Files
agent-framework/dotnet
T
westey 3571a7d321 .NET: [BREAKING] Subclass AgentThread so that different agents have their own threads with their own typed settings. (#798)
* Subclass AgentThread so that different agents have their own threads with their own typed settings.

* Address PR comment.

* Add unit tests for base abstract threads

* Fix style warning

* Fix stlying

* FIx and suppress warnings as needed.

* Remove covariant thread response types and fix some styling.

* Remove unecessary json property name attributes and make OrchestratingAgentThread private

* Fix break from merge from main.

* Fix formatting

* Fix deserialization bug in Memory sample

* Remove thread deletion from basic samples.

* Remove public constructors for thread subclasses and add more factory methods to concrete agent types.

* Update AgentProxy thread constructors to be internal as well.

* Revert AgentProxyThread to internal

* Change AIContextProvider to internal set

* Change conversation id and message store properties to internal set

* Update styling.

* Seal various thread types.

* Add thread type check for thread deletion

* Fix tests after latest merge from main

* Add thread type checks for thread deletion.

---------

Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
3571a7d321 · 2025-09-23 10:30:06 +00:00
History
..

Get Started with Microsoft Agent Framework for C# Developers

Run the Minimal Console demo

The Minimal Console demo is a simple console application which shows how to create and run an agent.

Supported Platforms:

  • .Net: net9.0, net8.0, netstandard2.0, net472
  • OS: Windows, macOS, Linux

If you want to use the latest published packages following the instructions here.

1. Configure required environment variables

This samples uses Azure OpenAI by default so you need to set the following environment variable

$env:AZURE_OPENAI_ENDPOINT = "https://<your deployment>.openai.azure.com/"

If you want to use OpenAI

  1. Edit Program.cs and change the following lines:
    AIAgent agent = new AzureOpenAIClient(
      new Uri(Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")!),
      new AzureCliCredential())
       .GetChatClient("gpt-4o-mini")
       .CreateAIAgent(
         instructions: "You are a helpful assistant, you can help the user with weather information.",
         tools: [AIFunctionFactory.Create(GetWeather)]);
    
    To this:
    AIAgent agent = new OpenAIClient(Environment.GetEnvironmentVariable("OPENAI_API_KEY")!)
      .GetChatClient("gpt-4o-mini")
      .CreateAIAgent(
        instructions: "You are a helpful assistant, you can help the user with weather information.",
        tools: [AIFunctionFactory.Create(GetWeather)]);
    
  2. Create an environment variable with your OpenAI key
    $env:OPENAI_API_KEY = "sk-..."
    

2. Build the project

cd demos\MinimalConsole
dotnet build

3. Run the demonstration

dotnet run --framework net9.0 --no-build

Sample output:

The weather in Amsterdam is currently cloudy, with a high temperature of 15°C.