Input and output

Get structured output from agents

Get structured output from agents 这一页讲的，就是 Get structured output from agents 这件事在 Claude Code 里到底怎么用。

页面信息

对应原页

页面性质

第三方中文解释页

使用建议

先看人话解释，再对照原页命令和代码

这页不是官方原文，而是顺着官方文档结构做的中文解释版。命令、参数、配置名这些硬东西尽量保留，解释部分则尽量讲成人能照着做的话。

如果你碰到特别敏感的配置、权限或企业环境差异，最好顺手点上面的“查看原始文档”再核一遍。

这一页先讲明白

这页主要讲 Get structured output from agents：Return validated JSON from agent workflows using JSON Schema, Zod, or Pydantic. Get type-safe, structured data after multi-turn tool use.

你可以把它当成"Input and output"这块里专门管这一摊事的说明书。

你可以把"Get structured output from agents"理解成 Input and output 这一栏里的一把专门工具。这页不是让你背书，而是教你什么时候该把这把工具拿出来。

原文这页大多会按 Why structured outputs?、Quick start、Type-safe schemas with Zod and Pydantic、Output format configuration 这些环节往下讲。

翻成人话，大概就是：Why structured outputs?

第一，先别一上来全开全配。先按最小一步试通，确认没跑偏，再继续往下加。

第二，命令、配置名、参数名这些硬东西尽量保留原样。人话解释是帮你听懂，不是帮你改关键字。

第三，照着原文这几个环节挨个过：Why structured outputs? -> Quick start -> Type-safe schemas with Zod and Pydantic -> Output format configuration。像下地先看水路、再试机器、再正式开干，一步一步最稳。

关键片段

原页关键片段：Why structured outputs? 1

这一段要真抓重点，通常就抓下面这块原文。

Here's a classic chocolate chip cookie recipe!

**Chocolate Chip Cookies**
Prep time: 15 minutes | Cook time: 10 minutes

Ingredients:
- 2 1/4 cups all-purpose flour
- 1 cup butter, softened
...

改配置

原页关键片段：Why structured outputs? 2

这会儿轮到改配置了，字段名和关键字别自己乱换。

{
  "name": "Chocolate Chip Cookies",
  "prep_time_minutes": 15,
  "cook_time_minutes": 10,
  "ingredients": [
    { "item": "all-purpose flour", "amount": 2.25, "unit": "cups" },
    { "item": "butter, softened", "amount": 1, "unit": "cup" }
    // ...
  ],
  "steps": ["Preheat oven to 375°F", "Cream butter and sugar" /* ... */]
}

终端里敲

原页关键片段：Quick start

这一段不是只让你理解意思，下面这条命令就是现在要跑的。

import { query } from "@anthropic-ai/claude-agent-sdk";

// Define the shape of data you want back
const schema = {
  type: "object",
  properties: {
    company_name: { type: "string" },
    founded_year: { type: "number" },
    headquarters: { type: "string" }
  },
  required: ["company_name"]
};

for await (const message of query({
  prompt: "Research Anthropic and provide key company information",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  // The result message contains structured_output with validated data
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    console.log(message.structured_output);
    // { company_name: "Anthropic", founded_year: 2021, headquarters: "San Francisco, CA" }
  }
}

终端里敲

原页关键片段：Type-safe schemas with Zod and Pydantic

真到动手的时候了，下面这条直接敲一遍，看它回什么。

import { z } from "zod";
import { query } from "@anthropic-ai/claude-agent-sdk";

// Define schema with Zod
const FeaturePlan = z.object({
  feature_name: z.string(),
  summary: z.string(),
  steps: z.array(
    z.object({
      step_number: z.number(),
      description: z.string(),
      estimated_complexity: z.enum(["low", "medium", "high"])
    })
  ),
  risks: z.array(z.string())
});

type FeaturePlan = z.infer<typeof FeaturePlan>;

// Convert to JSON Schema
const schema = z.toJSONSchema(FeaturePlan);

// Use in query
for await (const message of query({
  prompt:
    "Plan how to add dark mode support to a React app. Break it into implementation steps.",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    // Validate and get fully typed result
    const parsed = FeaturePlan.safeParse(message.structured_output);
    if (parsed.success) {
      const plan: FeaturePlan = parsed.data;
      console.log(`Feature: ${plan.feature_name}`);
      console.log(`Summary: ${plan.summary}`);
      plan.steps.forEach((step) => {
        console.log(`${step.step_number}. [${step.estimated_complexity}] ${step.description}`);
      });
    }
  }
}

终端里敲

原页关键片段：Example: TODO tracking agent

真到动手的时候了，下面这条直接敲一遍，看它回什么。

import { query } from "@anthropic-ai/claude-agent-sdk";

// Define structure for TODO extraction
const todoSchema = {
  type: "object",
  properties: {
    todos: {
      type: "array",
      items: {
        type: "object",
        properties: {
          text: { type: "string" },
          file: { type: "string" },
          line: { type: "number" },
          author: { type: "string" },
          date: { type: "string" }
        },
        required: ["text", "file", "line"]
      }
    },
    total_count: { type: "number" }
  },
  required: ["todos", "total_count"]
};

// Agent uses Grep to find TODOs, Bash to get git blame info
for await (const message of query({
  prompt: "Find all TODO comments in this codebase and identify who added them",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: todoSchema
    }
  }
})) {
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    const data = message.structured_output as { total_count: number; todos: Array<{ file: string; line: number; text: string; author?: string; date?: string }> };
    console.log(`Found ${data.total_count} TODOs`);
    data.todos.forEach((todo) => {
      console.log(`${todo.file}:${todo.line} - ${todo.text}`);
      if (todo.author) {
        console.log(`  Added by ${todo.author} on ${todo.date}`);
      }
    });
  }
}

关键片段

原页关键片段：Error handling

先看下面这块原始片段，等会儿再回头看解释会顺得多。

for await (const msg of query({
  prompt: "Extract contact info from the document",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: contactSchema
    }
  }
})) {
  if (msg.type === "result") {
    if (msg.subtype === "success" && msg.structured_output) {
      // Use the validated output
      console.log(msg.structured_output);
    } else if (msg.subtype === "error_max_structured_output_retries") {
      // Handle the failure - retry with simpler prompt, fall back to unstructured, etc.
      console.error("Could not produce valid output");
    }
  }
}

预留广告位

正文中段响应式广告 等你后面真接 AdSense，这里再放正式广告。

Documentation Index

这里不是让你背"Documentation Index"这个词，而是让你看它真干活时怎么使。

看这段时要特别盯工具和权限边界，别为了省事一把全开。

Why structured outputs?

这一段主要是在把"Why structured outputs?"讲实，不是只摆个标题给你看。

关键片段

Why structured outputs? 1

这一段要真抓重点，通常就抓下面这块原文。

Here's a classic chocolate chip cookie recipe!

**Chocolate Chip Cookies**
Prep time: 15 minutes | Cook time: 10 minutes

Ingredients:
- 2 1/4 cups all-purpose flour
- 1 cup butter, softened
...

改配置

Why structured outputs? 2

这会儿轮到改配置了，字段名和关键字别自己乱换。

{
  "name": "Chocolate Chip Cookies",
  "prep_time_minutes": 15,
  "cook_time_minutes": 10,
  "ingredients": [
    { "item": "all-purpose flour", "amount": 2.25, "unit": "cups" },
    { "item": "butter, softened", "amount": 1, "unit": "cup" }
    // ...
  ],
  "steps": ["Preheat oven to 375°F", "Cream butter and sugar" /* ... */]
}

Quick start

看到这里，就把"Quick start"当成一件真要上手的活来看。

终端里敲

Quick start

这一段不是只让你理解意思，下面这条命令就是现在要跑的。

import { query } from "@anthropic-ai/claude-agent-sdk";

// Define the shape of data you want back
const schema = {
  type: "object",
  properties: {
    company_name: { type: "string" },
    founded_year: { type: "number" },
    headquarters: { type: "string" }
  },
  required: ["company_name"]
};

for await (const message of query({
  prompt: "Research Anthropic and provide key company information",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  // The result message contains structured_output with validated data
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    console.log(message.structured_output);
    // { company_name: "Anthropic", founded_year: 2021, headquarters: "San Francisco, CA" }
  }
}

Type-safe schemas with Zod and Pydantic

看到这里，就别靠猜了，字段、格式和写法都得按说明来。

终端里敲

Type-safe schemas with Zod and Pydantic

真到动手的时候了，下面这条直接敲一遍，看它回什么。

import { z } from "zod";
import { query } from "@anthropic-ai/claude-agent-sdk";

// Define schema with Zod
const FeaturePlan = z.object({
  feature_name: z.string(),
  summary: z.string(),
  steps: z.array(
    z.object({
      step_number: z.number(),
      description: z.string(),
      estimated_complexity: z.enum(["low", "medium", "high"])
    })
  ),
  risks: z.array(z.string())
});

type FeaturePlan = z.infer<typeof FeaturePlan>;

// Convert to JSON Schema
const schema = z.toJSONSchema(FeaturePlan);

// Use in query
for await (const message of query({
  prompt:
    "Plan how to add dark mode support to a React app. Break it into implementation steps.",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    // Validate and get fully typed result
    const parsed = FeaturePlan.safeParse(message.structured_output);
    if (parsed.success) {
      const plan: FeaturePlan = parsed.data;
      console.log(`Feature: ${plan.feature_name}`);
      console.log(`Summary: ${plan.summary}`);
      plan.steps.forEach((step) => {
        console.log(`${step.step_number}. [${step.estimated_complexity}] ${step.description}`);
      });
    }
  }
}

Output format configuration

这里主要是在交代"Output format configuration"这一块会碰到哪些事。

Example: TODO tracking agent

这里主要是在交代"Example: TODO tracking agent"这一块会碰到哪些事。

看这段时要特别盯工具和权限边界，别为了省事一把全开。

终端里敲

Example: TODO tracking agent

真到动手的时候了，下面这条直接敲一遍，看它回什么。

import { query } from "@anthropic-ai/claude-agent-sdk";

// Define structure for TODO extraction
const todoSchema = {
  type: "object",
  properties: {
    todos: {
      type: "array",
      items: {
        type: "object",
        properties: {
          text: { type: "string" },
          file: { type: "string" },
          line: { type: "number" },
          author: { type: "string" },
          date: { type: "string" }
        },
        required: ["text", "file", "line"]
      }
    },
    total_count: { type: "number" }
  },
  required: ["todos", "total_count"]
};

// Agent uses Grep to find TODOs, Bash to get git blame info
for await (const message of query({
  prompt: "Find all TODO comments in this codebase and identify who added them",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: todoSchema
    }
  }
})) {
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    const data = message.structured_output as { total_count: number; todos: Array<{ file: string; line: number; text: string; author?: string; date?: string }> };
    console.log(`Found ${data.total_count} TODOs`);
    data.todos.forEach((todo) => {
      console.log(`${todo.file}:${todo.line} - ${todo.text}`);
      if (todo.author) {
        console.log(`  Added by ${todo.author} on ${todo.date}`);
      }
    });
  }
}

Error handling

看到这里，就把"Error handling"当成一件真要上手的活来看。

关键片段

Error handling

先看下面这块原始片段，等会儿再回头看解释会顺得多。

for await (const msg of query({
  prompt: "Extract contact info from the document",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: contactSchema
    }
  }
})) {
  if (msg.type === "result") {
    if (msg.subtype === "success" && msg.structured_output) {
      // Use the validated output
      console.log(msg.structured_output);
    } else if (msg.subtype === "error_max_structured_output_retries") {
      // Handle the failure - retry with simpler prompt, fall back to unstructured, etc.
      console.error("Could not produce valid output");
    }
  }
}

Related resources

这一段主要是在把"Related resources"讲实，不是只摆个标题给你看。

看这段时要特别盯工具和权限边界，别为了省事一把全开。

照着做一遍

如果你不想来回翻，就先照这几步顺着做。

每做完一步就看一下结果，再决定要不要继续往下。

关键片段

第 1 步：Why structured outputs? 1

这一段要真抓重点，通常就抓下面这块原文。

Here's a classic chocolate chip cookie recipe!

**Chocolate Chip Cookies**
Prep time: 15 minutes | Cook time: 10 minutes

Ingredients:
- 2 1/4 cups all-purpose flour
- 1 cup butter, softened
...

改配置

第 2 步：Why structured outputs? 2

这会儿轮到改配置了，字段名和关键字别自己乱换。

{
  "name": "Chocolate Chip Cookies",
  "prep_time_minutes": 15,
  "cook_time_minutes": 10,
  "ingredients": [
    { "item": "all-purpose flour", "amount": 2.25, "unit": "cups" },
    { "item": "butter, softened", "amount": 1, "unit": "cup" }
    // ...
  ],
  "steps": ["Preheat oven to 375°F", "Cream butter and sugar" /* ... */]
}

终端里敲

第 3 步：Quick start

这一段不是只让你理解意思，下面这条命令就是现在要跑的。

import { query } from "@anthropic-ai/claude-agent-sdk";

// Define the shape of data you want back
const schema = {
  type: "object",
  properties: {
    company_name: { type: "string" },
    founded_year: { type: "number" },
    headquarters: { type: "string" }
  },
  required: ["company_name"]
};

for await (const message of query({
  prompt: "Research Anthropic and provide key company information",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  // The result message contains structured_output with validated data
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    console.log(message.structured_output);
    // { company_name: "Anthropic", founded_year: 2021, headquarters: "San Francisco, CA" }
  }
}

终端里敲

第 4 步：Type-safe schemas with Zod and Pydantic

真到动手的时候了，下面这条直接敲一遍，看它回什么。

import { z } from "zod";
import { query } from "@anthropic-ai/claude-agent-sdk";

// Define schema with Zod
const FeaturePlan = z.object({
  feature_name: z.string(),
  summary: z.string(),
  steps: z.array(
    z.object({
      step_number: z.number(),
      description: z.string(),
      estimated_complexity: z.enum(["low", "medium", "high"])
    })
  ),
  risks: z.array(z.string())
});

type FeaturePlan = z.infer<typeof FeaturePlan>;

// Convert to JSON Schema
const schema = z.toJSONSchema(FeaturePlan);

// Use in query
for await (const message of query({
  prompt:
    "Plan how to add dark mode support to a React app. Break it into implementation steps.",
  options: {
    outputFormat: {
      type: "json_schema",
      schema: schema
    }
  }
})) {
  if (message.type === "result" && message.subtype === "success" && message.structured_output) {
    // Validate and get fully typed result
    const parsed = FeaturePlan.safeParse(message.structured_output);
    if (parsed.success) {
      const plan: FeaturePlan = parsed.data;
      console.log(`Feature: ${plan.feature_name}`);
      console.log(`Summary: ${plan.summary}`);
      plan.steps.forEach((step) => {
        console.log(`${step.step_number}. [${step.estimated_complexity}] ${step.description}`);
      });
    }
  }
}

一眼看懂这一页

先把这页到底在讲什么看明白，再去碰具体命令和配置，最不容易绕晕。

Get structured output from agents
   |
   v
这是 Input and output 里的一摊要紧活
   |
   v
先弄懂，再下手

文末提醒

这站会按官方 docs 的导航和内容变化继续重生成，原站加页、删页、改页时，这里会跟着更新。

人话解释会尽量顺着原页往下讲，但命令、参数名、配置名这些硬东西还是保留原样，免得你抄过去跑不起来。