agent-framework-azure-ai-py

Topics in the source

• Agent Framework Azure Hosted Agents
• Architecture
• Installation
• Environment Variables
• Authentication & Lifecycle
• Core Workflow
• Basic Agent
• Agent with Function Tools

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK. 🔑 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 AZURETOKENCREDENTIALS=prod (or AZURETOKENCREDENTIALS= ) 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 (...) as client: - Async: async with (...) 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. | Method | Description | |--------|-------------| | createagent() | Create new agent on Azure AI service | | getagent(agentid) | Retrieve existing agent by ID | | asagent(sdkagent) | Wrap SDK Agent object (no HTTP call) | | Tool | Import | Purpose | |------|--------|----

This is an excerpt. Refer to the complete source and its current requirements.