chore: import upstream snapshot with attribution

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowEval/Evaluation_WorkflowEval.csproj

@@ -0,0 +1,16 @@
+<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.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
+  </ItemGroup>
+
+</Project>

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowEval/Program.cs

@@ -0,0 +1,74 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates evaluating a multi-agent workflow with per-agent breakdown.
+
+using Azure.AI.Projects;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Workflows;
+using Microsoft.Extensions.AI;
+
+string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
+    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
+string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
+
+// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
+// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
+// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
+AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
+
+// Create two agents: a planner and an executor.
+AIAgent planner = aiProjectClient.AsAIAgent(
+    model: deploymentName,
+    instructions: "You plan trips. Output a concise bullet-point plan.",
+    name: "planner");
+
+AIAgent executor = aiProjectClient.AsAIAgent(
+    model: deploymentName,
+    instructions: "You execute travel plans. Confirm the bookings listed in the plan.",
+    name: "executor");
+
+// Build a simple planner -> executor workflow.
+Workflow workflow = new WorkflowBuilder(planner)
+    .AddEdge(planner, executor)
+    .Build();
+
+// Run the workflow to completion (RunAsync returns Run which supports EvaluateAsync).
+await using Run run = await InProcessExecution.RunAsync(
+    workflow,
+    new ChatMessage(ChatRole.User, "Plan a weekend trip to Paris"));
+
+// Print the events from the run.
+foreach (WorkflowEvent evt in run.OutgoingEvents)
+{
+    if (evt is AgentResponseEvent response)
+    {
+        Console.WriteLine($"  {response.ExecutorId}: {response.Response.Text[..Math.Min(80, response.Response.Text.Length)]}...");
+    }
+}
+
+// Evaluate with per-agent breakdown.
+EvalCheck isNonempty = FunctionEvaluator.Create("is_nonempty", (string response) => response.Trim().Length > 5);
+EvalCheck hasKeywords = EvalChecks.KeywordCheck("plan", "trip");
+LocalEvaluator local = new(isNonempty, hasKeywords);
+
+AgentEvaluationResults results = await run.EvaluateAsync(local);
+
+Console.WriteLine();
+Console.WriteLine($"Overall: {results.Passed}/{results.Total} passed");
+
+if (results.SubResults is not null)
+{
+    foreach (var (agentName, sub) in results.SubResults)
+    {
+        Console.WriteLine($"  {agentName}: {sub.Passed}/{sub.Total} passed");
+        for (int i = 0; i < sub.Items.Count; i++)
+        {
+            foreach (var metric in sub.Items[i].Metrics)
+            {
+                string status = metric.Value.Interpretation?.Failed == true ? "FAIL" : "PASS";
+                Console.WriteLine($"    [{status}] {metric.Key}");
+            }
+        }
+    }
+}

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowEval/README.md

@@ -0,0 +1,30 @@
+# Evaluation - Workflow Eval
+
+This sample demonstrates evaluating a multi-agent workflow with per-agent breakdown.
+
+## What this sample demonstrates
+
+- Building a two-agent workflow (planner → executor)
+- Running the workflow and collecting events
+- Using `run.EvaluateAsync()` to evaluate the completed run
+- Per-agent sub-results via `results.SubResults`
+- Combining `FunctionEvaluator.Create` with `EvalChecks.KeywordCheck`
+
+## Prerequisites
+
+- .NET 10 SDK or later
+- Azure authentication available to `DefaultAzureCredential` (for local development, run `az login`)
+
+Set the following environment variables:
+
+```powershell
+$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
+$env:FOUNDRY_MODEL="gpt-4o-mini"
+```
+
+## Run the sample
+
+```powershell
+cd dotnet/samples/03-workflows/Evaluation
+dotnet run --project .\Evaluation_WorkflowEval
+```

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowExpectedOutputs/Evaluation_WorkflowExpectedOutputs.csproj

@@ -0,0 +1,16 @@
+<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.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Workflows\Microsoft.Agents.AI.Workflows.csproj" />
+  </ItemGroup>
+
+</Project>

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowExpectedOutputs/Program.cs

@@ -0,0 +1,76 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates evaluating a multi-agent workflow against a
+// golden answer using Foundry's reference-based Similarity evaluator.
+
+using Azure.AI.Projects;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Workflows;
+using Microsoft.Extensions.AI;
+using FoundryEvals = Microsoft.Agents.AI.Foundry.FoundryEvals;
+
+string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT")
+    ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
+string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
+
+// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
+// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
+// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
+AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
+
+// Build a two-agent workflow: a researcher writes a draft answer, then an
+// editor polishes it into the final response that we compare to ground truth.
+// EmitAgentResponseEvents is enabled so the workflow surfaces an AgentResponseEvent
+// for each agent — this is what EvaluateAsync uses to find the overall final answer.
+var hostOptions = new AIAgentHostOptions { EmitAgentResponseEvents = true };
+
+AIAgent researcher = projectClient.AsAIAgent(
+    model: deploymentName,
+    instructions: "You research questions and produce a short factual draft answer.",
+    name: "researcher");
+
+AIAgent editor = projectClient.AsAIAgent(
+    model: deploymentName,
+    instructions: "You take a draft answer and produce the final concise response.",
+    name: "editor");
+
+ExecutorBinding researcherExecutor = researcher.BindAsExecutor(hostOptions);
+ExecutorBinding editorExecutor = editor.BindAsExecutor(hostOptions);
+
+Workflow workflow = new WorkflowBuilder(researcherExecutor)
+    .AddEdge(researcherExecutor, editorExecutor)
+    .Build();
+
+// Run the workflow against the user question.
+const string Query = "What is the capital of France?";
+const string GroundTruth = "Paris";
+
+await using Run run = await InProcessExecution.RunAsync(
+    workflow,
+    new ChatMessage(ChatRole.User, Query));
+
+// Evaluate the overall workflow output against a golden answer using the
+// reference-based Similarity evaluator. The 'expectedOutput' value is stamped
+// onto the overall EvalItem.ExpectedOutput and is surfaced to Foundry as
+// `ground_truth` in the underlying JSONL payload.
+//
+// Per-agent breakdown is disabled here: ground truth applies to the workflow's
+// final answer, not to each sub-agent's intermediate output. Without
+// includePerAgent: false, the evaluator would be invoked for per-agent items
+// (which have no ExpectedOutput) and Similarity would fail validation.
+FoundryEvals similarity = new(projectClient, deploymentName, FoundryEvals.Similarity);
+
+AgentEvaluationResults results = await run.EvaluateAsync(
+    similarity,
+    includePerAgent: false,
+    expectedOutput: GroundTruth);
+
+Console.WriteLine($"Query: {Query}");
+Console.WriteLine($"Expected: {GroundTruth}");
+Console.WriteLine($"Provider: {results.ProviderName}");
+Console.WriteLine($"Passed: {results.Passed}/{results.Total}");
+if (results.ReportUrl is not null)
+{
+    Console.WriteLine($"Report: {results.ReportUrl}");
+}

dotnet/samples/03-workflows/Evaluation/Evaluation_WorkflowExpectedOutputs/README.md

@@ -0,0 +1,37 @@
+# Evaluation - Workflow Expected Outputs
+
+This sample demonstrates evaluating a multi-agent workflow's final answer
+against a golden expected output using Foundry's reference-based **Similarity**
+evaluator.
+
+## What this sample demonstrates
+
+- Building a small researcher → editor workflow
+- Running the workflow and obtaining a `Run`
+- Calling `run.EvaluateAsync(evaluator, expectedOutput: ...)` to attach a
+  ground-truth answer to the overall workflow item
+- Using `FoundryEvals.Similarity`, which requires a `ground_truth` value
+  per item
+
+The `expectedOutput` value is stamped onto the overall `EvalItem.ExpectedOutput`
+and is surfaced to Foundry as `ground_truth` in the JSONL payload sent to the
+Evals API.
+
+## Prerequisites
+
+- .NET 10 SDK or later
+- Azure authentication available to `DefaultAzureCredential` (for local development, run `az login`)
+
+Set the following environment variables:
+
+```powershell
+$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
+$env:FOUNDRY_MODEL="gpt-4o-mini"
+```
+
+## Run the sample
+
+```powershell
+cd dotnet/samples/03-workflows/Evaluation
+dotnet run --project .\Evaluation_WorkflowExpectedOutputs
+```