SDK de observabilidade

Instale os pacotes essenciais de observabilidade e runtime. Todos os agentes que usam a Observabilidade do Agent 365 precisam desses pacotes.

pip install microsoft-agents-a365-observability-core
pip install microsoft-agents-a365-runtime

Se o seu agente usa o pacote Hospedagem de Agentes da Microsoft, instale o pacote de integração de hospedagem. Ele fornece middleware que preenche automaticamente a bagagem e os escopos a partir do TurnContext, e inclui o armazenamento de tokens para o exportador de observabilidade.

pip install microsoft-agents-a365-observability-hosting

Se o seu agente usa um das estruturas de IA com suporte, instale a extensão correspondente de instrumentação automática para capturar telemetria automaticamente, sem código manual de instrumentação. Para obter detalhes de configuração, consulte Instrumentação automática.

# For Semantic Kernel
pip install microsoft-agents-a365-observability-extensions-semantic-kernel

# For OpenAI Agents SDK
pip install microsoft-agents-a365-observability-extensions-openai

# For Microsoft Agent Framework
pip install microsoft-agents-a365-observability-extensions-agent-framework

# For LangChain
pip install microsoft-agents-a365-observability-extensions-langchain

Instale os pacotes essenciais de observabilidade e runtime. Todos os agentes que usam a Observabilidade do Agent 365 precisam desses pacotes.

npm install @microsoft/agents-a365-observability
npm install @microsoft/agents-a365-runtime

Se o seu agente usa o pacote @microsoft/agents-hosting, instale o pacote de integração de hospedagem. Ele fornece middleware que preenche automaticamente a bagagem e os escopos a partir do TurnContext, e inclui o armazenamento de tokens para o exportador de observabilidade.

npm install @microsoft/agents-a365-observability-hosting

Se o seu agente usa um das estruturas de IA com suporte, instale a extensão correspondente de instrumentação automática para capturar telemetria automaticamente, sem código manual de instrumentação. Para obter detalhes de configuração, consulte Instrumentação automática.

// For OpenAI Agents SDK
npm install @microsoft/agents-a365-observability-extensions-openai

// For LangChain
npm install @microsoft/agents-a365-observability-extensions-langchain

Instale o pacote principal de observabilidade e o pacote de runtime. Todos os agentes que usam a Observabilidade do Agent 365 precisam desse pacote.

dotnet add package Microsoft.Agents.A365.Observability.Runtime

Se o seu agente usa o pacote Microsoft.Agents.A365.Observability.Hosting do NuGet, instale o pacote de integração de hospedagem. Ele fornece middleware que preenche automaticamente a bagagem e os escopos a partir do TurnContext, e inclui o armazenamento de tokens para o exportador de observabilidade.

dotnet add package Microsoft.Agents.A365.Observability.Hosting

Se o seu agente usa um das estruturas de IA com suporte, instale a extensão correspondente de instrumentação automática para capturar telemetria automaticamente, sem código manual de instrumentação. Para obter detalhes de configuração, consulte Instrumentação automática.

// For Semantic Kernel
dotnet add package Microsoft.Agents.A365.Observability.Extensions.SemanticKernel

// For OpenAI
dotnet add package Microsoft.Agents.A365.Observability.Extensions.OpenAI

// For Agent Framework
dotnet add package Microsoft.Agents.A365.Observability.Extensions.AgentFramework

Defina a ENABLE_A365_OBSERVABILITY_EXPORTER variável do ambiente como true para observabilidade. Essa configuração exporta logs para o serviço e requer que seja fornecido um token_resolver. Caso contrário, o exportador de console será usado.

from microsoft_agents_a365.observability.core import configure

def token_resolver(agent_id: str, tenant_id: str) -> str | None:
    # Implement secure token retrieval here
    return "Bearer <token>"

configure(
    service_name="my-agent-service",
    service_namespace="my.namespace",
    token_resolver=token_resolver,
)

O resolvedor de tokens não é incluído no registro de logs do console.

Você pode personalizar o comportamento do exportador passando uma instância Agent365ExporterOptions para exporter_options. Quando exporter_options é fornecido, ele tem precedência sobre os parâmetros token_resolver e cluster_category.

from microsoft_agents_a365.observability.core import configure, Agent365ExporterOptions

configure(
    service_name="my-agent-service",
    service_namespace="my.namespace",
    exporter_options=Agent365ExporterOptions(
        cluster_category="prod",
        token_resolver=token_resolver,
    ),
    suppress_invoke_agent_input=True,
)

A tabela a seguir descreve os parâmetros opcionais para configure().

A tabela a seguir descreve as propriedades opcionais para Agent365ExporterOptions.

Defina a ENABLE_A365_OBSERVABILITY_EXPORTER variável do ambiente como true para observabilidade. Essa configuração exporta logs para o serviço e requer que um resolvedor de tokens seja fornecido. Caso contrário, o exportador de console será usado.

import { ObservabilityManager } from '@microsoft/agents-a365-observability';

// Define a token resolver to authenticate with the observability service for exporting logs
const tokenResolver = (agentId, tenantId) => {
    // Your token resolution logic here
    return "your-token";
};

// Advanced configuration with builder pattern
const builder = ObservabilityManager.configure(builder =>
  builder
    .withService('my-agent-service', '1.0.0')
    .withTokenResolver((agentId, tenantId) => {
      return tokenResolver(agentId, tenantId);
    })
);

builder.start();

Como alternativa às variáveis de ambiente, você pode configurar a observabilidade de forma programática usando um provedor de configuração por meio do método withConfigurationProvider. Se você também usar métodos de construtores individuais (como withExporterOptions ou withClusterCategory), os métodos de construtores individuais têm precedência sobre os valores do provedor de configuração.

import { ObservabilityManager } from '@microsoft/agents-a365-observability';
import { ObservabilityConfiguration } from '@microsoft/agents-a365-observability';

const configProvider = new ObservabilityConfiguration({
  isObservabilityExporterEnabled: () => true,
  // Set log levels as pipe-separated values (for example, 'info|warn|error')
  observabilityLogLevel: () => 'info|warn|error',
});

const builder = ObservabilityManager.configure(builder =>
  builder
    .withService('my-agent-service', '1.0.0')
    .withConfigurationProvider(configProvider)
    .withTokenResolver((agentId, tenantId) => {
      return tokenResolver(agentId, tenantId);
    })
);

builder.start();

Você pode personalizar o comportamento do exportador passando uma instância Agent365ExporterOptions para withExporterOptions. Essa opção permite controlar o processamento em lote, os tempos limite e o modo de roteamento.

import {
  ObservabilityManager,
  Agent365ExporterOptions,
} from '@microsoft/agents-a365-observability';
import { ClusterCategory } from '@microsoft/agents-a365-runtime';

const exporterOptions = new Agent365ExporterOptions();
exporterOptions.maxQueueSize = 10;

const builder = ObservabilityManager.configure(builder =>
  builder
    .withService('my-agent-service', '1.0.0')
    .withClusterCategory(ClusterCategory.prod)
    .withExporterOptions(exporterOptions)
    .withTokenResolver(tokenResolver)
);

builder.start();

A tabela a seguir descreve as propriedades opcionais para Agent365ExporterOptions.

Você também pode fornecer um logger personalizado que implemente a interface ILogger (info, warn, error, event). Passe-o para o construtor usando withCustomLogger.

const builder = ObservabilityManager.configure(builder =>
  builder
    .withService('my-agent-service', '1.0.0')
    .withCustomLogger({
      info: (message, ...args) => { /* your logging logic */ },
      warn: (message, ...args) => { /* your logging logic */ },
      error: (message, ...args) => { /* your logging logic */ },
      event: (eventName, success, durationMs, message, details) => { /* your logging logic */ }
    })
    .withTokenResolver((agentId, tenantId) => {
      return tokenResolver(agentId, tenantId);
    })
);

builder.start();

Definir EnableAgent365Exporter como true em appsettings.json.

Em Program.cs, adicione Agent365ExporterOptions à coleção de serviços. Essa alteração configura o delegado que o exportador de rastreamento usa para recuperar o token.

Adicione dependências relacionadas à observabilidade usando AddA365Tracing().

using Microsoft.Agents.A365.Observability.Runtime;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Exporters;

var builder = WebApplication.CreateBuilder(args);

builder.Services.AddSingleton(sp =>
    {
        return new Agent365ExporterOptions
        {
            TokenResolver = async (agentId, tenantId) =>
            {
                // It's recommended to implement caching in your token provider for performance.
                var token = await tokenProvider.GetObservabilityTokenAsync(agentId, tenantId);
                return token;
            }
        };
    });

builder.AddA365Tracing();

Você pode personalizar o comportamento do exportador passando um delegado de configuração e um tipo de exportador para AddA365Tracing().

builder.AddA365Tracing(
    configure: tracingBuilder =>
    {
        // Use the builder to add extensions (e.g., WithSemanticKernel(), WithOpenAI())
    },
    agent365ExporterType: Agent365ExporterType.Agent365ExporterAsync
);

A tabela a seguir descreve as propriedades opcionais para Agent365ExporterOptions.

from microsoft_agents_a365.observability.core import BaggageBuilder

with (
    BaggageBuilder()
    .tenant_id("tenant-123")
    .agent_id("agent-456")
    .conversation_id("conv-789")
    .build()
):
    # Any spans started in this context will receive these as attributes
    pass

Para preencher automaticamente o BaggageBuilder a partir do TurnContext, use o auxiliar populate no pacote microsoft-agents-a365-observability-hosting. Esse auxiliar extrai automaticamente os detalhes do chamador, agente, locatário, canal e conversa da atividade.

from microsoft_agents.hosting.core.turn_context import TurnContext
from microsoft_agents_a365.observability.core import BaggageBuilder
from microsoft_agents_a365.observability.hosting.scope_helpers.populate_baggage import populate

builder = BaggageBuilder()
populate(builder, turn_context)

with builder.build():
    # Baggage is auto-populated from the TurnContext activity
    pass

import { BaggageBuilder } from '@microsoft/agents-a365-observability';

// Create and apply baggage context
const baggageScope = new BaggageBuilder()
  // Core identifiers
  .tenantId('tenant-123')
  .agentId('agent-456')
  .conversationId('conv-789')
  .build();

// Execute operations within the baggage context
baggageScope.run(() => {
  // All spans created within this context will inherit the baggage values

  // Invoke another agent
  const agentScope = InvokeAgentScope.start(request, scopeDetails, agentDetails);
  // ... agent logic

  // Execute tools
  const toolScope = ExecuteToolScope.start(request, toolDetails, agentDetails);
  // ... tool logic
});

Para preencher automaticamente o BaggageBuilder a partir do TurnContext, use o auxiliar fromTurnContext no pacote @microsoft/agents-a365-observability-hosting. Esse auxiliar extrai automaticamente os detalhes do chamador, agente, locatário, canal e conversa da atividade.

import { BaggageBuilder } from '@microsoft/agents-a365-observability';
import { BaggageBuilderUtils } from '@microsoft/agents-a365-observability-hosting';

const baggageScope = BaggageBuilderUtils.fromTurnContext(new BaggageBuilder(), context)
  .invokeAgentServer(context.activity.serviceUrl, 3978)
  .build();

await baggageScope.run(async () => {
  // Baggage is auto-populated from the TurnContext activity
});

using Microsoft.Agents.A365.Observability.Runtime.Common;

using var baggageScope = new BaggageBuilder()
    .TenantId("tenant-123")
    .AgentId("agent-456")
    .ConversationId("conv-789")
    .Build();
// Any spans started in this context will receive them as attributes.

Para preencher automaticamente o BaggageBuilder a partir do ITurnContext, use o método de extensão FromTurnContext no pacote Microsoft.Agents.A365.Observability.Hosting. Esse método extrai automaticamente os detalhes do chamador, agente, locatário, canal e conversa da atividade.

using Microsoft.Agents.A365.Observability.Runtime.Common;
using Microsoft.Agents.A365.Observability.Hosting.Extensions;

using var baggageScope = new BaggageBuilder()
    .FromTurnContext(turnContext)
    .Build();

Registre BaggageMiddleware no conjunto do middleware do adaptador. Ele extrai automaticamente os detalhes de chamadas, agente, locatário, canal e conversa de cada entrada TurnContext e encapsula a solicitação em um escopo de bagagem.

from microsoft_agents_a365.observability.hosting import BaggageMiddleware

adapter.use(BaggageMiddleware())

Como alternativa, use ObservabilityHostingManager para configurar o middleware de bagagem junto com outros recursos de hospedagem:

from microsoft_agents_a365.observability.hosting import ObservabilityHostingManager, ObservabilityHostingOptions

options = ObservabilityHostingOptions(enable_baggage=True)
ObservabilityHostingManager.configure(adapter.middleware_set, options)

O middleware ignora a configuração de dados adicionais para respostas assíncronas (eventos ContinueConversation) para evitar substituir as informações que a solicitação de origem já estabeleceu.

Registre BaggageMiddleware no adaptador. Ele extrai automaticamente os detalhes de chamadas, agente, locatário, canal e conversa de cada entrada TurnContext e encapsula a solicitação em um escopo de bagagem.

import { BaggageMiddleware } from '@microsoft/agents-a365-observability-hosting';

// Option 1: Register middleware directly on the adapter
adapter.use(new BaggageMiddleware());

Como alternativa, use ObservabilityHostingManager para configurar o middleware de bagagem junto com outros recursos de hospedagem:

import { ObservabilityHostingManager } from '@microsoft/agents-a365-observability-hosting';

const manager = new ObservabilityHostingManager();
manager.configure(adapter, { enableBaggage: true });

O middleware ignora a configuração de dados adicionais para respostas assíncronas (eventos ContinueConversation) para evitar substituir as informações que a solicitação de origem já estabeleceu.

Registre BaggageTurnMiddleware no adaptador. Ele extrai automaticamente os detalhes de chamadas, agente, locatário, canal e conversa de cada entrada ITurnContext e encapsula a solicitação em um escopo de bagagem.

using Microsoft.Agents.A365.Observability.Hosting.Middleware;

adapter.Use(new BaggageTurnMiddleware());

O middleware ignora a configuração de dados adicionais para respostas assíncronas (eventos ContinueConversation) para evitar substituir as informações que a solicitação de origem já estabeleceu.

Se você precisar de bagagem de nível HTTP (por exemplo, para definir IDs de locatário e agente antes das execuções do pipeline do Bot Framework), registre ObservabilityBaggageMiddleware no pipeline do ASP.NET Core usando o método de extensão UseObservabilityRequestContext. Você deve fornecer uma função de resolvedor que extraia a ID do locatário e a ID do agente do contexto HTTP.

using Microsoft.Agents.A365.Observability.Hosting.Middleware;

app.UseObservabilityRequestContext((httpContext) =>
{
    // Extract tenant and agent IDs from your request context
    var tenantId = GetTenantIdFromContext(httpContext);
    var agentId = GetAgentIdFromContext(httpContext);
    return (tenantId, agentId);
});

O exemplo de código a seguir mostra como gerar um token usando o SDK microsoft_agents.hosting.core. O token de autenticação gerado aqui é usado para exportar os intervalos para o serviço de ingestão do A365. Os agentes podem gerar um token por conta própria, por exemplo, usando a a MSAL (Biblioteca de Autenticação da Microsoft), mas precisam garantir que o token tenha o escopo de observabilidade.

from microsoft_agents.activity import load_configuration_from_env
from microsoft_agents.authentication.msal import MsalConnectionManager
from microsoft_agents.hosting.aiohttp import CloudAdapter
from microsoft_agents.hosting.core import (
    AgentApplication,
    Authorization,
    MemoryStorage,
    TurnContext,
    TurnState,
)
from microsoft_agents_a365.runtime import (
    get_observability_authentication_scope,
)

agents_sdk_config = load_configuration_from_env(environ)

STORAGE = MemoryStorage()
CONNECTION_MANAGER = MsalConnectionManager(**agents_sdk_config)
ADAPTER = CloudAdapter(connection_manager=CONNECTION_MANAGER)
ADAPTER.use(TranscriptLoggerMiddleware(ConsoleTranscriptLogger()))
AUTHORIZATION = Authorization(STORAGE, CONNECTION_MANAGER, **agents_sdk_config)

AGENT_APP = AgentApplication[TurnState](
    storage=STORAGE, adapter=ADAPTER, authorization=AUTHORIZATION, **agents_sdk_config
)

@AGENT_APP.activity("message", auth_handlers=["AGENTIC"])
async def on_message(context: TurnContext, _state: TurnState):
    aau_auth_token = await AGENT_APP.auth.exchange_token(
                        context,
                        scopes=get_observability_authentication_scope(),
                        auth_handler_id="AGENTIC",
                    )
    # cache this auth token and return via token resolver

Para um agente criado com a CLI do AA365 que usar um colega de equipe de IA e o pacote Biblioteca de Hosting de Observabilidade do Microsoft Agent 365, use AgenticTokenCache para tratar o cache de tokens automaticamente. Registre o token uma vez por agente e locatário durante um manipulador de atividades e passe cache.get_observability_token como token_resolver na configuração de observabilidade.

from microsoft_agents_a365.observability.core import configure
from microsoft_agents_a365.observability.hosting.token_cache_helpers import (
    AgenticTokenCache,
    AgenticTokenStruct,
)
from microsoft_agents_a365.runtime import get_observability_authentication_scope

# Create a shared cache instance
token_cache = AgenticTokenCache()

# Use the cache as your token resolver in configure()
configure(
    service_name="my-agent-service",
    service_namespace="my.namespace",
    token_resolver=token_cache.get_observability_token,
)

@AGENT_APP.activity("message", auth_handlers=["AGENTIC"])
async def on_message(context: TurnContext, _state: TurnState):
    token_cache.register_observability(
        agent_id="agent-456",
        tenant_id="tenant-123",
        token_generator=AgenticTokenStruct(
            authorization=AGENT_APP.auth,
            turn_context=context,
        ),
        observability_scopes=get_observability_authentication_scope(),
    )

O exemplo de código a seguir mostra como gerar um token usando o SDK @microsoft/agents-hosting. O token de autenticação gerado aqui é usado para exportar os intervalos para o serviço de ingestão do A365. Os agentes podem gerar um token por conta própria, por exemplo, usando a a MSAL (Biblioteca de Autenticação da Microsoft), mas precisam garantir que o token tenha o escopo de observabilidade.

import {
  TurnState,
  AgentApplication,
  MemoryStorage,
  TurnContext,
} from '@microsoft/agents-hosting';
import { ActivityTypes } from '@microsoft/agents-activity';
import { getObservabilityAuthenticationScope } from '@microsoft/agents-a365-runtime';

interface ConversationState {
  count: number;
}
type ApplicationTurnState = TurnState<ConversationState>;

const storage = new MemoryStorage();

export const agentApplication = new AgentApplication<ApplicationTurnState>({
  authorization: {
    agentic: {}, // We have the type and scopes set in the .env file
  },
  storage,
});

agentApplication.onActivity(
  ActivityTypes.Message,
  async (context: TurnContext, state: ApplicationTurnState) => {
    const aauAuthToken = await agentApplication.authorization.exchangeToken(context, 'agentic', {
      scopes: getObservabilityAuthenticationScope()
    });
    // cache this auth token and return via token resolver
  }
);

Para um agente criado com a CLI do A365 que usa um colega de equipe de IA e o pacote @microsoft/agents-a365-observability-hosting, use AgenticTokenCacheInstance para tratar o cache de token automaticamente. Chame RefreshObservabilityToken uma vez por agente e locatário durante um manipulador de atividades e informe AgenticTokenCacheInstance.getObservabilityToken como o parâmetro tokenResolver na configuração de observabilidade.

import { ObservabilityManager } from '@microsoft/agents-a365-observability';
import { AgenticTokenCacheInstance } from '@microsoft/agents-a365-observability-hosting';
import { getObservabilityAuthenticationScope } from '@microsoft/agents-a365-runtime';

// Use the cache as your token resolver in configure()
const builder = ObservabilityManager.configure(builder =>
  builder
    .withService('my-agent-service', '1.0.0')
    .withTokenResolver((agentId, tenantId) =>
      AgenticTokenCacheInstance.getObservabilityToken(agentId, tenantId)
    )
);

builder.start();

agentApplication.onActivity(
  ActivityTypes.Message,
  async (context: TurnContext, state: ApplicationTurnState) => {
    const agentId = context.activity.recipient?.agenticAppId || '';
    const tenantId = context.activity.recipient?.tenantId || '';

    await AgenticTokenCacheInstance.RefreshObservabilityToken(
      agentId,
      tenantId,
      context,
      agentApplication.authorization,
      getObservabilityAuthenticationScope()
    );
  }
);

O exemplo de código a seguir mostra como gerar um token usando o SDK de hospedagem Microsoft.Agents. Usar o token de autenticação que você gera para exportar os intervalos para o serviço de ingestão do A365. Os agentes podem gerar um token por conta própria, por exemplo, usando a a MSAL (Biblioteca de Autenticação da Microsoft), mas precisam garantir que o token tenha o escopo de observabilidade.

Forneça um resolvedor de tokens registrando-se Agent365ExporterOptions com um TokenResolver Delegado. O delegado recebe o agentId e o tenantId e retorna um token de autenticação.

using Microsoft.Agents.A365.Observability.Runtime.Tracing.Exporters;

builder.Services.AddSingleton(sp =>
    {
        return new Agent365ExporterOptions
        {
            TokenResolver = async (agentId, tenantId) =>
            {
                // Implement your token retrieval logic here
                return await GetTokenAsync(agentId, tenantId);
            }
        };
    });

Para um agente criado com a CLI do A365 que usa um colega de equipe de IA e o pacote Microsoft.Agents.A365.Observability.Hosting do NuGet, use o método AddAgenticTracingExporter() para lidar automaticamente com o cache de token por meio de injeção de dependência.

using Microsoft.Agents.A365.Observability.Hosting;

builder.Services.AddAgenticTracingExporter();

Na aplicativo do agente, registre o token.

using Microsoft.Agents.Builder;
using Microsoft.Agents.Builder.App.UserAuth;
using Microsoft.Extensions.Logging;
using Microsoft.Agents.A365.Observability.Hosting.Caching;
using Microsoft.Agents.A365.Observability.Runtime.Common;
using System;
using System.Threading.Tasks;

public class MyAgent : AgentApplication
{
    private readonly IExporterTokenCache<AgenticTokenStruct> _agentTokenCache;
    private readonly ILogger<MyAgent> _logger;

    public MyAgent(AgentApplicationOptions options, IExporterTokenCache<AgenticTokenStruct> agentTokenCache, ILogger<MyAgent> logger)
        : base(options)
    {
        _agentTokenCache = agentTokenCache ?? throw new ArgumentNullException(nameof(agentTokenCache));
        _logger = logger ?? throw new ArgumentNullException(nameof(logger));
    }

    protected async Task MessageActivityAsync(ITurnContext turnContext, ITurnState turnState, CancellationToken cancellationToken)
    {
        using var baggageScope = new BaggageBuilder()
            .TenantId(turnContext.Activity.Recipient.TenantId)
            .AgentId(turnContext.Activity.Recipient.AgenticAppId)
            .Build();

        try
        {
            _agentTokenCache.RegisterObservability(
                turnContext.Activity.Recipient.AgenticAppId,
                turnContext.Activity.Recipient.TenantId,
                new AgenticTokenStruct(
                    userAuthorization: UserAuthorization,
                    turnContext: turnContext,
                    authHandlerName: "AGENTIC"
                ),
                EnvironmentUtils.GetObservabilityAuthenticationScope()
            );
        }
        catch (Exception ex)
        {
            _logger.LogWarning($"Error registering for observability: {ex.Message}");
        }
    }
}

Instale o pacote.

pip install microsoft-agents-a365-observability-extensions-semantic-kernel

Configure a observabilidade.

from microsoft_agents_a365.observability.core import configure
from microsoft_agents_a365.observability.extensions.semantickernel.trace_instrumentor import SemanticKernelInstrumentor

# Configure observability
configure(
    service_name="my-semantic-kernel-agent",
    service_namespace="ai.agents"
)

# Enable auto-instrumentation
instrumentor = SemanticKernelInstrumentor()
instrumentor.instrument()

# Your Semantic Kernel code is now automatically traced

Não há suporte ao Kernel semântico pelo JavaScript.

Adicione dependências à coleção de serviços.

using Microsoft.Agents.A365.Observability.Extensions.SemanticKernel;

builder.AddA365Tracing(configure: config => config.WithSemanticKernel());

Defina AgentId e TenantId usando BaggageBuilder. Certifique-se de que a ID que você usa ao criar um ChatCompletionAgent corresponde à ID do agente para quem você passa para BaggageBuilder..

using Microsoft.Agents.A365.Observability.Extensions.SemanticKernel;
using Microsoft.Agents.A365.Observability.Runtime.Common;
public class MyAgent
{
    public async Task<AgentResponse> ProcessUserRequest(string userInput)
    {
      using var baggageScope = new BaggageBuilder()
          .AgentId(<your-agent-id>) // NOTE: This will be the agent ID with which the TokenResolver delegate is invoked. 
          .TenantId(<your-tenant-id>) // NOTE: This will be the tenant ID with which the TokenResolver delegate is invoked.
          .Build();
      
      var chatCompletionAgent = new ChatCompletionAgent
      {
          // NOTE: This will be the agent ID with which the TokenResolver delegate is invoked. Should match above.
          Id = <your-agent-id>,
          ...
      };
    }
}

Instale o pacote.

pip install microsoft-agents-a365-observability-extensions-openai

Configure a observabilidade.

from microsoft_agents_a365.observability.core import configure
from microsoft_agents_a365.observability.extensions.openai import OpenAIAgentsTraceInstrumentor

# Configure observability
configure(
    service_name="my-openai-agent",
    service_namespace="ai.agents"
)

# Enable auto-instrumentation
instrumentor = OpenAIAgentsTraceInstrumentor()
instrumentor.instrument()

# Your OpenAI Agents code is now automatically traced

Instale o pacote.

npm install @microsoft/agents-a365-observability-extensions-openai

Configure a observabilidade.

import { ObservabilityManager } from '@microsoft/agents-a365-observability';
import { OpenAIAgentsTraceInstrumentor } from '@microsoft/agents-a365-observability-extensions-openai';

// Configure observability first
const sdk = ObservabilityManager.configure((builder) =>
  builder
    .withService('My Agent Service', '1.0.0')
);

// Create and enable the instrumentor
const instrumentor = new OpenAIAgentsTraceInstrumentor({
  enabled: true,
  tracerName: 'openai-agents-tracer',
  tracerVersion: '1.0.0'
});

sdk.start();

instrumentor.enable();

Adicione dependências à coleção de serviços.

using Microsoft.Agents.A365.Observability.Extensions.OpenAI;

builder.AddA365Tracing(configure: config => config.WithOpenAI());

Defina AgentId e TenantId usando BaggageBuilder. Para chamadas de ferramenta, inicie um rastreamento usando Trace() em uma instância ChatToolCall.

using Microsoft.Agents.A365.Observability.Extensions.OpenAI;
using Microsoft.Agents.A365.Observability.Runtime.Common;

public class MyAgent
{
    public async Task<AgentResponse> ProcessUserRequest(string userInput)
    {
      using var baggageScope = new BaggageBuilder()
          .AgentId(<your-agent-id>) // NOTE: This will be the agent ID with which the TokenResolver delegate is invoked. 
          .TenantId(<your-tenant-id>) // NOTE: This will be the tenant ID with which the TokenResolver delegate is invoked.
          .Build();
      
      // NOTE: This will be the agent and tenant ID with which the TokenResolver delegate will be invoked. 
      using var scope = chatToolCall.Trace(agentId: <your-agent-id>, <your-tenant-id>);
    }
}

Instale o pacote.

pip install microsoft-agents-a365-observability-extensions-agent-framework

Configure a observabilidade.

from microsoft_agents_a365.observability.core import configure
from microsoft_agents_a365.observability.extensions.agentframework import (
    AgentFrameworkInstrumentor,
)

# Configure observability
configure(
    service_name="AgentFrameworkTracingWithAzureOpenAI",
    service_namespace="AgentFrameworkTesting",
)

# Enable auto-instrumentation
AgentFrameworkInstrumentor().instrument()

Não há suporte ao Agent Framework com JavaScript.

Adicione dependências à coleção de serviços.

using Microsoft.Agents.A365.Observability.Extensions.AgentFramework;

builder.AddA365Tracing(configure: config => config.WithAgentFramework());

Defina AgentId e TenantId usando BaggageBuilder.

using Microsoft.Agents.A365.Observability.Runtime.Common;

public class MyAgent : AgentApplication
{
    protected async Task MessageActivityAsync(ITurnContext turnContext, ITurnState turnState, CancellationToken cancellationToken)
    {
      using var baggageScope = new BaggageBuilder()
          .AgentId(<your-agent-id>) // NOTE: This will be the agent ID with which the TokenResolver delegate is invoked. 
          .TenantId(<your-tenant-id>) // NOTE: This will be the tenant ID with which the TokenResolver delegate is invoked.
          .Build();
    }
}

Instale o pacote.

pip install microsoft-agents-a365-observability-extensions-langchain

Configure a observabilidade.

from microsoft_agents_a365.observability.core.config import configure
from microsoft_agents_a365.observability.extensions.langchain import CustomLangChainInstrumentor

# Configure observability
configure(
    service_name="my-langchain-agent",
    service_namespace="ai.agents"
)

# Enable auto-instrumentation
CustomLangChainInstrumentor()

# Your LangChain code is now automatically traced

Instale o pacote.

npm install @microsoft/agents-a365-observability-extensions-langchain

Configure a observabilidade.

import { ObservabilityManager } from '@microsoft/agents-a365-observability';
import { LangChainTraceInstrumentor } from '@microsoft/agents-a365-observability-extensions-langchain';
import * as LangChainCallbacks from '@langchain/core/callbacks/manager';

// Configure observability first
const sdk = ObservabilityManager.configure((builder) =>
  builder
    .withService('My Agent Service', '1.0.0')
);

sdk.start();

// Enable LangChain auto-instrumentation
LangChainTraceInstrumentor.instrument(LangChainCallbacks);

// Your LangChain code is now automatically traced

Não há suporte a LangChain com .NET.

from microsoft_agents_a365.observability.core import (
    InvokeAgentScope,
    InvokeAgentScopeDetails,
    AgentDetails,
    CallerDetails,
    UserDetails,
    Channel,
    Request,
    ServiceEndpoint,
)

agent_details = AgentDetails(
    agent_id="agent-456",
    agent_name="My Agent",
    agent_description="An AI agent powered by Azure OpenAI",
    agentic_user_id="auid-123",
    agentic_user_email="agent@contoso.com",
    agent_blueprint_id="blueprint-789",
    tenant_id="tenant-123",
)

scope_details = InvokeAgentScopeDetails(
    endpoint=ServiceEndpoint(hostname="myagent.contoso.com", port=443),
)

request = Request(
    content="User asks a question",
    session_id="session-42",
    conversation_id="conv-xyz",
    channel=Channel(name="msteams"),
)

caller_details = CallerDetails(
    user_details=UserDetails(
        user_id="user-123",
        user_email="jane.doe@contoso.com",
        user_name="Jane Doe",
    ),
)

with InvokeAgentScope.start(request, scope_details, agent_details, caller_details):
    # Perform agent invocation logic
    response = call_agent(...)

import {
  InvokeAgentScope,
  InvokeAgentScopeDetails,
  AgentDetails,
  CallerDetails,
  UserDetails,
  Channel,
  Request,
  ServiceEndpoint,
} from '@microsoft/agents-a365-observability';

// Use the same agentDetails instance across all scopes in a request
const agentDetails: AgentDetails = {
  agentId: 'agent-456',
  agentName: 'Email Assistant',
  agentDescription: 'An AI agent powered by Azure OpenAI',
  agentAuid: 'auid-123',
  agentEmail: 'agent@contoso.com',
  agentBlueprintId: 'blueprint-789',
  tenantId: 'tenant-123',
};

const scopeDetails: InvokeAgentScopeDetails = {
  endpoint: { host: 'myagent.contoso.com', port: 443 } as ServiceEndpoint,
};

// Use the same request instance across all scopes in a request
const request: Request = {
  content: 'Please help me organize my emails',
  sessionId: 'session-42',
  conversationId: 'conv-xyz',
  channel: { name: 'msteams' } as Channel,
};

// Optional: Caller details (human user, or agent-to-agent)
const callerDetails: CallerDetails = {
  userDetails: {
    userId: 'user-123',
    userEmail: 'jane.doe@contoso.com',
    userName: 'Jane Doe',
  } as UserDetails,
};

const scope = InvokeAgentScope.start(request, scopeDetails, agentDetails, callerDetails);

try {
  await scope.withActiveSpanAsync(async () => {
    // Record input messages
    scope.recordInputMessages(['Please help me organize my emails', 'Focus on urgent items']);

    // Your agent invocation logic here
    const response = await invokeAgent(request.content);

    // Record output messages
    scope.recordOutputMessages(['I found 15 urgent emails', 'Here is your organized inbox']);
  });
} catch (error) {
  scope.recordError(error as Error);
  throw error;
} finally {
  scope.dispose();
}

Se o seu agente usa o pacote @microsoft/agents-a365-observability-hosting, você pode usar ScopeUtils.populateInvokeAgentScopeFromTurnContext para criar o escopo com detalhes do agente, detalhes do chamador e informações do canal automaticamente derivadas de TurnContext.

import { InvokeAgentScopeDetails, AgentDetails, ServiceEndpoint } from '@microsoft/agents-a365-observability';
import { ScopeUtils } from '@microsoft/agents-a365-observability-hosting';

const agentDetails: AgentDetails = { agentId: 'agent-456' };
const scopeDetails: InvokeAgentScopeDetails = {
  endpoint: { host: 'myagent.contoso.com', port: 443 } as ServiceEndpoint,
};

const scope = ScopeUtils.populateInvokeAgentScopeFromTurnContext(
  agentDetails,
  scopeDetails,
  context,     // TurnContext
  authToken    // authentication token string
);

try {
  await scope.withActiveSpanAsync(async () => {
    // Agent details, caller details, and channel are auto-populated from context
    const response = await invokeAgent(context.activity.text);
    scope.recordOutputMessages([response]);
  });
} finally {
  scope.dispose();
}

using System;
using System.Threading.Tasks;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Contracts;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Scopes;

public class MyAgent
{
    public async Task<AgentResponse> ProcessUserRequest(string userInput)
    {
        var agentDetails = new AgentDetails(
            agentId: "agent-456",
            agentName: "MyAgent",
            agentDescription: "Handles user requests.",
            agenticUserId: "auid-123",
            agenticUserEmail: "agent@contoso.com",
            agentBlueprintId: "blueprint-789",
            tenantId: "tenant-123"
        );

        var scopeDetails = new InvokeAgentScopeDetails(
            endpoint: new Uri("https://myagent.contoso.com")
        );

        var request = new Request(
            content: userInput,
            sessionId: "session-abc",
            channel: new Channel("msteams"),
            conversationId: "conv-xyz"
        );

        var callerDetails = new CallerDetails(
            userDetails: new UserDetails(
                userId: "user-123",
                userEmail: "jane.doe@contoso.com",
                userName: "Jane Doe"
            )
        );

        // Start the scope
        using var scope = InvokeAgentScope.Start(
            request: request,
            scopeDetails: scopeDetails,
            agentDetails: agentDetails,
            callerDetails: callerDetails
        );

        // Record input messages
        scope.RecordInputMessages(new[] { userInput });

        // ... your agent logic here ...

        var output = $"Processed: {userInput}";
        scope.RecordOutputMessages(new[] { output });

        return new AgentResponse { Content = output };
    }
}

public class AgentResponse
{
    public string Content { get; set; }
}

from microsoft_agents_a365.observability.core import (
    ExecuteToolScope,
    ToolCallDetails,
    Request,
    ServiceEndpoint,
)

# Use the same agent_details and request instances from the InvokeAgentScope example above

tool_details = ToolCallDetails(
    tool_name="summarize",
    tool_type="function",
    tool_call_id="tc-001",
    arguments="{'text': '...'}",
    description="Summarize provided text",
    endpoint=ServiceEndpoint(hostname="tools.contoso.com", port=8080),
)

with ExecuteToolScope.start(request, tool_details, agent_details) as scope:
    result = run_tool(tool_details)
    scope.record_response(result)

import { ExecuteToolScope, ToolCallDetails } from '@microsoft/agents-a365-observability';

// Use the same agentDetails and request instances from the InvokeAgentScope example above

const toolDetails: ToolCallDetails = {
  toolName: 'email-search',
  arguments: JSON.stringify({ query: 'from:boss@company.com', limit: 10 }),
  toolCallId: 'tool-call-456',
  description: 'Search emails by criteria',
  toolType: 'function',
  endpoint: {
    host: 'tools.contoso.com',
    port: 8080,  // Will be recorded since not 443
    protocol: 'https'
  },
};

const scope = ExecuteToolScope.start(request, toolDetails, agentDetails);

try {
  return await scope.withActiveSpanAsync(async () => {
    // Execute the tool
    const result = await searchEmails(toolDetails.arguments);

    // Record the tool execution result
    scope.recordResponse(result);

    return result;
  });
} catch (error) {
  scope.recordError(error as Error);
  throw error;
} finally {
  scope.dispose();
}

Se o agente usar o pacote @microsoft/agents-a365-observability-hosting, use ScopeUtils.populateExecuteToolScopeFromTurnContext para criar o escopo com os detalhes do agente derivados automaticamente do TurnContext.

import { ToolCallDetails } from '@microsoft/agents-a365-observability';
import { ScopeUtils } from '@microsoft/agents-a365-observability-hosting';

const toolDetails: ToolCallDetails = {
  toolName: 'email-search',
  arguments: JSON.stringify({ query: 'from:boss@company.com' }),
  toolCallId: 'tool-call-456',
  toolType: 'function',
};

const scope = ScopeUtils.populateExecuteToolScopeFromTurnContext(
  toolDetails,
  context,     // TurnContext
  authToken    // authentication token string
);

try {
  await scope.withActiveSpanAsync(async () => {
    const result = await searchEmails(toolDetails.arguments);
    scope.recordResponse(JSON.stringify(result));
  });
} finally {
  scope.dispose();
}

using System;
using System.Threading.Tasks;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Contracts;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Scopes;

// Use the same agentDetails and request instances from the InvokeAgentScope example above

var toolCallDetails = new ToolCallDetails(
    toolName: "summarize",
    arguments: "{\"text\": \"...\"}",
    toolCallId: "tc-001",
    description: "Summarize provided text",
    toolType: "function",
    endpoint: new Uri("https://tools.contoso.com:8080")
);

using var scope = ExecuteToolScope.Start(
    request: request,
    details: toolCallDetails,
    agentDetails: agentDetails
);

// ... your tool logic here ...

scope.RecordResponse("{\"summary\": \"The text was summarized.\"}");

from microsoft_agents_a365.observability.core import (
    InferenceScope,
    InferenceCallDetails,
    InferenceOperationType,
)

# Use the same agent_details and request instances from the InvokeAgentScope example above

inference_details = InferenceCallDetails(
    operationName=InferenceOperationType.CHAT,
    model="gpt-4o-mini",
    providerName="azure-openai",
    inputTokens=123,
    outputTokens=456,
    finishReasons=["stop"],
)

with InferenceScope.start(request, inference_details, agent_details) as scope:
    completion = call_llm(...)
    scope.record_output_messages([completion.text])
    scope.record_input_tokens(completion.usage.input_tokens)
    scope.record_output_tokens(completion.usage.output_tokens)

import { InferenceScope, InferenceDetails, InferenceOperationType } from '@microsoft/agents-a365-observability';

// Use the same agentDetails and request instances from the InvokeAgentScope example above

const inferenceDetails: InferenceDetails = {
  operationName: InferenceOperationType.CHAT,
  model: 'gpt-4o-mini',
  providerName: 'azure-openai',
};

const scope = InferenceScope.start(request, inferenceDetails, agentDetails);

try {
  return await scope.withActiveSpanAsync(async () => {
    // Record input messages
    scope.recordInputMessages(['Summarize the following emails for me...']);

    // Call the LLM
    const response = await callLLM();

    // Record detailed telemetry with granular methods
    scope.recordOutputMessages(['Here is your email summary...']);
    scope.recordInputTokens(145);
    scope.recordOutputTokens(82);
    scope.recordFinishReasons(['stop']);

    return response.text;
  });
} catch (error) {
  scope.recordError(error as Error);
  throw error;
} finally {
  scope.dispose();
}

Se o agente usar o pacote @microsoft/agents-a365-observability-hosting, você poderá usar ScopeUtils.populateInferenceScopeFromTurnContext para criar o escopo com os detalhes do agente derivados automaticamente do TurnContext.

import { InferenceDetails, InferenceOperationType } from '@microsoft/agents-a365-observability';
import { ScopeUtils } from '@microsoft/agents-a365-observability-hosting';

const inferenceDetails: InferenceDetails = {
  operationName: InferenceOperationType.CHAT,
  model: 'gpt-4o-mini',
  providerName: 'azure-openai',
};

const scope = ScopeUtils.populateInferenceScopeFromTurnContext(
  inferenceDetails,
  context,     // TurnContext
  authToken    // authentication token string
);

try {
  await scope.withActiveSpanAsync(async () => {
    const response = await callLLM();
    scope.recordOutputMessages([response.text]);
    scope.recordInputTokens(response.usage.inputTokens);
    scope.recordOutputTokens(response.usage.outputTokens);
  });
} finally {
  scope.dispose();
}

using Microsoft.Agents.A365.Observability.Runtime.Tracing.Contracts;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Scopes;

// Use the same agentDetails and request instances from the InvokeAgentScope example above

var inferenceDetails = new InferenceCallDetails(
    operationName: InferenceOperationType.Chat,
    model: "gpt-4o-mini",
    providerName: "Azure OpenAI",
    inputTokens: 123,
    outputTokens: 456,
    finishReasons: new[] { "stop" }
);

using var scope = InferenceScope.Start(
    request: request,
    details: inferenceDetails,
    agentDetails: agentDetails
);

// ... your inference logic here ...

scope.RecordOutputMessages(new[] { "AI response message" });
scope.RecordInputTokens(123);
scope.RecordOutputTokens(456);

from microsoft_agents_a365.observability.core import (
    OutputScope,
    Response,
    SpanDetails,
)

# Use the same agent_details and request instances from the InvokeAgentScope example above

# Get the parent context from the originating scope
parent_context = invoke_scope.get_context()

response = Response(messages=["Here is your organized inbox with 15 urgent emails."])

with OutputScope.start(
    request,
    response,
    agent_details,
    span_details=SpanDetails(parent_context=parent_context),
):
    # Output messages are recorded automatically from the response
    pass

import { OutputScope, OutputResponse, SpanDetails } from '@microsoft/agents-a365-observability';

// Use the same agentDetails and request instances from the InvokeAgentScope example above

// Get the parent context from the originating scope
const parentContext = invokeScope.getSpanContext();

const response: OutputResponse = {
  messages: ['Here is your organized inbox with 15 urgent emails.'],
};

const scope = OutputScope.start(
  request,
  response,
  agentDetails,
  undefined, // userDetails
  { parentContext } as SpanDetails
);

// Output messages are recorded automatically from the response
scope.dispose();

using Microsoft.Agents.A365.Observability.Runtime.Tracing.Contracts;
using Microsoft.Agents.A365.Observability.Runtime.Tracing.Scopes;

// Use the same agentDetails and request instances from the InvokeAgentScope example above

// Get the parent context from the originating scope
var parentContext = invokeScope.GetActivityContext();

var response = new Response(new[] { "Here is your organized inbox with 15 urgent emails." });

using var scope = OutputScope.Start(
    request: request,
    response: response,
    agentDetails: agentDetails,
    spanDetails: new SpanDetails(parentContext: parentContext)
);
// Output messages are recorded automatically from the response

Defina a variável de ambiente ENABLE_A365_OBSERVABILITY_EXPORTER como false. Essa configuração exporta intervalos (rastreamentos) para o console.

Para investigar falhas de exportação, habilite o log detalhado definindo ENABLE_A365_OBSERVABILITY_EXPORTER como true e configure o log de depuração na inicialização do aplicativo:

import logging

logging.basicConfig(level=logging.DEBUG)
logging.getLogger("microsoft_agents_a365.observability.core").setLevel(logging.DEBUG)

# Or target only the exporter:
logging.getLogger(
    "microsoft_agents_a365.observability.core.exporters.agent365_exporter"
).setLevel(logging.DEBUG)

Principais mensagens de log:

DEBUG  Token resolved for agent {agentId} tenant {tenantId}
DEBUG  Exporting {n} spans to {url}
DEBUG  HTTP 200 - correlation ID: abc-123
ERROR  Token resolution failed: {error}
ERROR  HTTP 401 exporting spans - correlation ID: abc-123
INFO   No spans with tenant/agent identity found; nothing exported.

Defina a variável de ambiente ENABLE_A365_OBSERVABILITY_EXPORTER como false. Essa configuração exporta intervalos (rastreamentos) para o console.

Para investigar falhas de exportação, defina variáveis de ambiente em .env ou shell:

# Enable the Agent365 exporter
ENABLE_A365_OBSERVABILITY_EXPORTER=true

# Enable verbose logging
A365_OBSERVABILITY_LOG_LEVEL=info|warn|error

Verifique a saída do console para mensagens como:

[INFO]  [Agent365Exporter] Exporting 245 spans
[INFO]  [Agent365Exporter] Partitioned into 3 identity groups (2 spans skipped)
[INFO]  [Agent365Exporter] Token resolved successfully via tokenResolver
[EVENT] export-group succeeded in 98ms {"tenantId":"...","agentId":"...","correlationId":"abc-123"}
[ERROR] [Agent365Exporter] Failed with status 401, correlation ID: abc-123
[WARN]  export-partition-span-missing-identity: 5 spans skipped due to missing tenant or agent ID

Opcionalmente, use um logger personalizado para capturar eventos de exportação em um arquivo:

import { setLogger, ExporterEventNames } from '@microsoft/agents-a365-observability';

setLogger({
  info: (msg, ...args) => myLogger.info(msg, ...args),
  warn: (msg, ...args) => myLogger.warn(msg, ...args),
  error: (msg, ...args) => myLogger.error(msg, ...args),
  event: (eventType: ExporterEventNames, isSuccess: boolean, durationMs: number,
          message?: string, details?: Record<string, string>) => {
    myLogger.info({ eventType, isSuccess, durationMs, message, ...details });
  }
});

Definir EnableAgent365Exporter como false em appsettings.json. Essa configuração exporta intervalos (rastreamentos) para o console.

Para investigar falhas de exportação, configure o registro em log detalhado em appsettings.json:

{
  "EnableAgent365Exporter": "True",
  "Logging": {
    "LogLevel": {
      "Microsoft.Agents.A365.Observability": "Debug"
    }
  }
}

Ou defina variáveis de ambiente:

EnableAgent365Exporter=True
A365_OBSERVABILITY_DOMAIN_OVERRIDE=https://your-test-endpoint.example.com
A365_OBSERVABILITY_SCOPE_OVERRIDE=https://api.powerplatform.com/.default

Principais mensagens de log:

info: Agent365ExporterCore: Obtained token for agent {agentId} tenant {tenantId}.
info: Agent365ExporterCore: Sending {count} spans to {requestUri} for agent {agentId} tenant {tenantId}.
info: Agent365ExporterCore: HTTP {statusCode} exporting spans. 'x-ms-correlation-id': '{correlationId}'.
error: Agent365Exporter: Exception exporting spans: {exception}
warn: Agent365ExporterCore: No token obtained for agent {agentId} tenant {tenantId}. Skipping export.