Add agent framework sample

samples/microsoft_agent_framework/.env.example

@@ -0,0 +1,4 @@
+FOUNDRY_PROJECT_ENDPOINT= "..."
+FOUNDRY_MODEL="..."
+APPLICATIONINSIGHTS_CONNECTION_STRING="..."
+OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4317

samples/microsoft_agent_framework/README.md

@@ -0,0 +1,63 @@
+# Microsoft Agent Framework Sample
+
+This sample demonstrates how to use [Agent Framework](https://aka.ms/agent-framework) to create a simple agent using Foundry model services and export OpenTelemetry traces using the Microsoft OpenTelemetry SDK to Azure Monitor (Application Insights) or a local OpenTelemetry Collector.
+
+Learn more about the Microsoft Agent Framework in our [GitHub repository](https://github.com/microsoft/agent-framework).
+
+## Prerequisites
+
+- Python 3.10+
+- A [Foundry project](https://learn.microsoft.com/en-us/azure/foundry/tutorials/quickstart-create-foundry-resources?tabs=portal) endpoint and model
+- (Optional) An [Application Insights](https://learn.microsoft.com/en-us/azure/azure-monitor/app/create-workspace-resource?tabs=portal) resource (for the connection string)
+- (Optional) An [Aspire Dashboard](https://aspire.dev/dashboard/overview/#standalone-mode) to visualize traces (if you want to use a local OpenTelemetry Collector)
+
+## Environment setup
+
+1. Create and activate a virtual environment using [uv](https://docs.astral.sh/uv/) (recommended):
+
+   ```bash
+   uv venv .venv
+   ```
+
+   ```bash
+   # Windows (PowerShell)
+   .venv\Scripts\Activate.ps1
+
+   # Windows (Command Prompt)
+   .venv\Scripts\activate.bat
+
+   # macOS/Linux
+   source .venv/bin/activate
+   ```
+
+   > **Note:** `python -m venv .venv` also works, but can hang indefinitely on Windows with Microsoft Store Python due to a known `ensurepip` issue. Use `uv venv .venv` to avoid this.
+
+2. Install dependencies:
+
+   ```bash
+   uv pip install -r requirements.txt
+   ```
+
+3. Create a `.env` file with your Foundry configuration following the `env.example` file in the sample.
+
+4. Make sure you are logged in with the Azure CLI:
+
+   ```bash
+   az login
+   ```
+
+## Azure Monitor
+
+Create an Application Insights resource in the Azure portal and copy the connection string to your `.env` file. If you don't have an Application Insights resource, you can skip this step, but you won't be able to see traces in Azure Monitor.
+
+## OTel Exporter
+
+You can also configure the OTLP exporter endpoint to send traces to a local OpenTelemetry Collector by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` environment variable in your `.env` file.
+
+## Run the sample
+
+Microsoft Agent Framework is natively instrumented with OpenTelemetry, so you can run the sample directly:
+
+```bash
+python sample_maf_agent.py
+```

samples/microsoft_agent_framework/requirements.txt

@@ -0,0 +1,3 @@
+agent-framework-core
+agent-framework-foundry
+microsoft-opentelemetry

samples/microsoft_agent_framework/sample_maf_agent.py

@@ -0,0 +1,63 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+from random import randint
+from typing import Annotated
+
+from agent_framework import Agent, tool
+from agent_framework.foundry import FoundryChatClient
+from agent_framework.observability import get_tracer
+from azure.identity import AzureCliCredential
+from dotenv import load_dotenv
+from microsoft.opentelemetry import use_microsoft_opentelemetry
+from opentelemetry.trace import SpanKind
+from opentelemetry.trace.span import format_trace_id
+from pydantic import Field
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+@tool(approval_mode="never_require")
+async def get_weather(
+    location: Annotated[str, Field(description="The location to get the weather for.")],
+) -> str:
+    """Get the weather for a given location."""
+    await asyncio.sleep(randint(0, 10) / 10.0)  # Simulate a network call
+    conditions = ["sunny", "cloudy", "rainy", "stormy"]
+    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."
+
+
+async def main():
+    # Set up Azure monitor exporters for telemetry
+    # This will automatically enable instrumentation for Agent Framework
+    use_microsoft_opentelemetry(enable_azure_monitor=True)
+
+    questions = [
+        "What's the weather in Amsterdam?",
+        "and in Paris, and which is better?",
+        "Why is the sky blue?",
+    ]
+
+    with get_tracer().start_as_current_span("Scenario: Agent Chat", kind=SpanKind.CLIENT) as current_span:
+        print(f"Trace ID: {format_trace_id(current_span.get_span_context().trace_id)}")
+
+        agent = Agent(
+            client=FoundryChatClient(credential=AzureCliCredential()),
+            tools=get_weather,
+            name="WeatherAgent",
+            instructions="You are a weather assistant.",
+            id="weather-agent",
+        )
+
+        session = agent.create_session()
+        for question in questions:
+            print(f"\nUser: {question}")
+            print(f"{agent.name}: ", end="")
+            async for update in agent.run(question, session=session, stream=True):
+                if update.text:
+                    print(update.text, end="")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())