Anthropic

Introdução

Adicione os pacotes NuGet necessários ao seu projeto.

dotnet add package Microsoft.Agents.AI.Anthropic --prerelease

Se estiver a usar o Microsoft Foundry, adicione também:

dotnet add package Anthropic.Foundry --prerelease

Configuration

Variáveis de ambiente

Configure as variáveis de ambiente necessárias para autenticação antrópica:

# Required for Anthropic API access
$env:ANTHROPIC_API_KEY="your-anthropic-api-key"
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"  # or your preferred model

Você pode obter uma chave de API do Anthropic Console.

Para Microsoft Foundry com chave de API

$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Subdomain before .services.ai.azure.com
$env:ANTHROPIC_API_KEY="your-anthropic-api-key"
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"

Para o Microsoft Foundry com a CLI do Azure

$env:ANTHROPIC_RESOURCE="your-foundry-resource-name"  # Subdomain before .services.ai.azure.com
$env:ANTHROPIC_CHAT_MODEL_NAME="claude-haiku-4-5"

Criando um agente antrópico

Criação Básica de Agentes (API Pública Antrópica)

A forma mais simples de criar um agente Anthropic usando a API pública:

var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY");
var deploymentName = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";

AnthropicClient client = new() { ApiKey = apiKey };

AIAgent agent = client.AsAIAgent(
    model: deploymentName,
    name: "HelpfulAssistant",
    instructions: "You are a helpful assistant.");

// Invoke the agent and output the text result.
Console.WriteLine(await agent.RunAsync("Hello, how can you help me?"));

Usar Anthropic na Fundição

Depois de configurar o Anthropic no Microsoft Foundry, pode usá-lo com autenticação por chave API:

Autenticação por chave API

var resource = Environment.GetEnvironmentVariable("ANTHROPIC_RESOURCE");
var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY");
var deploymentName = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";

AnthropicClient client = new AnthropicFoundryClient(
    new AnthropicFoundryApiKeyCredentials(apiKey, resource));

AIAgent agent = client.AsAIAgent(
    model: deploymentName,
    name: "FoundryAgent",
    instructions: "You are a helpful assistant using Anthropic on Microsoft Foundry.");

Console.WriteLine(await agent.RunAsync("How do I use Anthropic on Foundry?"));

Autenticação de credenciais Azure

Para ambientes onde as credenciais Azure são preferidas:

var resource = Environment.GetEnvironmentVariable("ANTHROPIC_RESOURCE");
var deploymentName = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";

AnthropicClient client = new AnthropicFoundryClient(
    new AnthropicFoundryIdentityTokenCredentials(
        new DefaultAzureCredential(),
        resource,
        ["https://ai.azure.com/.default"]));

AIAgent agent = client.AsAIAgent(
    model: deploymentName,
    name: "FoundryAgent",
    instructions: "You are a helpful assistant using Anthropic on Microsoft Foundry.");

Console.WriteLine(await agent.RunAsync("How do I use Anthropic on Foundry?"));

Tools

Pensamento expandido

Configure o raciocínio da Anthropic através da representação em bruto da mensagem e consuma TextReasoningContent a partir de respostas normais ou em fluxo.

var apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
var model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-haiku-4-5";
var maxTokens = 4096;
var thinkingTokens = 2048;

var agent = new AnthropicClient(new ClientOptions { ApiKey = apiKey })
    .AsAIAgent(
        model: model,
        clientFactory: (chatClient) => chatClient
            .AsBuilder()
            .ConfigureOptions(
                options => options.RawRepresentationFactory = (_) => new MessageCreateParams()
                {
                    Model = options.ModelId ?? model,
                    MaxTokens = options.MaxOutputTokens ?? maxTokens,
                    Messages = [],
                    Thinking = new ThinkingConfigParam(new ThinkingConfigEnabled(budgetTokens: thinkingTokens))
                })
            .Build());

Console.WriteLine("1. Non-streaming:");
var response = await agent.RunAsync("Solve this problem step by step: If a train travels 60 miles per hour and needs to cover 180 miles, how long will the journey take? Show your reasoning.");

Console.WriteLine("#### Start Thinking ####");
Console.WriteLine($"\e[92m{string.Join("\n", response.Messages.SelectMany(m => m.Contents.OfType<TextReasoningContent>().Select(c => c.Text)))}\e[0m");
Console.WriteLine("#### End Thinking ####");

Console.WriteLine("\n#### Final Answer ####");
Console.WriteLine(response.Text);

Console.WriteLine("Token usage:");
Console.WriteLine($"Input: {response.Usage?.InputTokenCount}, Output: {response.Usage?.OutputTokenCount}, {string.Join(", ", response.Usage?.AdditionalCounts ?? [])}");
Console.WriteLine();

Console.WriteLine("2. Streaming");
await foreach (var update in agent.RunStreamingAsync("Explain the theory of relativity in simple terms."))
{
    foreach (var item in update.Contents)
    {
        if (item is TextReasoningContent reasoningContent)
        {
            Console.WriteLine($"\e[92m{reasoningContent.Text}\e[0m");
        }
        else if (item is TextContent textContent)
        {
            Console.WriteLine(textContent.Text);
        }
    }
}

Competências Antrópicas

As capacidades geridas pela Anthropic podem criar ficheiros através do ambiente de execução de código alojado. O exemplo lista as competências disponíveis, configura a competência do PowerPoint e descarrega o ficheiro gerado.

using Microsoft.Extensions.AI;

string apiKey = Environment.GetEnvironmentVariable("ANTHROPIC_API_KEY") ?? throw new InvalidOperationException("ANTHROPIC_API_KEY is not set.");
// Skills require Claude 4.5 models (Sonnet 4.5, Haiku 4.5, or Opus 4.5)
string model = Environment.GetEnvironmentVariable("ANTHROPIC_CHAT_MODEL_NAME") ?? "claude-sonnet-4-5-20250929";

// Create the Anthropic client
AnthropicClient anthropicClient = new() { ApiKey = apiKey };

// List available Anthropic-managed skills (optional - API may not be available in all regions)
Console.WriteLine("Available Anthropic-managed skills:");
try
{
    SkillListPage skills = await anthropicClient.Beta.Skills.List(
        new SkillListParams { Source = "anthropic", Betas = [AnthropicBeta.Skills2025_10_02] });

    foreach (var skill in skills.Items)
    {
        Console.WriteLine($"  {skill.Source}: {skill.ID} (version: {skill.LatestVersionID})");
    }
}
catch (Exception ex)
{
    Console.WriteLine($"  (Skills listing not available: {ex.Message})");
}

Console.WriteLine();

// Define the pptx skill - the SDK handles all beta flags and container configuration automatically
// when using AsAITool(), so no manual RawRepresentationFactory configuration is needed.
BetaSkillParams pptxSkill = new()
{
    Type = BetaSkillParamsType.Anthropic,
    SkillID = "pptx",
    Version = "latest"
};

// Create an agent with the pptx skill enabled.
// Skills require extended thinking and higher max tokens for complex file generation.
// The SDK's AsAITool() handles beta flags and container config automatically.
ChatClientAgent agent = anthropicClient.Beta.AsAIAgent(
    model: model,
    instructions: "You are a helpful agent for creating PowerPoint presentations.",
    tools: [pptxSkill.AsAITool()],
    clientFactory: (chatClient) => chatClient
        .AsBuilder()
        .ConfigureOptions(options =>
        {
            options.RawRepresentationFactory = (_) => new MessageCreateParams()
            {
                Model = model,
                MaxTokens = 20000,
                Messages = [],
                Thinking = new BetaThinkingConfigParam(
                    new BetaThinkingConfigEnabled(budgetTokens: 10000))
            };
        })
        .Build());

Console.WriteLine("Creating a presentation about renewable energy...\n");

}

// Collect generated files from CodeInterpreterToolResultContent outputs
List<HostedFileContent> hostedFiles = response.Messages
    .SelectMany(m => m.Contents.OfType<CodeInterpreterToolResultContent>())
    .Where(c => c.Outputs is not null)
    .SelectMany(c => c.Outputs!.OfType<HostedFileContent>())
    .ToList();

if (hostedFiles.Count > 0)
{
    Console.WriteLine("\n#### Generated Files ####");
    foreach (HostedFileContent file in hostedFiles)
    {
        Console.WriteLine($"  FileId: {file.FileId}");

        // Download the file using the Anthropic Files API
        using HttpResponse fileResponse = await anthropicClient.Beta.Files.Download(
            file.FileId,
            new FileDownloadParams { Betas = ["files-api-2025-04-14"] });

        // Save the file to disk
        string fileName = $"presentation_{file.FileId.Substring(0, 8)}.pptx";
        using FileStream fileStream = File.Create(fileName);
        Stream contentStream = await fileResponse.ReadAsStream();
        await contentStream.CopyToAsync(fileStream);

Usando o agente

O agente é um AIAgent padrão e suporta todas as operações padrão de um agente.

Consulte os tutoriais de introdução ao agente para obter mais informações sobre como executar e interagir com agentes.

Pré-requisitos

Instale o pacote Anthropic do Microsoft Agent Framework.

pip install agent-framework-anthropic --pre

Configuration

Variáveis de ambiente

Configure as variáveis de ambiente necessárias para autenticação antrópica:

# Required for Anthropic API access
ANTHROPIC_API_KEY="your-anthropic-api-key"
ANTHROPIC_CHAT_MODEL="claude-sonnet-4-5-20250929"  # or your preferred model

# Optional: override the Anthropic API endpoint (e.g. for Foundry-compatible deployments)
ANTHROPIC_BASE_URL="https://your-custom-endpoint.com"

Como alternativa, você pode usar um .env arquivo na raiz do projeto:

ANTHROPIC_API_KEY=your-anthropic-api-key
ANTHROPIC_CHAT_MODEL=claude-sonnet-4-5-20250929
# ANTHROPIC_BASE_URL=https://your-custom-endpoint.com  # optional

Você pode obter uma chave de API do Anthropic Console.

Introdução

Importe as classes necessárias do Agent Framework:

import asyncio
from agent_framework import Agent
from agent_framework.anthropic import AnthropicClient

Criando um agente antrópico

Criação básica de agentes

A maneira mais simples de criar um agente antrópico:

from agent_framework import Agent

async def basic_example():
    # Create an agent using Anthropic
    agent = Agent(
        client=AnthropicClient(),
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("Hello, how can you help me?")
    print(result.text)

Usando a configuração explícita

Você pode fornecer configuração explícita em vez de depender de variáveis de ambiente:

from agent_framework import Agent

async def explicit_config_example():
    agent = Agent(
        client=AnthropicClient(
            model="claude-sonnet-4-5-20250929",
            api_key="your-api-key-here",
        ),
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("What can you do?")
    print(result.text)

O Anthropic SDK 1.x não suporta as opções temperature, top_p nem top_k. O Agent Framework ignora estas opções e regista um aviso se as fornecer.

Utilização de uma URL Base Personalizada

Passe base_url diretamente para AnthropicClient para apontá-lo a qualquer endpoint compatível com Anthropic, como uma implementação alojada na Foundry. Isto permite-lhe manter o mesmo AnthropicClient código e apenas alterar o endpoint, em vez de mudar para AnthropicFoundryClient:

from agent_framework import Agent

async def custom_base_url_example():
    agent = Agent(
        client=AnthropicClient(
            model="claude-haiku-4-5",
            api_key="your-api-key-here",
            base_url="https://your-foundry-resource.services.ai.azure.com/models/anthropic",
        ),
        name="HelpfulAssistant",
        instructions="You are a helpful assistant.",
    )

    result = await agent.run("What can you do?")
    print(result.text)

base_url Volta à ANTHROPIC_BASE_URL variável ambiente quando não é passada explicitamente.

Usar Anthropic na Fundição

Depois de configurares o Anthropic no Foundry, certifica-te de que tens as seguintes variáveis de ambiente definidas:

ANTHROPIC_FOUNDRY_API_KEY="your-foundry-api-key"
ANTHROPIC_FOUNDRY_RESOURCE="your-foundry-resource-name"
ANTHROPIC_CHAT_MODEL="claude-haiku-4-5"

Depois, crie o agente da seguinte forma:

from agent_framework import Agent
from agent_framework.anthropic import AnthropicFoundryClient

async def foundry_example():
    agent = Agent(
        client=AnthropicFoundryClient(),
        name="FoundryAgent",
        instructions="You are a helpful assistant using Anthropic on Foundry.",
    )

    result = await agent.run("How do I use Anthropic on Foundry?")
    print(result.text)

Utilizar o Anthropic no Amazon Bedrock

AnthropicBedrockClient encaminha a inferência do modelo Claude através do Amazon Bedrock.

AWS_ACCESS_KEY_ID="<access-key>"
AWS_SECRET_ACCESS_KEY="<secret-key>"
AWS_REGION="us-east-1"
# Optional:
AWS_PROFILE="<profile>"
AWS_SESSION_TOKEN="<session-token>"
ANTHROPIC_BEDROCK_BASE_URL="<custom-endpoint>"
ANTHROPIC_CHAT_MODEL="anthropic.claude-3-5-sonnet-20241022-v2:0"

Atualmente, não há um exemplo executável do Agent Framework publicado para AnthropicBedrockClient.

Utilizar Anthropic no Google Vertex AI

AnthropicVertexClient encaminha a inferência do modelo Claude através do Google Vertex AI.

CLOUD_ML_REGION="us-east5"
ANTHROPIC_VERTEX_PROJECT_ID="<google-cloud-project>"
ANTHROPIC_CHAT_MODEL="claude-sonnet-4@20250514"
# Optional:
ANTHROPIC_VERTEX_BASE_URL="<custom-endpoint>"

Atualmente, não há um exemplo executável do Agent Framework publicado para AnthropicVertexClient.

Lidar com falhas de pedidos

Para execuções com e sem streaming, as falhas nas solicitações ao SDK da Anthropic são comunicadas através de exceções do Agent Framework. Falhas de autenticação e de permissões geram ChatClientInvalidAuthException, outras falhas HTTP 4xx geram ChatClientInvalidRequestException, e todas as outras falhas do fornecedor geram ChatClientException.

Se o Anthropic invalidar uma resposta após o início de uma chamada de função local, o Agent Framework levanta ResponseInvalidatedException e não executa nem persiste a chamada invalidada. Um consumidor de streaming pode já ter recebido atualizações parciais quando ocorre a exceção; descarte essas atualizações em vez de as tratar como uma resposta concluída.

Perceba ChatClientException quando o mesmo tratamento de erros deve aplicar-se a todos os fornecedores de chat.

Tools

AnthropicClient expõe fábricas de ferramentas alojadas pela Anthropic, juntamente com o suporte padrão para ferramentas de função. Utilize client.get_*_tool(...) para construir uma ferramenta e passá-la através de tools= em Agent(...).

Para exemplos mais ricos — combinando MCP alojado, pesquisa na Web, raciocínio alargado e Competências da Anthropic — veja Ferramentas Alojadas abaixo.

Funcionalidades do agente

from typing import Annotated

def get_weather(
    location: Annotated[str, "The location to get the weather for."],
) -> str:
    """Get the weather for a given location."""
    conditions = ["sunny", "cloudy", "rainy", "stormy"]
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."

from agent_framework import Agent

async def tools_example():
    agent = Agent(
        client=AnthropicClient(),
        name="WeatherAgent",
        instructions="You are a helpful weather assistant.",
        tools=get_weather,  # Add tools to the agent
    )

    result = await agent.run("What's the weather like in Seattle?")
    print(result.text)

Respostas de streaming

Obtenha respostas à medida que são geradas para uma melhor experiência do utilizador:

from agent_framework import Agent

async def streaming_example():
    agent = Agent(
        client=AnthropicClient(),
        name="WeatherAgent",
        instructions="You are a helpful weather agent.",
        tools=get_weather,
    )

    query = "What's the weather like in Portland and in Paris?"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)
    async for chunk in agent.run(query, stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

Ferramentas hospedadas

Os agentes antrópicos suportam ferramentas hospedadas, como pesquisa na Web, MCP (Model Context Protocol) e execução de código:

from agent_framework import Agent
from agent_framework.anthropic import AnthropicClient

async def hosted_tools_example():
    client = AnthropicClient()
    agent = Agent(
        client=client,
        name="DocsAgent",
        instructions="You are a helpful agent for both Microsoft docs questions and general questions.",
        tools=[
            client.get_mcp_tool(
                name="Microsoft Learn MCP",
                url="https://learn.microsoft.com/api/mcp",
            ),
            client.get_web_search_tool(),
        ],
        default_options={"max_tokens": 20000},
    )

    result = await agent.run("Can you compare Python decorators with C# attributes?")
    print(result.text)

Pensamento Ampliado (Raciocínio)

Anthropic suporta capacidades de pensamento estendidas através do thinking recurso, que permite que o modelo mostre seu processo de raciocínio:

from agent_framework import Agent
from agent_framework.anthropic import AnthropicClient

async def thinking_example():
    client = AnthropicClient()
    agent = Agent(
        client=client,
        name="DocsAgent",
        instructions="You are a helpful agent.",
        tools=[client.get_web_search_tool()],
        default_options={
            "max_tokens": 20000,
            "thinking": {"type": "enabled", "budget_tokens": 10000}
        },
    )

    query = "Can you compare Python decorators with C# attributes?"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)

    async for chunk in agent.run(query, stream=True):
        for content in chunk.contents:
            if content.type == "text_reasoning":
                # Display thinking in a different color
                print(f"\033[32m{content.text}\033[0m", end="", flush=True)
            if content.type == "usage":
                print(f"\n\033[34m[Usage: {content.usage_details}]\033[0m\n", end="", flush=True)
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print()

Competências Antrópicas

A Anthropic oferece competências geridas que ampliam as capacidades dos agentes, como a criação de apresentações PowerPoint. As competências requerem a ferramenta Code Interpreter para funcionar:

from typing import cast

from agent_framework import Agent, Content
from agent_framework.anthropic import AnthropicClient
from anthropic import AsyncAnthropic

async def skills_example():
    client = AnthropicClient()
    anthropic_client = cast(AsyncAnthropic, client.anthropic_client)

    # Create an agent with the pptx skill enabled
    # Skills require the Code Interpreter tool
    agent = Agent(
        client=client,
        name="PresentationAgent",
        instructions="You are a helpful agent for creating PowerPoint presentations.",
        tools=client.get_code_interpreter_tool(),
        default_options={
            "max_tokens": 20000,
            "thinking": {"type": "enabled", "budget_tokens": 10000},
            "container": {
                "skills": [{"type": "anthropic", "skill_id": "pptx", "version": "latest"}]
            },
        },
    )

    query = "Create a presentation about renewable energy with 5 slides"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)

    files: list[Content] = []
    async for chunk in agent.run(query, stream=True):
        for content in chunk.contents:
            match content.type:
                case "text":
                    print(content.text, end="", flush=True)
                case "text_reasoning":
                    print(f"\033[32m{content.text}\033[0m", end="", flush=True)
                case "hosted_file":
                    # Catch generated files
                    files.append(content)

    print("\n")

    # Download generated files
    if files:
        print("Generated files:")
        for idx, file in enumerate(files):
            if file.file_id is None:
                continue
            file_content = await anthropic_client.files.download(
                file_id=file.file_id
            )
            filename = f"presentation-{idx}.pptx"
            with open(filename, "wb") as f:
                await file_content.write_to_file(f.name)
            print(f"File {idx}: {filename} saved to disk.")

Exemplo completo

# Copyright (c) Microsoft. All rights reserved.

import asyncio
from random import randint
from typing import Annotated

from agent_framework import Agent, tool
from agent_framework.anthropic import AnthropicClient

"""
Anthropic Chat Agent Example

This sample demonstrates using Anthropic with an agent and a single custom tool.
"""


# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/02-agents/tools/function_tool_with_approval.py and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
@tool(approval_mode="never_require")
def get_weather(
    location: Annotated[str, "The location to get the weather for."],
) -> str:
    """Get the weather for a given location."""
    conditions = ["sunny", "cloudy", "rainy", "stormy"]
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."


async def non_streaming_example() -> None:
    """Example of non-streaming response (get the complete result at once)."""
    print("=== Non-streaming Response Example ===")

    agent = Agent(
        client=AnthropicClient(),
        name="WeatherAgent",
        instructions="You are a helpful weather agent.",
        tools=get_weather,
    )

    query = "What's the weather like in Seattle?"
    print(f"User: {query}")
    result = await agent.run(query)
    print(f"Result: {result}\n")


async def streaming_example() -> None:
    """Example of streaming response (get results as they are generated)."""
    print("=== Streaming Response Example ===")

    agent = Agent(
        client=AnthropicClient(),
        name="WeatherAgent",
        instructions="You are a helpful weather agent.",
        tools=get_weather,
    )

    query = "What's the weather like in Portland and in Paris?"
    print(f"User: {query}")
    print("Agent: ", end="", flush=True)
    async for chunk in agent.run(query, stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    print("\n")


async def main() -> None:
    print("=== Anthropic Example ===")

    await streaming_example()
    await non_streaming_example()


if __name__ == "__main__":
    asyncio.run(main())

Usando o agente

O agente é um Agent padrão e suporta todas as operações padrão de um agente.

Consulte os tutoriais de introdução ao agente para obter mais informações sobre como executar e interagir com agentes.

Anthropic

O anthropicprovider pacote cria agentes usando a API Anthropic.

Installation

go get github.com/microsoft/agent-framework-go

Criar um agente Anthropic

import (
    "github.com/microsoft/agent-framework-go/agent"
    "github.com/microsoft/agent-framework-go/provider/anthropicprovider"

    "github.com/anthropics/anthropic-sdk-go"
)

a := anthropicprovider.NewAgent(
    anthropic.NewClient(), // uses ANTHROPIC_API_KEY env var
    anthropicprovider.AgentConfig{
        Model: "claude-sonnet-4-5",
        Instructions: "You are a helpful assistant.",
        Config: agent.Config{
            Name:         "ClaudeAgent",
        },
    },
)

resp, err := a.RunText(ctx, "Tell me a joke.").Collect()

Opções personalizadas

Passe parâmetros específicos do Anthropic usando anthropicprovider.MessageNewParams:

resp, err := a.RunText(ctx, "Hello!",
    anthropicprovider.MessageNewParams(anthropic.MessageNewParams{
        MaxTokens: 500,
    }),
).Collect()