunk and pauses. To allow the tool to execute, call `approveNetworkToolCall` with the `runId`.
+
+```typescript
+const stream = await routingAgent.network('Process this query', {
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+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') {
+    console.log('Tool requires approval:', chunk.payload)
+  }
+
+  // if the requirApproval is in a tool directly in the network agent
+  if (chunk.type === 'tool-execution-approval') {
+    console.log('Tool requires approval:', chunk.payload)
+  }
+}
+
+// Approve and resume execution
+const approvedStream = await routingAgent.approveNetworkToolCall({
+  runId,
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+for await (const chunk of approvedStream) {
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+## Declining network tool calls
+
+To decline a pending tool call and prevent execution, call `declineNetworkToolCall`. The network continues without executing the tool.
+
+```typescript
+const declinedStream = await routingAgent.declineNetworkToolCall({
+  runId,
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+for await (const chunk of declinedStream) {
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+## Resuming suspended networks
+
+When a primitive in the network calls `suspend()`, the stream emits an `agent-execution-suspended`/`tool-execution-suspended`/`workflow-execution-suspended` chunk with a `suspendPayload` containing context from the primitive. Use `resumeNetwork` to provide the data requested by the primitive and continue execution.
+
+```typescript
+import { createTool } from '@mastra/core/tools'
+import { z } from 'zod'
+
+const confirmationTool = createTool({
+  id: 'confirmation-tool',
+  description: 'Requests user confirmation before proceeding',
+  inputSchema: z.object({
+    action: z.string(),
+  }),
+  outputSchema: z.object({
+    confirmed: z.boolean(),
+    action: z.string(),
+  }),
+  suspendSchema: z.object({
+    message: z.string(),
+    action: z.string(),
+  }),
+  resumeSchema: z.object({
+    confirmed: z.boolean(),
+  }),
+  execute: async (inputData, context) => {
+    const { resumeData, suspend } = context?.agent ?? {}
+
+    if (!resumeData?.confirmed) {
+      return suspend?.({
+        message: `Please confirm: ${inputData.action}`,
+        action: inputData.action,
+      })
+    }
+
+    return { confirmed: true, action: inputData.action }
+  },
+})
+```
+
+Handle the suspension and resume with user-provided data:
+
+```typescript
+const stream = await routingAgent.network('Delete the old records', {
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+for await (const chunk of stream) {
+  if (chunk.type === 'workflow-execution-suspended') {
+    console.log(chunk.payload.suspendPayload)
+    // { message: "Please confirm: delete old records", action: "delete old records" }
+  }
+}
+
+// Resume with user confirmation
+const resumedStream = await routingAgent.resumeNetwork(
+  { confirmed: true },
+  {
+    runId: stream.runId,
+    memory: {
+      thread: 'user-123',
+      resource: 'my-app',
+    },
+  },
+)
+
+for await (const chunk of resumedStream) {
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+## Automatic primitive resumption
+
+When using primitives that call `suspend()`, you can enable automatic resumption so the network resumes suspended primitives based on the user's next message. This creates a conversational flow where users provide the required information naturally.
+
+### Enabling auto-resume
+
+Set `autoResumeSuspendedTools` to `true` in the agent's `defaultNetworkOptions` or when calling `network()`:
+
+```typescript
+import { Agent } from '@mastra/core/agent'
+import { Memory } from '@mastra/memory'
+
+// Option 1: In agent configuration
+const routingAgent = new Agent({
+  id: 'routing-agent',
+  name: 'Routing Agent',
+  instructions: 'You coordinate tasks across multiple agents',
+  model: 'openai/gpt-4o-mini',
+  tools: { confirmationTool },
+  memory: new Memory(),
+  defaultNetworkOptions: {
+    autoResumeSuspendedTools: true,
+  },
+})
+
+// Option 2: Per-request
+const stream = await routingAgent.network('Process this request', {
+  autoResumeSuspendedTools: true,
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+```
+
+### How it works
+
+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
+
+### Example
+
+```typescript
+const stream = await routingAgent.network('Delete the old records', {
+  autoResumeSuspendedTools: true,
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+for await (const chunk of stream) {
+  if (chunk.type === 'workflow-execution-suspended') {
+    console.log(chunk.payload.suspendPayload)
+    // { message: "Please confirm: delete old records", action: "delete old records" }
+  }
+}
+
+// User provides confirmation in their next message
+const resumedStream = await routingAgent.network('Yes, confirmed', {
+  autoResumeSuspendedTools: true,
+  memory: {
+    thread: 'user-123',
+    resource: 'my-app',
+  },
+})
+
+for await (const chunk of resumedStream) {
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+**Conversation flow:**
+
+```text
+User: "Delete the old records"
+Agent: "Please confirm: delete old records"
+
+User: "Yes, confirmed"
+Agent: "Records deleted successfully"
+```
+
+### Requirements
+
+For automatic tool resumption to work:
+
+- **Memory configured**: The agent needs memory to track suspended tools across messages
+- **Same thread**: The follow-up message must use the same memory thread and resource identifiers
+- **`resumeSchema` defined**: The tool (either directly in the network agent or in a subAgent) / workflow (step that gets suspended) must define a `resumeSchema` so the agent knows what data to extract from the user's message
+
+### Manual vs automatic resumption
+
+| 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](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](https://mastra.ai/docs/agents/agent-memory)

package/dist/docs/references/docs-agents-networks.md

@@ -0,0 +1,299 @@
+# Agent Networks
+
+> **Supervisor Pattern Recommended:** The [supervisor pattern](https://mastra.ai/docs/agents/supervisor-agents) using `agent.stream()` or `agent.generate()` is now the recommended approach for coordinating multiple agents. It provides the same multi-agent coordination capabilities as `.network()` with significant improvements:
+>
+> - **Better control**: Iteration hooks, delegation hooks, and task completion scoring give you fine-grained control over execution
+> - **Simpler API**: Uses familiar `stream()` and `generate()` methods instead of a separate `.network()` API
+> - **More flexible**: Stop execution early, modify delegations, filter context, and provide feedback to guide the agent
+> - **Type-safe**: Full TypeScript support for all hooks and callbacks
+> - **Easier debugging**: Monitor progress with `onIterationComplete`, track delegations with `onDelegationStart`/`onDelegationComplete`
+>
+> See the [migration guide](https://mastra.ai/guides/migrations/network-to-supervisor) to upgrade from `.network()`.
+
+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 (subagents, workflows, or tools) to call, in what order, and with what data.
+
+## When to use networks
+
+Use networks for complex tasks that require coordination across multiple primitives. Unlike workflows, which follow a predefined sequence, networks rely on LLM reasoning to interpret the request and decide what to run.
+
+## Core principles
+
+Mastra agent networks operate using these principles:
+
+- Memory is required when using `.network()` and is used to store task history and determine when a task is complete.
+- Primitives are selected based on their descriptions. Clear, specific descriptions improve routing. For workflows and tools, the input schema helps determine the right inputs at runtime.
+- If multiple primitives have overlapping functionality, the agent favors the more specific one, using a combination of schema and descriptions to decide which to run.
+
+## Creating an agent network
+
+An agent network is built around a top-level routing agent that delegates tasks to subagents, 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
+import { Agent } from '@mastra/core/agent'
+import { Memory } from '@mastra/memory'
+import { LibSQLStore } from '@mastra/libsql'
+
+import { researchAgent } from './research-agent'
+import { writingAgent } from './writing-agent'
+
+import { cityWorkflow } from '../workflows/city-workflow'
+import { weatherTool } from '../tools/weather-tool'
+
+export const routingAgent = new Agent({
+  id: 'routing-agent',
+  name: 'Routing Agent',
+  instructions: `
+      You are a network of writers and researchers.
+      The user will ask you to research a topic.
+      Always respond with a complete report—no bullet points.
+      Write in full paragraphs, like a blog post.
+      Do not answer with incomplete or uncertain information.`,
+  model: 'openai/gpt-5.1',
+  agents: {
+    researchAgent,
+    writingAgent,
+  },
+  workflows: {
+    cityWorkflow,
+  },
+  tools: {
+    weatherTool,
+  },
+  memory: new Memory({
+    storage: new LibSQLStore({
+      id: 'mastra-storage',
+      url: 'file:../mastra.db',
+    }),
+  }),
+})
+```
+
+### Writing descriptions for network primitives
+
+When configuring a Mastra agent network, each primitive (agent, workflow, or tool) needs a clear description to help the routing agent decide which to use. The routing agent uses each primitive's description and schema to determine what it does and how to use it. Clear descriptions and well-defined input and output schemas improve routing accuracy.
+
+#### Agent descriptions
+
+Each subagent in a network should include a clear `description` that explains what the agent does.
+
+```typescript
+export const researchAgent = new Agent({
+  id: 'research-agent',
+  name: 'Research Agent',
+  description: `This agent gathers concise research insights in bullet-point form.
+    It's designed to extract key facts without generating full
+    responses or narrative content.`,
+})
+```
+
+```typescript
+export const writingAgent = new Agent({
+  id: 'writing-agent',
+  name: 'Writing Agent',
+  description: `This agent turns researched material into well-structured
+    written content. It produces full-paragraph reports with no bullet points,
+    suitable for use in articles, summaries, or blog posts.`,
+})
+```
+
+#### Workflow descriptions
+
+Workflows in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
+
+```typescript
+export const cityWorkflow = createWorkflow({
+  id: 'city-workflow',
+  description: `This workflow handles city-specific research tasks.
+    It first gathers factual information about the city, then synthesizes
+    that research into a full written report. Use it when the user input
+    includes a city to be researched.`,
+  inputSchema: z.object({
+    city: z.string(),
+  }),
+  outputSchema: z.object({
+    text: z.string(),
+  }),
+})
+```
+
+#### Tool descriptions
+
+Tools in a network should include a `description` to explain their purpose, along with `inputSchema` and `outputSchema` to describe the expected data.
+
+```typescript
+export const weatherTool = createTool({
+  id: 'weather-tool',
+  description: ` Retrieves current weather information using the wttr.in API.
+    Accepts a city or location name as input and returns a short weather summary.
+    Use this tool whenever up-to-date weather data is requested.
+  `,
+  inputSchema: z.object({
+    location: z.string(),
+  }),
+  outputSchema: z.object({
+    weather: z.string(),
+  }),
+})
+```
+
+## Calling agent networks
+
+Call a Mastra agent network using `.network()` with a user message. The method returns a stream of events that you can iterate over to track execution progress and retrieve the final result.
+
+### Agent example
+
+In this example, the network interprets the message and would route the request to both the `researchAgent` and `writingAgent` to generate a complete response.
+
+```typescript
+const result = await routingAgent.network('Tell me three cool ways to use Mastra')
+
+for await (const chunk of result) {
+  console.log(chunk.type)
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+#### Agent output
+
+The following `chunk.type` events are emitted during this request:
+
+```text
+routing-agent-start
+routing-agent-end
+agent-execution-start
+agent-execution-event-start
+agent-execution-event-step-start
+agent-execution-event-text-start
+agent-execution-event-text-delta
+agent-execution-event-text-end
+agent-execution-event-step-finish
+agent-execution-event-finish
+agent-execution-end
+network-execution-event-step-finish
+```
+
+## Workflow example
+
+In this example, the routing agent recognizes the city name in the message and runs the `cityWorkflow`. The workflow defines steps that call the `researchAgent` to gather facts, then the `writingAgent` to generate the final text.
+
+```typescript
+const result = await routingAgent.network('Tell me some historical facts about London')
+
+for await (const chunk of result) {
+  console.log(chunk.type)
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+### Workflow output
+
+The following `chunk.type` events are emitted during this request:
+
+```text
+routing-agent-end
+workflow-execution-start
+workflow-execution-event-workflow-start
+workflow-execution-event-workflow-step-start
+workflow-execution-event-workflow-step-result
+workflow-execution-event-workflow-finish
+workflow-execution-end
+routing-agent-start
+network-execution-event-step-finish
+```
+
+### Tool example
+
+In this example, the routing agent skips the `researchAgent`, `writingAgent`, and `cityWorkflow`, and calls the `weatherTool` directly to complete the task.
+
+```typescript
+const result = await routingAgent.network("What's the weather in London?")
+
+for await (const chunk of result) {
+  console.log(chunk.type)
+  if (chunk.type === 'network-execution-event-step-finish') {
+    console.log(chunk.payload.result)
+  }
+}
+```
+
+#### Tool output
+
+The following `chunk.type` events are emitted during this request:
+
+```text
+routing-agent-start
+routing-agent-end
+tool-execution-start
+tool-execution-end
+network-execution-event-step-finish
+```
+
+## Structured output
+
+When you need typed, validated results from a network, use the `structuredOutput` option. After the network completes its task, it generates a structured response matching your schema.
+
+```typescript
+import { z } from 'zod'
+
+const resultSchema = z.object({
+  summary: z.string().describe('A brief summary of the findings'),
+  recommendations: z.array(z.string()).describe('List of recommendations'),
+  confidence: z.number().min(0).max(1).describe('Confidence score'),
+})
+
+const stream = await routingAgent.network('Research AI trends', {
+  structuredOutput: {
+    schema: resultSchema,
+  },
+})
+
+// Consume the stream
+for await (const chunk of stream) {
+  if (chunk.type === 'network-object') {
+    // Partial object during generation
+    console.log('Partial:', chunk.payload.object)
+  }
+  if (chunk.type === 'network-object-result') {
+    // Final structured object
+    console.log('Final:', chunk.payload.object)
+  }
+}
+
+// Get the typed result
+const result = await stream.object
+console.log(result?.summary)
+console.log(result?.recommendations)
+console.log(result?.confidence)
+```
+
+### Streaming partial objects
+
+For real-time updates during structured output generation, use `objectStream`:
+
+```typescript
+const stream = await routingAgent.network('Analyze market data', {
+  structuredOutput: { schema: resultSchema },
+})
+
+// Stream partial objects as they're generated
+for await (const partial of stream.objectStream) {
+  console.log('Building result:', partial)
+}
+
+// Get the final typed result
+const final = await stream.object
+```
+
+## Related
+
+- [Supervisor Agents](https://mastra.ai/docs/agents/supervisor-agents)
+- [Migration: .network() to Supervisor Pattern](https://mastra.ai/guides/migrations/network-to-supervisor)
+- [Guide: Research Coordinator](https://mastra.ai/guides/guide/research-coordinator)
+- [Agent Memory](https://mastra.ai/docs/agents/agent-memory)
+- [Agent Approval](https://mastra.ai/docs/agents/agent-approval)
+- [Workflows Overview](https://mastra.ai/docs/workflows/overview)
+- [Request Context](https://mastra.ai/docs/server/request-context)