agent-framework/dotnet/samples/02-agents/FoundryAgents/FoundryAgents_Step02_MultiturnConversation

Multi-turn Conversation with AI Agents

This sample demonstrates how to implement multi-turn conversations with AI agents, where context is preserved across multiple agent runs using threads and conversation IDs.

What this sample demonstrates

• Creating an AI agent with instructions
• Creating a project conversation to track conversations in the Foundry UI
• Using threads with conversation IDs to maintain conversation context
• Running multi-turn conversations with text output
• Running multi-turn conversations with streaming output
• Managing agent and conversation lifecycle (creation and deletion)

Prerequisites

Before you begin, ensure you have the following prerequisites:

• .NET 10 SDK or later
• Azure Foundry service endpoint and deployment configured
• Azure CLI installed and authenticated (for Azure credential authentication)

Note: This demo uses Azure CLI credentials for authentication. Make sure you're logged in with az login and have access to the Azure Foundry resource. For more information, see the Azure CLI documentation.

Set the following environment variables:

$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project" # Replace with your Azure Foundry resource endpoint
$env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"  # Optional, defaults to gpt-4o-mini

Run the sample

Navigate to the FoundryAgents sample directory and run:

cd dotnet/samples/02-agents/FoundryAgents
dotnet run --project .\FoundryAgents_Step02_MultiturnConversation

Expected behavior

The sample will:

1. Create an agent named "JokerAgent" with instructions to tell jokes
2. Create a project conversation to enable visibility in the Azure Foundry UI
3. Create a thread linked to the conversation ID for context tracking
4. Run the agent with a text prompt and display the response
5. Send a follow-up message to the same thread, demonstrating context preservation
6. Create a new thread sharing the same conversation ID and run the agent with streaming
7. Send a follow-up streaming message to demonstrate multi-turn streaming
8. Clean up resources by deleting the agent and conversation

Conversation ID vs PreviousResponseId

When working with multi-turn conversations, there are two approaches:

• With Conversation ID: By passing a conversation.Id to CreateSessionAsync(), the conversation will be visible in the Azure Foundry Project UI. This is useful for tracking and debugging conversations.
• Without Conversation ID: Sessions created without a conversation ID still work correctly, maintaining context via PreviousResponseId. However, these conversations may not appear in the Foundry UI.