.NET: [BREAKING] Add support for multiple AIContextProviders on a ChatClientAgent (#3863)

* Add support for multiple AIContextProviders on a ChatClientAgent

* Address PR comments and fix tests

* Address PR comments.

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/Program.cs

@@ -34,7 +34,7 @@ AIAgent agent = new AzureOpenAIClient(
     {
         ChatOptions = new() { Instructions = "You are good at telling jokes." },
         Name = "Joker",
-        AIContextProvider = new ChatHistoryMemoryProvider(
+        AIContextProviders = [new ChatHistoryMemoryProvider(
             vectorStore,
             collectionName: "chathistory",
             vectorDimensions: 3072,
@@ -48,7 +48,7 @@ AIAgent agent = new AzureOpenAIClient(
                 storageScope: new() { UserId = "UID1", SessionId = Guid.NewGuid().ToString() },
                 // Configure the scope which would be used to search for relevant prior messages.
                 // In this case, we are searching for any messages for the user across all sessions.
-                searchScope: new() { UserId = "UID1" }))
+                searchScope: new() { UserId = "UID1" }))]
     });
 
 // Start a new session for the agent conversation.

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/Program.cs

@@ -36,7 +36,7 @@ AIAgent agent = new AzureOpenAIClient(
         // If each session should have its own Mem0 scope, you can create a new id per session via the stateInitializer, e.g.:
         // new Mem0Provider(mem0HttpClient, stateInitializer: _ => new(new Mem0ProviderScope() { ThreadId = Guid.NewGuid().ToString() }))
         // In our case we are storing memories scoped by application and user instead so that memories are retained across threads.
-        AIContextProvider = new Mem0Provider(mem0HttpClient, stateInitializer: _ => new(new Mem0ProviderScope() { ApplicationId = "getting-started-agents", UserId = "sample-user" }))
+        AIContextProviders = [new Mem0Provider(mem0HttpClient, stateInitializer: _ => new(new Mem0ProviderScope() { ApplicationId = "getting-started-agents", UserId = "sample-user" }))]
     });
 
 AgentSession session = await agent.CreateSessionAsync();

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step03_CustomMemory/Program.cs

@@ -33,7 +33,7 @@ ChatClient chatClient = new AzureOpenAIClient(
 AIAgent agent = chatClient.AsAIAgent(new ChatClientAgentOptions()
 {
     ChatOptions = new() { Instructions = "You are a friendly assistant. Always address the user by their name." },
-    AIContextProvider = new UserInfoMemory(chatClient.AsIChatClient())
+    AIContextProviders = [new UserInfoMemory(chatClient.AsIChatClient())]
 });
 
 // Create a new session for the conversation.

dotnet/samples/GettingStarted/AgentWithRAG/AgentWithRAG_Step01_BasicTextRAG/Program.cs

@@ -62,7 +62,7 @@ AIAgent agent = azureOpenAIClient
     .AsAIAgent(new ChatClientAgentOptions
     {
         ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
-        AIContextProvider = new TextSearchProvider(SearchAdapter, textSearchOptions),
+        AIContextProviders = [new TextSearchProvider(SearchAdapter, textSearchOptions)],
         // Since we are using ChatCompletion which stores chat history locally, we can also add a message filter
         // that removes messages produced by the TextSearchProvider before they are added to the chat history, so that
         // we don't bloat chat history with all the search result messages.

dotnet/samples/GettingStarted/AgentWithRAG/AgentWithRAG_Step02_CustomVectorStoreRAG/Program.cs

@@ -71,7 +71,7 @@ AIAgent agent = azureOpenAIClient
     .AsAIAgent(new ChatClientAgentOptions
     {
         ChatOptions = new() { Instructions = "You are a helpful support specialist for the Microsoft Agent Framework. Answer questions using the provided context and cite the source document when available. Keep responses brief." },
-        AIContextProvider = new TextSearchProvider(SearchAdapter, textSearchOptions)
+        AIContextProviders = [new TextSearchProvider(SearchAdapter, textSearchOptions)]
     });
 
 AgentSession session = await agent.CreateSessionAsync();

dotnet/samples/GettingStarted/AgentWithRAG/AgentWithRAG_Step03_CustomRAGDataSource/Program.cs

@@ -29,7 +29,7 @@ AIAgent agent = new AzureOpenAIClient(
     .AsAIAgent(new ChatClientAgentOptions
     {
         ChatOptions = new() { Instructions = "You are a helpful support specialist for Contoso Outdoors. Answer questions using the provided context and cite the source document when available." },
-        AIContextProvider = new TextSearchProvider(MockSearchAsync, textSearchOptions)
+        AIContextProviders = [new TextSearchProvider(MockSearchAsync, textSearchOptions)]
     });
 
 AgentSession session = await agent.CreateSessionAsync();

dotnet/samples/GettingStarted/Agents/Agent_Step20_AdditionalAIContext/Program.cs

@@ -1,7 +1,7 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample shows how to inject additional AI context into a ChatClientAgent using a custom AIContextProvider component that is attached to the agent.
-// The sample also shows how to combine the results from multiple providers into a single class, in order to attach multiple of these to an agent.
+// This sample shows how to inject additional AI context into a ChatClientAgent using custom AIContextProvider components that are attached to the agent.
+// Multiple providers can be attached to an agent, and they will be called in sequence, each receiving the accumulated context from the previous one.
 // This mechanism can be used for various purposes, such as injecting RAG search results or memories into the agent's context.
 // Also note that Agent Framework already provides built-in AIContextProviders for many of these scenarios.
 
@@ -52,12 +52,12 @@ AIAgent agent = new AzureOpenAIClient(
             // You may want to store these messages, depending on their content and your requirements.
             StorageInputMessageFilter = messages => messages.Where(m => m.GetAgentRequestMessageSourceType() != AgentRequestMessageSourceType.AIContextProvider && m.GetAgentRequestMessageSourceType() != AgentRequestMessageSourceType.ChatHistory)
         }),
-        // Add an AI context provider that maintains a todo list for the agent and one that provides upcoming calendar entries.
-        // Wrap these in an AI context provider that aggregates the other two.
-        AIContextProvider = new AggregatingAIContextProvider([
+        // Add multiple AI context providers: one that maintains a todo list and one that provides upcoming calendar entries.
+        // The agent will call each provider in sequence, accumulating context from each.
+        AIContextProviders = [
             new TodoListAIContextProvider(),
             new CalendarSearchAIContextProvider(loadNextThreeCalendarEvents)
-        ]),
+        ],
     });
 
 // Invoke the agent and output the text result.
@@ -178,30 +178,4 @@ namespace SampleApp
             };
         }
     }
-
-    /// <summary>
-    /// An <see cref="AIContextProvider"/> which aggregates multiple AI context providers into one.
-    /// Tools and messages from all providers are combined, and instructions are concatenated.
-    /// </summary>
-    internal sealed class AggregatingAIContextProvider : AIContextProvider
-    {
-        private readonly List<AIContextProvider> _providers;
-
-        public AggregatingAIContextProvider(List<AIContextProvider> providers)
-        {
-            this._providers = providers;
-        }
-
-        protected override async ValueTask<AIContext> InvokingCoreAsync(InvokingContext context, CancellationToken cancellationToken = default)
-        {
-            // Invoke all the sub providers.
-            var currentAIContext = context.AIContext;
-            foreach (var provider in this._providers)
-            {
-                currentAIContext = await provider.InvokingAsync(new InvokingContext(context.Agent, context.Session, currentAIContext), cancellationToken);
-            }
-
-            return currentAIContext;
-        }
-    }
 }