Bump actions/checkout from 5 to 6 (#2404 )

Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
Python: Updated package versions (#2784 )
2026-06-16 21:04:09 +08:00 · 2025-12-11 18:43:52 +00:00 · 2025-12-11 18:39:08 +00:00 · 2025-12-11 17:24:08 +00:00 · 2025-12-11 14:08:20 +00:00 · 2025-12-11 11:04:22 +00:00
98 changed files with 4939 additions and 478 deletions
@@ -32,7 +32,7 @@ jobs:

    steps:
      - name: Checkout repository
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
        with:
          persist-credentials: false

@@ -37,7 +37,7 @@ jobs:
    outputs:
      dotnetChanges: ${{ steps.filter.outputs.dotnet}}
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - uses: dorny/paths-filter@v3
        id: filter
        with:
@@ -68,7 +68,7 @@ jobs:
    runs-on: ${{ matrix.os }}
    environment: ${{ matrix.environment }}
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
        with:
            persist-credentials: false
            sparse-checkout: |
@@ -30,7 +30,7 @@ jobs:

    steps:
      - name: Check out code
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
        with:
          fetch-depth: 0
          persist-credentials: false
@@ -19,7 +19,7 @@ jobs:
    runs-on: ubuntu-22.04
    # check out the latest version of the code
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
        with:
          persist-credentials: false

@@ -27,7 +27,7 @@ jobs:
    env:
      UV_PYTHON: ${{ matrix.python-version }}
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
        with:
          fetch-depth: 0
      - name: Set up python and install the project
@@ -24,7 +24,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Set up uv
        uses: astral-sh/setup-uv@v7
        with:
@@ -24,7 +24,7 @@ jobs:
    outputs:
      pythonChanges: ${{ steps.filter.outputs.python}}
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - uses: dorny/paths-filter@v3
        id: filter
        with:
@@ -59,7 +59,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6

      - name: Set up python and install the project
        id: python-setup
@@ -28,7 +28,7 @@ jobs:
    outputs:
      pythonChanges: ${{ steps.filter.outputs.python}}
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - uses: dorny/paths-filter@v3
        id: filter
        with:
@@ -75,7 +75,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
@@ -135,7 +135,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
@@ -23,7 +23,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
@@ -19,7 +19,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Download coverage report
        uses: actions/download-artifact@v6
        with:
@@ -20,7 +20,7 @@ jobs:
    env:
      UV_PYTHON: "3.10"
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      # Save the PR number to a file since the workflow_run event
      # in the coverage report workflow does not have access to it
      - name: Save PR number
@@ -27,7 +27,7 @@ jobs:
      run:
        working-directory: python
    steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
      - name: Set up python and install the project
        id: python-setup
        uses: ./.github/actions/python-setup
@@ -23,7 +23,7 @@
    <PackageVersion Include="Azure.AI.Projects.OpenAI" Version="1.0.0-beta.4" />
    <PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.8" />
    <PackageVersion Include="Azure.AI.OpenAI" Version="2.7.0-beta.2" />
-    <PackageVersion Include="Azure.Identity" Version="1.17.0" />
+    <PackageVersion Include="Azure.Identity" Version="1.17.1" />
    <PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.4.0" />
    <!-- Google Gemini  -->
    <PackageVersion Include="Google.GenAI" Version="0.6.0" />
@@ -33,18 +33,18 @@
    <!-- Newtonsoft.Json -->
    <PackageVersion Include="Newtonsoft.Json" Version="13.0.4" />
    <!-- System.* -->
-    <PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.0" />
+    <PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.1" />
    <PackageVersion Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
    <PackageVersion Include="System.ClientModel" Version="1.8.1" />
    <PackageVersion Include="System.CodeDom" Version="10.0.0" />
    <PackageVersion Include="System.Collections.Immutable" Version="10.0.0" />
    <PackageVersion Include="System.CommandLine" Version="2.0.0-rc.2.25502.107" />
-    <PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.0" />
+    <PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.1" />
    <PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.0" />
    <PackageVersion Include="System.Net.Http.Json" Version="10.0.0" />
    <PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.0" />
-    <PackageVersion Include="System.Text.Json" Version="10.0.0" />
-    <PackageVersion Include="System.Threading.Channels" Version="10.0.0" />
+    <PackageVersion Include="System.Text.Json" Version="10.0.1" />
+    <PackageVersion Include="System.Threading.Channels" Version="10.0.1" />
    <PackageVersion Include="System.Threading.Tasks.Extensions" Version="4.6.3" />
    <PackageVersion Include="System.Net.Security" Version="4.3.2" />
    <!-- OpenTelemetry -->
@@ -61,10 +61,10 @@
    <PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.0" />
    <PackageVersion Include="Swashbuckle.AspNetCore.SwaggerUI" Version="10.0.0" />
    <!-- Microsoft.Extensions.* -->
-    <PackageVersion Include="Microsoft.Extensions.AI" Version="10.0.1" />
-    <PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.0.1" />
+    <PackageVersion Include="Microsoft.Extensions.AI" Version="10.1.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.1.0" />
    <PackageVersion Include="Microsoft.Extensions.AI.AzureAIInference" Version="10.0.0-preview.1.25559.3" />
-    <PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
+    <PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.1.0-preview.1.25608.1" />
    <PackageVersion Include="Microsoft.Extensions.Caching.Memory" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.Configuration.Binder" Version="10.0.0" />
@@ -72,11 +72,11 @@
    <PackageVersion Include="Microsoft.Extensions.Configuration.Json" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.Configuration.UserSecrets" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.DependencyInjection" Version="10.0.0" />
-    <PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.0" />
+    <PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.1" />
    <PackageVersion Include="Microsoft.Extensions.Hosting" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.0" />
-    <PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.0" />
+    <PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.1" />
    <PackageVersion Include="Microsoft.Extensions.Logging.Console" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.0.0" />
    <PackageVersion Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.7.0" />
@@ -102,7 +102,7 @@
    <PackageVersion Include="ModelContextProtocol" Version="0.4.0-preview.3" />
    <!-- Inference SDKs -->
    <PackageVersion Include="Anthropic.SDK" Version="5.8.0" />
-    <PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.4.7" />
+    <PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.4.11" />
    <PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
    <PackageVersion Include="OllamaSharp" Version="5.4.8" />
    <PackageVersion Include="OpenAI" Version="2.7.0" />
@@ -129,6 +129,7 @@
    <Project Path="samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step02_Reasoning/Agent_OpenAI_Step02_Reasoning.csproj" />
    <Project Path="samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step03_CreateFromChatClient/Agent_OpenAI_Step03_CreateFromChatClient.csproj" />
    <Project Path="samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient.csproj" />
+    <Project Path="samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step05_Conversation/Agent_OpenAI_Step05_Conversation.csproj" />
  </Folder>
  <Folder Name="/Samples/Purview/" />
  <Folder Name="/Samples/Purview/AgentWithPurview/">
@@ -0,0 +1,15 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFrameworks>net10.0</TargetFrameworks>
+
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
+  </ItemGroup>
+
+</Project>
@@ -0,0 +1,98 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates how to maintain conversation state using the OpenAIResponseClientAgent
+// and AgentThread. By passing the same thread to multiple agent invocations, the agent
+// automatically maintains the conversation history, allowing the AI model to understand
+// context from previous exchanges.
+
+using System.ClientModel;
+using System.ClientModel.Primitives;
+using System.Text.Json;
+using Microsoft.Agents.AI;
+using Microsoft.Extensions.AI;
+using OpenAI;
+using OpenAI.Chat;
+using OpenAI.Conversations;
+
+string apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY") ?? throw new InvalidOperationException("OPENAI_API_KEY is not set.");
+string model = Environment.GetEnvironmentVariable("OPENAI_MODEL") ?? "gpt-4o-mini";
+
+// Create a ConversationClient directly from OpenAIClient
+OpenAIClient openAIClient = new(apiKey);
+ConversationClient conversationClient = openAIClient.GetConversationClient();
+
+// Create an agent directly from the OpenAIResponseClient using OpenAIResponseClientAgent
+ChatClientAgent agent = new(openAIClient.GetOpenAIResponseClient(model).AsIChatClient(), instructions: "You are a helpful assistant.", name: "ConversationAgent");
+
+ClientResult createConversationResult = await conversationClient.CreateConversationAsync(BinaryContent.Create(BinaryData.FromString("{}")));
+
+using JsonDocument createConversationResultAsJson = JsonDocument.Parse(createConversationResult.GetRawResponse().Content.ToString());
+string conversationId = createConversationResultAsJson.RootElement.GetProperty("id"u8)!.GetString()!;
+
+// Create a thread for the conversation - this enables conversation state management for subsequent turns
+AgentThread thread = agent.GetNewThread(conversationId);
+
+Console.WriteLine("=== Multi-turn Conversation Demo ===\n");
+
+// First turn: Ask about a topic
+Console.WriteLine("User: What is the capital of France?");
+UserChatMessage firstMessage = new("What is the capital of France?");
+
+// After this call, the conversation state associated in the options is stored in 'thread' and used in subsequent calls
+ChatCompletion firstResponse = await agent.RunAsync([firstMessage], thread);
+Console.WriteLine($"Assistant: {firstResponse.Content.Last().Text}\n");
+
+// Second turn: Follow-up question that relies on conversation context
+Console.WriteLine("User: What famous landmarks are located there?");
+UserChatMessage secondMessage = new("What famous landmarks are located there?");
+
+ChatCompletion secondResponse = await agent.RunAsync([secondMessage], thread);
+Console.WriteLine($"Assistant: {secondResponse.Content.Last().Text}\n");
+
+// Third turn: Another follow-up that demonstrates context continuity
+Console.WriteLine("User: How tall is the most famous one?");
+UserChatMessage thirdMessage = new("How tall is the most famous one?");
+
+ChatCompletion thirdResponse = await agent.RunAsync([thirdMessage], thread);
+Console.WriteLine($"Assistant: {thirdResponse.Content.Last().Text}\n");
+
+Console.WriteLine("=== End of Conversation ===");
+
+// Show full conversation history
+Console.WriteLine("Full Conversation History:");
+ClientResult getConversationResult = await conversationClient.GetConversationAsync(conversationId);
+
+Console.WriteLine("Conversation created.");
+Console.WriteLine($"    Conversation ID: {conversationId}");
+Console.WriteLine();
+
+CollectionResult getConversationItemsResults = conversationClient.GetConversationItems(conversationId);
+foreach (ClientResult result in getConversationItemsResults.GetRawPages())
+{
+    Console.WriteLine("Message contents retrieved. Order is most recent first by default.");
+    using JsonDocument getConversationItemsResultAsJson = JsonDocument.Parse(result.GetRawResponse().Content.ToString());
+    foreach (JsonElement element in getConversationItemsResultAsJson.RootElement.GetProperty("data").EnumerateArray())
+    {
+        string messageId = element.GetProperty("id"u8).ToString();
+        string messageRole = element.GetProperty("role"u8).ToString();
+        Console.WriteLine($"    Message ID: {messageId}");
+        Console.WriteLine($"    Message Role: {messageRole}");
+
+        foreach (var content in element.GetProperty("content").EnumerateArray())
+        {
+            string messageContentText = content.GetProperty("text"u8).ToString();
+            Console.WriteLine($"    Message Text: {messageContentText}");
+        }
+        Console.WriteLine();
+    }
+}
+
+ClientResult deleteConversationResult = conversationClient.DeleteConversation(conversationId);
+using JsonDocument deleteConversationResultAsJson = JsonDocument.Parse(deleteConversationResult.GetRawResponse().Content.ToString());
+bool deleted = deleteConversationResultAsJson.RootElement
+    .GetProperty("deleted"u8)
+    .GetBoolean();
+
+Console.WriteLine("Conversation deleted.");
+Console.WriteLine($"    Deleted: {deleted}");
+Console.WriteLine();
@@ -0,0 +1,90 @@
+# Managing Conversation State with OpenAI
+
+This sample demonstrates how to maintain conversation state across multiple turns using the Agent Framework with OpenAI's Conversation API.
+
+## What This Sample Shows
+
+- **Conversation State Management**: Shows how to use `ConversationClient` and `AgentThread` to maintain conversation context across multiple agent invocations
+- **Multi-turn Conversations**: Demonstrates follow-up questions that rely on context from previous messages in the conversation
+- **Server-Side Storage**: Uses OpenAI's Conversation API to manage conversation history server-side, allowing the model to access previous messages without resending them
+- **Conversation Lifecycle**: Demonstrates creating, retrieving, and deleting conversations
+
+## Key Concepts
+
+### ConversationClient for Server-Side Storage
+
+The `ConversationClient` manages conversations on OpenAI's servers:
+
+```csharp
+// Create a ConversationClient from OpenAIClient
+OpenAIClient openAIClient = new(apiKey);
+ConversationClient conversationClient = openAIClient.GetConversationClient();
+
+// Create a new conversation
+ClientResult createConversationResult = await conversationClient.CreateConversationAsync(BinaryContent.Create(BinaryData.FromString("{}")));
+```
+
+### AgentThread for Conversation State
+
+The `AgentThread` works with `ChatClientAgentRunOptions` to link the agent to a server-side conversation:
+
+```csharp
+// Set up agent run options with the conversation ID
+ChatClientAgentRunOptions agentRunOptions = new() { ChatOptions = new ChatOptions() { ConversationId = conversationId } };
+
+// Create a thread for the conversation
+AgentThread thread = agent.GetNewThread();
+
+// First call links the thread to the conversation
+ChatCompletion firstResponse = await agent.RunAsync([firstMessage], thread, agentRunOptions);
+
+// Subsequent calls use the thread without needing to pass options again
+ChatCompletion secondResponse = await agent.RunAsync([secondMessage], thread);
+```
+
+### Retrieving Conversation History
+
+You can retrieve the full conversation history from the server:
+
+```csharp
+CollectionResult getConversationItemsResults = conversationClient.GetConversationItems(conversationId);
+foreach (ClientResult result in getConversationItemsResults.GetRawPages())
+{
+    // Process conversation items
+}
+```
+
+### How It Works
+
+1. **Create an OpenAI Client**: Initialize an `OpenAIClient` with your API key
+2. **Create a Conversation**: Use `ConversationClient` to create a server-side conversation
+3. **Create an Agent**: Initialize an `OpenAIResponseClientAgent` with the desired model and instructions
+4. **Create a Thread**: Call `agent.GetNewThread()` to create a new conversation thread
+5. **Link Thread to Conversation**: Pass `ChatClientAgentRunOptions` with the `ConversationId` on the first call
+6. **Send Messages**: Subsequent calls to `agent.RunAsync()` only need the thread - context is maintained
+7. **Cleanup**: Delete the conversation when done using `conversationClient.DeleteConversation()`
+
+## Running the Sample
+
+1. Set the required environment variables:
+   ```powershell
+   $env:OPENAI_API_KEY = "your_api_key_here"
+   $env:OPENAI_MODEL = "gpt-4o-mini"
+   ```
+
+2. Run the sample:
+   ```powershell
+   dotnet run
+   ```
+
+## Expected Output
+
+The sample demonstrates a three-turn conversation where each follow-up question relies on context from previous messages:
+
+1. First question asks about the capital of France
+2. Second question asks about landmarks "there" - requiring understanding of the previous answer
+3. Third question asks about "the most famous one" - requiring context from both previous turns
+
+After the conversation, the sample retrieves and displays the full conversation history from the server, then cleans up by deleting the conversation.
+
+This demonstrates that the conversation state is properly maintained across multiple agent invocations using OpenAI's server-side conversation storage.
@@ -13,4 +13,5 @@ Agent Framework provides additional support to allow OpenAI developers to use th
 |[Creating an AIAgent](./Agent_OpenAI_Step01_Running/)|This sample demonstrates how to create and run a basic agent with native OpenAI SDK types. Shows both regular and streaming invocation of the agent.|
 |[Using Reasoning Capabilities](./Agent_OpenAI_Step02_Reasoning/)|This sample demonstrates how to create an AI agent with reasoning capabilities using OpenAI's reasoning models and response types.|
 |[Creating an Agent from a ChatClient](./Agent_OpenAI_Step03_CreateFromChatClient/)|This sample demonstrates how to create an AI agent directly from an OpenAI.Chat.ChatClient instance using OpenAIChatClientAgent.|
-|[Creating an Agent from an OpenAIResponseClient](./Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/)|This sample demonstrates how to create an AI agent directly from an OpenAI.Responses.OpenAIResponseClient instance using OpenAIResponseClientAgent.|
+|[Creating an Agent from an OpenAIResponseClient](./Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/)|This sample demonstrates how to create an AI agent directly from an OpenAI.Responses.OpenAIResponseClient instance using OpenAIResponseClientAgent.|
+|[Managing Conversation State](./Agent_OpenAI_Step05_Conversation/)|This sample demonstrates how to maintain conversation state across multiple turns using the AgentThread for context continuity.|
@@ -36,11 +36,11 @@
  </ItemGroup>

  <ItemGroup>
-    <PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
+    <PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.5" />
    <PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.2" />
-    <PackageReference Include="Azure.Identity" Version="1.17.0" />
+    <PackageReference Include="Azure.Identity" Version="1.17.1" />
    <PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251125.1" />
-    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.1.0-preview.1.25608.1" />
  </ItemGroup>

  <!-- Add analyzers with compatible versions -->
@@ -37,9 +37,9 @@
  <ItemGroup>
    <PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
    <PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.2" />
-    <PackageReference Include="Azure.Identity" Version="1.17.0" />
+    <PackageReference Include="Azure.Identity" Version="1.17.1" />
    <PackageReference Include="Microsoft.Agents.AI.OpenAI" Version="1.0.0-preview.251125.1" />
-    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.1.0-preview.1.25608.1" />
  </ItemGroup>

  <!-- Add analyzers with compatible versions -->
@@ -37,9 +37,9 @@
  <ItemGroup>
    <PackageReference Include="Azure.AI.AgentServer.AgentFramework" Version="1.0.0-beta.4" />
    <PackageReference Include="Azure.AI.OpenAI" Version="2.7.0-beta.2" />
-    <PackageReference Include="Azure.Identity" Version="1.17.0" />
+    <PackageReference Include="Azure.Identity" Version="1.17.1" />
    <PackageReference Include="Microsoft.Agents.AI.Workflows" Version="1.0.0-preview.251125.1" />
-    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.0.1-preview.1.25571.5" />
+    <PackageReference Include="Microsoft.Extensions.AI.OpenAI" Version="10.1.0-preview.1.25608.1" />
  </ItemGroup>

  <!-- Add analyzers with compatible versions -->
@@ -198,7 +198,7 @@ internal sealed class A2AAgent : AIAgent
    }

    /// <inheritdoc/>
-    public override string Id => this._id ?? base.Id;
+    protected override string? IdCore => this._id;

    /// <inheritdoc/>
    public override string? Name => this._name ?? base.Name;
@@ -22,9 +22,6 @@ namespace Microsoft.Agents.AI;
 [DebuggerDisplay("{DisplayName,nq}")]
 public abstract class AIAgent
 {
-    /// <summary>Default ID of this agent instance.</summary>
-    private readonly string _id = Guid.NewGuid().ToString("N");
-
    /// <summary>
    /// Gets the unique identifier for this agent instance.
    /// </summary>
@@ -37,7 +34,19 @@ public abstract class AIAgent
    /// agent instances in multi-agent scenarios. They should remain stable for the lifetime
    /// of the agent instance.
    /// </remarks>
-    public virtual string Id => this._id;
+    public string Id { get => this.IdCore ?? field; } = Guid.NewGuid().ToString("N");
+
+    /// <summary>
+    /// Gets a custom identifier for the agent, which can be overridden by derived classes.
+    /// </summary>
+    /// <value>
+    /// A string representing the agent's identifier, or <see langword="null"/> if the default ID should be used.
+    /// </value>
+    /// <remarks>
+    /// Derived classes can override this property to provide a custom identifier.
+    /// When <see langword="null"/> is returned, the <see cref="Id"/> property will use the default randomly-generated identifier.
+    /// </remarks>
+    protected virtual string? IdCore => null;

    /// <summary>
    /// Gets the human-readable name of the agent.
@@ -61,7 +70,7 @@ public abstract class AIAgent
    /// This property provides a guaranteed non-null string suitable for display in user interfaces,
    /// logs, or other contexts where a readable identifier is needed.
    /// </remarks>
-    public virtual string DisplayName => this.Name ?? this.Id ?? this._id; // final fallback to _id in case Id override returns null
+    public virtual string DisplayName => this.Name ?? this.Id;

    /// <summary>
    /// Gets a description of the agent's purpose, capabilities, or behavior.
@@ -54,7 +54,7 @@ public class DelegatingAIAgent : AIAgent
    protected AIAgent InnerAgent { get; }

    /// <inheritdoc />
-    public override string Id => this.InnerAgent.Id;
+    protected override string? IdCore => this.InnerAgent.Id;

    /// <inheritdoc />
    public override string? Name => this.InnerAgent.Name;
@@ -81,7 +81,7 @@ internal sealed partial class DevUIMiddleware
            }

            context.Response.StatusCode = StatusCodes.Status301MovedPermanently;
-            context.Response.Headers.Location = redirectUrl;
+            context.Response.Headers.Location = redirectUrl; // CodeQL [SM04598] justification: The redirect URL is constructed from a server-configured base path (_basePath), not user input. The query string is only appended as parameters and cannot change the redirect destination since this is a relative URL.

            if (this._logger.IsEnabled(LogLevel.Debug))
            {
@@ -19,7 +19,7 @@ internal sealed class EntityAgentWrapper(
    private readonly IServiceProvider? _entityScopedServices = entityScopedServices;

    // The ID of the agent is always the entity ID.
-    public override string Id => this._entityContext.Id.ToString();
+    protected override string? IdCore => this._entityContext.Id.ToString();

    public override async Task<AgentRunResponse> RunAsync(
        IEnumerable<ChatMessage> messages,
@@ -39,7 +39,7 @@ internal sealed class WorkflowHostAgent : AIAgent
        this._describeTask = this._workflow.DescribeProtocolAsync().AsTask();
    }

-    public override string Id => this._id ?? base.Id;
+    protected override string? IdCore => this._id;
    public override string? Name { get; }
    public override string? Description { get; }

@@ -121,7 +121,7 @@ public sealed partial class ChatClientAgent : AIAgent
    public IChatClient ChatClient { get; }

    /// <inheritdoc/>
-    public override string Id => this._agentOptions?.Id ?? base.Id;
+    protected override string? IdCore => this._agentOptions?.Id;

    /// <inheritdoc/>
    public override string? Name => this._agentOptions?.Name;
@@ -214,13 +214,31 @@ public class AIAgentTests
    [Fact]
    public void ValidateAgentIDIsIdempotent()
    {
+        // Arrange
        var agent = new MockAgent();

+        // Act
        string id = agent.Id;
+
+        // Assert
        Assert.NotNull(id);
        Assert.Equal(id, agent.Id);
    }

+    [Fact]
+    public void ValidateAgentIDCanBeProvidedByDerivedAgentClass()
+    {
+        // Arrange
+        var agent = new MockAgent(id: "test-agent-id");
+
+        // Act
+        string id = agent.Id;
+
+        // Assert
+        Assert.NotNull(id);
+        Assert.Equal("test-agent-id", id);
+    }
+
    #region GetService Method Tests

    /// <summary>
@@ -344,6 +362,13 @@ public class AIAgentTests

    private sealed class MockAgent : AIAgent
    {
+        public MockAgent(string? id = null)
+        {
+            this.IdCore = id;
+        }
+
+        protected override string? IdCore { get; }
+
        public override AgentThread GetNewThread()
            => throw new NotImplementedException();

@@ -6,6 +6,7 @@ using System.Threading;
 using System.Threading.Tasks;
 using Microsoft.Extensions.AI;
 using Moq;
+using Moq.Protected;

 namespace Microsoft.Agents.AI.Abstractions.UnitTests;

@@ -31,7 +32,7 @@ public class DelegatingAIAgentTests
        this._testThread = new TestAgentThread();

        // Setup inner agent mock
-        this._innerAgentMock.Setup(x => x.Id).Returns("test-agent-id");
+        this._innerAgentMock.Protected().SetupGet<string>("IdCore").Returns("test-agent-id");
        this._innerAgentMock.Setup(x => x.Name).Returns("Test Agent");
        this._innerAgentMock.Setup(x => x.Description).Returns("Test Description");
        this._innerAgentMock.Setup(x => x.GetNewThread()).Returns(this._testThread);
@@ -93,7 +94,7 @@ public class DelegatingAIAgentTests

        // Assert
        Assert.Equal("test-agent-id", id);
-        this._innerAgentMock.Verify(x => x.Id, Times.Once);
+        this._innerAgentMock.Protected().VerifyGet<string>("IdCore", Times.Once());
    }

    /// <summary>
@@ -276,15 +276,9 @@ public sealed class BasicStreamingTests : IAsyncDisposable
 [SuppressMessage("Performance", "CA1812:Avoid uninstantiated internal classes", Justification = "Instantiated via dependency injection")]
 internal sealed class FakeChatClientAgent : AIAgent
 {
-    public FakeChatClientAgent()
-    {
-        this.Id = "fake-agent";
-        this.Description = "A fake agent for testing";
-    }
+    protected override string? IdCore => "fake-agent";

-    public override string Id { get; }
-
-    public override string? Description { get; }
+    public override string? Description => "A fake agent for testing";

    public override AgentThread GetNewThread()
    {
@@ -350,15 +344,9 @@ internal sealed class FakeChatClientAgent : AIAgent
 [SuppressMessage("Performance", "CA1812:Avoid uninstantiated internal classes", Justification = "Instantiated via dependency injection")]
 internal sealed class FakeMultiMessageAgent : AIAgent
 {
-    public FakeMultiMessageAgent()
-    {
-        this.Id = "fake-multi-message-agent";
-        this.Description = "A fake agent that sends multiple messages for testing";
-    }
+    protected override string? IdCore => "fake-multi-message-agent";

-    public override string Id { get; }
-
-    public override string? Description { get; }
+    public override string? Description => "A fake agent that sends multiple messages for testing";

    public override AgentThread GetNewThread()
    {
@@ -421,7 +421,7 @@ public sealed class AGUIEndpointRouteBuilderExtensionsTests

    private sealed class MultiResponseAgent : AIAgent
    {
-        public override string Id => "multi-response-agent";
+        protected override string? IdCore => "multi-response-agent";

        public override string? Description => "Agent that produces multiple text chunks";

@@ -510,7 +510,7 @@ public sealed class AGUIEndpointRouteBuilderExtensionsTests

    private sealed class TestAgent : AIAgent
    {
-        public override string Id => "test-agent";
+        protected override string? IdCore => "test-agent";

        public override string? Description => "Test agent";

@@ -57,7 +57,7 @@ internal sealed class HelloAgent(string id = nameof(HelloAgent)) : AIAgent
    public const string Greeting = "Hello World!";
    public const string DefaultId = nameof(HelloAgent);

-    public override string Id => id;
+    protected override string? IdCore => id;
    public override string? Name => id;

    public override AgentThread GetNewThread()
@@ -19,7 +19,7 @@ public class SpecializedExecutorSmokeTests
 {
    public class TestAIAgent(List<ChatMessage>? messages = null, string? id = null, string? name = null) : AIAgent
    {
-        public override string Id => id ?? base.Id;
+        protected override string? IdCore => id;
        public override string? Name => name;

        public static List<ChatMessage> ToChatMessages(params string[] messages)
@@ -13,7 +13,7 @@ namespace Microsoft.Agents.AI.Workflows.UnitTests;

 internal class TestEchoAgent(string? id = null, string? name = null, string? prefix = null) : AIAgent
 {
-    public override string Id => id ?? base.Id;
+    protected override string? IdCore => id;
    public override string? Name => name ?? base.Name;

    public override AgentThread DeserializeThread(JsonElement serializedThread, JsonSerializerOptions? jsonSerializerOptions = null)
@@ -7,6 +7,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ## [Unreleased]

+## [1.0.0b251211] - 2025-12-11
+
+### Added
+
+- **agent-framework-core**: Extend HITL support for all orchestration patterns (#2620)
+- **agent-framework-core**: Add factory pattern to concurrent orchestration builder (#2738)
+- **agent-framework-core**: Add factory pattern to sequential orchestration builder (#2710)
+- **agent-framework-azure-ai**: Capture file IDs from code interpreter in streaming responses (#2741)
+
+### Changed
+
+- **agent-framework-azurefunctions**: Change DurableAIAgent log level from warning to debug when invoked without thread (#2736)
+
+### Fixed
+
+- **agent-framework-core**: Added more complete parsing for mcp tool arguments (#2756)
+- **agent-framework-core**: Fix GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outputs (#2750)
+- **samples**: Standardize OpenAI API key environment variable naming (#2629)
+
 ## [1.0.0b251209] - 2025-12-09

 ### Added
@@ -347,7 +366,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 For more information, see the [announcement blog post](https://devblogs.microsoft.com/foundry/introducing-microsoft-agent-framework-the-open-source-engine-for-agentic-ai-apps/).

-[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251209...HEAD
+[Unreleased]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251211...HEAD
+[1.0.0b251211]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251209...python-1.0.0b251211
 [1.0.0b251209]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251204...python-1.0.0b251209
 [1.0.0b251204]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251120...python-1.0.0b251204
 [1.0.0b251120]: https://github.com/microsoft/agent-framework/compare/python-1.0.0b251117...python-1.0.0b251120
@@ -4,7 +4,7 @@ description = "A2A integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -1,6 +1,6 @@
 [project]
 name = "agent-framework-ag-ui"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 description = "AG-UI protocol integration for Agent Framework"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -4,7 +4,7 @@ description = "Anthropic integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Azure AI Search integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -63,6 +63,8 @@ from azure.ai.agents.models import (
    McpTool,
    MessageDeltaChunk,
    MessageDeltaTextContent,
+    MessageDeltaTextFileCitationAnnotation,
+    MessageDeltaTextFilePathAnnotation,
    MessageDeltaTextUrlCitationAnnotation,
    MessageImageUrlParam,
    MessageInputContentBlock,
@@ -471,6 +473,45 @@ class AzureAIAgentClient(BaseChatClient):

        return url_citations

+    def _extract_file_path_contents(self, message_delta_chunk: MessageDeltaChunk) -> list[HostedFileContent]:
+        """Extract file references from MessageDeltaChunk annotations.
+
+        Code interpreter generates files that are referenced via file path or file citation
+        annotations in the message content. This method extracts those file IDs and returns
+        them as HostedFileContent objects.
+
+        Handles two annotation types:
+        - MessageDeltaTextFilePathAnnotation: Contains file_path.file_id
+        - MessageDeltaTextFileCitationAnnotation: Contains file_citation.file_id
+
+        Args:
+            message_delta_chunk: The message delta chunk to process
+
+        Returns:
+            List of HostedFileContent objects for any files referenced in annotations
+        """
+        file_contents: list[HostedFileContent] = []
+
+        for content in message_delta_chunk.delta.content:
+            if isinstance(content, MessageDeltaTextContent) and content.text and content.text.annotations:
+                for annotation in content.text.annotations:
+                    if isinstance(annotation, MessageDeltaTextFilePathAnnotation):
+                        # Extract file_id from the file_path annotation
+                        file_path = getattr(annotation, "file_path", None)
+                        if file_path is not None:
+                            file_id = getattr(file_path, "file_id", None)
+                            if file_id:
+                                file_contents.append(HostedFileContent(file_id=file_id))
+                    elif isinstance(annotation, MessageDeltaTextFileCitationAnnotation):
+                        # Extract file_id from the file_citation annotation
+                        file_citation = getattr(annotation, "file_citation", None)
+                        if file_citation is not None:
+                            file_id = getattr(file_citation, "file_id", None)
+                            if file_id:
+                                file_contents.append(HostedFileContent(file_id=file_id))
+
+        return file_contents
+
    def _get_real_url_from_citation_reference(
        self, citation_url: str, azure_search_tool_calls: list[dict[str, Any]]
    ) -> str:
@@ -530,6 +571,9 @@ class AzureAIAgentClient(BaseChatClient):
                        # Extract URL citations from the delta chunk
                        url_citations = self._extract_url_citations(event_data, azure_search_tool_calls)

+                        # Extract file path contents from code interpreter outputs
+                        file_contents = self._extract_file_path_contents(event_data)
+
                        # Create contents with citations if any exist
                        citation_content: list[Contents] = []
                        if event_data.text or url_citations:
@@ -538,6 +582,9 @@ class AzureAIAgentClient(BaseChatClient):
                                text_content_obj.annotations = url_citations
                            citation_content.append(text_content_obj)

+                        # Add file contents from file path annotations
+                        citation_content.extend(file_contents)
+
                        yield ChatResponseUpdate(
                            role=role,
                            contents=citation_content if citation_content else None,
@@ -4,7 +4,7 @@ description = "Azure AI Foundry integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -24,6 +24,7 @@ from agent_framework import (
    FunctionCallContent,
    FunctionResultContent,
    HostedCodeInterpreterTool,
+    HostedFileContent,
    HostedFileSearchTool,
    HostedMCPTool,
    HostedVectorStoreContent,
@@ -42,6 +43,8 @@ from azure.ai.agents.models import (
    FileInfo,
    MessageDeltaChunk,
    MessageDeltaTextContent,
+    MessageDeltaTextFileCitationAnnotation,
+    MessageDeltaTextFilePathAnnotation,
    MessageDeltaTextUrlCitationAnnotation,
    RequiredFunctionToolCall,
    RequiredMcpToolCall,
@@ -1362,6 +1365,108 @@ def test_azure_ai_chat_client_extract_url_citations_with_citations(mock_agents_c
    assert citation.annotated_regions[0].end_index == 20


+def test_azure_ai_chat_client_extract_file_path_contents_with_file_path_annotation(
+    mock_agents_client: MagicMock,
+) -> None:
+    """Test _extract_file_path_contents with MessageDeltaChunk containing file path annotation."""
+    chat_client = create_test_azure_ai_chat_client(mock_agents_client, agent_id="test-agent")
+
+    # Create mock file_path annotation
+    mock_file_path = MagicMock()
+    mock_file_path.file_id = "assistant-test-file-123"
+
+    mock_annotation = MagicMock(spec=MessageDeltaTextFilePathAnnotation)
+    mock_annotation.file_path = mock_file_path
+
+    # Create mock text content with annotations
+    mock_text = MagicMock()
+    mock_text.annotations = [mock_annotation]
+
+    mock_text_content = MagicMock(spec=MessageDeltaTextContent)
+    mock_text_content.text = mock_text
+
+    # Create mock delta
+    mock_delta = MagicMock()
+    mock_delta.content = [mock_text_content]
+
+    # Create mock MessageDeltaChunk
+    mock_chunk = MagicMock(spec=MessageDeltaChunk)
+    mock_chunk.delta = mock_delta
+
+    # Call the method
+    file_contents = chat_client._extract_file_path_contents(mock_chunk)
+
+    # Verify results
+    assert len(file_contents) == 1
+    assert isinstance(file_contents[0], HostedFileContent)
+    assert file_contents[0].file_id == "assistant-test-file-123"
+
+
+def test_azure_ai_chat_client_extract_file_path_contents_with_file_citation_annotation(
+    mock_agents_client: MagicMock,
+) -> None:
+    """Test _extract_file_path_contents with MessageDeltaChunk containing file citation annotation."""
+    chat_client = create_test_azure_ai_chat_client(mock_agents_client, agent_id="test-agent")
+
+    # Create mock file_citation annotation
+    mock_file_citation = MagicMock()
+    mock_file_citation.file_id = "cfile_test-citation-456"
+
+    mock_annotation = MagicMock(spec=MessageDeltaTextFileCitationAnnotation)
+    mock_annotation.file_citation = mock_file_citation
+
+    # Create mock text content with annotations
+    mock_text = MagicMock()
+    mock_text.annotations = [mock_annotation]
+
+    mock_text_content = MagicMock(spec=MessageDeltaTextContent)
+    mock_text_content.text = mock_text
+
+    # Create mock delta
+    mock_delta = MagicMock()
+    mock_delta.content = [mock_text_content]
+
+    # Create mock MessageDeltaChunk
+    mock_chunk = MagicMock(spec=MessageDeltaChunk)
+    mock_chunk.delta = mock_delta
+
+    # Call the method
+    file_contents = chat_client._extract_file_path_contents(mock_chunk)
+
+    # Verify results
+    assert len(file_contents) == 1
+    assert isinstance(file_contents[0], HostedFileContent)
+    assert file_contents[0].file_id == "cfile_test-citation-456"
+
+
+def test_azure_ai_chat_client_extract_file_path_contents_empty_annotations(
+    mock_agents_client: MagicMock,
+) -> None:
+    """Test _extract_file_path_contents with no annotations returns empty list."""
+    chat_client = create_test_azure_ai_chat_client(mock_agents_client, agent_id="test-agent")
+
+    # Create mock text content with no annotations
+    mock_text = MagicMock()
+    mock_text.annotations = []
+
+    mock_text_content = MagicMock(spec=MessageDeltaTextContent)
+    mock_text_content.text = mock_text
+
+    # Create mock delta
+    mock_delta = MagicMock()
+    mock_delta.content = [mock_text_content]
+
+    # Create mock MessageDeltaChunk
+    mock_chunk = MagicMock(spec=MessageDeltaChunk)
+    mock_chunk.delta = mock_delta
+
+    # Call the method
+    file_contents = chat_client._extract_file_path_contents(mock_chunk)
+
+    # Verify results
+    assert len(file_contents) == 0
+
+
 def get_weather(
    location: Annotated[str, Field(description="The location to get the weather for.")],
 ) -> str:
@@ -256,7 +256,7 @@ class DurableAIAgent(AgentProtocol):
            # This ensures each call gets its own conversation context
            session_key = str(self.context.new_uuid())
            session_id = AgentSessionId(name=self.agent_name, key=session_key)
-            logger.warning("[DurableAIAgent] No thread provided, created unique session_id: %s", session_id)
+            logger.debug("[DurableAIAgent] No thread provided, created unique session_id: %s", session_id)

        # Create entity ID from session ID
        entity_id = session_id.to_entity_id()
@@ -4,7 +4,7 @@ description = "Azure Functions integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "OpenAI ChatKit integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Copilot Studio integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -1,6 +1,5 @@
 # Copyright (c) Microsoft. All rights reserved.

-import json
 import logging
 import re
 import sys
@@ -19,9 +18,9 @@ from mcp.client.websocket import websocket_client
 from mcp.shared.context import RequestContext
 from mcp.shared.exceptions import McpError
 from mcp.shared.session import RequestResponder
-from pydantic import BaseModel, Field, create_model
+from pydantic import BaseModel, create_model

-from ._tools import AIFunction, HostedMCPSpecificApproval
+from ._tools import AIFunction, HostedMCPSpecificApproval, _build_pydantic_model_from_json_schema
 from ._types import (
    ChatMessage,
    Contents,
@@ -274,95 +273,26 @@ def _get_input_model_from_mcp_prompt(prompt: types.Prompt) -> type[BaseModel]:
    if not prompt.arguments:
        return create_model(f"{prompt.name}_input")

-    field_definitions: dict[str, Any] = {}
+    # Convert prompt arguments to JSON schema format
+    properties: dict[str, Any] = {}
+    required: list[str] = []
+
    for prompt_argument in prompt.arguments:
-        # For prompts, all arguments are typically required and string type
-        # unless specified otherwise in the prompt argument
-        python_type = str  # Default type for prompt arguments
-
-        # Create field definition for create_model
+        # For prompts, all arguments are typically string type unless specified otherwise
+        properties[prompt_argument.name] = {
+            "type": "string",
+            "description": prompt_argument.description if hasattr(prompt_argument, "description") else "",
+        }
        if prompt_argument.required:
-            field_definitions[prompt_argument.name] = (python_type, ...)
-        else:
-            field_definitions[prompt_argument.name] = (python_type, None)
+            required.append(prompt_argument.name)

-    return create_model(f"{prompt.name}_input", **field_definitions)
+    schema = {"properties": properties, "required": required}
+    return _build_pydantic_model_from_json_schema(prompt.name, schema)


 def _get_input_model_from_mcp_tool(tool: types.Tool) -> type[BaseModel]:
    """Creates a Pydantic model from a tools parameters."""
-    properties = tool.inputSchema.get("properties", None)
-    required = tool.inputSchema.get("required", [])
-    definitions = tool.inputSchema.get("$defs", {})
-
-    # Check if 'properties' is missing or not a dictionary
-    if not properties:
-        return create_model(f"{tool.name}_input")
-
-    def resolve_type(prop_details: dict[str, Any]) -> type:
-        """Resolve JSON Schema type to Python type, handling $ref."""
-        # Handle $ref by resolving the reference
-        if "$ref" in prop_details:
-            ref = prop_details["$ref"]
-            # Extract the reference path (e.g., "#/$defs/CustomerIdParam" -> "CustomerIdParam")
-            if ref.startswith("#/$defs/"):
-                def_name = ref.split("/")[-1]
-                if def_name in definitions:
-                    # Resolve the reference and use its type
-                    resolved = definitions[def_name]
-                    return resolve_type(resolved)
-            # If we can't resolve the ref, default to dict for safety
-            return dict
-
-        # Map JSON Schema types to Python types
-        json_type = prop_details.get("type", "string")
-        match json_type:
-            case "integer":
-                return int
-            case "number":
-                return float
-            case "boolean":
-                return bool
-            case "array":
-                return list
-            case "object":
-                return dict
-            case _:
-                return str  # default
-
-    field_definitions: dict[str, Any] = {}
-    for prop_name, prop_details in properties.items():
-        prop_details = json.loads(prop_details) if isinstance(prop_details, str) else prop_details
-
-        python_type = resolve_type(prop_details)
-        description = prop_details.get("description", "")
-
-        # Build field kwargs (description, array items schema, etc.)
-        field_kwargs: dict[str, Any] = {}
-        if description:
-            field_kwargs["description"] = description
-
-        # Preserve array items schema if present
-        if prop_details.get("type") == "array" and "items" in prop_details:
-            items_schema = prop_details["items"]
-            if items_schema and items_schema != {}:
-                field_kwargs["json_schema_extra"] = {"items": items_schema}
-
-        # Create field definition for create_model
-        if prop_name in required:
-            if field_kwargs:
-                field_definitions[prop_name] = (python_type, Field(**field_kwargs))
-            else:
-                field_definitions[prop_name] = (python_type, ...)
-        else:
-            default_value = prop_details.get("default", None)
-            field_kwargs["default"] = default_value
-            if field_kwargs and any(k != "default" for k in field_kwargs):
-                field_definitions[prop_name] = (python_type, Field(**field_kwargs))
-            else:
-                field_definitions[prop_name] = (python_type, default_value)
-
-    return create_model(f"{tool.name}_input", **field_definitions)
+    return _build_pydantic_model_from_json_schema(tool.name, tool.inputSchema)


 def _normalize_mcp_name(name: str) -> str:
@@ -25,7 +25,6 @@ from typing import (

 from opentelemetry.metrics import Histogram
 from pydantic import AnyUrl, BaseModel, Field, ValidationError, create_model
-from pydantic.fields import FieldInfo

 from ._logging import get_logger
 from ._serialization import SerializationMixin
@@ -932,6 +931,151 @@ TYPE_MAPPING = {
 }


+def _build_pydantic_model_from_json_schema(
+    model_name: str,
+    schema: Mapping[str, Any],
+) -> type[BaseModel]:
+    """Creates a Pydantic model from JSON Schema with support for $refs, nested objects, and typed arrays.
+
+    Args:
+        model_name: The name of the model to be created.
+        schema: The JSON Schema definition (should contain 'properties', 'required', '$defs', etc.).
+
+    Returns:
+        The dynamically created Pydantic model class.
+    """
+    properties = schema.get("properties")
+    required = schema.get("required", [])
+    definitions = schema.get("$defs", {})
+
+    # Check if 'properties' is missing or not a dictionary
+    if not properties:
+        return create_model(f"{model_name}_input")
+
+    def _resolve_type(prop_details: dict[str, Any], parent_name: str = "") -> type:
+        """Resolve JSON Schema type to Python type, handling $ref, nested objects, and typed arrays.
+
+        Args:
+            prop_details: The JSON Schema property details
+            parent_name: Name to use for creating nested models (for uniqueness)
+
+        Returns:
+            Python type annotation (could be int, str, list[str], or a nested Pydantic model)
+        """
+        # Handle $ref by resolving the reference
+        if "$ref" in prop_details:
+            ref = prop_details["$ref"]
+            # Extract the reference path (e.g., "#/$defs/CustomerIdParam" -> "CustomerIdParam")
+            if ref.startswith("#/$defs/"):
+                def_name = ref.split("/")[-1]
+                if def_name in definitions:
+                    # Resolve the reference and use its type
+                    resolved = definitions[def_name]
+                    return _resolve_type(resolved, def_name)
+            # If we can't resolve the ref, default to dict for safety
+            return dict
+
+        # Map JSON Schema types to Python types
+        json_type = prop_details.get("type", "string")
+        match json_type:
+            case "integer":
+                return int
+            case "number":
+                return float
+            case "boolean":
+                return bool
+            case "array":
+                # Handle typed arrays
+                items_schema = prop_details.get("items")
+                if items_schema and isinstance(items_schema, dict):
+                    # Recursively resolve the item type
+                    item_type = _resolve_type(items_schema, f"{parent_name}_item")
+                    # Return list[ItemType] instead of bare list
+                    return list[item_type]  # type: ignore
+                # If no items schema or invalid, return bare list
+                return list
+            case "object":
+                # Handle nested objects by creating a nested Pydantic model
+                nested_properties = prop_details.get("properties")
+                nested_required = prop_details.get("required", [])
+
+                if nested_properties and isinstance(nested_properties, dict):
+                    # Create the name for the nested model
+                    nested_model_name = f"{parent_name}_nested" if parent_name else "NestedModel"
+
+                    # Recursively build field definitions for the nested model
+                    nested_field_definitions: dict[str, Any] = {}
+                    for nested_prop_name, nested_prop_details in nested_properties.items():
+                        nested_prop_details = (
+                            json.loads(nested_prop_details)
+                            if isinstance(nested_prop_details, str)
+                            else nested_prop_details
+                        )
+
+                        nested_python_type = _resolve_type(
+                            nested_prop_details, f"{nested_model_name}_{nested_prop_name}"
+                        )
+                        nested_description = nested_prop_details.get("description", "")
+
+                        # Build field kwargs for nested property
+                        nested_field_kwargs: dict[str, Any] = {}
+                        if nested_description:
+                            nested_field_kwargs["description"] = nested_description
+
+                        # Create field definition
+                        if nested_prop_name in nested_required:
+                            nested_field_definitions[nested_prop_name] = (
+                                (
+                                    nested_python_type,
+                                    Field(**nested_field_kwargs),
+                                )
+                                if nested_field_kwargs
+                                else (nested_python_type, ...)
+                            )
+                        else:
+                            nested_field_kwargs["default"] = nested_prop_details.get("default", None)
+                            nested_field_definitions[nested_prop_name] = (
+                                nested_python_type,
+                                Field(**nested_field_kwargs),
+                            )
+
+                    # Create and return the nested Pydantic model
+                    return create_model(nested_model_name, **nested_field_definitions)  # type: ignore
+
+                # If no properties defined, return bare dict
+                return dict
+            case _:
+                return str  # default
+
+    field_definitions: dict[str, Any] = {}
+    for prop_name, prop_details in properties.items():
+        prop_details = json.loads(prop_details) if isinstance(prop_details, str) else prop_details
+
+        python_type = _resolve_type(prop_details, f"{model_name}_{prop_name}")
+        description = prop_details.get("description", "")
+
+        # Build field kwargs (description, etc.)
+        field_kwargs: dict[str, Any] = {}
+        if description:
+            field_kwargs["description"] = description
+
+        # Create field definition for create_model
+        if prop_name in required:
+            if field_kwargs:
+                field_definitions[prop_name] = (python_type, Field(**field_kwargs))
+            else:
+                field_definitions[prop_name] = (python_type, ...)
+        else:
+            default_value = prop_details.get("default", None)
+            field_kwargs["default"] = default_value
+            if field_kwargs and any(k != "default" for k in field_kwargs):
+                field_definitions[prop_name] = (python_type, Field(**field_kwargs))
+            else:
+                field_definitions[prop_name] = (python_type, default_value)
+
+    return create_model(f"{model_name}_input", **field_definitions)
+
+
 def _create_model_from_json_schema(tool_name: str, schema_json: Mapping[str, Any]) -> type[BaseModel]:
    """Creates a Pydantic model from a given JSON Schema.

@@ -948,29 +1092,8 @@ def _create_model_from_json_schema(tool_name: str, schema_json: Mapping[str, Any
            f"JSON schema for tool '{tool_name}' must contain a 'properties' key of type dict. "
            f"Got: {schema_json.get('properties', None)}"
        )
-    # Extract field definitions with type annotations
-    field_definitions: dict[str, tuple[type, FieldInfo]] = {}
-    for field_name, field_schema in schema_json["properties"].items():
-        field_args: dict[str, Any] = {}
-        if (field_description := field_schema.get("description", None)) is not None:
-            field_args["description"] = field_description
-        if (field_default := field_schema.get("default", None)) is not None:
-            field_args["default"] = field_default
-        field_type = field_schema.get("type", None)
-        if field_type is None:
-            raise ValueError(
-                f"Missing 'type' for field '{field_name}' in JSON schema. "
-                f"Got: {field_schema}, Supported types: {list(TYPE_MAPPING.keys())}"
-            )
-        python_type = TYPE_MAPPING.get(field_type)
-        if python_type is None:
-            raise ValueError(
-                f"Unsupported type '{field_type}' for field '{field_name}' in JSON schema. "
-                f"Got: {field_schema}, Supported types: {list(TYPE_MAPPING.keys())}"
-            )
-        field_definitions[field_name] = (python_type, Field(**field_args))

-    return create_model(f"{tool_name}_input", **field_definitions)  # type: ignore[call-overload, no-any-return]
+    return _build_pydantic_model_from_json_schema(tool_name, schema_json)


@overload
@@ -85,6 +85,7 @@ from ._magentic import (
    MagenticStallInterventionRequest,
    StandardMagenticManager,
 )
+from ._orchestration_request_info import AgentInputRequest, AgentResponseReviewRequest, RequestInfoInterceptor
 from ._orchestration_state import OrchestrationState
 from ._request_info_mixin import response_handler
 from ._runner import Runner
@@ -122,6 +123,8 @@ __all__ = [
    "AgentExecutor",
    "AgentExecutorRequest",
    "AgentExecutorResponse",
+    "AgentInputRequest",
+    "AgentResponseReviewRequest",
    "AgentRunEvent",
    "AgentRunUpdateEvent",
    "Case",
@@ -164,6 +167,7 @@ __all__ = [
    "Message",
    "OrchestrationState",
    "RequestInfoEvent",
+    "RequestInfoInterceptor",
    "Runner",
    "RunnerContext",
    "SequentialBuilder",
@@ -47,7 +47,9 @@ class BaseGroupChatOrchestrator(Executor, ABC):
        self._max_rounds: int | None = None
        self._termination_condition: Callable[[list[ChatMessage]], bool | Awaitable[bool]] | None = None

-    def register_participant_entry(self, name: str, *, entry_id: str, is_agent: bool) -> None:
+    def register_participant_entry(
+        self, name: str, *, entry_id: str, is_agent: bool, exit_id: str | None = None
+    ) -> None:
        """Record routing details for a participant's entry executor.

        This method provides a unified interface for registering participants
@@ -57,8 +59,10 @@ class BaseGroupChatOrchestrator(Executor, ABC):
            name: Participant name (used for selection and tracking)
            entry_id: Executor ID for this participant's entry point
            is_agent: Whether this is an AgentExecutor (True) or custom Executor (False)
+            exit_id: Executor ID for this participant's exit point (where responses come from).
+                    If None, defaults to entry_id.
        """
-        self._registry.register(name, entry_id=entry_id, is_agent=is_agent)
+        self._registry.register(name, entry_id=entry_id, is_agent=is_agent, exit_id=exit_id)

    # Conversation state management (shared across all patterns)

@@ -3,6 +3,7 @@
 import asyncio
 import inspect
 import logging
+import uuid
 from collections.abc import Callable, Sequence
 from typing import Any

@@ -14,6 +15,7 @@ from ._agent_executor import AgentExecutorRequest, AgentExecutorResponse
 from ._checkpoint import CheckpointStorage
 from ._executor import Executor, handler
 from ._message_utils import normalize_messages_input
+from ._orchestration_request_info import RequestInfoInterceptor
 from ._workflow import Workflow
 from ._workflow_builder import WorkflowBuilder
 from ._workflow_context import WorkflowContext
@@ -188,8 +190,11 @@ class ConcurrentBuilder:
    r"""High-level builder for concurrent agent workflows.

    - `participants([...])` accepts a list of AgentProtocol (recommended) or Executor.
+    - `register_participants([...])` accepts a list of factories for AgentProtocol (recommended)
+       or Executor factories
    - `build()` wires: dispatcher -> fan-out -> participants -> fan-in -> aggregator.
-    - `with_custom_aggregator(...)` overrides the default aggregator with an Executor or callback.
+    - `with_aggregator(...)` overrides the default aggregator with an Executor or callback.
+    - `register_aggregator(...)` accepts a factory for an Executor as custom aggregator.

    Usage:

@@ -200,24 +205,103 @@ class ConcurrentBuilder:
        # Minimal: use default aggregator (returns list[ChatMessage])
        workflow = ConcurrentBuilder().participants([agent1, agent2, agent3]).build()

+        # With agent factories
+        workflow = ConcurrentBuilder().register_participants([create_agent1, create_agent2, create_agent3]).build()
+

        # Custom aggregator via callback (sync or async). The callback receives
        # list[AgentExecutorResponse] and its return value becomes the workflow's output.
-        def summarize(results):
+        def summarize(results: list[AgentExecutorResponse]) -> str:
            return " | ".join(r.agent_run_response.messages[-1].text for r in results)


-        workflow = ConcurrentBuilder().participants([agent1, agent2, agent3]).with_custom_aggregator(summarize).build()
+        workflow = ConcurrentBuilder().participants([agent1, agent2, agent3]).with_aggregator(summarize).build()
+
+
+        # Custom aggregator via a factory
+        class MyAggregator(Executor):
+            @handler
+            async def aggregate(self, results: list[AgentExecutorResponse], ctx: WorkflowContext[Never, str]) -> None:
+                await ctx.yield_output(" | ".join(r.agent_run_response.messages[-1].text for r in results))
+
+
+        workflow = (
+            ConcurrentBuilder()
+            .register_participants([create_agent1, create_agent2, create_agent3])
+            .register_aggregator(lambda: MyAggregator(id="my_aggregator"))
+            .build()
+        )


        # Enable checkpoint persistence so runs can resume
        workflow = ConcurrentBuilder().participants([agent1, agent2, agent3]).with_checkpointing(storage).build()
+
+        # Enable request info before aggregation
+        workflow = ConcurrentBuilder().participants([agent1, agent2]).with_request_info().build()
    """

    def __init__(self) -> None:
        self._participants: list[AgentProtocol | Executor] = []
+        self._participant_factories: list[Callable[[], AgentProtocol | Executor]] = []
        self._aggregator: Executor | None = None
+        self._aggregator_factory: Callable[[], Executor] | None = None
        self._checkpoint_storage: CheckpointStorage | None = None
+        self._request_info_enabled: bool = False
+
+    def register_participants(
+        self,
+        participant_factories: Sequence[Callable[[], AgentProtocol | Executor]],
+    ) -> "ConcurrentBuilder":
+        r"""Define the parallel participants for this concurrent workflow.
+
+        Accepts factories (callables) that return AgentProtocol instances (e.g., created
+        by a chat client) or Executor instances. Each participant created by a factory
+        is wired as a parallel branch using fan-out edges from an internal dispatcher.
+
+        Args:
+            participant_factories: Sequence of callables returning AgentProtocol or Executor instances
+
+        Raises:
+            ValueError: if `participant_factories` is empty or `.participants()`
+                       or `.register_participants()` were already called
+
+        Example:
+
+        .. code-block:: python
+
+            def create_researcher() -> ChatAgent:
+                return ...
+
+
+            def create_marketer() -> ChatAgent:
+                return ...
+
+
+            def create_legal() -> ChatAgent:
+                return ...
+
+
+            class MyCustomExecutor(Executor): ...
+
+
+            wf = ConcurrentBuilder().register_participants([create_researcher, create_marketer, create_legal]).build()
+
+            # Mixing agent(s) and executor(s) is supported
+            wf2 = ConcurrentBuilder().register_participants([create_researcher, MyCustomExecutor]).build()
+        """
+        if self._participants:
+            raise ValueError(
+                "Cannot mix .participants([...]) and .register_participants() in the same builder instance."
+            )
+
+        if self._participant_factories:
+            raise ValueError("register_participants() has already been called on this builder instance.")
+
+        if not participant_factories:
+            raise ValueError("participant_factories cannot be empty")
+
+        self._participant_factories = list(participant_factories)
+        return self

    def participants(self, participants: Sequence[AgentProtocol | Executor]) -> "ConcurrentBuilder":
        r"""Define the parallel participants for this concurrent workflow.
@@ -226,8 +310,12 @@ class ConcurrentBuilder:
        instances. Each participant is wired as a parallel branch using fan-out edges
        from an internal dispatcher.

+        Args:
+            participants: Sequence of AgentProtocol or Executor instances
+
        Raises:
-            ValueError: if `participants` is empty or contains duplicates
+            ValueError: if `participants` is empty, contains duplicates, or `.register_participants()`
+                       or `.participants()` were already called
            TypeError: if any entry is not AgentProtocol or Executor

        Example:
@@ -239,6 +327,14 @@ class ConcurrentBuilder:
            # Mixing agent(s) and executor(s) is supported
            wf2 = ConcurrentBuilder().participants([researcher_agent, my_custom_executor]).build()
        """
+        if self._participant_factories:
+            raise ValueError(
+                "Cannot mix .participants([...]) and .register_participants() in the same builder instance."
+            )
+
+        if self._participants:
+            raise ValueError("participants() has already been called on this builder instance.")
+
        if not participants:
            raise ValueError("participants cannot be empty")

@@ -261,50 +357,140 @@ class ConcurrentBuilder:
        self._participants = list(participants)
        return self

-    def with_aggregator(self, aggregator: Executor | Callable[..., Any]) -> "ConcurrentBuilder":
-        r"""Override the default aggregator with an Executor or a callback.
+    def register_aggregator(self, aggregator_factory: Callable[[], Executor]) -> "ConcurrentBuilder":
+        r"""Define a custom aggregator for this concurrent workflow.

-        - Executor: must handle `list[AgentExecutorResponse]` and
-            yield output using `ctx.yield_output(...)` and add a
-          output and the workflow becomes idle.
+        Accepts a factory (callable) that returns an Executor instance. The executor
+        should handle `list[AgentExecutorResponse]` and yield output using `ctx.yield_output(...)`.
+
+        Args:
+            aggregator_factory: Callable that returns an Executor instance
+
+        Example:
+        .. code-block:: python
+
+            class MyCustomExecutor(Executor): ...
+
+
+            wf = (
+                ConcurrentBuilder()
+                .register_participants([create_researcher, create_marketer, create_legal])
+                .register_aggregator(lambda: MyCustomExecutor(id="my_aggregator"))
+                .build()
+            )
+        """
+        if self._aggregator is not None:
+            raise ValueError(
+                "Cannot mix .with_aggregator(...) and .register_aggregator(...) in the same builder instance."
+            )
+
+        if self._aggregator_factory is not None:
+            raise ValueError("register_aggregator() has already been called on this builder instance.")
+
+        self._aggregator_factory = aggregator_factory
+        return self
+
+    def with_aggregator(
+        self,
+        aggregator: Executor
+        | Callable[[list[AgentExecutorResponse]], Any]
+        | Callable[[list[AgentExecutorResponse], WorkflowContext[Never, Any]], Any],
+    ) -> "ConcurrentBuilder":
+        r"""Override the default aggregator with an executor, an executor factory, or a callback.
+
+        - Executor: must handle `list[AgentExecutorResponse]` and yield output using `ctx.yield_output(...)`
        - Callback: sync or async callable with one of the signatures:
          `(results: list[AgentExecutorResponse]) -> Any | None` or
          `(results: list[AgentExecutorResponse], ctx: WorkflowContext) -> Any | None`.
          If the callback returns a non-None value, it becomes the workflow's output.

+        Args:
+            aggregator: Executor instance, or callback function
+
        Example:

        .. code-block:: python
+            # Executor-based aggregator
+            class CustomAggregator(Executor):
+                @handler
+                async def aggregate(self, results: list[AgentExecutorResponse], ctx: WorkflowContext) -> None:
+                    await ctx.yield_output(" | ".join(r.agent_run_response.messages[-1].text for r in results))
+
+
+            wf = ConcurrentBuilder().participants([a1, a2, a3]).with_aggregator(CustomAggregator()).build()
+

            # Callback-based aggregator (string result)
-            async def summarize(results):
+            async def summarize(results: list[AgentExecutorResponse]) -> str:
                return " | ".join(r.agent_run_response.messages[-1].text for r in results)


-            wf = ConcurrentBuilder().participants([a1, a2, a3]).with_custom_aggregator(summarize).build()
+            wf = ConcurrentBuilder().participants([a1, a2, a3]).with_aggregator(summarize).build()
+
+
+            # Callback-based aggregator (yield result)
+            async def summarize(results: list[AgentExecutorResponse], ctx: WorkflowContext[Never, str]) -> None:
+                await ctx.yield_output(" | ".join(r.agent_run_response.messages[-1].text for r in results))
+
+
+            wf = ConcurrentBuilder().participants([a1, a2, a3]).with_aggregator(summarize).build()
        """
+        if self._aggregator_factory is not None:
+            raise ValueError(
+                "Cannot mix .with_aggregator(...) and .register_aggregator(...) in the same builder instance."
+            )
+
+        if self._aggregator is not None:
+            raise ValueError("with_aggregator() has already been called on this builder instance.")
+
        if isinstance(aggregator, Executor):
            self._aggregator = aggregator
        elif callable(aggregator):
            self._aggregator = _CallbackAggregator(aggregator)
        else:
            raise TypeError("aggregator must be an Executor or a callable")
+
        return self

    def with_checkpointing(self, checkpoint_storage: CheckpointStorage) -> "ConcurrentBuilder":
-        """Enable checkpoint persistence using the provided storage backend."""
+        """Enable checkpoint persistence using the provided storage backend.
+
+        Args:
+            checkpoint_storage: CheckpointStorage instance for persisting workflow state
+        """
        self._checkpoint_storage = checkpoint_storage
        return self

+    def with_request_info(self) -> "ConcurrentBuilder":
+        """Enable request info before aggregation in the workflow.
+
+        When enabled, the workflow pauses after all parallel agents complete,
+        emitting a RequestInfoEvent that allows the caller to review and optionally
+        modify the combined results before aggregation. The caller provides feedback
+        via the standard response_handler/request_info pattern.
+
+        Note:
+            Unlike SequentialBuilder and GroupChatBuilder, ConcurrentBuilder does not
+            support per-agent filtering since all agents run in parallel and results
+            are collected together. The pause occurs once with all agent outputs received.
+
+        Returns:
+            self: The builder instance for fluent chaining.
+        """
+        self._request_info_enabled = True
+        return self
+
    def build(self) -> Workflow:
        r"""Build and validate the concurrent workflow.

        Wiring pattern:
        - Dispatcher (internal) fans out the input to all `participants`
-        - Fan-in aggregator collects `AgentExecutorResponse` objects
+        - Fan-in collects `AgentExecutorResponse` objects from all participants
+        - If request info is enabled, the orchestration emits a request info event with outputs from all participants
+            before sending the outputs to the aggregator
        - Aggregator yields output and the workflow becomes idle. The output is either:
          - list[ChatMessage] (default aggregator: one user + one assistant per agent)
-          - custom payload from the provided callback/executor
+          - custom payload from the provided aggregator

        Returns:
            Workflow: a ready-to-run workflow instance
@@ -318,17 +504,69 @@ class ConcurrentBuilder:

            workflow = ConcurrentBuilder().participants([agent1, agent2]).build()
        """
-        if not self._participants:
-            raise ValueError("No participants provided. Call .participants([...]) first.")
+        if not self._participants and not self._participant_factories:
+            raise ValueError(
+                "No participants provided. Call .participants([...]) or .register_participants([...]) first."
+            )

+        # Internal nodes
        dispatcher = _DispatchToAllParticipants(id="dispatcher")
-        aggregator = self._aggregator or _AggregateAgentConversations(id="aggregator")
+        aggregator = (
+            self._aggregator
+            if self._aggregator is not None
+            else (
+                self._aggregator_factory()
+                if self._aggregator_factory is not None
+                else _AggregateAgentConversations(id="aggregator")
+            )
+        )

        builder = WorkflowBuilder()
-        builder.set_start_executor(dispatcher)
-        builder.add_fan_out_edges(dispatcher, list(self._participants))
-        builder.add_fan_in_edges(list(self._participants), aggregator)
+        if self._participant_factories:
+            # Register executors/agents to avoid warnings from the workflow builder
+            # if factories are provided instead of direct instances. This doesn't
+            # break the factory pattern since the concurrent builder still creates
+            # new instances per workflow build.
+            factory_names: list[str] = []
+            for factory in self._participant_factories:
+                factory_name = uuid.uuid4().hex
+                factory_names.append(factory_name)
+                instance = factory()
+                if isinstance(instance, Executor):
+                    builder.register_executor(lambda executor=instance: executor, name=factory_name)  # type: ignore[misc]
+                else:
+                    builder.register_agent(lambda agent=instance: agent, name=factory_name)  # type: ignore[misc]
+            # Register the dispatcher and the aggregator
+            builder.register_executor(lambda: dispatcher, name="dispatcher")
+            builder.register_executor(lambda: aggregator, name="aggregator")

+            builder.set_start_executor("dispatcher")
+            builder.add_fan_out_edges("dispatcher", factory_names)
+            if self._request_info_enabled:
+                # Insert interceptor between fan-in and aggregator
+                # participants -> fan-in -> interceptor -> aggregator
+                builder.register_executor(
+                    lambda: RequestInfoInterceptor(executor_id="request_info"),
+                    name="request_info_interceptor",
+                )
+                builder.add_fan_in_edges(factory_names, "request_info_interceptor")
+                builder.add_edge("request_info_interceptor", "aggregator")
+            else:
+                # Direct fan-in to aggregator
+                builder.add_fan_in_edges(factory_names, "aggregator")
+        else:
+            builder.set_start_executor(dispatcher)
+            builder.add_fan_out_edges(dispatcher, self._participants)
+
+            if self._request_info_enabled:
+                # Insert interceptor between fan-in and aggregator
+                # participants -> fan-in -> interceptor -> aggregator
+                request_info_interceptor = RequestInfoInterceptor(executor_id="request_info")
+                builder.add_fan_in_edges(self._participants, request_info_interceptor)
+                builder.add_edge(request_info_interceptor, aggregator)
+            else:
+                # Direct fan-in to aggregator
+                builder.add_fan_in_edges(self._participants, aggregator)
        if self._checkpoint_storage is not None:
            builder = builder.with_checkpointing(self._checkpoint_storage)

@@ -36,6 +36,7 @@ from ._base_group_chat_orchestrator import BaseGroupChatOrchestrator
 from ._checkpoint import CheckpointStorage
 from ._conversation_history import ensure_author, latest_user_message
 from ._executor import Executor, handler
+from ._orchestration_request_info import RequestInfoInterceptor
 from ._participant_utils import GroupChatParticipantSpec, prepare_participant_metadata, wrap_participant
 from ._workflow import Workflow
 from ._workflow_builder import WorkflowBuilder
@@ -131,7 +132,11 @@ class ManagerSelectionResponse(BaseModel):
        final_message: Optional final message string when finishing conversation (will be converted to ChatMessage)
    """

-    model_config = {"extra": "forbid"}
+    model_config = {
+        "extra": "forbid",
+        # OpenAI strict mode requires all properties to be in required array
+        "json_schema_extra": {"required": ["selected_participant", "instruction", "finish", "final_message"]},
+    }

    selected_participant: str | None = None
    instruction: str | None = None
@@ -562,14 +567,36 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
        participant_name: str,
        message: ChatMessage,
        ctx: WorkflowContext[AgentExecutorRequest | _GroupChatRequestMessage, list[ChatMessage]],
+        trailing_messages: list[ChatMessage] | None = None,
    ) -> None:
-        """Common response ingestion logic shared by agent and custom participants."""
+        """Common response ingestion logic shared by agent and custom participants.
+
+        Args:
+            participant_name: Name of the participant who sent the message
+            message: The participant's response message
+            ctx: Workflow context for routing and output
+            trailing_messages: Optional list of messages to inject after the participant's
+                message (e.g., additional input from the RequestInfoInterceptor)
+        """
        if participant_name not in self._participants:
            raise ValueError(f"Received response from unknown participant '{participant_name}'.")

        message = ensure_author(message, participant_name)
        self._conversation.extend((message,))
        self._history.append(_GroupChatTurn(participant_name, "agent", message))
+
+        # Inject any trailing messages (e.g., human input) into the conversation
+        if trailing_messages:
+            for trailing_msg in trailing_messages:
+                self._conversation.extend((trailing_msg,))
+                # Record as user input in history
+                author = trailing_msg.author_name or "human"
+                self._history.append(_GroupChatTurn(author, "user", trailing_msg))
+                logger.debug(
+                    f"Injected human input into group chat conversation: "
+                    f"{trailing_msg.text[:50] if trailing_msg.text else '(empty)'}..."
+                )
+
        self._pending_agent = None

        if await self._complete_on_termination(ctx):
@@ -685,14 +712,18 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
        to the selected participant. This method implements the core orchestration
        logic for agent-based managers.

+        Also handles any human input that was injected into the response's full_conversation
+        by the human input hook interceptor.
+
        Args:
            response: AgentExecutor response from manager agent
            ctx: Workflow context for routing and output

        Behavior:
+            - Extracts any human input from the response
            - Parses manager selection from response
            - If finish=True: yields final message and completes workflow
-            - If participant selected: routes request to that participant
+            - If participant selected: routes request to that participant with human input included
            - Validates selected participant exists
            - Enforces round limits if configured

@@ -700,6 +731,9 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
            ValueError: If manager selects invalid/unknown participant
            RuntimeError: If manager response cannot be parsed
        """
+        # Extract any human input that was injected by the human input hook
+        trailing_user_messages = self._extract_trailing_user_messages(response)
+
        selection = self._parse_manager_selection(response)

        if self._pending_finalization:
@@ -753,6 +787,19 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
            self._conversation.append(manager_message)
            self._history.append(_GroupChatTurn(self._manager_name, "manager", manager_message))

+        # Inject any human input that was attached to the manager's response
+        # This ensures the next participant sees the human's guidance
+        if trailing_user_messages:
+            for human_msg in trailing_user_messages:
+                conversation.append(human_msg)
+                self._conversation.append(human_msg)
+                author = human_msg.author_name or "human"
+                self._history.append(_GroupChatTurn(author, "user", human_msg))
+                logger.debug(
+                    f"Injected human input after manager selection: "
+                    f"{human_msg.text[:50] if human_msg.text else '(empty)'}..."
+                )
+
        if await self._complete_on_termination(ctx):
            return

@@ -808,6 +855,41 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
            )
        return ensure_author(final_message, participant_name)

+    @staticmethod
+    def _extract_trailing_user_messages(response: AgentExecutorResponse) -> list[ChatMessage]:
+        """Extract any user messages that appear after the last assistant message.
+
+        This is used to capture human input that was injected by the human input hook
+        interceptor. The hook adds user messages to full_conversation after the agent's
+        response, so they appear at the end of the sequence.
+
+        Args:
+            response: AgentExecutor response that may contain trailing user messages
+
+        Returns:
+            List of user messages that appear after the last assistant message,
+            or empty list if none found
+        """
+        if not response.full_conversation:
+            return []
+
+        # Find index of last assistant message
+        last_assistant_idx = -1
+        for i, msg in enumerate(response.full_conversation):
+            if msg.role == Role.ASSISTANT:
+                last_assistant_idx = i
+
+        if last_assistant_idx < 0:
+            return []
+
+        # Collect any user messages after the last assistant message
+        trailing_user: list[ChatMessage] = []
+        for msg in response.full_conversation[last_assistant_idx + 1 :]:
+            if msg.role == Role.USER:
+                trailing_user.append(msg)
+
+        return trailing_user
+
    async def _handle_task_message(
        self,
        task_message: ChatMessage,
@@ -979,6 +1061,9 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
        Routes responses based on whether they come from the manager or a participant:
        - Manager responses: parsed for speaker selection decisions
        - Participant responses: ingested as conversation messages
+
+        Also handles any human input that was injected into the response's full_conversation
+        by the human input hook interceptor.
        """
        participant_name = self._registry.get_participant_name(response.executor_id)
        if participant_name is None:
@@ -994,7 +1079,13 @@ class GroupChatOrchestratorExecutor(BaseGroupChatOrchestrator):
        else:
            # Regular participant response
            message = self._extract_agent_message(response, participant_name)
-            await self._ingest_participant_message(participant_name, message, ctx)
+
+            # Check for human input injected by human input hook
+            # Human input appears as user messages at the end of full_conversation
+            # after the agent's assistant message
+            trailing_user_messages = self._extract_trailing_user_messages(response)
+
+            await self._ingest_participant_message(participant_name, message, ctx, trailing_user_messages)


 def _default_orchestrator_factory(wiring: _GroupChatConfig) -> Executor:
@@ -1089,13 +1180,14 @@ def assemble_group_chat_workflow(
        manager_entry = manager_pipeline[0]
        manager_exit = manager_pipeline[-1]

-        # Register manager with orchestrator
+        # Register manager with orchestrator (with entry and exit IDs for pipeline routing)
        register_entry = getattr(orchestrator, "register_participant_entry", None)
        if callable(register_entry):
            register_entry(
                wiring.manager_name,
                entry_id=manager_entry.id,
                is_agent=not isinstance(wiring.manager_participant, Executor),
+                exit_id=manager_exit.id if manager_exit is not manager_entry else None,
            )

        # Wire manager edges: Orchestrator ↔ Manager
@@ -1118,10 +1210,13 @@ def assemble_group_chat_workflow(

        register_entry = getattr(orchestrator, "register_participant_entry", None)
        if callable(register_entry):
+            # Register both entry and exit IDs so responses can be routed correctly
+            # when interceptors are prepended to the pipeline
            register_entry(
                name,
                entry_id=entry_executor.id,
                is_agent=not isinstance(spec.participant, Executor),
+                exit_id=exit_executor.id if exit_executor is not entry_executor else None,
            )

        workflow_builder = workflow_builder.add_edge(orchestrator, entry_executor)
@@ -1213,6 +1308,30 @@ class GroupChatBuilder:
            .build()
        )

+    *Pattern 3: Request info for mid-conversation feedback*
+
+    .. code-block:: python
+
+        from agent_framework import GroupChatBuilder
+
+        # Pause before all participants
+        workflow = (
+            GroupChatBuilder()
+            .set_select_speakers_func(select_next_speaker)
+            .participants([researcher, writer])
+            .with_request_info()
+            .build()
+        )
+
+        # Pause only before specific participants
+        workflow = (
+            GroupChatBuilder()
+            .set_select_speakers_func(select_next_speaker)
+            .participants([researcher, writer, editor])
+            .with_request_info(agents=[editor])  # Only pause before editor responds
+            .build()
+        )
+
    **Participant Specification:**

    Two ways to specify participants:
@@ -1262,6 +1381,8 @@ class GroupChatBuilder:
        self._interceptors: list[_InterceptorSpec] = []
        self._orchestrator_factory = group_chat_orchestrator(_orchestrator_factory)
        self._participant_factory = _participant_factory or _default_participant_factory
+        self._request_info_enabled: bool = False
+        self._request_info_filter: set[str] | None = None

    def _set_manager_function(
        self,
@@ -1338,6 +1459,12 @@ class GroupChatBuilder:
        Note:
            The manager agent's response_format must be ManagerSelectionResponse for structured output.
            Custom response formats raise ValueError instead of being overridden.
+
+            The manager can be included in :py:meth:`with_request_info` to pause before the manager
+            runs, allowing human steering of orchestration decisions. If no filter is specified,
+            the manager is included automatically. To filter explicitly::
+
+                .with_request_info(agents=[manager, writer])  # Pause before manager and writer
        """
        if self._manager is not None or self._manager_participant is not None:
            raise ValueError(
@@ -1668,6 +1795,54 @@ class GroupChatBuilder:
        self._max_rounds = max_rounds
        return self

+    def with_request_info(
+        self,
+        *,
+        agents: Sequence[str | AgentProtocol | Executor] | None = None,
+    ) -> "GroupChatBuilder":
+        """Enable request info before participants run in the workflow.
+
+        When enabled, the workflow pauses before each participant runs, emitting
+        a RequestInfoEvent that allows the caller to review the conversation and
+        optionally inject guidance before the participant responds. The caller provides
+        input via the standard response_handler/request_info pattern.
+
+        Args:
+            agents: Optional filter - only pause before these specific agents/executors.
+                   Accepts agent names (str), agent instances, or executor instances.
+                   If None (default), pauses before every participant.
+
+        Returns:
+            self: The builder instance for fluent chaining.
+
+        Example:
+
+        .. code-block:: python
+
+            # Pause before all participants
+            workflow = (
+                GroupChatBuilder()
+                .set_manager(manager)
+                .participants([optimist, pragmatist, creative])
+                .with_request_info()
+                .build()
+            )
+
+            # Pause only before specific participants
+            workflow = (
+                GroupChatBuilder()
+                .set_manager(manager)
+                .participants([optimist, pragmatist, creative])
+                .with_request_info(agents=[pragmatist])  # Only pause before pragmatist
+                .build()
+            )
+        """
+        from ._orchestration_request_info import resolve_request_info_filter
+
+        self._request_info_enabled = True
+        self._request_info_filter = resolve_request_info_filter(list(agents) if agents else None)
+        return self
+
    def _get_participant_metadata(self) -> dict[str, Any]:
        if self._participant_metadata is None:
            self._participant_metadata = prepare_participant_metadata(
@@ -1754,9 +1929,32 @@ class GroupChatBuilder:
            participant_executors=metadata["executors"],
        )

+        # Determine participant factory - wrap if request info is enabled
+        participant_factory = self._participant_factory
+        if self._request_info_enabled:
+            # Create a wrapper factory that adds request info interceptor before each participant
+            base_factory = participant_factory
+            agent_filter = self._request_info_filter
+
+            def _factory_with_request_info(
+                spec: GroupChatParticipantSpec,
+                config: _GroupChatConfig,
+            ) -> _GroupChatParticipantPipeline:
+                pipeline = list(base_factory(spec, config))
+                if pipeline:
+                    # Add interceptor executor BEFORE the participant (prepend)
+                    interceptor = RequestInfoInterceptor(
+                        executor_id=f"request_info:{spec.name}",
+                        agent_filter=agent_filter,
+                    )
+                    pipeline.insert(0, interceptor)
+                return tuple(pipeline)
+
+            participant_factory = _factory_with_request_info
+
        result = assemble_group_chat_workflow(
            wiring=wiring,
-            participant_factory=self._participant_factory,
+            participant_factory=participant_factory,
            orchestrator_factory=self._orchestrator_factory,
            interceptors=self._interceptors,
            checkpoint_storage=self._checkpoint_storage,
@@ -45,8 +45,10 @@ from ._executor import Executor, handler
 from ._group_chat import (
    _default_participant_factory,  # type: ignore[reportPrivateUsage]
    _GroupChatConfig,  # type: ignore[reportPrivateUsage]
+    _GroupChatParticipantPipeline,  # type: ignore[reportPrivateUsage]
    assemble_group_chat_workflow,
 )
+from ._orchestration_request_info import RequestInfoInterceptor
 from ._orchestrator_helpers import clean_conversation_for_handoff
 from ._participant_utils import GroupChatParticipantSpec, prepare_participant_metadata, sanitize_identifier
 from ._request_info_mixin import response_handler
@@ -315,6 +317,30 @@ class _HandoffCoordinator(BaseGroupChatOrchestrator):
        """Get the coordinator name for orchestrator-generated messages."""
        return "handoff_coordinator"

+    def _extract_agent_id_from_source(self, source: str | None) -> str | None:
+        """Extract the original agent ID from the source executor ID.
+
+        When a request info interceptor is in the pipeline, the source will be
+        like 'request_info:agent_name'. This method extracts the
+        actual agent ID.
+
+        Args:
+            source: The source executor ID from the workflow context
+
+        Returns:
+            The actual agent ID, or the original source if not an interceptor
+        """
+        if source is None:
+            return None
+        if source.startswith("request_info:"):
+            return source[len("request_info:") :]
+        # TODO(@moonbox3): Remove legacy prefix support in a separate PR (GA cleanup)
+        if source.startswith("human_review:"):
+            return source[len("human_review:") :]
+        if source.startswith("human_input_interceptor:"):
+            return source[len("human_input_interceptor:") :]
+        return source
+
    @handler
    async def handle_agent_response(
        self,
@@ -322,7 +348,8 @@ class _HandoffCoordinator(BaseGroupChatOrchestrator):
        ctx: WorkflowContext[AgentExecutorRequest | list[ChatMessage], list[ChatMessage] | _ConversationForUserInput],
    ) -> None:
        """Process an agent's response and determine whether to route, request input, or terminate."""
-        source = ctx.get_source_executor_id()
+        raw_source = ctx.get_source_executor_id()
+        source = self._extract_agent_id_from_source(raw_source)
        is_starting_agent = source == self._starting_agent_id

        # On first turn of a run, conversation is empty
@@ -400,8 +427,8 @@ class _HandoffCoordinator(BaseGroupChatOrchestrator):
        cleaned_for_display = clean_conversation_for_handoff(conversation)

        # The awaiting_agent_id is the agent that just responded and is awaiting user input
-        # This is the source of the current response
-        next_agent_id = source
+        # This is the source of the current response (fallback to starting agent if source is unknown)
+        next_agent_id = source or self._starting_agent_id

        message_to_gateway = _ConversationForUserInput(conversation=cleaned_for_display, next_agent_id=next_agent_id)
        await ctx.send_message(message_to_gateway, target_id=self._input_gateway_id)  # type: ignore[arg-type]
@@ -826,6 +853,8 @@ class HandoffBuilder:
        self._return_to_previous: bool = False
        self._interaction_mode: Literal["human_in_loop", "autonomous"] = "human_in_loop"
        self._autonomous_turn_limit: int | None = _DEFAULT_AUTONOMOUS_TURN_LIMIT
+        self._request_info_enabled: bool = False
+        self._request_info_filter: set[str] | None = None

        if participants:
            self.participants(participants)
@@ -1418,6 +1447,52 @@ class HandoffBuilder:
        self._return_to_previous = enabled
        return self

+    def with_request_info(
+        self,
+        *,
+        agents: Sequence[str | AgentProtocol | Executor] | None = None,
+    ) -> "HandoffBuilder":
+        """Enable request info before participants run in the workflow.
+
+        When enabled, the workflow pauses before each participant runs, emitting
+        a RequestInfoEvent that allows the caller to review the conversation and
+        optionally inject guidance before the participant responds. The caller provides
+        input via the standard response_handler/request_info pattern.
+
+        Args:
+            agents: Optional filter - only pause before these specific agents/executors.
+                   Accepts agent names (str), agent instances, or executor instances.
+                   If None (default), pauses before every participant.
+
+        Returns:
+            self: The builder instance for fluent chaining.
+
+        Example:
+
+        .. code-block:: python
+
+            # Pause before all participants
+            workflow = (
+                HandoffBuilder(participants=[coordinator, refund, shipping])
+                .set_coordinator("coordinator_agent")
+                .with_request_info()
+                .build()
+            )
+
+            # Pause only before specialist agents (not coordinator)
+            workflow = (
+                HandoffBuilder(participants=[coordinator, refund, shipping])
+                .set_coordinator("coordinator_agent")
+                .with_request_info(agents=[refund, shipping])
+                .build()
+            )
+        """
+        from ._orchestration_request_info import resolve_request_info_filter
+
+        self._request_info_enabled = True
+        self._request_info_filter = resolve_request_info_filter(list(agents) if agents else None)
+        return self
+
    def build(self) -> Workflow:
        """Construct the final Workflow instance from the configured builder.

@@ -1562,9 +1637,33 @@ class HandoffBuilder:
            participant_executors=self._executors,
        )

+        # Determine participant factory - wrap with request info interceptor if enabled
+        participant_factory: Callable[[GroupChatParticipantSpec, _GroupChatConfig], _GroupChatParticipantPipeline] = (
+            _default_participant_factory
+        )
+        if self._request_info_enabled:
+            base_factory = _default_participant_factory
+            agent_filter = self._request_info_filter
+
+            def _factory_with_request_info(
+                spec: GroupChatParticipantSpec,
+                config: _GroupChatConfig,
+            ) -> _GroupChatParticipantPipeline:
+                pipeline = list(base_factory(spec, config))
+                if pipeline:
+                    # Add interceptor executor BEFORE the participant (prepend)
+                    interceptor = RequestInfoInterceptor(
+                        executor_id=f"request_info:{spec.name}",
+                        agent_filter=agent_filter,
+                    )
+                    pipeline.insert(0, interceptor)
+                return tuple(pipeline)
+
+            participant_factory = _factory_with_request_info
+
        result = assemble_group_chat_workflow(
            wiring=wiring,
-            participant_factory=_default_participant_factory,
+            participant_factory=participant_factory,
            orchestrator_factory=_handoff_orchestrator_factory,
            interceptors=(),
            checkpoint_storage=self._checkpoint_storage,
@@ -1575,7 +1674,18 @@ class HandoffBuilder:
            raise TypeError("Expected tuple from assemble_group_chat_workflow with return_builder=True")
        builder, coordinator = result

-        builder = builder.add_edge(input_node, starting_executor)
+        # When request_info is enabled, the input should go through the interceptor first
+        if self._request_info_enabled:
+            # Get the entry executor from the builder's registered executors
+            starting_entry_id = f"request_info:{self._starting_agent_id}"
+            starting_entry_executor = builder._executors.get(starting_entry_id)  # type: ignore
+            if starting_entry_executor:
+                builder = builder.add_edge(input_node, starting_entry_executor)
+            else:
+                # Fallback to direct connection if interceptor not found
+                builder = builder.add_edge(input_node, starting_executor)
+        else:
+            builder = builder.add_edge(input_node, starting_executor)
        builder = builder.add_edge(coordinator, user_gateway)
        builder = builder.add_edge(user_gateway, coordinator)

@@ -2089,6 +2089,17 @@ class MagenticBuilder:
    The builder provides a fluent API for configuring participants, the manager, optional
    plan review, checkpointing, and event callbacks.

+    Human-in-the-loop Support:
+        Magentic provides specialized HITL mechanisms via:
+
+        - `.with_plan_review()` - Review and approve/revise plans before execution
+        - `.with_human_input_on_stall()` - Intervene when workflow stalls
+        - Tool approval via `FunctionApprovalRequestContent` - Approve individual tool calls
+
+        These emit `MagenticHumanInterventionRequest` events that provide structured
+        decision options (APPROVE, REVISE, CONTINUE, REPLAN, GUIDANCE) appropriate
+        for Magentic's planning-based orchestration.
+
    Usage:

    .. code-block:: python
@@ -0,0 +1,329 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Request info support for high-level builder APIs.
+
+This module provides a mechanism for pausing workflows to request external input
+before agent turns in `SequentialBuilder`, `ConcurrentBuilder`, `GroupChatBuilder`,
+and `HandoffBuilder`.
+
+The design follows the standard `request_info` pattern used throughout the
+workflow system, keeping the API consistent and predictable.
+
+Key components:
+- AgentInputRequest: Request type emitted via RequestInfoEvent for pre-agent steering
+- RequestInfoInterceptor: Internal executor that pauses workflow before agent runs
+"""
+
+import logging
+import uuid
+from dataclasses import dataclass, field
+from typing import Any
+
+from .._agents import AgentProtocol
+from .._types import ChatMessage, Role
+from ._agent_executor import AgentExecutorRequest
+from ._executor import Executor, handler
+from ._request_info_mixin import response_handler
+from ._workflow_context import WorkflowContext
+
+logger = logging.getLogger(__name__)
+
+
+def resolve_request_info_filter(
+    agents: list[str | AgentProtocol | Executor] | None,
+) -> set[str] | None:
+    """Resolve a list of agent/executor references to a set of IDs for filtering.
+
+    Args:
+        agents: List of agent names (str), AgentProtocol instances, or Executor instances.
+                If None, returns None (meaning no filtering - pause for all).
+
+    Returns:
+        Set of executor/agent IDs to filter on, or None if no filtering.
+    """
+    if agents is None:
+        return None
+
+    result: set[str] = set()
+    for agent in agents:
+        if isinstance(agent, str):
+            result.add(agent)
+        elif isinstance(agent, Executor):
+            result.add(agent.id)
+        elif isinstance(agent, AgentProtocol):
+            name = getattr(agent, "name", None)
+            if name:
+                result.add(name)
+            else:
+                logger.warning("AgentProtocol without name cannot be used for request_info filtering")
+        else:
+            logger.warning(f"Unsupported type for request_info filter: {type(agent).__name__}")
+
+    return result if result else None
+
+
+@dataclass
+class AgentInputRequest:
+    """Request for human input before an agent runs in high-level builder workflows.
+
+    Emitted via RequestInfoEvent when a workflow pauses before an agent executes.
+    The response is injected into the conversation as a user message to steer
+    the agent's behavior.
+
+    This is the standard request type used by `.with_request_info()` on
+    SequentialBuilder, ConcurrentBuilder, GroupChatBuilder, and HandoffBuilder.
+
+    Attributes:
+        target_agent_id: ID of the agent that is about to run
+        conversation: Current conversation history the agent will receive
+        instruction: Optional instruction from the orchestrator (e.g., manager in GroupChat)
+        metadata: Builder-specific context (stores internal state for resume)
+    """
+
+    target_agent_id: str | None
+    conversation: list[ChatMessage] = field(default_factory=lambda: [])
+    instruction: str | None = None
+    metadata: dict[str, Any] = field(default_factory=lambda: {})
+
+
+# Keep legacy name as alias for backward compatibility
+AgentResponseReviewRequest = AgentInputRequest
+
+
+DEFAULT_REQUEST_INFO_ID = "request_info_interceptor"
+
+
+class RequestInfoInterceptor(Executor):
+    """Internal executor that pauses workflow for human input before agent runs.
+
+    This executor is inserted into the workflow graph by builders when
+    `.with_request_info()` is called. It intercepts AgentExecutorRequest messages
+    BEFORE the agent runs and pauses the workflow via `ctx.request_info()` with
+    an AgentInputRequest.
+
+    When a response is received, the response handler injects the input
+    as a user message into the conversation and forwards the request to the agent.
+
+    The optional `agent_filter` parameter allows limiting which agents trigger the pause.
+    If the target agent's ID is not in the filter set, the request is forwarded
+    without pausing.
+    """
+
+    def __init__(
+        self,
+        executor_id: str | None = None,
+        agent_filter: set[str] | None = None,
+    ) -> None:
+        """Initialize the request info interceptor executor.
+
+        Args:
+            executor_id: ID for this executor. If None, generates a unique ID
+                        using the format "request_info_interceptor-<uuid4>".
+            agent_filter: Optional set of agent/executor IDs to filter on.
+                         If provided, only requests to these agents trigger a pause.
+                         If None (default), all requests trigger a pause.
+        """
+        if executor_id is None:
+            executor_id = f"{DEFAULT_REQUEST_INFO_ID}-{uuid.uuid4().hex[:8]}"
+        super().__init__(executor_id)
+        self._agent_filter = agent_filter
+
+    def _should_pause_for_agent(self, agent_id: str | None) -> bool:
+        """Check if we should pause for the given agent ID."""
+        if self._agent_filter is None:
+            return True
+        if agent_id is None:
+            return False
+        # Check both the full ID and any name portion after a prefix
+        # e.g., "groupchat_agent:writer" should match filter "writer"
+        if agent_id in self._agent_filter:
+            return True
+        # Extract name from prefixed IDs like "groupchat_agent:writer" or "request_info:writer"
+        if ":" in agent_id:
+            name_part = agent_id.split(":", 1)[1]
+            if name_part in self._agent_filter:
+                return True
+        return False
+
+    def _extract_agent_name_from_executor_id(self) -> str | None:
+        """Extract the agent name from this interceptor's executor ID.
+
+        The interceptor ID is typically "request_info:<agent_name>", so we
+        extract the agent name to determine which agent we're intercepting for.
+        """
+        if ":" in self.id:
+            return self.id.split(":", 1)[1]
+        return None
+
+    @handler
+    async def intercept_agent_request(
+        self,
+        request: AgentExecutorRequest,
+        ctx: WorkflowContext[AgentExecutorRequest, Any],
+    ) -> None:
+        """Intercept request before agent runs and pause for human input.
+
+        Pauses the workflow and emits a RequestInfoEvent with the current
+        conversation for steering. If an agent filter is configured and this
+        agent is not in the filter, the request is forwarded without pausing.
+
+        Args:
+            request: The request about to be sent to the agent
+            ctx: Workflow context for requesting info
+        """
+        # Determine the target agent from our executor ID
+        target_agent = self._extract_agent_name_from_executor_id()
+
+        # Check if we should pause for this agent
+        if not self._should_pause_for_agent(target_agent):
+            logger.debug(f"Skipping request_info pause for agent {target_agent} (not in filter)")
+            await ctx.send_message(request)
+            return
+
+        conversation = list(request.messages or [])
+
+        input_request = AgentInputRequest(
+            target_agent_id=target_agent,
+            conversation=conversation,
+            instruction=None,  # Could be extended to include manager instruction
+            metadata={"_original_request": request, "_input_type": "AgentExecutorRequest"},
+        )
+        await ctx.request_info(input_request, str)
+
+    @handler
+    async def intercept_conversation(
+        self,
+        messages: list[ChatMessage],
+        ctx: WorkflowContext[list[ChatMessage], Any],
+    ) -> None:
+        """Intercept conversation before agent runs (used by SequentialBuilder).
+
+        SequentialBuilder passes list[ChatMessage] directly to agents. This handler
+        intercepts that flow and pauses for human input.
+
+        Args:
+            messages: The conversation about to be sent to the agent
+            ctx: Workflow context for requesting info
+        """
+        # Determine the target agent from our executor ID
+        target_agent = self._extract_agent_name_from_executor_id()
+
+        # Check if we should pause for this agent
+        if not self._should_pause_for_agent(target_agent):
+            logger.debug(f"Skipping request_info pause for agent {target_agent} (not in filter)")
+            await ctx.send_message(messages)
+            return
+
+        input_request = AgentInputRequest(
+            target_agent_id=target_agent,
+            conversation=list(messages),
+            instruction=None,
+            metadata={"_original_messages": messages, "_input_type": "list[ChatMessage]"},
+        )
+        await ctx.request_info(input_request, str)
+
+    @handler
+    async def intercept_concurrent_requests(
+        self,
+        requests: list[AgentExecutorRequest],
+        ctx: WorkflowContext[list[AgentExecutorRequest], Any],
+    ) -> None:
+        """Intercept requests before concurrent agents run.
+
+        This handler is used by ConcurrentBuilder to get human input before
+        all parallel agents execute.
+
+        Args:
+            requests: List of requests for all concurrent agents
+            ctx: Workflow context for requesting info
+        """
+        # Combine conversations for display
+        combined_conversation: list[ChatMessage] = []
+        if requests:
+            combined_conversation = list(requests[0].messages or [])
+
+        input_request = AgentInputRequest(
+            target_agent_id=None,  # Multiple agents
+            conversation=combined_conversation,
+            instruction=None,
+            metadata={"_original_requests": requests},
+        )
+        await ctx.request_info(input_request, str)
+
+    @response_handler
+    async def handle_input_response(
+        self,
+        original_request: AgentInputRequest,
+        # TODO(@moonbox3): Extend to support other content types
+        response: str,
+        ctx: WorkflowContext[AgentExecutorRequest | list[ChatMessage], Any],
+    ) -> None:
+        """Handle the human input and forward the modified request to the agent.
+
+        Injects the response as a user message into the conversation
+        and forwards the modified request to the agent.
+
+        Args:
+            original_request: The AgentInputRequest that triggered the pause
+            response: The human input text
+            ctx: Workflow context for continuing the workflow
+
+        TODO: Consider having each orchestration implement its own response handler
+              for more specialized behavior.
+        """
+        human_message = ChatMessage(role=Role.USER, text=response)
+
+        # Handle concurrent case (list of AgentExecutorRequest)
+        original_requests: list[AgentExecutorRequest] | None = original_request.metadata.get("_original_requests")
+        if original_requests is not None:
+            updated_requests: list[AgentExecutorRequest] = []
+            for orig_req in original_requests:
+                messages = list(orig_req.messages or [])
+                messages.append(human_message)
+                updated_requests.append(
+                    AgentExecutorRequest(
+                        messages=messages,
+                        should_respond=orig_req.should_respond,
+                    )
+                )
+
+            logger.debug(
+                f"Human input received for concurrent workflow, "
+                f"continuing with {len(updated_requests)} updated requests"
+            )
+            await ctx.send_message(updated_requests)  # type: ignore[arg-type]
+            return
+
+        # Handle list[ChatMessage] case (SequentialBuilder)
+        original_messages: list[ChatMessage] | None = original_request.metadata.get("_original_messages")
+        if original_messages is not None:
+            messages = list(original_messages)
+            messages.append(human_message)
+
+            logger.debug(
+                f"Human input received for agent {original_request.target_agent_id}, "
+                f"forwarding conversation with steering context"
+            )
+            await ctx.send_message(messages)
+            return
+
+        # Handle AgentExecutorRequest case (GroupChatBuilder)
+        orig_request: AgentExecutorRequest | None = original_request.metadata.get("_original_request")
+        if orig_request is not None:
+            messages = list(orig_request.messages or [])
+            messages.append(human_message)
+
+            updated_request = AgentExecutorRequest(
+                messages=messages,
+                should_respond=orig_request.should_respond,
+            )
+
+            logger.debug(
+                f"Human input received for agent {original_request.target_agent_id}, "
+                f"forwarding request with steering context"
+            )
+            await ctx.send_message(updated_request)
+            return
+
+        logger.error("Input response handler missing original request/messages in metadata")
+        raise RuntimeError("Missing original request or messages in AgentInputRequest metadata")
@@ -140,6 +140,9 @@ class ParticipantRegistry:

    Provides a clean interface for the common pattern of mapping participant names
    to executor IDs and tracking which are agents vs custom executors.
+
+    Tracks both entry IDs (where to send requests) and exit IDs (where responses
+    come from) to support pipeline configurations where these differ.
    """

    def __init__(self) -> None:
@@ -154,19 +157,26 @@ class ParticipantRegistry:
        *,
        entry_id: str,
        is_agent: bool,
+        exit_id: str | None = None,
    ) -> None:
        """Register a participant's routing information.

        Args:
            name: Participant name
-            entry_id: Executor ID for this participant's entry point
+            entry_id: Executor ID for this participant's entry point (where to send)
            is_agent: Whether this is an AgentExecutor (True) or custom Executor (False)
+            exit_id: Executor ID for this participant's exit point (where responses come from).
+                    If None, defaults to entry_id (single-executor pipeline).
        """
        self._participant_entry_ids[name] = entry_id
+        actual_exit_id = exit_id if exit_id is not None else entry_id

        if is_agent:
            self._agent_executor_ids[name] = entry_id
+            # Map both entry and exit IDs to participant name for response routing
            self._executor_id_to_participant[entry_id] = name
+            if actual_exit_id != entry_id:
+                self._executor_id_to_participant[actual_exit_id] = name
        else:
            self._non_agent_participants.add(name)

@@ -37,7 +37,7 @@ confusion and to mirror how the concurrent builder uses explicit dispatcher/aggr
 """  # noqa: E501

 import logging
-from collections.abc import Sequence
+from collections.abc import Callable, Sequence
 from typing import Any

 from agent_framework import AgentProtocol, ChatMessage
@@ -52,6 +52,7 @@ from ._executor import (
    handler,
 )
 from ._message_utils import normalize_messages_input
+from ._orchestration_request_info import RequestInfoInterceptor
 from ._workflow import Workflow
 from ._workflow_builder import WorkflowBuilder
 from ._workflow_context import WorkflowContext
@@ -71,14 +72,8 @@ class _InputToConversation(Executor):
        await ctx.send_message(normalize_messages_input(message))

    @handler
-    async def from_messages(
-        self,
-        messages: list[str | ChatMessage],
-        ctx: WorkflowContext[list[ChatMessage]],
-    ) -> None:
-        # Make a copy to avoid mutation downstream
-        normalized = normalize_messages_input(messages)
-        await ctx.send_message(list(normalized))
+    async def from_messages(self, messages: list[str | ChatMessage], ctx: WorkflowContext[list[ChatMessage]]) -> None:
+        await ctx.send_message(normalize_messages_input(messages))


 class _ResponseToConversation(Executor):
@@ -103,7 +98,10 @@ class _EndWithConversation(Executor):
 class SequentialBuilder:
    r"""High-level builder for sequential agent/executor workflows with shared context.

-    - `participants([...])` accepts a list of AgentProtocol (recommended) or Executor
+    - `participants([...])` accepts a list of AgentProtocol (recommended) or Executor instances
+    - `register_participants([...])` accepts a list of factories for AgentProtocol (recommended)
+       or Executor factories
+    - Executors must define a handler that consumes list[ChatMessage] and sends out a list[ChatMessage]
    - The workflow wires participants in order, passing a list[ChatMessage] down the chain
    - Agents append their assistant messages to the conversation
    - Custom executors can transform/summarize and return a list[ChatMessage]
@@ -115,15 +113,51 @@ class SequentialBuilder:

        from agent_framework import SequentialBuilder

+        # With agent instances
        workflow = SequentialBuilder().participants([agent1, agent2, summarizer_exec]).build()

+        # With agent factories
+        workflow = (
+            SequentialBuilder().register_participants([create_agent1, create_agent2, create_summarizer_exec]).build()
+        )
+
        # Enable checkpoint persistence
        workflow = SequentialBuilder().participants([agent1, agent2]).with_checkpointing(storage).build()
+
+        # Enable request info for mid-workflow feedback (pauses before each agent)
+        workflow = SequentialBuilder().participants([agent1, agent2]).with_request_info().build()
+
+        # Enable request info only for specific agents
+        workflow = (
+            SequentialBuilder()
+            .participants([agent1, agent2, agent3])
+            .with_request_info(agents=[agent2])  # Only pause before agent2
+            .build()
+        )
    """

    def __init__(self) -> None:
        self._participants: list[AgentProtocol | Executor] = []
+        self._participant_factories: list[Callable[[], AgentProtocol | Executor]] = []
        self._checkpoint_storage: CheckpointStorage | None = None
+        self._request_info_enabled: bool = False
+        self._request_info_filter: set[str] | None = None
+
+    def register_participants(
+        self,
+        participant_factories: Sequence[Callable[[], AgentProtocol | Executor]],
+    ) -> "SequentialBuilder":
+        """Register participant factories for this sequential workflow."""
+        if self._participants:
+            raise ValueError(
+                "Cannot mix .participants([...]) and .register_participants() in the same builder instance."
+            )
+
+        if not participant_factories:
+            raise ValueError("participant_factories cannot be empty")
+
+        self._participant_factories = list(participant_factories)
+        return self

    def participants(self, participants: Sequence[AgentProtocol | Executor]) -> "SequentialBuilder":
        """Define the ordered participants for this sequential workflow.
@@ -131,6 +165,11 @@ class SequentialBuilder:
        Accepts AgentProtocol instances (auto-wrapped as AgentExecutor) or Executor instances.
        Raises if empty or duplicates are provided for clarity.
        """
+        if self._participant_factories:
+            raise ValueError(
+                "Cannot mix .participants([...]) and .register_participants() in the same builder instance."
+            )
+
        if not participants:
            raise ValueError("participants cannot be empty")

@@ -157,19 +196,70 @@ class SequentialBuilder:
        self._checkpoint_storage = checkpoint_storage
        return self

+    def with_request_info(
+        self,
+        *,
+        agents: Sequence[str | AgentProtocol | Executor] | None = None,
+    ) -> "SequentialBuilder":
+        """Enable request info before agents run in the workflow.
+
+        When enabled, the workflow pauses before each agent runs, emitting
+        a RequestInfoEvent that allows the caller to review the conversation and
+        optionally inject guidance before the agent responds. The caller provides
+        input via the standard response_handler/request_info pattern.
+
+        Args:
+            agents: Optional filter - only pause before these specific agents/executors.
+                   Accepts agent names (str), agent instances, or executor instances.
+                   If None (default), pauses before every agent.
+
+        Returns:
+            self: The builder instance for fluent chaining.
+
+        Example:
+
+        .. code-block:: python
+
+            # Pause before all agents
+            workflow = SequentialBuilder().participants([a1, a2]).with_request_info().build()
+
+            # Pause only before specific agents
+            workflow = (
+                SequentialBuilder()
+                .participants([drafter, reviewer, finalizer])
+                .with_request_info(agents=[reviewer])  # Only pause before reviewer
+                .build()
+            )
+        """
+        from ._orchestration_request_info import resolve_request_info_filter
+
+        self._request_info_enabled = True
+        self._request_info_filter = resolve_request_info_filter(list(agents) if agents else None)
+        return self
+
    def build(self) -> Workflow:
        """Build and validate the sequential workflow.

        Wiring pattern:
        - _InputToConversation normalizes the initial input into list[ChatMessage]
        - For each participant in order:
-            - If Agent (or AgentExecutor): pass conversation to the agent, then convert response
-              to conversation via _ResponseToConversation
+            - If Agent (or AgentExecutor): pass conversation to the agent, then optionally
+              route through a request info interceptor, then convert response to conversation
+              via _ResponseToConversation
            - Else (custom Executor): pass conversation directly to the executor
        - _EndWithConversation yields the final conversation and the workflow becomes idle
        """
-        if not self._participants:
-            raise ValueError("No participants provided. Call .participants([...]) first.")
+        if not self._participants and not self._participant_factories:
+            raise ValueError(
+                "No participants or participant factories provided to the builder. "
+                "Use .participants([...]) or .ss([...])."
+            )
+
+        if self._participants and self._participant_factories:
+            # Defensive strategy: this should never happen due to checks in respective methods
+            raise ValueError(
+                "Cannot mix .participants([...]) and .register_participants() in the same builder instance."
+            )

        # Internal nodes
        input_conv = _InputToConversation(id="input-conversation")
@@ -181,22 +271,38 @@ class SequentialBuilder:
        # Start of the chain is the input normalizer
        prior: Executor | AgentProtocol = input_conv

-        for p in self._participants:
-            # Agent-like branch: either explicitly an AgentExecutor or any non-AgentExecutor
-            if not (isinstance(p, Executor) and not isinstance(p, AgentExecutor)):
-                # input conversation -> (agent) -> response -> conversation
-                builder.add_edge(prior, p)
-                # Give the adapter a deterministic, self-describing id
-                label: str
-                label = p.id if isinstance(p, Executor) else getattr(p, "name", None) or p.__class__.__name__
+        participants: list[Executor | AgentProtocol] = []
+        if self._participant_factories:
+            for factory in self._participant_factories:
+                p = factory()
+                participants.append(p)
+        else:
+            participants = self._participants
+
+        for p in participants:
+            if isinstance(p, (AgentProtocol, AgentExecutor)):
+                label = p.id if isinstance(p, AgentExecutor) else p.display_name
+
+                if self._request_info_enabled:
+                    # Insert request info interceptor BEFORE the agent
+                    interceptor = RequestInfoInterceptor(
+                        executor_id=f"request_info:{label}",
+                        agent_filter=self._request_info_filter,
+                    )
+                    builder.add_edge(prior, interceptor)
+                    builder.add_edge(interceptor, p)
+                else:
+                    builder.add_edge(prior, p)
+
                resp_to_conv = _ResponseToConversation(id=f"to-conversation:{label}")
                builder.add_edge(p, resp_to_conv)
                prior = resp_to_conv
            elif isinstance(p, Executor):
                # Custom executor operates on list[ChatMessage]
+                # If the executor doesn't handle list[ChatMessage] correctly, validation will fail
                builder.add_edge(prior, p)
                prior = p
-            else:  # pragma: no cover - defensive
+            else:
                raise TypeError(f"Unsupported participant type: {type(p).__name__}")

        # Terminate with the final conversation
@@ -1,7 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.

 import logging
-from dataclasses import fields, is_dataclass
 from types import UnionType
 from typing import Any, TypeVar, Union, cast, get_args, get_origin

@@ -10,67 +9,6 @@ logger = logging.getLogger(__name__)
 T = TypeVar("T")


-def _coerce_to_type(value: Any, target_type: type[T]) -> T | None:
-    """Best-effort conversion of value into target_type.
-
-    Args:
-        value: The value to convert (can be dict, dataclass, or object with __dict__)
-        target_type: The target type to convert to
-
-    Returns:
-        Instance of target_type if conversion succeeds, None otherwise
-    """
-    if isinstance(value, target_type):
-        return value  # type: ignore[return-value]
-
-    # Convert dataclass instances or objects with __dict__ into dict first
-    value_as_dict: dict[str, Any]
-    if not isinstance(value, dict):
-        if is_dataclass(value):
-            value_as_dict = {f.name: getattr(value, f.name) for f in fields(value)}
-        else:
-            value_dict = getattr(value, "__dict__", None)
-            if isinstance(value_dict, dict):
-                value_as_dict = cast(dict[str, Any], value_dict)
-            else:
-                return None
-    else:
-        value_as_dict = cast(dict[str, Any], value)
-
-    # Try to construct the target type from the dict
-    ctor_kwargs: dict[str, Any] = dict(value_as_dict)
-
-    if is_dataclass(target_type):
-        field_names = {f.name for f in fields(target_type)}
-        ctor_kwargs = {k: v for k, v in value_as_dict.items() if k in field_names}
-
-    try:
-        return target_type(**ctor_kwargs)  # type: ignore[call-arg,return-value]
-    except TypeError as exc:
-        logger.debug(f"_coerce_to_type could not call {target_type.__name__}(**..): {exc}")
-    except Exception as exc:  # pragma: no cover - unexpected constructor failure
-        logger.warning(
-            f"_coerce_to_type encountered unexpected error calling {target_type.__name__} constructor: {exc}"
-        )
-
-    # Fallback: try to create instance without __init__ and set attributes
-    try:
-        instance = object.__new__(target_type)
-    except Exception as exc:  # pragma: no cover - pathological type
-        logger.debug(f"_coerce_to_type could not allocate {target_type.__name__} without __init__: {exc}")
-        return None
-
-    for key, val in value_as_dict.items():
-        try:
-            setattr(instance, key, val)
-        except Exception as exc:
-            logger.debug(
-                f"_coerce_to_type could not set {target_type.__name__}.{key} during fallback assignment: {exc}"
-            )
-            continue
-    return instance  # type: ignore[return-value]
-
-
 def is_instance_of(data: Any, target_type: type | UnionType | Any) -> bool:
    """Check if the data is an instance of the target type.

@@ -374,7 +374,7 @@ class WorkflowBuilder:
                )
        """
        if name in self._executor_registry:
-            raise ValueError(f"An executor factory with the name '{name}' is already registered.")
+            raise ValueError(f"An agent factory with the name '{name}' is already registered.")

        def wrapped_factory() -> AgentExecutor:
            agent = factory_func()
@@ -1148,21 +1148,29 @@ class WorkflowBuilder:
        if isinstance(self._start_executor, Executor):
            start_executor = self._start_executor

-        executors: dict[str, Executor] = {}
+        # Maps registered factory names to created executor instances for edge resolution
+        factory_name_to_instance: dict[str, Executor] = {}
+        # Maps executor IDs to created executor instances to prevent duplicates
+        executor_id_to_instance: dict[str, Executor] = {}
        deferred_edge_groups: list[EdgeGroup] = []
        for name, exec_factory in self._executor_registry.items():
            instance = exec_factory()
+            if instance.id in executor_id_to_instance:
+                raise ValueError(f"Executor with ID '{instance.id}' has already been created.")
+            executor_id_to_instance[instance.id] = instance
+
            if isinstance(self._start_executor, str) and name == self._start_executor:
                start_executor = instance
+
            # All executors will get their own internal edge group for receiving system messages
            deferred_edge_groups.append(InternalEdgeGroup(instance.id))  # type: ignore[call-arg]
-            executors[name] = instance
+            factory_name_to_instance[name] = instance

        def _get_executor(name: str) -> Executor:
            """Helper to get executor by the registered name. Raises if not found."""
-            if name not in executors:
-                raise ValueError(f"Executor with name '{name}' has not been registered.")
-            return executors[name]
+            if name not in factory_name_to_instance:
+                raise ValueError(f"Factory '{name}' has not been registered.")
+            return factory_name_to_instance[name]

        for registration in self._edge_registry:
            match registration:
@@ -1179,7 +1187,7 @@ class WorkflowBuilder:
                    cases_converted: list[SwitchCaseEdgeGroupCase | SwitchCaseEdgeGroupDefault] = []
                    for case in cases:
                        if not isinstance(case.target, str):
-                            raise ValueError("Switch case target must be a registered executor name (str) if deferred.")
+                            raise ValueError("Switch case target must be a registered factory name (str) if deferred.")
                        target_exec = _get_executor(case.target)
                        if isinstance(case, Default):
                            cases_converted.append(SwitchCaseEdgeGroupDefault(target_id=target_exec.id))
@@ -1201,7 +1209,7 @@ class WorkflowBuilder:
        if start_executor is None:
            raise ValueError("Failed to resolve starting executor from registered factories.")

-        return start_executor, list(executors.values()), deferred_edge_groups
+        return start_executor, list(executor_id_to_instance.values()), deferred_edge_groups

    def build(self) -> Workflow:
        """Build and return the constructed workflow.
@@ -521,9 +521,9 @@ class ObservabilitySettings(AFBaseSettings):
                logger_provider.add_log_record_processor(BatchLogRecordProcessor(exporter))
                should_add_console_exporter = False
        if should_add_console_exporter:
-            from opentelemetry.sdk._logs.export import ConsoleLogExporter
+            from opentelemetry.sdk._logs.export import ConsoleLogRecordExporter

-            logger_provider.add_log_record_processor(BatchLogRecordProcessor(ConsoleLogExporter()))
+            logger_provider.add_log_record_processor(BatchLogRecordProcessor(ConsoleLogRecordExporter()))

        # Attach a handler with the provider to the root logger
        logger = logging.getLogger()
@@ -3,7 +3,7 @@
 from collections.abc import AsyncIterable, Awaitable, Callable, Mapping, MutableMapping, MutableSequence, Sequence
 from datetime import datetime, timezone
 from itertools import chain
-from typing import Any, TypeVar
+from typing import Any, TypeVar, cast

 from openai import AsyncOpenAI, BadRequestError
 from openai.types.responses.file_search_tool_param import FileSearchToolParam
@@ -199,7 +199,7 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
            return response_format, prepared_text

        if isinstance(response_format, Mapping):
-            format_config = self._convert_response_format(response_format)
+            format_config = self._convert_response_format(cast("Mapping[str, Any]", response_format))
            if prepared_text is None:
                prepared_text = {}
            elif "format" in prepared_text and prepared_text["format"] != format_config:
@@ -212,20 +212,21 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
    def _convert_response_format(self, response_format: Mapping[str, Any]) -> dict[str, Any]:
        """Convert Chat style response_format into Responses text format config."""
        if "format" in response_format and isinstance(response_format["format"], Mapping):
-            return dict(response_format["format"])
+            return dict(cast("Mapping[str, Any]", response_format["format"]))

        format_type = response_format.get("type")
        if format_type == "json_schema":
            schema_section = response_format.get("json_schema", response_format)
            if not isinstance(schema_section, Mapping):
                raise ServiceInvalidRequestError("json_schema response_format must be a mapping.")
-            schema = schema_section.get("schema")
+            schema_section_typed = cast("Mapping[str, Any]", schema_section)
+            schema: Any = schema_section_typed.get("schema")
            if schema is None:
                raise ServiceInvalidRequestError("json_schema response_format requires a schema.")
-            name = (
-                schema_section.get("name")
-                or schema_section.get("title")
-                or (schema.get("title") if isinstance(schema, Mapping) else None)
+            name: str = str(
+                schema_section_typed.get("name")
+                or schema_section_typed.get("title")
+                or (cast("Mapping[str, Any]", schema).get("title") if isinstance(schema, Mapping) else None)
                or "response"
            )
            format_config: dict[str, Any] = {
@@ -532,12 +533,13 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                        "text": content.text,
                    },
                }
-                if content.additional_properties is not None:
-                    if status := content.additional_properties.get("status"):
+                props: dict[str, Any] | None = getattr(content, "additional_properties", None)
+                if props:
+                    if status := props.get("status"):
                        ret["status"] = status
-                    if reasoning_text := content.additional_properties.get("reasoning_text"):
+                    if reasoning_text := props.get("reasoning_text"):
                        ret["content"] = {"type": "reasoning_text", "text": reasoning_text}
-                    if encrypted_content := content.additional_properties.get("encrypted_content"):
+                    if encrypted_content := props.get("encrypted_content"):
                        ret["encrypted_content"] = encrypted_content
                return ret
            case DataContent() | UriContent():
@@ -824,7 +826,7 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
            "raw_representation": response,
        }

-        conversation_id = self.get_conversation_id(response, chat_options.store)
+        conversation_id = self.get_conversation_id(response, chat_options.store)  # type: ignore[reportArgumentType]

        if conversation_id:
            args["conversation_id"] = conversation_id
@@ -911,6 +913,8 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                        metadata.update(self._get_metadata_from_response(event_part))
                    case "refusal":
                        contents.append(TextContent(text=event_part.refusal, raw_representation=event))
+                    case _:
+                        pass
            case "response.output_text.delta":
                contents.append(TextContent(text=event.delta, raw_representation=event))
                metadata.update(self._get_metadata_from_response(event))
@@ -1032,6 +1036,60 @@ class OpenAIBaseResponsesClient(OpenAIBase, BaseChatClient):
                        raw_representation=event,
                    )
                )
+            case "response.output_text.annotation.added":
+                # Handle streaming text annotations (file citations, file paths, etc.)
+                annotation: Any = event.annotation
+
+                def _get_ann_value(key: str) -> Any:
+                    """Extract value from annotation (dict or object)."""
+                    if isinstance(annotation, dict):
+                        return cast("dict[str, Any]", annotation).get(key)
+                    return getattr(annotation, key, None)
+
+                ann_type = _get_ann_value("type")
+                ann_file_id = _get_ann_value("file_id")
+                if ann_type == "file_path":
+                    if ann_file_id:
+                        contents.append(
+                            HostedFileContent(
+                                file_id=str(ann_file_id),
+                                additional_properties={
+                                    "annotation_index": event.annotation_index,
+                                    "index": _get_ann_value("index"),
+                                },
+                                raw_representation=event,
+                            )
+                        )
+                elif ann_type == "file_citation":
+                    if ann_file_id:
+                        contents.append(
+                            HostedFileContent(
+                                file_id=str(ann_file_id),
+                                additional_properties={
+                                    "annotation_index": event.annotation_index,
+                                    "filename": _get_ann_value("filename"),
+                                    "index": _get_ann_value("index"),
+                                },
+                                raw_representation=event,
+                            )
+                        )
+                elif ann_type == "container_file_citation":
+                    if ann_file_id:
+                        contents.append(
+                            HostedFileContent(
+                                file_id=str(ann_file_id),
+                                additional_properties={
+                                    "annotation_index": event.annotation_index,
+                                    "container_id": _get_ann_value("container_id"),
+                                    "filename": _get_ann_value("filename"),
+                                    "start_index": _get_ann_value("start_index"),
+                                    "end_index": _get_ann_value("end_index"),
+                                },
+                                raw_representation=event,
+                            )
+                        )
+                else:
+                    logger.debug("Unparsed annotation type in streaming: %s", ann_type)
            case _:
                logger.debug("Unparsed event of type: %s: %s", event.type, event)

@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -35,7 +35,7 @@ dependencies = [
    # connectors and functions
    "openai>=1.99.0",
    "azure-identity>=1,<2",
-    "mcp[ws]>=1.13",
+    "mcp[ws]>=1.23",
    "packaging>=24.1",
 ]

@@ -9,7 +9,7 @@ import pytest
 from mcp import types
 from mcp.client.session import ClientSession
 from mcp.shared.exceptions import McpError
-from pydantic import AnyUrl, ValidationError
+from pydantic import AnyUrl, BaseModel, ValidationError

 from agent_framework import (
    ChatMessage,
@@ -357,122 +357,360 @@ def test_chat_message_to_mcp_types():
    assert isinstance(mcp_contents[1], types.ImageContent)


-def test_get_input_model_from_mcp_tool():
-    """Test creation of input model from MCP tool."""
-    tool = types.Tool(
-        name="test_tool",
-        description="A test tool",
-        inputSchema={
-            "type": "object",
-            "properties": {"param1": {"type": "string"}, "param2": {"type": "number"}},
-            "required": ["param1"],
-        },
-    )
-    model = _get_input_model_from_mcp_tool(tool)
-
-    # Create an instance to verify the model works
-    instance = model(param1="test", param2=42)
-    assert instance.param1 == "test"
-    assert instance.param2 == 42
-
-    # Test validation
-    with pytest.raises(ValidationError):  # Missing required param1
-        model(param2=42)
-
-
-def test_get_input_model_from_mcp_tool_with_nested_object():
-    """Test creation of input model from MCP tool with nested object property."""
-    tool = types.Tool(
-        name="get_customer_detail",
-        description="Get customer details",
-        inputSchema={
-            "type": "object",
-            "properties": {
-                "params": {
-                    "type": "object",
-                    "properties": {"customer_id": {"type": "integer"}},
-                    "required": ["customer_id"],
+@pytest.mark.parametrize(
+    "test_id,input_schema,valid_data,expected_values,invalid_data,validation_check",
+    [
+        # Basic types with required/optional fields
+        (
+            "basic_types",
+            {
+                "type": "object",
+                "properties": {"param1": {"type": "string"}, "param2": {"type": "number"}},
+                "required": ["param1"],
+            },
+            {"param1": "test", "param2": 42},
+            {"param1": "test", "param2": 42},
+            {"param2": 42},  # Missing required param1
+            None,
+        ),
+        # Nested object
+        (
+            "nested_object",
+            {
+                "type": "object",
+                "properties": {
+                    "params": {
+                        "type": "object",
+                        "properties": {"customer_id": {"type": "integer"}},
+                        "required": ["customer_id"],
+                    }
+                },
+                "required": ["params"],
+            },
+            {"params": {"customer_id": 251}},
+            {"params.customer_id": 251},
+            {"params": {}},  # Missing required customer_id
+            lambda instance: isinstance(instance.params, BaseModel),
+        ),
+        # $ref resolution
+        (
+            "ref_schema",
+            {
+                "type": "object",
+                "properties": {"params": {"$ref": "#/$defs/CustomerIdParam"}},
+                "required": ["params"],
+                "$defs": {
+                    "CustomerIdParam": {
+                        "type": "object",
+                        "properties": {"customer_id": {"type": "integer"}},
+                        "required": ["customer_id"],
+                    }
+                },
+            },
+            {"params": {"customer_id": 251}},
+            {"params.customer_id": 251},
+            {"params": {}},  # Missing required customer_id
+            lambda instance: isinstance(instance.params, BaseModel),
+        ),
+        # Array of strings (typed)
+        (
+            "array_of_strings",
+            {
+                "type": "object",
+                "properties": {
+                    "tags": {
+                        "type": "array",
+                        "description": "List of tags",
+                        "items": {"type": "string"},
+                    }
+                },
+                "required": ["tags"],
+            },
+            {"tags": ["tag1", "tag2", "tag3"]},
+            {"tags": ["tag1", "tag2", "tag3"]},
+            None,  # No validation error test for this case
+            None,
+        ),
+        # Array of integers (typed)
+        (
+            "array_of_integers",
+            {
+                "type": "object",
+                "properties": {
+                    "numbers": {
+                        "type": "array",
+                        "description": "List of integers",
+                        "items": {"type": "integer"},
+                    }
+                },
+                "required": ["numbers"],
+            },
+            {"numbers": [1, 2, 3]},
+            {"numbers": [1, 2, 3]},
+            None,
+            None,
+        ),
+        # Array of objects (complex nested)
+        (
+            "array_of_objects",
+            {
+                "type": "object",
+                "properties": {
+                    "users": {
+                        "type": "array",
+                        "description": "List of users",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "id": {"type": "integer", "description": "User ID"},
+                                "name": {"type": "string", "description": "User name"},
+                            },
+                            "required": ["id", "name"],
+                        },
+                    }
+                },
+                "required": ["users"],
+            },
+            {"users": [{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]},
+            {"users[0].id": 1, "users[0].name": "Alice", "users[1].id": 2, "users[1].name": "Bob"},
+            {"users": [{"id": 1}]},  # Missing required 'name'
+            lambda instance: all(isinstance(user, BaseModel) for user in instance.users),
+        ),
+        # Deeply nested objects (3+ levels)
+        (
+            "deeply_nested",
+            {
+                "type": "object",
+                "properties": {
+                    "query": {
+                        "type": "object",
+                        "properties": {
+                            "filters": {
+                                "type": "object",
+                                "properties": {
+                                    "date_range": {
+                                        "type": "object",
+                                        "properties": {
+                                            "start": {"type": "string"},
+                                            "end": {"type": "string"},
+                                        },
+                                        "required": ["start", "end"],
+                                    },
+                                    "categories": {"type": "array", "items": {"type": "string"}},
+                                },
+                                "required": ["date_range"],
+                            }
+                        },
+                        "required": ["filters"],
+                    }
+                },
+                "required": ["query"],
+            },
+            {
+                "query": {
+                    "filters": {
+                        "date_range": {"start": "2024-01-01", "end": "2024-12-31"},
+                        "categories": ["tech", "science"],
+                    }
                }
            },
-            "required": ["params"],
-        },
-    )
-    model = _get_input_model_from_mcp_tool(tool)
+            {
+                "query.filters.date_range.start": "2024-01-01",
+                "query.filters.date_range.end": "2024-12-31",
+                "query.filters.categories": ["tech", "science"],
+            },
+            {"query": {"filters": {"date_range": {}}}},  # Missing required start and end
+            None,
+        ),
+        # Complex $ref with nested structure
+        (
+            "ref_nested_structure",
+            {
+                "type": "object",
+                "properties": {"order": {"$ref": "#/$defs/OrderParams"}},
+                "required": ["order"],
+                "$defs": {
+                    "OrderParams": {
+                        "type": "object",
+                        "properties": {
+                            "customer": {"$ref": "#/$defs/Customer"},
+                            "items": {"type": "array", "items": {"$ref": "#/$defs/OrderItem"}},
+                        },
+                        "required": ["customer", "items"],
+                    },
+                    "Customer": {
+                        "type": "object",
+                        "properties": {"id": {"type": "integer"}, "email": {"type": "string"}},
+                        "required": ["id", "email"],
+                    },
+                    "OrderItem": {
+                        "type": "object",
+                        "properties": {"product_id": {"type": "string"}, "quantity": {"type": "integer"}},
+                        "required": ["product_id", "quantity"],
+                    },
+                },
+            },
+            {
+                "order": {
+                    "customer": {"id": 123, "email": "test@example.com"},
+                    "items": [{"product_id": "prod1", "quantity": 2}],
+                }
+            },
+            {
+                "order.customer.id": 123,
+                "order.customer.email": "test@example.com",
+                "order.items[0].product_id": "prod1",
+                "order.items[0].quantity": 2,
+            },
+            {"order": {"customer": {"id": 123}, "items": []}},  # Missing email
+            lambda instance: isinstance(instance.order.customer, BaseModel),
+        ),
+        # Mixed types (primitives, arrays, nested objects)
+        (
+            "mixed_types",
+            {
+                "type": "object",
+                "properties": {
+                    "simple_string": {"type": "string"},
+                    "simple_number": {"type": "integer"},
+                    "string_array": {"type": "array", "items": {"type": "string"}},
+                    "nested_config": {
+                        "type": "object",
+                        "properties": {
+                            "enabled": {"type": "boolean"},
+                            "options": {"type": "array", "items": {"type": "string"}},
+                        },
+                        "required": ["enabled"],
+                    },
+                },
+                "required": ["simple_string", "nested_config"],
+            },
+            {
+                "simple_string": "test",
+                "simple_number": 42,
+                "string_array": ["a", "b"],
+                "nested_config": {"enabled": True, "options": ["opt1", "opt2"]},
+            },
+            {
+                "simple_string": "test",
+                "simple_number": 42,
+                "string_array": ["a", "b"],
+                "nested_config.enabled": True,
+                "nested_config.options": ["opt1", "opt2"],
+            },
+            None,
+            None,
+        ),
+        # Empty schema (no properties)
+        (
+            "empty_schema",
+            {"type": "object", "properties": {}},
+            {},
+            {},
+            None,
+            None,
+        ),
+        # All primitive types
+        (
+            "all_primitives",
+            {
+                "type": "object",
+                "properties": {
+                    "string_field": {"type": "string"},
+                    "integer_field": {"type": "integer"},
+                    "number_field": {"type": "number"},
+                    "boolean_field": {"type": "boolean"},
+                },
+            },
+            {"string_field": "test", "integer_field": 42, "number_field": 3.14, "boolean_field": True},
+            {"string_field": "test", "integer_field": 42, "number_field": 3.14, "boolean_field": True},
+            None,
+            None,
+        ),
+        # Edge case: unresolvable $ref (fallback to dict)
+        (
+            "unresolvable_ref",
+            {
+                "type": "object",
+                "properties": {"data": {"$ref": "#/$defs/NonExistent"}},
+                "$defs": {},
+            },
+            {"data": {"key": "value"}},
+            {"data": {"key": "value"}},
+            None,
+            None,
+        ),
+        # Edge case: array without items schema (fallback to bare list)
+        (
+            "array_no_items",
+            {
+                "type": "object",
+                "properties": {"items": {"type": "array"}},
+            },
+            {"items": [1, "two", 3.0]},
+            {"items": [1, "two", 3.0]},
+            None,
+            None,
+        ),
+        # Edge case: object without properties (fallback to dict)
+        (
+            "object_no_properties",
+            {
+                "type": "object",
+                "properties": {"config": {"type": "object"}},
+            },
+            {"config": {"arbitrary": "data", "nested": {"key": "value"}}},
+            {"config": {"arbitrary": "data", "nested": {"key": "value"}}},
+            None,
+            None,
+        ),
+    ],
+)
+def test_get_input_model_from_mcp_tool_parametrized(
+    test_id, input_schema, valid_data, expected_values, invalid_data, validation_check
+):
+    """Parametrized test for JSON schema to Pydantic model conversion.

-    # Create an instance to verify the model works with nested objects
-    instance = model(params={"customer_id": 251})
-    assert instance.params == {"customer_id": 251}
-    assert isinstance(instance.params, dict)
+    This test covers various edge cases including:
+    - Basic types with required/optional fields
+    - Nested objects
+    - $ref resolution
+    - Typed arrays (strings, integers, objects)
+    - Deeply nested structures
+    - Complex $ref with nested structures
+    - Mixed types

-    # Verify model_dump produces the correct nested structure
-    dumped = instance.model_dump()
-    assert dumped == {"params": {"customer_id": 251}}
-
-
-def test_get_input_model_from_mcp_tool_with_ref_schema():
-    """Test creation of input model from MCP tool with $ref schema.
-
-    This simulates a FastMCP tool that uses Pydantic models with $ref in the schema.
-    The schema should be resolved and nested objects should be preserved.
+    To add a new test case, add a tuple to the parametrize decorator with:
+    - test_id: A descriptive name for the test case
+    - input_schema: The JSON schema (inputSchema dict)
+    - valid_data: Valid data to instantiate the model
+    - expected_values: Dict of expected values (supports dot notation for nested access)
+    - invalid_data: Invalid data to test validation errors (None to skip)
+    - validation_check: Optional callable to perform additional validation checks
    """
-    # This is similar to what FastMCP generates when you have:
-    # async def get_customer_detail(params: CustomerIdParam) -> CustomerDetail
-    tool = types.Tool(
-        name="get_customer_detail",
-        description="Get customer details",
-        inputSchema={
-            "type": "object",
-            "properties": {"params": {"$ref": "#/$defs/CustomerIdParam"}},
-            "required": ["params"],
-            "$defs": {
-                "CustomerIdParam": {
-                    "type": "object",
-                    "properties": {"customer_id": {"type": "integer"}},
-                    "required": ["customer_id"],
-                }
-            },
-        },
-    )
+    tool = types.Tool(name="test_tool", description="A test tool", inputSchema=input_schema)
    model = _get_input_model_from_mcp_tool(tool)

-    # Create an instance to verify the model works with $ref schemas
-    instance = model(params={"customer_id": 251})
-    assert instance.params == {"customer_id": 251}
-    assert isinstance(instance.params, dict)
+    # Test valid data
+    instance = model(**valid_data)

-    # Verify model_dump produces the correct nested structure
-    dumped = instance.model_dump()
-    assert dumped == {"params": {"customer_id": 251}}
+    # Check expected values
+    for field_path, expected_value in expected_values.items():
+        # Support dot notation and array indexing for nested access
+        current = instance
+        parts = field_path.replace("]", "").replace("[", ".").split(".")
+        for part in parts:
+            current = current[int(part)] if part.isdigit() else getattr(current, part)
+        assert current == expected_value, f"Field {field_path} = {current}, expected {expected_value}"

+    # Run additional validation checks if provided
+    if validation_check:
+        assert validation_check(instance), f"Validation check failed for {test_id}"

-def test_get_input_model_from_mcp_tool_with_simple_array():
-    """Test array with simple items schema (items schema should be preserved in json_schema_extra)."""
-    tool = types.Tool(
-        name="simple_array_tool",
-        description="Tool with simple array",
-        inputSchema={
-            "type": "object",
-            "properties": {
-                "tags": {
-                    "type": "array",
-                    "description": "List of tags",
-                    "items": {"type": "string"},  # Simple string array
-                }
-            },
-            "required": ["tags"],
-        },
-    )
-    model = _get_input_model_from_mcp_tool(tool)
-
-    # Create an instance
-    instance = model(tags=["tag1", "tag2", "tag3"])
-    assert instance.tags == ["tag1", "tag2", "tag3"]
-
-    # Verify JSON schema still preserves items for simple types
-    json_schema = model.model_json_schema()
-    tags_property = json_schema["properties"]["tags"]
-    assert "items" in tags_property
-    assert tags_property["items"]["type"] == "string"
+    # Test invalid data if provided
+    if invalid_data is not None:
+        with pytest.raises(ValidationError):
+            model(**invalid_data)


 def test_get_input_model_from_mcp_prompt():
@@ -993,6 +993,110 @@ def test_streaming_response_basic_structure() -> None:
    assert response.raw_representation is mock_event


+def test_streaming_annotation_added_with_file_path() -> None:
+    """Test streaming annotation added event with file_path type extracts HostedFileContent."""
+    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
+    chat_options = ChatOptions()
+    function_call_ids: dict[int, tuple[str, str]] = {}
+
+    mock_event = MagicMock()
+    mock_event.type = "response.output_text.annotation.added"
+    mock_event.annotation_index = 0
+    mock_event.annotation = {
+        "type": "file_path",
+        "file_id": "file-abc123",
+        "index": 42,
+    }
+
+    response = client._create_streaming_response_content(mock_event, chat_options, function_call_ids)
+
+    assert len(response.contents) == 1
+    content = response.contents[0]
+    assert isinstance(content, HostedFileContent)
+    assert content.file_id == "file-abc123"
+    assert content.additional_properties is not None
+    assert content.additional_properties.get("annotation_index") == 0
+    assert content.additional_properties.get("index") == 42
+
+
+def test_streaming_annotation_added_with_file_citation() -> None:
+    """Test streaming annotation added event with file_citation type extracts HostedFileContent."""
+    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
+    chat_options = ChatOptions()
+    function_call_ids: dict[int, tuple[str, str]] = {}
+
+    mock_event = MagicMock()
+    mock_event.type = "response.output_text.annotation.added"
+    mock_event.annotation_index = 1
+    mock_event.annotation = {
+        "type": "file_citation",
+        "file_id": "file-xyz789",
+        "filename": "sample.txt",
+        "index": 15,
+    }
+
+    response = client._create_streaming_response_content(mock_event, chat_options, function_call_ids)
+
+    assert len(response.contents) == 1
+    content = response.contents[0]
+    assert isinstance(content, HostedFileContent)
+    assert content.file_id == "file-xyz789"
+    assert content.additional_properties is not None
+    assert content.additional_properties.get("filename") == "sample.txt"
+    assert content.additional_properties.get("index") == 15
+
+
+def test_streaming_annotation_added_with_container_file_citation() -> None:
+    """Test streaming annotation added event with container_file_citation type."""
+    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
+    chat_options = ChatOptions()
+    function_call_ids: dict[int, tuple[str, str]] = {}
+
+    mock_event = MagicMock()
+    mock_event.type = "response.output_text.annotation.added"
+    mock_event.annotation_index = 2
+    mock_event.annotation = {
+        "type": "container_file_citation",
+        "file_id": "file-container123",
+        "container_id": "container-456",
+        "filename": "data.csv",
+        "start_index": 10,
+        "end_index": 50,
+    }
+
+    response = client._create_streaming_response_content(mock_event, chat_options, function_call_ids)
+
+    assert len(response.contents) == 1
+    content = response.contents[0]
+    assert isinstance(content, HostedFileContent)
+    assert content.file_id == "file-container123"
+    assert content.additional_properties is not None
+    assert content.additional_properties.get("container_id") == "container-456"
+    assert content.additional_properties.get("filename") == "data.csv"
+    assert content.additional_properties.get("start_index") == 10
+    assert content.additional_properties.get("end_index") == 50
+
+
+def test_streaming_annotation_added_with_unknown_type() -> None:
+    """Test streaming annotation added event with unknown type is ignored."""
+    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
+    chat_options = ChatOptions()
+    function_call_ids: dict[int, tuple[str, str]] = {}
+
+    mock_event = MagicMock()
+    mock_event.type = "response.output_text.annotation.added"
+    mock_event.annotation_index = 0
+    mock_event.annotation = {
+        "type": "url_citation",
+        "url": "https://example.com",
+    }
+
+    response = client._create_streaming_response_content(mock_event, chat_options, function_call_ids)
+
+    # url_citation should not produce HostedFileContent
+    assert len(response.contents) == 0
+
+
 def test_service_response_exception_includes_original_error_details() -> None:
    """Test that ServiceResponseException messages include original error details in the new format."""
    client = OpenAIResponsesClient(model_id="test-model", api_key="test-key")
@@ -3,6 +3,7 @@
 from typing import Any, cast

 import pytest
+from typing_extensions import Never

 from agent_framework import (
    AgentExecutorRequest,
@@ -52,6 +53,55 @@ def test_concurrent_builder_rejects_duplicate_executors() -> None:
        ConcurrentBuilder().participants([a, b])


+def test_concurrent_builder_rejects_duplicate_executors_from_factories() -> None:
+    """Test that duplicate executor IDs from factories are detected at build time."""
+
+    def create_dup1() -> Executor:
+        return _FakeAgentExec("dup", "A")
+
+    def create_dup2() -> Executor:
+        return _FakeAgentExec("dup", "B")  # same executor id
+
+    builder = ConcurrentBuilder().register_participants([create_dup1, create_dup2])
+    with pytest.raises(ValueError, match="Executor with ID 'dup' has already been created."):
+        builder.build()
+
+
+def test_concurrent_builder_rejects_mixed_participants_and_factories() -> None:
+    """Test that mixing .participants() and .register_participants() raises an error."""
+    # Case 1: participants first, then register_participants
+    with pytest.raises(ValueError, match="Cannot mix .participants"):
+        (
+            ConcurrentBuilder()
+            .participants([_FakeAgentExec("a", "A")])
+            .register_participants([lambda: _FakeAgentExec("b", "B")])
+        )
+
+    # Case 2: register_participants first, then participants
+    with pytest.raises(ValueError, match="Cannot mix .participants"):
+        (
+            ConcurrentBuilder()
+            .register_participants([lambda: _FakeAgentExec("a", "A")])
+            .participants([_FakeAgentExec("b", "B")])
+        )
+
+
+def test_concurrent_builder_rejects_multiple_calls_to_participants() -> None:
+    """Test that multiple calls to .participants() raises an error."""
+    with pytest.raises(ValueError, match=r"participants\(\) has already been called"):
+        (ConcurrentBuilder().participants([_FakeAgentExec("a", "A")]).participants([_FakeAgentExec("b", "B")]))
+
+
+def test_concurrent_builder_rejects_multiple_calls_to_register_participants() -> None:
+    """Test that multiple calls to .register_participants() raises an error."""
+    with pytest.raises(ValueError, match=r"register_participants\(\) has already been called"):
+        (
+            ConcurrentBuilder()
+            .register_participants([lambda: _FakeAgentExec("a", "A")])
+            .register_participants([lambda: _FakeAgentExec("b", "B")])
+        )
+
+
 async def test_concurrent_default_aggregator_emits_single_user_and_assistants() -> None:
    # Three synthetic agent executors
    e1 = _FakeAgentExec("agentA", "Alpha")
@@ -159,6 +209,138 @@ def test_concurrent_custom_aggregator_uses_callback_name_for_id() -> None:
    assert aggregator.id == "summarize"


+async def test_concurrent_with_aggregator_executor_instance() -> None:
+    """Test with_aggregator using an Executor instance (not factory)."""
+
+    class CustomAggregator(Executor):
+        @handler
+        async def aggregate(self, results: list[AgentExecutorResponse], ctx: WorkflowContext[Never, str]) -> None:
+            texts: list[str] = []
+            for r in results:
+                msgs: list[ChatMessage] = r.agent_run_response.messages
+                texts.append(msgs[-1].text if msgs else "")
+            await ctx.yield_output(" & ".join(sorted(texts)))
+
+    e1 = _FakeAgentExec("agentA", "One")
+    e2 = _FakeAgentExec("agentB", "Two")
+
+    aggregator_instance = CustomAggregator(id="instance_aggregator")
+    wf = ConcurrentBuilder().participants([e1, e2]).with_aggregator(aggregator_instance).build()
+
+    completed = False
+    output: str | None = None
+    async for ev in wf.run_stream("prompt: instance test"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = cast(str, ev.data)
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    assert isinstance(output, str)
+    assert output == "One & Two"
+
+
+async def test_concurrent_with_aggregator_executor_factory() -> None:
+    """Test with_aggregator using an Executor factory."""
+
+    class CustomAggregator(Executor):
+        @handler
+        async def aggregate(self, results: list[AgentExecutorResponse], ctx: WorkflowContext[Never, str]) -> None:
+            texts: list[str] = []
+            for r in results:
+                msgs: list[ChatMessage] = r.agent_run_response.messages
+                texts.append(msgs[-1].text if msgs else "")
+            await ctx.yield_output(" | ".join(sorted(texts)))
+
+    e1 = _FakeAgentExec("agentA", "One")
+    e2 = _FakeAgentExec("agentB", "Two")
+
+    wf = (
+        ConcurrentBuilder()
+        .participants([e1, e2])
+        .register_aggregator(lambda: CustomAggregator(id="custom_aggregator"))
+        .build()
+    )
+
+    completed = False
+    output: str | None = None
+    async for ev in wf.run_stream("prompt: factory test"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = cast(str, ev.data)
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    assert isinstance(output, str)
+    assert output == "One | Two"
+
+
+async def test_concurrent_with_aggregator_executor_factory_with_default_id() -> None:
+    """Test with_aggregator using an Executor class directly as factory (with default __init__ parameters)."""
+
+    class CustomAggregator(Executor):
+        def __init__(self, id: str = "default_aggregator") -> None:
+            super().__init__(id)
+
+        @handler
+        async def aggregate(self, results: list[AgentExecutorResponse], ctx: WorkflowContext[Never, str]) -> None:
+            texts: list[str] = []
+            for r in results:
+                msgs: list[ChatMessage] = r.agent_run_response.messages
+                texts.append(msgs[-1].text if msgs else "")
+            await ctx.yield_output(" | ".join(sorted(texts)))
+
+    e1 = _FakeAgentExec("agentA", "One")
+    e2 = _FakeAgentExec("agentB", "Two")
+
+    wf = ConcurrentBuilder().participants([e1, e2]).register_aggregator(CustomAggregator).build()
+
+    completed = False
+    output: str | None = None
+    async for ev in wf.run_stream("prompt: factory test"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = cast(str, ev.data)
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    assert isinstance(output, str)
+    assert output == "One | Two"
+
+
+def test_concurrent_builder_rejects_multiple_calls_to_with_aggregator() -> None:
+    """Test that multiple calls to .with_aggregator() raises an error."""
+
+    def summarize(results: list[AgentExecutorResponse]) -> str:  # type: ignore[override]
+        return str(len(results))
+
+    with pytest.raises(ValueError, match=r"with_aggregator\(\) has already been called"):
+        (ConcurrentBuilder().with_aggregator(summarize).with_aggregator(summarize))
+
+
+def test_concurrent_builder_rejects_multiple_calls_to_register_aggregator() -> None:
+    """Test that multiple calls to .register_aggregator() raises an error."""
+
+    class CustomAggregator(Executor):
+        pass
+
+    with pytest.raises(ValueError, match=r"register_aggregator\(\) has already been called"):
+        (
+            ConcurrentBuilder()
+            .register_aggregator(lambda: CustomAggregator(id="agg1"))
+            .register_aggregator(lambda: CustomAggregator(id="agg2"))
+        )
+
+
 async def test_concurrent_checkpoint_resume_round_trip() -> None:
    storage = InMemoryCheckpointStorage()

@@ -278,3 +460,92 @@ async def test_concurrent_checkpoint_runtime_overrides_buildtime() -> None:

        assert len(runtime_checkpoints) > 0, "Runtime storage should have checkpoints"
        assert len(buildtime_checkpoints) == 0, "Build-time storage should have no checkpoints when overridden"
+
+
+def test_concurrent_builder_rejects_empty_participant_factories() -> None:
+    with pytest.raises(ValueError):
+        ConcurrentBuilder().register_participants([])
+
+
+async def test_concurrent_builder_reusable_after_build_with_participants() -> None:
+    """Test that the builder can be reused to build multiple identical workflows with participants()."""
+    e1 = _FakeAgentExec("agentA", "One")
+    e2 = _FakeAgentExec("agentB", "Two")
+
+    builder = ConcurrentBuilder().participants([e1, e2])
+
+    builder.build()
+
+    assert builder._participants[0] is e1  # type: ignore
+    assert builder._participants[1] is e2  # type: ignore
+    assert builder._participant_factories == []  # type: ignore
+
+
+async def test_concurrent_builder_reusable_after_build_with_factories() -> None:
+    """Test that the builder can be reused to build multiple workflows with register_participants()."""
+    call_count = 0
+
+    def create_agent_executor_a() -> Executor:
+        nonlocal call_count
+        call_count += 1
+        return _FakeAgentExec("agentA", "One")
+
+    def create_agent_executor_b() -> Executor:
+        nonlocal call_count
+        call_count += 1
+        return _FakeAgentExec("agentB", "Two")
+
+    builder = ConcurrentBuilder().register_participants([create_agent_executor_a, create_agent_executor_b])
+
+    # Build the first workflow
+    wf1 = builder.build()
+
+    assert builder._participants == []  # type: ignore
+    assert len(builder._participant_factories) == 2  # type: ignore
+    assert call_count == 2
+
+    # Build the second workflow
+    wf2 = builder.build()
+    assert call_count == 4
+
+    # Verify that the two workflows have different executor instances
+    assert wf1.executors["agentA"] is not wf2.executors["agentA"]
+    assert wf1.executors["agentB"] is not wf2.executors["agentB"]
+
+
+async def test_concurrent_with_register_participants() -> None:
+    """Test workflow creation using register_participants with factories."""
+
+    def create_agent1() -> Executor:
+        return _FakeAgentExec("agentA", "Alpha")
+
+    def create_agent2() -> Executor:
+        return _FakeAgentExec("agentB", "Beta")
+
+    def create_agent3() -> Executor:
+        return _FakeAgentExec("agentC", "Gamma")
+
+    wf = ConcurrentBuilder().register_participants([create_agent1, create_agent2, create_agent3]).build()
+
+    completed = False
+    output: list[ChatMessage] | None = None
+    async for ev in wf.run_stream("test prompt"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = cast(list[ChatMessage], ev.data)
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    messages: list[ChatMessage] = output
+
+    # Expect one user message + one assistant message per participant
+    assert len(messages) == 1 + 3
+    assert messages[0].role == Role.USER
+    assert "test prompt" in messages[0].text
+
+    assistant_texts = {m.text for m in messages[1:]}
+    assert assistant_texts == {"Alpha", "Beta", "Gamma"}
+    assert all(m.role == Role.ASSISTANT for m in messages[1:])
@@ -1082,3 +1082,106 @@ def test_set_manager_builds_with_agent_manager() -> None:

    assert isinstance(orchestrator, GroupChatOrchestratorExecutor)
    assert orchestrator._is_manager_agent()
+
+
+async def test_group_chat_with_request_info_filtering():
+    """Test that with_request_info(agents=[...]) only pauses before specified agents run."""
+    from agent_framework import AgentInputRequest, RequestInfoEvent
+
+    # Create agents - we want to verify only beta triggers pause
+    alpha = StubAgent("alpha", "response from alpha")
+    beta = StubAgent("beta", "response from beta")
+
+    # Manager that selects alpha first, then beta, then finishes
+    call_count = 0
+
+    async def selector(state: GroupChatStateSnapshot) -> str | None:
+        nonlocal call_count
+        call_count += 1
+        if call_count == 1:
+            return "alpha"
+        if call_count == 2:
+            return "beta"
+        return None
+
+    workflow = (
+        GroupChatBuilder()
+        .set_select_speakers_func(selector, display_name="manager", final_message="done")
+        .participants(alpha=alpha, beta=beta)
+        .with_request_info(agents=["beta"])  # Only pause before beta runs
+        .build()
+    )
+
+    # Run until we get a request info event (should be before beta, not alpha)
+    request_events: list[RequestInfoEvent] = []
+    async for event in workflow.run_stream("test task"):
+        if isinstance(event, RequestInfoEvent) and isinstance(event.data, AgentInputRequest):
+            request_events.append(event)
+            # Don't break - let stream complete naturally when paused
+
+    # Should have exactly one request event before beta
+    assert len(request_events) == 1
+    request_event = request_events[0]
+
+    # The target agent should be beta's executor ID (groupchat_agent:beta)
+    assert request_event.data.target_agent_id is not None
+    assert "beta" in request_event.data.target_agent_id
+
+    # Continue the workflow with a response
+    outputs: list[WorkflowOutputEvent] = []
+    async for event in workflow.send_responses_streaming({request_event.request_id: "continue please"}):
+        if isinstance(event, WorkflowOutputEvent):
+            outputs.append(event)
+
+    # Workflow should complete
+    assert len(outputs) == 1
+
+
+async def test_group_chat_with_request_info_no_filter_pauses_all():
+    """Test that with_request_info() without agents pauses before all participants."""
+    from agent_framework import AgentInputRequest, RequestInfoEvent
+
+    # Create agents
+    alpha = StubAgent("alpha", "response from alpha")
+
+    # Manager selects alpha then finishes
+    call_count = 0
+
+    async def selector(state: GroupChatStateSnapshot) -> str | None:
+        nonlocal call_count
+        call_count += 1
+        if call_count == 1:
+            return "alpha"
+        return None
+
+    workflow = (
+        GroupChatBuilder()
+        .set_select_speakers_func(selector, display_name="manager", final_message="done")
+        .participants(alpha=alpha)
+        .with_request_info()  # No filter - pause for all
+        .build()
+    )
+
+    # Run until we get a request info event
+    request_events: list[RequestInfoEvent] = []
+    async for event in workflow.run_stream("test task"):
+        if isinstance(event, RequestInfoEvent) and isinstance(event.data, AgentInputRequest):
+            request_events.append(event)
+            break
+
+    # Should pause before alpha
+    assert len(request_events) == 1
+    assert request_events[0].data.target_agent_id is not None
+    assert "alpha" in request_events[0].data.target_agent_id
+
+
+def test_group_chat_builder_with_request_info_returns_self():
+    """Test that with_request_info() returns self for method chaining."""
+    builder = GroupChatBuilder()
+    result = builder.with_request_info()
+    assert result is builder
+
+    # Also test with agents parameter
+    builder2 = GroupChatBuilder()
+    result2 = builder2.with_request_info(agents=["test"])
+    assert result2 is builder2
@@ -687,6 +687,54 @@ async def test_tool_choice_preserved_from_agent_config():
    assert str(last_tool_choice) == "required", f"Expected 'required', got {last_tool_choice}"


+async def test_handoff_builder_with_request_info():
+    """Test that HandoffBuilder supports request info via with_request_info()."""
+    from agent_framework import AgentInputRequest, RequestInfoEvent
+
+    # Create test agents
+    coordinator = _RecordingAgent(name="coordinator")
+    specialist = _RecordingAgent(name="specialist")
+
+    # Build workflow with request info enabled
+    workflow = (
+        HandoffBuilder(participants=[coordinator, specialist])
+        .set_coordinator("coordinator")
+        .with_termination_condition(lambda conv: len([m for m in conv if m.role == Role.USER]) >= 1)
+        .with_request_info()
+        .build()
+    )
+
+    # Run workflow until it pauses for request info
+    request_event: RequestInfoEvent | None = None
+    async for event in workflow.run_stream("Hello"):
+        if isinstance(event, RequestInfoEvent) and isinstance(event.data, AgentInputRequest):
+            request_event = event
+
+    # Verify request info was emitted
+    assert request_event is not None, "Request info should have been emitted"
+    assert isinstance(request_event.data, AgentInputRequest)
+
+    # Provide response and continue
+    output_events: list[WorkflowOutputEvent] = []
+    async for event in workflow.send_responses_streaming({request_event.request_id: "approved"}):
+        if isinstance(event, WorkflowOutputEvent):
+            output_events.append(event)
+
+    # Verify we got output events
+    assert len(output_events) > 0, "Should produce output events after response"
+
+
+async def test_handoff_builder_with_request_info_method_chaining():
+    """Test that with_request_info returns self for method chaining."""
+    coordinator = _RecordingAgent(name="coordinator")
+
+    builder = HandoffBuilder(participants=[coordinator])
+    result = builder.with_request_info()
+
+    assert result is builder, "with_request_info should return self for chaining"
+    assert builder._request_info_enabled is True  # type: ignore
+
+
 async def test_return_to_previous_state_serialization():
    """Test that return_to_previous state is properly serialized/deserialized for checkpointing."""
    from agent_framework._workflows._handoff import _HandoffCoordinator  # type: ignore[reportPrivateUsage]
@@ -857,3 +857,22 @@ async def test_magentic_checkpoint_runtime_overrides_buildtime() -> None:

        assert len(runtime_checkpoints) > 0, "Runtime storage should have checkpoints"
        assert len(buildtime_checkpoints) == 0, "Build-time storage should have no checkpoints when overridden"
+
+
+def test_magentic_builder_does_not_have_human_input_hook():
+    """Test that MagenticBuilder does not expose with_human_input_hook (uses specialized HITL instead).
+
+    Magentic uses specialized human intervention mechanisms:
+    - with_plan_review() for plan approval
+    - with_human_input_on_stall() for stall intervention
+    - Tool approval via FunctionApprovalRequestContent
+
+    These emit MagenticHumanInterventionRequest events with structured decision options.
+    """
+    builder = MagenticBuilder()
+
+    # MagenticBuilder should NOT have the generic human input hook mixin
+    assert not hasattr(builder, "with_human_input_hook"), (
+        "MagenticBuilder should not have with_human_input_hook - "
+        "use with_plan_review() or with_human_input_on_stall() instead"
+    )
@@ -0,0 +1,168 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Unit tests for request info support in high-level builders."""
+
+from typing import Any
+from unittest.mock import MagicMock
+
+from agent_framework import (
+    AgentInputRequest,
+    AgentProtocol,
+    AgentResponseReviewRequest,
+    ChatMessage,
+    RequestInfoInterceptor,
+    Role,
+)
+from agent_framework._workflows._executor import Executor, handler
+from agent_framework._workflows._orchestration_request_info import resolve_request_info_filter
+from agent_framework._workflows._workflow_context import WorkflowContext
+
+
+class DummyExecutor(Executor):
+    """Dummy executor with a handler for testing."""
+
+    @handler
+    async def handle(self, data: str, ctx: WorkflowContext[Any, Any]) -> None:
+        pass
+
+
+class TestResolveRequestInfoFilter:
+    """Tests for resolve_request_info_filter function."""
+
+    def test_returns_none_for_none_input(self):
+        """Test that None input returns None (no filtering)."""
+        result = resolve_request_info_filter(None)
+        assert result is None
+
+    def test_returns_none_for_empty_list(self):
+        """Test that empty list returns None."""
+        result = resolve_request_info_filter([])
+        assert result is None
+
+    def test_resolves_string_names(self):
+        """Test resolving string agent names."""
+        result = resolve_request_info_filter(["agent1", "agent2"])
+        assert result == {"agent1", "agent2"}
+
+    def test_resolves_executor_ids(self):
+        """Test resolving Executor instances by ID."""
+        exec1 = DummyExecutor(id="executor1")
+        exec2 = DummyExecutor(id="executor2")
+
+        result = resolve_request_info_filter([exec1, exec2])
+        assert result == {"executor1", "executor2"}
+
+    def test_resolves_agent_names(self):
+        """Test resolving AgentProtocol-like objects by name attribute."""
+        agent1 = MagicMock(spec=AgentProtocol)
+        agent1.name = "writer"
+        agent2 = MagicMock(spec=AgentProtocol)
+        agent2.name = "reviewer"
+
+        result = resolve_request_info_filter([agent1, agent2])
+        assert result == {"writer", "reviewer"}
+
+    def test_mixed_types(self):
+        """Test resolving a mix of strings, agents, and executors."""
+        agent = MagicMock(spec=AgentProtocol)
+        agent.name = "writer"
+        executor = DummyExecutor(id="custom_exec")
+
+        result = resolve_request_info_filter(["manual_name", agent, executor])
+        assert result == {"manual_name", "writer", "custom_exec"}
+
+    def test_skips_agent_without_name(self):
+        """Test that agents without names are skipped."""
+        agent_with_name = MagicMock(spec=AgentProtocol)
+        agent_with_name.name = "valid"
+        agent_without_name = MagicMock(spec=AgentProtocol)
+        agent_without_name.name = None
+
+        result = resolve_request_info_filter([agent_with_name, agent_without_name])
+        assert result == {"valid"}
+
+
+class TestAgentInputRequest:
+    """Tests for AgentInputRequest dataclass (formerly AgentResponseReviewRequest)."""
+
+    def test_create_request(self):
+        """Test creating an AgentInputRequest with all fields."""
+        conversation = [ChatMessage(role=Role.USER, text="Hello")]
+        request = AgentInputRequest(
+            target_agent_id="test_agent",
+            conversation=conversation,
+            instruction="Review this",
+            metadata={"key": "value"},
+        )
+
+        assert request.target_agent_id == "test_agent"
+        assert request.conversation == conversation
+        assert request.instruction == "Review this"
+        assert request.metadata == {"key": "value"}
+
+    def test_create_request_defaults(self):
+        """Test creating an AgentInputRequest with default values."""
+        request = AgentInputRequest(target_agent_id="test_agent")
+
+        assert request.target_agent_id == "test_agent"
+        assert request.conversation == []
+        assert request.instruction is None
+        assert request.metadata == {}
+
+    def test_backward_compatibility_alias(self):
+        """Test that AgentResponseReviewRequest is an alias for AgentInputRequest."""
+        assert AgentResponseReviewRequest is AgentInputRequest
+
+
+class TestRequestInfoInterceptor:
+    """Tests for RequestInfoInterceptor executor."""
+
+    def test_interceptor_creation_generates_unique_id(self):
+        """Test creating a RequestInfoInterceptor generates unique IDs."""
+        interceptor1 = RequestInfoInterceptor()
+        interceptor2 = RequestInfoInterceptor()
+        assert interceptor1.id.startswith("request_info_interceptor-")
+        assert interceptor2.id.startswith("request_info_interceptor-")
+        assert interceptor1.id != interceptor2.id
+
+    def test_interceptor_with_custom_id(self):
+        """Test creating a RequestInfoInterceptor with custom ID."""
+        interceptor = RequestInfoInterceptor(executor_id="custom_review")
+        assert interceptor.id == "custom_review"
+
+    def test_interceptor_with_agent_filter(self):
+        """Test creating a RequestInfoInterceptor with agent filter."""
+        agent_filter = {"agent1", "agent2"}
+        interceptor = RequestInfoInterceptor(
+            executor_id="filtered_review",
+            agent_filter=agent_filter,
+        )
+        assert interceptor.id == "filtered_review"
+        assert interceptor._agent_filter == agent_filter
+
+    def test_should_pause_for_agent_no_filter(self):
+        """Test that interceptor pauses for all agents when no filter is set."""
+        interceptor = RequestInfoInterceptor()
+        assert interceptor._should_pause_for_agent("any_agent") is True
+        assert interceptor._should_pause_for_agent("another_agent") is True
+        assert interceptor._should_pause_for_agent(None) is True
+
+    def test_should_pause_for_agent_with_filter(self):
+        """Test that interceptor only pauses for agents in the filter."""
+        agent_filter = {"writer", "reviewer"}
+        interceptor = RequestInfoInterceptor(agent_filter=agent_filter)
+
+        assert interceptor._should_pause_for_agent("writer") is True
+        assert interceptor._should_pause_for_agent("reviewer") is True
+        assert interceptor._should_pause_for_agent("drafter") is False
+        assert interceptor._should_pause_for_agent(None) is False
+
+    def test_should_pause_for_agent_with_prefixed_id(self):
+        """Test that filter matches agent names in prefixed executor IDs."""
+        agent_filter = {"writer"}
+        interceptor = RequestInfoInterceptor(agent_filter=agent_filter)
+
+        # Should match the name portion after the colon
+        assert interceptor._should_pause_for_agent("groupchat_agent:writer") is True
+        assert interceptor._should_pause_for_agent("request_info:writer") is True
+        assert interceptor._should_pause_for_agent("groupchat_agent:editor") is False
@@ -15,6 +15,7 @@ from agent_framework import (
    Role,
    SequentialBuilder,
    TextContent,
+    TypeCompatibilityError,
    WorkflowContext,
    WorkflowOutputEvent,
    WorkflowRunState,
@@ -58,11 +59,43 @@ class _SummarizerExec(Executor):
        await ctx.send_message(list(conversation) + [summary])


+class _InvalidExecutor(Executor):
+    """Invalid executor that does not have a handler that accepts a list of chat messages"""
+
+    @handler
+    async def summarize(self, conversation: list[str], ctx: WorkflowContext[list[ChatMessage]]) -> None:
+        pass
+
+
 def test_sequential_builder_rejects_empty_participants() -> None:
    with pytest.raises(ValueError):
        SequentialBuilder().participants([])


+def test_sequential_builder_rejects_empty_participant_factories() -> None:
+    with pytest.raises(ValueError):
+        SequentialBuilder().register_participants([])
+
+
+def test_sequential_builder_rejects_mixing_participants_and_factories() -> None:
+    """Test that mixing .participants() and .register_participants() raises an error."""
+    a1 = _EchoAgent(id="agent1", name="A1")
+
+    # Try .participants() then .register_participants()
+    with pytest.raises(ValueError, match="Cannot mix"):
+        SequentialBuilder().participants([a1]).register_participants([lambda: _EchoAgent(id="agent2", name="A2")])
+
+    # Try .register_participants() then .participants()
+    with pytest.raises(ValueError, match="Cannot mix"):
+        SequentialBuilder().register_participants([lambda: _EchoAgent(id="agent1", name="A1")]).participants([a1])
+
+
+def test_sequential_builder_validation_rejects_invalid_executor() -> None:
+    """Test that adding an invalid executor to the builder raises an error."""
+    with pytest.raises(TypeCompatibilityError):
+        SequentialBuilder().participants([_EchoAgent(id="agent1", name="A1"), _InvalidExecutor(id="invalid")]).build()
+
+
 async def test_sequential_agents_append_to_context() -> None:
    a1 = _EchoAgent(id="agent1", name="A1")
    a2 = _EchoAgent(id="agent2", name="A2")
@@ -91,6 +124,37 @@ async def test_sequential_agents_append_to_context() -> None:
    assert "A2 reply" in msgs[2].text


+async def test_sequential_register_participants_with_agent_factories() -> None:
+    """Test that register_participants works with agent factories."""
+
+    def create_agent1() -> _EchoAgent:
+        return _EchoAgent(id="agent1", name="A1")
+
+    def create_agent2() -> _EchoAgent:
+        return _EchoAgent(id="agent2", name="A2")
+
+    wf = SequentialBuilder().register_participants([create_agent1, create_agent2]).build()
+
+    completed = False
+    output: list[ChatMessage] | None = None
+    async for ev in wf.run_stream("hello factories"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = ev.data
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    assert isinstance(output, list)
+    msgs: list[ChatMessage] = output
+    assert len(msgs) == 3
+    assert msgs[0].role == Role.USER and "hello factories" in msgs[0].text
+    assert msgs[1].role == Role.ASSISTANT and "A1 reply" in msgs[1].text
+    assert msgs[2].role == Role.ASSISTANT and "A2 reply" in msgs[2].text
+
+
 async def test_sequential_with_custom_executor_summary() -> None:
    a1 = _EchoAgent(id="agent1", name="A1")
    summarizer = _SummarizerExec(id="summarizer")
@@ -103,7 +167,7 @@ async def test_sequential_with_custom_executor_summary() -> None:
        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
            completed = True
        elif isinstance(ev, WorkflowOutputEvent):
-            output = ev.data  # type: ignore[assignment]
+            output = ev.data
        if completed and output is not None:
            break

@@ -117,6 +181,37 @@ async def test_sequential_with_custom_executor_summary() -> None:
    assert msgs[2].role == Role.ASSISTANT and msgs[2].text.startswith("Summary of users:")


+async def test_sequential_register_participants_mixed_agents_and_executors() -> None:
+    """Test register_participants with both agent and executor factories."""
+
+    def create_agent() -> _EchoAgent:
+        return _EchoAgent(id="agent1", name="A1")
+
+    def create_summarizer() -> _SummarizerExec:
+        return _SummarizerExec(id="summarizer")
+
+    wf = SequentialBuilder().register_participants([create_agent, create_summarizer]).build()
+
+    completed = False
+    output: list[ChatMessage] | None = None
+    async for ev in wf.run_stream("topic Y"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = ev.data
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    msgs: list[ChatMessage] = output
+    # Expect: [user, A1 reply, summary]
+    assert len(msgs) == 3
+    assert msgs[0].role == Role.USER and "topic Y" in msgs[0].text
+    assert msgs[1].role == Role.ASSISTANT and "A1 reply" in msgs[1].text
+    assert msgs[2].role == Role.ASSISTANT and msgs[2].text.startswith("Summary of users:")
+
+
 async def test_sequential_checkpoint_resume_round_trip() -> None:
    storage = InMemoryCheckpointStorage()

@@ -229,3 +324,130 @@ async def test_sequential_checkpoint_runtime_overrides_buildtime() -> None:

        assert len(runtime_checkpoints) > 0, "Runtime storage should have checkpoints"
        assert len(buildtime_checkpoints) == 0, "Build-time storage should have no checkpoints when overridden"
+
+
+async def test_sequential_register_participants_with_checkpointing() -> None:
+    """Test that checkpointing works with register_participants."""
+    storage = InMemoryCheckpointStorage()
+
+    def create_agent1() -> _EchoAgent:
+        return _EchoAgent(id="agent1", name="A1")
+
+    def create_agent2() -> _EchoAgent:
+        return _EchoAgent(id="agent2", name="A2")
+
+    wf = SequentialBuilder().register_participants([create_agent1, create_agent2]).with_checkpointing(storage).build()
+
+    baseline_output: list[ChatMessage] | None = None
+    async for ev in wf.run_stream("checkpoint with factories"):
+        if isinstance(ev, WorkflowOutputEvent):
+            baseline_output = ev.data
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            break
+
+    assert baseline_output is not None
+
+    checkpoints = await storage.list_checkpoints()
+    assert checkpoints
+    checkpoints.sort(key=lambda cp: cp.timestamp)
+
+    resume_checkpoint = next(
+        (cp for cp in checkpoints if (cp.metadata or {}).get("checkpoint_type") == "superstep"),
+        checkpoints[-1],
+    )
+
+    wf_resume = (
+        SequentialBuilder().register_participants([create_agent1, create_agent2]).with_checkpointing(storage).build()
+    )
+
+    resumed_output: list[ChatMessage] | None = None
+    async for ev in wf_resume.run_stream(checkpoint_id=resume_checkpoint.checkpoint_id):
+        if isinstance(ev, WorkflowOutputEvent):
+            resumed_output = ev.data
+        if isinstance(ev, WorkflowStatusEvent) and ev.state in (
+            WorkflowRunState.IDLE,
+            WorkflowRunState.IDLE_WITH_PENDING_REQUESTS,
+        ):
+            break
+
+    assert resumed_output is not None
+    assert [m.role for m in resumed_output] == [m.role for m in baseline_output]
+    assert [m.text for m in resumed_output] == [m.text for m in baseline_output]
+
+
+async def test_sequential_register_participants_factories_called_on_build() -> None:
+    """Test that factories are called during build(), not during register_participants()."""
+    call_count = 0
+
+    def create_agent() -> _EchoAgent:
+        nonlocal call_count
+        call_count += 1
+        return _EchoAgent(id=f"agent{call_count}", name=f"A{call_count}")
+
+    builder = SequentialBuilder().register_participants([create_agent, create_agent])
+
+    # Factories should not be called yet
+    assert call_count == 0
+
+    wf = builder.build()
+
+    # Now factories should have been called
+    assert call_count == 2
+
+    # Run the workflow to ensure it works
+    completed = False
+    output: list[ChatMessage] | None = None
+    async for ev in wf.run_stream("test factories timing"):
+        if isinstance(ev, WorkflowStatusEvent) and ev.state == WorkflowRunState.IDLE:
+            completed = True
+        elif isinstance(ev, WorkflowOutputEvent):
+            output = ev.data  # type: ignore[assignment]
+        if completed and output is not None:
+            break
+
+    assert completed
+    assert output is not None
+    msgs: list[ChatMessage] = output
+    # Should have user message + 2 agent replies
+    assert len(msgs) == 3
+
+
+async def test_sequential_builder_reusable_after_build_with_participants() -> None:
+    """Test that the builder can be reused to build multiple identical workflows with participants()."""
+    a1 = _EchoAgent(id="agent1", name="A1")
+    a2 = _EchoAgent(id="agent2", name="A2")
+
+    builder = SequentialBuilder().participants([a1, a2])
+
+    # Build first workflow
+    builder.build()
+
+    assert builder._participants[0] is a1  # type: ignore
+    assert builder._participants[1] is a2  # type: ignore
+    assert builder._participant_factories == []  # type: ignore
+
+
+async def test_sequential_builder_reusable_after_build_with_factories() -> None:
+    """Test that the builder can be reused to build multiple workflows with register_participants()."""
+    call_count = 0
+
+    def create_agent1() -> _EchoAgent:
+        nonlocal call_count
+        call_count += 1
+        return _EchoAgent(id="agent1", name="A1")
+
+    def create_agent2() -> _EchoAgent:
+        nonlocal call_count
+        call_count += 1
+        return _EchoAgent(id="agent2", name="A2")
+
+    builder = SequentialBuilder().register_participants([create_agent1, create_agent2])
+
+    # Build first workflow - factories should be called
+    builder.build()
+
+    assert call_count == 2
+    assert builder._participants == []  # type: ignore
+    assert len(builder._participant_factories) == 2  # type: ignore
+    assert builder._participant_factories[0] is create_agent1  # type: ignore
+    assert builder._participant_factories[1] is create_agent2  # type: ignore
@@ -111,7 +111,8 @@ def test_add_agent_with_custom_parameters():
    builder = WorkflowBuilder()

    # Add agent with custom parameters
-    result = builder.add_agent(agent, output_response=True, id="my_custom_id")
+    with pytest.deprecated_call():
+        result = builder.add_agent(agent, output_response=True, id="my_custom_id")

    # Verify that add_agent returns the builder for chaining
    assert result is builder
@@ -133,7 +134,8 @@ def test_add_agent_reuses_same_wrapper():
    builder = WorkflowBuilder()

    # Add agent with specific parameters
-    builder.add_agent(agent, output_response=True, id="agent_exec")
+    with pytest.deprecated_call():
+        builder.add_agent(agent, output_response=True, id="agent_exec")

    # Use the same agent instance in add_edge - should reuse the same wrapper
    builder.set_start_executor(agent)
@@ -158,8 +160,9 @@ def test_add_agent_then_use_in_edges():
    builder = WorkflowBuilder()

    # Add agents with specific settings
-    builder.add_agent(agent1, output_response=False, id="exec1")
-    builder.add_agent(agent2, output_response=True, id="exec2")
+    with pytest.deprecated_call():
+        builder.add_agent(agent1, output_response=False, id="exec1")
+        builder.add_agent(agent2, output_response=True, id="exec2")

    # Use the same agent instances to create edges
    workflow = builder.set_start_executor(agent1).add_edge(agent1, agent2).build()
@@ -183,7 +186,8 @@ def test_add_agent_without_explicit_id_uses_agent_name():
    agent = DummyAgent(id="agent_x", name="named_agent")
    builder = WorkflowBuilder()

-    result = builder.add_agent(agent)
+    with pytest.deprecated_call():
+        result = builder.add_agent(agent)

    # Verify that add_agent returns the builder for chaining
    assert result is builder
@@ -203,10 +207,11 @@ def test_add_agent_duplicate_id_raises_error():
    builder = WorkflowBuilder()

    # Add first agent
-    builder.add_agent(agent1)
+    with pytest.deprecated_call():
+        builder.add_agent(agent1)

    # Adding second agent with same name should raise ValueError
-    with pytest.raises(ValueError, match="Duplicate executor ID"):
+    with pytest.deprecated_call(), pytest.raises(ValueError, match="Duplicate executor ID"):
        builder.add_agent(agent2)


@@ -288,6 +293,20 @@ def test_register_duplicate_name_raises_error():
        builder.register_executor(lambda: MockExecutor(id="executor_2"), name="MyExecutor")


+def test_register_duplicate_id_raises_error():
+    """Test that registering duplicate id raises an error."""
+    builder = WorkflowBuilder()
+
+    # Register first executor
+    builder.register_executor(lambda: MockExecutor(id="executor"), name="MyExecutor1")
+    builder.register_executor(lambda: MockExecutor(id="executor"), name="MyExecutor2")
+    builder.set_start_executor("MyExecutor1")
+
+    # Registering second executor with same ID should raise ValueError
+    with pytest.raises(ValueError, match="Executor with ID 'executor' has already been created."):
+        builder.build()
+
+
 def test_register_agent_basic():
    """Test basic agent registration with lazy initialization."""
    builder = WorkflowBuilder()
@@ -4,7 +4,7 @@ description = "Declarative specification support for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Debug UI for Microsoft Agent Framework with OpenAI-compatible API
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Experimental modules for Microsoft Agent Framework"
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Mem0 integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Microsoft Purview (Graph dataSecurityAndGovernance) integration f
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://github.com/microsoft/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Redis integration for Microsoft Agent Framework."
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -4,7 +4,7 @@ description = "Microsoft Agent Framework for building AI Agents with Python. Thi
 authors = [{ name = "Microsoft", email = "af-support@microsoft.com"}]
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 license-files = ["LICENSE"]
 urls.homepage = "https://aka.ms/agent-framework"
 urls.source = "https://github.com/microsoft/agent-framework/tree/main/python"
@@ -23,7 +23,7 @@ classifiers = [
  "Typing :: Typed",
 ]
 dependencies = [
-    "agent-framework-core[all]==1.0.0b251209",
+    "agent-framework-core[all]==1.0.0b251211",
 ]

 [dependency-groups]
@@ -25,6 +25,7 @@ This directory contains samples demonstrating the capabilities of Microsoft Agen
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_azure_ai_search.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_azure_ai_search.py) | Azure AI Agent with Azure AI Search Example |
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_bing_grounding.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_bing_grounding.py) | Azure AI agent with Bing Grounding search for real-time web information |
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter.py) | Azure AI Agent with Code Interpreter Example |
+| [`getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter_file_generation.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter_file_generation.py) | Azure AI Agent with Code Interpreter File Generation Example |
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_existing_agent.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_existing_agent.py) | Azure AI Agent with Existing Agent Example |
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_existing_thread.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_existing_thread.py) | Azure AI Agent with Existing Thread Example |
 | [`getting_started/agents/azure_ai_agent/azure_ai_with_explicit_settings.py`](./getting_started/agents/azure_ai_agent/azure_ai_with_explicit_settings.py) | Azure AI Agent with Explicit Settings Example |
@@ -47,6 +48,7 @@ This directory contains samples demonstrating the capabilities of Microsoft Agen
 | [`getting_started/agents/azure_ai/azure_ai_with_bing_custom_search.py`](./getting_started/agents/azure_ai/azure_ai_with_bing_custom_search.py) | Azure AI Agent with Bing Custom Search Example |
 | [`getting_started/agents/azure_ai/azure_ai_with_browser_automation.py`](./getting_started/agents/azure_ai/azure_ai_with_browser_automation.py) | Azure AI Agent with Browser Automation Example |
 | [`getting_started/agents/azure_ai/azure_ai_with_code_interpreter.py`](./getting_started/agents/azure_ai/azure_ai_with_code_interpreter.py) | Azure AI Agent with Code Interpreter Example |
+| [`getting_started/agents/azure_ai/azure_ai_with_code_interpreter_file_generation.py`](./getting_started/agents/azure_ai/azure_ai_with_code_interpreter_file_generation.py) | Azure AI Agent with Code Interpreter File Generation Example |
 | [`getting_started/agents/azure_ai/azure_ai_with_existing_agent.py`](./getting_started/agents/azure_ai/azure_ai_with_existing_agent.py) | Azure AI Agent with Existing Agent Example |
 | [`getting_started/agents/azure_ai/azure_ai_with_existing_conversation.py`](./getting_started/agents/azure_ai/azure_ai_with_existing_conversation.py) | Azure AI Agent with Existing Conversation Example |
 | [`getting_started/agents/azure_ai/azure_ai_with_explicit_settings.py`](./getting_started/agents/azure_ai/azure_ai_with_explicit_settings.py) | Azure AI Agent with Explicit Settings Example |
@@ -33,7 +33,7 @@ Try to over-document the samples. This includes comments in the code, README.md
 For the getting started samples and the concept samples, we should have the following:

 1. A README.md file is included in each set of samples that explains the purpose of the samples and the setup required to run them.
-2. A summary should be included at the top of the file that explains the purpose of the sample and required components/concepts to understand the sample. For example:
+2. A summary should be included underneath the imports that explains the purpose of the sample and required components/concepts to understand the sample. For example:

    ```python
    '''
@@ -14,6 +14,7 @@ This folder contains examples demonstrating different ways to create and use age
 | [`azure_ai_with_bing_custom_search.py`](azure_ai_with_bing_custom_search.py) | Shows how to use Bing Custom Search with Azure AI agents to search custom search instances and provide responses with relevant results. Requires a Bing Custom Search connection and instance configured in your Azure AI project. |
 | [`azure_ai_with_browser_automation.py`](azure_ai_with_browser_automation.py) | Shows how to use Browser Automation with Azure AI agents to perform automated web browsing tasks and provide responses based on web interactions. Requires a Browser Automation connection configured in your Azure AI project. |
 | [`azure_ai_with_code_interpreter.py`](azure_ai_with_code_interpreter.py) | Shows how to use the `HostedCodeInterpreterTool` with Azure AI agents to write and execute Python code for mathematical problem solving and data analysis. |
+| [`azure_ai_with_code_interpreter_file_generation.py`](azure_ai_with_code_interpreter_file_generation.py) | Shows how to retrieve file IDs from code interpreter generated files using both streaming and non-streaming approaches. |
 | [`azure_ai_with_existing_agent.py`](azure_ai_with_existing_agent.py) | Shows how to work with a pre-existing agent by providing the agent name and version to the Azure AI client. Demonstrates agent reuse patterns for production scenarios. |
 | [`azure_ai_with_existing_conversation.py`](azure_ai_with_existing_conversation.py) | Demonstrates how to use an existing conversation created on the service side with Azure AI agents. Shows two approaches: specifying conversation ID at the client level and using AgentThread with an existing conversation ID. |
 | [`azure_ai_with_application_endpoint.py`](azure_ai_with_application_endpoint.py) | Demonstrates calling the Azure AI application-scoped endpoint. |
@@ -0,0 +1,111 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from agent_framework import (
+    CitationAnnotation,
+    HostedCodeInterpreterTool,
+    HostedFileContent,
+    TextContent,
+)
+from agent_framework._agents import AgentRunResponseUpdate
+from agent_framework.azure import AzureAIClient
+from azure.identity.aio import AzureCliCredential
+
+"""
+Azure AI V2 Code Interpreter File Generation Sample
+
+This sample demonstrates how the V2 AzureAIClient handles file annotations
+when code interpreter generates text files. It shows both non-streaming
+and streaming approaches to verify file ID extraction.
+"""
+
+QUERY = (
+    "Write a simple Python script that creates a text file called 'sample.txt' containing "
+    "'Hello from the code interpreter!' and save it to disk."
+)
+
+
+async def test_non_streaming() -> None:
+    """Test non-streaming response - should have annotations on TextContent."""
+    print("=== Testing Non-Streaming Response ===")
+
+    async with (
+        AzureCliCredential() as credential,
+        AzureAIClient(credential=credential).create_agent(
+            name="V2CodeInterpreterFileAgent",
+            instructions="You are a helpful assistant that can write and execute Python code to create files.",
+            tools=HostedCodeInterpreterTool(),
+        ) as agent,
+    ):
+        print(f"User: {QUERY}\n")
+
+        result = await agent.run(QUERY)
+        print(f"Agent: {result.text}\n")
+
+        # Check for annotations in the response
+        annotations_found: list[str] = []
+        # AgentRunResponse has messages property, which contains ChatMessage objects
+        for message in result.messages:
+            for content in message.contents:
+                if isinstance(content, TextContent) and content.annotations:
+                    for annotation in content.annotations:
+                        if isinstance(annotation, CitationAnnotation) and annotation.file_id:
+                            annotations_found.append(annotation.file_id)
+                            print(f"Found file annotation: file_id={annotation.file_id}")
+
+        if annotations_found:
+            print(f"SUCCESS: Found {len(annotations_found)} file annotation(s)")
+        else:
+            print("WARNING: No file annotations found in non-streaming response")
+
+
+async def test_streaming() -> None:
+    """Test streaming response - check if file content is captured via HostedFileContent."""
+    print("\n=== Testing Streaming Response ===")
+
+    async with (
+        AzureCliCredential() as credential,
+        AzureAIClient(credential=credential).create_agent(
+            name="V2CodeInterpreterFileAgentStreaming",
+            instructions="You are a helpful assistant that can write and execute Python code to create files.",
+            tools=HostedCodeInterpreterTool(),
+        ) as agent,
+    ):
+        print(f"User: {QUERY}\n")
+        annotations_found: list[str] = []
+        text_chunks: list[str] = []
+        file_ids_found: list[str] = []
+
+        async for update in agent.run_stream(QUERY):
+            if isinstance(update, AgentRunResponseUpdate):
+                for content in update.contents:
+                    if isinstance(content, TextContent):
+                        if content.text:
+                            text_chunks.append(content.text)
+                        if content.annotations:
+                            for annotation in content.annotations:
+                                if isinstance(annotation, CitationAnnotation) and annotation.file_id:
+                                    annotations_found.append(annotation.file_id)
+                                    print(f"Found streaming annotation: file_id={annotation.file_id}")
+                    elif isinstance(content, HostedFileContent):
+                        file_ids_found.append(content.file_id)
+                        print(f"Found streaming HostedFileContent: file_id={content.file_id}")
+
+        print(f"\nAgent response: {''.join(text_chunks)[:200]}...")
+
+        if annotations_found or file_ids_found:
+            total = len(annotations_found) + len(file_ids_found)
+            print(f"SUCCESS: Found {total} file reference(s) in streaming")
+        else:
+            print("WARNING: No file annotations found in streaming response")
+
+
+async def main() -> None:
+    print("AzureAIClient Code Interpreter File Generation Test\n")
+    await test_non_streaming()
+    await test_streaming()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -9,6 +9,7 @@ This folder contains examples demonstrating different ways to create and use age
 | [`azure_ai_basic.py`](azure_ai_basic.py) | The simplest way to create an agent using `ChatAgent` with `AzureAIAgentClient`. It automatically handles all configuration using environment variables. |
 | [`azure_ai_with_bing_custom_search.py`](azure_ai_with_bing_custom_search.py) | Shows how to use Bing Custom Search with Azure AI agents to find real-time information from the web using custom search configurations. Demonstrates how to set up and use HostedWebSearchTool with custom search instances. |
 | [`azure_ai_with_bing_grounding.py`](azure_ai_with_bing_grounding.py) | Shows how to use Bing Grounding search with Azure AI agents to find real-time information from the web. Demonstrates web search capabilities with proper source citations and comprehensive error handling. |
+| [`azure_ai_with_code_interpreter_file_generation.py`](azure_ai_with_code_interpreter_file_generation.py) | Shows how to retrieve file IDs from code interpreter generated files using both streaming and non-streaming approaches. |
 | [`azure_ai_with_code_interpreter.py`](azure_ai_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure AI agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
 | [`azure_ai_with_existing_agent.py`](azure_ai_with_existing_agent.py) | Shows how to work with a pre-existing agent by providing the agent ID to the Azure AI chat client. This example also demonstrates proper cleanup of manually created agents. |
 | [`azure_ai_with_existing_thread.py`](azure_ai_with_existing_thread.py) | Shows how to work with a pre-existing thread by providing the thread ID to the Azure AI chat client. This example also demonstrates proper cleanup of manually created threads. |
@@ -0,0 +1,102 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from agent_framework import AgentRunResponseUpdate, ChatAgent, HostedCodeInterpreterTool, HostedFileContent
+from agent_framework.azure import AzureAIAgentClient
+from azure.identity.aio import AzureCliCredential
+
+"""
+Azure AI Agent Code Interpreter File Generation Example
+
+This sample demonstrates using HostedCodeInterpreterTool with AzureAIAgentClient
+to generate a text file and then retrieve it.
+
+The test flow:
+1. Create an agent with code interpreter tool
+2. Ask the agent to generate a txt file using Python code
+3. Capture the file_id from HostedFileContent in the response
+4. Retrieve the file using the agents_client.files API
+"""
+
+
+async def main() -> None:
+    """Test file generation and retrieval with code interpreter."""
+
+    async with AzureCliCredential() as credential:
+        client = AzureAIAgentClient(credential=credential)
+
+        try:
+            async with ChatAgent(
+                chat_client=client,
+                instructions=(
+                    "You are a Python code execution assistant. "
+                    "ALWAYS use the code interpreter tool to execute Python code when asked to create files. "
+                    "Write actual Python code to create files, do not just describe what you would do."
+                ),
+                tools=[HostedCodeInterpreterTool()],
+            ) as agent:
+                # Be very explicit about wanting code execution and a download link
+                query = (
+                    "Use the code interpreter to execute this Python code and then provide me "
+                    "with a download link for the generated file:\n"
+                    "```python\n"
+                    "with open('/mnt/data/sample.txt', 'w') as f:\n"
+                    "    f.write('Hello, World! This is a test file.')\n"
+                    "'/mnt/data/sample.txt'\n"  # Return the path so it becomes downloadable
+                    "```"
+                )
+                print(f"User: {query}\n")
+                print("=" * 60)
+
+                # Collect file_ids from the response
+                file_ids: list[str] = []
+
+                async for chunk in agent.run_stream(query):
+                    if not isinstance(chunk, AgentRunResponseUpdate):
+                        continue
+
+                    for content in chunk.contents:
+                        if content.type == "text":
+                            print(content.text, end="", flush=True)
+                        elif content.type == "hosted_file":
+                            if isinstance(content, HostedFileContent):
+                                file_ids.append(content.file_id)
+                                print(f"\n[File generated: {content.file_id}]")
+
+                print("\n" + "=" * 60)
+
+                # Attempt to retrieve discovered files
+                if file_ids:
+                    print(f"\nAttempting to retrieve {len(file_ids)} file(s):")
+                    for file_id in file_ids:
+                        try:
+                            file_info = await client.agents_client.files.get(file_id)
+                            print(f"  File {file_id}: Retrieved successfully")
+                            print(f"    Filename: {file_info.filename}")
+                            print(f"    Purpose: {file_info.purpose}")
+                            print(f"    Bytes: {file_info.bytes}")
+                        except Exception as e:
+                            print(f"  File {file_id}: FAILED to retrieve - {e}")
+                else:
+                    print("No file IDs were captured from the response.")
+
+                # List all files to see if any exist
+                print("\nListing all files in the agent service:")
+                try:
+                    files_list = await client.agents_client.files.list()
+                    count = 0
+                    for file_info in files_list.data:
+                        count += 1
+                        print(f"  - {file_info.id}: {file_info.filename} ({file_info.purpose})")
+                    if count == 0:
+                        print("  No files found.")
+                except Exception as e:
+                    print(f"  Failed to list files: {e}")
+
+        finally:
+            await client.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -78,9 +78,22 @@ Once comfortable with these, explore the rest of the samples below.

 | Sample | File | Concepts |
 |---|---|---|
-| Human-In-The-Loop (Guessing Game) | [human-in-the-loop/guessing_game_with_human_input.py](./human-in-the-loop/guessing_game_with_human_input.py) | Interactive request/response prompts with a human |
-| Azure Agents Tool Feedback Loop | [agents/azure_chat_agents_tool_calls_with_feedback.py](./agents/azure_chat_agents_tool_calls_with_feedback.py) | Two-agent workflow that streams tool calls and pauses for human guidance between passes |
+| Human-In-The-Loop (Guessing Game) | [human-in-the-loop/guessing_game_with_human_input.py](./human-in-the-loop/guessing_game_with_human_input.py) | Interactive request/response prompts with a human via `ctx.request_info()` |
 | Agents with Approval Requests in Workflows | [human-in-the-loop/agents_with_approval_requests.py](./human-in-the-loop/agents_with_approval_requests.py) | Agents that create approval requests during workflow execution and wait for human approval to proceed |
+| SequentialBuilder Request Info | [human-in-the-loop/sequential_request_info.py](./human-in-the-loop/sequential_request_info.py) | Request info for agent responses mid-workflow using `.with_request_info()` on SequentialBuilder |
+| ConcurrentBuilder Request Info | [human-in-the-loop/concurrent_request_info.py](./human-in-the-loop/concurrent_request_info.py) | Review concurrent agent outputs before aggregation using `.with_request_info()` on ConcurrentBuilder |
+| GroupChatBuilder Request Info | [human-in-the-loop/group_chat_request_info.py](./human-in-the-loop/group_chat_request_info.py) | Steer group discussions with periodic guidance using `.with_request_info()` on GroupChatBuilder |
+
+
+### tool-approval
+
+Tool approval samples demonstrate using `@ai_function(approval_mode="always_require")` to gate sensitive tool executions with human approval. These work with the high-level builder APIs.
+
+| Sample | File | Concepts |
+|---|---|---|
+| SequentialBuilder Tool Approval | [tool-approval/sequential_builder_tool_approval.py](./tool-approval/sequential_builder_tool_approval.py) | Sequential workflow with tool approval gates for sensitive operations |
+| ConcurrentBuilder Tool Approval | [tool-approval/concurrent_builder_tool_approval.py](./tool-approval/concurrent_builder_tool_approval.py) | Concurrent workflow with tool approvals across parallel agents |
+| GroupChatBuilder Tool Approval | [tool-approval/group_chat_builder_tool_approval.py](./tool-approval/group_chat_builder_tool_approval.py) | Group chat workflow with tool approval for multi-agent collaboration |

 ### observability

@@ -97,6 +110,7 @@ For additional observability samples in Agent Framework, see the [observability
 | Concurrent Orchestration (Default Aggregator) | [orchestration/concurrent_agents.py](./orchestration/concurrent_agents.py) | Fan-out to multiple agents; fan-in with default aggregator returning combined ChatMessages |
 | Concurrent Orchestration (Custom Aggregator) | [orchestration/concurrent_custom_aggregator.py](./orchestration/concurrent_custom_aggregator.py) | Override aggregator via callback; summarize results with an LLM |
 | Concurrent Orchestration (Custom Agent Executors) | [orchestration/concurrent_custom_agent_executors.py](./orchestration/concurrent_custom_agent_executors.py) | Child executors own ChatAgents; concurrent fan-out/fan-in via ConcurrentBuilder |
+| Concurrent Orchestration (Participant Factory) | [orchestration/concurrent_participant_factory.py](./orchestration/concurrent_participant_factory.py) | Use participant factories for state isolation between workflow instances |
 | Group Chat with Agent Manager | [orchestration/group_chat_agent_manager.py](./orchestration/group_chat_agent_manager.py) | Agent-based manager using `set_manager()` to select next speaker |
 | Group Chat Philosophical Debate | [orchestration/group_chat_philosophical_debate.py](./orchestration/group_chat_philosophical_debate.py) | Agent manager moderates long-form, multi-round debate across diverse participants |
 | Group Chat with Simple Function Selector | [orchestration/group_chat_simple_selector.py](./orchestration/group_chat_simple_selector.py) | Group chat with a simple function selector for next speaker |
@@ -111,6 +125,7 @@ For additional observability samples in Agent Framework, see the [observability
 | Magentic + Checkpoint Resume | [orchestration/magentic_checkpoint.py](./orchestration/magentic_checkpoint.py) | Resume Magentic orchestration from saved checkpoints |
 | Sequential Orchestration (Agents) | [orchestration/sequential_agents.py](./orchestration/sequential_agents.py) | Chain agents sequentially with shared conversation context |
 | Sequential Orchestration (Custom Executor) | [orchestration/sequential_custom_executors.py](./orchestration/sequential_custom_executors.py) | Mix agents with a summarizer that appends a compact summary |
+| Sequential Orchestration (Participant Factories) | [orchestration/sequential_participant_factory.py](./orchestration/sequential_participant_factory.py) | Use participant factories for state isolation between workflow instances |

 **Magentic checkpointing tip**: Treat `MagenticBuilder.participants` keys as stable identifiers. When resuming from a checkpoint, the rebuilt workflow must reuse the same participant names; otherwise the checkpoint cannot be applied and the run will fail fast.

@@ -0,0 +1,198 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""
+Sample: Request Info with ConcurrentBuilder
+
+This sample demonstrates using the `.with_request_info()` method to pause a
+ConcurrentBuilder workflow AFTER all parallel agents complete but BEFORE
+aggregation, allowing human review and modification of the combined results.
+
+Purpose:
+Show how to use the request info API that pauses after concurrent agents run,
+allowing review and steering of results before they are aggregated.
+
+Demonstrate:
+- Configuring request info with `.with_request_info()`
+- Reviewing outputs from multiple concurrent agents
+- Injecting human guidance after agents execute but before aggregation
+
+Prerequisites:
+- Azure OpenAI configured for AzureOpenAIChatClient with required environment variables
+- Authentication via azure-identity (run az login before executing)
+"""
+
+import asyncio
+from typing import Any
+
+from agent_framework import (
+    AgentInputRequest,
+    ChatMessage,
+    ConcurrentBuilder,
+    RequestInfoEvent,
+    Role,
+    WorkflowOutputEvent,
+    WorkflowRunState,
+    WorkflowStatusEvent,
+)
+from agent_framework._workflows._agent_executor import AgentExecutorResponse
+from agent_framework.azure import AzureOpenAIChatClient
+from azure.identity import AzureCliCredential
+
+# Store chat client at module level for aggregator access
+_chat_client: AzureOpenAIChatClient | None = None
+
+
+async def aggregate_with_synthesis(results: list[AgentExecutorResponse]) -> Any:
+    """Custom aggregator that synthesizes concurrent agent outputs using an LLM.
+
+    This aggregator extracts the outputs from each parallel agent and uses the
+    chat client to create a unified summary, incorporating any human feedback
+    that was injected into the conversation.
+
+    Args:
+        results: List of responses from all concurrent agents
+
+    Returns:
+        The synthesized summary text
+    """
+    if not _chat_client:
+        return "Error: Chat client not initialized"
+
+    # Extract each agent's final output
+    expert_sections: list[str] = []
+    human_guidance = ""
+
+    for r in results:
+        try:
+            messages = getattr(r.agent_run_response, "messages", [])
+            final_text = messages[-1].text if messages and hasattr(messages[-1], "text") else "(no content)"
+            expert_sections.append(f"{getattr(r, 'executor_id', 'analyst')}:\n{final_text}")
+
+            # Check for human feedback in the conversation (will be last user message if present)
+            if r.full_conversation:
+                for msg in reversed(r.full_conversation):
+                    if msg.role == Role.USER and msg.text and "perspectives" not in msg.text.lower():
+                        human_guidance = msg.text
+                        break
+        except Exception:
+            expert_sections.append(f"{getattr(r, 'executor_id', 'analyst')}: (error extracting output)")
+
+    # Build prompt with human guidance if provided
+    guidance_text = f"\n\nHuman guidance: {human_guidance}" if human_guidance else ""
+
+    system_msg = ChatMessage(
+        Role.SYSTEM,
+        text=(
+            "You are a synthesis expert. Consolidate the following analyst perspectives "
+            "into one cohesive, balanced summary (3-4 sentences). If human guidance is provided, "
+            "prioritize aspects as directed."
+        ),
+    )
+    user_msg = ChatMessage(Role.USER, text="\n\n".join(expert_sections) + guidance_text)
+
+    response = await _chat_client.get_response([system_msg, user_msg])
+    return response.messages[-1].text if response.messages else ""
+
+
+async def main() -> None:
+    global _chat_client
+    _chat_client = AzureOpenAIChatClient(credential=AzureCliCredential())
+
+    # Create agents that analyze from different perspectives
+    technical_analyst = _chat_client.create_agent(
+        name="technical_analyst",
+        instructions=(
+            "You are a technical analyst. When given a topic, provide a technical "
+            "perspective focusing on implementation details, performance, and architecture. "
+            "Keep your analysis to 2-3 sentences."
+        ),
+    )
+
+    business_analyst = _chat_client.create_agent(
+        name="business_analyst",
+        instructions=(
+            "You are a business analyst. When given a topic, provide a business "
+            "perspective focusing on ROI, market impact, and strategic value. "
+            "Keep your analysis to 2-3 sentences."
+        ),
+    )
+
+    user_experience_analyst = _chat_client.create_agent(
+        name="ux_analyst",
+        instructions=(
+            "You are a UX analyst. When given a topic, provide a user experience "
+            "perspective focusing on usability, accessibility, and user satisfaction. "
+            "Keep your analysis to 2-3 sentences."
+        ),
+    )
+
+    # Build workflow with request info enabled and custom aggregator
+    workflow = (
+        ConcurrentBuilder()
+        .participants([technical_analyst, business_analyst, user_experience_analyst])
+        .with_aggregator(aggregate_with_synthesis)
+        .with_request_info()
+        .build()
+    )
+
+    # Run the workflow with human-in-the-loop
+    pending_responses: dict[str, str] | None = None
+    workflow_complete = False
+
+    print("Starting multi-perspective analysis workflow...")
+    print("=" * 60)
+
+    while not workflow_complete:
+        # Run or continue the workflow
+        stream = (
+            workflow.send_responses_streaming(pending_responses)
+            if pending_responses
+            else workflow.run_stream("Analyze the impact of large language models on software development.")
+        )
+
+        pending_responses = None
+
+        # Process events
+        async for event in stream:
+            if isinstance(event, RequestInfoEvent):
+                if isinstance(event.data, AgentInputRequest):
+                    # Display pre-execution context for steering concurrent agents
+                    print("\n" + "-" * 40)
+                    print("INPUT REQUESTED (BEFORE CONCURRENT AGENTS)")
+                    print("-" * 40)
+                    print(f"About to call agents: {event.data.target_agent_id}")
+                    print("Conversation context:")
+                    recent = (
+                        event.data.conversation[-2:] if len(event.data.conversation) > 2 else event.data.conversation
+                    )
+                    for msg in recent:
+                        role = msg.role.value if msg.role else "unknown"
+                        text = (msg.text or "")[:150]
+                        print(f"  [{role}]: {text}...")
+                    print("-" * 40)
+
+                    # Get human input to steer all agents
+                    user_input = input("Your guidance for the analysts (or 'skip' to continue): ")  # noqa: ASYNC250
+                    if user_input.lower() == "skip":
+                        user_input = "Please analyze objectively from your unique perspective."
+
+                    pending_responses = {event.request_id: user_input}
+                    print("(Resuming workflow...)")
+
+            elif isinstance(event, WorkflowOutputEvent):
+                print("\n" + "=" * 60)
+                print("WORKFLOW COMPLETE")
+                print("=" * 60)
+                print("Aggregated output:")
+                # Custom aggregator returns a string
+                if event.data:
+                    print(event.data)
+                workflow_complete = True
+
+            elif isinstance(event, WorkflowStatusEvent):
+                if event.state == WorkflowRunState.IDLE:
+                    workflow_complete = True
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,175 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""
+Sample: Request Info with GroupChatBuilder
+
+This sample demonstrates using the `.with_request_info()` method to pause a
+GroupChatBuilder workflow BEFORE specific participants speak. By using the
+`agents=` filter parameter, you can target only certain participants rather
+than pausing before every turn.
+
+Purpose:
+Show how to use the request info API with selective filtering to pause before
+specific participants speak, allowing human input to steer their response.
+
+Demonstrate:
+- Configuring request info with `.with_request_info(agents=[...])`
+- Using agent filtering to reduce interruptions
+- Steering agent behavior with pre-agent human input
+
+Prerequisites:
+- Azure OpenAI configured for AzureOpenAIChatClient with required environment variables
+- Authentication via azure-identity (run az login before executing)
+"""
+
+import asyncio
+
+from agent_framework import (
+    AgentInputRequest,
+    AgentRunUpdateEvent,
+    ChatMessage,
+    GroupChatBuilder,
+    RequestInfoEvent,
+    WorkflowOutputEvent,
+    WorkflowRunState,
+    WorkflowStatusEvent,
+)
+from agent_framework.azure import AzureOpenAIChatClient
+from azure.identity import AzureCliCredential
+
+
+async def main() -> None:
+    chat_client = AzureOpenAIChatClient(credential=AzureCliCredential())
+
+    # Create agents for a group discussion
+    optimist = chat_client.create_agent(
+        name="optimist",
+        instructions=(
+            "You are an optimistic team member. You see opportunities and potential "
+            "in ideas. Engage constructively with the discussion, building on others' "
+            "points while maintaining a positive outlook. Keep responses to 2-3 sentences."
+        ),
+    )
+
+    pragmatist = chat_client.create_agent(
+        name="pragmatist",
+        instructions=(
+            "You are a pragmatic team member. You focus on practical implementation "
+            "and realistic timelines. Sometimes you disagree with overly optimistic views. "
+            "Keep responses to 2-3 sentences."
+        ),
+    )
+
+    creative = chat_client.create_agent(
+        name="creative",
+        instructions=(
+            "You are a creative team member. You propose innovative solutions and "
+            "think outside the box. You may suggest alternatives to conventional approaches. "
+            "Keep responses to 2-3 sentences."
+        ),
+    )
+
+    # Manager orchestrates the discussion
+    manager = chat_client.create_agent(
+        name="manager",
+        instructions=(
+            "You are a discussion manager coordinating a team conversation between optimist, "
+            "pragmatist, and creative. Your job is to select who speaks next.\n\n"
+            "RULES:\n"
+            "1. Rotate through ALL participants - do not favor any single participant\n"
+            "2. Each participant should speak at least once before any participant speaks twice\n"
+            "3. If human feedback redirects the topic, acknowledge it and continue rotating\n"
+            "4. Continue for at least 5 participant turns before concluding\n"
+            "5. Do NOT select the same participant twice in a row"
+        ),
+    )
+
+    # Build workflow with request info enabled
+    # Using agents= filter to only pause before pragmatist speaks (not every turn)
+    workflow = (
+        GroupChatBuilder()
+        .set_manager(manager=manager, display_name="Discussion Manager")
+        .participants([optimist, pragmatist, creative])
+        .with_max_rounds(6)
+        .with_request_info(agents=[pragmatist])  # Only pause before pragmatist speaks
+        .build()
+    )
+
+    # Run the workflow with human-in-the-loop
+    pending_responses: dict[str, str] | None = None
+    workflow_complete = False
+    current_agent: str | None = None  # Track current streaming agent
+
+    print("Starting group discussion workflow...")
+    print("=" * 60)
+
+    while not workflow_complete:
+        # Run or continue the workflow
+        stream = (
+            workflow.send_responses_streaming(pending_responses)
+            if pending_responses
+            else workflow.run_stream(
+                "Discuss how our team should approach adopting AI tools for productivity. "
+                "Consider benefits, risks, and implementation strategies."
+            )
+        )
+
+        pending_responses = None
+
+        # Process events
+        async for event in stream:
+            if isinstance(event, AgentRunUpdateEvent):
+                # Show all agent responses as they stream
+                if event.data and event.data.text:
+                    agent_name = event.data.author_name or "unknown"
+                    # Print agent name header only when agent changes
+                    if agent_name != current_agent:
+                        current_agent = agent_name
+                        print(f"\n[{agent_name}]: ", end="", flush=True)
+                    print(event.data.text, end="", flush=True)
+
+            elif isinstance(event, RequestInfoEvent):
+                current_agent = None  # Reset for next agent
+                if isinstance(event.data, AgentInputRequest):
+                    # Display pre-agent context for human input
+                    print("\n" + "-" * 40)
+                    print("INPUT REQUESTED")
+                    print(f"About to call agent: {event.data.target_agent_id}")
+                    print("-" * 40)
+                    print("Conversation context:")
+                    recent = (
+                        event.data.conversation[-3:] if len(event.data.conversation) > 3 else event.data.conversation
+                    )
+                    for msg in recent:
+                        role = msg.role.value if msg.role else "unknown"
+                        text = (msg.text or "")[:100]
+                        print(f"  [{role}]: {text}...")
+                    print("-" * 40)
+
+                    # Get human input to steer the agent
+                    user_input = input("Steer the discussion (or 'skip' to continue): ")  # noqa: ASYNC250
+                    if user_input.lower() == "skip":
+                        user_input = "Please continue the discussion naturally."
+
+                    pending_responses = {event.request_id: user_input}
+                    print("(Resuming discussion...)")
+
+            elif isinstance(event, WorkflowOutputEvent):
+                print("\n" + "=" * 60)
+                print("DISCUSSION COMPLETE")
+                print("=" * 60)
+                print("Final conversation:")
+                if event.data:
+                    messages: list[ChatMessage] = event.data[-4:]
+                    for msg in messages:
+                        role = msg.role.value if msg.role else "unknown"
+                        text = (msg.text or "")[:200]
+                        print(f"[{role}]: {text}...")
+                workflow_complete = True
+
+            elif isinstance(event, WorkflowStatusEvent) and event.state == WorkflowRunState.IDLE:
+                workflow_complete = True
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,128 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""
+Sample: Request Info with SequentialBuilder
+
+This sample demonstrates using the `.with_request_info()` method to pause a
+SequentialBuilder workflow BEFORE each agent runs, allowing external input
+(e.g., human steering) before the agent responds.
+
+Purpose:
+Show how to use the request info API that pauses before every agent response,
+using the standard request_info pattern for consistency.
+
+Demonstrate:
+- Configuring request info with `.with_request_info()`
+- Handling RequestInfoEvent with AgentInputRequest data
+- Injecting responses back into the workflow via send_responses_streaming
+
+Prerequisites:
+- Azure OpenAI configured for AzureOpenAIChatClient with required environment variables
+- Authentication via azure-identity (run az login before executing)
+"""
+
+import asyncio
+
+from agent_framework import (
+    AgentInputRequest,
+    ChatMessage,
+    RequestInfoEvent,
+    SequentialBuilder,
+    WorkflowOutputEvent,
+    WorkflowRunState,
+    WorkflowStatusEvent,
+)
+from agent_framework.azure import AzureOpenAIChatClient
+from azure.identity import AzureCliCredential
+
+
+async def main() -> None:
+    chat_client = AzureOpenAIChatClient(credential=AzureCliCredential())
+
+    # Create agents for a sequential document review workflow
+    drafter = chat_client.create_agent(
+        name="drafter",
+        instructions=("You are a document drafter. When given a topic, create a brief draft (2-3 sentences)."),
+    )
+
+    editor = chat_client.create_agent(
+        name="editor",
+        instructions=(
+            "You are an editor. Review the draft and suggest improvements. "
+            "Incorporate any human feedback that was provided."
+        ),
+    )
+
+    finalizer = chat_client.create_agent(
+        name="finalizer",
+        instructions=(
+            "You are a finalizer. Take the edited content and create a polished final version. "
+            "Incorporate any additional feedback provided."
+        ),
+    )
+
+    # Build workflow with request info enabled (pauses before each agent)
+    workflow = SequentialBuilder().participants([drafter, editor, finalizer]).with_request_info().build()
+
+    # Run the workflow with request info handling
+    pending_responses: dict[str, str] | None = None
+    workflow_complete = False
+
+    print("Starting document review workflow...")
+    print("=" * 60)
+
+    while not workflow_complete:
+        # Run or continue the workflow
+        stream = (
+            workflow.send_responses_streaming(pending_responses)
+            if pending_responses
+            else workflow.run_stream("Write a brief introduction to artificial intelligence.")
+        )
+
+        pending_responses = None
+
+        # Process events
+        async for event in stream:
+            if isinstance(event, RequestInfoEvent):
+                if isinstance(event.data, AgentInputRequest):
+                    # Display pre-agent context for steering
+                    print("\n" + "-" * 40)
+                    print("REQUEST INFO: INPUT REQUESTED")
+                    print(f"About to call agent: {event.data.target_agent_id}")
+                    print("-" * 40)
+                    print("Conversation context:")
+                    recent = (
+                        event.data.conversation[-2:] if len(event.data.conversation) > 2 else event.data.conversation
+                    )
+                    for msg in recent:
+                        role = msg.role.value if msg.role else "unknown"
+                        text = (msg.text or "")[:150]
+                        print(f"  [{role}]: {text}...")
+                    print("-" * 40)
+
+                    # Get input to steer the agent
+                    user_input = input("Your guidance (or 'skip' to continue): ")  # noqa: ASYNC250
+                    if user_input.lower() == "skip":
+                        user_input = "Please continue naturally."
+
+                    pending_responses = {event.request_id: user_input}
+                    print("(Resuming workflow...)")
+
+            elif isinstance(event, WorkflowOutputEvent):
+                print("\n" + "=" * 60)
+                print("WORKFLOW COMPLETE")
+                print("=" * 60)
+                print("Final output:")
+                if event.data:
+                    messages: list[ChatMessage] = event.data[-3:]
+                    for msg in messages:
+                        role = msg.role.value if msg.role else "unknown"
+                        print(f"[{role}]: {msg.text}")
+                workflow_complete = True
+
+            elif isinstance(event, WorkflowStatusEvent) and event.state == WorkflowRunState.IDLE:
+                workflow_complete = True
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -17,7 +17,7 @@ to synthesize a concise, consolidated summary from the experts' outputs.
 The workflow completes when all participants become idle.

 Demonstrates:
- ConcurrentBuilder().participants([...]).with_custom_aggregator(callback)
+- ConcurrentBuilder().participants([...]).with_aggregator(callback)
 - Fan-out to agents and fan-in at an aggregator
 - Aggregation implemented via an LLM call (chat_client.get_response)
 - Workflow output yielded with the synthesized summary string
@@ -0,0 +1,169 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+from typing import Any, Never
+
+from agent_framework import (
+    ChatAgent,
+    ChatMessage,
+    ConcurrentBuilder,
+    Executor,
+    Role,
+    Workflow,
+    WorkflowContext,
+    handler,
+)
+from agent_framework.azure import AzureOpenAIChatClient
+from azure.identity import AzureCliCredential
+
+"""
+Sample: Concurrent Orchestration with participant factories and Custom Aggregator
+
+Build a concurrent workflow with ConcurrentBuilder that fans out one prompt to
+multiple domain agents and fans in their responses.
+
+Override the default aggregator with a custom Executor class that uses
+AzureOpenAIChatClient.get_response() to synthesize a concise, consolidated summary
+from the experts' outputs.
+
+All participants and the aggregator are created via factory functions that return
+their respective ChatAgent or Executor instances.
+
+Using participant factories allows you to set up proper state isolation between workflow
+instances created by the same builder. This is particularly useful when you need to handle
+requests or tasks in parallel with stateful participants.
+
+Demonstrates:
+- ConcurrentBuilder().register_participants([...]).with_aggregator(callback)
+- Fan-out to agents and fan-in at an aggregator
+- Aggregation implemented via an LLM call (chat_client.get_response)
+- Workflow output yielded with the synthesized summary string
+
+Prerequisites:
+- Azure OpenAI configured for AzureOpenAIChatClient (az login + required env vars)
+"""
+
+
+def create_researcher() -> ChatAgent:
+    """Factory function to create a researcher agent instance."""
+    return AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+        instructions=(
+            "You're an expert market and product researcher. Given a prompt, provide concise, factual insights,"
+            " opportunities, and risks."
+        ),
+        name="researcher",
+    )
+
+
+def create_marketer() -> ChatAgent:
+    """Factory function to create a marketer agent instance."""
+    return AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+        instructions=(
+            "You're a creative marketing strategist. Craft compelling value propositions and target messaging"
+            " aligned to the prompt."
+        ),
+        name="marketer",
+    )
+
+
+def create_legal() -> ChatAgent:
+    """Factory function to create a legal/compliance agent instance."""
+    return AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+        instructions=(
+            "You're a cautious legal/compliance reviewer. Highlight constraints, disclaimers, and policy concerns"
+            " based on the prompt."
+        ),
+        name="legal",
+    )
+
+
+class SummarizationExecutor(Executor):
+    """Custom aggregator executor that synthesizes expert outputs into a concise summary."""
+
+    def __init__(self) -> None:
+        super().__init__(id="summarization_executor")
+        self.chat_client = AzureOpenAIChatClient(credential=AzureCliCredential())
+
+    @handler
+    async def summarize_results(self, results: list[Any], ctx: WorkflowContext[Never, str]) -> None:
+        expert_sections: list[str] = []
+        for r in results:
+            try:
+                messages = getattr(r.agent_run_response, "messages", [])
+                final_text = messages[-1].text if messages and hasattr(messages[-1], "text") else "(no content)"
+                expert_sections.append(f"{getattr(r, 'executor_id', 'expert')}:\n{final_text}")
+            except Exception as e:
+                expert_sections.append(f"{getattr(r, 'executor_id', 'expert')}: (error: {type(e).__name__}: {e})")
+
+        # Ask the model to synthesize a concise summary of the experts' outputs
+        system_msg = ChatMessage(
+            Role.SYSTEM,
+            text=(
+                "You are a helpful assistant that consolidates multiple domain expert outputs "
+                "into one cohesive, concise summary with clear takeaways. Keep it under 200 words."
+            ),
+        )
+        user_msg = ChatMessage(Role.USER, text="\n\n".join(expert_sections))
+
+        response = await self.chat_client.get_response([system_msg, user_msg])
+
+        await ctx.yield_output(response.messages[-1].text if response.messages else "")
+
+
+async def run_workflow(workflow: Workflow, query: str) -> None:
+    events = await workflow.run(query)
+    outputs = events.get_outputs()
+
+    if outputs:
+        print(outputs[0])  # Get the first (and typically only) output
+    else:
+        raise RuntimeError("No outputs received from the workflow.")
+
+
+async def main() -> None:
+    # Create a concurrent builder with participant factories and a custom aggregator
+    # - register_participants([...]) accepts factory functions that return
+    #   AgentProtocol (agents) or Executor instances.
+    # - register_aggregator(...) takes a factory function that returns an Executor instance.
+    concurrent_builder = (
+        ConcurrentBuilder()
+        .register_participants([create_researcher, create_marketer, create_legal])
+        .register_aggregator(SummarizationExecutor)
+    )
+
+    # Build workflow_a
+    workflow_a = concurrent_builder.build()
+
+    # Run workflow_a
+    # Context is maintained across runs
+    print("=== First Run on workflow_a ===")
+    await run_workflow(workflow_a, "We are launching a new budget-friendly electric bike for urban commuters.")
+    print("\n=== Second Run on workflow_a ===")
+    await run_workflow(workflow_a, "Refine your response to focus on the California market.")
+
+    # Build workflow_b
+    # This will create new instances of all participants and the aggregator
+    # The agents will also get new threads
+    workflow_b = concurrent_builder.build()
+    # Run workflow_b
+    # Context is not maintained across instances
+    # Should not expect mentions of electric bikes in the results
+    print("\n=== First Run on workflow_b ===")
+    await run_workflow(workflow_b, "Refine your response to focus on the California market.")
+
+    """
+    Sample Output:
+
+    === First Run on workflow_a ===
+    The budget-friendly electric bike market is poised for significant growth, driven by urbanization, ...
+
+    === Second Run on workflow_a ===
+    Launching a budget-friendly electric bike in California presents significant opportunities, driven ...
+
+    === First Run on workflow_b ===
+    To successfully penetrate the California market, consider these tailored strategies focused on ...
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,241 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""
+Handoff Workflow with Code Interpreter File Generation Sample
+
+This sample demonstrates retrieving file IDs from code interpreter output
+in a handoff workflow context. A triage agent routes to a code specialist
+that generates a text file, and we verify the file_id is captured correctly
+from the streaming AgentRunUpdateEvent events.
+
+Verifies GitHub issue #2718: files generated by code interpreter in
+HandoffBuilder workflows can be properly retrieved.
+
+Toggle USE_V2_CLIENT to switch between:
+    - V1: AzureAIAgentClient (azure-ai-agents SDK)
+    - V2: AzureAIClient (azure-ai-projects 2.x with Responses API)
+
+IMPORTANT: When using V2 AzureAIClient with HandoffBuilder, each agent must
+have its own client instance. The V2 client binds to a single server-side
+agent name, so sharing a client between agents causes routing issues.
+
+Prerequisites:
+    - `az login` (Azure CLI authentication)
+    - V1: AZURE_AI_AGENT_PROJECT_CONNECTION_STRING
+    - V2: AZURE_AI_PROJECT_ENDPOINT, AZURE_AI_MODEL_DEPLOYMENT_NAME
+"""
+
+import asyncio
+from collections.abc import AsyncIterable
+from contextlib import asynccontextmanager
+from collections.abc import AsyncIterator
+
+from agent_framework import (
+    AgentRunUpdateEvent,
+    ChatAgent,
+    HandoffBuilder,
+    HandoffUserInputRequest,
+    HostedCodeInterpreterTool,
+    HostedFileContent,
+    RequestInfoEvent,
+    TextContent,
+    WorkflowEvent,
+    WorkflowRunState,
+    WorkflowStatusEvent,
+)
+from azure.identity.aio import AzureCliCredential
+
+# Toggle between V1 (AzureAIAgentClient) and V2 (AzureAIClient)
+USE_V2_CLIENT = False
+
+
+async def _drain(stream: AsyncIterable[WorkflowEvent]) -> list[WorkflowEvent]:
+    """Collect all events from an async stream."""
+    return [event async for event in stream]
+
+
+def _handle_events(events: list[WorkflowEvent]) -> tuple[list[RequestInfoEvent], list[str]]:
+    """Process workflow events and extract file IDs and pending requests.
+
+    Returns:
+        Tuple of (pending_requests, file_ids_found)
+    """
+    requests: list[RequestInfoEvent] = []
+    file_ids: list[str] = []
+
+    for event in events:
+        if isinstance(event, WorkflowStatusEvent):
+            if event.state in {WorkflowRunState.IDLE, WorkflowRunState.IDLE_WITH_PENDING_REQUESTS}:
+                print(f"[status] {event.state.name}")
+
+        elif isinstance(event, RequestInfoEvent):
+            if isinstance(event.data, HandoffUserInputRequest):
+                print("\n=== Conversation So Far ===")
+                for msg in event.data.conversation:
+                    speaker = msg.author_name or msg.role.value
+                    text = msg.text or ""
+                    txt = text[:200] + "..." if len(text) > 200 else text
+                    print(f"- {speaker}: {txt}")
+                print("===========================\n")
+            requests.append(event)
+
+        elif isinstance(event, AgentRunUpdateEvent):
+            update = event.data
+            if update is None:
+                continue
+            for content in update.contents:
+                if isinstance(content, HostedFileContent):
+                    file_ids.append(content.file_id)
+                    print(f"[Found HostedFileContent: file_id={content.file_id}]")
+                elif isinstance(content, TextContent) and content.annotations:
+                    for annotation in content.annotations:
+                        if hasattr(annotation, "file_id") and annotation.file_id:
+                            file_ids.append(annotation.file_id)
+                            print(f"[Found file annotation: file_id={annotation.file_id}]")
+
+    return requests, file_ids
+
+
+@asynccontextmanager
+async def create_agents_v1(credential: AzureCliCredential) -> AsyncIterator[tuple[ChatAgent, ChatAgent]]:
+    """Create agents using V1 AzureAIAgentClient."""
+    from agent_framework.azure import AzureAIAgentClient
+
+    async with AzureAIAgentClient(credential=credential) as client:
+        triage = client.create_agent(
+            name="triage_agent",
+            instructions=(
+                "You are a triage agent. Route code-related requests to the code_specialist. "
+                "When the user asks to create or generate files, hand off to code_specialist "
+                "by calling handoff_to_code_specialist."
+            ),
+        )
+
+        code_specialist = client.create_agent(
+            name="code_specialist",
+            instructions=(
+                "You are a Python code specialist. Use the code interpreter to execute Python code "
+                "and create files when requested. Always save files to /mnt/data/ directory."
+            ),
+            tools=[HostedCodeInterpreterTool()],
+        )
+
+        yield triage, code_specialist
+
+
+@asynccontextmanager
+async def create_agents_v2(credential: AzureCliCredential) -> AsyncIterator[tuple[ChatAgent, ChatAgent]]:
+    """Create agents using V2 AzureAIClient.
+
+    Each agent needs its own client instance because the V2 client binds
+    to a single server-side agent name.
+    """
+    from agent_framework.azure import AzureAIClient
+
+    async with (
+        AzureAIClient(credential=credential) as triage_client,
+        AzureAIClient(credential=credential) as code_client,
+    ):
+        triage = triage_client.create_agent(
+            name="TriageAgent",
+            instructions=(
+                "You are a triage agent. Your ONLY job is to route requests to the appropriate specialist. "
+                "For code or file creation requests, call handoff_to_CodeSpecialist immediately. "
+                "Do NOT try to complete tasks yourself. Just hand off."
+            ),
+        )
+
+        code_specialist = code_client.create_agent(
+            name="CodeSpecialist",
+            instructions=(
+                "You are a Python code specialist. You have access to a code interpreter tool. "
+                "Use the code interpreter to execute Python code and create files. "
+                "Always save files to /mnt/data/ directory. "
+                "Do NOT discuss handoffs or routing - just complete the coding task directly."
+            ),
+            tools=[HostedCodeInterpreterTool()],
+        )
+
+        yield triage, code_specialist
+
+
+async def main() -> None:
+    """Run a simple handoff workflow with code interpreter file generation."""
+    client_version = "V2 (AzureAIClient)" if USE_V2_CLIENT else "V1 (AzureAIAgentClient)"
+    print(f"=== Handoff Workflow with Code Interpreter File Generation [{client_version}] ===\n")
+
+    async with AzureCliCredential() as credential:
+        create_agents = create_agents_v2 if USE_V2_CLIENT else create_agents_v1
+
+        async with create_agents(credential) as (triage, code_specialist):
+            workflow = (
+                HandoffBuilder()
+                .participants([triage, code_specialist])
+                .set_coordinator(triage)
+                .with_termination_condition(lambda conv: sum(1 for msg in conv if msg.role.value == "user") >= 2)
+                .build()
+            )
+
+            user_inputs = [
+                "Please create a text file called hello.txt with 'Hello from handoff workflow!' inside it.",
+                "exit",
+            ]
+            input_index = 0
+            all_file_ids: list[str] = []
+
+            print(f"User: {user_inputs[0]}")
+            events = await _drain(workflow.run_stream(user_inputs[0]))
+            requests, file_ids = _handle_events(events)
+            all_file_ids.extend(file_ids)
+            input_index += 1
+
+            while requests:
+                request = requests[0]
+                if input_index >= len(user_inputs):
+                    break
+                user_input = user_inputs[input_index]
+                print(f"\nUser: {user_input}")
+
+                responses = {request.request_id: user_input}
+                events = await _drain(workflow.send_responses_streaming(responses))
+                requests, file_ids = _handle_events(events)
+                all_file_ids.extend(file_ids)
+                input_index += 1
+
+            print("\n" + "=" * 50)
+            if all_file_ids:
+                print(f"SUCCESS: Found {len(all_file_ids)} file ID(s) in handoff workflow:")
+                for fid in all_file_ids:
+                    print(f"  - {fid}")
+            else:
+                print("WARNING: No file IDs captured from the handoff workflow.")
+            print("=" * 50)
+
+            """
+            Sample Output:
+
+            User: Please create a text file called hello.txt with 'Hello from handoff workflow!' inside it.
+            [Found HostedFileContent: file_id=assistant-JT1sA...]
+
+            === Conversation So Far ===
+            - user: Please create a text file called hello.txt with 'Hello from handoff workflow!' inside it.
+            - triage_agent: I am handing off your request to create the text file "hello.txt" with the specified content to the code specialist. They will assist you shortly.
+            - code_specialist: The file "hello.txt" has been created with the content "Hello from handoff workflow!". You can download it using the link below:
+
+            [hello.txt](sandbox:/mnt/data/hello.txt)
+            ===========================
+
+            [status] IDLE_WITH_PENDING_REQUESTS
+
+            User: exit
+            [status] IDLE
+
+            ==================================================
+            SUCCESS: Found 1 file ID(s) in handoff workflow:
+            - assistant-JT1sA...
+            ==================================================
+            """  # noqa: E501
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -13,7 +13,6 @@ from agent_framework import (
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
-from typing_extensions import Never

 """
 Sample: Sequential workflow mixing agents and a custom summarizer executor
@@ -42,12 +41,12 @@ class Summarizer(Executor):
    """Simple summarizer: consumes full conversation and appends an assistant summary."""

    @handler
-    async def summarize(self, conversation: list[ChatMessage], ctx: WorkflowContext[Never, list[ChatMessage]]) -> None:
+    async def summarize(self, conversation: list[ChatMessage], ctx: WorkflowContext[list[ChatMessage]]) -> None:
        users = sum(1 for m in conversation if m.role == Role.USER)
        assistants = sum(1 for m in conversation if m.role == Role.ASSISTANT)
        summary = ChatMessage(role=Role.ASSISTANT, text=f"Summary -> users:{users} assistants:{assistants}")
        final_conversation = list(conversation) + [summary]
-        await ctx.yield_output(final_conversation)
+        await ctx.send_message(final_conversation)


 async def main() -> None:
@@ -0,0 +1,127 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+
+from agent_framework import (
+    ChatAgent,
+    ChatMessage,
+    Executor,
+    Role,
+    SequentialBuilder,
+    Workflow,
+    WorkflowContext,
+    handler,
+)
+from agent_framework.azure import AzureOpenAIChatClient
+from azure.identity import AzureCliCredential
+
+"""
+Sample: Sequential workflow with participant factories
+
+This sample demonstrates how to create a sequential workflow with participant factories.
+
+Using participant factories allows you to set up proper state isolation between workflow
+instances created by the same builder. This is particularly useful when you need to handle
+requests or tasks in parallel with stateful participants.
+
+In this example, we create a sequential workflow with two participants: an accumulator
+and a content producer. The accumulator is stateful and maintains a list of all messages it has
+received. Context is maintained across runs of the same workflow instance but not across different
+workflow instances.
+"""
+
+
+class Accumulate(Executor):
+    """Simple accumulator.
+
+    Accumulates all messages from the conversation and prints them out.
+    """
+
+    def __init__(self, id: str):
+        super().__init__(id)
+        # Some internal state to accumulate messages
+        self._accumulated: list[str] = []
+
+    @handler
+    async def accumulate(self, conversation: list[ChatMessage], ctx: WorkflowContext[list[ChatMessage]]) -> None:
+        self._accumulated.extend([msg.text for msg in conversation])
+        print(f"Number of queries received so far: {len(self._accumulated)}")
+        await ctx.send_message(conversation)
+
+
+def create_agent() -> ChatAgent:
+    return AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
+        instructions="Produce a concise paragraph answering the user's request.",
+        name="ContentProducer",
+    )
+
+
+async def run_workflow(workflow: Workflow, query: str) -> None:
+    events = await workflow.run(query)
+    outputs = events.get_outputs()
+
+    if outputs:
+        messages: list[ChatMessage] = outputs[0]
+        for message in messages:
+            name = message.author_name or ("assistant" if message.role == Role.ASSISTANT else "user")
+            print(f"{name}: {message.text}")
+    else:
+        raise RuntimeError("No outputs received from the workflow.")
+
+
+async def main() -> None:
+    # 1) Create a builder with participant factories
+    builder = SequentialBuilder().register_participants([
+        lambda: Accumulate("accumulator"),
+        create_agent,
+    ])
+    # 2) Build workflow_a
+    workflow_a = builder.build()
+
+    # 3) Run workflow_a
+    # Context is maintained across runs
+    print("=== First Run on workflow_a ===")
+    await run_workflow(workflow_a, "Why is the sky blue?")
+    print("\n=== Second Run on workflow_a ===")
+    await run_workflow(workflow_a, "Repeat my previous question.")
+
+    # 4) Build workflow_b
+    # This will create a new instance of the accumulator and content producer
+    # using the same workflow builder
+    workflow_b = builder.build()
+
+    # 5) Run workflow_b
+    # Context is not maintained across instances
+    print("\n=== First Run on workflow_b ===")
+    await run_workflow(workflow_b, "Repeat my previous question.")
+
+    """
+    Sample Output:
+
+    === First Run on workflow_a ===
+    Number of queries received so far: 1
+    user: Why is the sky blue?
+    ContentProducer: The sky appears blue due to a phenomenon called Rayleigh scattering.
+                     When sunlight enters the Earth's atmosphere, it collides with gases
+                     and particles, scattering shorter wavelengths of light (blue and violet)
+                     more than the longer wavelengths (red and yellow). Although violet light
+                     is scattered even more than blue, our eyes are more sensitive to blue
+                     light, and some violet light is absorbed by the ozone layer. As a result,
+                     we perceive the sky as predominantly blue during the day.
+
+    === Second Run on workflow_a ===
+    Number of queries received so far: 2
+    user: Repeat my previous question.
+    ContentProducer: Why is the sky blue?
+
+    === First Run on workflow_b ===
+    Number of queries received so far: 1
+    user: Repeat my previous question.
+    ContentProducer: I'm sorry, but I can't repeat your previous question as I don't have
+                     access to your past queries. However, feel free to ask anything again,
+                     and I'll be happy to help!
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,183 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+from typing import Annotated
+
+from agent_framework import (
+    ChatMessage,
+    ConcurrentBuilder,
+    FunctionApprovalRequestContent,
+    FunctionApprovalResponseContent,
+    RequestInfoEvent,
+    WorkflowOutputEvent,
+    WorkflowRunState,
+    WorkflowStatusEvent,
+    ai_function,
+)
+from agent_framework.openai import OpenAIChatClient
+
+"""
+Sample: Concurrent Workflow with Tool Approval Requests
+
+This sample demonstrates how to use ConcurrentBuilder with tools that require human
+approval before execution. Multiple agents run in parallel, and any tool requiring
+approval will pause the workflow until the human responds.
+
+This sample works as follows:
+1. A ConcurrentBuilder workflow is created with two agents running in parallel.
+2. One agent has a tool requiring approval (financial transaction).
+3. The other agent has only non-approval tools (market data lookup).
+4. Both agents receive the same task and work concurrently.
+5. When the financial agent tries to execute a trade, it triggers an approval request.
+6. The sample simulates human approval and the workflow completes.
+7. Results from both agents are aggregated and output.
+
+Purpose:
+Show how tool call approvals work in parallel execution scenarios where only some
+agents have sensitive tools.
+
+Demonstrate:
+- Combining agents with and without approval-required tools in concurrent workflows.
+- Handling RequestInfoEvent during concurrent agent execution.
+- Understanding that approval pauses only the agent that triggered it, not all agents.
+
+Prerequisites:
+- OpenAI or Azure OpenAI configured with the required environment variables.
+- Basic familiarity with ConcurrentBuilder and streaming workflow events.
+"""
+
+
+# 1. Define tools for the research agent (no approval required)
+@ai_function
+def get_stock_price(symbol: Annotated[str, "The stock ticker symbol"]) -> str:
+    """Get the current stock price for a given symbol."""
+    # Mock data for demonstration
+    prices = {"AAPL": 175.50, "GOOGL": 140.25, "MSFT": 378.90, "AMZN": 178.75}
+    price = prices.get(symbol.upper(), 100.00)
+    return f"{symbol.upper()}: ${price:.2f}"
+
+
+@ai_function
+def get_market_sentiment(symbol: Annotated[str, "The stock ticker symbol"]) -> str:
+    """Get market sentiment analysis for a stock."""
+    # Mock sentiment data
+    return f"Market sentiment for {symbol.upper()}: Bullish (72% positive mentions in last 24h)"
+
+
+# 2. Define tools for the trading agent (approval required for trades)
+@ai_function(approval_mode="always_require")
+def execute_trade(
+    symbol: Annotated[str, "The stock ticker symbol"],
+    action: Annotated[str, "Either 'buy' or 'sell'"],
+    quantity: Annotated[int, "Number of shares to trade"],
+) -> str:
+    """Execute a stock trade. Requires human approval due to financial impact."""
+    return f"Trade executed: {action.upper()} {quantity} shares of {symbol.upper()}"
+
+
+@ai_function
+def get_portfolio_balance() -> str:
+    """Get current portfolio balance and available funds."""
+    return "Portfolio: $50,000 invested, $10,000 cash available"
+
+
+async def main() -> None:
+    # 3. Create two agents with different tool sets
+    chat_client = OpenAIChatClient()
+
+    research_agent = chat_client.create_agent(
+        name="ResearchAgent",
+        instructions=(
+            "You are a market research analyst. Analyze stock data and provide "
+            "recommendations based on price and sentiment. Do not execute trades."
+        ),
+        tools=[get_stock_price, get_market_sentiment],
+    )
+
+    trading_agent = chat_client.create_agent(
+        name="TradingAgent",
+        instructions=(
+            "You are a trading assistant. When asked to buy or sell shares, you MUST "
+            "call the execute_trade function to complete the transaction. Check portfolio "
+            "balance first, then execute the requested trade."
+        ),
+        tools=[get_portfolio_balance, execute_trade],
+    )
+
+    # 4. Build a concurrent workflow with both agents
+    # ConcurrentBuilder requires at least 2 participants for fan-out
+    workflow = ConcurrentBuilder().participants([research_agent, trading_agent]).build()
+
+    # 5. Start the workflow - both agents will process the same task in parallel
+    print("Starting concurrent workflow with tool approval...")
+    print("Two agents will analyze MSFT - one for research, one for trading.")
+    print("-" * 60)
+
+    # Phase 1: Run workflow and collect all events (stream ends at IDLE or IDLE_WITH_PENDING_REQUESTS)
+    request_info_events: list[RequestInfoEvent] = []
+    workflow_completed_without_approvals = False
+    async for event in workflow.run_stream("Analyze MSFT stock and if sentiment is positive, buy 10 shares."):
+        if isinstance(event, RequestInfoEvent):
+            request_info_events.append(event)
+            if isinstance(event.data, FunctionApprovalRequestContent):
+                print(f"\nApproval requested for tool: {event.data.function_call.name}")
+                print(f"  Arguments: {event.data.function_call.arguments}")
+        elif isinstance(event, WorkflowStatusEvent) and event.state == WorkflowRunState.IDLE:
+            workflow_completed_without_approvals = True
+
+    # 6. Handle approval requests (if any)
+    if request_info_events:
+        responses: dict[str, FunctionApprovalResponseContent] = {}
+        for request_event in request_info_events:
+            if isinstance(request_event.data, FunctionApprovalRequestContent):
+                print(f"\nSimulating human approval for: {request_event.data.function_call.name}")
+                # Create approval response
+                responses[request_event.request_id] = request_event.data.create_response(approved=True)
+
+        if responses:
+            # Phase 2: Send all approvals and continue workflow
+            output: list[ChatMessage] | None = None
+            async for event in workflow.send_responses_streaming(responses):
+                if isinstance(event, WorkflowOutputEvent):
+                    output = event.data
+
+            if output:
+                print("\n" + "-" * 60)
+                print("Workflow completed. Aggregated results from both agents:")
+                for msg in output:
+                    if hasattr(msg, "author_name") and msg.author_name:
+                        print(f"\n[{msg.author_name}]:")
+                    text = msg.text[:300] + "..." if len(msg.text) > 300 else msg.text
+                    if text:
+                        print(f"  {text}")
+    elif workflow_completed_without_approvals:
+        print("\nWorkflow completed without requiring approvals.")
+        print("(The trading agent may have only checked balance without executing a trade)")
+
+    """
+    Sample Output:
+    Starting concurrent workflow with tool approval...
+    Two agents will analyze MSFT - one for research, one for trading.
+    ------------------------------------------------------------
+
+    Approval requested for tool: execute_trade
+      Arguments: {"symbol": "MSFT", "action": "buy", "quantity": 10}
+    Simulating human approval for: execute_trade
+
+    ------------------------------------------------------------
+    Workflow completed. Aggregated results from both agents:
+
+    [ResearchAgent]:
+      MSFT is currently trading at $175.50 with bullish market sentiment
+      (72% positive mentions). Based on the positive sentiment, this could
+      be a good opportunity to consider buying.
+
+    [TradingAgent]:
+      I've checked your portfolio balance ($10,000 cash available) and
+      executed the trade: BUY 10 shares of MSFT at approximately $175.50
+      per share, totaling ~$1,755.
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,206 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+from typing import Annotated
+
+from agent_framework import (
+    FunctionApprovalRequestContent,
+    GroupChatBuilder,
+    GroupChatStateSnapshot,
+    RequestInfoEvent,
+    ai_function,
+)
+from agent_framework.openai import OpenAIChatClient
+
+"""
+Sample: Group Chat Workflow with Tool Approval Requests
+
+This sample demonstrates how to use GroupChatBuilder with tools that require human
+approval before execution. A group of specialized agents collaborate on a task, and
+sensitive tool calls trigger human-in-the-loop approval.
+
+This sample works as follows:
+1. A GroupChatBuilder workflow is created with multiple specialized agents.
+2. A selector function determines which agent speaks next based on conversation state.
+3. Agents collaborate on a software deployment task.
+4. When the deployment agent tries to deploy to production, it triggers an approval request.
+5. The sample simulates human approval and the workflow completes.
+
+Purpose:
+Show how tool call approvals integrate with multi-agent group chat workflows where
+different agents have different levels of tool access.
+
+Demonstrate:
+- Using set_select_speakers_func with agents that have approval-required tools.
+- Handling RequestInfoEvent in group chat scenarios.
+- Multi-round group chat with tool approval interruption and resumption.
+
+Prerequisites:
+- OpenAI or Azure OpenAI configured with the required environment variables.
+- Basic familiarity with GroupChatBuilder and streaming workflow events.
+"""
+
+
+# 1. Define tools for different agents
+@ai_function
+def run_tests(test_suite: Annotated[str, "Name of the test suite to run"]) -> str:
+    """Run automated tests for the application."""
+    return f"Test suite '{test_suite}' completed: 47 passed, 0 failed, 0 skipped"
+
+
+@ai_function
+def check_staging_status() -> str:
+    """Check the current status of the staging environment."""
+    return "Staging environment: Healthy, Version 2.3.0 deployed, All services running"
+
+
+@ai_function(approval_mode="always_require")
+def deploy_to_production(
+    version: Annotated[str, "The version to deploy"],
+    components: Annotated[str, "Comma-separated list of components to deploy"],
+) -> str:
+    """Deploy specified components to production. Requires human approval."""
+    return f"Production deployment complete: Version {version}, Components: {components}"
+
+
+@ai_function
+def create_rollback_plan(version: Annotated[str, "The version being deployed"]) -> str:
+    """Create a rollback plan for the deployment."""
+    return (
+        f"Rollback plan created for version {version}: "
+        "Automated rollback to v2.2.0 if health checks fail within 5 minutes"
+    )
+
+
+# 2. Define the speaker selector function
+def select_next_speaker(state: GroupChatStateSnapshot) -> str | None:
+    """Select the next speaker based on the conversation flow.
+
+    This simple selector follows a predefined flow:
+    1. QA Engineer runs tests
+    2. DevOps Engineer checks staging and creates rollback plan
+    3. DevOps Engineer deploys to production (triggers approval)
+    """
+    round_index: int = state["round_index"]
+
+    # Define the conversation flow
+    speaker_order: list[str] = [
+        "QAEngineer",  # Round 0: Run tests
+        "DevOpsEngineer",  # Round 1: Check staging, create rollback
+        "DevOpsEngineer",  # Round 2: Deploy to production (approval required)
+    ]
+
+    if round_index >= len(speaker_order):
+        return None  # End the conversation
+
+    return speaker_order[round_index]
+
+
+async def main() -> None:
+    # 3. Create specialized agents
+    chat_client = OpenAIChatClient()
+
+    qa_engineer = chat_client.create_agent(
+        name="QAEngineer",
+        instructions=(
+            "You are a QA engineer responsible for running tests before deployment. "
+            "Run the appropriate test suites and report results clearly."
+        ),
+        tools=[run_tests],
+    )
+
+    devops_engineer = chat_client.create_agent(
+        name="DevOpsEngineer",
+        instructions=(
+            "You are a DevOps engineer responsible for deployments. First check staging "
+            "status and create a rollback plan, then proceed with production deployment. "
+            "Always ensure safety measures are in place before deploying."
+        ),
+        tools=[check_staging_status, create_rollback_plan, deploy_to_production],
+    )
+
+    # 4. Build a group chat workflow with the selector function
+    workflow = (
+        GroupChatBuilder()
+        # Optionally, use `.set_manager(...)` to customize the group chat manager
+        .set_select_speakers_func(select_next_speaker)
+        .participants([qa_engineer, devops_engineer])
+        .with_max_rounds(5)
+        .build()
+    )
+
+    # 5. Start the workflow
+    print("Starting group chat workflow for software deployment...")
+    print("Agents: QA Engineer, DevOps Engineer")
+    print("-" * 60)
+
+    # Phase 1: Run workflow and collect all events (stream ends at IDLE or IDLE_WITH_PENDING_REQUESTS)
+    request_info_events: list[RequestInfoEvent] = []
+    async for event in workflow.run_stream(
+        "We need to deploy version 2.4.0 to production. Please coordinate the deployment."
+    ):
+        if isinstance(event, RequestInfoEvent):
+            request_info_events.append(event)
+            if isinstance(event.data, FunctionApprovalRequestContent):
+                print("\n[APPROVAL REQUIRED]")
+                print(f"  Tool: {event.data.function_call.name}")
+                print(f"  Arguments: {event.data.function_call.arguments}")
+
+    # 6. Handle approval requests
+    if request_info_events:
+        for request_event in request_info_events:
+            if isinstance(request_event.data, FunctionApprovalRequestContent):
+                print("\n" + "=" * 60)
+                print("Human review required for production deployment!")
+                print("In a real scenario, you would review the deployment details here.")
+                print("Simulating approval for demo purposes...")
+                print("=" * 60)
+
+                # Create approval response
+                approval_response = request_event.data.create_response(approved=True)
+
+                # Phase 2: Send approval and continue workflow
+                async for _ in workflow.send_responses_streaming({request_event.request_id: approval_response}):
+                    pass  # Consume all events
+
+                print("\n" + "-" * 60)
+                print("Deployment workflow completed successfully!")
+                print("All agents have finished their tasks.")
+    else:
+        print("\nWorkflow completed without requiring production deployment approval.")
+
+    """
+    Sample Output:
+    Starting group chat workflow for software deployment...
+    Agents: QA Engineer, DevOps Engineer
+    ------------------------------------------------------------
+
+    [QAEngineer]: Running the integration test suite to verify the application
+    before deployment... Test suite 'integration' completed: 47 passed, 0 failed.
+    All tests passing - ready for deployment.
+
+    [DevOpsEngineer]: Checking staging environment status... Staging is healthy
+    with version 2.3.0. Creating rollback plan for version 2.4.0... Rollback plan
+    created with automated rollback to v2.2.0 if health checks fail.
+
+    [APPROVAL REQUIRED]
+      Tool: deploy_to_production
+      Arguments: {"version": "2.4.0", "components": "api,web,worker"}
+
+    ============================================================
+    Human review required for production deployment!
+    In a real scenario, you would review the deployment details here.
+    Simulating approval for demo purposes...
+    ============================================================
+
+    [DevOpsEngineer]: Production deployment complete! Version 2.4.0 has been
+    successfully deployed with components: api, web, worker.
+
+    ------------------------------------------------------------
+    Deployment workflow completed successfully!
+    All agents have finished their tasks.
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -0,0 +1,144 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import asyncio
+from typing import Annotated
+
+from agent_framework import (
+    ChatMessage,
+    FunctionApprovalRequestContent,
+    RequestInfoEvent,
+    SequentialBuilder,
+    WorkflowOutputEvent,
+    ai_function,
+)
+from agent_framework.openai import OpenAIChatClient
+
+"""
+Sample: Sequential Workflow with Tool Approval Requests
+
+This sample demonstrates how to use SequentialBuilder with tools that require human
+approval before execution. The approval flow uses the existing @ai_function decorator
+with approval_mode="always_require" to trigger human-in-the-loop interactions.
+
+This sample works as follows:
+1. A SequentialBuilder workflow is created with a single agent that has tools requiring approval.
+2. The agent receives a user task and determines it needs to call a sensitive tool.
+3. The tool call triggers a FunctionApprovalRequestContent, pausing the workflow.
+4. The sample simulates human approval by responding to the RequestInfoEvent.
+5. Once approved, the tool executes and the agent completes its response.
+6. The workflow outputs the final conversation with all messages.
+
+Purpose:
+Show how tool call approvals integrate seamlessly with SequentialBuilder without
+requiring any additional builder configuration.
+
+Demonstrate:
+- Using @ai_function(approval_mode="always_require") for sensitive operations.
+- Handling RequestInfoEvent with FunctionApprovalRequestContent in sequential workflows.
+- Resuming workflow execution after approval via send_responses_streaming.
+
+Prerequisites:
+- OpenAI or Azure OpenAI configured with the required environment variables.
+- Basic familiarity with SequentialBuilder and streaming workflow events.
+"""
+
+
+# 1. Define tools - one requiring approval, one that doesn't
+@ai_function(approval_mode="always_require")
+def execute_database_query(
+    query: Annotated[str, "The SQL query to execute against the production database"],
+) -> str:
+    """Execute a SQL query against the production database. Requires human approval."""
+    # In a real implementation, this would execute the query
+    return f"Query executed successfully. Results: 3 rows affected by '{query}'"
+
+
+@ai_function
+def get_database_schema() -> str:
+    """Get the current database schema. Does not require approval."""
+    return """
+    Tables:
+    - users (id, name, email, created_at)
+    - orders (id, user_id, total, status, created_at)
+    - products (id, name, price, stock)
+    """
+
+
+async def main() -> None:
+    # 2. Create the agent with tools (approval mode is set per-tool via decorator)
+    chat_client = OpenAIChatClient()
+    database_agent = chat_client.create_agent(
+        name="DatabaseAgent",
+        instructions=(
+            "You are a database assistant. You can view the database schema and execute "
+            "queries. Always check the schema before running queries. Be careful with "
+            "queries that modify data."
+        ),
+        tools=[get_database_schema, execute_database_query],
+    )
+
+    # 3. Build a sequential workflow with the agent
+    workflow = SequentialBuilder().participants([database_agent]).build()
+
+    # 4. Start the workflow with a user task
+    print("Starting sequential workflow with tool approval...")
+    print("-" * 60)
+
+    # Phase 1: Run workflow and collect all events (stream ends at IDLE or IDLE_WITH_PENDING_REQUESTS)
+    request_info_events: list[RequestInfoEvent] = []
+    async for event in workflow.run_stream(
+        "Check the schema and then update all orders with status 'pending' to 'processing'"
+    ):
+        if isinstance(event, RequestInfoEvent):
+            request_info_events.append(event)
+            if isinstance(event.data, FunctionApprovalRequestContent):
+                print(f"\nApproval requested for tool: {event.data.function_call.name}")
+                print(f"  Arguments: {event.data.function_call.arguments}")
+
+    # 5. Handle approval requests
+    if request_info_events:
+        for request_event in request_info_events:
+            if isinstance(request_event.data, FunctionApprovalRequestContent):
+                # In a real application, you would prompt the user here
+                print("\nSimulating human approval (auto-approving for demo)...")
+
+                # Create approval response
+                approval_response = request_event.data.create_response(approved=True)
+
+                # Phase 2: Send approval and continue workflow
+                output: list[ChatMessage] | None = None
+                async for event in workflow.send_responses_streaming({request_event.request_id: approval_response}):
+                    if isinstance(event, WorkflowOutputEvent):
+                        output = event.data
+
+                if output:
+                    print("\n" + "-" * 60)
+                    print("Workflow completed. Final conversation:")
+                    for msg in output:
+                        role = msg.role.value if hasattr(msg.role, "value") else msg.role
+                        text = msg.text[:200] + "..." if len(msg.text) > 200 else msg.text
+                        print(f"  [{role}]: {text}")
+    else:
+        print("No approval requests were generated (schema check may have been sufficient).")
+
+    """
+    Sample Output:
+    Starting sequential workflow with tool approval...
+    ------------------------------------------------------------
+
+    Approval requested for tool: execute_database_query
+      Arguments: {"query": "UPDATE orders SET status = 'processing' WHERE status = 'pending'"}
+
+    Simulating human approval (auto-approving for demo)...
+
+    ------------------------------------------------------------
+    Workflow completed. Final conversation:
+      [user]: Check the schema and then update all orders with status 'pending' to 'processing'
+      [assistant]: I've checked the schema and executed the update query. The query
+                   "UPDATE orders SET status = 'processing' WHERE status = 'pending'"
+                   was executed successfully, affecting 3 rows.
+    """
+
+
+if __name__ == "__main__":
+    asyncio.run(main())
@@ -89,7 +89,7 @@ wheels = [

 [[package]]
 name = "agent-framework"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { virtual = "." }
 dependencies = [
    { name = "agent-framework-core", extra = ["all"], marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -156,7 +156,7 @@ docs = [

 [[package]]
 name = "agent-framework-a2a"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/a2a" }
 dependencies = [
    { name = "a2a-sdk", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -171,7 +171,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-ag-ui"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/ag-ui" }
 dependencies = [
    { name = "ag-ui-protocol", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -201,7 +201,7 @@ provides-extras = ["dev"]

 [[package]]
 name = "agent-framework-anthropic"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/anthropic" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -216,7 +216,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azure-ai"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/azure-ai" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -235,7 +235,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azure-ai-search"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/azure-ai-search" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -250,7 +250,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-azurefunctions"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/azurefunctions" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -275,7 +275,7 @@ dev = [{ name = "types-python-dateutil", specifier = ">=2.9.0" }]

 [[package]]
 name = "agent-framework-chatkit"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/chatkit" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -290,7 +290,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-copilotstudio"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/copilotstudio" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -305,7 +305,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-core"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/core" }
 dependencies = [
    { name = "azure-identity", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -356,7 +356,7 @@ requires-dist = [
    { name = "agent-framework-purview", marker = "extra == 'all'", editable = "packages/purview" },
    { name = "agent-framework-redis", marker = "extra == 'all'", editable = "packages/redis" },
    { name = "azure-identity", specifier = ">=1,<2" },
-    { name = "mcp", extras = ["ws"], specifier = ">=1.13" },
+    { name = "mcp", extras = ["ws"], specifier = ">=1.23" },
    { name = "openai", specifier = ">=1.99.0" },
    { name = "opentelemetry-api", specifier = ">=1.39.0" },
    { name = "opentelemetry-exporter-otlp-proto-grpc", specifier = ">=1.39.0" },
@@ -371,7 +371,7 @@ provides-extras = ["all"]

 [[package]]
 name = "agent-framework-declarative"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/declarative" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -396,7 +396,7 @@ dev = [{ name = "types-pyyaml" }]

 [[package]]
 name = "agent-framework-devui"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/devui" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -430,7 +430,7 @@ provides-extras = ["dev", "all"]

 [[package]]
 name = "agent-framework-lab"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/lab" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -521,7 +521,7 @@ dev = [

 [[package]]
 name = "agent-framework-mem0"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/mem0" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -536,7 +536,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-purview"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/purview" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
@@ -553,7 +553,7 @@ requires-dist = [

 [[package]]
 name = "agent-framework-redis"
-version = "1.0.0b251209"
+version = "1.0.0b251211"
 source = { editable = "packages/redis" }
 dependencies = [
    { name = "agent-framework-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or sys_platform == 'win32'" },
Author	SHA1	Message	Date
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>Chris	16230d3b20	Bump actions/checkout from 5 to 6 (#2404 ) Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v5...v6) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>	2025-12-11 18:43:52 +00:00
Dmytro StrukandGitHub	8d53b20026	Python: Updated package versions (#2784 ) * Updated package versions * Small fix	2025-12-11 18:39:08 +00:00
Eduard van ValkenburgandGitHub	c376868ec9	Python: added more complete parsing for mcp tool arguments (#2756 ) * added more complete parsing for mcp tool arguments * fixed mypy * added nonlocal model counter, and some fixes * fixes in naming logic * extracted json parsing function, added parametrized test and checked coverage	2025-12-11 17:24:08 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	8bb9927f3c	Bump Azure.AI.AgentServer.AgentFramework from 1.0.0-beta.4 to 1.0.0-beta.5 (#2778 ) --- updated-dependencies: - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.AI.AgentServer.AgentFramework dependency-version: 1.0.0-beta.5 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-12-11 14:08:20 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	194486c4cc	Bump Azure.Identity from 1.17.0 to 1.17.1 (#2780 ) --- updated-dependencies: - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch - dependency-name: Azure.Identity dependency-version: 1.17.1 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-12-11 11:04:22 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	0413f4220a	Bump AWSSDK.Extensions.Bedrock.MEAI from 4.0.4.7 to 4.0.4.11 (#2777 ) --- updated-dependencies: - dependency-name: AWSSDK.Extensions.Bedrock.MEAI dependency-version: 4.0.4.11 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2025-12-11 11:01:19 +00:00
Copilot GitHub rogerbarreto Copilotcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>	67e83042cf	.NET: Add Conversation State Sample (Step05) (#2697 ) * Initial plan * Add Agent_OpenAI_Step05_Conversation sample for conversation state management Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update Program.cs comment to accurately describe the sample Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> * Update the code to use the ConversationClient more in line with the samples in OpenAI * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Changing sample to use ChatClientAgent and conversationId in GetNewThread --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: rogerbarreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-12-11 10:58:42 +00:00
Korolev Dmitry GitHub Mark Wallace	5da1c2fd4c	code ql sm04598 (#2723 ) Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>	2025-12-11 10:34:58 +00:00
SergeyMenshykhandGitHub	989b6ebe71	.NET: [BREAKING] Prevent nulls in AIAgent property (#2719 ) * prevent nulls in AIAgent property * address feedback	2025-12-11 09:50:25 +00:00
Evan MattsonandGitHub	3481914981	Capture file IDs from code interpreter in streaming responses (#2741 )	2025-12-11 07:30:19 +00:00
KurtandGitHub	4c6a5d4aa1	Python: fix: GroupChat ManagerSelectionResponse JSON Schema for OpenAI Structured Outpu… (#2750 ) * fix: ManagerSelectionResponse JSON Schema for OpenAI Structured Output Strict Mode * refactor: install pre-commit then commit again	2025-12-11 02:34:12 +00:00
Tao ChenandGitHub	191779ce80	Python: Add factory pattern to concurrent orchestration builder (#2738 ) * Add factory pattern to concurrent orchestration builder * Update readme * Address AI comments * Fix unit tests * Fix import * Prevent multiple calls to set participants or factories * Add comments * Mitigate warnings * Fix mypy * Address comments * Address Copilot comments * Fix tests	2025-12-11 01:23:28 +00:00
Copilot GitHub stephentoubcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Roger Barreto	638fbb5f03	Update Microsoft.Extensions.AI.* packages to 10.1.0 (#2735 ) * Initial plan * Update Microsoft.Extensions.AI dependencies to latest versions (10.1.0) Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: stephentoub <2642209+stephentoub@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>	2025-12-10 19:04:05 +00:00
Tao ChenandGitHub	523305ac62	Python: Add factory pattern to sequential orchestration builder (#2710 ) * Add factory pattern to sequential orchestration builder * Use temp list to avoid override * Add sample and some other fixes * Fix comments * Small fix * Update readme	2025-12-10 18:16:10 +00:00
Copilot GitHub larohracopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>Laveesh Rohra	3f4eeb00be	Python: Change DurableAIAgent log level from warning to debug when invoked without thread (#2736 ) * Initial plan * Change logger.warning to logger.debug for missing thread Co-authored-by: larohra <41490930+larohra@users.noreply.github.com> * Fix test to use getMessage() method for log records Co-authored-by: larohra <41490930+larohra@users.noreply.github.com> * Remove test for logging change per review feedback Co-authored-by: larohra <41490930+larohra@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: larohra <41490930+larohra@users.noreply.github.com> Co-authored-by: Laveesh Rohra <larohra@microsoft.com>	2025-12-10 17:57:08 +00:00
Evan MattsonandGitHub	b378ca75d1	Python: extend HITL support for all orchestration patterns (#2620 ) * Support HITL for orchestration patterns * Cleanup around naming * Fix typing issues * Clean up * Naming clean up * Updates to HITL to make it cleaner * Rename human input hook to orchestration request info * Clean up per PR feedback	2025-12-10 15:59:29 +00:00