claude-agent-sdk

What this skill does

# Claude Agent SDK - Structured Outputs & Error Prevention Guide

**Package**: @anthropic-ai/[email protected] (Nov 21, 2025)
**Breaking Changes**: v0.1.45 - Structured outputs (Nov 2025), v0.1.0 - No default system prompt, settingSources required

---

## What's New in v0.1.45+ (Nov 2025)

**Major Features:**

### 1. Structured Outputs (v0.1.45, Nov 14, 2025)
- **JSON schema validation** - Guarantees responses match exact schemas
- **`outputFormat` parameter** - Define output structure with JSON schema or Zod
- **Access validated results** - Via `message.structured_output`
- **Beta header required**: `structured-outputs-2025-11-13`
- **Type safety** - Full TypeScript inference with Zod schemas

**Example:**
```typescript
import { query } from "@anthropic-ai/claude-agent-sdk";
import { z } from "zod";

const schema = z.object({
  summary: z.string(),
  sentiment: z.enum(['positive', 'neutral', 'negative']),
  confidence: z.number().min(0).max(1)
});

const response = query({
  prompt: "Analyze this code review feedback",
  options: {
    model: "claude-sonnet-4-5",
    outputFormat: {
      type: "json_schema",
      json_schema: {
        name: "AnalysisResult",
        strict: true,
        schema: zodToJsonSchema(schema)
      }
    }
  }
});

for await (const message of response) {
  if (message.type === 'result' && message.structured_output) {
    // Guaranteed to match schema
    const validated = schema.parse(message.structured_output);
    console.log(`Sentiment: ${validated.sentiment}`);
  }
}
```

### 2. Plugins System (v0.1.27)
- **`plugins` array** - Load local plugin paths
- **Custom plugin support** - Extend agent capabilities

### 3. Hooks System (v0.1.0+)
- **Event-driven callbacks** - PreToolUse, PostToolUse, Notification, UserPromptSubmit
- **Session event hooks** - Monitor and control agent behavior

### 4. Additional Options
- **`fallbackModel`** - Automatic model fallback on failures
- **`maxThinkingTokens`** - Control extended thinking budget
- **`strictMcpConfig`** - Strict MCP configuration validation
- **`continue`** - Resume with new prompt (differs from `resume`)
- **`permissionMode: 'plan'`** - New permission mode for planning workflows

📚 **Docs**: https://platform.claude.com/docs/en/agent-sdk/structured-outputs

---

## The Complete Claude Agent SDK Reference

## Table of Contents

1. [Core Query API](#core-query-api)
2. [Tool Integration](#tool-integration-built-in--custom)
3. [MCP Servers](#mcp-servers-model-context-protocol)
4. [Subagent Orchestration](#subagent-orchestration)
5. [Session Management](#session-management)
6. [Permission Control](#permission-control)
7. [Filesystem Settings](#filesystem-settings)
8. [Message Types & Streaming](#message-types--streaming)
9. [Error Handling](#error-handling)
10. [Known Issues](#known-issues-prevention)

---

## Core Query API

**Key signature:**
```typescript
query(prompt: string | AsyncIterable<SDKUserMessage>, options?: Options)
  -> AsyncGenerator<SDKMessage>
```

**Critical Options:**
- `outputFormat` - Structured JSON schema validation (v0.1.45+)
- `settingSources` - Filesystem settings loading ('user'|'project'|'local')
- `canUseTool` - Custom permission logic callback
- `agents` - Programmatic subagent definitions
- `mcpServers` - MCP server configuration
- `permissionMode` - 'default'|'acceptEdits'|'bypassPermissions'|'plan'

---

## Tool Integration (Built-in + Custom)

**Tool Control:**
- `allowedTools` - Whitelist (takes precedence)
- `disallowedTools` - Blacklist
- `canUseTool` - Custom permission callback (see Permission Control section)

**Built-in Tools:** Read, Write, Edit, Bash, Grep, Glob, WebSearch, WebFetch, Task, NotebookEdit, BashOutput, KillBash, ListMcpResources, ReadMcpResource

---

## MCP Servers (Model Context Protocol)

**Server Types:**
- **In-process** - `createSdkMcpServer()` with `tool()` definitions
- **External** - stdio, HTTP, SSE transport

**Tool Definition:**
```typescript
tool(name: string, description: string, zodSchema, handler)
```

**Handler Return:**
```typescript
{ content: [{ type: "text", text: "..." }], isError?: boolean }
```

### External MCP Servers (stdio)

```typescript
const response = query({
  prompt: "List files and analyze Git history",
  options: {
    mcpServers: {
      // Filesystem server
      "filesystem": {
        command: "npx",
        args: ["@modelcontextprotocol/server-filesystem"],
        env: {
          ALLOWED_PATHS: "/Users/developer/projects:/tmp"
        }
      },
      // Git operations server
      "git": {
        command: "npx",
        args: ["@modelcontextprotocol/server-git"],
        env: {
          GIT_REPO_PATH: "/Users/developer/projects/my-repo"
        }
      }
    },
    allowedTools: [
      "mcp__filesystem__list_files",
      "mcp__filesystem__read_file",
      "mcp__git__log",
      "mcp__git__diff"
    ]
  }
});
```

### External MCP Servers (HTTP/SSE)

```typescript
const response = query({
  prompt: "Analyze data from remote service",
  options: {
    mcpServers: {
      "remote-service": {
        url: "https://api.example.com/mcp",
        headers: {
          "Authorization": "Bearer your-token-here",
          "Content-Type": "application/json"
        }
      }
    },
    allowedTools: ["mcp__remote-service__analyze"]
  }
});
```

### MCP Tool Naming Convention

**Format**: `mcp__<server-name>__<tool-name>`

**CRITICAL:**
- Server name and tool name MUST match configuration
- Use double underscores (`__`) as separators
- Include in `allowedTools` array

**Examples:** `mcp__weather-service__get_weather`, `mcp__filesystem__read_file`

---

## Subagent Orchestration

### AgentDefinition Type

```typescript
type AgentDefinition = {
  description: string;        // When to use this agent
  prompt: string;             // System prompt for agent
  tools?: string[];           // Allowed tools (optional)
  model?: 'sonnet' | 'opus' | 'haiku' | 'inherit';  // Model (optional)
}
```

**Field Details:**

- **description**: When to use agent (used by main agent for delegation)
- **prompt**: System prompt (defines role, inherits main context)
- **tools**: Allowed tools (if omitted, inherits from main agent)
- **model**: Model override (`haiku`/`sonnet`/`opus`/`inherit`)

**Usage:**
```typescript
agents: {
  "security-checker": {
    description: "Security audits and vulnerability scanning",
    prompt: "You check security. Scan for secrets, verify OWASP compliance.",
    tools: ["Read", "Grep", "Bash"],
    model: "sonnet"
  }
}
```

---

## Session Management

**Options:**
- `resume: sessionId` - Continue previous session
- `forkSession: true` - Create new branch from session
- `continue: prompt` - Resume with new prompt (differs from `resume`)

**Session Forking Pattern (Unique Capability):**

```typescript
// Explore alternative without modifying original
const forked = query({
  prompt: "Try GraphQL instead of REST",
  options: {
    resume: sessionId,
    forkSession: true  // Creates new branch, original session unchanged
  }
});
```

**Capture Session ID:**
```typescript
for await (const message of response) {
  if (message.type === 'system' && message.subtype === 'init') {
    sessionId = message.session_id;  // Save for later resume/fork
  }
}
```

---

## Permission Control

**Permission Modes:**
```typescript
type PermissionMode = "default" | "acceptEdits" | "bypassPermissions" | "plan";
```

- `default` - Standard permission checks
- `acceptEdits` - Auto-approve file edits
- `bypassPermissions` - Skip ALL checks (use in CI/CD only)
- `plan` - Planning mode (v0.1.45+)

### Custom Permission Logic

```typescript
const response = query({
  prompt: "Deploy application to production",
  options: {
    permissionMode: "default",
    canUseTool: async (toolName, input) => {
      // Allow read-only operations
      if (['Read', 'Grep', 'Glob'].includes(toolName)) {
        return { behavior: "allow" };
      }

      // Deny destructive bash commands
      if (to