mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
8b191de936
* .NET: Add Microsoft Fabric sample #3674 (#4230) Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> * Python: Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference (#4207) * Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference Add embedding client implementations to existing provider packages: - OllamaEmbeddingClient: Text embeddings via Ollama's embed API - BedrockEmbeddingClient: Text embeddings via Amazon Titan on Bedrock - AzureAIInferenceEmbeddingClient: Text and image embeddings via Azure AI Inference, supporting Content | str input with separate model IDs for text (AZURE_AI_INFERENCE_EMBEDDING_MODEL_ID) and image (AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL_ID) endpoints Additional changes: - Rename EmbeddingCoT -> EmbeddingT, EmbeddingOptionsCoT -> EmbeddingOptionsT - Add otel_provider_name passthrough to all embedding clients - Register integration pytest marker in all packages - Add lazy-loading namespace exports for Ollama and Bedrock embeddings - Add image embedding sample using Cohere-embed-v3-english - Add azure-ai-inference dependency to azure-ai package Part of #1188 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix mypy duplicate name and ruff lint issues - Rename second 'vector' variable to 'img_vector' in image embedding loop - Combine nested with statements in tests - Remove unused result assignments in tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * updates from feedback * Fix CI failures in embedding usage handling - Fix Azure AI embedding mypy issues by normalizing vectors to list[float], safely accumulating optional usage token fields, and filtering None entries before constructing GeneratedEmbeddings - Avoid Bandit false positive by initializing usage details as an empty dict - Update OpenAI embedding tests to assert canonical usage keys (input_token_count/total_token_count) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * [Purview] Mark responses as responses and fix epoch bug for python long overflow (#4225) * .NET: Support InvokeMcpTool for declarative workflows (#4204) * Initial implementation of InvokeMcpTool in declarative workflow * Cleaned up sample implementation * Updated sample comments. * Added missing executor routing attribute * Fix PR comments. * Updated based on PR comments. * Updated based on PR comments. * Removed unnecessary using statement. * Update Python package versions to rc2 (#4258) - Bump core and azure-ai to 1.0.0rc2 - Bump preview packages to 1.0.0b260225 - Update dependencies to >=1.0.0rc2 - Add CHANGELOG entries for changes since rc1 - Update uv.lock Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * .NET: Fixing issue where OpenTelemetry span is never exported in .NET in-process workflow execution (#4196) * 1. Add reproduction test for issue #4155: workflow.run Activity never stopped in streaming OffThread path The WorkflowRunActivity_IsStopped_Streaming_OffThread test demonstrates that the workflow.run OpenTelemetry Activity created in StreamingRunEventStream.RunLoopAsync is started but never stopped when using the OffThread/Default streaming execution. The background run loop keeps running after event consumption completes, so the using Activity? declaration never disposes until explicit StopAsync() is called. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> 2. Fix workflow.run Activity never stopped in streaming OffThread execution (#4155) The workflow.run OpenTelemetry Activity in StreamingRunEventStream.RunLoopAsync was scoped to the method lifetime via 'using'. Since the run loop only exits on cancellation, the Activity was never stopped/exported until explicit disposal. Fix: Remove 'using' and explicitly dispose the Activity when the workflow reaches Idle status (all supersteps complete). A safety-net disposal in the finally block handles cancellation and error paths. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add root-level workflow.session activity spanning run loop lifetime\n\nImplements two-level telemetry hierarchy per PR feedback from lokitoth:\n- workflow.session: spans the entire run loop / stream lifetime\n- workflow_invoke: per input-to-halt cycle, nested within the session\n\nThis ensures the session activity stays open across multiple turns,\nwhile individual run activities are created and disposed per cycle.\n\nAlso fixes linkedSource CancellationTokenSource disposal leak in\nStreamingRunEventStream (added using declaration)." * Address Copilot review: fix Activity/CTS disposal, rename activity, add error tag\n\n1. LockstepRunEventStream: Remove 'using' from Activity in async iterator\n and manually dispose in finally block (fixes #4155 pattern). Also dispose\n linkedSource CTS in finally to prevent leak.\n2. Tags.cs: Add ErrorMessage (\"error.message\") tag for runtime errors,\n distinct from BuildErrorMessage (\"build.error.message\").\n3. ActivityNames: Rename WorkflowRun from \"workflow_invoke\" to \"workflow.run\"\n for cross-language consistency.\n4. WorkflowTelemetryContext: Fix XML doc to say \"outer/parent span\" instead\n of \"root-level span\".\n5. ObservabilityTests: Assert WorkflowSession absence when DisableWorkflowRun\n is true.\n6. WorkflowRunActivityStopTests: Fix streaming test race by disposing\n StreamingRun before asserting activities are stopped.\n7. StreamingRunEventStream/LockstepRunEventStream: Use Tags.ErrorMessage\n instead of Tags.BuildErrorMessage for runtime error events." * Review fixes: revert workflow_invoke rename, use 'using' for linkedSource, move SessionStarted earlier\n\n- Revert ActivityNames.WorkflowRun back to \"workflow_invoke\" (OTEL semantic convention contract)\n- Use 'using' declaration for linkedSource CTS in LockstepRunEventStream (no timing sensitivity)\n- Move SessionStarted event before WaitForInputAsync in StreamingRunEventStream to match Lockstep behavior" * Improve naming and comments in WorkflowRunActivityStopTests" * Prevent session Activity.Current leak in lockstep mode, add nesting test Save and restore Activity.Current in LockstepRunEventStream.Start() so the session activity doesn't leak into caller code via AsyncLocal. Re-establish Activity.Current = sessionActivity before creating the run activity in TakeEventStreamAsync to preserve parent-child nesting. Add test verifying app activities after RunAsync are not parented under the session, and that the workflow_invoke activity nests under the session." * Fix stale XML doc: WorkflowRun -> WorkflowInvoke in ObservabilityTests --------- Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python / .NET Samples - Restructure and Improve Samples (Feature Branc… (#4092) * Python: .NET Samples - Restructure and Improve Samples (Feature Branch) (#4091) * Moved by agent (#4094) * Fix readme links * .NET Samples - Create `04-hosting` learning path step (#4098) * Agent move * Agent reorderd * Remove A2A section from README Removed A2A section from the Getting Started README. * Agent fixed links * Fix broken sample links in durable-agents README (#4101) * Initial plan * Fix broken internal links in documentation Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Revert template link changes; keep only durable-agents README fix Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * .NET Samples - Create `03-workflows` learning path step (#4102) * Fix solution project path * Python: Fix broken markdown links to repo resources (outside /docs) (#4105) * Initial plan * Fix broken markdown links to repo resources Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Update README to rename .NET Workflows Samples section --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * .NET Samples - Create `02-agents` learning path step (#4107) * .NET: Fix broken relative link in GroupChatToolApproval README (#4108) * Initial plan * Fix broken link in GroupChatToolApproval README Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Update labeler configuration for workflow samples * .NET - Reorder Agents samples to start from Step01 instead of Step04 (#4110) * Fix solution * Resolve new sample paths * Move new AgentSkills and AgentWithMemory_Step04 samples * Fix link * Fix readme path * fix: update stale dotnet/samples/Durable path reference in AGENTS.md Co-authored-by: crickman <66376200+crickman@users.noreply.github.com> * Moved new sample * Update solution * Resolve merge (new sample) * Sync to new sample - FoundryAgents_Step21_BingCustomSearch * Updated README * .NET Samples - Configuration Naming Update (#4149) * .NET: Restore AzureFunctions index parity with ConsoleApps under DurableAgents samples (#4221) * Clean-up `05_host_your_agent` * Config setting consistency * Refine samples * AGENTS.md * Move new samples * Re-order samples * Move new project and fixup solution * Fixup model config * Fix up new UT project --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> * Python: Fix Bedrock embedding test stub missing meta attribute (#4287) * Fix Bedrock embedding test stub missing meta attribute * Increase test coverage so gate passes * Python: (ag-ui): fix approval payloads being re-processed on subsequent conversation turns (#4232) * Fix ag-ui tool call issue * Safe json fix * Python: Update workflow orchestration samples to use AzureOpenAIResponsesClient (#4285) * Update workflow orchestration samples to use AzureOpenAIResponsesClient * Fix broken link * Move scripts to scripts folder --------- Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> Co-authored-by: Chris <66376200+crickman@users.noreply.github.com> Co-authored-by: Eduard van Valkenburg <eavanvalkenburg@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Rishabh Chawla <rishabhchawla1995@gmail.com> Co-authored-by: Peter Ibekwe <109177538+peibekwe@users.noreply.github.com> Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com> Co-authored-by: Ben Thomas <ben.thomas@microsoft.com> Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: Evan Mattson <35585003+moonbox3@users.noreply.github.com>
239 lines
9.4 KiB
C#
239 lines
9.4 KiB
C#
// Copyright (c) Microsoft. All rights reserved.
|
|
|
|
using System.Text.Json;
|
|
using System.Text.Json.Serialization;
|
|
using Azure.AI.OpenAI;
|
|
using Azure.Identity;
|
|
using Microsoft.Agents.AI;
|
|
using Microsoft.Agents.AI.Workflows;
|
|
using Microsoft.Extensions.AI;
|
|
|
|
namespace WorkflowCustomAgentExecutorsSample;
|
|
|
|
/// <summary>
|
|
/// This sample demonstrates how to create custom executors for AI agents.
|
|
/// This is useful when you want more control over the agent's behaviors in a workflow.
|
|
///
|
|
/// In this example, we create two custom executors:
|
|
/// 1. SloganWriterExecutor: An AI agent that generates slogans based on a given task.
|
|
/// 2. FeedbackExecutor: An AI agent that provides feedback on the generated slogans.
|
|
/// (These two executors manage the agent instances and their conversation threads.)
|
|
///
|
|
/// The workflow alternates between these two executors until the slogan meets a certain
|
|
/// quality threshold or a maximum number of attempts is reached.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// Pre-requisites:
|
|
/// - Foundational samples should be completed first.
|
|
/// - An Azure OpenAI chat completion deployment that supports structured outputs must be configured.
|
|
/// </remarks>
|
|
public static class Program
|
|
{
|
|
private static async Task Main()
|
|
{
|
|
// Set up the Azure OpenAI client
|
|
var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
|
|
var deploymentName = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
|
|
var chatClient = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential()).GetChatClient(deploymentName).AsIChatClient();
|
|
|
|
// Create the executors
|
|
var sloganWriter = new SloganWriterExecutor("SloganWriter", chatClient);
|
|
var feedbackProvider = new FeedbackExecutor("FeedbackProvider", chatClient);
|
|
|
|
// Build the workflow by adding executors and connecting them
|
|
var workflow = new WorkflowBuilder(sloganWriter)
|
|
.AddEdge(sloganWriter, feedbackProvider)
|
|
.AddEdge(feedbackProvider, sloganWriter)
|
|
.WithOutputFrom(feedbackProvider)
|
|
.Build();
|
|
|
|
// Execute the workflow
|
|
await using StreamingRun run = await InProcessExecution.RunStreamingAsync(workflow, input: "Create a slogan for a new electric SUV that is affordable and fun to drive.");
|
|
await foreach (WorkflowEvent evt in run.WatchStreamAsync())
|
|
{
|
|
if (evt is SloganGeneratedEvent or FeedbackEvent)
|
|
{
|
|
// Custom events to allow us to monitor the progress of the workflow.
|
|
Console.WriteLine($"{evt}");
|
|
}
|
|
|
|
if (evt is WorkflowOutputEvent outputEvent)
|
|
{
|
|
Console.WriteLine($"{outputEvent}");
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// A class representing the output of the slogan writer agent.
|
|
/// </summary>
|
|
public sealed class SloganResult
|
|
{
|
|
[JsonPropertyName("task")]
|
|
public required string Task { get; set; }
|
|
|
|
[JsonPropertyName("slogan")]
|
|
public required string Slogan { get; set; }
|
|
}
|
|
|
|
/// <summary>
|
|
/// A class representing the output of the feedback agent.
|
|
/// </summary>
|
|
public sealed class FeedbackResult
|
|
{
|
|
[JsonPropertyName("comments")]
|
|
public string Comments { get; set; } = string.Empty;
|
|
|
|
[JsonPropertyName("rating")]
|
|
public int Rating { get; set; }
|
|
|
|
[JsonPropertyName("actions")]
|
|
public string Actions { get; set; } = string.Empty;
|
|
}
|
|
|
|
/// <summary>
|
|
/// A custom event to indicate that a slogan has been generated.
|
|
/// </summary>
|
|
internal sealed class SloganGeneratedEvent(SloganResult sloganResult) : WorkflowEvent(sloganResult)
|
|
{
|
|
public override string ToString() => $"Slogan: {sloganResult.Slogan}";
|
|
}
|
|
|
|
/// <summary>
|
|
/// A custom executor that uses an AI agent to generate slogans based on a given task.
|
|
/// Note that this executor has two message handlers:
|
|
/// 1. HandleAsync(string message): Handles the initial task to create a slogan.
|
|
/// 2. HandleAsync(Feedback message): Handles feedback to improve the slogan.
|
|
/// </summary>
|
|
internal sealed partial class SloganWriterExecutor : Executor
|
|
{
|
|
private readonly AIAgent _agent;
|
|
private AgentSession? _session;
|
|
|
|
/// <summary>
|
|
/// Initializes a new instance of the <see cref="SloganWriterExecutor"/> class.
|
|
/// </summary>
|
|
/// <param name="id">A unique identifier for the executor.</param>
|
|
/// <param name="chatClient">The chat client to use for the AI agent.</param>
|
|
public SloganWriterExecutor(string id, IChatClient chatClient) : base(id)
|
|
{
|
|
ChatClientAgentOptions agentOptions = new()
|
|
{
|
|
ChatOptions = new()
|
|
{
|
|
Instructions = "You are a professional slogan writer. You will be given a task to create a slogan.",
|
|
ResponseFormat = ChatResponseFormat.ForJsonSchema<SloganResult>()
|
|
}
|
|
};
|
|
|
|
this._agent = new ChatClientAgent(chatClient, agentOptions);
|
|
}
|
|
|
|
[MessageHandler]
|
|
public async ValueTask<SloganResult> HandleAsync(string message, IWorkflowContext context, CancellationToken cancellationToken = default)
|
|
{
|
|
this._session ??= await this._agent.CreateSessionAsync(cancellationToken);
|
|
|
|
var result = await this._agent.RunAsync(message, this._session, cancellationToken: cancellationToken);
|
|
|
|
var sloganResult = JsonSerializer.Deserialize<SloganResult>(result.Text) ?? throw new InvalidOperationException("Failed to deserialize slogan result.");
|
|
|
|
await context.AddEventAsync(new SloganGeneratedEvent(sloganResult), cancellationToken);
|
|
return sloganResult;
|
|
}
|
|
|
|
[MessageHandler]
|
|
public async ValueTask<SloganResult> HandleAsync(FeedbackResult message, IWorkflowContext context, CancellationToken cancellationToken = default)
|
|
{
|
|
var feedbackMessage = $"""
|
|
Here is the feedback on your previous slogan:
|
|
Comments: {message.Comments}
|
|
Rating: {message.Rating}
|
|
Suggested Actions: {message.Actions}
|
|
|
|
Please use this feedback to improve your slogan.
|
|
""";
|
|
|
|
var result = await this._agent.RunAsync(feedbackMessage, this._session, cancellationToken: cancellationToken);
|
|
var sloganResult = JsonSerializer.Deserialize<SloganResult>(result.Text) ?? throw new InvalidOperationException("Failed to deserialize slogan result.");
|
|
|
|
await context.AddEventAsync(new SloganGeneratedEvent(sloganResult), cancellationToken);
|
|
return sloganResult;
|
|
}
|
|
}
|
|
|
|
/// <summary>
|
|
/// A custom event to indicate that feedback has been provided.
|
|
/// </summary>
|
|
internal sealed class FeedbackEvent(FeedbackResult feedbackResult) : WorkflowEvent(feedbackResult)
|
|
{
|
|
private readonly JsonSerializerOptions _options = new() { WriteIndented = true };
|
|
public override string ToString() => $"Feedback:\n{JsonSerializer.Serialize(feedbackResult, this._options)}";
|
|
}
|
|
|
|
/// <summary>
|
|
/// A custom executor that uses an AI agent to provide feedback on a slogan.
|
|
/// </summary>
|
|
internal sealed class FeedbackExecutor : Executor<SloganResult>
|
|
{
|
|
private readonly AIAgent _agent;
|
|
private AgentSession? _session;
|
|
|
|
public int MinimumRating { get; init; } = 8;
|
|
|
|
public int MaxAttempts { get; init; } = 3;
|
|
|
|
private int _attempts;
|
|
|
|
/// <summary>
|
|
/// Initializes a new instance of the <see cref="FeedbackExecutor"/> class.
|
|
/// </summary>
|
|
/// <param name="id">A unique identifier for the executor.</param>
|
|
/// <param name="chatClient">The chat client to use for the AI agent.</param>
|
|
public FeedbackExecutor(string id, IChatClient chatClient) : base(id)
|
|
{
|
|
ChatClientAgentOptions agentOptions = new()
|
|
{
|
|
ChatOptions = new()
|
|
{
|
|
Instructions = "You are a professional editor. You will be given a slogan and the task it is meant to accomplish.",
|
|
ResponseFormat = ChatResponseFormat.ForJsonSchema<FeedbackResult>()
|
|
}
|
|
};
|
|
|
|
this._agent = new ChatClientAgent(chatClient, agentOptions);
|
|
}
|
|
|
|
public override async ValueTask HandleAsync(SloganResult message, IWorkflowContext context, CancellationToken cancellationToken = default)
|
|
{
|
|
this._session ??= await this._agent.CreateSessionAsync(cancellationToken);
|
|
|
|
var sloganMessage = $"""
|
|
Here is a slogan for the task '{message.Task}':
|
|
Slogan: {message.Slogan}
|
|
Please provide feedback on this slogan, including comments, a rating from 1 to 10, and suggested actions for improvement.
|
|
""";
|
|
|
|
var response = await this._agent.RunAsync(sloganMessage, this._session, cancellationToken: cancellationToken);
|
|
var feedback = JsonSerializer.Deserialize<FeedbackResult>(response.Text) ?? throw new InvalidOperationException("Failed to deserialize feedback.");
|
|
|
|
await context.AddEventAsync(new FeedbackEvent(feedback), cancellationToken);
|
|
|
|
if (feedback.Rating >= this.MinimumRating)
|
|
{
|
|
await context.YieldOutputAsync($"The following slogan was accepted:\n\n{message.Slogan}", cancellationToken);
|
|
return;
|
|
}
|
|
|
|
if (this._attempts >= this.MaxAttempts)
|
|
{
|
|
await context.YieldOutputAsync($"The slogan was rejected after {this.MaxAttempts} attempts. Final slogan:\n\n{message.Slogan}", cancellationToken);
|
|
return;
|
|
}
|
|
|
|
await context.SendMessageAsync(feedback, cancellationToken: cancellationToken);
|
|
this._attempts++;
|
|
}
|
|
}
|