.Net Agents - Update Azure Foundry Agent SDK (#12027)

### Motivation and Context

As part of going GA with Foundry Agents, Azure team has split
`Azure.AI.Projects` into two packages: `Azure.AI.Projects` &
`Azure.AI.Agents.Persistent`

In addition, connecting to a foundry project will be based on
endpoint/credential and connection-string will not be supported.

### Description

- Updated package dependency to include: `Azure.AI.Projects.OneDP` &
`Azure.AI.Agents.Persistent`
- Updated declarative agents to support `endpoint` instead of
`connection-string`
- Updated tests and samples
- Deprecated `OpenAIClientProvider` 
- Removed `AzureAIClientProvider`


![image](https://github.com/user-attachments/assets/16ba9e4d-86b0-4bbb-a817-dc8bd346ddb0)



### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄

Author: crickman

dotnet/Directory.Packages.props

@@ -17,10 +17,10 @@
     <PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.0-preview.16" />
     <PackageVersion Include="AWSSDK.Extensions.NETCore.Setup" Version="4.0.0" />
     <PackageVersion Include="AWSSDK.SecurityToken" Version="4.0.0.2" />
+    <PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.0.0" />
     <PackageVersion Include="Azure.AI.ContentSafety" Version="1.0.0" />
-    <PackageVersion Include="Azure.AI.Inference" Version="1.0.0-beta.2" />
+    <PackageVersion Include="Azure.AI.Inference" Version="1.0.0-beta.5" />
     <PackageVersion Include="Azure.AI.OpenAI" Version="[2.2.0-beta.4]" />
-    <PackageVersion Include="Azure.AI.Projects" Version="[1.0.0-beta.8]" />
     <PackageVersion Include="Azure.Identity" Version="1.13.2" />
     <PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.3.0" />
     <PackageVersion Include="Azure.Search.Documents" Version="11.6.0" />

dotnet/nuget.config

@@ -3,7 +3,7 @@
 
   <packageSources>
     <clear />
-    <add key="nuget.org" value="https://api.nuget.org/v3/index.json" />
+    <add key="nuget.org" value="https://api.nuget.org/v3/index.json" />  
   </packageSources>
 
   <packageSourceMapping>

dotnet/samples/Concepts/Agents/AzureAIAgent_FileManipulation.cs

@@ -1,10 +1,9 @@
 // Copyright (c) Microsoft. All rights reserved.
-using Azure.AI.Projects;
+using Azure.AI.Agents.Persistent;
 using Microsoft.SemanticKernel;
 using Microsoft.SemanticKernel.Agents.AzureAI;
 using Microsoft.SemanticKernel.ChatCompletion;
 using Resources;
-using Agent = Azure.AI.Projects.Agent;
 
 namespace Agents;
 
@@ -17,10 +16,10 @@ public class AzureAIAgent_FileManipulation(ITestOutputHelper output) : BaseAzure
     public async Task AnalyzeCSVFileUsingAzureAIAgentAsync()
     {
         await using Stream stream = EmbeddedResource.ReadStream("sales.csv")!;
-        AgentFile fileInfo = await this.AgentsClient.UploadFileAsync(stream, AgentFilePurpose.Agents, "sales.csv");
+        PersistentAgentFileInfo fileInfo = await this.Client.Files.UploadFileAsync(stream, PersistentAgentFilePurpose.Agents, "sales.csv");
 
         // Define the agent
-        Agent definition = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             tools: [new CodeInterpreterToolDefinition()],
             toolResources:
@@ -31,8 +30,8 @@ public async Task AnalyzeCSVFileUsingAzureAIAgentAsync()
                         FileIds = { fileInfo.Id },
                     }
                 });
-        AzureAIAgent agent = new(definition, this.AgentsClient);
-        AzureAIAgentThread thread = new(this.AgentsClient);
+        AzureAIAgent agent = new(definition, this.Client);
+        AzureAIAgentThread thread = new(this.Client);
 
         // Respond to user input
         try
@@ -44,8 +43,8 @@ public async Task AnalyzeCSVFileUsingAzureAIAgentAsync()
         finally
         {
             await thread.DeleteAsync();
-            await this.AgentsClient.DeleteAgentAsync(agent.Id);
-            await this.AgentsClient.DeleteFileAsync(fileInfo.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
+            await this.Client.Files.DeleteFileAsync(fileInfo.Id);
         }
 
         // Local function to invoke agent and display the conversation messages.

dotnet/samples/Concepts/Agents/AzureAIAgent_Streaming.cs

@@ -1,11 +1,10 @@
 // Copyright (c) Microsoft. All rights reserved.
 using System.ComponentModel;
-using Azure.AI.Projects;
+using Azure.AI.Agents.Persistent;
 using Microsoft.SemanticKernel;
 using Microsoft.SemanticKernel.Agents;
 using Microsoft.SemanticKernel.Agents.AzureAI;
 using Microsoft.SemanticKernel.ChatCompletion;
-using Agent = Azure.AI.Projects.Agent;
 
 namespace Agents;
 
@@ -21,23 +20,30 @@ public async Task UseStreamingAgentAsync()
         const string AgentInstructions = "Repeat the user message in the voice of a pirate and then end with a parrot sound.";
 
         // Define the agent
-        Agent definition = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             AgentName,
             null,
             AgentInstructions);
-        AzureAIAgent agent = new(definition, this.AgentsClient);
+        AzureAIAgent agent = new(definition, this.Client);
 
-        // Create a thread for the agent conversation.
-        AzureAIAgentThread agentThread = new(this.AgentsClient, metadata: SampleMetadata);
+        try
+        {
+            // Create a thread for the agent conversation.
+            AzureAIAgentThread agentThread = new(this.Client, metadata: SampleMetadata);
 
-        // Respond to user input
-        await InvokeAgentAsync(agent, agentThread, "Fortune favors the bold.");
-        await InvokeAgentAsync(agent, agentThread, "I came, I saw, I conquered.");
-        await InvokeAgentAsync(agent, agentThread, "Practice makes perfect.");
+            // Respond to user input
+            await InvokeAgentAsync(agent, agentThread, "Fortune favors the bold.");
+            await InvokeAgentAsync(agent, agentThread, "I came, I saw, I conquered.");
+            await InvokeAgentAsync(agent, agentThread, "Practice makes perfect.");
 
-        // Output the entire chat history
-        await DisplayChatHistoryAsync(agentThread);
+            // Output the entire chat history
+            await DisplayChatHistoryAsync(agentThread);
+        }
+        finally
+        {
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
+        }
     }
 
     [Fact]
@@ -47,26 +53,34 @@ public async Task UseStreamingAssistantAgentWithPluginAsync()
         const string AgentInstructions = "Answer questions about the menu.";
 
         // Define the agent
-        Agent definition = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             AgentName,
             null,
             AgentInstructions);
-        AzureAIAgent agent = new(definition, this.AgentsClient);
+        AzureAIAgent agent = new(definition, this.Client);
 
         // Initialize plugin and add to the agent's Kernel (same as direct Kernel usage).
         KernelPlugin plugin = KernelPluginFactory.CreateFromType<MenuPlugin>();
         agent.Kernel.Plugins.Add(plugin);
 
         // Create a thread for the agent conversation.
-        AzureAIAgentThread agentThread = new(this.AgentsClient, metadata: SampleMetadata);
+        AzureAIAgentThread agentThread = new(this.Client, metadata: SampleMetadata);
 
-        // Respond to user input
-        await InvokeAgentAsync(agent, agentThread, "What is the special soup and its price?");
-        await InvokeAgentAsync(agent, agentThread, "What is the special drink and its price?");
+        try
+        {
+            // Respond to user input
+            await InvokeAgentAsync(agent, agentThread, "What is the special soup and its price?");
+            await InvokeAgentAsync(agent, agentThread, "What is the special drink and its price?");
 
-        // Output the entire chat history
-        await DisplayChatHistoryAsync(agentThread);
+            // Output the entire chat history
+            await DisplayChatHistoryAsync(agentThread);
+        }
+        finally
+        {
+            await this.Client.Threads.DeleteThreadAsync(agentThread.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
+        }
     }
 
     [Fact]
@@ -76,23 +90,31 @@ public async Task UseStreamingAssistantWithCodeInterpreterAsync()
         const string AgentInstructions = "Solve math problems with code.";
 
         // Define the agent
-        Agent definition = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             AgentName,
             null,
             AgentInstructions,
             [new CodeInterpreterToolDefinition()]);
-        AzureAIAgent agent = new(definition, this.AgentsClient);
+        AzureAIAgent agent = new(definition, this.Client);
 
         // Create a thread for the agent conversation.
-        AzureAIAgentThread agentThread = new(this.AgentsClient, metadata: SampleMetadata);
+        AzureAIAgentThread agentThread = new(this.Client, metadata: SampleMetadata);
 
-        // Respond to user input
-        await InvokeAgentAsync(agent, agentThread, "Is 191 a prime number?");
-        await InvokeAgentAsync(agent, agentThread, "Determine the values in the Fibonacci sequence that that are less then the value of 101");
+        try
+        {
+            // Respond to user input
+            await InvokeAgentAsync(agent, agentThread, "Is 191 a prime number?");
+            await InvokeAgentAsync(agent, agentThread, "Determine the values in the Fibonacci sequence that that are less then the value of 101");
 
-        // Output the entire chat history
-        await DisplayChatHistoryAsync(agentThread);
+            // Output the entire chat history
+            await DisplayChatHistoryAsync(agentThread);
+        }
+        finally
+        {
+            await this.Client.Threads.DeleteThreadAsync(agentThread.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
+        }
     }
 
     // Local function to invoke agent and display the conversation messages.

dotnet/samples/Demos/ModelContextProtocolClientServer/MCPClient/Samples/AzureAIAgentWithMCPToolsSample.cs

@@ -4,7 +4,7 @@
 using System.Collections.Generic;
 using System.Linq;
 using System.Threading.Tasks;
-using Azure.AI.Projects;
+using Azure.AI.Agents.Persistent;
 using Azure.Identity;
 using Microsoft.Extensions.Configuration;
 using Microsoft.SemanticKernel;
@@ -68,7 +68,7 @@ public static async Task RunAsync()
         await response!.Thread.DeleteAsync();
 
         // Delete the agent after use
-        await agent.Client.DeleteAgentAsync(agent.Id);
+        await agent.Client.Administration.DeleteAgentAsync(agent.Id);
     }
 
     /// <summary>
@@ -86,7 +86,7 @@ private static async Task<AzureAIAgent> CreateAzureAIAgentAsync(Kernel kernel, s
             .AddEnvironmentVariables()
             .Build();
 
-        if (config["AzureAI:ConnectionString"] is not { } connectionString)
+        if (config["AzureAI:Endpoint"] is not { } endpoint)
         {
             const string Message = "Please provide a valid `AzureAI:ConnectionString` secret to run this sample. See the associated README.md for more details.";
             Console.Error.WriteLine(Message);
@@ -96,11 +96,9 @@ private static async Task<AzureAIAgent> CreateAzureAIAgentAsync(Kernel kernel, s
         string modelId = config["AzureAI:ChatModelId"] ?? "gpt-4o-mini";
 
         // Create the Azure AI Agent
-        AIProjectClient projectClient = AzureAIAgent.CreateAzureAIClient(connectionString, new AzureCliCredential());
+        PersistentAgentsClient agentsClient = AzureAIAgent.CreateAgentsClient(endpoint, new AzureCliCredential());
 
-        AgentsClient agentsClient = projectClient.GetAgentsClient();
-
-        Azure.AI.Projects.Agent agent = await agentsClient.CreateAgentAsync(modelId, name, null, instructions);
+        PersistentAgent agent = await agentsClient.Administration.CreateAgentAsync(modelId, name, null, instructions);
 
         return new AzureAIAgent(agent, agentsClient)
         {

dotnet/samples/GettingStartedWithAgents/AzureAIAgent/Step01_AzureAIAgent.cs

@@ -1,4 +1,5 @@
 // Copyright (c) Microsoft. All rights reserved.
+using Azure.AI.Agents.Persistent;
 using Microsoft.SemanticKernel;
 using Microsoft.SemanticKernel.Agents;
 using Microsoft.SemanticKernel.Agents.AzureAI;
@@ -19,11 +20,10 @@ public async Task UseTemplateForAzureAgent()
         string generateStoryYaml = EmbeddedResource.Read("GenerateStory.yaml");
         PromptTemplateConfig templateConfig = KernelFunctionYaml.ToPromptTemplateConfig(generateStoryYaml);
         // Instructions, Name and Description properties defined via the PromptTemplateConfig.
-        Azure.AI.Projects.Agent definition = await this.AgentsClient.CreateAgentAsync(TestConfiguration.AzureAI.ChatModelId, templateConfig.Name, templateConfig.Description, templateConfig.Template);
-
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(TestConfiguration.AzureAI.ChatModelId, templateConfig.Name, templateConfig.Description, templateConfig.Template);
         AzureAIAgent agent = new(
             definition,
-            this.AgentsClient,
+            this.Client,
             templateFactory: new KernelPromptTemplateFactory(),
             templateFormat: PromptTemplateConfig.SemanticKernelTemplateFormat)
         {
@@ -35,7 +35,7 @@ public async Task UseTemplateForAzureAgent()
         };
 
         // Create a thread for the agent conversation.
-        AgentThread thread = new AzureAIAgentThread(this.AgentsClient, metadata: SampleMetadata);
+        AgentThread thread = new AzureAIAgentThread(this.Client, metadata: SampleMetadata);
 
         try
         {
@@ -53,7 +53,7 @@ await InvokeAgentAsync(
         finally
         {
             await thread.DeleteAsync();
-            await this.AgentsClient.DeleteAgentAsync(agent.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
         }
 
         // Local function to invoke agent and display the response.

dotnet/samples/GettingStartedWithAgents/AzureAIAgent/Step02_AzureAIAgent_Plugins.cs

@@ -1,4 +1,5 @@
 // Copyright (c) Microsoft. All rights reserved.
+using Azure.AI.Agents.Persistent;
 using Microsoft.SemanticKernel;
 using Microsoft.SemanticKernel.Agents;
 using Microsoft.SemanticKernel.Agents.AzureAI;
@@ -23,7 +24,7 @@ public async Task UseAzureAgentWithPlugin()
                 name: "Host");
 
         // Create a thread for the agent conversation.
-        AgentThread thread = new AzureAIAgentThread(this.AgentsClient, metadata: SampleMetadata);
+        AgentThread thread = new AzureAIAgentThread(this.Client, metadata: SampleMetadata);
 
         // Respond to user input
         try
@@ -36,7 +37,7 @@ public async Task UseAzureAgentWithPlugin()
         finally
         {
             await thread.DeleteAsync();
-            await this.AgentsClient.DeleteAgentAsync(agent.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
         }
     }
 
@@ -47,7 +48,7 @@ public async Task UseAzureAgentWithPluginEnumParameter()
         AzureAIAgent agent = await CreateAzureAgentAsync(plugin: KernelPluginFactory.CreateFromType<WidgetFactory>());
 
         // Create a thread for the agent conversation.
-        AgentThread thread = new AzureAIAgentThread(this.AgentsClient, metadata: SampleMetadata);
+        AgentThread thread = new AzureAIAgentThread(this.Client, metadata: SampleMetadata);
 
         // Respond to user input
         try
@@ -57,20 +58,20 @@ public async Task UseAzureAgentWithPluginEnumParameter()
         finally
         {
             await thread.DeleteAsync();
-            await this.AgentsClient.DeleteAgentAsync(agent.Id);
+            await this.Client.Administration.DeleteAgentAsync(agent.Id);
         }
     }
 
     private async Task<AzureAIAgent> CreateAzureAgentAsync(KernelPlugin plugin, string? instructions = null, string? name = null)
     {
         // Define the agent
-        Azure.AI.Projects.Agent definition = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent definition = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             name,
             null,
             instructions);
 
-        AzureAIAgent agent = new(definition, this.AgentsClient);
+        AzureAIAgent agent = new(definition, this.Client);
 
         // Add to the agent's Kernel
         if (plugin != null)

dotnet/samples/GettingStartedWithAgents/AzureAIAgent/Step03_AzureAIAgent_Chat.cs

@@ -1,10 +1,10 @@
 // Copyright (c) Microsoft. All rights reserved.
+using Azure.AI.Agents.Persistent;
 using Microsoft.SemanticKernel;
 using Microsoft.SemanticKernel.Agents;
 using Microsoft.SemanticKernel.Agents.AzureAI;
 using Microsoft.SemanticKernel.Agents.Chat;
 using Microsoft.SemanticKernel.ChatCompletion;
-using Agent = Azure.AI.Projects.Agent;
 
 namespace GettingStarted.AzureAgents;
 
@@ -39,18 +39,18 @@ Consider suggestions when refining an idea.
     public async Task UseGroupChatWithTwoAgents()
     {
         // Define the agents
-        Agent reviewerModel = await this.AgentsClient.CreateAgentAsync(
+        PersistentAgent reviewerModel = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             ReviewerName,
             null,
             ReviewerInstructions);
-        AzureAIAgent agentReviewer = new(reviewerModel, this.AgentsClient);
-        Agent writerModel = await this.AgentsClient.CreateAgentAsync(
+        AzureAIAgent agentReviewer = new(reviewerModel, this.Client);
+        PersistentAgent writerModel = await this.Client.Administration.CreateAgentAsync(
             TestConfiguration.AzureAI.ChatModelId,
             CopyWriterName,
             null,
             CopyWriterInstructions);
-        AzureAIAgent agentWriter = new(writerModel, this.AgentsClient);
+        AzureAIAgent agentWriter = new(writerModel, this.Client);
 
         // Create a chat for agent interaction.
         AgentGroupChat chat =
@@ -89,6 +89,8 @@ public async Task UseGroupChatWithTwoAgents()
         finally
         {
             await chat.ResetAsync();
+            await agentReviewer.Client.Administration.DeleteAgentAsync(agentReviewer.Id);
+            await agentWriter.Client.Administration.DeleteAgentAsync(agentWriter.Id);
         }
     }