.NET Compaction - Introducing compaction strategies and pipeline

dotnet/Directory.Packages.props

@@ -108,6 +108,7 @@
     <!-- Inference SDKs -->
     <PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.5.1" />
     <PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
+    <PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />
     <PackageVersion Include="OllamaSharp" Version="5.4.8" />
     <PackageVersion Include="OpenAI" Version="2.8.0" />
     <!-- Identity -->

dotnet/agent-framework-dotnet.slnx

@@ -56,6 +56,7 @@
     <Project Path="samples/02-agents/Agents/Agent_Step15_DeepResearch/Agent_Step15_DeepResearch.csproj" />
     <Project Path="samples/02-agents/Agents/Agent_Step16_Declarative/Agent_Step16_Declarative.csproj" />
     <Project Path="samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj" />
+    <Project Path="samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/DeclarativeAgents/">
     <Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />

dotnet/samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj

@@ -0,0 +1,21 @@
+<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" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
+  </ItemGroup>
+
+</Project>

dotnet/samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Program.cs

@@ -0,0 +1,112 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates how to use a ChatHistoryCompactionPipeline as the ChatReducer for an agent's
+// in-memory chat history. The pipeline chains multiple compaction strategies from gentle to aggressive:
+//   1. ToolResultCompactionStrategy - Collapses old tool-call groups into concise summaries
+//   2. SummarizationCompactionStrategy - LLM-compresses older conversation spans
+//   3. SlidingWindowCompactionStrategy - Keeps only the most recent N user turns
+//   4. TruncationCompactionStrategy - Emergency token-budget backstop
+
+using System.ComponentModel;
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Compaction;
+using Microsoft.Extensions.AI;
+
+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";
+
+// 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.
+AzureOpenAIClient openAIClient = new(new Uri(endpoint), new DefaultAzureCredential());
+
+// Create a chat client for the agent and a separate one for the summarization strategy.
+// Using the same model for simplicity; in production, use a smaller/cheaper model for summarization.
+IChatClient agentChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
+IChatClient summarizerChatClient = openAIClient.GetChatClient(deploymentName).AsIChatClient();
+
+// Define a tool the agent can use, so we can see tool-result compaction in action.
+[Description("Look up the current price of a product by name.")]
+static string LookupPrice([Description("The product name to look up.")] string productName) =>
+    productName.ToUpperInvariant() switch
+    {
+        "LAPTOP" => "The laptop costs $999.99.",
+        "KEYBOARD" => "The keyboard costs $79.99.",
+        "MOUSE" => "The mouse costs $29.99.",
+        _ => $"Sorry, I don't have pricing for '{productName}'."
+    };
+
+// Configure the compaction pipeline with one of each strategy, ordered least to most aggressive.
+PipelineCompactionStrategy compactionPipeline =
+    new(// 1. Gentle: collapse old tool-call groups into short summaries like "[Tool calls: LookupPrice]"
+        new ToolResultCompactionStrategy(CompactionTriggers.TokensExceed(0x200)),
+
+        // 2. Moderate: use an LLM to summarize older conversation spans into a concise message
+        new SummarizationCompactionStrategy(summarizerChatClient, CompactionTriggers.TokensExceed(0x500)),
+
+        // 3. Aggressive: keep only the last N user turns and their responses
+        new SlidingWindowCompactionStrategy(CompactionTriggers.TurnsExceed(4)),
+
+        // 4. Emergency: drop oldest groups until under the token budget
+        new TruncationCompactionStrategy(CompactionTriggers.TokensExceed(0x8000)));
+
+// Create the agent with an in-memory chat history provider whose reducer is the compaction pipeline.
+AIAgent agent =
+    agentChatClient.AsAIAgent(
+        new ChatClientAgentOptions
+        {
+            Name = "ShoppingAssistant",
+            ChatOptions = new()
+            {
+                Instructions =
+                    """
+                    You are a helpful, but long winded, shopping assistant.
+                    Help the user look up prices and compare products.
+                    When responding, Be sure to be extra descriptive and use as
+                    many words as possible without sounding ridiculous.
+                    """,
+                Tools = [AIFunctionFactory.Create(LookupPrice)],
+            },
+            CompactionStrategy = compactionPipeline,
+        });
+
+AgentSession session = await agent.CreateSessionAsync();
+
+// Helper to print chat history size
+void PrintChatHistory()
+{
+    if (session.TryGetInMemoryChatHistory(out var history))
+    {
+        Console.ForegroundColor = ConsoleColor.Cyan;
+        Console.WriteLine($"\n[Messages: x{history.Count}]\n");
+        Console.ResetColor();
+    }
+}
+
+// Run a multi-turn conversation with tool calls to exercise the pipeline.
+string[] prompts =
+[
+    "What's the price of a laptop?",
+    "How about a keyboard?",
+    "And a mouse?",
+    "Which product is the cheapest?",
+    "Can you compare the laptop and the keyboard for me?",
+    "What was the first product I asked about?",
+    "Thank you!",
+];
+
+foreach (string prompt in prompts)
+{
+    Console.ForegroundColor = ConsoleColor.Cyan;
+    Console.Write("\n[User] ");
+    Console.ResetColor();
+    Console.WriteLine(prompt);
+    Console.ForegroundColor = ConsoleColor.Cyan;
+    Console.Write("\n[Agent] ");
+    Console.ResetColor();
+    Console.WriteLine(await agent.RunAsync(prompt, session));
+
+    PrintChatHistory();
+}

dotnet/samples/02-agents/Agents/README.md

@@ -44,6 +44,7 @@ Before you begin, ensure you have the following prerequisites:
 |[Deep research with an agent](./Agent_Step15_DeepResearch/)|This sample demonstrates how to use the Deep Research Tool to perform comprehensive research on complex topics|
 |[Declarative agent](./Agent_Step16_Declarative/)|This sample demonstrates how to declaratively define an agent.|
 |[Providing additional AI Context to an agent using multiple AIContextProviders](./Agent_Step17_AdditionalAIContext/)|This sample demonstrates how to inject additional AI context into a ChatClientAgent using multiple custom AIContextProvider components that are attached to the agent.|
+|[Using compaction pipeline with an agent](./Agent_Step18_CompactionPipeline/)|This sample demonstrates how to use a compaction pipeline to efficiently limit the size of the conversation history for an agent.|
 
 ## Running the samples from the console
 

dotnet/src/Microsoft.Agents.AI.Abstractions/InMemoryChatHistoryProvider.cs

@@ -79,20 +79,21 @@ public List<ChatMessage> GetMessages(AgentSession? session)
     /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
     public void SetMessages(AgentSession? session, List<ChatMessage> messages)
     {
-        _ = Throw.IfNull(messages);
+        Throw.IfNull(messages);
 
-        var state = this._sessionState.GetOrInitializeState(session);
+        State state = this._sessionState.GetOrInitializeState(session);
         state.Messages = messages;
     }
 
     /// <inheritdoc />
     protected override async ValueTask<IEnumerable<ChatMessage>> ProvideChatHistoryAsync(InvokingContext context, CancellationToken cancellationToken = default)
     {
-        var state = this._sessionState.GetOrInitializeState(context.Session);
+        State state = this._sessionState.GetOrInitializeState(context.Session);
 
         if (this.ReducerTriggerEvent is InMemoryChatHistoryProviderOptions.ChatReducerTriggerEvent.BeforeMessagesRetrieval && this.ChatReducer is not null)
         {
-            state.Messages = (await this.ChatReducer.ReduceAsync(state.Messages, cancellationToken).ConfigureAwait(false)).ToList();
+            // Apply pre-invocation compaction strategy if configured
+            await this.CompactMessagesAsync(state, cancellationToken).ConfigureAwait(false);
         }
 
         return state.Messages;
@@ -101,18 +102,31 @@ protected override async ValueTask<IEnumerable<ChatMessage>> ProvideChatHistoryA
     /// <inheritdoc />
     protected override async ValueTask StoreChatHistoryAsync(InvokedContext context, CancellationToken cancellationToken = default)
     {
-        var state = this._sessionState.GetOrInitializeState(context.Session);
+        State state = this._sessionState.GetOrInitializeState(context.Session);
 
         // Add request and response messages to the provider
         var allNewMessages = context.RequestMessages.Concat(context.ResponseMessages ?? []);
         state.Messages.AddRange(allNewMessages);
 
-        if (this.ReducerTriggerEvent is InMemoryChatHistoryProviderOptions.ChatReducerTriggerEvent.AfterMessageAdded && this.ChatReducer is not null)
+        if (this.ReducerTriggerEvent is InMemoryChatHistoryProviderOptions.ChatReducerTriggerEvent.AfterMessageAdded)
         {
-            state.Messages = (await this.ChatReducer.ReduceAsync(state.Messages, cancellationToken).ConfigureAwait(false)).ToList();
+            // Apply pre-write compaction strategy if configured
+            await this.CompactMessagesAsync(state, cancellationToken).ConfigureAwait(false);
         }
     }
 
+    private async Task CompactMessagesAsync(State state, CancellationToken cancellationToken = default)
+    {
+        if (this.ChatReducer is not null)
+        {
+            // ChatReducer takes precedence, if configured
+            state.Messages = [.. await this.ChatReducer.ReduceAsync(state.Messages, cancellationToken).ConfigureAwait(false)];
+            return;
+        }
+
+        // %%% TODO: CONSIDER COMPACTION
+    }
+
     /// <summary>
     /// Represents the state of a <see cref="InMemoryChatHistoryProvider"/> stored in the <see cref="AgentSession.StateBag"/>.
     /// </summary>

dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgentOptions.cs

@@ -1,7 +1,10 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 using System.Collections.Generic;
+using System.Diagnostics.CodeAnalysis;
+using Microsoft.Agents.AI.Compaction;
 using Microsoft.Extensions.AI;
+using Microsoft.Shared.DiagnosticIds;
 
 namespace Microsoft.Agents.AI;
 
@@ -45,6 +48,23 @@ public sealed class ChatClientAgentOptions
     /// </summary>
     public IEnumerable<AIContextProvider>? AIContextProviders { get; set; }
 
+    /// <summary>
+    /// Gets or sets the <see cref="CompactionStrategy"/> to use for in-run context compaction.
+    /// </summary>
+    /// <remarks>
+    /// <para>
+    /// When set, this strategy is applied to the message list before each call to the underlying
+    /// <see cref="IChatClient"/> during agent execution. This keeps the context within token limits
+    /// as tool calls accumulate during long-running agent invocations.
+    /// </para>
+    /// <para>
+    /// The strategy organizes messages into atomic groups (preserving tool-call/result pairings)
+    /// before applying compaction logic. See <see cref="CompactionStrategy"/> for details.
+    /// </para>
+    /// </remarks>
+    [Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
+    public CompactionStrategy? CompactionStrategy { get; set; }
+
     /// <summary>
     /// Gets or sets a value indicating whether to use the provided <see cref="IChatClient"/> instance as is,
     /// without applying any default decorators.
@@ -101,6 +121,7 @@ public ChatClientAgentOptions Clone()
             ChatOptions = this.ChatOptions?.Clone(),
             ChatHistoryProvider = this.ChatHistoryProvider,
             AIContextProviders = this.AIContextProviders is null ? null : new List<AIContextProvider>(this.AIContextProviders),
+            CompactionStrategy = this.CompactionStrategy,
             UseProvidedChatClientAsIs = this.UseProvidedChatClientAsIs,
             ClearOnChatHistoryProviderConflict = this.ClearOnChatHistoryProviderConflict,
             WarnOnChatHistoryProviderConflict = this.WarnOnChatHistoryProviderConflict,

dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientExtensions.cs

@@ -4,6 +4,7 @@
 using System.Collections.Generic;
 using System.Diagnostics;
 using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Compaction;
 using Microsoft.Extensions.AI;
 using Microsoft.Extensions.DependencyInjection;
 using Microsoft.Extensions.Logging;
@@ -53,9 +54,16 @@ internal static IChatClient WithDefaultAgentMiddleware(this IChatClient chatClie
     {
         var chatBuilder = chatClient.AsBuilder();
 
+        // Add compaction as the innermost middleware so it runs before every LLM call,
+        // including those triggered by tool call iterations within FunctionInvokingChatClient.
+        if (options?.CompactionStrategy is { } compactionStrategy)
+        {
+            chatBuilder.Use(innerClient => new CompactingChatClient(innerClient, compactionStrategy));
+        }
+
         if (chatClient.GetService<FunctionInvokingChatClient>() is null)
         {
-            _ = chatBuilder.Use((innerClient, services) =>
+            chatBuilder.Use((innerClient, services) =>
             {
                 var loggerFactory = services.GetService<ILoggerFactory>();
 

dotnet/src/Microsoft.Agents.AI/Compaction/ChatReducerCompactionStrategy.cs

@@ -0,0 +1,91 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System.Collections.Generic;
+using System.Diagnostics.CodeAnalysis;
+using System.Threading;
+using System.Threading.Tasks;
+using Microsoft.Extensions.AI;
+using Microsoft.Shared.DiagnosticIds;
+using Microsoft.Shared.Diagnostics;
+
+namespace Microsoft.Agents.AI.Compaction;
+
+/// <summary>
+/// A compaction strategy that delegates to an <see cref="IChatReducer"/> to reduce the conversation's
+/// included messages.
+/// </summary>
+/// <remarks>
+/// <para>
+/// This strategy bridges the <see cref="IChatReducer"/> abstraction from <c>Microsoft.Extensions.AI</c>
+/// into the compaction pipeline. It collects the currently included messages from the
+/// <see cref="MessageIndex"/>, passes them to the reducer, and rebuilds the index from the
+/// reduced message list when the reducer produces fewer messages.
+/// </para>
+/// <para>
+/// The <see cref="CompactionTrigger"/> controls when reduction is attempted.
+/// Use <see cref="CompactionTriggers"/> for common trigger conditions such as token or message thresholds.
+/// </para>
+/// <para>
+/// Use this strategy when you have an existing <see cref="IChatReducer"/> implementation
+/// (such as <c>MessageCountingChatReducer</c>) and want to apply it as part of a
+/// <see cref="CompactionStrategy"/> pipeline or as an in-run compaction strategy.
+/// </para>
+/// </remarks>
+[Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
+public sealed class ChatReducerCompactionStrategy : CompactionStrategy
+{
+    /// <summary>
+    /// Initializes a new instance of the <see cref="ChatReducerCompactionStrategy"/> class.
+    /// </summary>
+    /// <param name="chatReducer">
+    /// The <see cref="IChatReducer"/> that performs the message reduction.
+    /// </param>
+    /// <param name="trigger">
+    /// The <see cref="CompactionTrigger"/> that controls when compaction proceeds.
+    /// </param>
+    /// <param name="target">
+    /// An optional target condition that controls when compaction stops. When <see langword="null"/>,
+    /// defaults to the inverse of the <paramref name="trigger"/> — compaction stops as soon as the trigger would no longer fire.
+    /// Note that the <see cref="IChatReducer"/> performs reduction in a single call, so the target is
+    /// not evaluated incrementally; it is available for composition with other strategies via
+    /// <see cref="PipelineCompactionStrategy"/>.
+    /// </param>
+    public ChatReducerCompactionStrategy(IChatReducer chatReducer, CompactionTrigger trigger, CompactionTrigger? target = null)
+        : base(trigger, target)
+    {
+        this.ChatReducer = Throw.IfNull(chatReducer);
+    }
+
+    /// <summary>
+    /// Gets the chat reducer used to reduce messages.
+    /// </summary>
+    public IChatReducer ChatReducer { get; }
+
+    /// <inheritdoc/>
+    protected override async Task<bool> ApplyCompactionAsync(MessageIndex index, CancellationToken cancellationToken)
+    {
+        List<ChatMessage> includedMessages = [.. index.GetIncludedMessages()];
+        if (includedMessages.Count == 0)
+        {
+            return false;
+        }
+
+        IEnumerable<ChatMessage> reduced = await this.ChatReducer.ReduceAsync(includedMessages, cancellationToken).ConfigureAwait(false);
+        IList<ChatMessage> reducedMessages = reduced as IList<ChatMessage> ?? [.. reduced];
+
+        if (reducedMessages.Count >= includedMessages.Count)
+        {
+            return false;
+        }
+
+        // Rebuild the index from the reduced messages
+        MessageIndex rebuilt = MessageIndex.Create(reducedMessages, index.Tokenizer);
+        index.Groups.Clear();
+        foreach (MessageGroup group in rebuilt.Groups)
+        {
+            index.Groups.Add(group);
+        }
+
+        return true;
+    }
+}