@mastra/libsql 0.0.0-structured-output-issue-20260302184919 → 0.0.0-structured-output-errors-20260409185629

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

@@ -1,82 +1,100 @@
-# Agent Approval
+# 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.
+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 running long processes. With agent approval you can suspend a tool call before it executes so a human can approve or decline it, or let tools suspend themselves to request additional context from the user.
 
-## Tool call approval
+## When to use agent approval
 
-Tool call approval can be enabled at the agent level and apply to every tool the agent uses, or at the tool level providing more granular control over individual tool calls.
+- **Destructive or irreversible actions** such as deleting records, sending emails, or processing payments.
+- **Cost-heavy operations** like calling expensive third-party APIs where you want to verify arguments first.
+- **Conditional confirmation** where a tool starts executing and then discovers it needs the user to confirm or supply extra data before finishing.
 
-### Storage
+## Quickstart
 
-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.
+Mark a tool with `requireApproval: true`, then check for the `tool-call-approval` chunk in the stream to approve or decline:
 
 ```typescript
-import { Mastra } from '@mastra/core/mastra'
-import { LibSQLStore } from '@mastra/libsql'
+import { Agent } from '@mastra/core/agent'
+import { createTool } from '@mastra/core/tools'
+import { z } from 'zod'
 
-export const mastra = new Mastra({
-  storage: new LibSQLStore({
-    id: 'mastra-storage',
-    url: ':memory:',
-  }),
+const deleteTool = createTool({
+  id: 'delete-record',
+  description: 'Delete a record by ID',
+  inputSchema: z.object({ id: z.string() }),
+  outputSchema: z.object({ deleted: z.boolean() }),
+  requireApproval: true,
+  execute: async ({ id }) => {
+    await db.delete(id)
+    return { deleted: true }
+  },
 })
-```
 
-## Agent-level approval
+const agent = new Agent({
+  id: 'my-agent',
+  name: 'My Agent',
+  model: 'openai/gpt-5-mini',
+  tools: { deleteTool },
+})
 
-When calling an agent using `.stream()` set `requireToolApproval` to `true` which will prevent the agent from calling any of the tools defined in its configuration.
+const stream = await agent.stream('Delete record abc-123')
 
-```typescript
-const stream = await agent.stream("What's the weather in London?", {
-  requireToolApproval: true,
-})
+for await (const chunk of stream.fullStream) {
+  if (chunk.type === 'tool-call-approval') {
+    const approved = await agent.approveToolCall({ runId: stream.runId })
+    for await (const c of approved.textStream) process.stdout.write(c)
+  }
+}
 ```
 
-### Approving tool calls
+> **Note:** Agent approval uses snapshots to capture request state. Configure a [storage provider](https://mastra.ai/docs/memory/storage) on your Mastra instance or you'll see a "snapshot not found" error.
 
-To approve a tool call, access `approveToolCall` from the `agent`, passing in the `runId` of the stream. This will let the agent know its now OK to call its tools.
+## How approval works
 
-```typescript
-const handleApproval = async () => {
-  const approvedStream = await agent.approveToolCall({ runId: stream.runId })
+Mastra offers two distinct mechanisms for pausing tool calls: **pre-execution approval** and **runtime suspension**.
 
-  for await (const chunk of approvedStream.textStream) {
-    process.stdout.write(chunk)
-  }
-  process.stdout.write('\n')
-}
-```
+### Pre-execution approval
+
+Pre-execution approval pauses a tool call _before_ its `execute` function runs. The LLM still decides which tool to call and provides arguments, but `execute` doesn't run until you explicitly approve.
 
-### Declining tool calls
+Two flags control this, combined with OR logic. If _either_ is `true`, the call pauses:
 
-To decline a tool call, access the `declineToolCall` from the `agent`. You will see the streamed response from the agent, but it won't call its tools.
+| Flag                        | Where to set it                   | Scope                                       |
+| --------------------------- | --------------------------------- | ------------------------------------------- |
+| `requireToolApproval: true` | `stream()` / `generate()` options | Pauses **every** tool call for that request |
+| `requireApproval: true`     | `createTool()` definition         | Pauses calls to **that specific tool**      |
+
+The stream emits a `tool-call-approval` chunk containing the `toolCallId`, `toolName`, and `args`. Call `approveToolCall()` or `declineToolCall()` with the stream's `runId` to continue:
 
 ```typescript
-const handleDecline = async () => {
-  const declinedStream = await agent.declineToolCall({ runId: stream.runId })
+const stream = await agent.stream("What's the weather in London?", {
+  requireToolApproval: true,
+})
 
-  for await (const chunk of declinedStream.textStream) {
-    process.stdout.write(chunk)
+for await (const chunk of stream.fullStream) {
+  if (chunk.type === 'tool-call-approval') {
+    console.log('Tool:', chunk.payload.toolName)
+    console.log('Args:', chunk.payload.args)
+
+    // Approve
+    const approved = await agent.approveToolCall({ runId: stream.runId })
+    for await (const c of approved.textStream) process.stdout.write(c)
+
+    // Or decline
+    const declined = await agent.declineToolCall({ runId: stream.runId })
+    for await (const c of declined.textStream) process.stdout.write(c)
   }
-  process.stdout.write('\n')
 }
 ```
 
-## Tool approval with generate()
-
-Tool approval also works with the `generate()` method for non-streaming use cases. When using `generate()` with `requireToolApproval: true`, the method returns immediately when a tool requires approval instead of executing it.
-
-### How it works
+### Runtime suspension with `suspend()`
 
-When a tool requires approval during a `generate()` call, the response includes:
+A tool can also pause _during_ its `execute` function by calling `suspend()`. This is useful when the tool starts running and then discovers it needs additional user input or confirmation before it can finish.
 
-- `finishReason: 'suspended'` - indicates the agent is waiting for approval
-- `suspendPayload` - contains tool call details (`toolCallId`, `toolName`, `args`)
-- `runId` - needed to approve or decline the tool call
+The stream emits a `tool-call-suspended` chunk with a custom payload defined by the tool's `suspendSchema`. You resume by calling `resumeStream()` with data matching the tool's `resumeSchema`.
 
-### Approving tool calls
+## Tool approval with `generate()`
 
-To approve a tool call with `generate()`, use the `approveToolCallGenerate` method:
+Tool approval also works with `generate()` for non-streaming use cases. When a tool requires approval, `generate()` returns immediately with `finishReason: 'suspended'`, a `suspendPayload` containing the tool call details (`toolCallId`, `toolName`, `args`), and a `runId`:
 
 ```typescript
 const output = await agent.generate('Find user John', {
@@ -85,35 +103,23 @@ const output = await agent.generate('Find user John', {
 
 if (output.finishReason === 'suspended') {
   console.log('Tool requires approval:', output.suspendPayload.toolName)
-  console.log('Arguments:', output.suspendPayload.args)
 
-  // Approve the tool call and get the final result
+  // Approve
   const result = await agent.approveToolCallGenerate({
     runId: output.runId,
     toolCallId: output.suspendPayload.toolCallId,
   })
-
   console.log('Final result:', result.text)
-}
-```
-
-### Declining tool calls
 
-To decline a tool call, use the `declineToolCallGenerate` method:
-
-```typescript
-if (output.finishReason === 'suspended') {
+  // Or decline
   const result = await agent.declineToolCallGenerate({
     runId: output.runId,
     toolCallId: output.suspendPayload.toolCallId,
   })
-
-  // Agent will respond acknowledging the declined tool
-  console.log(result.text)
 }
 ```
 
-### Stream vs Generate comparison
+### Stream vs generate comparison
 
 | Aspect             | `stream()`                   | `generate()`                                     |
 | ------------------ | ---------------------------- | ------------------------------------------------ |
@@ -123,13 +129,15 @@ if (output.finishReason === 'suspended') {
 | Decline method     | `declineToolCall({ runId })` | `declineToolCallGenerate({ runId, toolCallId })` |
 | Result             | Stream to iterate            | Full output object                               |
 
+> **Note:** `toolCallId` is optional on all four methods. Pass it when multiple tool calls may be pending at the same time (common in supervisor agents). When omitted, the agent resumes the most recent suspended tool call.
+
 ## Tool-level approval
 
-There are two types of tool call approval. The first uses `requireApproval`, which is a property on the tool definition, while `requireToolApproval` is a parameter passed to `agent.stream()`. The second uses `suspend` and lets the agent provide context or confirmation prompts so the user can decide whether the tool call should continue.
+Instead of pausing every tool call at the agent level, you can mark individual tools as requiring approval. This gives you granular control: only specific tools pause, while others execute immediately.
 
-### Tool approval using `requireToolApproval`
+### Approval using `requireApproval`
 
-In this approach, `requireApproval` is configured on the tool definition (shown below) rather than on the agent.
+Set `requireApproval: true` on a tool definition. The tool pauses before execution regardless of whether `requireToolApproval` is set on the agent:
 
 ```typescript
 export const testTool = createTool({
@@ -154,30 +162,30 @@ export const testTool = createTool({
 })
 ```
 
-When `requireApproval` is true for a tool, the stream will include chunks of type `tool-call-approval` to indicate that the call is paused. To continue the call, invoke `resumeStream` with the required `resumeSchema` and the `runId`.
+When `requireApproval` is `true`, the stream emits `tool-call-approval` chunks the same way agent-level approval does. Use `approveToolCall()` or `declineToolCall()` to continue:
 
 ```typescript
 const stream = await agent.stream("What's the weather in London?")
 
 for await (const chunk of stream.fullStream) {
   if (chunk.type === 'tool-call-approval') {
-    console.log('Approval required.')
+    console.log('Approval required for:', chunk.payload.toolName)
   }
 }
 
-const handleResume = async () => {
-  const resumedStream = await agent.resumeStream({ approved: true }, { runId: stream.runId })
+const handleApproval = async () => {
+  const approvedStream = await agent.approveToolCall({ runId: stream.runId })
 
-  for await (const chunk of resumedStream.textStream) {
+  for await (const chunk of approvedStream.textStream) {
     process.stdout.write(chunk)
   }
   process.stdout.write('\n')
 }
 ```
 
-### Tool approval using `suspend`
+### Approval using `suspend()`
 
-With this approach, neither the agent nor the tool uses `requireApproval`. Instead, the tool implementation calls `suspend` to pause execution and return context or confirmation prompts to the user.
+With this approach, neither the agent nor the tool uses `requireApproval`. Instead, the tool's `execute` function calls `suspend()` to pause at a specific point and return context or confirmation prompts to the user. This is useful when approval depends on runtime conditions rather than being unconditional.
 
 ```typescript
 export const testToolB = createTool({
@@ -210,7 +218,7 @@ export const testToolB = createTool({
 })
 ```
 
-With this approach the stream will include a `tool-call-suspended` chunk, and the `suspendPayload` will contain the `reason` defined by the tool's `suspendSchema`. To continue the call, invoke `resumeStream` with the required `resumeSchema` and the `runId`.
+With this approach the stream includes a `tool-call-suspended` chunk, and the `suspendPayload` contains the `reason` defined by the tool's `suspendSchema`. Call `resumeStream` with the `resumeSchema` data and `runId` to continue:
 
 ```typescript
 const stream = await agent.stream("What's the weather in London?")
@@ -233,94 +241,64 @@ const handleResume = async () => {
 
 ## Automatic tool resumption
 
-When using tools that call `suspend()`, you can enable automatic resumption so the agent resumes suspended tools based on the user's next message. This creates a conversational flow where users provide the required information naturally, without your application needing to call `resumeStream()` explicitly.
-
-### Enabling auto-resume
-
-Set `autoResumeSuspendedTools` to `true` in the agent's default options or when calling `stream()`:
+When using tools that call `suspend()`, you can enable automatic resumption so the agent resumes suspended tools based on the user's next message. Set `autoResumeSuspendedTools` to `true` in the agent's default options or per-request:
 
 ```typescript
 import { Agent } from '@mastra/core/agent'
 import { Memory } from '@mastra/memory'
 
-// Option 1: In agent configuration
 const agent = new Agent({
   id: 'my-agent',
   name: 'My Agent',
   instructions: 'You are a helpful assistant',
-  model: 'openai/gpt-4o-mini',
+  model: 'openai/gpt-5-mini',
   tools: { weatherTool },
   memory: new Memory(),
   defaultOptions: {
     autoResumeSuspendedTools: true,
   },
 })
-
-// Option 2: Per-request
-const stream = await agent.stream("What's the weather?", {
-  autoResumeSuspendedTools: true,
-})
 ```
 
-### How it works
-
-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
-
-### Example
+When enabled, the agent detects suspended tools from message history on the next user message, extracts `resumeData` based on the tool's `resumeSchema`, and automatically resumes the tool. The following example shows a complete conversational flow:
 
 ```typescript
 import { createTool } from '@mastra/core/tools'
 import { z } from 'zod'
 
-export const weatherTool = createTool({
-  id: 'weather-info',
-  description: 'Fetches weather information for a city',
+const weatherTool = createTool({
+  id: 'weather-tool',
+  description: 'Fetches weather for a city',
+  inputSchema: z.object({
+    city: z.string(),
+  }),
+  outputSchema: z.object({
+    weather: z.string(),
+  }),
   suspendSchema: z.object({
     message: z.string(),
   }),
   resumeSchema: z.object({
     city: z.string(),
   }),
-  execute: async (_inputData, context) => {
-    // Check if this is a resume with data
-    if (!context?.agent?.resumeData) {
-      // First call - suspend and ask for the city
-      return context?.agent?.suspend({
-        message: 'What city do you want to know the weather for?',
-      })
+  execute: async (inputData, context) => {
+    const { resumeData, suspend } = context?.agent ?? {}
+
+    // If no city provided, ask the user
+    if (!inputData.city && !resumeData?.city) {
+      return suspend?.({ message: 'What city do you want to know the weather for?' })
     }
 
-    // Resume call - city was extracted from user's message
-    const { city } = context.agent.resumeData
+    const city = resumeData?.city ?? inputData.city
     const response = await fetch(`https://wttr.in/${city}?format=3`)
     const weather = await response.text()
 
-    return { city, weather }
-  },
-})
-
-const agent = new Agent({
-  id: 'my-agent',
-  name: 'My Agent',
-  instructions: 'You are a helpful assistant',
-  model: 'openai/gpt-4o-mini',
-  tools: { weatherTool },
-  memory: new Memory(),
-  defaultOptions: {
-    autoResumeSuspendedTools: true,
+    return { weather: `${city}: ${weather}` }
   },
 })
+```
 
+```typescript
 const stream = await agent.stream("What's the weather like?")
 
 for await (const chunk of stream.fullStream) {
@@ -329,18 +307,13 @@ for await (const chunk of stream.fullStream) {
   }
 }
 
-const handleResume = async () => {
-  const resumedStream = await agent.stream('San Francisco')
-
-  for await (const chunk of resumedStream.textStream) {
-    process.stdout.write(chunk)
-  }
-  process.stdout.write('\n')
+// User sends follow-up on the same thread
+const resumedStream = await agent.stream('San Francisco')
+for await (const chunk of resumedStream.textStream) {
+  process.stdout.write(chunk)
 }
 ```
 
-**Conversation flow:**
-
 ```text
 User: "What's the weather like?"
 Agent: "What city do you want to know the weather for?"
@@ -349,7 +322,7 @@ User: "San Francisco"
 Agent: "The weather in San Francisco is: San Francisco: ☀️ +72°F"
 ```
 
-The second message automatically resumes the suspended tool - the agent extracts `{ city: "San Francisco" }` from the user's message and passes it as `resumeData`.
+The second message automatically resumes the suspended tool. The agent extracts `{ city: "San Francisco" }` from the user's message and passes it as `resumeData`.
 
 ### Requirements
 
@@ -368,21 +341,21 @@ For automatic tool resumption to work:
 
 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.
 
-## Tool approval: Supervisor pattern
-
-The [supervisor pattern](https://mastra.ai/docs/agents/networks) lets a supervisor agent coordinate multiple subagents using `.stream()` or `.generate()`. The supervisor delegates tasks to subagents, which may use tools that require approval. When this happens, tool approvals properly propagate through the delegation chain -- the approval request surfaces at the supervisor level where you can handle it, regardless of which subagent triggered it.
+## Tool approval: Supervisor agents
 
-### How it works
+A [supervisor agent](https://mastra.ai/docs/agents/supervisor-agents) coordinates multiple subagents using `.stream()` or `.generate()`. When a subagent calls a tool that requires approval, the request propagates up through the delegation chain and surfaces at the supervisor level:
 
-1. The supervisor agent delegates a task to a subagent.
+1. The supervisor delegates a task to a subagent.
 2. The subagent calls a tool that has `requireApproval: true` or uses `suspend()`.
-3. The approval request bubbles up through the delegation chain to the supervisor.
-4. You handle the approval or decline at the supervisor level.
-5. The decision propagates back down to the subagent, which continues or terminates accordingly.
+3. The approval request bubbles up to the supervisor.
+4. You approve or decline at the supervisor level.
+5. The decision propagates back down to the subagent.
 
-### Example
+Tool approvals also propagate through multiple levels of delegation. If a supervisor delegates to subagent A, which delegates to subagent B that has a tool with `requireApproval: true`, the approval request still surfaces at the top-level supervisor.
 
-The following example creates a subagent with a database lookup tool that requires approval. The supervisor delegates to this subagent, and when the tool triggers an approval request, it surfaces in the supervisor's stream as a `tool-call-approval` chunk. You then approve the tool call using `approveToolCall` with the stream's `runId`.
+### Approve and decline in supervisor agents
+
+The example below creates a subagent with a tool requiring approval. When the tool triggers an approval request, it surfaces in the supervisor's stream as a `tool-call-approval` chunk:
 
 ```typescript
 import { Agent } from '@mastra/core/agent'
@@ -390,7 +363,6 @@ import { createTool } from '@mastra/core/tools'
 import { Memory } from '@mastra/memory'
 import { z } from 'zod'
 
-// subagent with approval-required tool
 const findUserTool = createTool({
   id: 'find-user',
   description: 'Finds user by ID in the database',
@@ -404,7 +376,7 @@ const findUserTool = createTool({
       email: z.string(),
     }),
   }),
-  requireApproval: true, // Requires approval before execution
+  requireApproval: true,
   execute: async input => {
     const user = await database.findUser(input.userId)
     return { user }
@@ -415,7 +387,7 @@ const dataAgent = new Agent({
   id: 'data-agent',
   name: 'Data Agent',
   description: 'Handles database queries and user data retrieval',
-  model: 'openai/gpt-4o-mini',
+  model: 'openai/gpt-5-mini',
   tools: { findUserTool },
 })
 
@@ -424,12 +396,11 @@ const supervisorAgent = new Agent({
   name: 'Supervisor Agent',
   instructions: `You coordinate data retrieval tasks.
     Delegate to data-agent for user lookups.`,
-  model: 'openai/gpt-5.1',
+  model: 'openai/gpt-5.4',
   agents: { dataAgent },
   memory: new Memory(),
 })
 
-// When supervisor delegates to dataAgent and tool requires approval
 const stream = await supervisorAgent.stream('Find user with ID 12345')
 
 for await (const chunk of stream.fullStream) {
@@ -443,40 +414,22 @@ for await (const chunk of stream.fullStream) {
       toolCallId: chunk.payload.toolCallId,
     })
 
-    // Process resumed stream
     for await (const resumeChunk of resumeStream.textStream) {
       process.stdout.write(resumeChunk)
     }
-  }
-}
-```
-
-### Declining tool calls in supervisor pattern
-
-You can also decline tool calls at the supervisor level by calling `declineToolCall`. The supervisor will respond acknowledging the declined tool without executing it:
-
-```typescript
-for await (const chunk of stream.fullStream) {
-  if (chunk.type === 'tool-call-approval') {
-    console.log('Declining tool call:', chunk.payload.toolName)
 
-    // Decline the tool call
+    // To decline instead, use:
     const declineStream = await supervisorAgent.declineToolCall({
       runId: stream.runId,
       toolCallId: chunk.payload.toolCallId,
     })
-
-    // The supervisor will respond acknowledging the declined tool
-    for await (const declineChunk of declineStream.textStream) {
-      process.stdout.write(declineChunk)
-    }
   }
 }
 ```
 
-### Using suspend() in supervisor pattern
+### Use `suspend()` in supervisor agents
 
-Tools can also use [`suspend()`](#tool-approval-using-suspend) to pause execution and return context to the user. This approach works through the supervisor delegation chain the same way `requireApproval` does -- the suspension surfaces at the supervisor level:
+Tools can also use [`suspend()`](#approval-using-suspend) to pause execution and return context to the user. This approach works through the supervisor delegation chain the same way `requireApproval` does: the suspension surfaces at the supervisor level:
 
 ```typescript
 const conditionalTool = createTool({
@@ -504,8 +457,10 @@ const conditionalTool = createTool({
     return await performOperation(input.operation)
   },
 })
+```
 
-// When using this tool through a subagent in supervisor pattern
+```typescript
+// When using this tool through a subagent in supervisor agents
 for await (const chunk of stream.fullStream) {
   if (chunk.type === 'tool-call-suspended') {
     console.log('Tool suspended:', chunk.payload.suspendPayload.message)
@@ -523,9 +478,9 @@ for await (const chunk of stream.fullStream) {
 }
 ```
 
-### Tool approval with generate()
+### Supervisor approval with `generate()`
 
-Tool approval propagation also works with `generate()` in supervisor pattern:
+Tool approval propagation also works with `generate()` in supervisor agents:
 
 ```typescript
 const output = await supervisorAgent.generate('Find user with ID 12345', {
@@ -545,14 +500,10 @@ if (output.finishReason === 'suspended') {
 }
 ```
 
-### Multi-level delegation
-
-Tool approvals propagate through multiple levels of delegation. For example, if a supervisor delegates to subagent A, which in turn delegates to subagent B that has a tool with `requireApproval: true`, the approval request still surfaces at the top-level supervisor. You handle the approval or decline there, and the result flows back down through the entire delegation chain to the tool that requested it.
-
 ## Related
 
-- [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)
+- [Tools](https://mastra.ai/docs/agents/using-tools)
+- [Agent overview](https://mastra.ai/docs/agents/overview)
+- [MCP overview](https://mastra.ai/docs/mcp/overview)
+- [Memory](https://mastra.ai/docs/memory/overview)
+- [Request context](https://mastra.ai/docs/server/request-context)