LangChain 中文文档

外观

结构化输出允许智能体以特定、可预测的格式返回数据。无需解析自然语言响应，你就能获得 JSON 对象、Pydantic 模型或 dataclass 形式的可直接被应用使用的结构化数据。

TIP

本页介绍使用 create_agent 的智能体的结构化输出。要直接在模型上使用结构化输出（不在智能体范围内），请参见 模型 - 结构化输出。

LangChain 的 create_agent 会自动处理结构化输出。用户设置期望的结构化输出 schema，当模型生成结构化数据时，它会先被捕获、校验，然后返回到智能体状态的 'structured_response' 键中。

python
def create_agent(
    ...
    response_format: Union[
        ToolStrategy[StructuredResponseT],
        ProviderStrategy[StructuredResponseT],
        type[StructuredResponseT],
        None,
    ]
)

响应格式 ​

使用 response_format 控制智能体如何返回结构化数据：

  • ToolStrategy[StructuredResponseT]：使用工具调用进行结构化输出
  • ProviderStrategy[StructuredResponseT]：使用提供商原生结构化输出
  • type[StructuredResponseT]：Schema 类型——根据模型能力自动选择最佳策略
  • None：未显式请求结构化输出

当直接提供 schema 类型时，LangChain 会自动选择：

  • 如果所选模型和提供商支持原生结构化输出（例如 OpenAI、Anthropic (Claude) 或 xAI (Grok)），则选择 ProviderStrategy。
  • 对于所有其他模型，选择 ToolStrategy。

INFO

如果使用 langchain>=1.1，对原生结构化输出功能的支持会从模型的配置文件数据（profile data）中动态读取。如果数据不可用，请使用其他条件或手动指定：

python
custom_profile = {
    "structured_output": True,
    # ...
}
model = init_chat_model("...", profile=custom_profile)

如果指定了工具，模型必须支持同时使用工具和结构化输出。

结构化响应会返回到智能体最终状态的 structured_response 键中。 结构化输出允许智能体以特定、可预测的格式返回数据。无需解析自然语言响应，你就能获得类型化的结构化数据。

TIP

本页介绍使用 createAgent 的智能体的结构化输出。要直接在模型上使用结构化输出（不在智能体范围内），请参见 模型 - 结构化输出。

LangChain 预构建的 ReAct 智能体 createAgent 会自动处理结构化输出。用户设置期望的结构化输出 schema，当模型生成结构化数据时，它会先被捕获、校验，然后返回到智能体状态的 structuredResponse 键中。

ts
type ResponseFormat = (
    | ZodSchema<StructuredResponseT> // 一个 Zod schema
    | StandardSchema<StructuredResponseT> // 任何 Standard Schema 库
    | Record<string, unknown> // 一个 JSON Schema
)

const agent = createAgent({
    // ...
    responseFormat: ResponseFormat | ResponseFormat[]
})

响应格式 ​

控制智能体如何返回结构化数据。你可以提供 Zod schema、任何兼容 Standard Schema 的 schema，或 JSON Schema 对象。默认情况下，智能体使用工具调用策略，即通过额外的工具调用来创建输出。某些模型支持原生结构化输出，在这种情况下智能体会改用该策略。

你可以通过将 ResponseFormat 包装在 toolStrategy 或 providerStrategy 函数调用中来控制此行为：

ts
import { toolStrategy, providerStrategy } from "langchain";

const agent = createAgent({
    // 如果模型支持，则使用提供商策略
    responseFormat: providerStrategy(z.object({ ... }))
    // 或强制使用工具策略
    responseFormat: toolStrategy(z.object({ ... }))
})

结构化响应会返回到智能体最终状态的 structuredResponse 键中。

TIP

如果使用 langchain>=1.1，对原生结构化输出功能的支持会从模型的配置文件数据（profile data）中动态读取。如果数据不可用，请使用其他条件或手动指定：

typescript
const customProfile: ModelProfile = {
    structuredOutput: true,
    // ...
}
const model = await initChatModel("...", { profile: customProfile });

如果指定了工具，模型必须支持同时使用工具和结构化输出。

提供商策略 ​

一些模型提供商通过其 API 原生支持结构化输出（例如 OpenAI、xAI (Grok)、Gemini、Anthropic (Claude)）。在可用时，这是最可靠的方法。

要使用此策略，请配置 ProviderStrategy：

python
class ProviderStrategy(Generic[SchemaT]):
    schema: type[SchemaT]
    strict: bool | None = None

INFO

strict 参数要求 langchain>=1.2。

  • （必填）：定义结构化输出格式的 schema。支持： - Pydantic 模型：带字段校验的 BaseModel 子类。返回校验后的 Pydantic 实例。 - Dataclass：带类型注解的 Python dataclass。返回字典。 - TypedDict：类型化字典类。返回字典。 - JSON Schema：带 JSON schema 规范的字典。必须包含顶层 title 和 description 键。返回字典。

  • 可选布尔参数，用于启用严格 schema 遵循。部分提供商支持（例如 OpenAI 和 xAI）。默认为 None（禁用）。

当你直接将 schema 类型传递给 create_agent.response_format 且模型支持原生结构化输出时，LangChain 会自动使用 ProviderStrategy：

python
from pydantic import BaseModel, Field
from langchain.agents import create_agent

class ContactInfo(BaseModel):
    """Contact information for a person."""
    name: str = Field(description="The name of the person")
    email: str = Field(description="The email address of the person")
    phone: str = Field(description="The phone number of the person")

agent = create_agent(
    model="gpt-5.5",
    response_format=ContactInfo  # 自动选择 ProviderStrategy
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
})

print(result["structured_response"])
# ContactInfo(name='John Doe', email='john@example.com', phone='(555) 123-4567')
python
from dataclasses import dataclass
from langchain.agents import create_agent

@dataclass
class ContactInfo:
    """Contact information for a person."""
    name: str # 人员的姓名
    email: str # 人员的电子邮件地址
    phone: str # 人员的电话号码

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ContactInfo  # 自动选择 ProviderStrategy
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
})

result["structured_response"]
# {'name': 'John Doe', 'email': 'john@example.com', 'phone': '(555) 123-4567'}
python
from typing_extensions import TypedDict
from langchain.agents import create_agent

class ContactInfo(TypedDict):
    """Contact information for a person."""
    name: str # 人员的姓名
    email: str # 人员的电子邮件地址
    phone: str # 人员的电话号码

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ContactInfo  # 自动选择 ProviderStrategy
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
})

result["structured_response"]
# {'name': 'John Doe', 'email': 'john@example.com', 'phone': '(555) 123-4567'}
python
from langchain.agents import create_agent

contact_info_schema = {
    "title": "ContactInfo",
    "type": "object",
    "description": "Contact information for a person.",
    "properties": {
        "name": {"type": "string", "description": "The name of the person"},
        "email": {"type": "string", "description": "The email address of the person"},
        "phone": {"type": "string", "description": "The phone number of the person"}
    },
    "required": ["name", "email", "phone"]
}

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ProviderStrategy(contact_info_schema)
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
})

result["structured_response"]
# {'name': 'John Doe', 'email': 'john@example.com', 'phone': '(555) 123-4567'}
ts
function providerStrategy<StructuredResponseT>(
    schema: ZodSchema<StructuredResponseT> | SerializableSchema | JsonSchemaFormat
): ProviderStrategy<StructuredResponseT>
  • （必填）：定义结构化输出格式的 schema。支持： - Zod Schema：一个 zod schema - Standard Schema：任何实现 Standard Schema 规范的 schema - JSON Schema：一个 JSON schema 对象

当你直接将 schema 类型传递给 createAgent.responseFormat 且模型支持原生结构化输出时，LangChain 会自动使用 ProviderStrategy：

ts
import * as z from "zod";
import { createAgent, providerStrategy } from "langchain";

const ContactInfo = z.object({
    name: z.string().describe("The name of the person"),
    email: z.string().describe("The email address of the person"),
    phone: z.string().describe("The phone number of the person"),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: providerStrategy(ContactInfo)
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
});

console.log(result.structuredResponse);
// { name: "John Doe", email: "john@example.com", phone: "(555) 123-4567" }
ts
import * as v from "valibot";
import { toStandardJsonSchema } from "@valibot/to-json-schema";
import { createAgent, providerStrategy } from "langchain";

const ContactInfo = toStandardJsonSchema(
    v.object({
        name: v.pipe(v.string(), v.description("The name of the person")),
        email: v.pipe(v.string(), v.description("The email address of the person")),
        phone: v.pipe(v.string(), v.description("The phone number of the person")),
    })
);

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: providerStrategy(ContactInfo)
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
});

console.log(result.structuredResponse);
// { name: "John Doe", email: "john@example.com", phone: "(555) 123-4567" }
ts
import { createAgent, providerStrategy } from "langchain";

const contactInfoSchema = {
    "type": "object",
    "description": "Contact information for a person.",
    "properties": {
        "name": {"type": "string", "description": "The name of the person"},
        "email": {"type": "string", "description": "The email address of the person"},
        "phone": {"type": "string", "description": "The phone number of the person"}
    },
    "required": ["name", "email", "phone"]
}

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: providerStrategy(contactInfoSchema)
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]
});

console.log(result.structuredResponse);
// { name: "John Doe", email: "john@example.com", phone: "(555) 123-4567" }

提供商原生结构化输出提供高可靠性和严格校验，因为模型提供商会强制遵循 schema。在可用时请使用它。

INFO

如果你选择的模型提供商原生支持结构化输出，那么写 response_format=ProductReview 与写 response_format=ProviderStrategy(ProductReview) 在功能上是等价的。

无论哪种情况，如果不支持结构化输出，智能体都会回退到工具调用策略。

INFO

如果你选择的模型提供商原生支持结构化输出，那么写 responseFormat: contactInfoSchema 与写 responseFormat: providerStrategy(contactInfoSchema) 在功能上是等价的。

无论哪种情况，如果不支持结构化输出，智能体都会回退到工具调用策略。

工具调用策略 ​

对于不支持原生结构化输出的模型，LangChain 使用工具调用来实现同样的结果。这适用于所有支持工具调用的模型（大多数现代模型）。

要使用此策略，请配置 ToolStrategy：

python
class ToolStrategy(Generic[SchemaT]):
    schema: type[SchemaT]
    tool_message_content: str | None
    handle_errors: Union[
        bool,
        str,
        type[Exception],
        tuple[type[Exception], ...],
        Callable[[Exception], str],
    ]

  • （必填）：定义结构化输出格式的 schema。支持： - Pydantic 模型：带字段校验的 BaseModel 子类。返回校验后的 Pydantic 实例。 - Dataclass：带类型注解的 Python dataclass。返回字典。 - TypedDict：类型化字典类。返回字典。 - JSON Schema：带 JSON schema 规范的字典。必须包含顶层 title 和 description 键。返回字典。 - 联合类型：多个 schema 选项。模型会根据上下文选择最合适的 schema。

  • 生成结构化输出时返回的工具消息的自定义内容。 如果未提供，默认使用显示结构化响应数据的消息。

  • 结构化输出校验失败时的错误处理策略。默认为 True。 - True：使用默认错误模板捕获所有错误 - str：使用此自定义消息捕获所有错误 - type[Exception]：仅使用默认消息捕获此异常类型 - tuple[type[Exception], ...]：仅使用默认消息捕获这些异常类型 - Callable[[Exception], str]：返回错误消息的自定义函数 - False：不重试，让异常继续传播

python
from pydantic import BaseModel, Field
from typing import Literal
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class ProductReview(BaseModel):
    """Analysis of a product review."""
    rating: int | None = Field(description="The rating of the product", ge=1, le=5)
    sentiment: Literal["positive", "negative"] = Field(description="The sentiment of the review")
    key_points: list[str] = Field(description="The key points of the review. Lowercase, 1-3 words each.")

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ToolStrategy(ProductReview)
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})
result["structured_response"]
# ProductReview(rating=5, sentiment='positive', key_points=['fast shipping', 'expensive'])
python
from dataclasses import dataclass
from typing import Literal
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

@dataclass
class ProductReview:
    """Analysis of a product review."""
    rating: int | None  # 产品的评分（1-5）
    sentiment: Literal["positive", "negative"]  # 评论的情感倾向
    key_points: list[str]  # 评论的要点

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ToolStrategy(ProductReview)
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})
result["structured_response"]
# {'rating': 5, 'sentiment': 'positive', 'key_points': ['fast shipping', 'expensive']}
python
from typing import Literal
from typing_extensions import TypedDict
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class ProductReview(TypedDict):
    """Analysis of a product review."""
    rating: int | None  # 产品的评分（1-5）
    sentiment: Literal["positive", "negative"]  # 评论的情感倾向
    key_points: list[str]  # 评论的要点

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ToolStrategy(ProductReview)
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})
result["structured_response"]
# {'rating': 5, 'sentiment': 'positive', 'key_points': ['fast shipping', 'expensive']}
python
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

product_review_schema = {
    "title": "ProductReview",
    "type": "object",
    "description": "Analysis of a product review.",
    "properties": {
        "rating": {
            "type": ["integer", "null"],
            "description": "The rating of the product (1-5)",
            "minimum": 1,
            "maximum": 5
        },
        "sentiment": {
            "type": "string",
            "enum": ["positive", "negative"],
            "description": "The sentiment of the review"
        },
        "key_points": {
            "type": "array",
            "items": {"type": "string"},
            "description": "The key points of the review"
        }
    },
    "required": ["sentiment", "key_points"]
}

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ToolStrategy(product_review_schema)
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})
result["structured_response"]
# {'rating': 5, 'sentiment': 'positive', 'key_points': ['fast shipping', 'expensive']}
python
from pydantic import BaseModel, Field
from typing import Literal, Union
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class ProductReview(BaseModel):
    """Analysis of a product review."""
    rating: int | None = Field(description="The rating of the product", ge=1, le=5)
    sentiment: Literal["positive", "negative"] = Field(description="The sentiment of the review")
    key_points: list[str] = Field(description="The key points of the review. Lowercase, 1-3 words each.")

class CustomerComplaint(BaseModel):
    """A customer complaint about a product or service."""
    issue_type: Literal["product", "service", "shipping", "billing"] = Field(description="The type of issue")
    severity: Literal["low", "medium", "high"] = Field(description="The severity of the complaint")
    description: str = Field(description="Brief description of the complaint")

agent = create_agent(
    model="gpt-5.5",
    tools=tools,
    response_format=ToolStrategy(Union[ProductReview, CustomerComplaint])
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})
result["structured_response"]
# ProductReview(rating=5, sentiment='positive', key_points=['fast shipping', 'expensive'])

自定义工具消息内容 ​

tool_message_content 参数允许你自定义生成结构化输出时出现在对话历史中的消息：

python
from pydantic import BaseModel, Field
from typing import Literal
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class MeetingAction(BaseModel):
    """Action items extracted from a meeting transcript."""
    task: str = Field(description="The specific task to be completed")
    assignee: str = Field(description="Person responsible for the task")
    priority: Literal["low", "medium", "high"] = Field(description="Priority level")

agent = create_agent(
    model="gpt-5.5",
    tools=[],
    response_format=ToolStrategy(
        schema=MeetingAction,
        tool_message_content="Action item captured and added to meeting notes!"
    )
)

agent.invoke({
    "messages": [{"role": "user", "content": "From our meeting: Sarah needs to update the project timeline as soon as possible"}]
})
================================ Human Message =================================

From our meeting: Sarah needs to update the project timeline as soon as possible
================================== Ai Message ==================================
Tool Calls:
  MeetingAction (call_1)
 Call ID: call_1
  Args:
    task: Update the project timeline
    assignee: Sarah
    priority: high
================================= Tool Message =================================
Name: MeetingAction

Action item captured and added to meeting notes!

如果没有 tool_message_content，我们最终的 ToolMessage 将是：

================================= Tool Message =================================
Name: MeetingAction

Returning structured response: {'task': 'update the project timeline', 'assignee': 'Sarah', 'priority': 'high'}
ts
function toolStrategy<StructuredResponseT>(
    responseFormat:
        | JsonSchemaFormat
        | ZodSchema<StructuredResponseT>
        | SerializableSchema
        | (ZodSchema<StructuredResponseT> | SerializableSchema | JsonSchemaFormat)[]
    options?: ToolStrategyOptions
): ToolStrategy<StructuredResponseT>

  • （必填）：定义结构化输出格式的 schema。支持： - Zod Schema：一个 zod schema - Standard Schema：任何实现 Standard Schema 规范的 schema - JSON Schema：一个 JSON schema 对象

  • 生成结构化输出时返回的工具消息的自定义内容。 如果未提供，默认使用显示结构化响应数据的消息。

  • 包含可选 handleError 参数用于自定义错误处理策略的选项参数。 - true：使用默认错误模板捕获所有错误（默认） - False：不重试，让异常继续传播 - (error: ToolStrategyError) => string | Promise<string>：使用提供的消息重试或抛出错误

ts
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ProductReview = z.object({
    rating: z.number().min(1).max(5).optional(),
    sentiment: z.enum(["positive", "negative"]),
    keyPoints: z.array(z.string()).describe("The key points of the review. Lowercase, 1-3 words each."),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy(ProductReview)
})

const result = await agent.invoke({
    "messages": [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})

console.log(result.structuredResponse);
// { "rating": 5, "sentiment": "positive", "keyPoints": ["fast shipping", "expensive"] }
ts
import * as v from "valibot";
import { toStandardJsonSchema } from "@valibot/to-json-schema";
import { createAgent, toolStrategy } from "langchain";

const ProductReview = toStandardJsonSchema(
    v.object({
        rating: v.optional(v.pipe(v.number(), v.minValue(1), v.maxValue(5))),
        sentiment: v.picklist(["positive", "negative"]),
        keyPoints: v.pipe(v.array(v.string()), v.description("The key points of the review. Lowercase, 1-3 words each.")),
    })
);

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy(ProductReview)
})

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})

console.log(result.structuredResponse);
// { "rating": 5, "sentiment": "positive", "keyPoints": ["fast shipping", "expensive"] }
ts
import { createAgent, toolStrategy } from "langchain";

const productReviewSchema = {
    "type": "object",
    "description": "Analysis of a product review.",
    "properties": {
        "rating": {
            "type": ["integer", "null"],
            "description": "The rating of the product (1-5)",
            "minimum": 1,
            "maximum": 5
        },
        "sentiment": {
            "type": "string",
            "enum": ["positive", "negative"],
            "description": "The sentiment of the review"
        },
        "key_points": {
            "type": "array",
            "items": {"type": "string"},
            "description": "The key points of the review"
        }
    },
    "required": ["sentiment", "key_points"]
}

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy(productReviewSchema)
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})

console.log(result.structuredResponse);
// { "rating": 5, "sentiment": "positive", "keyPoints": ["fast shipping", "expensive"] }
ts
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ProductReview = z.object({
    rating: z.number().min(1).max(5).optional(),
    sentiment: z.enum(["positive", "negative"]),
    keyPoints: z.array(z.string()).describe("The key points of the review. Lowercase, 1-3 words each."),
});

const CustomerComplaint = z.object({
    issueType: z.enum(["product", "service", "shipping", "billing"]),
    severity: z.enum(["low", "medium", "high"]),
    description: z.string().describe("Brief description of the complaint"),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy([ProductReview, CustomerComplaint])
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "Analyze this review: 'Great product: 5 out of 5 stars. Fast shipping, but expensive'"}]
})

console.log(result.structuredResponse);
// { "rating": 5, "sentiment": "positive", "keyPoints": ["fast shipping", "expensive"] }

自定义工具消息内容 ​

toolMessageContent 参数允许你自定义生成结构化输出时出现在对话历史中的消息：

ts
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const MeetingAction = z.object({
    task: z.string().describe("The specific task to be completed"),
    assignee: z.string().describe("Person responsible for the task"),
    priority: z.enum(["low", "medium", "high"]).describe("Priority level"),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy(MeetingAction, {
        toolMessageContent: "Action item captured and added to meeting notes!"
    })
});

const result = await agent.invoke({
    messages: [{"role": "user", "content": "From our meeting: Sarah needs to update the project timeline as soon as possible"}]
});

console.log(result);
/**
 * {
 *   messages: [
 *     { role: "user", content: "From our meeting: Sarah needs to update the project timeline as soon as possible" },
 *     { role: "assistant", content: "Action item captured and added to meeting notes!", tool_calls: [ { name: "MeetingAction", args: { task: "update the project timeline", assignee: "Sarah", priority: "high" }, id: "call_456" } ] },
 *     { role: "tool", content: "Action item captured and added to meeting notes!", tool_call_id: "call_456", name: "MeetingAction" }
 *   ],
 *   structuredResponse: { task: "update the project timeline", assignee: "Sarah", priority: "high" }
 * }
 */

如果没有 toolMessageContent，我们会看到：

ts
# console.log(result);
/**
 * {
 *   messages: [
 *     ...
 *     { role: "tool", content: "Returning structured response: {'task': 'update the project timeline', 'assignee': 'Sarah', 'priority': 'high'}", tool_call_id: "call_456", name: "MeetingAction" }
 *   ],
 *   structuredResponse: { task: "update the project timeline", assignee: "Sarah", priority: "high" }
 * }
 */

错误处理 ​

模型在通过工具调用生成结构化输出时可能会出错。LangChain 提供了智能重试机制来自动处理这些错误。

多个结构化输出错误 ​

当模型错误地调用多个结构化输出工具时，智能体会在 ToolMessage 中提供错误反馈，并提示模型重试：

python
from pydantic import BaseModel, Field
from typing import Union
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class ContactInfo(BaseModel):
    name: str = Field(description="Person's name")
    email: str = Field(description="Email address")

class EventDetails(BaseModel):
    event_name: str = Field(description="Name of the event")
    date: str = Field(description="Event date")

agent = create_agent(
    model="gpt-5.5",
    tools=[],
    response_format=ToolStrategy(Union[ContactInfo, EventDetails])  # 默认：handle_errors=True
)

agent.invoke({
    "messages": [{"role": "user", "content": "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th"}]
})
================================ Human Message =================================

Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th
None
================================== Ai Message ==================================
Tool Calls:
  ContactInfo (call_1)
 Call ID: call_1
  Args:
    name: John Doe
    email: john@email.com
  EventDetails (call_2)
 Call ID: call_2
  Args:
    event_name: Tech Conference
    date: March 15th
================================= Tool Message =================================
Name: ContactInfo

Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.
 Please fix your mistakes.
================================= Tool Message =================================
Name: EventDetails

Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.
 Please fix your mistakes.
================================== Ai Message ==================================
Tool Calls:
  ContactInfo (call_3)
 Call ID: call_3
  Args:
    name: John Doe
    email: john@email.com
================================= Tool Message =================================
Name: ContactInfo

Returning structured response: {'name': 'John Doe', 'email': 'john@email.com'}
ts
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ContactInfo = z.object({
    name: z.string().describe("Person's name"),
    email: z.string().describe("Email address"),
});

const EventDetails = z.object({
    event_name: z.string().describe("Name of the event"),
    date: z.string().describe("Event date"),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy([ContactInfo, EventDetails]),
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content:
            "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th",
        },
    ],
});

console.log(result);

/**
 * {
 *   messages: [
 *     { role: "user", content: "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ContactInfo", args: { name: "John Doe", email: "john@email.com" }, id: "call_1" }, { name: "EventDetails", args: { event_name: "Tech Conference", date: "March 15th" }, id: "call_2" } ] },
 *     { role: "tool", content: "Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.\n Please fix your mistakes.", tool_call_id: "call_1", name: "ContactInfo" },
 *     { role: "tool", content: "Error: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected.\n Please fix your mistakes.", tool_call_id: "call_2", name: "EventDetails" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ContactInfo", args: { name: "John Doe", email: "john@email.com" }, id: "call_3" } ] },
 *     { role: "tool", content: "Returning structured response: {'name': 'John Doe', 'email': 'john@email.com'}", tool_call_id: "call_3", name: "ContactInfo" }
 *   ],
 *   structuredResponse: { name: "John Doe", email: "john@email.com" }
 * }
 */

Schema 校验错误 ​

当结构化输出与预期 schema 不匹配时，智能体提供具体的错误反馈：

python
from pydantic import BaseModel, Field
from langchain.agents import create_agent
from langchain.agents.structured_output import ToolStrategy

class ProductRating(BaseModel):
    rating: int | None = Field(description="Rating from 1-5", ge=1, le=5)
    comment: str = Field(description="Review comment")

agent = create_agent(
    model="gpt-5.5",
    tools=[],
    response_format=ToolStrategy(ProductRating),  # 默认：handle_errors=True
    system_prompt="You are a helpful assistant that parses product reviews. Do not make any field or value up."
)

agent.invoke({
    "messages": [{"role": "user", "content": "Parse this: Amazing product, 10/10!"}]
})
================================ Human Message =================================

Parse this: Amazing product, 10/10!
================================== Ai Message ==================================
Tool Calls:
  ProductRating (call_1)
 Call ID: call_1
  Args:
    rating: 10
    comment: Amazing product
================================= Tool Message =================================
Name: ProductRating

Error: Failed to parse structured output for tool 'ProductRating': 1 validation error for ProductRating.rating
  Input should be less than or equal to 5 [type=less_than_equal, input_value=10, input_type=int].
 Please fix your mistakes.
================================== Ai Message ==================================
Tool Calls:
  ProductRating (call_2)
 Call ID: call_2
  Args:
    rating: 5
    comment: Amazing product
================================= Tool Message =================================
Name: ProductRating

Returning structured response: {'rating': 5, 'comment': 'Amazing product'}

错误处理策略 ​

你可以使用 handle_errors 参数自定义错误的处理方式：

自定义错误消息：

python
ToolStrategy(
    schema=ProductRating,
    handle_errors="Please provide a valid rating between 1-5 and include a comment."
)

如果 handle_errors 是字符串，智能体将始终使用固定的工具消息提示模型重试：

================================= Tool Message =================================
Name: ProductRating

Please provide a valid rating between 1-5 and include a comment.

仅处理特定异常：

python
ToolStrategy(
    schema=ProductRating,
    handle_errors=ValueError  # 仅在遇到 ValueError 时重试，其余抛出
)

如果 handle_errors 是异常类型，那么仅当抛出的异常是指定类型时，智能体才会（使用默认错误消息）重试。在所有其他情况下，异常都会被抛出。

处理多种异常类型：

python
ToolStrategy(
    schema=ProductRating,
    handle_errors=(ValueError, TypeError)  # 遇到 ValueError 和 TypeError 时重试
)

如果 handle_errors 是异常元组，那么仅当抛出的异常是指定类型之一时，智能体才会（使用默认错误消息）重试。在所有其他情况下，异常都会被抛出。

自定义错误处理函数：

python

from langchain.agents.structured_output import StructuredOutputValidationError
from langchain.agents.structured_output import MultipleStructuredOutputsError

def custom_error_handler(error: Exception) -> str:
    if isinstance(error, StructuredOutputValidationError):
        return "There was an issue with the format. Try again."
    elif isinstance(error, MultipleStructuredOutputsError):
        return "Multiple structured outputs were returned. Pick the most relevant one."
    else:
        return f"Error: {str(error)}"

agent = create_agent(
    model="gpt-5.5",
    tools=[],
    response_format=ToolStrategy(
                        schema=Union[ContactInfo, EventDetails],
                        handle_errors=custom_error_handler
                    )  # 默认：handle_errors=True
)

result = agent.invoke({
    "messages": [{"role": "user", "content": "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th"}]
})

for msg in result['messages']:
    # 如果消息实际上是 ToolMessage 对象（而非字典），请检查其类名
    if type(msg).__name__ == "ToolMessage":
        print(msg.content)
    # 如果消息是字典，或者你想要一个回退方案
    elif isinstance(msg, dict) and msg.get('tool_call_id'):
        print(msg['content'])

发生 StructuredOutputValidationError 时：

================================= Tool Message =================================
Name: ToolStrategy

There was an issue with the format. Try again.

发生 MultipleStructuredOutputsError 时：

================================= Tool Message =================================
Name: ToolStrategy

Multiple structured outputs were returned. Pick the most relevant one.

发生其他错误时：

================================= Tool Message =================================
Name: ToolStrategy

Error: <error message>

不进行错误处理：

python
response_format = ToolStrategy(
    schema=ProductRating,
    handle_errors=False  # 所有错误都会被抛出
)
ts
import * as z from "zod";
import { createAgent, toolStrategy } from "langchain";

const ProductRating = z.object({
    rating: z.number().min(1).max(5).describe("Rating from 1-5"),
    comment: z.string().describe("Review comment"),
});

const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    responseFormat: toolStrategy(ProductRating),
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content: "Parse this: Amazing product, 10/10!",
        },
    ],
});

console.log(result);

/**
 * {
 *   messages: [
 *     { role: "user", content: "Parse this: Amazing product, 10/10!" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ProductRating", args: { rating: 10, comment: "Amazing product" }, id: "call_1" } ] },
 *     { role: "tool", content: "Error: Failed to parse structured output for tool 'ProductRating': 1 validation error for ProductRating\nrating\n  Input should be less than or equal to 5 [type=less_than_equal, input_value=10, input_type=int].\n Please fix your mistakes.", tool_call_id: "call_1", name: "ProductRating" },
 *     { role: "assistant", content: "", tool_calls: [ { name: "ProductRating", args: { rating: 5, comment: "Amazing product" }, id: "call_2" } ] },
 *     { role: "tool", content: "Returning structured response: {'rating': 5, 'comment': 'Amazing product'}", tool_call_id: "call_2", name: "ProductRating" }
 *   ],
 *   structuredResponse: { rating: 5, comment: "Amazing product" }
 * }
 */

错误处理策略 ​

你可以使用 handleErrors 参数自定义错误的处理方式：

自定义错误消息：

ts
const responseFormat = toolStrategy(ProductRating, {
    handleError: "Please provide a valid rating between 1-5 and include a comment."
)

// 错误消息变为：
// { role: "tool", content: "Please provide a valid rating between 1-5 and include a comment." }

仅处理特定异常：

ts
import { ToolInputParsingException } from "@langchain/core/tools";

const responseFormat = toolStrategy(ProductRating, {
    handleError: (error: ToolStrategyError) => {
        if (error instanceof ToolInputParsingException) {
        return "Please provide a valid rating between 1-5 and include a comment.";
        }
        return error.message;
    }
)

// 只有校验错误会使用默认消息重试：
// { role: "tool", content: "Error: Failed to parse structured output for tool 'ProductRating': ...\n Please fix your mistakes." }

处理多种异常类型：

ts
const responseFormat = toolStrategy(ProductRating, {
    handleError: (error: ToolStrategyError) => {
        if (error instanceof ToolInputParsingException) {
        return "Please provide a valid rating between 1-5 and include a comment.";
        }
        if (error instanceof CustomUserError) {
        return "This is a custom user error.";
        }
        return error.message;
    }
)

不进行错误处理：

ts
const responseFormat = toolStrategy(ProductRating, {
    handleError: false  // 所有错误都会被抛出
)