azure-servicebus-py

Messagerie d'entreprise pour une communication cloud fiable avec files d'attente et sujets pub/sub.

npx skills add https://github.com/microsoft/agent-skills --skill azure-servicebus-py

Azure Service Bus SDK for Python

Enterprise messaging for reliable cloud communication with queues and pub/sub topics.

Installation

pip install azure-servicebus azure-identity

Environment Variables

SERVICEBUS_FULLY_QUALIFIED_NAMESPACE=<namespace>.servicebus.windows.net  # Required for all auth methods
SERVICEBUS_QUEUE_NAME=myqueue  # Required for queue operations
SERVICEBUS_TOPIC_NAME=mytopic  # Required for topic operations
SERVICEBUS_SUBSCRIPTION_NAME=mysubscription  # Required for subscription operations
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production

Authentication & Lifecycle

🔑 Two rules apply to every code sample below:

  1. Prefer DefaultAzureCredential. It works locally (Azure CLI / VS Code / Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account/API keys — they bypass Entra audit and rotation.
    • Local dev: DefaultAzureCredential works as-is.
    • Production: set AZURE_TOKEN_CREDENTIALS=prod (or AZURE_TOKEN_CREDENTIALS=<specific_credential>) to constrain the credential chain to production-safe credentials.
  2. Wrap every client in a context manager so HTTP transports, sockets, and token caches are released deterministically:
    • Sync: with <Client>(...) as client:
    • Async: async with <Client>(...) as client: and async with DefaultAzureCredential() as credential: (from azure.identity.aio)

Snippets may abbreviate this setup, but production code should always follow both rules.

from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.servicebus import ServiceBusClient

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
namespace = "<namespace>.servicebus.windows.net"

with ServiceBusClient(
    fully_qualified_namespace=namespace,
    credential=credential
) as client:
    # Use client here (see following sections for operations)
    ...

Client Types

ClientPurposeGet From
ServiceBusClientConnection managementDirect instantiation
ServiceBusSenderSend messagesclient.get_queue_sender() / get_topic_sender()
ServiceBusReceiverReceive messagesclient.get_queue_receiver() / get_subscription_receiver()

Send Messages (Async)

import asyncio
from azure.servicebus.aio import ServiceBusClient
from azure.servicebus import ServiceBusMessage
from azure.identity.aio import DefaultAzureCredential

async def send_messages():
    credential = DefaultAzureCredential()
    
    async with ServiceBusClient(
        fully_qualified_namespace="<namespace>.servicebus.windows.net",
        credential=credential
    ) as client:
        sender = client.get_queue_sender(queue_name="myqueue")
        
        async with sender:
            # Single message
            message = ServiceBusMessage("Hello, Service Bus!")
            await sender.send_messages(message)
            
            # Batch of messages
            messages = [ServiceBusMessage(f"Message {i}") for i in range(10)]
            await sender.send_messages(messages)
            
            # Message batch (for size control)
            batch = await sender.create_message_batch()
            for i in range(100):
                try:
                    batch.add_message(ServiceBusMessage(f"Batch message {i}"))
                except ValueError:  # Batch full
                    await sender.send_messages(batch)
                    batch = await sender.create_message_batch()
                    batch.add_message(ServiceBusMessage(f"Batch message {i}"))
            await sender.send_messages(batch)

asyncio.run(send_messages())

Receive Messages (Async)

async def receive_messages():
    credential = DefaultAzureCredential()
    
    async with ServiceBusClient(
        fully_qualified_namespace="<namespace>.servicebus.windows.net",
        credential=credential
    ) as client:
        receiver = client.get_queue_receiver(queue_name="myqueue")
        
        async with receiver:
            # Receive batch
            messages = await receiver.receive_messages(
                max_message_count=10,
                max_wait_time=5  # seconds
            )
            
            for msg in messages:
                print(f"Received: {str(msg)}")
                await receiver.complete_message(msg)  # Remove from queue

asyncio.run(receive_messages())

Receive Modes

ModeBehaviorUse Case
PEEK_LOCK (default)Message locked, must complete/abandonReliable processing
RECEIVE_AND_DELETERemoved immediately on receiveAt-most-once delivery
from azure.servicebus import ServiceBusReceiveMode

receiver = client.get_queue_receiver(
    queue_name="myqueue",
    receive_mode=ServiceBusReceiveMode.RECEIVE_AND_DELETE
)

Message Settlement

async with receiver:
    messages = await receiver.receive_messages(max_message_count=1)
    
    for msg in messages:
        try:
            # Process message...
            await receiver.complete_message(msg)  # Success - remove from queue
        except ProcessingError:
            await receiver.abandon_message(msg)  # Retry later
        except PermanentError:
            await receiver.dead_letter_message(
                msg,
                reason="ProcessingFailed",
                error_description="Could not process"
            )
ActionEffect
complete_message()Remove from queue (success)
abandon_message()Release lock, retry immediately
dead_letter_message()Move to dead-letter queue
defer_message()Set aside, receive by sequence number

Topics and Subscriptions

# Send to topic
sender = client.get_topic_sender(topic_name="mytopic")
async with sender:
    await sender.send_messages(ServiceBusMessage("Topic message"))

# Receive from subscription
receiver = client.get_subscription_receiver(
    topic_name="mytopic",
    subscription_name="mysubscription"
)
async with receiver:
    messages = await receiver.receive_messages(max_message_count=10)

Sessions (FIFO)

# Send with session
message = ServiceBusMessage("Session message")
message.session_id = "order-123"
await sender.send_messages(message)

# Receive from specific session
receiver = client.get_queue_receiver(
    queue_name="session-queue",
    session_id="order-123"
)

# Receive from next available session
from azure.servicebus import NEXT_AVAILABLE_SESSION
receiver = client.get_queue_receiver(
    queue_name="session-queue",
    session_id=NEXT_AVAILABLE_SESSION
)

Scheduled Messages

from datetime import datetime, timedelta, timezone

message = ServiceBusMessage("Scheduled message")
scheduled_time = datetime.now(timezone.utc) + timedelta(minutes=10)

# Schedule message
sequence_number = await sender.schedule_messages(message, scheduled_time)

# Cancel scheduled message
await sender.cancel_scheduled_messages(sequence_number)

Dead-Letter Queue

from azure.servicebus import ServiceBusSubQueue

# Receive from dead-letter queue
dlq_receiver = client.get_queue_receiver(
    queue_name="myqueue",
    sub_queue=ServiceBusSubQueue.DEAD_LETTER
)

async with dlq_receiver:
    messages = await dlq_receiver.receive_messages(max_message_count=10)
    for msg in messages:
        print(f"Dead-lettered: {msg.dead_letter_reason}")
        await dlq_receiver.complete_message(msg)

Sync Client (for simple scripts)

from azure.servicebus import ServiceBusClient, ServiceBusMessage
from azure.identity import DefaultAzureCredential

with ServiceBusClient(
    fully_qualified_namespace="<namespace>.servicebus.windows.net",
    credential=DefaultAzureCredential()
) as client:
    with client.get_queue_sender("myqueue") as sender:
        sender.send_messages(ServiceBusMessage("Sync message"))
    
    with client.get_queue_receiver("myqueue") as receiver:
        for msg in receiver:
            print(str(msg))
            receiver.complete_message(msg)

Best Practices

  1. Pick sync OR async and stay consistent. Do not mix azure.xxx sync clients with azure.xxx.aio async clients in the same call path. Choose one mode per module.
  2. Always use context managers for clients and async credentials. Wrap every client in with Client(...) as client: (sync) or async with Client(...) as client: (async) for proper cleanup. For async DefaultAzureCredential from azure.identity.aio, also use async with credential: so tokens and transports are cleaned up.
  3. Use DefaultAzureCredential for portable auth across local dev and Azure (avoid connection strings / API keys when possible).
  4. Use async client for production workloads
  5. Complete messages after successful processing
  6. Use dead-letter queue for poison messages
  7. Use sessions for ordered, FIFO processing
  8. Use message batches for high-throughput scenarios
  9. Set max_wait_time to avoid infinite blocking

Reference Files

FileContents
references/patterns.mdCompeting consumers, sessions, retry patterns, request-response, transactions
references/dead-letter.mdDLQ handling, poison messages, reprocessing strategies
scripts/setup_servicebus.pyCLI for queue/topic/subscription management and DLQ monitoring

Plus de skills de microsoft

oss-growth
microsoft
Persona de growth hacker OSS
official
microsoft-foundry
microsoft
Déployer, évaluer et gérer les agents Foundry de bout en bout : build Docker, push ACR, création d’agent hébergé/par prompt, démarrage de conteneur, évaluation par lots, évaluation continue, workflows d’optimisation de prompt, agent.yaml, curation de jeux de données à partir de traces. UTILISER POUR : déployer un agent vers Foundry, agent hébergé, créer un agent, invoquer un agent, évaluer un agent, exécuter une évaluation par lots, évaluation continue, surveillance continue, statut d’évaluation continue, optimiser un prompt, améliorer un prompt, optimiseur de prompt, optimiser les instructions d’un agent, améliorer un agent...
officialdevelopmentdevops
azure-ai
microsoft
Utiliser pour Azure AI : Recherche, Parole, OpenAI, Intelligence documentaire. Aide pour la recherche, la recherche vectorielle/hybride, la reconnaissance vocale, la synthèse vocale, la transcription, l'OCR. QUAND : Recherche AI, recherche par requête, recherche vectorielle, recherche hybride, recherche sémantique, reconnaissance vocale, synthèse vocale, transcrire, OCR, convertir du texte en parole.
officialdevelopmentapi
azure-deploy
microsoft
Exécutez les déploiements Azure pour les applications DÉJÀ PRÉPARÉES disposant de fichiers .azure/deployment-plan.md et d'infrastructure existants. N'utilisez PAS cette compétence lorsque l'utilisateur demande de CRÉER une nouvelle application — utilisez plutôt azure-prepare. Cette compétence exécute les commandes azd up, azd deploy, terraform apply et az deployment avec une récupération d'erreur intégrée. Nécessite .azure/deployment-plan.md de azure-prepare et un état validé de azure-validate. QUAND : "exécuter azd up", "exécuter azd deploy", "exécuter le déploiement",...
officialdevopsaws
azure-storage
microsoft
Services Azure Storage incluant Blob Storage, File Shares, Queue Storage, Table Storage et Data Lake. Répond aux questions sur les niveaux d'accès au stockage (chaud, froid, froid, archive), quand utiliser chaque niveau et comparaison des niveaux. Fournit du stockage d'objets, des partages de fichiers SMB, de la messagerie asynchrone, du NoSQL clé-valeur et de l'analyse de big data. Inclut la gestion du cycle de vie. À UTILISER POUR : stockage blob, partages de fichiers, stockage de files d'attente, stockage de tables, data lake, téléchargement de fichiers, téléchargement de blobs, comptes de stockage, niveaux d'accès,...
officialdevelopmentdatabase
azure-diagnostics
microsoft
Déboguer les problèmes de production Azure à l'aide d'AppLens, Azure Monitor, l'état des ressources et un triage sécurisé. QUAND : déboguer des problèmes de production, résoudre les problèmes d'App Service, CPU élevé d'App Service, échec de déploiement d'App Service, résoudre les problèmes de Container Apps, résoudre les problèmes de Functions, résoudre les problèmes d'AKS, kubectl ne peut pas se connecter, échecs kube-system/CoreDNS, pod en attente, crashloop, nœud non prêt, échecs de mise à niveau, analyser les logs, KQL, insights, échecs de pull d'image, problèmes de démarrage à froid, échecs de sonde de santé,...
officialdevopsdevelopment
azure-prepare
microsoft
Préparer les applications Azure pour le déploiement (infra Bicep/Terraform, azure.yaml, Dockerfiles). Utiliser pour créer/moderniser ou créer+déployer ; pas pour la migration cross-cloud (utiliser azure-cloud-migrate). NE PAS UTILISER POUR : les applications copilot-sdk (utiliser azure-hosted-copilot-sdk). QUAND : "créer une application", "construire une application web", "créer une API", "créer une API HTTP serverless", "créer un frontend", "créer un backend", "construire un service", "moderniser une application", "mettre à jour une application", "ajouter une authentification", "ajouter un cache", "héberger sur Azure", "créer et...
officialdevelopmentdevops
azure-validate
microsoft
Validation pré-déploiement pour la préparation Azure. Effectuez des vérifications approfondies sur la configuration, l'infrastructure (Bicep ou Terraform), les attributions de rôles RBAC, les autorisations d'identité managée et les prérequis avant le déploiement. QUAND : valider mon application, vérifier l'état de préparation au déploiement, exécuter des contrôles préalables, vérifier la configuration, vérifier si prêt à déployer, valider azure.yaml, valider Bicep, tester avant le déploiement, résoudre les erreurs de déploiement, valider Azure Functions, valider l'application de fonction, valider serverless...
officialdevopstesting