Azure AI Hosted Agents (Python)

Build container-based hosted agents using ImageBasedHostedAgentDefinition from the Azure AI Projects SDK.

Installation

pip install azure-ai-projects>=2.0.0b3 azure-identity

Minimum SDK Version: 2.0.0b3 or later required for hosted agent support.

Environment Variables

AZURE_AI_PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project>

Prerequisites

Before creating hosted agents:

Container Image - Build and push to Azure Container Registry (ACR)
ACR Pull Permissions - Grant your project's managed identity AcrPull role on the ACR
Capability Host - Account-level capability host with enablePublicHostingEnvironment=true
SDK Version - Ensure azure-ai-projects>=2.0.0b3

Authentication

Always use DefaultAzureCredential :

from azure.identity import DefaultAzureCredential from azure.ai.projects import AIProjectClient

credential = DefaultAzureCredential() client = AIProjectClient( endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential )

Core Workflow

Imports

import os from azure.identity import DefaultAzureCredential from azure.ai.projects import AIProjectClient from azure.ai.projects.models import ( ImageBasedHostedAgentDefinition, ProtocolVersionRecord, AgentProtocol, )

Create Hosted Agent

client = AIProjectClient( endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=DefaultAzureCredential() )

agent = client.agents.create_version( agent_name="my-hosted-agent", definition=ImageBasedHostedAgentDefinition( container_protocol_versions=[ ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1") ], cpu="1", memory="2Gi", image="myregistry.azurecr.io/my-agent:latest", tools=[{"type": "code_interpreter"}], environment_variables={ "AZURE_AI_PROJECT_ENDPOINT": os.environ["AZURE_AI_PROJECT_ENDPOINT"], "MODEL_NAME": "gpt-4o-mini" } ) )

print(f"Created agent: {agent.name} (version: {agent.version})")

List Agent Versions

versions = client.agents.list_versions(agent_name="my-hosted-agent") for version in versions: print(f"Version: {version.version}, State: {version.state}")

Delete Agent Version

client.agents.delete_version( agent_name="my-hosted-agent", version=agent.version )

ImageBasedHostedAgentDefinition Parameters

Parameter Type Required Description

container_protocol_versions

list[ProtocolVersionRecord]

Yes Protocol versions the agent supports

image

str

Yes Full container image path (registry/image:tag)

cpu

str

No CPU allocation (e.g., "1", "2")

memory

str

No Memory allocation (e.g., "2Gi", "4Gi")

tools

list[dict]

No Tools available to the agent

environment_variables

dict[str, str]

No Environment variables for the container

Protocol Versions

The container_protocol_versions parameter specifies which protocols your agent supports:

from azure.ai.projects.models import ProtocolVersionRecord, AgentProtocol

RESPONSES protocol - standard agent responses

container_protocol_versions=[ ProtocolVersionRecord(protocol=AgentProtocol.RESPONSES, version="v1") ]

Available Protocols:

Protocol Description

AgentProtocol.RESPONSES

Standard response protocol for agent interactions

Resource Allocation

Specify CPU and memory for your container:

definition=ImageBasedHostedAgentDefinition( container_protocol_versions=[...], image="myregistry.azurecr.io/my-agent:latest", cpu="2", # 2 CPU cores memory="4Gi" # 4 GiB memory )

Resource Limits:

Resource Min Max Default

CPU 0.5 4 1

Memory 1Gi 8Gi 2Gi

Tools Configuration

Add tools to your hosted agent:

Code Interpreter

tools=[{"type": "code_interpreter"}]

MCP Tools

tools=[ {"type": "code_interpreter"}, { "type": "mcp", "server_label": "my-mcp-server", "server_url": "https://my-mcp-server.example.com" } ]

Multiple Tools

tools=[ {"type": "code_interpreter"}, {"type": "file_search"}, { "type": "mcp", "server_label": "custom-tool", "server_url": "https://custom-tool.example.com" } ]

Environment Variables

Pass configuration to your container:

environment_variables={ "AZURE_AI_PROJECT_ENDPOINT": os.environ["AZURE_AI_PROJECT_ENDPOINT"], "MODEL_NAME": "gpt-4o-mini", "LOG_LEVEL": "INFO", "CUSTOM_CONFIG": "value" }

Best Practice: Never hardcode secrets. Use environment variables or Azure Key Vault.

Complete Example

def create_hosted_agent(): """Create a hosted agent with custom container image."""

client = AIProjectClient(
    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
    credential=DefaultAzureCredential()
)

agent = client.agents.create_version(
    agent_name="data-processor-agent",
    definition=ImageBasedHostedAgentDefinition(
        container_protocol_versions=[
            ProtocolVersionRecord(
                protocol=AgentProtocol.RESPONSES,
                version="v1"
            )
        ],
        image="myregistry.azurecr.io/data-processor:v1.0",
        cpu="2",
        memory="4Gi",
        tools=[
            {"type": "code_interpreter"},
            {"type": "file_search"}
        ],
        environment_variables={
            "AZURE_AI_PROJECT_ENDPOINT": os.environ["AZURE_AI_PROJECT_ENDPOINT"],
            "MODEL_NAME": "gpt-4o-mini",
            "MAX_RETRIES": "3"
        }
    )
)

print(f"Created hosted agent: {agent.name}")
print(f"Version: {agent.version}")
print(f"State: {agent.state}")

return agent

if name == "main": create_hosted_agent()

Async Pattern

import os from azure.identity.aio import DefaultAzureCredential from azure.ai.projects.aio import AIProjectClient from azure.ai.projects.models import ( ImageBasedHostedAgentDefinition, ProtocolVersionRecord, AgentProtocol, )

async def create_hosted_agent_async(): """Create a hosted agent asynchronously."""

async with DefaultAzureCredential() as credential:
    async with AIProjectClient(
        endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
        credential=credential
    ) as client:
        agent = await client.agents.create_version(
            agent_name="async-agent",
            definition=ImageBasedHostedAgentDefinition(
                container_protocol_versions=[
                    ProtocolVersionRecord(
                        protocol=AgentProtocol.RESPONSES,
                        version="v1"
                    )
                ],
                image="myregistry.azurecr.io/async-agent:latest",
                cpu="1",
                memory="2Gi"
            )
        )
        return agent

Common Errors

Error Cause Solution

ImagePullBackOff

ACR pull permission denied Grant AcrPull role to project's managed identity

InvalidContainerImage

Image not found Verify image path and tag exist in ACR

CapabilityHostNotFound

No capability host configured Create account-level capability host

ProtocolVersionNotSupported

Invalid protocol version Use AgentProtocol.RESPONSES with version "v1"

Best Practices

Version Your Images - Use specific tags, not latest in production
Minimal Resources - Start with minimum CPU/memory, scale up as needed
Environment Variables - Use for all configuration, never hardcode
Error Handling - Wrap agent creation in try/except blocks
Cleanup - Delete unused agent versions to free resources

Reference Links

Azure AI Projects SDK
Hosted Agents Documentation
Azure Container Registry

hosted-agents-v2-py

Safety Notice

Copy this and send it to your AI assistant to learn

RESPONSES protocol - standard agent responses

Source Transparency

Related Skills

github-issue-creator

azure-observability

azure-appconfiguration-java

azure-aigateway