.NET: Create a sample to show bounded chat history with overflow into chat history memory

dotnet/agent-framework-dotnet.slnx

@@ -143,6 +143,7 @@
     <Project Path="samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/AgentWithMemory_Step02_MemoryUsingMem0.csproj" />
     <Project Path="samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step03_CustomMemory/AgentWithMemory_Step03_CustomMemory.csproj" />
     <Project Path="samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/AgentWithMemory_Step04_MemoryUsingFoundry.csproj" />
+    <Project Path="samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj" />
   </Folder>
   <Folder Name="/Samples/GettingStarted/AgentWithOpenAI/">
     <File Path="samples/GettingStarted/AgentWithOpenAI/README.md" />

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj

@@ -0,0 +1,22 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFrameworks>net10.0</TargetFrameworks>
+
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Azure.AI.OpenAI" />
+    <PackageReference Include="Azure.Identity" />
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" />
+    <PackageReference Include="Microsoft.SemanticKernel.Connectors.InMemory" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
+  </ItemGroup>
+
+</Project>

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/BoundedChatHistoryProvider.cs

@@ -0,0 +1,128 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using Microsoft.Agents.AI;
+using Microsoft.Extensions.AI;
+using Microsoft.Extensions.VectorData;
+
+namespace SampleApp;
+
+/// <summary>
+/// A <see cref="ChatHistoryProvider"/> that keeps a bounded window of recent messages in session state
+/// (via <see cref="InMemoryChatHistoryProvider"/>) and overflows older messages to a vector store
+/// (via <see cref="ChatHistoryMemoryProvider"/>). When providing chat history, it searches the vector
+/// store for relevant older messages and prepends them as a memory context message.
+/// </summary>
+/// <remarks>
+/// Only non-system messages are counted towards the session state limit and overflow mechanism. System messages are always retained in session state and are not included in the vector store.
+/// Function calls and function results are also dropped when truncation happens, both from in-memory state, and they are also not persisted to the vector store.
+/// </remarks>
+internal sealed class BoundedChatHistoryProvider : ChatHistoryProvider, IDisposable
+{
+    private readonly InMemoryChatHistoryProvider _inMemoryProvider;
+    private readonly ChatHistoryMemoryProvider _memoryProvider;
+    private readonly TruncatingChatReducer _reducer;
+    private readonly string _contextPrompt;
+
+    /// <summary>
+    /// Initializes a new instance of the <see cref="BoundedChatHistoryProvider"/> class.
+    /// </summary>
+    /// <param name="maxSessionMessages">The maximum number of non-system messages to keep in session state before overflowing to the vector store.</param>
+    /// <param name="vectorStore">The vector store to use for storing and retrieving overflow chat history.</param>
+    /// <param name="collectionName">The name of the collection for storing overflow chat history in the vector store.</param>
+    /// <param name="vectorDimensions">The number of dimensions to use for the chat history vector store embeddings.</param>
+    /// <param name="stateInitializer">A delegate that initializes the memory provider state, providing the storage and search scopes.</param>
+    /// <param name="contextPrompt">Optional prompt to prefix memory search results. Defaults to a standard memory context prompt.</param>
+    public BoundedChatHistoryProvider(
+        int maxSessionMessages,
+        VectorStore vectorStore,
+        string collectionName,
+        int vectorDimensions,
+        Func<AgentSession?, ChatHistoryMemoryProvider.State> stateInitializer,
+        string? contextPrompt = null)
+    {
+        if (maxSessionMessages < 0)
+        {
+            throw new ArgumentOutOfRangeException(nameof(maxSessionMessages), "maxSessionMessages must be non-negative.");
+        }
+
+        this._reducer = new TruncatingChatReducer(maxSessionMessages);
+        this._inMemoryProvider = new InMemoryChatHistoryProvider(new InMemoryChatHistoryProviderOptions
+        {
+            ChatReducer = this._reducer,
+            ReducerTriggerEvent = InMemoryChatHistoryProviderOptions.ChatReducerTriggerEvent.AfterMessageAdded,
+            StorageInputMessageFilter = msgs => msgs,
+        });
+        this._memoryProvider = new ChatHistoryMemoryProvider(
+            vectorStore,
+            collectionName,
+            vectorDimensions,
+            stateInitializer,
+            options: new ChatHistoryMemoryProviderOptions
+            {
+                SearchInputMessageFilter = msgs => msgs,
+                StorageInputMessageFilter = msgs => msgs,
+            });
+        this._contextPrompt = contextPrompt
+            ?? "The following are memories from earlier in this conversation. Use them to inform your responses:";
+    }
+
+    /// <inheritdoc />
+    protected override async ValueTask<IEnumerable<ChatMessage>> ProvideChatHistoryAsync(
+        InvokingContext context,
+        CancellationToken cancellationToken = default)
+    {
+        // Delegate to the inner provider's full lifecycle (retrieve, filter, stamp, merge with request messages).
+        var allMessages = await this._inMemoryProvider.InvokingAsync(context, cancellationToken).ConfigureAwait(false);
+
+        // Search the vector store for relevant older messages.
+        var aiContext = new AIContext { Messages = context.RequestMessages.ToList() };
+        var invokingContext = new AIContextProvider.InvokingContext(
+            context.Agent, context.Session, aiContext);
+
+        var result = await this._memoryProvider.InvokingAsync(invokingContext, cancellationToken).ConfigureAwait(false);
+
+        // Extract only the messages added by the memory provider (stamped with AIContextProvider source type).
+        var memoryMessages = result.Messages?
+            .Where(m => m.GetAgentRequestMessageSourceType() == AgentRequestMessageSourceType.AIContextProvider)
+            .ToList();
+
+        if (memoryMessages is { Count: > 0 })
+        {
+            var memoryText = string.Join("\n", memoryMessages.Select(m => m.Text).Where(t => !string.IsNullOrWhiteSpace(t)));
+
+            if (!string.IsNullOrWhiteSpace(memoryText))
+            {
+                var contextMessage = new ChatMessage(ChatRole.User, $"{this._contextPrompt}\n{memoryText}");
+                return new[] { contextMessage }.Concat(allMessages);
+            }
+        }
+
+        return allMessages;
+    }
+
+    /// <inheritdoc />
+    protected override async ValueTask StoreChatHistoryAsync(
+        InvokedContext context,
+        CancellationToken cancellationToken = default)
+    {
+        // Delegate storage to the in-memory provider. Its TruncatingChatReducer (AfterMessageAdded trigger)
+        // will automatically truncate to the configured maximum and expose any removed messages.
+        var innerContext = new InvokedContext(
+            context.Agent, context.Session, context.RequestMessages, context.ResponseMessages!);
+        await this._inMemoryProvider.InvokedAsync(innerContext, cancellationToken).ConfigureAwait(false);
+
+        // Archive any messages that the reducer removed to the vector store.
+        if (this._reducer.RemovedMessages is { Count: > 0 })
+        {
+            var overflowContext = new AIContextProvider.InvokedContext(
+                context.Agent, context.Session, this._reducer.RemovedMessages, []);
+            await this._memoryProvider.InvokedAsync(overflowContext, cancellationToken).ConfigureAwait(false);
+        }
+    }
+
+    /// <inheritdoc/>
+    public void Dispose()
+    {
+        this._memoryProvider.Dispose();
+    }
+}

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/Program.cs

@@ -0,0 +1,79 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample shows how to create a bounded chat history provider that keeps a configurable number of
+// recent messages in session state and automatically overflows older messages to a vector store.
+// When the agent is invoked, it searches the vector store for relevant older messages and
+// prepends them as a "memory" context message before the recent session history.
+
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+using Microsoft.Extensions.AI;
+using Microsoft.Extensions.VectorData;
+using Microsoft.SemanticKernel.Connectors.InMemory;
+using OpenAI.Chat;
+using SampleApp;
+
+var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
+var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
+var embeddingDeploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME") ?? "text-embedding-3-large";
+
+// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
+// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
+// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
+var credential = new DefaultAzureCredential();
+
+// Create a vector store to store overflow chat messages.
+// For demonstration purposes, we are using an in-memory vector store.
+// Replace this with a persistent vector store implementation for production scenarios.
+VectorStore vectorStore = new InMemoryVectorStore(new InMemoryVectorStoreOptions()
+{
+    EmbeddingGenerator = new AzureOpenAIClient(new Uri(endpoint), credential)
+        .GetEmbeddingClient(embeddingDeploymentName)
+        .AsIEmbeddingGenerator()
+});
+
+var sessionId = Guid.NewGuid().ToString();
+
+// Create the BoundedChatHistoryProvider with a maximum of 4 non-system messages in session state.
+// It internally creates an InMemoryChatHistoryProvider with a TruncatingChatReducer and a
+// ChatHistoryMemoryProvider with the correct configuration to ensure overflow messages are
+// automatically archived to the vector store and recalled via semantic search.
+var boundedProvider = new BoundedChatHistoryProvider(
+    maxSessionMessages: 4,
+    vectorStore,
+    collectionName: "chathistory-overflow",
+    vectorDimensions: 3072,
+    session => new ChatHistoryMemoryProvider.State(
+        storageScope: new() { UserId = "UID1", SessionId = sessionId },
+        searchScope: new() { UserId = "UID1" }));
+
+// Create the agent with the bounded chat history provider.
+AIAgent agent = new AzureOpenAIClient(new Uri(endpoint), credential)
+    .GetChatClient(deploymentName)
+    .AsAIAgent(new ChatClientAgentOptions
+    {
+        ChatOptions = new() { Instructions = "You are a helpful assistant. Answer questions concisely." },
+        Name = "Assistant",
+        ChatHistoryProvider = boundedProvider,
+    });
+
+// Start a conversation. The first several exchanges will fill up the session state window.
+AgentSession session = await agent.CreateSessionAsync();
+
+Console.WriteLine("--- Filling the session window (4 messages max) ---\n");
+
+Console.WriteLine(await agent.RunAsync("My favorite color is blue.", session));
+Console.WriteLine(await agent.RunAsync("I have a dog named Max.", session));
+
+// At this point the session state holds 4 messages (2 user + 2 assistant).
+// The next exchange will push the oldest messages into the vector store.
+Console.WriteLine("\n--- Next exchange will trigger overflow to vector store ---\n");
+
+Console.WriteLine(await agent.RunAsync("What is the capital of France?", session));
+
+// The oldest messages about favorite color have now been archived to the vector store.
+// Ask the agent something that requires recalling the overflowed information.
+Console.WriteLine("\n--- Asking about overflowed information (should recall from vector store) ---\n");
+
+Console.WriteLine(await agent.RunAsync("What is my favorite color?", session));

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/README.md

@@ -0,0 +1,40 @@
+# Bounded Chat History with Vector Store Overflow
+
+This sample demonstrates how to create a custom `ChatHistoryProvider` that keeps a bounded window of recent messages in session state and automatically overflows older messages to a vector store. When the agent is invoked, it searches the vector store for relevant older messages and prepends them as memory context.
+
+## Concepts
+
+- **`TruncatingChatReducer`**: A custom `IChatReducer` that keeps the most recent N messages and exposes removed messages via a `RemovedMessages` property.
+- **`BoundedChatHistoryProvider`**: A custom `ChatHistoryProvider` that composes:
+  - `InMemoryChatHistoryProvider` for fast session-state storage (bounded by the reducer)
+  - `ChatHistoryMemoryProvider` for vector-store overflow and semantic search of older messages
+
+## Prerequisites
+
+- [.NET 10 SDK](https://dotnet.microsoft.com/download/dotnet/10.0)
+- An Azure OpenAI resource with:
+  - A chat deployment (e.g., `gpt-4o-mini`)
+  - An embedding deployment (e.g., `text-embedding-3-large`)
+
+## Configuration
+
+Set the following environment variables:
+
+| Variable | Description | Default |
+|---|---|---|
+| `AZURE_OPENAI_ENDPOINT` | Your Azure OpenAI endpoint URL | *(required)* |
+| `AZURE_OPENAI_DEPLOYMENT_NAME` | Chat model deployment name | `gpt-4o-mini` |
+| `AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME` | Embedding model deployment name | `text-embedding-3-large` |
+
+## Running the Sample
+
+```bash
+dotnet run
+```
+
+## How it Works
+
+1. The agent starts a conversation with a bounded session window of 4 non-system, non-function messages (i.e., user/assistant turns). System messages are always preserved, and function call/result messages are truncated and not preserved.
+2. As messages accumulate beyond the limit, the `TruncatingChatReducer` removes the oldest messages.
+3. The `BoundedChatHistoryProvider` detects the removed messages and stores them in a vector store via `ChatHistoryMemoryProvider`.
+4. On subsequent invocations, the provider searches the vector store for relevant older messages and prepends them as memory context, allowing the agent to recall information from earlier in the conversation.

dotnet/samples/GettingStarted/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/TruncatingChatReducer.cs

@@ -0,0 +1,65 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using Microsoft.Extensions.AI;
+
+namespace SampleApp;
+
+/// <summary>
+/// A truncating chat reducer that keeps the most recent messages up to a configured maximum,
+/// preserving any leading system message. Removed messages are exposed via <see cref="RemovedMessages"/>
+/// so that a caller can archive them (e.g. to a vector store).
+/// </summary>
+internal sealed class TruncatingChatReducer : IChatReducer
+{
+    private readonly int _maxMessages;
+
+    /// <summary>
+    /// Initializes a new instance of the <see cref="TruncatingChatReducer"/> class.
+    /// </summary>
+    /// <param name="maxMessages">The maximum number of non-system messages to retain.</param>
+    public TruncatingChatReducer(int maxMessages)
+    {
+        this._maxMessages = maxMessages > 0 ? maxMessages : throw new ArgumentOutOfRangeException(nameof(maxMessages));
+    }
+
+    /// <summary>
+    /// Gets the messages that were removed during the most recent call to <see cref="ReduceAsync"/>.
+    /// </summary>
+    public IReadOnlyList<ChatMessage> RemovedMessages { get; private set; } = [];
+
+    /// <inheritdoc />
+    public Task<IEnumerable<ChatMessage>> ReduceAsync(IEnumerable<ChatMessage> messages, CancellationToken cancellationToken)
+    {
+        _ = messages ?? throw new ArgumentNullException(nameof(messages));
+
+        ChatMessage? systemMessage = null;
+        Queue<ChatMessage> retained = new(capacity: this._maxMessages);
+        List<ChatMessage> removed = [];
+
+        foreach (var message in messages)
+        {
+            if (message.Role == ChatRole.System)
+            {
+                // Preserve the first system message outside the counting window.
+                systemMessage ??= message;
+            }
+            else if (!message.Contents.Any(c => c is FunctionCallContent or FunctionResultContent))
+            {
+                if (retained.Count >= this._maxMessages)
+                {
+                    removed.Add(retained.Dequeue());
+                }
+
+                retained.Enqueue(message);
+            }
+        }
+
+        this.RemovedMessages = removed;
+
+        IEnumerable<ChatMessage> result = systemMessage is not null
+            ? new[] { systemMessage }.Concat(retained)
+            : retained;
+
+        return Task.FromResult(result);
+    }
+}

dotnet/samples/GettingStarted/AgentWithMemory/README.md

@@ -8,5 +8,6 @@ These samples show how to create an agent with the Agent Framework that uses Mem
 |[Memory with MemoryStore](./AgentWithMemory_Step02_MemoryUsingMem0/)|This sample demonstrates how to create and run an agent that uses the Mem0 service to extract and retrieve individual memories.|
 |[Custom Memory Implementation](./AgentWithMemory_Step03_CustomMemory/)|This sample demonstrates how to create a custom memory component and attach it to an agent.|
 |[Memory with Azure AI Foundry](./AgentWithMemory_Step04_MemoryUsingFoundry/)|This sample demonstrates how to create and run an agent that uses Azure AI Foundry's managed memory service to extract and retrieve individual memories.|
+|[Bounded Chat History with Overflow](./AgentWithMemory_Step05_BoundedChatHistory/)|This sample demonstrates how to create a bounded chat history provider that overflows older messages to a vector store and recalls them as memories.|
 
 > **See also**: [Memory Search with Foundry Agents](../FoundryAgents/FoundryAgents_Step26_MemorySearch/) - demonstrates using the built-in Memory Search tool with Azure Foundry Agents.