Distribución Microsoft OpenTelemetry

Prerequisites: Python 3.10 o posterior.

pip install microsoft-opentelemetry

Requisitos previos: Node.js 18 o posterior. Las aplicaciones de ESM requieren Node.js 20.6.0 o posterior.

npm install @microsoft/opentelemetry

node --import @microsoft/opentelemetry/loader ./dist/index.js

Instale el paquete NuGet Microsoft.OpenTelemetry. Este único paquete incluye el entorno de ejecución de observabilidad del Agente 365, la integración de hospedaje, la instrumentación automática para marcos de IA compatibles y las bibliotecas openTelemetry estándar.

<PackageReference Include="Microsoft.OpenTelemetry" />

O bien, use la CLI de .NET:

dotnet add package Microsoft.OpenTelemetry

Llame a use_microsoft_opentelemetry() para habilitar la observabilidad.

from microsoft.opentelemetry import use_microsoft_opentelemetry
from microsoft.opentelemetry.a365.hosting.token_cache_helpers import AgenticTokenCache

token_cache = AgenticTokenCache()

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=lambda agent_id, tenant_id: (
        (t := asyncio.run(token_cache.get_observability_token(agent_id, tenant_id)))
        and t.token or None
    ),
)

Para la resolución de tokens personalizada (en lugar de la resolución de tokens predeterminada), consulte Resolución de tokens manual.

Puede personalizar el comportamiento del exportador pasando los kwargs opcionales a365_* a use_microsoft_opentelemetry().

Use ObservabilityManager con AgenticTokenCacheInstance para controlar el almacenamiento en caché de tokens automáticamente:

import { useMicrosoftOpenTelemetry, AgenticTokenCacheInstance } from '@microsoft/opentelemetry';
import { resourceFromAttributes } from '@opentelemetry/resources';

useMicrosoftOpenTelemetry({
  resource: resourceFromAttributes({
    'service.name': 'Default Token Cache Sample',
    'service.version': '1.0.0',
  }),
  azureMonitor: {
    enabled: Boolean(process.env.APPLICATIONINSIGHTS_CONNECTION_STRING),
  },
  instrumentationOptions: {
    http: { enabled: false },
  },
  a365: {
    enabled: process.env.ENABLE_A365_OBSERVABILITY_EXPORTER !== 'false',
    tokenResolver: (agentId, tenantId) =>
      AgenticTokenCacheInstance.getObservabilityToken(agentId, tenantId) ?? '',
  },
});

Para la resolución de tokens personalizada (en lugar de la resolución de tokens predeterminada), consulte Resolución de tokens manual.

Puede personalizar el comportamiento del exportador estableciendo propiedades opcionales en el a365 objeto .

Para obtener opciones de configuración completas y variables de entorno, consulte el archivo Léame del repositorio de JavaScript.

En Program.cs, llame a UseMicrosoftOpenTelemetry() para habilitar la observabilidad. La enumeración de banderas ExportTarget controla dónde se envía la telemetría: combine los destinos mediante | (por ejemplo, ExportTarget.Console | ExportTarget.Agent365).

Caché automática de tokens (DI) (recomendada para aplicaciones de Agent Framework):

Cuando no se establece TokenResolver, la distribución registra automáticamente IExporterTokenCache<AgenticTokenStruct> a través de la inyección de dependencias. El agente llama RegisterObservability() a en tiempo de ejecución para proporcionar credenciales y la memoria caché controla la adquisición y actualización de tokens.

// Program.cs — no TokenResolver needed
builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Exporters = ExportTarget.Agent365;
    // TokenResolver is auto-registered via the agentic token cache in DI, with required imports in the next code snippet.
});

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

// In your agent class
public class MyAgent : AgentApplication
{
    private readonly IExporterTokenCache<AgenticTokenStruct> _agentTokenCache;

    public MyAgent(AgentApplicationOptions options,
        IExporterTokenCache<AgenticTokenStruct> agentTokenCache) : base(options)
    {
        _agentTokenCache = agentTokenCache;
    }

    protected async Task MessageActivityAsync(
        ITurnContext turnContext, ITurnState turnState, CancellationToken cancellationToken)
    {
        _agentTokenCache.RegisterObservability(
            turnContext.Activity.Recipient.AgenticAppId,
            turnContext.Activity.Recipient.TenantId,
            new AgenticTokenStruct(
                userAuthorization: UserAuthorization,
                turnContext: turnContext,
                authHandlerName: "AGENTIC"),
            EnvironmentUtils.GetObservabilityAuthenticationScope());
    }
}

Para la resolución de tokens personalizada (en lugar de la resolución de tokens predeterminada), consulte Resolución de tokens manual.

Puede personalizar el comportamiento del exportador estableciendo propiedades opcionales en o.Agent365.Exporter.

from microsoft.opentelemetry.a365.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 rellenar automáticamente el BaggageBuilder desde el TurnContext, use la herramienta populate del paquete microsoft-opentelemetry. Este asistente extrae automáticamente los detalles del autor de la llamada, el agente, el inquilino, el canal y la conversación de la actividad.

from microsoft.opentelemetry.a365.core import BaggageBuilder
from microsoft.opentelemetry.a365.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, InvokeAgentScope, ExecuteToolScope } from '@microsoft/opentelemetry';

// 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 rellenar automáticamente el BaggageBuilder desde el TurnContext, use la herramienta fromTurnContext del paquete @microsoft/opentelemetry. Este asistente extrae automáticamente los detalles del autor de la llamada, el agente, el inquilino, el canal y la conversación de la actividad.

import { BaggageBuilder, BaggageBuilderUtils } from '@microsoft/opentelemetry';

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

baggageScope.run(() => {
  // 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 rellenar automáticamente el BaggageBuilder desde el ITurnContext, use el método de extensión FromTurnContext en el paquete de Microsoft.Agents.A365.Observability.Hosting. Este método extrae automáticamente los detalles del autor de la llamada, el agente, el inquilino, el canal y la conversación de la actividad.

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

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

En Python, registre el middleware de bagaje a través de ObservabilityHostingManager.configure() en lugar de hacerlo directamente en el adaptador.

from microsoft.opentelemetry.a365.hosting import ObservabilityHostingManager, ObservabilityHostingOptions

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

El middleware omite la configuración de la información de contexto para las respuestas asincrónicas (eventos ContinueConversation) para evitar sobrescribir la información de contexto que la solicitud de origen ya ha establecido.

Regístrese BaggageMiddleware en el adaptador. Extrae automáticamente los detalles de llamada, agente, arrendatario, canal y conversación de cada entrada TurnContext y ajusta la solicitud en un contexto de equipaje.

import { BaggageMiddleware } from '@microsoft/opentelemetry';

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

Como alternativa, use ObservabilityHostingManager para configurar el middleware de contexto junto con otras características de hospedaje.

import { ObservabilityHostingManager } from '@microsoft/opentelemetry';

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

El middleware omite la configuración de la información de contexto para las respuestas asincrónicas (eventos ContinueConversation) para evitar sobrescribir la información de contexto que la solicitud de origen ya ha establecido.

Regístrese BaggageTurnMiddleware en el adaptador. Extrae automáticamente los detalles de llamada, agente, arrendatario, canal y conversación de cada entrada ITurnContext y ajusta la solicitud en un contexto de equipaje.

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

adapter.Use(new BaggageTurnMiddleware());

El middleware omite la configuración de la información de contexto para las respuestas asincrónicas (eventos ContinueConversation) para evitar sobrescribir la información de contexto que la solicitud de origen ya ha establecido.

Si necesita información de contexto a nivel HTTP (por ejemplo, para establecer los identificadores de entidad y agente antes de que se ejecute la canalización de Bot Framework), registre ObservabilityBaggageMiddleware en la canalización de ASP.NET Core mediante el método de extensión UseObservabilityRequestContext. Debe proporcionar una función de resolución que extraiga el identificador de inquilino y el identificador del agente del 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);
});

from microsoft.opentelemetry import use_microsoft_opentelemetry

def token_resolver(agent_id, tenant_id):
    return "your-token"

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=token_resolver,
    instrumentation_options={
        "semantic_kernel": {"enabled": True},
    },
)

El Kernel semántico no admite la instrumentación automática para Node.js.

La instrumentación del Kernel semántico está habilitada por defecto. Para deshabilitarlo, establezca la opción de instrumentación explícitamente.

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Instrumentation.EnableSemanticKernelInstrumentation = false;
});

from microsoft.opentelemetry import use_microsoft_opentelemetry

def token_resolver(agent_id, tenant_id):
    return "your-token"

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=token_resolver,
    instrumentation_options={
        "openai_agents": {"enabled": True},
    },
)

import { useMicrosoftOpenTelemetry } from "@microsoft/opentelemetry";

const tokenResolver = (agentId, tenantId) => {
  return "your-token";
};

useMicrosoftOpenTelemetry({
  a365: {
    enabled: true,
    tokenResolver,
  },
  instrumentationOptions: {
    openaiAgents: { enabled: true },
  },
});

OpenAI y la instrumentación de Azure OpenAI están habilitadas de forma predeterminada. Para deshabilitarlo, establezca la opción de instrumentación explícitamente.

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Instrumentation.EnableOpenAIInstrumentation = false;
});

from microsoft.opentelemetry import use_microsoft_opentelemetry

def token_resolver(agent_id, tenant_id):
    return "your-token"

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=token_resolver,
    instrumentation_options={
        "agent_framework": {"enabled": True},
    },
)

La instrumentación automática de Agent Framework no se admite para Node.js.

La instrumentación de Agent Framework está habilitada de forma predeterminada. Para deshabilitarlo, establezca la opción de instrumentación explícitamente.

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Instrumentation.EnableAgentFrameworkInstrumentation = false;
});

from microsoft.opentelemetry import use_microsoft_opentelemetry

def token_resolver(agent_id, tenant_id):
    return "your-token"

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=token_resolver,
    instrumentation_options={
        "langchain": {"enabled": True},
    },
)

import { useMicrosoftOpenTelemetry } from "@microsoft/opentelemetry";

const tokenResolver = (agentId, tenantId) => {
  return "your-token";
};

useMicrosoftOpenTelemetry({
  a365: {
    enabled: true,
    tokenResolver,
  },
  instrumentationOptions: {
    langchain: { enabled: true },
  },
});

La instrumentación automática de LangChain no aparece para .NET.

from microsoft.opentelemetry.a365.core import (
    AgentDetails,
    Channel,
    InvokeAgentScope,
    InvokeAgentScopeDetails,
    Request,
    ServiceEndpoint,
)

agent_details = AgentDetails(
    agent_id="agent-456",
    agent_name="Email Assistant",
    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",
)

request = Request(
    content="Please help me organize my emails",
    session_id="session-42",
    conversation_id="conv-xyz",
    channel=Channel(name="msteams"),
)

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

with InvokeAgentScope.start(
    request=request,
    scope_details=scope_details,
    agent_details=agent_details,
) as scope:
    scope.record_input_messages(["Please help me organize my emails"])

    # Run the agent invocation.

    invoke_scope.record_output_messages(["I found 15 urgent emails."])

import { InvokeAgentScope } from "@microsoft/opentelemetry";
import type {
  AgentDetails,
  A365Request,
  InvokeAgentScopeDetails,
} from "@microsoft/opentelemetry";

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 request: A365Request = {
  content: "Please help me organize my emails",
  sessionId: "session-42",
  conversationId: "conv-xyz",
  channel: { name: "msteams" },
};

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

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

try {
  await invokeScope.withActiveSpanAsync(async () => {
    invokeScope.recordInputMessages(["Please help me organize my emails"]);

    // Run the agent invocation.

    invokeScope.recordOutputMessages(["I found 15 urgent emails."]);
  });
} catch (error) {
  invokeScope.recordError(error as Error);
  throw error;
} finally {
  invokeScope.dispose();
}

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

var agentDetails = new AgentDetails(
    agentId: "agent-456",
    agentName: "Email Assistant",
    agentDescription: "An AI agent powered by Azure OpenAI",
    agenticUserId: "auid-123",
    agenticUserEmail: "agent@contoso.com",
    agentBlueprintId: "blueprint-789",
    tenantId: "tenant-123");

var request = new Request(
    content: "Please help me organize my emails",
    sessionId: "session-42",
    conversationId: "conv-xyz",
    channel: new Channel(name: "msteams"));

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

using var invokeScope = InvokeAgentScope.Start(
    request: request,
    scopeDetails: scopeDetails,
    agentDetails: agentDetails);

invokeScope.RecordInputMessages(new[] { "Please help me organize my emails" });

// Run the agent invocation.

invokeScope.RecordOutputMessages(new[] { "I found 15 urgent emails." });

from microsoft.opentelemetry.a365.core import (
    ExecuteToolScope,
    ServiceEndpoint,
    ToolCallDetails,
    ToolType,
)

tool_details = ToolCallDetails(
    tool_name="email-search",
    arguments={"query": "from:manager@contoso.com"},
    tool_call_id="tool-call-456",
    description="Search emails by criteria",
    tool_type=ToolType.FUNCTION.value,
    endpoint=ServiceEndpoint(
        hostname="tools.contoso.com",
        port=8080,
        protocol="https",
    ),
)

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

import { ExecuteToolScope } from "@microsoft/opentelemetry";
import type { ToolCallDetails } from "@microsoft/opentelemetry";

const toolDetails: ToolCallDetails = {
  toolName: "email-search",
  arguments: JSON.stringify({ query: "from:manager@contoso.com" }),
  toolCallId: "tool-call-456",
  description: "Search emails by criteria",
  toolType: "function",
  endpoint: {
    host: "tools.contoso.com",
    port: 8080,
    protocol: "https",
  },
};

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

try {
  await invokeScope.withActiveSpanAsync(async () => {
    const result = await searchEmails(toolDetails.arguments);
    scope.recordResponse(JSON.stringify(result));
  });
} catch (error) {
  scope.recordError(error as Error);
  throw error;
} finally {
  scope.dispose();
}

var toolDetails = new ToolCallDetails(
    toolName: "email-search",
    arguments: "{\"query\": \"from:manager@contoso.com\"}",
    toolCallId: "tool-call-456",
    description: "Search emails by criteria",
    toolType: "function",
    endpoint: new Uri("https://tools.contoso.com:8080"));

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

// Execute the tool.

scope.RecordResponse("{\"count\": 15}");

from microsoft.opentelemetry.a365.core import (
    InferenceCallDetails,
    InferenceOperationType,
    InferenceScope,
)

inference_details = InferenceCallDetails(
    operationName=InferenceOperationType.CHAT,
    model="gpt-4o-mini",
    providerName="azure-openai",
)

with InferenceScope.start(
    request=request,
    details=inference_details,
    agent_details=agent_details,
) as scope:
    scope.record_input_messages(["Summarize the following emails for me."])
    response = call_llm()
    scope.record_output_messages([response.text])
    scope.record_input_tokens(response.usage.input_tokens)
    scope.record_output_tokens(response.usage.output_tokens)
    scope.record_finish_reasons(["stop"])

import { InferenceOperationType, InferenceScope } from "@microsoft/opentelemetry";
import type { InferenceDetails } from "@microsoft/opentelemetry";

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

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

try {
  await invokeScope.withActiveSpanAsync(async () => {
    scope.recordInputMessages(["Summarize the following emails for me."]);
    const response = await callLLM();
    scope.recordOutputMessages([response.text]);
    scope.recordInputTokens(response.usage.inputTokens);
    scope.recordOutputTokens(response.usage.outputTokens);
    scope.recordFinishReasons(["stop"]);
  });
} catch (error) {
  scope.recordError(error as Error);
  throw error;
} finally {
  scope.dispose();
}

var inferenceDetails = new InferenceCallDetails(
    operationName: InferenceOperationType.Chat,
    model: "gpt-4o-mini",
    providerName: "Azure OpenAI");

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

scope.RecordInputMessages(new[] { "Summarize the following emails for me." });

// Call the model.

scope.RecordOutputMessages(new[] { "Here is your email summary." });
scope.RecordInputTokens(145);
scope.RecordOutputTokens(82);
scope.RecordFinishReasons(new[] { "stop" });

from microsoft.opentelemetry.a365.core import OutputScope, Response, SpanDetails

# Capture this before exiting the originating InvokeAgentScope context.
parent_context = invoke_scope.get_span_context()
response = Response(
    messages=["Here is your organized inbox."],
)

with OutputScope.start(
    request=request,
    response=response,
    agent_details=agent_details,
    user_details=None,
    span_details=SpanDetails(parent_context=parent_context),
) as scope:
    pass

import { OutputScope } from "@microsoft/opentelemetry";
import type { A365SpanDetails, OutputResponse } from "@microsoft/opentelemetry";

// Capture this before disposing the originating InvokeAgentScope.
const parentContext = invokeScope.getSpanContext();
const response: OutputResponse = {
  messages: ["Here is your organized inbox."],
};

const scope = OutputScope.start(
  request,
  response,
  agentDetails,
  undefined,
  { parentContext } as A365SpanDetails
);

scope.dispose();

// Capture this before disposing the originating InvokeAgentScope.
var parentContext = invokeScope.GetActivityContext();
var response = new Response(new[] { "Here is your organized inbox." });

using var scope = OutputScope.Start(
    request: request,
    response: response,
    agentDetails: agentDetails,
    spanDetails: new SpanDetails(parentContext: parentContext));

export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

from microsoft.opentelemetry import use_microsoft_opentelemetry

use_microsoft_opentelemetry()

export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

import { useMicrosoftOpenTelemetry } from "@microsoft/opentelemetry";

useMicrosoftOpenTelemetry();

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Exporters = ExportTarget.Otlp;
    o.OtlpEndpoint = new Uri("http://localhost:4317");
});

export ENABLE_A365_OBSERVABILITY_EXPORTER=false

from microsoft.opentelemetry import use_microsoft_opentelemetry

def token_resolver(agent_id, tenant_id):
    return "local-validation-token"

use_microsoft_opentelemetry(
    enable_a365=True,
    a365_token_resolver=token_resolver,
)

# Run instrumented application code.

export ENABLE_A365_OBSERVABILITY_EXPORTER=false

import {
  useMicrosoftOpenTelemetry,
  shutdownMicrosoftOpenTelemetry,
} from "@microsoft/opentelemetry";

const tokenResolver = (agentId, tenantId) => {
  return "local-validation-token";
};

useMicrosoftOpenTelemetry({
  a365: {
    enabled: true,
    tokenResolver,
  },
});

// Run instrumented application code.

await shutdownMicrosoftOpenTelemetry();

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Exporters = ExportTarget.Console;
});

El solucionador debe ser sincrónico. Adquiere el token en tu controlador de actividad asincrónica y guárdalo para el resolver.

from microsoft.opentelemetry import use_microsoft_opentelemetry
from microsoft.opentelemetry.a365.runtime import get_observability_authentication_scope

_cached_token: str | None = None

def my_token_resolver(agent_id: str, tenant_id: str) -> str | None:
    return _cached_token

use_microsoft_opentelemetry(enable_a365=True, a365_token_resolver=my_token_resolver)

@AGENT_APP.activity("message", auth_handlers=["AGENTIC"])
async def on_message(context: TurnContext, _state: TurnState):
    global _cached_token
    _cached_token = await AGENT_APP.auth.exchange_token(
        context,
        scopes=get_observability_authentication_scope(),
        auth_handler_id="AGENTIC",
    )

import { useMicrosoftOpenTelemetry } from "@microsoft/opentelemetry";
import { TurnState, AgentApplication, TurnContext, MemoryStorage } from '@microsoft/agents-hosting';
import { ActivityTypes } from '@microsoft/agents-activity';

useMicrosoftOpenTelemetry({
  a365: {
    enabled: true,
    tokenResolver: (agentId: string, tenantId: string, authScopes?: string[]) =>
      myTokenService.getToken(agentId, tenantId),
  },
});


export class A365Agent extends AgentApplication<TurnState> {
  isApplicationInstalled: boolean = true;
  termsAndConditionsAccepted: boolean = true;
  agentName = 'A365 Agent';
  authHandlerName = 'agentic';
 
  constructor() {
    const useAgenticAuth = process.env.USE_AGENTIC_AUTH === 'true';

    super({
      storage: new MemoryStorage(),
      ...(useAgenticAuth && {
        authorization: {
          agentic: {
            type: 'agentic',
          }
        }
      })
    });

    this.onActivity(ActivityTypes.Message, async (context: TurnContext, state: TurnState) => {
      await this.handleAgentMessageActivity(context, state);
    });
  }

  async handleAgentMessageActivity(turnContext: TurnContext, _state: TurnState): Promise<void> {
    if (process.env.USE_AGENTIC_AUTH !== 'true') {
      console.log('[A365Agent] Authorization not configured, skipping observability token preload');
      return;
    }

    const agentId = turnContext?.activity?.recipient?.agenticAppId ?? '';
    const tenantId = turnContext?.activity?.recipient?.tenantId ?? '';

    // Acquire auth token via OBO exchange
    const authToken = await this.authorization.exchangeToken(turnContext, 'agentic', {
      scopes: ['api://9b975845-388f-4429-889e-eab1ef63949c/Agent365.Observability.OtelWrite']
    });

    // Cache the token so it can be returned by the token resolver
    myTokenService.set(agentId, tenantId, authToken?.token || '');
  }
}

using Microsoft.OpenTelemetry;

builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Exporters = ExportTarget.Agent365;
    o.Agent365.Exporter.TokenResolver = async (agentId, tenantId) =>
    {
        return await MyTokenService.GetTokenAsync(agentId, tenantId);
    };
});

Cuando se establece TokenResolver explícitamente, la caché de tokens de inserción automática no está registrada; en su lugar, se usa la resolución.

from microsoft.opentelemetry import use_microsoft_opentelemetry
from microsoft.opentelemetry.a365.hosting.token_cache_helpers import AgenticTokenCache, AgenticTokenStruct
from microsoft.opentelemetry.a365.runtime import get_observability_authentication_scope

token_cache = AgenticTokenCache()

_cached_tokens: dict[tuple[str, str], str | None] = {}

# Keep the sync resolver side-effect free; refresh the cache in the async request handler.
def sync_token_resolver(agent_id: str, tenant_id: str) -> str | None:
    return _cached_tokens.get((agent_id, tenant_id))

use_microsoft_opentelemetry(enable_a365=True, a365_token_resolver=sync_token_resolver)

@AGENT_APP.activity("message", auth_handlers=["AGENTIC"])
async def on_message(context: TurnContext, _state: TurnState):
    agent_id = context.activity.recipient.id
    tenant_id = context.activity.recipient.tenant_id
    token_cache.register_observability(
        agent_id=agent_id,
        tenant_id=tenant_id,
        token_generator=AgenticTokenStruct(
            authorization=AGENT_APP.auth,
            turn_context=context,
        ),
        observability_scopes=get_observability_authentication_scope(),
    )
    _cached_tokens[(agent_id, tenant_id)] = await token_cache.get_observability_token(
        agent_id, tenant_id,
    )

Use configureA365Hosting para registrar el middleware A365 en el adaptador. Este middleware controla el equipaje y la fontanería de tokens automáticamente.

import { configureA365Hosting } from "@microsoft/opentelemetry";

configureA365Hosting(adapter, {
  enableBaggage: true,
  enableOutputLogging: false,
});

Establezca enableOutputLogging: false si el contenido de la respuesta no se debe capturar como atributos de elemento span.

// Program.cs — no TokenResolver needed
builder.UseMicrosoftOpenTelemetry(o =>
{
    o.Exporters = ExportTarget.Agent365;
    // IExporterTokenCache<AgenticTokenStruct> is auto-registered via DI
});

En la clase del agente, llame a RegisterObservability() en cada turno:

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

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

    public MyAgent(AgentApplicationOptions options,
        IExporterTokenCache<AgenticTokenStruct> agentTokenCache) : base(options)
    {
        _agentTokenCache = agentTokenCache;
    }

    protected async Task MessageActivityAsync(
        ITurnContext turnContext, ITurnState turnState, CancellationToken cancellationToken)
    {
        _agentTokenCache.RegisterObservability(
            turnContext.Activity.Recipient.AgenticAppId,
            turnContext.Activity.Recipient.TenantId,
            new AgenticTokenStruct(
                userAuthorization: UserAuthorization,
                turnContext: turnContext,
                authHandlerName: "AGENTIC"),
            EnvironmentUtils.GetObservabilityAuthenticationScope());
    }
}