Python: Add Durable Agent Wrapper code (#1913)

* add initial changes

* Move code and add single sample

* Update logger

* Remove unused code

* address PR comments

* cleanup code and address comments

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>

python/samples/getting_started/azure_functions/01_single_agent/README.md

@@ -0,0 +1,49 @@
+# Single Agent Sample (Python)
+
+This sample demonstrates how to use the Durable Extension for Agent Framework to create a simple Azure Functions app that hosts a single AI agent and provides direct HTTP API access for interactive conversations.
+
+## Key Concepts Demonstrated
+
+- Defining a simple agent with the Microsoft Agent Framework and wiring it into
+  an Azure Functions app via the Durable Extension for Agent Framework.
+- Calling the agent through generated HTTP endpoints (`/api/agents/Joker/run`).
+- Managing conversation state with session identifiers, so multiple clients can
+  interact with the agent concurrently without sharing context.
+
+## Environment Setup
+
+### 1. Create and activate a virtual environment
+
+**Windows (PowerShell):**
+```powershell
+python -m venv .venv
+.venv\Scripts\Activate.ps1
+```
+
+**Linux/macOS:**
+```bash
+python -m venv .venv
+source .venv/bin/activate
+```
+
+### 2. Install dependencies
+
+- Azure Functions Core Tools 4.x – install from the official docs so you can run `func start` locally.
+- Azurite storage emulator – the sample uses `AzureWebJobsStorage=UseDevelopmentStorage=true`; start Azurite before launching the app.
+- Durable Task local backend – `DURABLE_TASK_SCHEDULER_CONNECTION_STRING` expects the Durable Task scheduler listening on `http://localhost:8080` (start the Durable Functions emulator if it is not already running).
+- Python dependencies – from this folder, run `pip install -r requirements.txt` (or the equivalent in your active virtual environment).
+- Environment variables – update `AZURE_OPENAI_ENDPOINT` and `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME` in `local.settings.json` with your Azure OpenAI resource details; keep the other values as provided unless you are using custom infrastructure.
+
+## Running the Sample
+
+With the environment configured and the Functions host running, you can interact
+with the Joker agent using the provided `demo.http` file or any HTTP client. For
+example:
+
+```bash
+curl -X POST http://localhost:7071/api/agents/Joker/run \
+     -H "Content-Type: text/plain" \
+     -d "Tell me a short joke about cloud computing."
+```
+
+The agent responds with a JSON payload that includes the generated joke.

python/samples/getting_started/azure_functions/01_single_agent/demo.http

@@ -0,0 +1,26 @@
+### Joker Agent Sample Interactions
+@baseUrl = http://localhost:7071
+@agentName = Joker
+@agentRoute = {{baseUrl}}/api/agents/{{agentName}}
+@healthRoute = {{baseUrl}}/api/health
+
+### Health Check
+GET {{healthRoute}}
+
+### Ask for a joke (JSON payload)
+POST {{agentRoute}}/run
+Content-Type: application/json
+
+{
+  "message": "Add a security element to it.",
+  "sessionId": "session-003",
+  "waitForCompletion": true
+}
+
+### Ask for a joke (plain text payload)
+POST {{agentRoute}}/run
+
+Give me a programming joke about race conditions.
+
+### Retrieve conversation state
+GET {{agentRoute}}/session-001

python/samples/getting_started/azure_functions/01_single_agent/function_app.py

@@ -0,0 +1,61 @@
+"""Azure Functions single-agent sample showcasing how to host a single Azure OpenAI agent.
+
+The sample reads the required endpoint and deployment environment variables, configures the Azure OpenAI chat client (using either an API key or Azure CLI credentials), and registers a joke-telling agent with an Azure Functions app that can optionally expose a health check.
+
+Summary: Demonstrates configuring and deploying a single 'Joker' agent via Azure Functions."""
+
+import logging
+import os
+from typing import Any
+
+from azure.identity import AzureCliCredential
+from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azurefunctions import AgentFunctionApp
+
+
+logger = logging.getLogger(__name__)
+
+
+AZURE_OPENAI_ENDPOINT_ENV = "AZURE_OPENAI_ENDPOINT"
+AZURE_OPENAI_DEPLOYMENT_ENV = "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"
+AZURE_OPENAI_API_KEY_ENV = "AZURE_OPENAI_API_KEY"
+
+
+def _build_client_kwargs() -> dict[str, Any]:
+    """Construct Azure OpenAI client options."""
+
+    endpoint = os.getenv(AZURE_OPENAI_ENDPOINT_ENV)
+    if not endpoint:
+        raise RuntimeError(f"{AZURE_OPENAI_ENDPOINT_ENV} environment variable is required.")
+
+    deployment = os.getenv(AZURE_OPENAI_DEPLOYMENT_ENV)
+    if not deployment:
+        raise RuntimeError(f"{AZURE_OPENAI_DEPLOYMENT_ENV} environment variable is required.")
+
+    logger.info("[SingleAgent] Using deployment '%s' at '%s'", deployment, endpoint)
+
+    client_kwargs: dict[str, Any] = {
+        "endpoint": endpoint,
+        "deployment_name": deployment,
+    }
+
+    api_key = os.getenv(AZURE_OPENAI_API_KEY_ENV)
+    if api_key:
+        client_kwargs["api_key"] = api_key
+    else:
+        client_kwargs["credential"] = AzureCliCredential()
+
+    return client_kwargs
+
+
+def _create_agent() -> Any:
+    """Create the Joker agent."""
+
+    client_kwargs = _build_client_kwargs()
+    return AzureOpenAIChatClient(**client_kwargs).create_agent(
+        name="Joker",
+        instructions="You are good at telling jokes.",
+    )
+
+
+app = AgentFunctionApp(agents=[_create_agent()], enable_health_check=True)

python/samples/getting_started/azure_functions/01_single_agent/host.json

@@ -0,0 +1,7 @@
+{
+  "version": "2.0",
+  "extensionBundle": {
+    "id": "Microsoft.Azure.Functions.ExtensionBundle",
+    "version": "[4.*, 5.0.0)"
+  }
+}

python/samples/getting_started/azure_functions/01_single_agent/local.settings.json

@@ -0,0 +1,10 @@
+{
+  "IsEncrypted": false,
+  "Values": {
+    "FUNCTIONS_WORKER_RUNTIME": "python",
+    "AzureWebJobsStorage": "UseDevelopmentStorage=true",
+    "DURABLE_TASK_SCHEDULER_CONNECTION_STRING": "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None",
+    "AZURE_OPENAI_ENDPOINT": "<AZURE_OPENAI_ENDPOINT>",
+    "AZURE_OPENAI_CHAT_DEPLOYMENT_NAME": "<AZURE_OPENAI_CHAT_DEPLOYMENT_NAME>"
+  }
+}

python/samples/getting_started/azure_functions/01_single_agent/requirements.txt

@@ -0,0 +1,2 @@
+agent-framework-azurefunctions
+azure-identity