Remove duplicate WebhookKey properties from merge

Both our branch and main added WebhookKey to the Anthropic test
mock classes, resulting in CS0102 duplicate definition errors.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.github/workflows/merge-gatekeeper.yml

@@ -2,7 +2,7 @@ name: Merge Gatekeeper
 
 on:
   pull_request:
-    branches: ["main", "feature*"]
+    branches: [ "main", "feature*" ]
   merge_group:
     branches: ["main"]
 
@@ -13,105 +13,23 @@ concurrency:
 jobs:
   merge-gatekeeper:
     runs-on: ubuntu-latest
+    # Restrict permissions of the GITHUB_TOKEN.
+    # Docs: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
     permissions:
       checks: read
       statuses: read
     steps:
-      - name: Wait for required checks
+      - name: Run Merge Gatekeeper
+        # NOTE: v1 is updated to reflect the latest v1.x.y. Please use any tag/branch that suits your needs:
+        #       https://github.com/upsidr/merge-gatekeeper/tags
+        #       https://github.com/upsidr/merge-gatekeeper/branches
+        uses: upsidr/merge-gatekeeper@v1
         if: github.event_name == 'pull_request'
-        uses: actions/github-script@v8
-        env:
-          TIMEOUT_SECONDS: "3600"
-          INTERVAL_SECONDS: "30"
-          SELF_JOB_NAME: ${{ github.job }}
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          timeout: 3600
+          interval: 30
           # "Cleanup artifacts", "Agent", "Prepare", and "Upload results" are check runs
           # created by an org-level GitHub App (MSDO), not by any workflow in this repo.
           # They are outside our control and their transient failures should not block merges.
-          IGNORED_NAMES: "CodeQL,CodeQL analysis (csharp),Cleanup artifacts,Agent,Prepare,Upload results"
-        with:
-          script: |
-            const timeoutSeconds = Number(process.env.TIMEOUT_SECONDS);
-            const intervalSeconds = Number(process.env.INTERVAL_SECONDS);
-            const selfName = process.env.SELF_JOB_NAME;
-            const ignored = new Set(
-              process.env.IGNORED_NAMES.split(',').map((s) => s.trim()).filter(Boolean),
-            );
-
-            const sha = context.payload.pull_request.head.sha;
-            const { owner, repo } = context.repo;
-
-            const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
-
-            // Mirrors upsidr/merge-gatekeeper: merge combined-statuses and check-runs
-            // for the PR head SHA, with combined-statuses winning on name collision.
-            async function collectChecks() {
-              const merged = new Map();
-
-              const combined = await github.rest.repos.getCombinedStatusForRef({
-                owner, repo, ref: sha, per_page: 100,
-              });
-              for (const s of combined.data.statuses ?? []) {
-                if (!merged.has(s.context)) {
-                  // Combined-status states: success | pending | error | failure
-                  merged.set(s.context, { name: s.context, state: s.state });
-                }
-              }
-
-              const runs = await github.paginate(github.rest.checks.listForRef, {
-                owner, repo, ref: sha, per_page: 100,
-              });
-              for (const r of runs) {
-                if (merged.has(r.name)) continue;
-                let state;
-                if (r.status !== 'completed') {
-                  state = 'pending';
-                } else if (r.conclusion === 'skipped') {
-                  continue; // Skipped runs are dropped, matching the original action.
-                } else if (r.conclusion === 'success' || r.conclusion === 'neutral') {
-                  state = 'success';
-                } else {
-                  // cancelled | timed_out | action_required | stale | failure
-                  state = 'error';
-                }
-                merged.set(r.name, { name: r.name, state });
-              }
-
-              return [...merged.values()];
-            }
-
-            function evaluate(entries) {
-              const failed = [];
-              const pending = [];
-              const succeeded = [];
-              for (const e of entries) {
-                if (e.name === selfName || ignored.has(e.name)) continue;
-                if (e.state === 'success') succeeded.push(e.name);
-                else if (e.state === 'error' || e.state === 'failure') failed.push(e.name);
-                else pending.push(e.name);
-              }
-              return { failed, pending, succeeded };
-            }
-
-            const deadline = Date.now() + timeoutSeconds * 1000;
-            for (;;) {
-              const entries = await collectChecks();
-              const { failed, pending, succeeded } = evaluate(entries);
-
-              core.info(
-                `succeeded=${succeeded.length} pending=${pending.length} failed=${failed.length}`,
-              );
-              if (failed.length) {
-                core.setFailed(`Failing checks: ${failed.join(', ')}`);
-                return;
-              }
-              if (pending.length === 0) {
-                core.info(`All required checks passed: ${succeeded.join(', ') || '(none)'}`);
-                return;
-              }
-              if (Date.now() > deadline) {
-                core.setFailed(`Timed out waiting for: ${pending.join(', ')}`);
-                return;
-              }
-              core.info(`Waiting on (${pending.length}): ${pending.slice(0, 10).join(', ')}${pending.length > 10 ? ', …' : ''}`);
-              await sleep(intervalSeconds * 1000);
-            }
+          ignored: CodeQL,CodeQL analysis (csharp),Cleanup artifacts,Agent,Prepare,Upload results

.gitignore

@@ -246,5 +246,3 @@ dotnet/filtered-*.slnx
 # Local tool state
 .omc/
 .omx/
-
-**/issues/

docs/decisions/0026-message-merger-invariants.md

@@ -1,191 +0,0 @@
----
-status: accepted
-contact: lokitoth
-date: 2026-05-13
-deciders: lokitoth
-consulted:
-informed:
----
-
-# MessageMerger Streaming Merge Invariants
-
-## Context and Problem Statement
-
-`Microsoft.Agents.AI.Workflows.MessageMerger` is the internal component that
-folds a stream of `AgentResponseUpdate` items emitted by an agent (or by a
-hosting executor wrapping an agent) into a single `AgentResponse` for a turn.
-Multi-agent workflows (handoff, group chat, orchestration) rely on this
-merger to produce a coherent transcript even when updates arrive interleaved
-across responses, messages, and timestamps.
-
-Prior to this change the contract that hosting executors and the merger
-should jointly enforce was implicit. The implementation also carried a small
-amount of dead state (`createdTimes`) that was collected but never consumed,
-suggesting that an earlier, timestamp-driven ordering scheme had been
-abandoned without documentation, and the live code still ran an unreliable
-`CreatedAt`-based sort that could reorder messages across concurrent agents
-inside a single workflow super-step. There were no tests pinning down the
-ordering or grouping behavior, so any future refactor risked silently
-regressing it.
-
-The problem this ADR addresses is therefore: **what merge guarantees does
-`MessageMerger` make to its callers, and how do we lock those guarantees in
-without changing observable behavior in non-pathological cases?**
-
-## Decision Drivers
-
-- **A. Predictable ordering.** Developers consuming a merged `AgentResponse`
-  must be able to reason about the order in which messages appear without
-  having to know whether updates carried `CreatedAt`.
-- **B. Coherent multi-agent transcripts.** When several agents stream into
-  one merger within a single workflow super-step, each agent's contribution
-  must read as a contiguous block; and a step's updates must precede the
-  next step's updates.
-- **C. Stable hosting-executor contract.** A turn must be addressable by a
-  single `ResponseId`; updates without one are an exceptional, "dangling"
-  case rather than the norm.
-- **D. Minimal behavioral change for non-pathological inputs.** This work
-  is intended to document and test current behavior, not to alter what
-  users see today in well-formed agent streams.
-- **E. Discoverability for future contributors.** Known sharp edges (e.g.
-  cross-`ResponseId` ordering, dangling-update placement) should be written
-  down so they are not rediscovered as bugs.
-
-## Considered Options
-
-1. **Option 1 — Document invariants, pin them with tests, and use pure
-   emission/insertion order for both responses and the messages inside
-   each response.** Removes the unreliable `CreatedAt`-based sort and the
-   dead `createdTimes` collection. Behavioral change only for inputs that
-   relied on `CreatedAt` to re-order updates after the fact — which the
-   prior comparer could not do correctly anyway (non-transitive).
-2. **Option 2 — Rewrite `MessageMerger` to group strictly by `AgentId`
-   (rather than `ResponseId`), and to use a stable, transitive comparer
-   that mixes `CreatedAt` with insertion index.** Behavioral change; would
-   also require updating hosting executors that currently assume
-   `ResponseId`-based grouping.
-3. **Option 3 — Leave the code and tests as-is; capture edge cases only
-   in a working note.** No code or test change.
-
-## Decision Outcome
-
-Chosen option: **Option 1 — Document invariants, pin them with tests,
-and use pure emission/insertion order; remove the dead `createdTimes`
-collection.**
-
-This option satisfies driver A (predictable ordering: emission order is
-the simplest reasoning model), driver B (per-`ResponseId` grouping plus
-first-seen ordering across responses gives both per-agent blocks within a
-step and step-ordering across steps), driver C (single ResponseId per
-turn is unchanged), and driver E (invariants and edge cases are now
-written down and covered by tests).
-
-Driver D (minimal behavioral change) is satisfied because well-formed
-agent streams already emit updates in the order they want to appear; the
-prior `CreatedAt`-based sort only mattered for pathological inputs (mixed
-or out-of-order timestamps from concurrent agents), and on those inputs
-the old comparer was non-transitive and therefore unreliable. Removing
-the sort makes those inputs deterministic — they now follow emission
-order — without disturbing the well-formed case.
-
-Option 2 was rejected for this iteration because it changes what callers
-observe in well-formed flows and would require a coordinated change
-across hosting executors. It is a candidate for a follow-up ADR if the
-known edge cases below are reported as bugs in practice.
-
-Option 3 was rejected because it leaves the invariants un-tested and the
-dead code in place, so the next refactor can break the contract without
-any signal.
-
-### Invariants
-
-The following invariants are now part of the contract of
-`MessageMerger`/hosting executors and are covered by tests in
-`MessageMergerTests`:
-
-1. **Single `ResponseId` per turn.** Every `AgentResponseUpdate` produced
-   by a hosting executor in a single agent turn shares one `ResponseId`.
-   If the underlying agent does not supply one, the executor assigns it.
-   Updates with `ResponseId == null` are treated as "dangling" and
-   flattened into loose messages at the end of the merged response.
-2. **Pure emission-order preservation.** Within a `ResponseId` block,
-   messages appear in the order their updates first arrived at the
-   merger. Across `ResponseId` blocks, blocks appear in first-seen order.
-   `CreatedAt` is **not** consulted when ordering messages or blocks —
-   only when stamping the merged response and its child messages.
-3. **Per-`ResponseId` grouping (no interleaving).** Messages produced
-   under one `ResponseId` are emitted as a contiguous block in the merged
-   `AgentResponse`. Combined with Invariant 1, this yields:
-   - **Within a workflow super-step with one agent**: all messages
-     appear together, in emission order.
-   - **Within a super-step with multiple agents**: each agent's messages
-     are a contiguous block, ordered by which agent emitted first.
-   - **Across super-steps**: a step's blocks all precede the next step's
-     blocks, because the next step cannot start emitting until the
-     current step's emissions have arrived at the merger.
-
-### Consequences
-
-- Good, because the merge contract is now explicit, regression-tested,
-  and trivially reasoned about (it is just emission order with
-  per-`ResponseId` grouping).
-- Good, because removing the unreliable `CreatedAt`-based sort eliminates
-  a latent bug — the prior comparer was non-transitive on mixed-timestamp
-  inputs, so `List<T>.Sort` could in principle return any of several
-  orderings or throw on some runtimes.
-- Good, because removing the unused `createdTimes` collection eliminates
-  a misleading code smell.
-- Good, because hosting-executor authors have a written checklist of
-  invariants to satisfy.
-- Neutral, because well-formed agent streams (those that emit updates in
-  the order they want to appear) see no change in output.
-- Bad, because callers who relied on a server-supplied `CreatedAt` to
-  retro-correct out-of-order emissions will no longer see that
-  correction — they must ensure emission order matches desired output
-  order, or attach to `RawRepresentation` for original timestamps.
-
-## Validation
-
-- Unit tests in
-  `dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/MessageMergerTests.cs`
-  cover each invariant:
-  - Insertion-order preservation with no timestamps.
-  - Insertion-order preservation with mixed timestamps (emission order
-    wins over `CreatedAt`).
-  - Determinism across repeated runs with mixed timestamps.
-  - Per-`ResponseId` grouping for interleaved multi-agent streams within
-    a single step.
-  - Per-`ResponseId` grouping with distinct response ids.
-- Existing tests for assembly, function-call/result ordering, and
-  `FinishReason` propagation continue to pass.
-
-## More Information
-
-### Known edge cases (intentionally not fixed in this ADR)
-
-These are properties of the *current* `MessageMerger` that callers should
-be aware of. They are not invariants — they may change in a future ADR —
-but they are present in the shipped behavior covered by tests above.
-
-| # | Edge case | Risk | Notes |
-|---|-----------|------|-------|
-| 1 | Cross-`ResponseId` ordering follows first-seen-`ResponseId` order, not chronological order across responses. | Medium | Acceptable today because each turn has a single `ResponseId` (Invariant 1); only matters if a caller deliberately interleaves multiple response ids inside one step. |
-| 2 | Updates with `ResponseId == null` are always emitted **after** all keyed responses, regardless of arrival time. | Medium | Documented as the "dangling" path; agents should always emit a `ResponseId`. |
-| 3 | Within a response, updates with `MessageId == null` are always emitted **after** keyed messages. | Low | Same rationale as #2, scoped to messages within a response. |
-| 4 | The merged response's `CreatedAt` is set to `DateTimeOffset.UtcNow`; per-response `CreatedAt` is propagated onto each contained `ChatMessage` instead of being preserved at the response level. | Low | Callers who need original per-update timestamps should read them from `RawRepresentation` or capture them before merging. |
-| 5 | Metadata on dangling (`ResponseId == null`) updates — `FinishReason`, `Usage`, `AgentId`, `AdditionalProperties` — is **not** merged into the final `AgentResponse`; only their `Messages` are surfaced. | Medium | Hosting executors must attach metadata to a keyed update if they want it reflected in the merged response. |
-| 6 | Emission order is the **only** ordering signal — `CreatedAt` differences between updates are ignored when ordering. | Low | This is the intended behavior under Invariant 2; producers must emit in the desired output order. |
-
-If any of these become observable problems in production, the appropriate
-follow-up is a new ADR that supersedes this one (likely realizing
-"Option 2") rather than a silent fix.
-
-### Code references
-
-- `dotnet/src/Microsoft.Agents.AI.Workflows/MessageMerger.cs` — merger
-  implementation. The previously-unused `createdTimes` collection and
-  the `CreatedAt`-based sort have both been removed in this change.
-- `dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/MessageMergerTests.cs` —
-  invariant tests added in this change.
-- `AgentInvocationContext.ResponseId` and `ToStreamingResponseAsync` —
-  the hosting-executor side of Invariant 1.

dotnet/agent-framework-dotnet.slnx

@@ -298,7 +298,6 @@
   </Folder>
   <Folder Name="/Samples/03-workflows/Evaluation/">
     <Project Path="samples/03-workflows/Evaluation/Evaluation_WorkflowEval/Evaluation_WorkflowEval.csproj" />
-    <Project Path="samples/03-workflows/Evaluation/Evaluation_WorkflowExpectedOutputs/Evaluation_WorkflowExpectedOutputs.csproj" />
   </Folder>
   <Folder Name="/Samples/04-hosting/">
   </Folder>
@@ -583,7 +582,6 @@
     <Project Path="src/Microsoft.Agents.AI.DurableTask/Microsoft.Agents.AI.DurableTask.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Foundry.Hosting/Microsoft.Agents.AI.Foundry.Hosting.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Foundry/Microsoft.Agents.AI.Foundry.csproj" />
-    <Project Path="src/Microsoft.Agents.AI.Harness/Microsoft.Agents.AI.Harness.csproj" />
     <Project Path="src/Microsoft.Agents.AI.GitHub.Copilot/Microsoft.Agents.AI.GitHub.Copilot.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.A2A.AspNetCore/Microsoft.Agents.AI.Hosting.A2A.AspNetCore.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.A2A/Microsoft.Agents.AI.Hosting.A2A.csproj" />
@@ -638,7 +636,6 @@
     <Project Path="tests/Microsoft.Agents.AI.Foundry.UnitTests/Microsoft.Agents.AI.Foundry.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Foundry.Hosting.UnitTests/Microsoft.Agents.AI.Foundry.Hosting.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.GitHub.Copilot.UnitTests/Microsoft.Agents.AI.GitHub.Copilot.UnitTests.csproj" />
-    <Project Path="tests/Microsoft.Agents.AI.Harness.UnitTests/Microsoft.Agents.AI.Harness.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.A2A.UnitTests/Microsoft.Agents.AI.Hosting.A2A.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.UnitTests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AzureFunctions.UnitTests/Microsoft.Agents.AI.Hosting.AzureFunctions.UnitTests.csproj" />

dotnet/agent-framework-release.slnf

@@ -7,7 +7,6 @@
       "src\\Microsoft.Agents.AI.AGUI\\Microsoft.Agents.AI.AGUI.csproj",
       "src\\Microsoft.Agents.AI.Anthropic\\Microsoft.Agents.AI.Anthropic.csproj",
       "src\\Microsoft.Agents.AI.GitHub.Copilot\\Microsoft.Agents.AI.GitHub.Copilot.csproj",
-      "src\\Microsoft.Agents.AI.Harness\\Microsoft.Agents.AI.Harness.csproj",
       "src\\Microsoft.Agents.AI.AzureAI.Persistent\\Microsoft.Agents.AI.AzureAI.Persistent.csproj",
       "src\\Microsoft.Agents.AI.Foundry\\Microsoft.Agents.AI.Foundry.csproj",
       "src\\Microsoft.Agents.AI.Foundry.Hosting\\Microsoft.Agents.AI.Foundry.Hosting.csproj",

dotnet/nuget/nuget-package.props

@@ -1,14 +1,14 @@
 <Project>
   <PropertyGroup>
     <!-- Central version prefix - applies to all nuget packages. -->
-    <VersionPrefix>1.6.0</VersionPrefix>
+    <VersionPrefix>1.5.0</VersionPrefix>
     <RCNumber>1</RCNumber>
-    <DateSuffix>260512</DateSuffix>
+    <DateSuffix>260507</DateSuffix>
     <PackageVersion Condition="'$(IsReleaseCandidate)' == 'true'">$(VersionPrefix)-rc$(RCNumber)</PackageVersion>
     <PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' != ''">$(VersionPrefix)-$(VersionSuffix).$(DateSuffix).1</PackageVersion>
     <PackageVersion Condition="'$(IsReleaseCandidate)' != 'true' AND '$(VersionSuffix)' == ''">$(VersionPrefix)-preview.$(DateSuffix).1</PackageVersion>
     <PackageVersion Condition="'$(IsReleased)' == 'true'">$(VersionPrefix)</PackageVersion>
-    <GitTag>1.6.0</GitTag>
+    <GitTag>1.5.0</GitTag>
 
     <Configurations>Debug;Release;Publish</Configurations>
     <IsPackable>true</IsPackable>

dotnet/samples/02-agents/AgentsWithFoundry/Agent_Step25_FoundryToolboxMcp/Program.cs

@@ -20,18 +20,22 @@ using OpenAI.Responses;
 #pragma warning disable OPENAI001 // Experimental API
 #pragma warning disable AAIP001  // AgentToolboxes is experimental
 
-// Name of the toolbox to create and connect to.
+// Must match the `<name>` segment of FOUNDRY_TOOLBOX_ENDPOINT.
 const string ToolboxName = "research_toolbox";
 const string Query = "What tools do you have access to?";
 
 string endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT")
     ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
 string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
+string toolboxEndpoint = Environment.GetEnvironmentVariable("FOUNDRY_TOOLBOX_ENDPOINT")
+    ?? throw new InvalidOperationException(
+        "FOUNDRY_TOOLBOX_ENDPOINT is not set. Example: " +
+        "https://<account>.services.ai.azure.com/api/projects/<project>/toolsets/<name>/mcp?api-version=2025-05-01-preview");
 
 TokenCredential credential = new DefaultAzureCredential();
 
 // Comment out if the toolbox already exists in your Foundry project.
-var toolboxEndpoint = await CreateSampleToolboxAsync(ToolboxName, endpoint, credential);
+await CreateSampleToolboxAsync(ToolboxName, endpoint, credential);
 
 // Inject a fresh Azure AI bearer token on every MCP request.
 using var httpClient = new HttpClient(new BearerTokenHandler(credential, "https://ai.azure.com/.default")
@@ -47,11 +51,6 @@ await using McpClient mcpClient = await McpClient.CreateAsync(
         {
             Endpoint = new Uri(toolboxEndpoint),
             Name = "foundry_toolbox",
-            TransportMode = HttpTransportMode.StreamableHttp,
-            AdditionalHeaders = new Dictionary<string, string>
-            {
-                ["Foundry-Features"] = "Toolboxes=V1Preview",
-            },
         },
         httpClient));
 
@@ -75,7 +74,7 @@ Console.WriteLine($"Assistant: {await agent.RunAsync(Query)}");
 // ---------------------------------------------------------------------------
 // Helper: create (or replace) a sample toolbox so the sample runs end-to-end
 // ---------------------------------------------------------------------------
-static async Task<string> CreateSampleToolboxAsync(string name, string endpoint, TokenCredential credential)
+static async Task CreateSampleToolboxAsync(string name, string endpoint, TokenCredential credential)
 {
     // Toolboxes are normally configured in the Foundry portal or a deployment
     // script, not the application itself. This helper exists so the sample can
@@ -104,13 +103,12 @@ static async Task<string> CreateSampleToolboxAsync(string name, string endpoint,
         serverUri: new Uri("https://gitmcp.io/Azure/azure-rest-api-specs"),
         toolCallApprovalPolicy: new McpToolCallApprovalPolicy(GlobalMcpToolCallApprovalPolicy.NeverRequireApproval)));
 
-    ToolboxVersion created = (await toolboxClient.CreateToolboxVersionAsync(
+    var created = (await toolboxClient.CreateToolboxVersionAsync(
         name: name,
         tools: [mcpTool],
         description: "Sample toolbox with an MCP tool — created by Agent_Step25 sample.")).Value;
 
     Console.WriteLine($"Created toolbox '{created.Name}' v{created.Version} ({created.Tools.Count} tool(s))");
-    return $"{endpoint}/toolboxes/{created.Name}/mcp?api-version=v{created.Version}";
 }
 
 // ---------------------------------------------------------------------------

dotnet/samples/02-agents/AgentsWithFoundry/Agent_Step25_FoundryToolboxMcp/README.md

@@ -19,11 +19,10 @@ Set the following environment variables:
 ```powershell
 $env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
 $env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-5.4-mini"
+$env:FOUNDRY_TOOLBOX_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project/toolsets/research_toolbox/mcp?api-version=2025-05-01-preview"
 ```
 
-The sample creates a toolbox named `research_toolbox` in your Foundry project on
-startup, then connects to its MCP endpoint at
-`{AZURE_AI_PROJECT_ENDPOINT}/toolboxes/research_toolbox/mcp?api-version=v{version}`.
+The `<name>` segment of `FOUNDRY_TOOLBOX_ENDPOINT` must match the `ToolboxName` constant in `Program.cs`.
 
 ## Run the sample
 

dotnet/samples/02-agents/Harness/Harness_Step01_Research/Harness_Step01_Research.csproj

@@ -13,7 +13,6 @@
   </ItemGroup>
 
   <ItemGroup>
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Harness\Microsoft.Agents.AI.Harness.csproj" />
     <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
     <ProjectReference Include="..\Harness_Shared_Console\Harness_Shared_Console.csproj" />
   </ItemGroup>

dotnet/samples/02-agents/Harness/Harness_Step01_Research/Program.cs

@@ -1,6 +1,6 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample demonstrates how to use a HarnessAgent with the Harness AIContextProviders
+// This sample demonstrates how to use a ChatClientAgent with the Harness AIContextProviders
 // (TodoProvider and AgentModeProvider) for interactive research tasks with web search
 // capabilities powered by Azure AI Foundry.
 // The agent plans research tasks, creates a todo list, gets user approval,
@@ -17,6 +17,7 @@ using System.ClientModel.Primitives;
 using Azure.Identity;
 using Harness.Shared.Console;
 using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Compaction;
 using Microsoft.Extensions.AI;
 using OpenAI;
 using OpenAI.Responses;
@@ -28,7 +29,7 @@ var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYME
 const int MaxContextWindowTokens = 1_050_000;
 const int MaxOutputTokens = 128_000;
 
-// Create a HarnessAgent with the Harness providers (TodoProvider and AgentModeProvider)
+// Create a ChatClientAgent with the Harness providers (TodoProvider and AgentModeProvider)
 // and research-focused instructions including the mandatory planning workflow.
 var instructions =
     """
@@ -109,9 +110,13 @@ var instructions =
     - Check for relevant previously downloaded data / findings before starting new research.
     """;
 
-// Create the agent using AsHarnessAgent, which pre-configures function invocation,
-// per-service-call chat history persistence, and in-loop compaction.
-// Then wrap with UseToolApproval to allow auto-approving tools once confirmed.
+// Create a compaction strategy based on the model's context window.
+// gpt-5.4: 1,050,000 token context window, 128,000 max output tokens.
+// Defaults: tool result eviction at 50% of input budget, truncation at 80%.
+var compactionStrategy = new ContextWindowCompactionStrategy(
+    maxContextWindowTokens: MaxContextWindowTokens,
+    maxOutputTokens: MaxOutputTokens);
+
 AIAgent agent =
     // Create an OpenAIClient that communicates with the Foundry responses service.
     new OpenAIClient(
@@ -125,32 +130,49 @@ AIAgent agent =
             RetryPolicy = new ClientRetryPolicy(3)          // Enable retries to improve resiliency.
         })
     .GetResponsesClient()
-    .AsIChatClientWithStoredOutputDisabled(deploymentName)   // We want to manage chat history locally (not stored in the responses service), so that we can manage compaction ourselves.
-    .AsHarnessAgent(MaxContextWindowTokens, MaxOutputTokens, new HarnessAgentOptions
-    {
-        Name = "ResearchAgent",
-        Description = "A research assistant that plans and executes research tasks.",
-        AIContextProviders =
-        [
-            new TodoProvider(),         // Add an AIContextProvider to allow the agent to create a TODO list, which is stored in the session.
-            new AgentModeProvider(),    // Add an AIContextProvider that tracks the agent mode and allows switching mode. Current mode is stored in the session.
-            new FileMemoryProvider(     // Add an AIContextProvider that can store memories in files under a session specific working folder.
-                new FileSystemAgentFileStore(Path.Combine(AppContext.BaseDirectory, "agent-files")),
-                (_) => new FileMemoryState() { WorkingFolder = DateTime.UtcNow.ToString("yyyyMMdd_HHmmss") + "_" + Guid.NewGuid().ToString() })
-        ],
-        ChatOptions = new ChatOptions
+    .AsIChatClientWithStoredOutputDisabled(deploymentName)  // We want to manage chat history locally (not stored in the responses service), so that we can manage compaction ourselves.
+
+    // Build a ChatClient Pipeline
+    .AsBuilder()
+    .UseFunctionInvocation()                                // We are building our own stack from scratch so we need to include Function Invocation ourselves.
+    .UseMessageInjection()                                  // Allow message injection during the function call loop.
+    .UsePerServiceCallChatHistoryPersistence()              // Save chat history updates to the session after each service call, rather than only at the end of the run.
+    .UseAIContextProviders(new CompactionProvider(compactionStrategy))  // Add Compaction before each service call to responses so that long function invocation loops don't overflow the context.
+
+    // Build our agent on top of the ChatClient Pipeline
+    .BuildAIAgent(
+        new ChatClientAgentOptions
         {
-            Instructions = instructions,
-            Tools =
+            Name = "ResearchAgent",
+            Description = "A research assistant that plans and executes research tasks.",
+            UseProvidedChatClientAsIs = true,                           // Since we built our own stack from scratch we need to tell the agent not to also add defaults like Function Invocation.
+            RequirePerServiceCallChatHistoryPersistence = true,         // Since we are added the per service call persistence ChatClient, we need to tell the agent to not also store chat history at the end of the run.
+            ChatHistoryProvider = new InMemoryChatHistoryProvider(      // Store chat history in memory in the session object. Will persist if the session is persisted.
+                new InMemoryChatHistoryProviderOptions
+                {
+                    ChatReducer = compactionStrategy.AsChatReducer(),   // Run compaction on the InMemory chat history when it gets too large.
+                }),
+            AIContextProviders =
             [
-                ResponseTool.CreateWebSearchTool().AsAITool(),          // Add the foundry hosted web search tool that runs in the service.
-                new WebBrowsingTool(                                    // Add a local web browsing tool that converts html to markdown.
-                    new WebBrowsingToolOptions { AllowPublicNetworks = true }),
+                new TodoProvider(),         // Add an AIContextProvider to allow the agent to create a TODO list, which is stored in the session.
+                new AgentModeProvider(),    // Add an AIContextProvider that tracks the agent mode and allows switching mode. Current mode is stored in the session.
+                new FileMemoryProvider(     // Add an AIContextProvider that can store memories in files under a session specific working folder.
+                    new FileSystemAgentFileStore(Path.Combine(AppContext.BaseDirectory, "agent-files")),
+                    (_) => new FileMemoryState() { WorkingFolder = DateTime.UtcNow.ToString("yyyyMMdd_HHmmss") + "_" + Guid.NewGuid().ToString() })
             ],
-            MaxOutputTokens = MaxOutputTokens,                          // Set a high token limit for long research tasks with many tool calls and long outputs.
-            Reasoning = new() { Effort = ReasoningEffort.Medium },
-        },
-    })
+            ChatOptions = new ChatOptions
+            {
+                Instructions = instructions,
+                Tools =
+                [
+                    ResponseTool.CreateWebSearchTool().AsAITool(),          // Add the foundry hosted web search tool that runs in the service.
+                    new WebBrowsingTool(                                    // Add a local web browsing tool that converts html to markdown.
+                        new WebBrowsingToolOptions { AllowPublicNetworks = true }),
+                ],
+                MaxOutputTokens = MaxOutputTokens,                          // Set a high token limit for long research tasks with many tool calls and long outputs.
+                Reasoning = new() { Effort = ReasoningEffort.Medium },
+            },
+        })
     .AsBuilder()
     .UseToolApproval()                                                      // Add the ability to auto approve tools once a user has said they don't want to be asked again. Approval rules are tied to the session.
     .Build();

dotnet/samples/02-agents/Harness/Harness_Step01_Research/README.md

@@ -1,11 +1,10 @@
 # What this sample demonstrates
 
-This sample demonstrates how to use a `HarnessAgent` with the Harness `AIContextProviders` (`TodoProvider` and `AgentModeProvider`) for interactive research tasks with web search capabilities powered by Azure AI Foundry. The `HarnessAgent` pre-configures function invocation, per-service-call chat history persistence, and context-window compaction.
+This sample demonstrates how to use a `ChatClientAgent` with the Harness `AIContextProviders` (`TodoProvider` and `AgentModeProvider`) for interactive research tasks with web search capabilities powered by Azure AI Foundry.
 
 Key features showcased:
 
-- **HarnessAgent** — a pre-configured agent that wraps a `ChatClientAgent` with function invocation, per-service-call persistence, and context-window compaction
-- **ToolApproval** — the agent is wrapped with `UseToolApproval()` to allow auto-approving tools once confirmed
+- **ChatClientAgent** — configured directly with Harness providers for planning and task management
 - **Web Search** — the agent can search the web for current information via `ResponseTool.CreateWebSearchTool()`
 - **TodoProvider** — the agent creates and manages a todo list to track research questions
 - **AgentModeProvider** — the agent switches between "plan" mode (breaking down the topic) and "execute" mode (answering each research question)

dotnet/samples/02-agents/Harness/Harness_Step02_Research_WithSubAgents/Harness_Step02_Research_WithSubAgents.csproj

@@ -13,7 +13,6 @@
   </ItemGroup>
 
   <ItemGroup>
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Harness\Microsoft.Agents.AI.Harness.csproj" />
     <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
     <ProjectReference Include="..\Harness_Shared_Console\Harness_Shared_Console.csproj" />
   </ItemGroup>

dotnet/samples/02-agents/Harness/Harness_Step02_Research_WithSubAgents/Program.cs

@@ -22,9 +22,6 @@ using OpenAI.Responses;
 var endpoint = Environment.GetEnvironmentVariable("AZURE_FOUNDRY_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_FOUNDRY_OPENAI_ENDPOINT is not set.");
 var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5.4";
 
-const int MaxContextWindowTokens = 1_050_000;
-const int MaxOutputTokens = 128_000;
-
 // --- Sub-agent: Web Search Agent ---
 // This agent can search the web and is used by the parent agent to look up stock prices.
 AIAgent webSearchAgent =
@@ -37,19 +34,20 @@ AIAgent webSearchAgent =
         })
     .GetResponsesClient()
     .AsIChatClientWithStoredOutputDisabled(deploymentName)
-    .AsHarnessAgent(MaxContextWindowTokens, MaxOutputTokens, new HarnessAgentOptions
-    {
-        Name = "WebSearchAgent",
-        Description = "An agent that can search the web to find information.",
-        ChatOptions = new ChatOptions
+    .AsAIAgent(
+        new ChatClientAgentOptions
         {
-            Instructions = "You are a web search assistant. When asked to find information, use the web search tool to look it up and return a concise, factual answer.",
-            Tools =
-            [
-                ResponseTool.CreateWebSearchTool().AsAITool(),
-            ],
-        },
-    });
+            Name = "WebSearchAgent",
+            Description = "An agent that can search the web to find information.",
+            ChatOptions = new ChatOptions
+            {
+                Instructions = "You are a web search assistant. When asked to find information, use the web search tool to look it up and return a concise, factual answer.",
+                Tools =
+                [
+                    ResponseTool.CreateWebSearchTool().AsAITool(),
+                ],
+            },
+        });
 
 // --- Parent agent: Stock Price Researcher ---
 // This agent orchestrates the sub-agent to look up stock prices in parallel.
@@ -85,20 +83,21 @@ AIAgent parentAgent =
         })
     .GetResponsesClient()
     .AsIChatClientWithStoredOutputDisabled(deploymentName)
-    .AsHarnessAgent(MaxContextWindowTokens, MaxOutputTokens, new HarnessAgentOptions
-    {
-        Name = "StockPriceResearcher",
-        Description = "An agent that researches stock prices using sub-agents.",
-        AIContextProviders =
-        [
-            new SubAgentsProvider([webSearchAgent]),
-        ],
-        ChatOptions = new ChatOptions
+    .AsAIAgent(
+        new ChatClientAgentOptions
         {
-            Instructions = parentInstructions,
-            MaxOutputTokens = 16_000,
-        },
-    });
+            Name = "StockPriceResearcher",
+            Description = "An agent that researches stock prices using sub-agents.",
+            AIContextProviders =
+            [
+                new SubAgentsProvider([webSearchAgent]),
+            ],
+            ChatOptions = new ChatOptions
+            {
+                Instructions = parentInstructions,
+                MaxOutputTokens = 16_000,
+            },
+        });
 
 // Run the interactive console session.
 await HarnessConsole.RunAgentAsync(

dotnet/samples/02-agents/Harness/Harness_Step02_Research_WithSubAgents/README.md

@@ -1,6 +1,6 @@
 # Harness Step 02 — SubAgents (Stock Price Research)
 
-This sample demonstrates how to use the **SubAgentsProvider** to delegate work from a parent agent to sub-agents. Both agents use `HarnessAgent` for pre-configured function invocation, per-service-call persistence, and context-window compaction.
+This sample demonstrates how to use the **SubAgentsProvider** to delegate work from a parent agent to sub-agents.
 
 ## What It Does
 

dotnet/samples/02-agents/Harness/Harness_Step03_DataProcessing/Harness_Step03_DataProcessing.csproj

@@ -13,7 +13,6 @@
   </ItemGroup>
 
   <ItemGroup>
-    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Harness\Microsoft.Agents.AI.Harness.csproj" />
     <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.csproj" />
     <ProjectReference Include="..\Harness_Shared_Console\Harness_Shared_Console.csproj" />
   </ItemGroup>

dotnet/samples/02-agents/Harness/Harness_Step03_DataProcessing/Program.cs

@@ -1,6 +1,6 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-// This sample demonstrates how to use a HarnessAgent with the FileAccessProvider
+// This sample demonstrates how to use a ChatClientAgent with the FileAccessProvider
 // to give an agent access to a folder of CSV data files. The agent can read, analyze,
 // and extract information from the data, then write results back as new files.
 //
@@ -17,6 +17,7 @@ using System.ClientModel.Primitives;
 using Azure.Identity;
 using Harness.Shared.Console;
 using Microsoft.Agents.AI;
+using Microsoft.Agents.AI.Compaction;
 using Microsoft.Extensions.AI;
 using OpenAI;
 using OpenAI.Responses;
@@ -56,7 +57,11 @@ var instructions =
     - Always explain what you learned and what you are going to do next between tool calls, so the user can follow along with your thought process.
     """;
 
-// Create the chat client from the OpenAI provider.
+// Create a compaction strategy based on the model's context window.
+var compactionStrategy = new ContextWindowCompactionStrategy(
+    maxContextWindowTokens: MaxContextWindowTokens,
+    maxOutputTokens: MaxOutputTokens);
+
 AIAgent agent =
     new OpenAIClient(
         new BearerTokenPolicy(new DefaultAzureCredential(), "https://ai.azure.com/.default"),
@@ -67,20 +72,36 @@ AIAgent agent =
         })
     .GetResponsesClient()
     .AsIChatClientWithStoredOutputDisabled(deploymentName)
-    .AsHarnessAgent(MaxContextWindowTokens, MaxOutputTokens, new HarnessAgentOptions
-    {
-        Name = "DataAnalyst",
-        Description = "A data analyst assistant that reads, analyzes, and processes data files.",
-        AIContextProviders =
-        [
-            new FileAccessProvider(fileStore),
-        ],
-        ChatOptions = new ChatOptions
+
+    .AsBuilder()
+    .UseFunctionInvocation()
+    .UsePerServiceCallChatHistoryPersistence()
+    .UseAIContextProviders(new CompactionProvider(compactionStrategy))
+
+    .BuildAIAgent(
+        new ChatClientAgentOptions
         {
-            Instructions = instructions,
-            MaxOutputTokens = MaxOutputTokens,
-        },
-    });
+            Name = "DataAnalyst",
+            Description = "A data analyst assistant that reads, analyzes, and processes data files.",
+            UseProvidedChatClientAsIs = true,
+            RequirePerServiceCallChatHistoryPersistence = true,
+            ChatHistoryProvider = new InMemoryChatHistoryProvider(
+                new InMemoryChatHistoryProviderOptions
+                {
+                    ChatReducer = compactionStrategy.AsChatReducer(),
+                }),
+            AIContextProviders =
+            [
+                new FileAccessProvider(fileStore),
+            ],
+            ChatOptions = new ChatOptions
+            {
+                Instructions = instructions,
+                MaxOutputTokens = MaxOutputTokens,
+            },
+        })
+    .AsBuilder()
+    .Build();
 
 // Run the interactive console session.
 await HarnessConsole.RunAgentAsync(

dotnet/samples/02-agents/Harness/Harness_Step03_DataProcessing/README.md

@@ -1,10 +1,9 @@
 # What this sample demonstrates
 
-This sample demonstrates how to use a `HarnessAgent` with the `FileAccessProvider` to give an agent access to a folder of data files for reading, analyzing, and writing results. The `HarnessAgent` pre-configures function invocation, per-service-call chat history persistence, and in-loop compaction — so the sample only needs to supply the chat client, token limits, and application-specific options.
+This sample demonstrates how to use a `ChatClientAgent` with the `FileAccessProvider` to give an agent access to a folder of data files for reading, analyzing, and writing results.
 
 Key features showcased:
 
-- **HarnessAgent** — a pre-configured agent that wraps a `ChatClientAgent` with function invocation, per-service-call persistence, and context-window compaction
 - **FileAccessProvider** — gives the agent tools to read, write, list, search, and delete files in a shared data folder
 - **CSV data processing** — the agent reads sales transaction data and performs analysis on demand
 - **Output file creation** — the agent can write summaries, filtered data, or reports back to the data folder

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

@@ -1,16 +0,0 @@
-<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

@@ -1,76 +0,0 @@
-// 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("AZURE_AI_PROJECT_ENDPOINT")
-    ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
-string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-4o-mini";
-
-// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
-// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
-// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
-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

@@ -1,37 +0,0 @@
-# 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 CLI installed and authenticated (`az login`)
-
-Set the following environment variables:
-
-```powershell
-$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
-$env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"
-```
-
-## Run the sample
-
-```powershell
-cd dotnet/samples/03-workflows/Evaluation
-dotnet run --project .\Evaluation_WorkflowExpectedOutputs
-```

dotnet/samples/05-end-to-end/AgentWebChat/AgentWebChat.AgentHost/Program.cs

@@ -163,22 +163,10 @@ app.MapA2AHttpJson(knightsKnavesAgentBuilder, path: "/a2a/knights-and-knaves");
 app.MapDevUI();
 
 app.MapOpenAIResponses();
-app.MapOpenAIResponses(pirateAgentBuilder);
-app.MapOpenAIResponses(knightsKnavesAgentBuilder);
-app.MapOpenAIResponses(chemistryAgent);
-app.MapOpenAIResponses(mathsAgent);
-app.MapOpenAIResponses(literatureAgent);
-app.MapOpenAIResponses(scienceSequentialWorkflow);
-app.MapOpenAIResponses(scienceConcurrentWorkflow);
 app.MapOpenAIConversations();
 
 app.MapOpenAIChatCompletions(pirateAgentBuilder);
 app.MapOpenAIChatCompletions(knightsKnavesAgentBuilder);
-app.MapOpenAIChatCompletions(chemistryAgent);
-app.MapOpenAIChatCompletions(mathsAgent);
-app.MapOpenAIChatCompletions(literatureAgent);
-app.MapOpenAIChatCompletions(scienceSequentialWorkflow);
-app.MapOpenAIChatCompletions(scienceConcurrentWorkflow);
 
 // Map the agents HTTP endpoints
 app.MapAgentDiscovery("/agents");

dotnet/samples/05-end-to-end/AgentWebChat/AgentWebChat.Web/OpenAIChatCompletionsAgentClient.cs

@@ -24,7 +24,7 @@ internal sealed class OpenAIChatCompletionsAgentClient(HttpClient httpClient) :
     {
         OpenAIClientOptions options = new()
         {
-            Endpoint = new Uri(httpClient.BaseAddress!, $"/{Uri.EscapeDataString(agentName)}/v1/"),
+            Endpoint = new Uri(httpClient.BaseAddress!, $"/{agentName}/v1/"),
             Transport = new HttpClientPipelineTransport(httpClient)
         };
 

dotnet/samples/05-end-to-end/AgentWebChat/AgentWebChat.Web/OpenAIResponsesAgentClient.cs

@@ -23,7 +23,7 @@ internal sealed class OpenAIResponsesAgentClient(HttpClient httpClient) : AgentC
     {
         OpenAIClientOptions options = new()
         {
-            Endpoint = new Uri(httpClient.BaseAddress!, $"/{Uri.EscapeDataString(agentName)}/v1/"),
+            Endpoint = new Uri(httpClient.BaseAddress!, "/v1/"),
             Transport = new HttpClientPipelineTransport(httpClient)
         };
 

dotnet/src/Microsoft.Agents.AI.Foundry/Evaluation/FoundryEvalConverter.cs

@@ -130,7 +130,6 @@ internal static class FoundryEvalConverter
             QueryMessages = ConvertMessages(queryMessages),
             ResponseMessages = ConvertMessages(responseMessages),
             Context = item.Context,
-            GroundTruth = item.ExpectedOutput,
             ToolDefinitions = item.Tools is { Count: > 0 }
                 ? item.Tools
                     .OfType<AIFunction>()
@@ -186,11 +185,6 @@ internal static class FoundryEvalConverter
                     dataMapping["context"] = "{{item.context}}";
                 }
 
-                if (GroundTruthEvaluators.Contains(qualified))
-                {
-                    dataMapping["ground_truth"] = "{{item.ground_truth}}";
-                }
-
                 if (ToolEvaluators.Contains(qualified))
                 {
                     dataMapping["tool_definitions"] = "{{item.tool_definitions}}";
@@ -212,7 +206,7 @@ internal static class FoundryEvalConverter
     /// <summary>
     /// Builds the <c>item_schema</c> for custom JSONL eval definitions.
     /// </summary>
-    internal static WireItemSchema BuildItemSchema(bool hasContext = false, bool hasTools = false, bool hasGroundTruth = false)
+    internal static WireItemSchema BuildItemSchema(bool hasContext = false, bool hasTools = false)
     {
         var properties = new Dictionary<string, WireSchemaProperty>
         {
@@ -227,11 +221,6 @@ internal static class FoundryEvalConverter
             properties["context"] = new WireSchemaProperty { Type = "string" };
         }
 
-        if (hasGroundTruth)
-        {
-            properties["ground_truth"] = new WireSchemaProperty { Type = "string" };
-        }
-
         if (hasTools)
         {
             properties["tool_definitions"] = new WireSchemaProperty { Type = "array" };
@@ -244,31 +233,6 @@ internal static class FoundryEvalConverter
         };
     }
 
-    /// <summary>
-    /// Returns the subset of <paramref name="evaluators"/> that require a ground-truth
-    /// (reference) value but cannot be evaluated because no item provided one.
-    /// </summary>
-    internal static List<string> FindMissingGroundTruthEvaluators(
-        IEnumerable<string> evaluators,
-        bool hasGroundTruth)
-    {
-        if (hasGroundTruth)
-        {
-            return [];
-        }
-
-        var missing = new List<string>();
-        foreach (var name in evaluators)
-        {
-            if (GroundTruthEvaluators.Contains(ResolveEvaluator(name)))
-            {
-                missing.Add(name);
-            }
-        }
-
-        return missing;
-    }
-
     /// <summary>
     /// Resolves a short evaluator name to its fully-qualified <c>builtin.*</c> form.
     /// </summary>
@@ -313,12 +277,6 @@ internal static class FoundryEvalConverter
         "builtin.tool_call_success",
     };
 
-    // Evaluators that require a ground_truth (reference) value per item.
-    internal static readonly HashSet<string> GroundTruthEvaluators = new(StringComparer.OrdinalIgnoreCase)
-    {
-        "builtin.similarity",
-    };
-
     // Short name → fully-qualified name mapping.
     internal static readonly Dictionary<string, string> BuiltinEvaluators = new(StringComparer.OrdinalIgnoreCase)
     {

dotnet/src/Microsoft.Agents.AI.Foundry/Evaluation/FoundryEvalWireModels.cs

@@ -103,9 +103,6 @@ internal sealed class WireEvalItemPayload
     [JsonPropertyName("context")]
     public string? Context { get; init; }
 
-    [JsonPropertyName("ground_truth")]
-    public string? GroundTruth { get; init; }
-
     [JsonPropertyName("tool_definitions")]
     public List<WireToolDefinition>? ToolDefinitions { get; init; }
 }

dotnet/src/Microsoft.Agents.AI.Foundry/Evaluation/FoundryEvals.cs

@@ -145,8 +145,6 @@ public sealed class FoundryEvals : IAgentEvaluator
 
         bool hasContext = payloads.Any(p => p.Context is not null);
         bool hasTools = payloads.Any(p => p.ToolDefinitions is { Count: > 0 });
-        bool hasGroundTruth = payloads.Any(p => p.GroundTruth is not null);
-        bool allHaveGroundTruth = payloads.Count > 0 && payloads.All(p => p.GroundTruth is not null);
 
         // Filter out tool evaluators if no items have tools; auto-add ToolCallAccuracy if tools present
         var evaluators = FilterToolEvaluators(this._evaluatorNames, hasTools);
@@ -155,27 +153,13 @@ public sealed class FoundryEvals : IAgentEvaluator
             evaluators = [.. evaluators, ToolCallAccuracy];
         }
 
-        // Fail fast if a ground-truth evaluator (e.g. similarity) is requested but not
-        // every item carries an ExpectedOutput. Reference-based evaluators score each
-        // item against its own ground truth, so even one missing value will surface as
-        // a provider-side validation error. Catch it here with a clearer message.
-        var missingGroundTruth = FoundryEvalConverter.FindMissingGroundTruthEvaluators(evaluators, allHaveGroundTruth);
-        if (missingGroundTruth.Count > 0)
-        {
-            throw new InvalidOperationException(
-                "The following evaluator(s) require a ground-truth/expected output on every item but " +
-                $"at least one item is missing an {nameof(EvalItem.ExpectedOutput)}: {string.Join(", ", missingGroundTruth)}. " +
-                "Provide an expected output per item (for example via the 'expectedOutput' parameter on EvaluateAsync), " +
-                "or set 'includePerAgent: false' so the evaluator only runs on the overall item.");
-        }
-
         // 2. Create the evaluation definition
         var createEvalPayload = new WireCreateEvalRequest
         {
             Name = evalName,
             DataSourceConfig = new WireCustomDataSourceConfig
             {
-                ItemSchema = FoundryEvalConverter.BuildItemSchema(hasContext, hasTools, hasGroundTruth),
+                ItemSchema = FoundryEvalConverter.BuildItemSchema(hasContext, hasTools),
             },
             TestingCriteria = FoundryEvalConverter.BuildTestingCriteria(
                 evaluators, this._model, includeDataMapping: true),
@@ -838,15 +822,15 @@ public sealed class FoundryEvals : IAgentEvaluator
         var result = new EvalItemResult(itemId, status, scores);
 
         // Extract error info from sample
-        if (outputItem.TryGetProperty("sample", out var sample) && sample.ValueKind == JsonValueKind.Object)
+        if (outputItem.TryGetProperty("sample", out var sample))
         {
-            if (sample.TryGetProperty("error", out var errObj) && errObj.ValueKind == JsonValueKind.Object)
+            if (sample.TryGetProperty("error", out var errObj))
             {
                 result.ErrorCode = errObj.TryGetProperty("code", out var code) ? code.GetString() : null;
                 result.ErrorMessage = errObj.TryGetProperty("message", out var msg) ? msg.GetString() : null;
             }
 
-            if (sample.TryGetProperty("usage", out var usage) && usage.ValueKind == JsonValueKind.Object && usage.TryGetProperty("total_tokens", out var tt) && tt.ValueKind == JsonValueKind.Number)
+            if (sample.TryGetProperty("usage", out var usage) && usage.TryGetProperty("total_tokens", out var tt) && tt.ValueKind == JsonValueKind.Number)
             {
                 var tokenUsage = new Dictionary<string, int>();
                 if (usage.TryGetProperty("prompt_tokens", out var pt) && pt.ValueKind == JsonValueKind.Number)
@@ -902,7 +886,7 @@ public sealed class FoundryEvals : IAgentEvaluator
         }
 
         // Extract response_id from datasource_item
-        if (outputItem.TryGetProperty("datasource_item", out var dsItem) && dsItem.ValueKind == JsonValueKind.Object)
+        if (outputItem.TryGetProperty("datasource_item", out var dsItem))
         {
             if (dsItem.TryGetProperty("resp_id", out var respId))
             {

dotnet/src/Microsoft.Agents.AI.Harness/ChatClientHarnessExtensions.cs

@@ -1,42 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Diagnostics.CodeAnalysis;
-using Microsoft.Agents.AI;
-using Microsoft.Shared.DiagnosticIds;
-
-namespace Microsoft.Extensions.AI;
-
-/// <summary>
-/// Provides extension methods for creating a <see cref="HarnessAgent"/> from an <see cref="IChatClient"/>.
-/// </summary>
-[Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-public static class ChatClientHarnessExtensions
-{
-    /// <summary>
-    /// Creates a new <see cref="HarnessAgent"/> that wraps this <see cref="IChatClient"/> with a pre-configured
-    /// pipeline including function invocation, per-service-call chat history persistence, and in-loop compaction.
-    /// </summary>
-    /// <param name="chatClient">
-    /// The <see cref="IChatClient"/> that provides access to the underlying AI model.
-    /// </param>
-    /// <param name="maxContextWindowTokens">
-    /// The maximum number of tokens the model's context window supports (e.g., 1,050,000 for gpt-5.4).
-    /// Used to configure the compaction strategy.
-    /// </param>
-    /// <param name="maxOutputTokens">
-    /// The maximum number of output tokens the model can generate per response (e.g., 128,000 for gpt-5.4).
-    /// Used to configure the compaction strategy.
-    /// </param>
-    /// <param name="options">
-    /// Optional configuration options for the agent, including instructions override, tools,
-    /// additional context providers, and chat history provider.
-    /// When <see langword="null"/>, the agent uses built-in default settings.
-    /// </param>
-    /// <returns>A new <see cref="HarnessAgent"/> instance.</returns>
-    public static HarnessAgent AsHarnessAgent(
-        this IChatClient chatClient,
-        int maxContextWindowTokens,
-        int maxOutputTokens,
-        HarnessAgentOptions? options = null) =>
-        new(chatClient, maxContextWindowTokens, maxOutputTokens, options);
-}

dotnet/src/Microsoft.Agents.AI.Harness/HarnessAgent.cs

@@ -1,135 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Diagnostics.CodeAnalysis;
-using Microsoft.Agents.AI.Compaction;
-using Microsoft.Extensions.AI;
-using Microsoft.Shared.DiagnosticIds;
-using Microsoft.Shared.Diagnostics;
-
-namespace Microsoft.Agents.AI;
-
-/// <summary>
-/// A pre-configured <see cref="DelegatingAIAgent"/> that wraps a <see cref="ChatClientAgent"/> with
-/// function invocation, per-service-call chat history persistence, and in-loop compaction.
-/// </summary>
-/// <remarks>
-/// <para>
-/// <see cref="HarnessAgent"/> assembles the following pipeline from a caller-supplied <see cref="IChatClient"/>:
-/// <list type="number">
-/// <item><description><see cref="FunctionInvokingChatClient"/> — automatic function/tool invocation.</description></item>
-/// <item><description><see cref="PerServiceCallChatHistoryPersistingChatClient"/> — persists chat history after every individual service call within a function-invocation loop.</description></item>
-/// <item><description><see cref="AIContextProviderChatClient"/> with a <see cref="CompactionProvider"/> — applies context-window compaction before each call so long function-invocation loops do not overflow the context window.</description></item>
-/// </list>
-/// </para>
-/// <para>
-/// The underlying <see cref="ChatClientAgent"/> is configured with
-/// <see cref="ChatClientAgentOptions.UseProvidedChatClientAsIs"/> and
-/// <see cref="ChatClientAgentOptions.RequirePerServiceCallChatHistoryPersistence"/> set to <see langword="true"/>
-/// to match the manually-assembled pipeline.
-/// </para>
-/// <para>
-/// When no <see cref="HarnessAgentOptions.ChatHistoryProvider"/> is supplied, the agent defaults to an
-/// <see cref="InMemoryChatHistoryProvider"/> whose chat reducer applies the same compaction strategy,
-/// keeping in-memory history from growing unboundedly across sessions.
-/// </para>
-/// </remarks>
-[Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-public sealed class HarnessAgent : DelegatingAIAgent
-{
-    /// <summary>
-    /// The built-in default system instructions used when <see cref="ChatOptions.Instructions"/> is not set.
-    /// </summary>
-    public const string DefaultInstructions =
-        """
-        You are a helpful AI assistant that uses tools to complete tasks.
-
-        ## General guidelines
-
-        - Think through the task before acting. Break complex work into clear steps.
-        - Use the tools available to you to gather information, perform actions, and verify results.
-        - Explain your reasoning between tool calls so the user can follow your progress.
-        - If a tool call fails or returns unexpected results, adapt your approach rather than repeating the same call.
-        - When you have completed the task, present a clear and concise summary of what you did and what you found.
-        """;
-
-    /// <summary>
-    /// Initializes a new instance of the <see cref="HarnessAgent"/> class.
-    /// </summary>
-    /// <param name="chatClient">
-    /// The <see cref="IChatClient"/> that provides access to the underlying AI model.
-    /// The agent wraps this client in a function-invocation, per-service-call persistence,
-    /// and compaction pipeline automatically.
-    /// </param>
-    /// <param name="maxContextWindowTokens">
-    /// The maximum number of tokens the model's context window supports (e.g., 1,050,000 for gpt-5.4).
-    /// Used to configure the compaction strategy.
-    /// </param>
-    /// <param name="maxOutputTokens">
-    /// The maximum number of output tokens the model can generate per response (e.g., 128,000 for gpt-5.4).
-    /// Used to configure the compaction strategy and to limit the model's output.
-    /// </param>
-    /// <param name="options">
-    /// Optional configuration options for the agent, including instructions override, tools,
-    /// additional context providers, and chat history provider.
-    /// When <see langword="null"/>, the agent uses built-in default settings.
-    /// </param>
-    /// <exception cref="System.ArgumentNullException">
-    /// <paramref name="chatClient"/> is <see langword="null"/>.
-    /// </exception>
-    /// <exception cref="System.ArgumentOutOfRangeException">
-    /// <paramref name="maxContextWindowTokens"/> is not positive, or
-    /// <paramref name="maxOutputTokens"/> is negative or greater than or equal to <paramref name="maxContextWindowTokens"/>.
-    /// </exception>
-    public HarnessAgent(IChatClient chatClient, int maxContextWindowTokens, int maxOutputTokens, HarnessAgentOptions? options = null)
-        : base(BuildInnerAgent(
-            Throw.IfNull(chatClient),
-            maxContextWindowTokens,
-            maxOutputTokens,
-            options))
-    {
-    }
-
-    private static ChatClientAgent BuildInnerAgent(IChatClient chatClient, int maxContextWindowTokens, int maxOutputTokens, HarnessAgentOptions? options)
-    {
-        var compactionStrategy = new ContextWindowCompactionStrategy(
-            maxContextWindowTokens: maxContextWindowTokens,
-            maxOutputTokens: maxOutputTokens);
-
-        ChatHistoryProvider chatHistoryProvider = options?.ChatHistoryProvider
-            ?? new InMemoryChatHistoryProvider(new InMemoryChatHistoryProviderOptions
-            {
-                ChatReducer = compactionStrategy.AsChatReducer(),
-            });
-
-        string instructions = options?.ChatOptions?.Instructions ?? DefaultInstructions;
-
-        ChatOptions chatOptions = BuildChatOptions(options?.ChatOptions, instructions, maxOutputTokens);
-
-        var compactionProvider = new CompactionProvider(compactionStrategy);
-
-        return chatClient
-            .AsBuilder()
-            .UseFunctionInvocation()
-            .UsePerServiceCallChatHistoryPersistence()
-            .UseAIContextProviders(compactionProvider)
-            .BuildAIAgent(new ChatClientAgentOptions
-            {
-                Id = options?.Id,
-                Name = options?.Name,
-                Description = options?.Description,
-                ChatOptions = chatOptions,
-                ChatHistoryProvider = chatHistoryProvider,
-                AIContextProviders = options?.AIContextProviders,
-                UseProvidedChatClientAsIs = true,
-                RequirePerServiceCallChatHistoryPersistence = true,
-            });
-    }
-
-    private static ChatOptions BuildChatOptions(ChatOptions? source, string instructions, int maxOutputTokens)
-    {
-        ChatOptions result = source?.Clone() ?? new ChatOptions();
-        result.Instructions = instructions;
-        result.MaxOutputTokens ??= maxOutputTokens;
-        return result;
-    }
-}

dotnet/src/Microsoft.Agents.AI.Harness/HarnessAgentOptions.cs

@@ -1,64 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Collections.Generic;
-using System.Diagnostics.CodeAnalysis;
-using Microsoft.Extensions.AI;
-using Microsoft.Shared.DiagnosticIds;
-
-namespace Microsoft.Agents.AI;
-
-/// <summary>
-/// Represents configuration options for a <see cref="HarnessAgent"/>.
-/// </summary>
-[Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-public sealed class HarnessAgentOptions
-{
-    /// <summary>
-    /// Gets or sets the agent id.
-    /// </summary>
-    public string? Id { get; set; }
-
-    /// <summary>
-    /// Gets or sets the agent name.
-    /// </summary>
-    public string? Name { get; set; }
-
-    /// <summary>
-    /// Gets or sets the agent description.
-    /// </summary>
-    public string? Description { get; set; }
-
-    /// <summary>
-    /// Gets or sets additional chat options such as tools for the agent to use.
-    /// </summary>
-    /// <remarks>
-    /// <para>
-    /// Use <see cref="ChatOptions.Tools"/> to supply additional tools the agent can invoke.
-    /// </para>
-    /// <para>
-    /// Use <see cref="ChatOptions.Instructions"/> to override the <see cref="HarnessAgent"/>'s built-in
-    /// default instructions. When <see cref="ChatOptions.Instructions"/> is <see langword="null"/> or not set,
-    /// the default instructions are used.
-    /// </para>
-    /// </remarks>
-    public ChatOptions? ChatOptions { get; set; }
-
-    /// <summary>
-    /// Gets or sets the <see cref="ChatHistoryProvider"/> to use for storing chat history.
-    /// </summary>
-    /// <remarks>
-    /// When <see langword="null"/>, the agent defaults to an <see cref="InMemoryChatHistoryProvider"/>
-    /// configured with a compaction-based chat reducer derived from the <c>maxContextWindowTokens</c>
-    /// and <c>maxOutputTokens</c> constructor parameters of <see cref="HarnessAgent"/>.
-    /// </remarks>
-    public ChatHistoryProvider? ChatHistoryProvider { get; set; }
-
-    /// <summary>
-    /// Gets or sets additional <see cref="AIContextProvider"/> instances to include in the agent pipeline.
-    /// </summary>
-    /// <remarks>
-    /// These providers are passed to the underlying <see cref="ChatClientAgent"/> via
-    /// <see cref="ChatClientAgentOptions.AIContextProviders"/>.
-    /// </remarks>
-    public IEnumerable<AIContextProvider>? AIContextProviders { get; set; }
-}

dotnet/src/Microsoft.Agents.AI.Harness/Microsoft.Agents.AI.Harness.csproj

@@ -1,28 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <IsReleaseCandidate>false</IsReleaseCandidate>
-    <InjectSharedThrow>true</InjectSharedThrow>
-    <InjectSharedDiagnosticIds>true</InjectSharedDiagnosticIds>
-    <InjectExperimentalAttributeOnLegacy>true</InjectExperimentalAttributeOnLegacy>
-    <InjectIsExternalInitOnLegacy>true</InjectIsExternalInitOnLegacy>
-    <InjectTrimAttributesOnLegacy>true</InjectTrimAttributesOnLegacy>
-  </PropertyGroup>
-
-  <Import Project="$(RepoRoot)/dotnet/nuget/nuget-package.props" />
-
-  <ItemGroup>
-    <ProjectReference Include="..\Microsoft.Agents.AI\Microsoft.Agents.AI.csproj" />
-  </ItemGroup>
-
-  <PropertyGroup>
-    <!-- NuGet Package Settings -->
-    <Title>Microsoft Agent Framework Harness</Title>
-    <Description>Provides the HarnessAgent, a pre-configured AI agent that can be used for long running tasks.</Description>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <InternalsVisibleTo Include="Microsoft.Agents.AI.Harness.UnitTests" />
-  </ItemGroup>
-
-</Project>

dotnet/src/Microsoft.Agents.AI.Workflows/AIAgentsAbstractionsExtensions.cs

@@ -32,8 +32,38 @@ internal static class AIAgentsAbstractionsExtensions
         return message;
     }
 
-    public static List<ChatMessage> CopyWithAssistantToUserForOtherParticipants(
-        this IEnumerable<ChatMessage> messages,
-        string targetAgentName)
-        => messages.Select(m => m.ChatAssistantToUserIfNotFromNamed(targetAgentName, out _, false)).ToList();
+    /// <summary>
+    /// Iterates through <paramref name="messages"/> looking for <see cref="ChatRole.Assistant"/> messages and swapping
+    /// any that have a different <see cref="ChatMessage.AuthorName"/> from <paramref name="targetAgentName"/> to
+    /// <see cref="ChatRole.User"/>.
+    /// </summary>
+    public static List<ChatMessage>? ChangeAssistantToUserForOtherParticipants(this IEnumerable<ChatMessage> messages, string targetAgentName)
+    {
+        List<ChatMessage>? roleChanged = null;
+        foreach (var m in messages)
+        {
+            m.ChatAssistantToUserIfNotFromNamed(targetAgentName, out bool changed);
+            if (changed)
+            {
+                (roleChanged ??= []).Add(m);
+            }
+        }
+
+        return roleChanged;
+    }
+
+    /// <summary>
+    /// Undoes changes made by <see cref="ChangeAssistantToUserForOtherParticipants"/> when passed the list of changes
+    /// made by that method.
+    /// </summary>
+    public static void ResetUserToAssistantForChangedRoles(this List<ChatMessage>? roleChanged)
+    {
+        if (roleChanged is not null)
+        {
+            foreach (var m in roleChanged)
+            {
+                m.Role = ChatRole.Assistant;
+            }
+        }
+    }
 }

dotnet/src/Microsoft.Agents.AI.Workflows/Evaluation/WorkflowEvaluationExtensions.cs

@@ -28,17 +28,6 @@ public static class WorkflowEvaluationExtensions
     /// Use <see cref="ConversationSplitters.LastTurn"/>, <see cref="ConversationSplitters.Full"/>,
     /// or a custom <see cref="IConversationSplitter"/> implementation.
     /// </param>
-    /// <param name="expectedOutput">
-    /// Optional ground-truth/expected output for the workflow's overall final answer.
-    /// When provided, it is stamped onto the overall <see cref="EvalItem.ExpectedOutput"/>
-    /// so reference-based evaluators (for example, similarity) can compare the
-    /// workflow's response against a golden answer. Ground truth is only applied
-    /// to the overall item; per-agent items are intentionally left without an
-    /// expected output, since ground truth is defined against the final response.
-    /// When using a reference-based evaluator that requires ground truth, set
-    /// <paramref name="includePerAgent"/> to <see langword="false"/> to avoid
-    /// invoking the evaluator on per-agent items that have no expected output.
-    /// </param>
     /// <param name="cancellationToken">Cancellation token.</param>
     /// <returns>Evaluation results with optional per-agent sub-results.</returns>
     public static async Task<AgentEvaluationResults> EvaluateAsync(
@@ -48,7 +37,6 @@ public static class WorkflowEvaluationExtensions
         bool includePerAgent = true,
         string evalName = "Workflow Eval",
         IConversationSplitter? splitter = null,
-        string? expectedOutput = null,
         CancellationToken cancellationToken = default)
     {
         var events = run.OutgoingEvents.ToList();
@@ -60,26 +48,28 @@ public static class WorkflowEvaluationExtensions
         var overallItems = new List<EvalItem>();
         if (includeOverall)
         {
-            var overallItem = BuildOverallItem(events, splitter, expectedOutput);
-            if (overallItem is not null)
+            var finalResponse = events.OfType<AgentResponseEvent>().LastOrDefault();
+            if (finalResponse is not null)
             {
-                overallItems.Add(overallItem);
-            }
-            else
-            {
-                // The caller asked for an overall evaluation but we couldn't find a final
-                // response to score — almost always because the workflow's agents weren't
-                // built with EmitAgentResponseEvents enabled (so no AgentResponseEvent was
-                // emitted) and no terminal ExecutorCompletedEvent carried an AgentResponse
-                // / ChatMessage / string payload. Fail loudly instead of silently returning
-                // 0/0 (or skipping evaluation against a supplied expectedOutput).
-                throw new InvalidOperationException(
-                    "Cannot evaluate the overall workflow output: no AgentResponseEvent or " +
-                    "ExecutorCompletedEvent with an AgentResponse/ChatMessage/string payload " +
-                    "was found in the run. Bind agents with " +
-                    "AIAgentHostOptions { EmitAgentResponseEvents = true } " +
-                    "(for example via agent.BindAsExecutor(new AIAgentHostOptions { EmitAgentResponseEvents = true })) " +
-                    "so the workflow surfaces the final agent response, or set 'includeOverall: false'.");
+                var firstInvoked = events.OfType<ExecutorInvokedEvent>().FirstOrDefault();
+                var query = firstInvoked?.Data switch
+                {
+                    ChatMessage cm => cm.Text ?? string.Empty,
+                    IReadOnlyList<ChatMessage> msgs => msgs.LastOrDefault(m => m.Role == ChatRole.User)?.Text ?? string.Empty,
+                    string s => s,
+                    _ => firstInvoked?.Data?.ToString() ?? string.Empty,
+                };
+                var conversation = new List<ChatMessage>
+                {
+                    new(ChatRole.User, query),
+                };
+
+                conversation.AddRange(finalResponse.Response.Messages);
+
+                overallItems.Add(new EvalItem(query, finalResponse.Response.Text, conversation)
+                {
+                    Splitter = splitter,
+                });
             }
         }
 
@@ -107,86 +97,6 @@ public static class WorkflowEvaluationExtensions
         return overallResult;
     }
 
-    internal static EvalItem? BuildOverallItem(
-        IReadOnlyList<WorkflowEvent> events,
-        IConversationSplitter? splitter,
-        string? expectedOutput)
-    {
-        var firstInvoked = events.OfType<ExecutorInvokedEvent>().FirstOrDefault();
-        var query = firstInvoked?.Data switch
-        {
-            ChatMessage cm => cm.Text ?? string.Empty,
-            IReadOnlyList<ChatMessage> msgs => msgs.LastOrDefault(m => m.Role == ChatRole.User)?.Text ?? string.Empty,
-            string s => s,
-            _ => firstInvoked?.Data?.ToString() ?? string.Empty,
-        };
-
-        var conversation = new List<ChatMessage>
-        {
-            new(ChatRole.User, query),
-        };
-
-        // Prefer AgentResponseEvent (only emitted when AIAgentHostOptions.EmitAgentResponseEvents
-        // is enabled). Otherwise fall back to the last ExecutorCompletedEvent that carries an
-        // AgentResponse / ChatMessage / string payload — these are always emitted by the runtime.
-        var finalResponse = events.OfType<AgentResponseEvent>().LastOrDefault();
-        string responseText;
-        if (finalResponse is not null)
-        {
-            responseText = finalResponse.Response.Text;
-            conversation.AddRange(finalResponse.Response.Messages);
-        }
-        else
-        {
-            ExecutorCompletedEvent? finalCompleted = null;
-            for (int i = events.Count - 1; i >= 0; i--)
-            {
-                if (events[i] is ExecutorCompletedEvent completed
-                    && !IsInternalExecutor(completed.ExecutorId)
-                    && completed.Data is AgentResponse or ChatMessage or string)
-                {
-                    finalCompleted = completed;
-                    break;
-                }
-            }
-
-            if (finalCompleted is null)
-            {
-                return null;
-            }
-
-            switch (finalCompleted.Data)
-            {
-                case AgentResponse ar:
-                    responseText = ar.Text;
-                    conversation.AddRange(ar.Messages);
-                    break;
-                case ChatMessage cm:
-                    responseText = cm.Text ?? string.Empty;
-                    conversation.Add(cm);
-                    break;
-                case string s:
-                    responseText = s;
-                    conversation.Add(new ChatMessage(ChatRole.Assistant, s));
-                    break;
-                default:
-                    // Unreachable — the for-loop above already constrains Data to one of the
-                    // three handled types. Throw if the contract drifts so the bug is visible
-                    // instead of silently dropping the overall item.
-                    throw new InvalidOperationException(
-                        "BuildOverallItem: unexpected ExecutorCompletedEvent.Data type " +
-                        $"'{finalCompleted.Data?.GetType().FullName ?? "null"}'. Expected " +
-                        $"{nameof(AgentResponse)}, {nameof(ChatMessage)}, or string.");
-            }
-        }
-
-        return new EvalItem(query, responseText, conversation)
-        {
-            Splitter = splitter,
-            ExpectedOutput = expectedOutput,
-        };
-    }
-
     internal static Dictionary<string, List<EvalItem>> ExtractAgentData(
         List<WorkflowEvent> events,
         IConversationSplitter? splitter)

dotnet/src/Microsoft.Agents.AI.Workflows/MessageMerger.cs

@@ -97,6 +97,28 @@ internal sealed class MessageMerger
         }
     }
 
+    private int CompareByDateTimeOffset(AgentResponse left, AgentResponse right)
+    {
+        const int LESS = -1, EQ = 0, GREATER = 1;
+
+        if (left.CreatedAt == right.CreatedAt)
+        {
+            return EQ;
+        }
+
+        if (!left.CreatedAt.HasValue)
+        {
+            return GREATER;
+        }
+
+        if (!right.CreatedAt.HasValue)
+        {
+            return LESS;
+        }
+
+        return left.CreatedAt.Value.CompareTo(right.CreatedAt.Value);
+    }
+
     public AgentResponse ComputeMerged(string primaryResponseId, string? primaryAgentId = null, string? primaryAgentName = null)
     {
         List<ChatMessage> messages = [];
@@ -104,15 +126,6 @@ internal sealed class MessageMerger
         HashSet<string> agentIds = [];
         HashSet<ChatFinishReason> finishReasons = [];
 
-        // Ordering contract (see docs/decisions/0026-message-merger-invariants.md):
-        // - Outer loop iterates ResponseIds in first-seen order, which preserves step
-        //   ordering: each agent invocation owns its own ResponseId, and successive
-        //   super-steps emit their first update only after the prior step's updates
-        //   have all arrived. Iterating Dictionary<,>.Keys preserves insertion order.
-        // - Inner loop iterates MessageIds in first-seen order, then appends dangling
-        //   updates last. This preserves emission order within an agent's block.
-        // We deliberately do NOT sort by CreatedAt: timestamps from concurrent agents
-        // or different clocks would interleave per-agent blocks and break Goal 1.
         foreach (string responseId in this._mergeStates.Keys)
         {
             ResponseMergeState mergeState = this._mergeStates[responseId];
@@ -123,12 +136,14 @@ internal sealed class MessageMerger
                 responseList.Add(mergeState.ComputeDangling());
             }
 
+            responseList.Sort(this.CompareByDateTimeOffset);
             responses[responseId] = responseList.Aggregate(MergeResponses);
             messages.AddRange(GetMessagesWithCreatedAt(responses[responseId]));
         }
 
         UsageDetails? usage = null;
         AdditionalPropertiesDictionary? additionalProperties = null;
+        HashSet<DateTimeOffset> createdTimes = [];
 
         foreach (AgentResponse response in responses.Values)
         {
@@ -137,6 +152,11 @@ internal sealed class MessageMerger
                 agentIds.Add(response.AgentId);
             }
 
+            if (response.CreatedAt.HasValue)
+            {
+                createdTimes.Add(response.CreatedAt.Value);
+            }
+
             if (response.FinishReason.HasValue)
             {
                 finishReasons.Add(response.FinishReason.Value);

dotnet/src/Microsoft.Agents.AI.Workflows/Specialized/HandoffAgentExecutor.cs

@@ -235,10 +235,11 @@ internal sealed class HandoffAgentExecutor :
         // This will not filter out tool responses and approval responses that are part of this agent's turn, which is
         // the expected behavior since those are part of the agent's reasoning process.
         HandoffMessagesFilter handoffMessagesFilter = new(this._options.ToolCallFilteringBehavior);
-        List<ChatMessage> messagesForAgent = (state.IncomingState.RequestedHandoffTargetAgentId is not null
+        IEnumerable<ChatMessage> messagesForAgent = state.IncomingState.RequestedHandoffTargetAgentId is not null
                                                   ? handoffMessagesFilter.FilterMessages(incomingMessages)
-                                                  : incomingMessages)
-                                             .CopyWithAssistantToUserForOtherParticipants(this._agent.Name ?? this._agent.Id);
+                                                  : incomingMessages;
+
+        List<ChatMessage>? roleChanges = messagesForAgent.ChangeAssistantToUserForOtherParticipants(this._agent.Name ?? this._agent.Id);
 
         bool emitUpdateEvents = state.IncomingState!.ShouldEmitStreamingEvents(this._options.EmitAgentResponseUpdateEvents);
         AgentInvocationResult result = await this.InvokeAgentAsync(messagesForAgent, context, emitUpdateEvents, cancellationToken)
@@ -249,6 +250,8 @@ internal sealed class HandoffAgentExecutor :
             throw new InvalidOperationException("Cannot request a handoff while holding pending requests.");
         }
 
+        roleChanges.ResetUserToAssistantForChangedRoles();
+
         int newConversationBookmark = state.ConversationBookmark;
         await this._sharedStateRef.InvokeWithStateAsync(
             (sharedState, ctx, ct) =>
@@ -433,18 +436,6 @@ internal sealed class HandoffAgentExecutor :
             FunctionCallContent handoffRequest = candidateRequests[candidateRequests.Count - 1];
             requestedHandoff = handoffRequest.Name;
 
-            // Stamp the synthetic "Transferred." tool-result update with the same
-            // ResponseId as the agent's preceding updates so it groups with the
-            // rest of this agent's step in MessageMerger (and therefore in
-            // RunAsync's merged AgentResponse and in chat history). Without this,
-            // the synthetic update goes to MessageMerger's null-ResponseId
-            // "dangling" bucket and surfaces after every keyed response, which
-            // re-orders multi-step handoff transcripts versus streaming output
-            // (issue #4544).
-            string? syntheticResponseId = updates
-                .Select(u => u.ResponseId)
-                .LastOrDefault(id => id is not null);
-
             await AddUpdateAsync(
                     new AgentResponseUpdate
                     {
@@ -453,7 +444,6 @@ internal sealed class HandoffAgentExecutor :
                         Contents = [CreateHandoffResult(handoffRequest.CallId)],
                         CreatedAt = DateTimeOffset.UtcNow,
                         MessageId = Guid.NewGuid().ToString("N"),
-                        ResponseId = syntheticResponseId,
                         Role = ChatRole.Tool,
                     },
                     cancellationToken

dotnet/src/Microsoft.Agents.AI/OpenTelemetryAgent.cs

@@ -3,12 +3,10 @@
 using System;
 using System.Collections.Generic;
 using System.Diagnostics;
-using System.Diagnostics.CodeAnalysis;
 using System.Runtime.CompilerServices;
 using System.Threading;
 using System.Threading.Tasks;
 using Microsoft.Extensions.AI;
-using Microsoft.Shared.DiagnosticIds;
 
 namespace Microsoft.Agents.AI;
 
@@ -34,13 +32,6 @@ public sealed class OpenTelemetryAgent : DelegatingAIAgent, IDisposable
     private readonly OpenTelemetryChatClient _otelClient;
     /// <summary>The provider name extracted from <see cref="AIAgentMetadata"/>.</summary>
     private readonly string? _providerName;
-    /// <summary>The resolved source name for telemetry. Always non-empty; defaults to <see cref="OpenTelemetryConsts.DefaultSourceName"/>.</summary>
-    private readonly string _sourceName;
-    /// <summary>
-    /// Indicates whether the underlying <see cref="IChatClient"/> of a <see cref="ChatClientAgent"/> inner agent
-    /// should be automatically wrapped with <see cref="OpenTelemetryChatClient"/> on each invocation.
-    /// </summary>
-    private readonly bool _autoWireChatClient;
 
     /// <summary>Initializes a new instance of the <see cref="OpenTelemetryAgent"/> class.</summary>
     /// <param name="innerAgent">The underlying <see cref="AIAgent"/> to be augmented with telemetry capabilities.</param>
@@ -53,44 +44,13 @@ public sealed class OpenTelemetryAgent : DelegatingAIAgent, IDisposable
     /// The constructor automatically extracts provider metadata from the inner agent and configures
     /// telemetry collection according to OpenTelemetry semantic conventions for AI systems.
     /// </remarks>
-    public OpenTelemetryAgent(AIAgent innerAgent, string? sourceName = null)
-#pragma warning disable MAAI001 // Auto-wiring is the new default; the experimental opt-out lives on the 3-arg overload.
-        : this(innerAgent, sourceName, autoWireChatClient: true)
-#pragma warning restore MAAI001
-    {
-    }
-
-    /// <summary>Initializes a new instance of the <see cref="OpenTelemetryAgent"/> class.</summary>
-    /// <param name="innerAgent">The underlying <see cref="AIAgent"/> to be augmented with telemetry capabilities.</param>
-    /// <param name="sourceName">
-    /// An optional source name that will be used to identify telemetry data from this agent.
-    /// If not provided, a default source name will be used for telemetry identification.
-    /// </param>
-    /// <param name="autoWireChatClient">
-    /// When <see langword="true"/> and the inner agent is a <see cref="ChatClientAgent"/>, the underlying
-    /// <see cref="IChatClient"/> is automatically wrapped with <see cref="OpenTelemetryChatClient"/> for each invocation
-    /// so that chat-level telemetry flows alongside agent-level telemetry. If the underlying chat client is already
-    /// instrumented, no additional wrapping is applied. Set to <see langword="false"/> to opt-out of this behavior.
-    /// </param>
-    /// <exception cref="ArgumentNullException"><paramref name="innerAgent"/> is <see langword="null"/>.</exception>
-    /// <remarks>
-    /// The constructor automatically extracts provider metadata from the inner agent and configures
-    /// telemetry collection according to OpenTelemetry semantic conventions for AI systems.
-    /// </remarks>
-    [Experimental(DiagnosticIds.Experiments.AgentsAIExperiments)]
-    public OpenTelemetryAgent(AIAgent innerAgent, string? sourceName, bool autoWireChatClient) : base(innerAgent)
+    public OpenTelemetryAgent(AIAgent innerAgent, string? sourceName = null) : base(innerAgent)
     {
         this._providerName = innerAgent.GetService<AIAgentMetadata>()?.ProviderName;
 
-        // Resolve once so the outer OpenTelemetryChatClient and the auto-wired inner
-        // OpenTelemetryChatClient always emit spans under the same ActivitySource, even when
-        // the caller passes "" or whitespace (which neither client should treat as a real source).
-        this._sourceName = string.IsNullOrWhiteSpace(sourceName) ? OpenTelemetryConsts.DefaultSourceName : sourceName!;
-        this._autoWireChatClient = autoWireChatClient;
-
         this._otelClient = new OpenTelemetryChatClient(
             new ForwardingChatClient(this),
-            sourceName: this._sourceName);
+            sourceName: string.IsNullOrEmpty(sourceName) ? OpenTelemetryConsts.DefaultSourceName : sourceName!);
     }
 
     /// <inheritdoc/>
@@ -203,85 +163,6 @@ public sealed class OpenTelemetryAgent : DelegatingAIAgent, IDisposable
         public Activity? CurrentActivity { get; }
     }
 
-    /// <summary>
-    /// If auto-wiring is enabled and the inner agent is a <see cref="ChatClientAgent"/> whose underlying
-    /// <see cref="IChatClient"/> is not already instrumented with <see cref="OpenTelemetryChatClient"/>, returns a
-    /// new <see cref="ChatClientAgentRunOptions"/> with a <see cref="ChatClientAgentRunOptions.ChatClientFactory"/>
-    /// that wraps the chat client with <see cref="OpenTelemetryChatClient"/>. When <paramref name="options"/> is a
-    /// plain <see cref="AgentRunOptions"/> (the base type, not <see cref="ChatClientAgentRunOptions"/>), the base
-    /// properties are copied onto the new <see cref="ChatClientAgentRunOptions"/> so high-level callers that pass
-    /// the abstract <see cref="AgentRunOptions"/> still benefit from auto-wiring and propagate their settings to
-    /// the inner agent. Otherwise, returns <paramref name="options"/> unchanged.
-    /// </summary>
-    private AgentRunOptions? GetRunOptionsWithChatClientWiring(AgentRunOptions? options)
-    {
-        if (!this._autoWireChatClient)
-        {
-            return options;
-        }
-
-        // The auto-wiring only applies when a ChatClientAgent is reachable from the inner agent. Otherwise, no-op.
-        // Use GetService rather than a type check so wrapping agents that expose a nested ChatClientAgent are supported.
-        var chatClientAgent = this.InnerAgent.GetService<ChatClientAgent>();
-        if (chatClientAgent is null)
-        {
-            return options;
-        }
-
-        // Respect ChatClientAgentOptions.UseProvidedChatClientAsIs: don't decorate the chat client when the user opted out.
-        if (chatClientAgent.GetService<ChatClientAgentOptions>()?.UseProvidedChatClientAsIs is true)
-        {
-            return options;
-        }
-
-        // Capture the underlying IChatClient and check whether it is already instrumented.
-        var chatClient = chatClientAgent.GetService<IChatClient>();
-        if (chatClient is null || chatClient.GetService(typeof(OpenTelemetryChatClient)) is not null)
-        {
-            return options;
-        }
-
-        string sourceName = this._sourceName;
-        static IChatClient WrapIfNeeded(IChatClient cc, string sourceName) =>
-            cc.GetService(typeof(OpenTelemetryChatClient)) is not null
-                ? cc
-                : cc.AsBuilder().UseOpenTelemetry(sourceName: sourceName).Build();
-
-        if (options is ChatClientAgentRunOptions ccOptions)
-        {
-            // Don't mutate the caller's options; clone and chain any caller-provided factory.
-            // If the user factory already returns an OpenTelemetry-instrumented client, don't double-wrap.
-            var clone = (ChatClientAgentRunOptions)ccOptions.Clone();
-            var userFactory = clone.ChatClientFactory;
-            clone.ChatClientFactory = cc => WrapIfNeeded(userFactory is null ? cc : userFactory(cc), sourceName);
-            return clone;
-        }
-
-        // For a plain AgentRunOptions (or null), create a ChatClientAgentRunOptions and preserve
-        // any base AgentRunOptions properties from the caller so they reach the inner agent.
-        var newOptions = new ChatClientAgentRunOptions
-        {
-            ChatClientFactory = cc => WrapIfNeeded(cc, sourceName),
-        };
-
-        if (options is not null)
-        {
-            CopyBaseAgentRunOptions(options, newOptions);
-        }
-
-        return newOptions;
-    }
-
-#pragma warning disable MEAI001 // ContinuationToken is experimental; copy it through to preserve caller-provided value.
-    private static void CopyBaseAgentRunOptions(AgentRunOptions source, AgentRunOptions target)
-    {
-        target.ContinuationToken = source.ContinuationToken;
-        target.AllowBackgroundResponses = source.AllowBackgroundResponses;
-        target.AdditionalProperties = source.AdditionalProperties?.Clone();
-        target.ResponseFormat = source.ResponseFormat;
-    }
-#pragma warning restore MEAI001
-
     /// <summary>The stub <see cref="IChatClient"/> used to delegate from the <see cref="OpenTelemetryChatClient"/> into the inner <see cref="AIAgent"/>.</summary>
     /// <param name="parentAgent"></param>
     private sealed class ForwardingChatClient(OpenTelemetryAgent parentAgent) : IChatClient
@@ -294,11 +175,8 @@ public sealed class OpenTelemetryAgent : DelegatingAIAgent, IDisposable
             // Update the current activity to reflect the agent invocation.
             parentAgent.UpdateCurrentActivity(fo?.CurrentActivity);
 
-            // If enabled, wire the underlying chat client with OpenTelemetryChatClient via ChatClientFactory.
-            var runOptions = parentAgent.GetRunOptionsWithChatClientWiring(fo?.Options);
-
             // Invoke the inner agent.
-            var response = await parentAgent.InnerAgent.RunAsync(messages, fo?.Session, runOptions, cancellationToken).ConfigureAwait(false);
+            var response = await parentAgent.InnerAgent.RunAsync(messages, fo?.Session, fo?.Options, cancellationToken).ConfigureAwait(false);
 
             // Wrap the response in a ChatResponse so we can pass it back through OpenTelemetryChatClient.
             return response.AsChatResponse();
@@ -312,11 +190,8 @@ public sealed class OpenTelemetryAgent : DelegatingAIAgent, IDisposable
             // Update the current activity to reflect the agent invocation.
             parentAgent.UpdateCurrentActivity(fo?.CurrentActivity);
 
-            // If enabled, wire the underlying chat client with OpenTelemetryChatClient via ChatClientFactory.
-            var runOptions = parentAgent.GetRunOptionsWithChatClientWiring(fo?.Options);
-
             // Invoke the inner agent.
-            await foreach (var update in parentAgent.InnerAgent.RunStreamingAsync(messages, fo?.Session, runOptions, cancellationToken).ConfigureAwait(false))
+            await foreach (var update in parentAgent.InnerAgent.RunStreamingAsync(messages, fo?.Session, fo?.Options, cancellationToken).ConfigureAwait(false))
             {
                 // Wrap the response updates in ChatResponseUpdates so we can pass them back through OpenTelemetryChatClient.
                 yield return update.AsChatResponseUpdate();

dotnet/tests/Microsoft.Agents.AI.Foundry.UnitTests/FoundryEvalConverterTests.cs

@@ -179,35 +179,6 @@ public sealed class FoundryEvalConverterTests
         Assert.Null(payload.Context);
     }
 
-    [Fact]
-    public void ConvertEvalItem_WithExpectedOutput_PopulatesGroundTruth()
-    {
-        // Arrange
-        var item = new EvalItem(query: "q", response: "r")
-        {
-            ExpectedOutput = "the golden answer",
-        };
-
-        // Act
-        var payload = FoundryEvalConverter.ConvertEvalItem(item);
-
-        // Assert
-        Assert.Equal("the golden answer", payload.GroundTruth);
-    }
-
-    [Fact]
-    public void ConvertEvalItem_WithoutExpectedOutput_OmitsGroundTruth()
-    {
-        // Arrange
-        var item = new EvalItem(query: "q", response: "r");
-
-        // Act
-        var payload = FoundryEvalConverter.ConvertEvalItem(item);
-
-        // Assert
-        Assert.Null(payload.GroundTruth);
-    }
-
     // ---------------------------------------------------------------
     // FoundryEvalConverter.BuildTestingCriteria tests
     // ---------------------------------------------------------------
@@ -268,33 +239,6 @@ public sealed class FoundryEvalConverterTests
         Assert.Equal("{{item.context}}", mapping["context"]);
     }
 
-    [Fact]
-    public void BuildTestingCriteria_SimilarityEvaluator_IncludesGroundTruth()
-    {
-        // Act
-        var criteria = FoundryEvalConverter.BuildTestingCriteria(
-            ["similarity"], "gpt-4o-mini", includeDataMapping: true);
-
-        // Assert
-        Assert.Single(criteria);
-        Assert.Equal("builtin.similarity", criteria[0].EvaluatorName);
-        var mapping = criteria[0].DataMapping;
-        Assert.NotNull(mapping);
-        Assert.True(mapping.ContainsKey("ground_truth"));
-        Assert.Equal("{{item.ground_truth}}", mapping["ground_truth"]);
-    }
-
-    [Fact]
-    public void BuildTestingCriteria_NonGroundTruthEvaluator_OmitsGroundTruth()
-    {
-        var criteria = FoundryEvalConverter.BuildTestingCriteria(
-            ["relevance"], "gpt-4o-mini", includeDataMapping: true);
-
-        var mapping = criteria[0].DataMapping;
-        Assert.NotNull(mapping);
-        Assert.False(mapping.ContainsKey("ground_truth"));
-    }
-
     [Fact]
     public void BuildTestingCriteria_WithoutDataMapping_OmitsMappingField()
     {
@@ -338,59 +282,6 @@ public sealed class FoundryEvalConverterTests
         Assert.True(schema.Properties.ContainsKey("tool_definitions"));
     }
 
-    [Fact]
-    public void BuildItemSchema_WithGroundTruth_IncludesGroundTruthProperty()
-    {
-        // Act
-        var schema = FoundryEvalConverter.BuildItemSchema(hasGroundTruth: true);
-
-        // Assert
-        Assert.True(schema.Properties.ContainsKey("ground_truth"));
-        Assert.Equal("string", schema.Properties["ground_truth"].Type);
-    }
-
-    [Fact]
-    public void BuildItemSchema_WithoutGroundTruth_OmitsGroundTruthProperty()
-    {
-        var schema = FoundryEvalConverter.BuildItemSchema();
-
-        Assert.False(schema.Properties.ContainsKey("ground_truth"));
-    }
-
-    // ---------------------------------------------------------------
-    // FoundryEvalConverter.FindMissingGroundTruthEvaluators tests
-    // ---------------------------------------------------------------
-
-    [Fact]
-    public void FindMissingGroundTruthEvaluators_NoGroundTruth_ReturnsSimilarity()
-    {
-        // Act
-        var missing = FoundryEvalConverter.FindMissingGroundTruthEvaluators(
-            ["similarity", "relevance"], hasGroundTruth: false);
-
-        // Assert
-        Assert.Single(missing);
-        Assert.Equal("similarity", missing[0]);
-    }
-
-    [Fact]
-    public void FindMissingGroundTruthEvaluators_HasGroundTruth_ReturnsEmpty()
-    {
-        var missing = FoundryEvalConverter.FindMissingGroundTruthEvaluators(
-            ["similarity"], hasGroundTruth: true);
-
-        Assert.Empty(missing);
-    }
-
-    [Fact]
-    public void FindMissingGroundTruthEvaluators_NoGroundTruthEvaluators_ReturnsEmpty()
-    {
-        var missing = FoundryEvalConverter.FindMissingGroundTruthEvaluators(
-            ["relevance", "coherence"], hasGroundTruth: false);
-
-        Assert.Empty(missing);
-    }
-
     // ---------------------------------------------------------------
     // FoundryEvalConverter.ConvertMessage DataContent test
     // ---------------------------------------------------------------

dotnet/tests/Microsoft.Agents.AI.Harness.UnitTests/HarnessAgentOptionsTests.cs

@@ -1,56 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-namespace Microsoft.Agents.AI.UnitTests;
-
-public class HarnessAgentOptionsTests
-{
-    /// <summary>
-    /// Verify that default property values are as expected.
-    /// </summary>
-    [Fact]
-    public void DefaultPropertyValues()
-    {
-        // Arrange & Act
-        var options = new HarnessAgentOptions();
-
-        // Assert
-        Assert.Null(options.Id);
-        Assert.Null(options.Name);
-        Assert.Null(options.Description);
-        Assert.Null(options.ChatOptions);
-        Assert.Null(options.ChatHistoryProvider);
-        Assert.Null(options.AIContextProviders);
-    }
-
-    /// <summary>
-    /// Verify that all properties can be set and retrieved.
-    /// </summary>
-    [Fact]
-    public void PropertiesCanBeSetAndRetrieved()
-    {
-        // Arrange
-        var chatHistoryProvider = new InMemoryChatHistoryProvider();
-        var contextProviders = new AIContextProvider[] { new TodoProvider() };
-
-        // Act
-        var options = new HarnessAgentOptions
-        {
-            Id = "test-id",
-            Name = "test-name",
-            Description = "test-description",
-            ChatOptions = new() { Temperature = 0.5f, Instructions = "custom instructions" },
-            ChatHistoryProvider = chatHistoryProvider,
-            AIContextProviders = contextProviders,
-        };
-
-        // Assert
-        Assert.Equal("test-id", options.Id);
-        Assert.Equal("test-name", options.Name);
-        Assert.Equal("test-description", options.Description);
-        Assert.NotNull(options.ChatOptions);
-        Assert.Equal(0.5f, options.ChatOptions!.Temperature);
-        Assert.Equal("custom instructions", options.ChatOptions.Instructions);
-        Assert.Same(chatHistoryProvider, options.ChatHistoryProvider);
-        Assert.Same(contextProviders, options.AIContextProviders);
-    }
-}

dotnet/tests/Microsoft.Agents.AI.Harness.UnitTests/HarnessAgentTests.cs

@@ -1,516 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Threading;
-using System.Threading.Tasks;
-using Microsoft.Extensions.AI;
-using Moq;
-
-namespace Microsoft.Agents.AI.UnitTests;
-
-public class HarnessAgentTests
-{
-    private const int TestMaxContextWindowTokens = 100_000;
-    private const int TestMaxOutputTokens = 10_000;
-
-    #region Constructor Validation
-
-    /// <summary>
-    /// Verify that the constructor throws when chatClient is null.
-    /// </summary>
-    [Fact]
-    public void Constructor_ThrowsWhenChatClientIsNull()
-    {
-        // Act & Assert
-        Assert.Throws<ArgumentNullException>(() => new HarnessAgent(null!, TestMaxContextWindowTokens, TestMaxOutputTokens));
-    }
-
-    /// <summary>
-    /// Verify that the constructor throws when MaxContextWindowTokens is invalid (zero).
-    /// </summary>
-    [Fact]
-    public void Constructor_ThrowsWhenMaxContextWindowTokensIsZero()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act & Assert
-        Assert.Throws<ArgumentOutOfRangeException>(() => new HarnessAgent(chatClient, 0, TestMaxOutputTokens));
-    }
-
-    /// <summary>
-    /// Verify that the constructor throws when MaxOutputTokens equals MaxContextWindowTokens.
-    /// </summary>
-    [Fact]
-    public void Constructor_ThrowsWhenMaxOutputTokensEqualsContextWindow()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act & Assert
-        Assert.Throws<ArgumentOutOfRangeException>(() => new HarnessAgent(chatClient, 100_000, 100_000));
-    }
-
-    /// <summary>
-    /// Verify that the constructor succeeds when options is null.
-    /// </summary>
-    [Fact]
-    public void Constructor_SucceedsWhenOptionsIsNull()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-
-        // Assert
-        Assert.NotNull(agent);
-    }
-
-    #endregion
-
-    #region Agent Identity
-
-    /// <summary>
-    /// Verify that Name and Description are passed through to the inner agent.
-    /// </summary>
-    [Fact]
-    public void NameAndDescription_ArePassedThrough()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            Name = "TestAgent",
-            Description = "A test agent",
-        });
-
-        // Assert
-        Assert.Equal("TestAgent", agent.Name);
-        Assert.Equal("A test agent", agent.Description);
-    }
-
-    /// <summary>
-    /// Verify that Id is passed through to the inner agent.
-    /// </summary>
-    [Fact]
-    public void Id_IsPassedThrough()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            Id = "my-agent-id",
-        });
-
-        // Assert
-        Assert.Equal("my-agent-id", agent.Id);
-    }
-
-    #endregion
-
-    #region Instructions
-
-    /// <summary>
-    /// Verify that default instructions are used when none are provided.
-    /// </summary>
-    [Fact]
-    public void Instructions_DefaultsToBuiltInInstructions()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.Equal(HarnessAgent.DefaultInstructions, innerAgent!.Instructions);
-    }
-
-    /// <summary>
-    /// Verify that default instructions are used when options is provided but ChatOptions.Instructions is null.
-    /// </summary>
-    [Fact]
-    public void Instructions_DefaultsWhenChatOptionsInstructionsIsNull()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            ChatOptions = new ChatOptions { Temperature = 0.5f },
-        });
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.Equal(HarnessAgent.DefaultInstructions, innerAgent!.Instructions);
-    }
-
-    /// <summary>
-    /// Verify that ChatOptions.Instructions overrides the defaults.
-    /// </summary>
-    [Fact]
-    public void Instructions_CanBeOverriddenViaChatOptions()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            ChatOptions = new ChatOptions { Instructions = "You are a custom assistant." },
-        });
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.Equal("You are a custom assistant.", innerAgent!.Instructions);
-    }
-
-    #endregion
-
-    #region ChatHistoryProvider
-
-    /// <summary>
-    /// Verify that the default ChatHistoryProvider is InMemoryChatHistoryProvider when none is specified.
-    /// </summary>
-    [Fact]
-    public void ChatHistoryProvider_DefaultsToInMemory()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.IsType<InMemoryChatHistoryProvider>(innerAgent!.ChatHistoryProvider);
-    }
-
-    /// <summary>
-    /// Verify that a custom ChatHistoryProvider is used when provided.
-    /// </summary>
-    [Fact]
-    public void ChatHistoryProvider_UsesCustomProviderWhenSpecified()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-        var customProvider = new InMemoryChatHistoryProvider();
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            ChatHistoryProvider = customProvider,
-        });
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.Same(customProvider, innerAgent!.ChatHistoryProvider);
-    }
-
-    #endregion
-
-    #region ChatClient Pipeline
-
-    /// <summary>
-    /// Verify that the inner agent's ChatClient includes FunctionInvokingChatClient in the pipeline.
-    /// </summary>
-    [Fact]
-    public void Pipeline_IncludesFunctionInvokingChatClient()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        var ficc = innerAgent!.ChatClient.GetService<FunctionInvokingChatClient>();
-        Assert.NotNull(ficc);
-    }
-
-    /// <summary>
-    /// Verify that the inner agent's ChatClient pipeline includes more than just the raw chat client,
-    /// confirming that per-service-call persistence and other decorators have been applied.
-    /// </summary>
-    [Fact]
-    public void Pipeline_HasDecoratedChatClient()
-    {
-        // Arrange
-        var mockClient = new Mock<IChatClient>();
-        var rawClient = mockClient.Object;
-
-        // Act
-        var agent = new HarnessAgent(rawClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert — the pipeline wraps the raw client, so the outer client is not the same object.
-        Assert.NotNull(innerAgent);
-        Assert.NotSame(rawClient, innerAgent!.ChatClient);
-    }
-
-    #endregion
-
-    #region AIContextProviders
-
-    /// <summary>
-    /// Verify that additional AIContextProviders from options are passed to the inner ChatClientAgent,
-    /// not merged into the chat client builder pipeline.
-    /// </summary>
-    [Fact]
-    public void AIContextProviders_ArePassedToInnerAgent()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-        var todoProvider = new TodoProvider();
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            AIContextProviders = [todoProvider],
-        });
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert — the TodoProvider should appear in the inner agent's AIContextProviders.
-        Assert.NotNull(innerAgent);
-        Assert.NotNull(innerAgent!.AIContextProviders);
-        Assert.Contains(todoProvider, innerAgent.AIContextProviders!);
-    }
-
-    /// <summary>
-    /// Verify that when no AIContextProviders are specified, the inner agent has no additional providers.
-    /// </summary>
-    [Fact]
-    public void AIContextProviders_IsNullWhenNoneSpecified()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.NotNull(innerAgent);
-        Assert.Null(innerAgent!.AIContextProviders);
-    }
-
-    #endregion
-
-    #region ChatOptions and Tools
-
-    /// <summary>
-    /// Verify that tools from ChatOptions are passed to the model during invocation.
-    /// </summary>
-    [Fact]
-    public async Task ChatOptions_ToolsArePreservedAsync()
-    {
-        // Arrange
-        var tool = AIFunctionFactory.Create(() => "test", "TestTool");
-        var mockClient = new Mock<IChatClient>();
-        ChatOptions? capturedOptions = null;
-        mockClient
-            .Setup(c => c.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .Callback<IEnumerable<ChatMessage>, ChatOptions?, CancellationToken>((_, opts, _) => capturedOptions = opts)
-            .ReturnsAsync(new ChatResponse(new ChatMessage(ChatRole.Assistant, "Done")));
-
-        var agent = new HarnessAgent(mockClient.Object, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            ChatOptions = new ChatOptions
-            {
-                Tools = [tool],
-            },
-        });
-        var session = await agent.CreateSessionAsync();
-
-        // Act
-        await agent.RunAsync([new ChatMessage(ChatRole.User, "Hi")], session);
-
-        // Assert — verify the tool was included in the ChatOptions passed to the model.
-        Assert.NotNull(capturedOptions);
-        Assert.NotNull(capturedOptions!.Tools);
-        Assert.Contains(capturedOptions.Tools, t => t == tool);
-    }
-
-    /// <summary>
-    /// Verify that the source ChatOptions are cloned and not modified.
-    /// </summary>
-    [Fact]
-    public void ChatOptions_SourceIsNotModified()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-        var sourceChatOptions = new ChatOptions
-        {
-            Instructions = "original instructions",
-            Temperature = 0.7f,
-        };
-
-        // Act
-        _ = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            ChatOptions = sourceChatOptions,
-        });
-
-        // Assert — source ChatOptions should not be mutated.
-        Assert.Equal("original instructions", sourceChatOptions.Instructions);
-        Assert.Equal(0.7f, sourceChatOptions.Temperature);
-    }
-
-    #endregion
-
-    #region GetService
-
-    /// <summary>
-    /// Verify that GetService returns the HarnessAgent for its own type.
-    /// </summary>
-    [Fact]
-    public void GetService_ReturnsSelfForHarnessAgentType()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-
-        // Assert
-        Assert.Same(agent, agent.GetService<HarnessAgent>());
-    }
-
-    /// <summary>
-    /// Verify that GetService returns the inner ChatClientAgent.
-    /// </summary>
-    [Fact]
-    public void GetService_ReturnsInnerChatClientAgent()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = new HarnessAgent(chatClient, TestMaxContextWindowTokens, TestMaxOutputTokens);
-
-        // Assert
-        Assert.NotNull(agent.GetService<ChatClientAgent>());
-    }
-
-    #endregion
-
-    #region RunAsync Delegation
-
-    /// <summary>
-    /// Verify that RunAsync delegates to the inner ChatClientAgent.
-    /// </summary>
-    [Fact]
-    public async Task RunAsync_DelegatesToInnerAgentAsync()
-    {
-        // Arrange
-        var mockClient = new Mock<IChatClient>();
-        mockClient
-            .Setup(c => c.GetResponseAsync(
-                It.IsAny<IEnumerable<ChatMessage>>(),
-                It.IsAny<ChatOptions>(),
-                It.IsAny<CancellationToken>()))
-            .ReturnsAsync(new ChatResponse(new ChatMessage(ChatRole.Assistant, "Hello!")));
-
-        var agent = new HarnessAgent(mockClient.Object, TestMaxContextWindowTokens, TestMaxOutputTokens);
-        var session = await agent.CreateSessionAsync();
-
-        // Act
-        var response = await agent.RunAsync(
-            [new ChatMessage(ChatRole.User, "Hi")],
-            session);
-
-        // Assert
-        Assert.NotNull(response);
-        Assert.True(response.Messages.Any());
-    }
-
-    #endregion
-
-    #region DefaultInstructions
-
-    /// <summary>
-    /// Verify that DefaultInstructions is a non-empty public constant.
-    /// </summary>
-    [Fact]
-    public void DefaultInstructions_IsNonEmpty()
-    {
-        // Assert
-        Assert.False(string.IsNullOrWhiteSpace(HarnessAgent.DefaultInstructions));
-    }
-
-    #endregion
-
-    #region AsHarnessAgent Extension Method
-
-    /// <summary>
-    /// Verify that AsHarnessAgent creates a HarnessAgent with default options.
-    /// </summary>
-    [Fact]
-    public void AsHarnessAgent_CreatesAgentWithDefaults()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = chatClient.AsHarnessAgent(TestMaxContextWindowTokens, TestMaxOutputTokens);
-
-        // Assert
-        Assert.NotNull(agent);
-        Assert.IsType<HarnessAgent>(agent);
-        Assert.Equal(HarnessAgent.DefaultInstructions, agent.GetService<ChatClientAgent>()!.Instructions);
-    }
-
-    /// <summary>
-    /// Verify that AsHarnessAgent passes options through to the HarnessAgent.
-    /// </summary>
-    [Fact]
-    public void AsHarnessAgent_PassesOptionsThrough()
-    {
-        // Arrange
-        var chatClient = new Mock<IChatClient>().Object;
-
-        // Act
-        var agent = chatClient.AsHarnessAgent(TestMaxContextWindowTokens, TestMaxOutputTokens, new HarnessAgentOptions
-        {
-            Name = "ExtensionAgent",
-            ChatOptions = new ChatOptions { Instructions = "Custom instructions" },
-        });
-        var innerAgent = agent.GetService<ChatClientAgent>();
-
-        // Assert
-        Assert.Equal("ExtensionAgent", agent.Name);
-        Assert.NotNull(innerAgent);
-        Assert.Equal("Custom instructions", innerAgent!.Instructions);
-    }
-
-    /// <summary>
-    /// Verify that AsHarnessAgent throws when chatClient is null.
-    /// </summary>
-    [Fact]
-    public void AsHarnessAgent_ThrowsWhenChatClientIsNull()
-    {
-        // Act & Assert
-        Assert.Throws<ArgumentNullException>(() => ((IChatClient)null!).AsHarnessAgent(TestMaxContextWindowTokens, TestMaxOutputTokens));
-    }
-
-    #endregion
-}

dotnet/tests/Microsoft.Agents.AI.Harness.UnitTests/Microsoft.Agents.AI.Harness.UnitTests.csproj

@@ -1,11 +0,0 @@
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <PropertyGroup>
-    <NoWarn>$(NoWarn);MAAI001</NoWarn>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <ProjectReference Include="..\..\src\Microsoft.Agents.AI.Harness\Microsoft.Agents.AI.Harness.csproj" />
-  </ItemGroup>
-
-</Project>

dotnet/tests/Microsoft.Agents.AI.Hosting.OpenAI.UnitTests/OpenAIResponsesAgentResolutionIntegrationTests.cs

@@ -267,43 +267,7 @@ public sealed class OpenAIResponsesAgentResolutionIntegrationTests : IAsyncDispo
         Assert.Equal(System.Net.HttpStatusCode.BadRequest, httpResponse.StatusCode);
 
         string responseJson = await httpResponse.Content.ReadAsStringAsync();
-        using JsonDocument errorDoc1 = JsonDocument.Parse(responseJson);
-        string? errorCode = errorDoc1.RootElement.GetProperty("error").GetProperty("code").GetString();
-        Assert.Equal("missing_required_parameter", errorCode);
-    }
-
-    /// <summary>
-    /// Verifies that the model field alone is not used for agent resolution.
-    /// The multi-agent endpoint requires agent.name or metadata.entity_id; setting only model returns 400.
-    /// </summary>
-    [Fact]
-    public async Task CreateResponse_WithModelOnly_ReturnsBadRequestAsync()
-    {
-        // Arrange
-        const string AgentName = "test-agent";
-
-        this._httpClient = await this.CreateTestServerWithAgentResolutionAsync(
-            (AgentName, "Instructions", "Response"));
-
-        // Act - Send request with model=agentName but no agent.name or metadata.entity_id
-        using StringContent requestContent = new(JsonSerializer.Serialize(new
-        {
-            model = AgentName,
-            input = new[]
-            {
-                new { type = "message", role = "user", content = "Test message" }
-            }
-        }), Encoding.UTF8, "application/json");
-
-        using HttpResponseMessage httpResponse = await this._httpClient!.PostAsync(new Uri("/v1/responses", UriKind.Relative), requestContent);
-
-        // Assert - model is not used for agent resolution
-        Assert.Equal(System.Net.HttpStatusCode.BadRequest, httpResponse.StatusCode);
-
-        string responseJson = await httpResponse.Content.ReadAsStringAsync();
-        using JsonDocument errorDoc2 = JsonDocument.Parse(responseJson);
-        string? errorCode = errorDoc2.RootElement.GetProperty("error").GetProperty("code").GetString();
-        Assert.Equal("missing_required_parameter", errorCode);
+        Assert.Contains("agent.name", responseJson, StringComparison.OrdinalIgnoreCase);
     }
 
     /// <summary>

dotnet/tests/Microsoft.Agents.AI.UnitTests/OpenTelemetryAgentTests.cs

@@ -627,455 +627,4 @@ public class OpenTelemetryAgentTests
     }
 
     private static string ReplaceWhitespace(string? input) => Regex.Replace(input ?? "", @"\s+", "").Trim();
-
-    #region AutoWireChatClient
-
-    [Fact]
-    public async Task AutoWireChatClient_DefaultsToEnabled_EmitsChatSpan_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        _ = await agent.RunAsync("hi");
-
-        // Expect 2 activities: the inner chat span (from auto-wired OpenTelemetryChatClient) and the invoke_agent span.
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => a.DisplayName.StartsWith("invoke_agent", StringComparison.Ordinal));
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_Streaming_EmitsChatSpan_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        await foreach (var _ in agent.RunStreamingAsync("hi"))
-        {
-        }
-
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => a.DisplayName.StartsWith("invoke_agent", StringComparison.Ordinal));
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_Disabled_DoesNotEmitChatSpan_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName, autoWireChatClient: false);
-
-        _ = await agent.RunAsync("hi");
-
-        // Only the invoke_agent activity should be emitted; no chat span.
-        var activity = Assert.Single(activities);
-        Assert.StartsWith("invoke_agent", activity.DisplayName);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_NonChatClientAgent_NoOp_Async()
-    {
-        // Inner is not a ChatClientAgent — auto-wiring must be a no-op and options must remain null.
-        AgentRunOptions? observedOptions = null;
-        var inner = new TestAIAgent
-        {
-            RunAsyncFunc = (messages, session, options, ct) =>
-            {
-                observedOptions = options;
-                return Task.FromResult(new AgentResponse(new ChatMessage(ChatRole.Assistant, "ok")));
-            },
-        };
-
-        using var agent = new OpenTelemetryAgent(inner);
-
-        _ = await agent.RunAsync("hi");
-
-        Assert.Null(observedOptions);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_UseProvidedChatClientAsIs_DoesNotEmitChatSpan_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient, new ChatClientAgentOptions { UseProvidedChatClientAsIs = true });
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        _ = await agent.RunAsync("hi");
-
-        // UseProvidedChatClientAsIs opts out of auto-wiring, so only the invoke_agent span should be emitted.
-        var activity = Assert.Single(activities);
-        Assert.StartsWith("invoke_agent", activity.DisplayName);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_AlreadyInstrumented_DoesNotDoubleWrap_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        // Pre-wrap with OpenTelemetryChatClient on the same source so spans flow through the tracer.
-        IChatClient preWrapped = fakeChatClient.AsBuilder().UseOpenTelemetry(sourceName: sourceName).Build();
-        var inner = new ChatClientAgent(preWrapped);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        _ = await agent.RunAsync("hi");
-
-        // Expect exactly 2 activities (one invoke_agent + one chat from the pre-existing wrapper). If we had double-wrapped, we would see 3.
-        Assert.Equal(2, activities.Count);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_PreservesUserChatClientFactory_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        bool userFactoryCalled = false;
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        var runOptions = new ChatClientAgentRunOptions
-        {
-            ChatClientFactory = cc =>
-            {
-                userFactoryCalled = true;
-                return cc;
-            },
-        };
-
-        _ = await agent.RunAsync("hi", options: runOptions);
-
-        Assert.True(userFactoryCalled);
-        // Auto-wiring should still produce a chat span on top of the user's factory.
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_PlainAgentRunOptions_PreservesBaseProperties_Async()
-    {
-        // Auto-wiring converts a plain AgentRunOptions into a ChatClientAgentRunOptions. The base
-        // properties (ContinuationToken, AllowBackgroundResponses, AdditionalProperties, ResponseFormat)
-        // must be preserved so they reach the inner agent.
-        AgentRunOptions? observedOptions = null;
-        var fakeChatClient = new AutoWireTestChatClient();
-        var innerChatClientAgent = new ChatClientAgent(fakeChatClient);
-
-        // Wrapping agent: surfaces the ChatClientAgent via GetService (so auto-wiring activates),
-        // but captures the AgentRunOptions passed to RunAsync by the OpenTelemetryAgent.
-        var wrapper = new TestAIAgent
-        {
-            GetServiceFunc = (type, key) =>
-                type == typeof(ChatClientAgent) ? innerChatClientAgent : null,
-            RunAsyncFunc = (messages, session, options, ct) =>
-            {
-                observedOptions = options;
-                return Task.FromResult(new AgentResponse(new ChatMessage(ChatRole.Assistant, "ok")));
-            },
-        };
-
-        using var agent = new OpenTelemetryAgent(wrapper);
-
-        var additionalProps = new AdditionalPropertiesDictionary { ["customKey"] = "customValue" };
-        var inputOptions = new AgentRunOptions
-        {
-            AllowBackgroundResponses = true,
-            AdditionalProperties = additionalProps,
-            ResponseFormat = ChatResponseFormat.Json,
-        };
-
-        _ = await agent.RunAsync("hi", options: inputOptions);
-
-        Assert.NotNull(observedOptions);
-        Assert.IsType<ChatClientAgentRunOptions>(observedOptions);
-        Assert.Equal(true, observedOptions!.AllowBackgroundResponses);
-        Assert.Same(ChatResponseFormat.Json, observedOptions.ResponseFormat);
-        Assert.NotNull(observedOptions.AdditionalProperties);
-        Assert.Equal("customValue", observedOptions.AdditionalProperties!["customKey"]);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_UserFactoryReturnsInstrumentedClient_DoesNotDoubleWrap_Async()
-    {
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        // User factory wraps the chat client with OpenTelemetryChatClient itself.
-        var runOptions = new ChatClientAgentRunOptions
-        {
-            ChatClientFactory = cc => cc.AsBuilder().UseOpenTelemetry(sourceName: sourceName).Build(),
-        };
-
-        _ = await agent.RunAsync("hi", options: runOptions);
-
-        // Expect 2 activities (invoke_agent + a single chat span). If we double-wrapped, we would see 3.
-        Assert.Equal(2, activities.Count);
-    }
-
-    [Theory]
-    [InlineData(null)]
-    [InlineData("")]
-    [InlineData("   ")]
-    [InlineData("\t")]
-    public async Task Ctor_NullOrWhitespaceSourceName_AutoWiredChatClientUsesDefaultSource_Async(string? sourceName)
-    {
-        // Both the agent-level invoke_agent span and the auto-wired chat span must be emitted under
-        // OpenTelemetryConsts.DefaultSourceName when the caller passes null, "", or whitespace, so they reach
-        // the same ActivitySource and are not silently dropped by the exporter.
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource("Experimental.Microsoft.Agents.AI")
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        _ = await agent.RunAsync("hi");
-
-        Assert.Equal(2, activities.Count);
-        Assert.All(activities, a => Assert.Equal("Experimental.Microsoft.Agents.AI", a.Source.Name));
-        Assert.Contains(activities, a => a.DisplayName.StartsWith("invoke_agent", StringComparison.Ordinal));
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-#pragma warning disable MEAI001 // ResponseContinuationToken is experimental.
-    [Fact]
-    public async Task AutoWireChatClient_PlainAgentRunOptions_PreservesContinuationToken_Async()
-    {
-        // ContinuationToken is the fourth base AgentRunOptions property copied by CopyBaseAgentRunOptions
-        // and is not exercised by AutoWireChatClient_PlainAgentRunOptions_PreservesBaseProperties_Async.
-        AgentRunOptions? observedOptions = null;
-        var fakeChatClient = new AutoWireTestChatClient();
-        var innerChatClientAgent = new ChatClientAgent(fakeChatClient);
-
-        var wrapper = new TestAIAgent
-        {
-            GetServiceFunc = (type, key) =>
-                type == typeof(ChatClientAgent) ? innerChatClientAgent : null,
-            RunAsyncFunc = (messages, session, options, ct) =>
-            {
-                observedOptions = options;
-                return Task.FromResult(new AgentResponse(new ChatMessage(ChatRole.Assistant, "ok")));
-            },
-        };
-
-        using var agent = new OpenTelemetryAgent(wrapper);
-
-        var token = ResponseContinuationToken.FromBytes(new byte[] { 1, 2, 3 });
-        var inputOptions = new AgentRunOptions
-        {
-            ContinuationToken = token,
-        };
-
-        _ = await agent.RunAsync("hi", options: inputOptions);
-
-        Assert.NotNull(observedOptions);
-        Assert.IsType<ChatClientAgentRunOptions>(observedOptions);
-        Assert.Same(token, observedOptions!.ContinuationToken);
-    }
-#pragma warning restore MEAI001
-
-    [Fact]
-    public async Task AutoWireChatClient_ChatClientAgentRunOptions_NoUserFactory_PreservesChatOptions_Async()
-    {
-        // When the caller passes a ChatClientAgentRunOptions without a ChatClientFactory, the auto-wiring
-        // must clone (not mutate) the caller's options, set the factory, and preserve nested ChatOptions.
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        ChatOptions? observedChatOptions = null;
-        var fakeChatClient = new AutoWireTestChatClient
-        {
-            OnGetResponseAsync = (msgs, opts) => observedChatOptions = opts,
-        };
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        var inputChatOptions = new ChatOptions { Temperature = 0.42f, ModelId = "test-model" };
-        var inputOptions = new ChatClientAgentRunOptions(inputChatOptions);
-
-        _ = await agent.RunAsync("hi", options: inputOptions);
-
-        // Caller's options must not have been mutated (no factory installed on the caller's instance).
-        Assert.Null(inputOptions.ChatClientFactory);
-
-        // Inner chat client must observe the caller-supplied ChatOptions.
-        Assert.NotNull(observedChatOptions);
-        Assert.Equal(0.42f, observedChatOptions!.Temperature);
-        Assert.Equal("test-model", observedChatOptions.ModelId);
-
-        // Auto-wiring still produces a chat span.
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_StreamingDisabled_DoesNotEmitChatSpan_Async()
-    {
-        // Symmetry with AutoWireChatClient_Disabled_DoesNotEmitChatSpan_Async for the streaming path.
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        var fakeChatClient = new AutoWireTestChatClient();
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName, autoWireChatClient: false);
-
-        await foreach (var _ in agent.RunStreamingAsync("hi"))
-        {
-        }
-
-        var activity = Assert.Single(activities);
-        Assert.StartsWith("invoke_agent", activity.DisplayName);
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_PlainAgentRunOptions_RealChatClientAgent_EmitsChatSpan_Async()
-    {
-        // High-level callers may pass the abstract base AgentRunOptions (not ChatClientAgentRunOptions) when
-        // wiring a ChatClientAgent. Auto-wiring must still kick in: convert to ChatClientAgentRunOptions,
-        // install the OTel-wrapping factory, and produce both the invoke_agent and chat spans end-to-end.
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        ChatOptions? observedChatOptions = null;
-        var fakeChatClient = new AutoWireTestChatClient
-        {
-            OnGetResponseAsync = (_, opts) => observedChatOptions = opts,
-        };
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        // Pass the base AgentRunOptions, not ChatClientAgentRunOptions.
-        var inputOptions = new AgentRunOptions { AllowBackgroundResponses = false };
-
-        _ = await agent.RunAsync("hi", options: inputOptions);
-
-        // Inner chat client was actually invoked (auto-wired factory ran without breaking the pipeline).
-        Assert.NotNull(observedChatOptions);
-
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => a.DisplayName.StartsWith("invoke_agent", StringComparison.Ordinal));
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    [Fact]
-    public async Task AutoWireChatClient_PlainAgentRunOptions_RealChatClientAgent_StreamingEmitsChatSpan_Async()
-    {
-        // Same as the sync test above but for the streaming path so both invocation paths
-        // are covered when callers pass a base AgentRunOptions.
-        var sourceName = Guid.NewGuid().ToString();
-        var activities = new List<Activity>();
-        using var tracerProvider = OpenTelemetry.Sdk.CreateTracerProviderBuilder()
-            .AddSource(sourceName)
-            .AddInMemoryExporter(activities)
-            .Build();
-
-        ChatOptions? observedChatOptions = null;
-        var fakeChatClient = new AutoWireTestChatClient
-        {
-            OnGetResponseAsync = (_, opts) => observedChatOptions = opts,
-        };
-        var inner = new ChatClientAgent(fakeChatClient);
-        using var agent = new OpenTelemetryAgent(inner, sourceName);
-
-        var inputOptions = new AgentRunOptions { AllowBackgroundResponses = false };
-
-        await foreach (var _ in agent.RunStreamingAsync("hi", options: inputOptions))
-        {
-        }
-
-        Assert.NotNull(observedChatOptions);
-
-        Assert.Equal(2, activities.Count);
-        Assert.Contains(activities, a => a.DisplayName.StartsWith("invoke_agent", StringComparison.Ordinal));
-        Assert.Contains(activities, a => string.Equals(a.GetTagItem("gen_ai.operation.name") as string, "chat", StringComparison.Ordinal));
-    }
-
-    private sealed class AutoWireTestChatClient : IChatClient
-    {
-        public Action<IEnumerable<ChatMessage>, ChatOptions?>? OnGetResponseAsync { get; set; }
-
-        public Task<ChatResponse> GetResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
-        {
-            this.OnGetResponseAsync?.Invoke(messages, options);
-            return Task.FromResult(new ChatResponse(new ChatMessage(ChatRole.Assistant, "ok")));
-        }
-
-        public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(IEnumerable<ChatMessage> messages, ChatOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
-        {
-            this.OnGetResponseAsync?.Invoke(messages, options);
-            await Task.Yield();
-            yield return new ChatResponseUpdate(ChatRole.Assistant, "ok");
-        }
-
-        public object? GetService(Type serviceType, object? serviceKey = null) =>
-            serviceType?.IsInstanceOfType(this) == true ? this : null;
-
-        public void Dispose() { }
-    }
-
-    #endregion
 }

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/AIAgentsAbstractionsExtensionsTests.cs

@@ -1,26 +0,0 @@
-// Copyright (c) Microsoft. All rights reserved.
-
-using System.Collections.Generic;
-using Microsoft.Extensions.AI;
-
-namespace Microsoft.Agents.AI.Workflows.UnitTests;
-
-public class AIAgentsAbstractionsExtensionsTests
-{
-    [Fact]
-    public void CopyWithAssistantToUserForOtherParticipants_DoesNotMutateOriginalMessages()
-    {
-        ChatMessage original = new(ChatRole.Assistant, "from first agent")
-        {
-            AuthorName = "firstAgent"
-        };
-
-        List<ChatMessage> copied = new[] { original }
-            .CopyWithAssistantToUserForOtherParticipants("secondAgent");
-
-        Assert.Single(copied);
-        Assert.Equal(ChatRole.Assistant, original.Role);
-        Assert.Equal(ChatRole.User, copied[0].Role);
-        Assert.NotSame(original, copied[0]);
-    }
-}

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/HandoffOrchestrationTests.cs

@@ -209,36 +209,6 @@ public class HandoffOrchestrationTests
         Assert.DoesNotContain(capturedNextAgentMessages, m => m.Role == ChatRole.Tool && m.Contents.Any(c => c is FunctionResultContent frc && frc.Result?.ToString() == "Transferred."));
     }
 
-    [Fact]
-    public async Task Handoffs_ReassignedMessagesDoNotMutateSharedConversationAsync()
-    {
-        var firstAgent = new ChatClientAgent(new MockChatClient((_, options) =>
-        {
-            string? transferFuncName = options?.Tools?.FirstOrDefault(t => t.Name.StartsWith("handoff_to_", StringComparison.Ordinal))?.Name;
-            Assert.NotNull(transferFuncName);
-
-            return new ChatResponse([
-                new ChatMessage(ChatRole.Assistant, "Context from first agent"),
-                new ChatMessage(ChatRole.Assistant, [new FunctionCallContent("call1", transferFuncName)]),
-            ]);
-        }), name: "firstAgent");
-        CapturingAgent secondAgent = new("secondAgent", "The second agent", "Context from first agent");
-
-        var workflow =
-            AgentWorkflowBuilder.CreateHandoffBuilderWith(firstAgent)
-            .WithHandoff(firstAgent, secondAgent)
-            .Build();
-
-        (_, List<ChatMessage>? result, _, _) = await RunWorkflowAsync(workflow, [new ChatMessage(ChatRole.User, "start")]);
-
-        Assert.NotNull(result);
-        Assert.Equal(ChatRole.User, secondAgent.RoleSeenDuringRun);
-
-        ChatMessage sharedMessage = Assert.Single(result, m => m.Text == "Context from first agent");
-        Assert.Equal(ChatRole.Assistant, sharedMessage.Role);
-        Assert.NotSame(sharedMessage, secondAgent.MessageSeenDuringRun);
-    }
-
     [Fact]
     public async Task Handoffs_TwoTransfers_HandoffTargetsDoNotReceiveHandoffFunctionMessagesAsync()
     {
@@ -304,208 +274,6 @@ public class HandoffOrchestrationTests
         Assert.DoesNotContain(capturedThirdAgentMessages, m => m.Role == ChatRole.Tool && m.Contents.Any(c => c is FunctionResultContent));
     }
 
-    [Fact]
-    public async Task Handoffs_MultipleTransfers_MergedMessagesPreserveStepOrderAsync()
-    {
-        // Regression test for https://github.com/microsoft/agent-framework/issues/4544
-        //
-        // Scenario: a multi-step handoff (A -> B -> C) is run through a workflow
-        // exposed as an AIAgent. When invoked via the non-streaming RunAsync
-        // entry-point, the merged AgentResponse.Messages must keep each step's
-        // messages contiguous — in particular, the "Transferred." tool result
-        // synthesized for a handoff function call must appear immediately after
-        // the function call that triggered it, before any messages from later
-        // steps. Streaming output already preserves this order; the bug
-        // manifested only after merging, where the synthesized tool results were
-        // bunched at the end of the response, far from their originating function
-        // calls (and consequently corrupted ChatHistory order).
-        //
-        // Each underlying agent response sets a real ResponseId — that is what
-        // causes MessageMerger to group its updates under that key. If the
-        // synthesized Tool update is emitted without that ResponseId, the merger
-        // routes it to the global "dangling" bucket and flushes it last,
-        // breaking per-step grouping.
-
-        var initialAgent = new ChatClientAgent(new MockChatClient((messages, options) =>
-        {
-            string? transferFuncName = options?.Tools?.FirstOrDefault(t => t.Name.StartsWith("handoff_to_", StringComparison.Ordinal))?.Name;
-            Assert.NotNull(transferFuncName);
-            return new(new ChatMessage(ChatRole.Assistant, [new TextContent("Routing to second agent"), new FunctionCallContent("call1", transferFuncName)]) { MessageId = "msg-initial" }) { ResponseId = "resp-initial" };
-        }), name: "initialAgent");
-
-        var secondAgent = new ChatClientAgent(new MockChatClient((messages, options) =>
-        {
-            string? transferFuncName = options?.Tools?.FirstOrDefault(t => t.Name.StartsWith("handoff_to_", StringComparison.Ordinal))?.Name;
-            Assert.NotNull(transferFuncName);
-            return new(new ChatMessage(ChatRole.Assistant, [new TextContent("Routing to third agent"), new FunctionCallContent("call2", transferFuncName)]) { MessageId = "msg-second" }) { ResponseId = "resp-second" };
-        }), name: "secondAgent", description: "The second agent");
-
-        var thirdAgent = new ChatClientAgent(new MockChatClient((messages, options) =>
-            new(new ChatMessage(ChatRole.Assistant, "Hello from agent3") { MessageId = "msg-third" }) { ResponseId = "resp-third" }),
-            name: "thirdAgent",
-            description: "The third / final agent");
-
-        var workflow =
-            AgentWorkflowBuilder.CreateHandoffBuilderWith(initialAgent)
-            .WithHandoff(initialAgent, secondAgent)
-            .WithHandoff(secondAgent, thirdAgent)
-            .Build();
-
-        AIAgent hostAgent = workflow.AsAIAgent(name: "HandoffWorkflow");
-
-        AgentResponse response = await hostAgent.RunAsync("abc");
-
-        List<ChatMessage> result = response.Messages.ToList();
-
-        // Expected merged sequence keeps each step contiguous:
-        //   [0] Assistant (initialAgent): text + FunctionCall(call1)
-        //   [1] Tool (initialAgent): FunctionResult(call1, "Transferred.")
-        //   [2] Assistant (secondAgent): text + FunctionCall(call2)
-        //   [3] Tool (secondAgent): FunctionResult(call2, "Transferred.")
-        //   [4] Assistant (thirdAgent): "Hello from agent3"
-        //
-        // The bug surfaced as the two Tool messages being moved to the end of the
-        // list — after thirdAgent's reply — which broke chat-history ordering.
-        Assert.Equal(5, result.Count);
-
-        Assert.Equal(ChatRole.Assistant, result[0].Role);
-        Assert.Contains("initialAgent", result[0].AuthorName);
-        Assert.Contains(result[0].Contents, c => c is FunctionCallContent fcc && fcc.CallId == "call1");
-
-        Assert.Equal(ChatRole.Tool, result[1].Role);
-        Assert.Contains("initialAgent", result[1].AuthorName);
-        Assert.Contains(result[1].Contents, c => c is FunctionResultContent frc && frc.CallId == "call1");
-
-        Assert.Equal(ChatRole.Assistant, result[2].Role);
-        Assert.Contains("secondAgent", result[2].AuthorName);
-        Assert.Contains(result[2].Contents, c => c is FunctionCallContent fcc && fcc.CallId == "call2");
-
-        Assert.Equal(ChatRole.Tool, result[3].Role);
-        Assert.Contains("secondAgent", result[3].AuthorName);
-        Assert.Contains(result[3].Contents, c => c is FunctionResultContent frc && frc.CallId == "call2");
-
-        Assert.Equal(ChatRole.Assistant, result[4].Role);
-        Assert.Contains("thirdAgent", result[4].AuthorName);
-        Assert.Equal("Hello from agent3", result[4].Text);
-    }
-
-    [Fact]
-    public async Task Handoffs_CoordSpecCoordPingPong_MergedMessagesPreserveStepOrderAsync()
-    {
-        // Regression test for https://github.com/microsoft/agent-framework/issues/4544 /
-        // https://github.com/microsoft/agent-framework/issues/5720.
-        //
-        // Scenario mirrors the user-reported "Coord -> Spec -> Coord" ping-pong where
-        // the same coordinator agent is invoked twice (first to hand off to the
-        // specialist, then a final time to summarize). Additionally exercises the
-        // case where the specialist returns its assistant text and its handoff
-        // FunctionCall in two SEPARATE ChatMessages (i.e. different MessageIds),
-        // because real OpenAI streams sometimes split text and tool calls that way.
-        //
-        // The merged AgentResponse.Messages must preserve per-step grouping:
-        //   step 1 (Coord):  FunctionCall(call1) then synthesized FunctionResult(call1)
-        //   step 2 (Spec) :  TextContent "Here are recs" then FunctionCall(call2)
-        //                    then synthesized FunctionResult(call2)
-        //   step 3 (Coord):  TextContent "Here are recs"
-        // The bug previously bunched the FunctionResult ("Transferred.") tool messages
-        // at the very end, breaking the contiguity of each step's block.
-
-        int coordCallCount = 0;
-        int specCallCount = 0;
-        var coord = new ChatClientAgent(new MockChatClient((messages, options) =>
-        {
-            coordCallCount++;
-            if (coordCallCount == 1)
-            {
-                string? transferFuncName = options?.Tools?.FirstOrDefault(t => t.Name.StartsWith("handoff_to_", StringComparison.Ordinal))?.Name;
-                Assert.NotNull(transferFuncName);
-                return new(new ChatMessage(ChatRole.Assistant, [new FunctionCallContent("call_coord_1", transferFuncName)]) { MessageId = "coord-msg-1" })
-                {
-                    ResponseId = "resp-coord-1",
-                };
-            }
-
-            // Second (final) Coord turn: emit only assistant text - no tool call.
-            // The test asserts this turn does NOT emit a handoff_to_* FunctionCallContent
-            // and that the workflow terminates here (coordCallCount stays at 2).
-            return new(new ChatMessage(ChatRole.Assistant, "Here are two fake Excel course recommendations") { MessageId = "coord-msg-2" })
-            {
-                ResponseId = "resp-coord-2",
-            };
-        }), name: "Coord");
-
-        var spec = new ChatClientAgent(new MockChatClient((messages, options) =>
-        {
-            specCallCount++;
-            string? transferFuncName = options?.Tools?.FirstOrDefault(t => t.Name.StartsWith("handoff_to_", StringComparison.Ordinal))?.Name;
-            Assert.NotNull(transferFuncName);
-
-            // Split text and FunctionCall into two separate ChatMessages (distinct MessageIds)
-            // to mirror the real-world streaming pattern where a specialist's narration
-            // and its handoff tool-call land in different ChatMessages.
-            return new(
-                [
-                    new ChatMessage(ChatRole.Assistant, "Here are two fake Excel course recommendations") { MessageId = "spec-msg-text" },
-                    new ChatMessage(ChatRole.Assistant, [new FunctionCallContent("call_spec_1", transferFuncName)]) { MessageId = "spec-msg-call" },
-                ])
-            {
-                ResponseId = "resp-spec-1",
-            };
-        }), name: "Spec", description: "The specialist agent");
-
-        var workflow =
-            AgentWorkflowBuilder.CreateHandoffBuilderWith(coord)
-            .WithHandoff(coord, spec)
-            .WithHandoff(spec, coord)
-            .Build();
-
-        AIAgent hostAgent = workflow.AsAIAgent(name: "HandoffWorkflow");
-
-        AgentResponse response = await hostAgent.RunAsync("Tell me about Excel courses.");
-
-        List<ChatMessage> result = response.Messages.ToList();
-
-        // Expected merged sequence keeps each step contiguous (6 messages):
-        //   [0] Assistant (Coord): FunctionCall(call_coord_1)
-        //   [1] Tool      (Coord): FunctionResult(call_coord_1, "Transferred.")
-        //   [2] Assistant (Spec) : TextContent "Here are recs"
-        //   [3] Assistant (Spec) : FunctionCall(call_spec_1)
-        //   [4] Tool      (Spec) : FunctionResult(call_spec_1, "Transferred.")
-        //   [5] Assistant (Coord): TextContent "Here are recs"
-        Assert.Equal(6, result.Count);
-
-        Assert.Equal(ChatRole.Assistant, result[0].Role);
-        Assert.Contains("Coord", result[0].AuthorName);
-        Assert.Contains(result[0].Contents, c => c is FunctionCallContent fcc && fcc.CallId == "call_coord_1");
-
-        Assert.Equal(ChatRole.Tool, result[1].Role);
-        Assert.Contains("Coord", result[1].AuthorName);
-        Assert.Contains(result[1].Contents, c => c is FunctionResultContent frc && frc.CallId == "call_coord_1");
-
-        Assert.Equal(ChatRole.Assistant, result[2].Role);
-        Assert.Contains("Spec", result[2].AuthorName);
-        Assert.Equal("Here are two fake Excel course recommendations", result[2].Text);
-
-        Assert.Equal(ChatRole.Assistant, result[3].Role);
-        Assert.Contains("Spec", result[3].AuthorName);
-        Assert.Contains(result[3].Contents, c => c is FunctionCallContent fcc && fcc.CallId == "call_spec_1");
-
-        Assert.Equal(ChatRole.Tool, result[4].Role);
-        Assert.Contains("Spec", result[4].AuthorName);
-        Assert.Contains(result[4].Contents, c => c is FunctionResultContent frc && frc.CallId == "call_spec_1");
-
-        Assert.Equal(ChatRole.Assistant, result[5].Role);
-        Assert.Contains("Coord", result[5].AuthorName);
-        Assert.Equal("Here are two fake Excel course recommendations", result[5].Text);
-
-        // Final Coord turn must emit ONLY assistant text - no further handoff/tool call.
-        Assert.DoesNotContain(result[5].Contents, c => c is FunctionCallContent);
-
-        // And the workflow must have terminated after that turn - no extra Coord/Spec re-invocations.
-        Assert.Equal(2, coordCallCount);
-        Assert.Equal(1, specCallCount);
-    }
-
     [Fact]
     public async Task Handoffs_FilteringNone_HandoffTargetReceivesAllMessagesIncludingToolCallsAsync()
     {
@@ -1430,44 +1198,6 @@ public class HandoffOrchestrationTests
         Workflow workflow, List<ChatMessage> input, ExecutionEnvironment executionEnvironment = ExecutionEnvironment.InProcess_Lockstep)
         => RunWorkflowCheckpointedAsync(workflow, input, executionEnvironment.ToWorkflowExecutionEnvironment());
 
-    private sealed class CapturingAgent(string name, string description, string textToCapture) : AIAgent
-    {
-        public override string Name => name;
-        public override string Description => description;
-        public ChatMessage? MessageSeenDuringRun { get; private set; }
-        public ChatRole? RoleSeenDuringRun { get; private set; }
-
-        protected override ValueTask<AgentSession> CreateSessionCoreAsync(CancellationToken cancellationToken = default)
-            => new(new TestAgentSession());
-
-        protected override ValueTask<AgentSession> DeserializeSessionCoreAsync(JsonElement serializedState, JsonSerializerOptions? jsonSerializerOptions = null, CancellationToken cancellationToken = default)
-            => new(new TestAgentSession());
-
-        protected override ValueTask<JsonElement> SerializeSessionCoreAsync(AgentSession session, JsonSerializerOptions? jsonSerializerOptions = null, CancellationToken cancellationToken = default)
-            => default;
-
-        protected override Task<AgentResponse> RunCoreAsync(
-            IEnumerable<ChatMessage> messages, AgentSession? session = null, AgentRunOptions? options = null, CancellationToken cancellationToken = default) =>
-            throw new NotImplementedException();
-
-        protected override async IAsyncEnumerable<AgentResponseUpdate> RunCoreStreamingAsync(
-            IEnumerable<ChatMessage> messages, AgentSession? session = null, AgentRunOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
-        {
-            await Task.Yield();
-
-            this.MessageSeenDuringRun = messages.Single(m => m.Text == textToCapture);
-            this.RoleSeenDuringRun = this.MessageSeenDuringRun.Role;
-
-            yield return new AgentResponseUpdate(ChatRole.Assistant, "Done")
-            {
-                AuthorName = this.Name,
-                MessageId = Guid.NewGuid().ToString("N"),
-            };
-        }
-    }
-
-    private sealed class TestAgentSession() : AgentSession();
-
     private sealed class DoubleEchoAgent(string name) : AIAgent
     {
         public override string Name => name;

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/InputWaiterAndOutputFilterTests.cs

@@ -36,18 +36,13 @@ public sealed class InputWaiterTests : IDisposable
     {
         Task waitTask = this._waiter.WaitForInputAsync(TimeSpan.FromSeconds(5));
 
-        Task completedBeforeSignal = await Task.WhenAny(waitTask, Task.Delay(100));
-        completedBeforeSignal.Should().NotBeSameAs(
-            waitTask,
-            "the waiter should not complete before input is signaled");
+        await Task.Delay(50);
+        waitTask.IsCompleted.Should().BeFalse("the waiter should block until input is signaled");
 
         this._waiter.SignalInput();
 
-        Task completedAfterSignal = await Task.WhenAny(waitTask, Task.Delay(TimeSpan.FromSeconds(1)));
-        completedAfterSignal.Should().BeSameAs(
-            waitTask,
-            "the wait task should complete after being signaled");
-
+        Task completed = await Task.WhenAny(waitTask, Task.Delay(TimeSpan.FromSeconds(1)));
+        completed.Should().BeSameAs(waitTask, "the wait task should complete after being signaled");
         await waitTask;
     }
 

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/MessageMergerTests.cs

@@ -1,7 +1,6 @@
 // Copyright (c) Microsoft. All rights reserved.
 
 using System;
-using System.Linq;
 using FluentAssertions;
 using Microsoft.Extensions.AI;
 
@@ -43,47 +42,6 @@ public class MessageMergerTests
         response.FinishReason.Should().BeNull();
     }
 
-    [Fact]
-    public void Test_MessageMerger_PreservesFunctionCallOrderingWhenToolResultHasCreatedAt()
-    {
-        // Arrange
-        string responseId = Guid.NewGuid().ToString("N");
-        string functionCallMessageId = Guid.NewGuid().ToString("N");
-        string functionResultMessageId = Guid.NewGuid().ToString("N");
-        string callId = Guid.NewGuid().ToString("N");
-        DateTimeOffset toolResultCreatedAt = DateTimeOffset.UtcNow;
-
-        MessageMerger merger = new();
-
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = functionCallMessageId,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new FunctionCallContent(callId, "handoff_to_TestAgent2")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = functionResultMessageId,
-            AgentId = TestAgentId1,
-            CreatedAt = toolResultCreatedAt,
-            Role = ChatRole.Tool,
-            Contents = [new FunctionResultContent(callId, "Transferred.")],
-        });
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(responseId);
-
-        // Assert
-        response.Messages.Should().HaveCount(2);
-        response.Messages[0].Role.Should().Be(ChatRole.Assistant);
-        response.Messages[0].Contents.Should().ContainSingle().Which.Should().BeOfType<FunctionCallContent>();
-        response.Messages[1].Role.Should().Be(ChatRole.Tool);
-        response.Messages[1].Contents.Should().ContainSingle().Which.Should().BeOfType<FunctionResultContent>();
-    }
-
     [Fact]
     public void Test_MessageMerger_PropagatesFinishReasonFromUpdates()
     {
@@ -113,494 +71,4 @@ public class MessageMergerTests
         // Assert - FinishReason from the update should propagate through
         response.FinishReason.Should().Be(ChatFinishReason.ContentFilter);
     }
-
-    #region Invariant 2: Output Order Preservation Tests
-
-    [Fact]
-    public void Test_MessageMerger_PreservesInsertionOrder_WhenNoTimestamps()
-    {
-        // Arrange: Multiple updates without CreatedAt, in specific order A, B, C
-        string responseId = Guid.NewGuid().ToString("N");
-        string messageIdA = Guid.NewGuid().ToString("N");
-        string messageIdB = Guid.NewGuid().ToString("N");
-        string messageIdC = Guid.NewGuid().ToString("N");
-
-        MessageMerger merger = new();
-
-        // Add updates without CreatedAt in order A, B, C
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdA,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Message A")],
-            // No CreatedAt
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdB,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Message B")],
-            // No CreatedAt
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdC,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Message C")],
-            // No CreatedAt
-        });
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(responseId);
-
-        // Assert: Output order should be A, B, C (insertion order)
-        response.Messages.Should().HaveCount(3);
-        response.Messages[0].Text.Should().Be("Message A");
-        response.Messages[1].Text.Should().Be("Message B");
-        response.Messages[2].Text.Should().Be("Message C");
-    }
-
-    [Fact]
-    public void Test_MessageMerger_PreservesInsertionOrder_WhenMixedTimestamps()
-    {
-        // Arrange: Updates with OUT-OF-ORDER timestamps relative to emission order.
-        // Emission order: A, B, C.
-        // Timestamp order: C (oldest), A, B (newest) - reverse of emission.
-        // Per Invariant 2, emission order wins; timestamps are ignored for ordering.
-        string responseId = Guid.NewGuid().ToString("N");
-        string messageIdA = Guid.NewGuid().ToString("N");
-        string messageIdB = Guid.NewGuid().ToString("N");
-        string messageIdC = Guid.NewGuid().ToString("N");
-
-        DateTimeOffset timeOldest = DateTimeOffset.UtcNow.AddMinutes(-10);
-        DateTimeOffset timeMiddle = DateTimeOffset.UtcNow.AddMinutes(-5);
-        DateTimeOffset timeNewest = DateTimeOffset.UtcNow;
-
-        MessageMerger merger = new();
-
-        // Emit A first but stamp it with timeMiddle.
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdA,
-            Role = ChatRole.Assistant,
-            CreatedAt = timeMiddle,
-            Contents = [new TextContent("Message A")],
-        });
-        // Emit B second, without a timestamp.
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdB,
-            Role = ChatRole.Assistant,
-            // No CreatedAt
-            Contents = [new TextContent("Message B")],
-        });
-        // Emit C third but stamp it with timeOldest - if we sorted by timestamp,
-        // C would come first; the new merger MUST keep emission order (A, B, C).
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdC,
-            Role = ChatRole.Assistant,
-            CreatedAt = timeOldest,
-            Contents = [new TextContent("Message C")],
-        });
-        // Stamp a fourth message with the newest timestamp - it should still come last
-        // because it was emitted last, not because of its timestamp.
-        string messageIdD = Guid.NewGuid().ToString("N");
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdD,
-            Role = ChatRole.Assistant,
-            CreatedAt = timeNewest,
-            Contents = [new TextContent("Message D")],
-        });
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(responseId);
-
-        // Assert: Emission order wins; CreatedAt is ignored for ordering.
-        response.Messages.Should().HaveCount(4);
-        response.Messages[0].Text.Should().Be("Message A");
-        response.Messages[1].Text.Should().Be("Message B");
-        response.Messages[2].Text.Should().Be("Message C");
-        response.Messages[3].Text.Should().Be("Message D");
-    }
-
-    [Fact]
-    public void Test_MessageMerger_ReproducibleOrdering_WithMixedTimestamps()
-    {
-        // Arrange: 3+ messages with mixed null/non-null CreatedAt values
-        // This tests that the same input sequence produces the same output
-        // (run-to-run reproducibility for a fixed input)
-        string responseId = Guid.NewGuid().ToString("N");
-        string messageIdA = Guid.NewGuid().ToString("N");
-        string messageIdB = Guid.NewGuid().ToString("N");
-        string messageIdC = Guid.NewGuid().ToString("N");
-
-        DateTimeOffset time10 = DateTimeOffset.UtcNow.AddSeconds(10);
-        DateTimeOffset time5 = DateTimeOffset.UtcNow.AddSeconds(5);
-
-        MessageMerger merger = new();
-
-        // A: CreatedAt = time10, idx=0
-        // B: CreatedAt = null, idx=1
-        // C: CreatedAt = time5, idx=2
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdA,
-            Role = ChatRole.Assistant,
-            CreatedAt = time10,
-            Contents = [new TextContent("Message A (T=10)")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdB,
-            Role = ChatRole.Assistant,
-            // No CreatedAt
-            Contents = [new TextContent("Message B (no timestamp)")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdC,
-            Role = ChatRole.Assistant,
-            CreatedAt = time5,
-            Contents = [new TextContent("Message C (T=5)")],
-        });
-
-        // Act - Run multiple times to verify reproducibility
-        AgentResponse response1 = merger.ComputeMerged(responseId);
-
-        // Create a fresh merger with same data to verify reproducibility
-        MessageMerger merger2 = new();
-        merger2.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdA,
-            Role = ChatRole.Assistant,
-            CreatedAt = time10,
-            Contents = [new TextContent("Message A (T=10)")],
-        });
-        merger2.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdB,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Message B (no timestamp)")],
-        });
-        merger2.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseId,
-            MessageId = messageIdC,
-            Role = ChatRole.Assistant,
-            CreatedAt = time5,
-            Contents = [new TextContent("Message C (T=5)")],
-        });
-        AgentResponse response2 = merger2.ComputeMerged(responseId);
-
-        // Assert: Result is reproducible and consistent across runs with same input order.
-        // Per Invariant 2, both runs must produce emission order (A, B, C) regardless
-        // of the messages' CreatedAt values.
-        response1.Messages.Should().HaveCount(3);
-        response2.Messages.Should().HaveCount(3);
-
-        response1.Messages.Select(m => m.Text).Should().ContainInOrder(
-            "Message A (T=10)", "Message B (no timestamp)", "Message C (T=5)");
-
-        // Both runs should produce identical ordering
-        for (int i = 0; i < 3; i++)
-        {
-            response1.Messages[i].Text.Should().Be(response2.Messages[i].Text);
-        }
-    }
-
-    #endregion
-
-    #region Invariant 3: Agent Message Grouping Tests
-
-    [Fact]
-    public void Test_MessageMerger_GroupsMessagesByResponseId_InMultiAgentScenario()
-    {
-        // Arrange: Interleaved updates from Agent1 (R1) and Agent2 (R2)
-        string responseIdR1 = Guid.NewGuid().ToString("N");
-        string responseIdR2 = Guid.NewGuid().ToString("N");
-        string messageIdA1M1 = Guid.NewGuid().ToString("N");
-        string messageIdA1M2 = Guid.NewGuid().ToString("N");
-        string messageIdA2M1 = Guid.NewGuid().ToString("N");
-        string messageIdA2M2 = Guid.NewGuid().ToString("N");
-
-        MessageMerger merger = new();
-
-        // Interleaved arrival: A1-msg1, A2-msg1, A1-msg2, A2-msg2
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR1,
-            MessageId = messageIdA1M1,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent1 Message 1")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR2,
-            MessageId = messageIdA2M1,
-            AgentId = TestAgentId2,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent2 Message 1")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR1,
-            MessageId = messageIdA1M2,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent1 Message 2")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR2,
-            MessageId = messageIdA2M2,
-            AgentId = TestAgentId2,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent2 Message 2")],
-        });
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(responseIdR1);
-
-        // Assert: Messages should be grouped by ResponseId (which groups by agent)
-        // Output should be either [A1-msg1, A1-msg2, A2-msg1, A2-msg2] or [A2-msg1, A2-msg2, A1-msg1, A1-msg2]
-        // The key invariant: Agent1's messages are contiguous, Agent2's messages are contiguous
-        response.Messages.Should().HaveCount(4);
-
-        // Verify grouping - collect message texts and verify they're grouped by agent
-        var messageTexts = response.Messages.Select(m => m.Text).ToList();
-
-        // Find first Agent1 message index and first Agent2 message index
-        int firstA1Index = messageTexts.FindIndex(t => t.StartsWith("Agent1", StringComparison.Ordinal));
-        int firstA2Index = messageTexts.FindIndex(t => t.StartsWith("Agent2", StringComparison.Ordinal));
-
-        // Assert both indices are valid (messages were found)
-        firstA1Index.Should().BeGreaterThanOrEqualTo(0, "Agent1 messages should be present in response");
-        firstA2Index.Should().BeGreaterThanOrEqualTo(0, "Agent2 messages should be present in response");
-
-        // All Agent1 messages should be contiguous (either at start or after all Agent2 messages)
-        var a1Messages = messageTexts.Where(t => t.StartsWith("Agent1", StringComparison.Ordinal)).ToList();
-        var a2Messages = messageTexts.Where(t => t.StartsWith("Agent2", StringComparison.Ordinal)).ToList();
-
-        a1Messages.Should().HaveCount(2);
-        a2Messages.Should().HaveCount(2);
-
-        // Verify no interleaving: if A1 comes first, A2 should come after all A1 messages
-        if (firstA1Index < firstA2Index)
-        {
-            // A1 messages at indices 0, 1 and A2 messages at indices 2, 3
-            messageTexts[0].Should().StartWith("Agent1");
-            messageTexts[1].Should().StartWith("Agent1");
-            messageTexts[2].Should().StartWith("Agent2");
-            messageTexts[3].Should().StartWith("Agent2");
-        }
-        else
-        {
-            // A2 messages at indices 0, 1 and A1 messages at indices 2, 3
-            messageTexts[0].Should().StartWith("Agent2");
-            messageTexts[1].Should().StartWith("Agent2");
-            messageTexts[2].Should().StartWith("Agent1");
-            messageTexts[3].Should().StartWith("Agent1");
-        }
-    }
-
-    [Fact]
-    public void Test_MessageMerger_MaintainsAgentGrouping_WithDifferentResponseIds()
-    {
-        // Arrange: Agent1 uses ResponseId=R1, Agent2 uses ResponseId=R2
-        // Multiple messages per ResponseId to properly test contiguity
-        string responseIdR1 = Guid.NewGuid().ToString("N");
-        string responseIdR2 = Guid.NewGuid().ToString("N");
-        string messageIdA1M1 = Guid.NewGuid().ToString("N");
-        string messageIdA1M2 = Guid.NewGuid().ToString("N");
-        string messageIdA1M3 = Guid.NewGuid().ToString("N");
-        string messageIdA2M1 = Guid.NewGuid().ToString("N");
-        string messageIdA2M2 = Guid.NewGuid().ToString("N");
-        string messageIdA2M3 = Guid.NewGuid().ToString("N");
-
-        MessageMerger merger = new();
-
-        // Interleaved arrival: A1-1, A2-1, A1-2, A2-2, A1-3, A2-3
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR1,
-            MessageId = messageIdA1M1,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent1 Response 1")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR2,
-            MessageId = messageIdA2M1,
-            AgentId = TestAgentId2,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent2 Response 1")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR1,
-            MessageId = messageIdA1M2,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent1 Response 2")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR2,
-            MessageId = messageIdA2M2,
-            AgentId = TestAgentId2,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent2 Response 2")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR1,
-            MessageId = messageIdA1M3,
-            AgentId = TestAgentId1,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent1 Response 3")],
-        });
-        merger.AddUpdate(new AgentResponseUpdate
-        {
-            ResponseId = responseIdR2,
-            MessageId = messageIdA2M3,
-            AgentId = TestAgentId2,
-            Role = ChatRole.Assistant,
-            Contents = [new TextContent("Agent2 Response 3")],
-        });
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(responseIdR1);
-
-        // Assert: Messages from each agent are contiguous (not interleaved)
-        response.Messages.Should().HaveCount(6);
-
-        var messageTexts = response.Messages.Select(m => m.Text).ToList();
-
-        // Verify all messages are present
-        messageTexts.Should().Contain("Agent1 Response 1");
-        messageTexts.Should().Contain("Agent1 Response 2");
-        messageTexts.Should().Contain("Agent1 Response 3");
-        messageTexts.Should().Contain("Agent2 Response 1");
-        messageTexts.Should().Contain("Agent2 Response 2");
-        messageTexts.Should().Contain("Agent2 Response 3");
-
-        // Find indices to verify contiguity
-        int firstA1Index = messageTexts.FindIndex(t => t.StartsWith("Agent1", StringComparison.Ordinal));
-        int lastA1Index = messageTexts.FindLastIndex(t => t.StartsWith("Agent1", StringComparison.Ordinal));
-        int firstA2Index = messageTexts.FindIndex(t => t.StartsWith("Agent2", StringComparison.Ordinal));
-        int lastA2Index = messageTexts.FindLastIndex(t => t.StartsWith("Agent2", StringComparison.Ordinal));
-
-        // Assert indices are valid
-        firstA1Index.Should().BeGreaterThanOrEqualTo(0, "Agent1 messages should be present");
-        firstA2Index.Should().BeGreaterThanOrEqualTo(0, "Agent2 messages should be present");
-
-        // Verify contiguity: all Agent1 messages should span exactly 3 consecutive indices
-        (lastA1Index - firstA1Index).Should().Be(2, "Agent1 messages should be contiguous (3 messages spanning 2 index gaps)");
-        (lastA2Index - firstA2Index).Should().Be(2, "Agent2 messages should be contiguous (3 messages spanning 2 index gaps)");
-
-        // Verify no interleaving: ranges should not overlap
-        bool a1BeforeA2 = lastA1Index < firstA2Index;
-        bool a2BeforeA1 = lastA2Index < firstA1Index;
-        (a1BeforeA2 || a2BeforeA1).Should().BeTrue("Agent message blocks should not interleave");
-    }
-
-    #endregion
-
-    #region Step Ordering Tests (workflow goals)
-
-    [Fact]
-    public void Test_MessageMerger_OrdersStepsBeforeNextStep_AndGroupsAgentsWithinStep()
-    {
-        // Scenario mirroring the workflow ordering goals:
-        //   Step 1: Agent1 alone emits 2 updates.
-        //   Step 2: Agent1 and Agent2 emit updates interleaved (concurrent in the step).
-        //   Step 3: Agent2 alone emits 2 updates.
-        // Each agent invocation has its own ResponseId, so per-ResponseId grouping
-        // yields per-agent grouping. Steps are naturally serialized in emission
-        // order (the next step cannot emit until the prior step's updates arrive),
-        // so the first-seen-ResponseId ordering preserves step boundaries.
-        const string step1Agent1 = "step1-agent1";
-        const string step2Agent1 = "step2-agent1";
-        const string step2Agent2 = "step2-agent2";
-        const string step3Agent2 = "step3-agent2";
-
-        MessageMerger merger = new();
-
-        // Step 1: Agent1 emits 2 messages.
-        AddSimpleUpdate(merger, step1Agent1, TestAgentId1, "S1-A1-m1");
-        AddSimpleUpdate(merger, step1Agent1, TestAgentId1, "S1-A1-m2");
-
-        // Step 2: Agent1 and Agent2 emit interleaved (A1, A2, A1, A2).
-        AddSimpleUpdate(merger, step2Agent1, TestAgentId1, "S2-A1-m1");
-        AddSimpleUpdate(merger, step2Agent2, TestAgentId2, "S2-A2-m1");
-        AddSimpleUpdate(merger, step2Agent1, TestAgentId1, "S2-A1-m2");
-        AddSimpleUpdate(merger, step2Agent2, TestAgentId2, "S2-A2-m2");
-
-        // Step 3: Agent2 emits 2 messages.
-        AddSimpleUpdate(merger, step3Agent2, TestAgentId2, "S3-A2-m1");
-        AddSimpleUpdate(merger, step3Agent2, TestAgentId2, "S3-A2-m2");
-
-        // Act
-        AgentResponse response = merger.ComputeMerged(step1Agent1);
-
-        // Assert: expected output order
-        //   Step 1 block (Agent1):  S1-A1-m1, S1-A1-m2
-        //   Step 2 Agent1 block:    S2-A1-m1, S2-A1-m2
-        //   Step 2 Agent2 block:    S2-A2-m1, S2-A2-m2
-        //   Step 3 block (Agent2):  S3-A2-m1, S3-A2-m2
-        response.Messages.Should().HaveCount(8);
-        var texts = response.Messages.Select(m => m.Text).ToList();
-        texts.Should().ContainInOrder(
-            "S1-A1-m1", "S1-A1-m2",
-            "S2-A1-m1", "S2-A1-m2",
-            "S2-A2-m1", "S2-A2-m2",
-            "S3-A2-m1", "S3-A2-m2");
-
-        // Step boundaries: no step-2 or step-3 message may appear before the last step-1 message.
-        int lastStep1Index = texts.FindLastIndex(t => t.StartsWith("S1-", StringComparison.Ordinal));
-        int firstStep2Index = texts.FindIndex(t => t.StartsWith("S2-", StringComparison.Ordinal));
-        int lastStep2Index = texts.FindLastIndex(t => t.StartsWith("S2-", StringComparison.Ordinal));
-        int firstStep3Index = texts.FindIndex(t => t.StartsWith("S3-", StringComparison.Ordinal));
-        lastStep1Index.Should().BeLessThan(firstStep2Index, "all step-1 messages precede step-2");
-        lastStep2Index.Should().BeLessThan(firstStep3Index, "all step-2 messages precede step-3");
-
-        // Within step 2 (multi-agent), per-agent blocks must be contiguous.
-        int firstS2A1 = texts.FindIndex(t => t.StartsWith("S2-A1", StringComparison.Ordinal));
-        int lastS2A1 = texts.FindLastIndex(t => t.StartsWith("S2-A1", StringComparison.Ordinal));
-        int firstS2A2 = texts.FindIndex(t => t.StartsWith("S2-A2", StringComparison.Ordinal));
-        int lastS2A2 = texts.FindLastIndex(t => t.StartsWith("S2-A2", StringComparison.Ordinal));
-        (lastS2A1 - firstS2A1).Should().Be(1, "Agent1 step-2 messages should be contiguous");
-        (lastS2A2 - firstS2A2).Should().Be(1, "Agent2 step-2 messages should be contiguous");
-        (lastS2A1 < firstS2A2 || lastS2A2 < firstS2A1).Should().BeTrue("agent blocks within a step must not interleave");
-
-        static void AddSimpleUpdate(MessageMerger m, string responseId, string agentId, string text)
-        {
-            m.AddUpdate(new AgentResponseUpdate
-            {
-                ResponseId = responseId,
-                MessageId = Guid.NewGuid().ToString("N"),
-                AgentId = agentId,
-                Role = ChatRole.Assistant,
-                Contents = [new TextContent(text)],
-            });
-        }
-    }
-
-    #endregion
 }

dotnet/tests/Microsoft.Agents.AI.Workflows.UnitTests/WorkflowEvaluationTests.cs

@@ -1,6 +1,5 @@
 // Copyright (c) Microsoft. All rights reserved.
 
-using System;
 using System.Collections.Generic;
 using System.Threading.Tasks;
 using Microsoft.Extensions.AI;
@@ -291,121 +290,6 @@ public sealed class WorkflowEvaluationTests
         Assert.DoesNotContain("end", result.Keys);
     }
 
-    // ---------------------------------------------------------------
-    // BuildOverallItem tests (expected output / ground truth)
-    // ---------------------------------------------------------------
-
-    [Fact]
-    public void BuildOverallItem_NoCompletedExecutorWithResponse_ReturnsNull()
-    {
-        // Arrange — no ExecutorCompletedEvent with usable response data and no AgentResponseEvent
-        var events = new List<WorkflowEvent>
-        {
-            new ExecutorInvokedEvent("agent-1", "query"),
-        };
-
-        // Act
-        var item = WorkflowEvaluationExtensions.BuildOverallItem(events, splitter: null, expectedOutput: null);
-
-        // Assert
-        Assert.Null(item);
-    }
-
-    [Fact]
-    public void BuildOverallItem_NoAgentResponseEvent_FallsBackToLastExecutorCompleted()
-    {
-        // Arrange — only ExecutorCompletedEvent (the default when EmitAgentResponseEvents is false)
-        var finalResponse = new AgentResponse(new ChatMessage(ChatRole.Assistant, "Paris"));
-        var events = new List<WorkflowEvent>
-        {
-            new ExecutorInvokedEvent("researcher", "What is the capital of France?"),
-            new ExecutorCompletedEvent("researcher", new AgentResponse(new ChatMessage(ChatRole.Assistant, "draft"))),
-            new ExecutorInvokedEvent("editor", "draft"),
-            new ExecutorCompletedEvent("editor", finalResponse),
-        };
-
-        // Act
-        var item = WorkflowEvaluationExtensions.BuildOverallItem(
-            events, splitter: null, expectedOutput: "Paris");
-
-        // Assert
-        Assert.NotNull(item);
-        Assert.Equal("What is the capital of France?", item.Query);
-        Assert.Equal("Paris", item.Response);
-        Assert.Equal("Paris", item.ExpectedOutput);
-    }
-
-    [Fact]
-    public void BuildOverallItem_WithFinalResponseAndExpectedOutput_StampsExpectedOutput()
-    {
-        // Arrange
-        var finalResponse = new AgentResponse(new ChatMessage(ChatRole.Assistant, "Ofrece 41 planes"));
-        var events = new List<WorkflowEvent>
-        {
-            new ExecutorInvokedEvent("agent-1", "How many plans does Netlife offer?"),
-            new ExecutorCompletedEvent("agent-1", finalResponse),
-            new AgentResponseEvent("agent-1", finalResponse),
-        };
-
-        // Act
-        var item = WorkflowEvaluationExtensions.BuildOverallItem(
-            events, splitter: null, expectedOutput: "Ofrece 41 planes");
-
-        // Assert
-        Assert.NotNull(item);
-        Assert.Equal("How many plans does Netlife offer?", item.Query);
-        Assert.Equal("Ofrece 41 planes", item.Response);
-        Assert.Equal("Ofrece 41 planes", item.ExpectedOutput);
-    }
-
-    [Fact]
-    public void BuildOverallItem_WithFinalResponseAndNoExpectedOutput_LeavesExpectedOutputNull()
-    {
-        // Arrange
-        var finalResponse = new AgentResponse(new ChatMessage(ChatRole.Assistant, "answer"));
-        var events = new List<WorkflowEvent>
-        {
-            new ExecutorInvokedEvent("agent-1", "query"),
-            new ExecutorCompletedEvent("agent-1", finalResponse),
-            new AgentResponseEvent("agent-1", finalResponse),
-        };
-
-        // Act
-        var item = WorkflowEvaluationExtensions.BuildOverallItem(events, splitter: null, expectedOutput: null);
-
-        // Assert
-        Assert.NotNull(item);
-        Assert.Null(item.ExpectedOutput);
-    }
-
-    [Fact]
-    public async Task EvaluateAsync_WithIncludeOverallButNoFinalResponse_ThrowsAsync()
-    {
-        // Arrange — build a workflow whose AIAgentHostExecutor is NOT bound with
-        // EmitAgentResponseEvents=true, so no AgentResponseEvent is emitted, and the
-        // ExecutorCompletedEvent for the host carries null Data. That is the scenario
-        // where BuildOverallItem returns null. When the caller asks for an overall
-        // evaluation (includeOverall: true), we should fail fast rather than silently
-        // returning empty results — regardless of whether expectedOutput was supplied.
-        var agent = new TestEchoAgent(name: "echo");
-        var workflow = AgentWorkflowBuilder.BuildSequential(agent);
-        var input = new List<ChatMessage> { new(ChatRole.User, "Hello") };
-
-        var evaluator = new LocalEvaluator(
-            FunctionEvaluator.Create("noop", (EvalItem _) => true));
-
-        await using var run = await InProcessExecution.RunAsync(workflow, input);
-
-        // Act + Assert — throws even without expectedOutput
-        var ex = await Assert.ThrowsAsync<InvalidOperationException>(() =>
-            run.EvaluateAsync(
-                evaluator,
-                includeOverall: true,
-                includePerAgent: false));
-
-        Assert.Contains("EmitAgentResponseEvents", ex.Message);
-    }
-
     // ---------------------------------------------------------------
     // EvaluateAsync integration test
     // ---------------------------------------------------------------

python/packages/ag-ui/README.md

@@ -99,30 +99,6 @@ The `AGUIChatClient` supports:
 - Integration with `Agent` for client-side history management
 - Interrupt metadata passthrough (`availableInterrupts` and `resume`)
 
-## Tool Return Helpers
-
-Use `state_update` when a backend tool needs to send different payloads to the model, the UI, and shared state. The `text` value remains the LLM-bound tool result, `tool_result` becomes the AG-UI `ToolCallResultEvent.content` for frontend rendering, and `state` is merged into durable shared state.
-
-```python
-from agent_framework import Content, tool
-from agent_framework.ag_ui import state_update
-
-@tool
-async def get_weather(city: str) -> Content:
-    data = await fetch_weather(city)
-    return state_update(
-        text=f"{city}: {data['temp']}°C and {data['conditions']}",
-        tool_result={
-            "component": "weather-card",
-            "city": city,
-            "temperature": data["temp"],
-            "conditions": data["conditions"],
-            "humidity": data["humidity"],
-        },
-        state={"weather": {"city": city, **data}},
-    )
-```
-
 ## Documentation
 
 - **[Getting Started Tutorial](getting_started/)** - Step-by-step guide to building AG-UI servers and clients

python/packages/ag-ui/agent_framework_ag_ui/_agent_run.py

@@ -49,11 +49,8 @@ from ._run_common import (
     _close_reasoning_block,  # type: ignore
     _emit_content,  # type: ignore
     _extract_resume_payload,  # type: ignore
-    _extract_tool_result_display,  # type: ignore
     _has_only_tool_calls,  # type: ignore
     _normalize_resume_interrupts,  # type: ignore
-    _resolve_ui_payload,  # type: ignore
-    _stringify_tool_result,  # type: ignore
 )
 from ._utils import (
     convert_agui_tools_to_agent_framework,
@@ -384,23 +381,17 @@ def _handle_step_based_approval(messages: list[Any]) -> list[BaseEvent]:
 
 
 def _make_approval_tool_result_events(resolved_approval_results: list[Content]) -> list[ToolCallResultEvent]:
-    """Build TOOL_CALL_RESULT events for tools executed during approval resolution.
-
-    Honors ``TOOL_RESULT_DISPLAY_KEY`` so tools returning
-    ``state_update(..., tool_result=...)`` route the display payload to the UI
-    event even when gated by HITL approval.
-    """
+    """Build TOOL_CALL_RESULT events for tools executed during approval resolution."""
     events: list[ToolCallResultEvent] = []
     for resolved in resolved_approval_results:
         if resolved.call_id:
             raw = resolved.result if resolved.result is not None else ""
-            llm_str = _stringify_tool_result(raw)
-            ui_str = _resolve_ui_payload(llm_str, _extract_tool_result_display(resolved))
+            result_str = raw if isinstance(raw, str) else json.dumps(make_json_safe(raw))
             events.append(
                 ToolCallResultEvent(
                     message_id=generate_event_id(),
                     tool_call_id=resolved.call_id,
-                    content=ui_str,
+                    content=result_str,
                     role="tool",
                 )
             )

python/packages/ag-ui/agent_framework_ag_ui/_run_common.py

@@ -32,14 +32,11 @@ from ag_ui.core import (
 from agent_framework import Content
 
 from ._orchestration._predictive_state import PredictiveStateHandler
-from ._state import TOOL_RESULT_DISPLAY_KEY, TOOL_RESULT_STATE_KEY
+from ._state import TOOL_RESULT_STATE_KEY
 from ._utils import generate_event_id, make_json_safe
 
 logger = logging.getLogger(__name__)
 
-# Sentinel for an unset display_result; distinguishes "caller didn't pass" from None/{}/"".
-_UNSET = object()
-
 
 def _has_only_tool_calls(contents: list[Any]) -> bool:
     """Check if contents have only tool calls (no text)."""
@@ -238,22 +235,6 @@ def _emit_tool_call(
     return events
 
 
-def _extract_tool_result_marker_values(content: Content, key: str) -> list[Any]:
-    """Extract marker values from outer and inner tool-result content."""
-    values: list[Any] = []
-
-    outer_ap = getattr(content, "additional_properties", None) or {}
-    if key in outer_ap:
-        values.append(outer_ap[key])
-
-    for item in content.items or ():
-        item_ap = getattr(item, "additional_properties", None) or {}
-        if key in item_ap:
-            values.append(item_ap[key])
-
-    return values
-
-
 def _extract_tool_result_state(content: Content) -> dict[str, Any] | None:
     """Extract a deterministic AG-UI state update from a tool-result ``Content``.
 
@@ -271,7 +252,14 @@ def _extract_tool_result_state(content: Content) -> dict[str, Any] | None:
     """
     merged: dict[str, Any] | None = None
 
-    for item_state in _extract_tool_result_marker_values(content, TOOL_RESULT_STATE_KEY):
+    outer_ap = getattr(content, "additional_properties", None) or {}
+    outer_state = outer_ap.get(TOOL_RESULT_STATE_KEY)
+    if isinstance(outer_state, dict):
+        merged = dict(outer_state)
+
+    for item in content.items or ():
+        item_ap = getattr(item, "additional_properties", None) or {}
+        item_state = item_ap.get(TOOL_RESULT_STATE_KEY)
         if isinstance(item_state, dict):
             if merged is None:
                 merged = dict(item_state)
@@ -281,21 +269,6 @@ def _extract_tool_result_state(content: Content) -> dict[str, Any] | None:
     return merged
 
 
-def _extract_tool_result_display(content: Content) -> Any:  # noqa: ANN401
-    """Extract a UI-only AG-UI tool result display payload, if present."""
-    display_values = _extract_tool_result_marker_values(content, TOOL_RESULT_DISPLAY_KEY)
-    return display_values[-1] if display_values else _UNSET
-
-
-def _stringify_tool_result(raw_result: Any) -> str:  # noqa: ANN401
-    return raw_result if isinstance(raw_result, str) else json.dumps(make_json_safe(raw_result))
-
-
-def _resolve_ui_payload(llm_str: str, display_result: Any) -> str:  # noqa: ANN401
-    """Pick the UI-bound string: the serialized display payload when set, else the LLM string."""
-    return llm_str if display_result is _UNSET else _stringify_tool_result(display_result)
-
-
 def _emit_tool_result_common(
     call_id: str,
     raw_result: Any,
@@ -303,7 +276,6 @@ def _emit_tool_result_common(
     predictive_handler: PredictiveStateHandler | None = None,
     *,
     state_update: Mapping[str, Any] | None = None,
-    display_result: Any = _UNSET,  # noqa: ANN401
 ) -> list[BaseEvent]:
     """Shared helper for emitting ToolCallEnd + ToolCallResult events and performing FlowState cleanup.
 
@@ -329,14 +301,13 @@ def _emit_tool_result_common(
     events.append(ToolCallEndEvent(tool_call_id=call_id))
     flow.tool_calls_ended.add(call_id)
 
-    result_content = _stringify_tool_result(raw_result)
-    ui_result_content = _resolve_ui_payload(result_content, display_result)
+    result_content = raw_result if isinstance(raw_result, str) else json.dumps(make_json_safe(raw_result))
     message_id = generate_event_id()
     events.append(
         ToolCallResultEvent(
             message_id=message_id,
             tool_call_id=call_id,
-            content=ui_result_content,
+            content=result_content,
             role="tool",
         )
     )
@@ -387,14 +358,12 @@ def _emit_tool_result(
         return []
     raw_result = content.result if content.result is not None else ""
     state_update = _extract_tool_result_state(content)
-    display_result = _extract_tool_result_display(content)
     return _emit_tool_result_common(
         content.call_id,
         raw_result,
         flow,
         predictive_handler,
         state_update=state_update,
-        display_result=display_result,
     )
 
 
@@ -561,14 +530,12 @@ def _emit_mcp_tool_result(
         return []
     raw_output = content.output if content.output is not None else ""
     state_update = _extract_tool_result_state(content)
-    display_result = _extract_tool_result_display(content)
     return _emit_tool_result_common(
         content.call_id,
         raw_output,
         flow,
         predictive_handler,
         state_update=state_update,
-        display_result=display_result,
     )
 
 

python/packages/ag-ui/agent_framework_ag_ui/_state.py

@@ -1,13 +1,12 @@
 # Copyright (c) Microsoft. All rights reserved.
 
-"""Deterministic tool-driven AG-UI state updates and display payloads.
+"""Deterministic tool-driven AG-UI state updates.
 
 Tools wired into the :mod:`agent_framework_ag_ui` endpoint can push a
-deterministic state update or a per-call tool result display payload by
-returning :func:`state_update`. Unlike ``predict_state_config`` — which emits
-``StateDeltaEvent``s optimistically from LLM-predicted tool call arguments —
-``state_update`` runs *after* the tool executes, so AG-UI state and display
-content always reflect the tool's actual return value.
+deterministic state update by returning :func:`state_update`. Unlike
+``predict_state_config`` — which emits ``StateDeltaEvent``s optimistically from
+LLM-predicted tool call arguments — ``state_update`` runs *after* the tool
+executes, so the AG-UI state always reflects the tool's actual return value.
 
 See issue https://github.com/microsoft/agent-framework/issues/3167 for the
 motivating discussion.
@@ -15,48 +14,33 @@ motivating discussion.
 
 from __future__ import annotations
 
-import json
 from collections.abc import Mapping
 from typing import Any
 
 from agent_framework import Content
 
-from ._utils import make_json_safe
-
-__all__ = ["TOOL_RESULT_DISPLAY_KEY", "TOOL_RESULT_STATE_KEY", "state_update"]
+__all__ = ["TOOL_RESULT_STATE_KEY", "state_update"]
 
 
 TOOL_RESULT_STATE_KEY = "__ag_ui_tool_result_state__"
 """Reserved ``Content.additional_properties`` key used to carry a tool-driven
 state snapshot from a tool return value through to the AG-UI emitter."""
 
-TOOL_RESULT_DISPLAY_KEY = "__ag_ui_tool_result_display__"
-"""Reserved ``Content.additional_properties`` key used to carry UI-only tool result display content from a tool return value through to the AG-UI emitter."""
-
-_UNSET = object()
-
-
-def _serialize_tool_result(value: Any) -> str:  # noqa: ANN401
-    return value if isinstance(value, str) else json.dumps(make_json_safe(value))
-
 
 def state_update(
     text: str = "",
     *,
-    state: Mapping[str, Any] | None = None,
-    tool_result: Any = _UNSET,  # noqa: ANN401
+    state: Mapping[str, Any],
 ) -> Content:
-    """Build a tool return value that updates AG-UI shared state or display content.
+    """Build a tool return value that deterministically updates AG-UI shared state.
 
     Return the result of this helper from an agent tool to push a state update
-    or UI-only display payload to AG-UI clients using the actual tool output,
-    rather than LLM-predicted tool arguments.
+    to AG-UI clients using the actual tool output, rather than LLM-predicted
+    tool arguments.
 
     When the AG-UI endpoint emits the tool result, it will:
 
     * Forward ``text`` to the LLM as the normal ``function_result`` content.
-    * Use ``tool_result`` as the ``ToolCallResultEvent.content`` payload shown
-      to AG-UI clients, falling back to ``text`` when no display payload is set.
     * Merge ``state`` into ``FlowState.current_state``.
     * Emit a deterministic ``StateSnapshotEvent`` after the ``ToolCallResult``
       event so frontends observe the updated state deterministically. If
@@ -65,7 +49,7 @@ def state_update(
     Example:
         .. code-block:: python
 
-            from agent_framework import Content, tool
+            from agent_framework import tool
             from agent_framework_ag_ui import state_update
 
 
@@ -77,61 +61,24 @@ def state_update(
                     state={"weather": {"city": city, **data}},
                 )
 
-    Example:
-        .. code-block:: python
-
-            from agent_framework import Content, tool
-            from agent_framework_ag_ui import state_update
-
-
-            @tool
-            async def get_weather(city: str) -> Content:
-                data = await _fetch_weather(city)
-                return state_update(
-                    text=f"{city}: {data['temp']}°C and {data['conditions']}",
-                    tool_result={
-                        "component": "weather-card",
-                        "city": city,
-                        "temperature": data["temp"],
-                        "conditions": data["conditions"],
-                        "humidity": data["humidity"],
-                    },
-                    state={"weather": {"city": city, **data}},
-                )
-
     Args:
         text: Text passed back to the LLM as the ``function_result`` content.
             Defaults to an empty string for tools whose only output is a state
             update.
         state: A mapping merged into the AG-UI shared state via JSON-compatible
             ``dict.update`` semantics. Nested dicts are replaced, not deep-merged.
-        tool_result: JSON-safe payload emitted to AG-UI clients as
-            ``ToolCallResultEvent.content`` for frontend rendering. The LLM
-            still receives ``text``. If ``text`` is empty, the serialized
-            display payload is also used as the LLM-bound text fallback.
 
     Returns:
         A ``Content`` object with ``type="text"``. The state payload rides in
-        ``additional_properties`` under :data:`TOOL_RESULT_STATE_KEY`
-        (``"__ag_ui_tool_result_state__"``), and the display payload rides
-        under :data:`TOOL_RESULT_DISPLAY_KEY`
-        (``"__ag_ui_tool_result_display__"``). Both reserved keys are extracted
-        by the AG-UI emitter.
+        ``additional_properties`` under :data:`TOOL_RESULT_STATE_KEY` and is
+        extracted by the AG-UI emitter.
 
     Raises:
         TypeError: If ``state`` is not a ``Mapping``.
     """
-    if state is not None and not isinstance(state, Mapping):
+    if not isinstance(state, Mapping):
         raise TypeError(f"state_update() 'state' must be a Mapping, got {type(state).__name__}")
-    additional_properties: dict[str, Any] = {}
-    if state is not None:
-        additional_properties[TOOL_RESULT_STATE_KEY] = dict(state)
-    if tool_result is not _UNSET:
-        display_content = _serialize_tool_result(tool_result)
-        additional_properties[TOOL_RESULT_DISPLAY_KEY] = display_content
-        if not text:
-            text = display_content
     return Content.from_text(
         text,
-        additional_properties=additional_properties,
+        additional_properties={TOOL_RESULT_STATE_KEY: dict(state)},
     )

python/packages/ag-ui/tests/ag_ui/golden/test_scenario_deterministic_state.py

@@ -68,19 +68,6 @@ def _tool_result_with_state(call_id: str, text: str, state: dict[str, Any]) -> A
     )
 
 
-def _tool_result_with_display(call_id: str, text: str, tool_result: Any, **kwargs: Any) -> AgentResponseUpdate:
-    """Build a function_result update carrying an optional UI display marker."""
-    return AgentResponseUpdate(
-        contents=[
-            Content.from_function_result(
-                call_id=call_id,
-                result=[state_update(text=text, tool_result=tool_result, **kwargs)],
-            )
-        ],
-        role="assistant",
-    )
-
-
 # ── Golden stream tests ──
 
 
@@ -278,87 +265,3 @@ async def test_deterministic_state_coexists_with_predict_state_config() -> None:
     # The final observed state must contain both the deterministic and predictive contributions.
     final = stream.snapshot()
     assert final["weather"] == {"city": "SF", "temp": 14}, f"Deterministic state missing from final snapshot: {final}"
-
-
-async def test_tool_result_display_payload_reaches_ui_event_only() -> None:
-    """Rich display payload overrides TOOL_CALL_RESULT without leaking marker keys."""
-    updates = [
-        _tool_call("call-1", "get_weather", '{"city": "SF"}'),
-        _tool_result_with_display(
-            "call-1",
-            text="Weather in SF: 14°C foggy",
-            tool_result={"city": "SF", "temp": 14, "conditions": "foggy"},
-        ),
-    ]
-    agent = _build_agent(updates)
-    stream = await _run(agent, PAYLOAD)
-
-    stream.assert_bookends()
-    stream.assert_no_run_error()
-    stream.assert_tool_calls_balanced()
-
-    result = stream.first("TOOL_CALL_RESULT")
-    assert result.content == '{"city": "SF", "temp": 14, "conditions": "foggy"}'
-    assert "__ag_ui_tool_result_display__" not in result.content
-    assert "__ag_ui_tool_result_state__" not in result.content
-
-
-async def test_tool_result_display_falls_back_to_text_when_unset() -> None:
-    """Without a display marker, the UI event keeps the existing text content."""
-    updates = [
-        _tool_call("call-1", "get_weather", '{"city": "SF"}'),
-        _tool_result_with_state(
-            "call-1",
-            text="Weather in SF: 14°C foggy",
-            state={"weather": {"city": "SF", "temp": 14}},
-        ),
-    ]
-    agent = _build_agent(updates)
-    stream = await _run(agent, PAYLOAD)
-
-    stream.assert_bookends()
-    stream.assert_no_run_error()
-    stream.assert_tool_calls_balanced()
-
-    result = stream.first("TOOL_CALL_RESULT")
-    assert result.content == "Weather in SF: 14°C foggy"
-    assert "__ag_ui_tool_result_display__" not in result.content
-    assert "__ag_ui_tool_result_state__" not in result.content
-
-
-async def test_tool_result_display_coexists_with_state_snapshot() -> None:
-    """Display and durable state markers produce one deterministic state snapshot."""
-    updates = [
-        _tool_call("call-1", "get_weather", '{"city": "SF"}'),
-        _tool_result_with_display(
-            "call-1",
-            text="Weather in SF: 14°C foggy",
-            tool_result={"city": "SF", "temp": 14, "conditions": "foggy"},
-            state={"weather": {"city": "SF", "temp": 14, "conditions": "foggy"}},
-        ),
-    ]
-    agent = _build_agent(updates)
-    stream = await _run(agent, PAYLOAD)
-
-    stream.assert_bookends()
-    stream.assert_no_run_error()
-    stream.assert_tool_calls_balanced()
-    stream.assert_ordered_types(["TOOL_CALL_RESULT", "STATE_SNAPSHOT", "RUN_FINISHED"])
-
-    result = stream.first("TOOL_CALL_RESULT")
-    assert result.content == '{"city": "SF", "temp": 14, "conditions": "foggy"}'
-
-    result_idx = stream.events.index(result)
-    deterministic_snapshots = [
-        event
-        for event in stream.events[result_idx + 1 :]
-        if getattr(getattr(event, "type", None), "value", getattr(event, "type", None)) == "STATE_SNAPSHOT"
-    ]
-    assert len(deterministic_snapshots) == 1
-    assert deterministic_snapshots[0].snapshot["weather"] == {
-        "city": "SF",
-        "temp": 14,
-        "conditions": "foggy",
-    }
-    assert "__ag_ui_tool_result_display__" not in str(deterministic_snapshots[0].snapshot)
-    assert "__ag_ui_tool_result_state__" not in str(deterministic_snapshots[0].snapshot)

python/packages/ag-ui/tests/ag_ui/test_approval_result_event.py

@@ -448,37 +448,3 @@ async def test_resolve_approval_responses_returns_only_approved() -> None:
     rejection_results = [c for c in all_contents if c.type == "function_result" and c.call_id == rejected_call_id]
     assert len(rejection_results) == 1
     assert "rejected" in str(rejection_results[0].result).lower()
-
-
-class TestApprovalToolResultDisplayChannel:
-    """Approved tools using ``state_update(..., tool_result=...)`` must route the
-    display payload to the UI event while ``flow.tool_results`` still receives
-    the LLM-bound text. The HITL approval emitter is separate from the standard
-    streaming emitter, so it gets its own coverage.
-    """
-
-    def test_approval_emits_display_payload_when_marker_present(self) -> None:
-        from agent_framework_ag_ui import state_update
-        from agent_framework_ag_ui._agent_run import _make_approval_tool_result_events
-
-        display_payload = {"city": "Seattle", "temp": 14, "conditions": "foggy"}
-        inner = state_update(text="14°C, foggy", tool_result=display_payload)
-        resolved = Content.from_function_result(call_id="call_disp", result=[inner])
-
-        events = _make_approval_tool_result_events([resolved])
-
-        assert len(events) == 1
-        # UI event must carry the serialized display payload, NOT the LLM text.
-        assert json.loads(events[0].content) == display_payload
-        assert events[0].content != "14°C, foggy"
-
-    def test_approval_falls_back_to_text_when_no_marker(self) -> None:
-        """Backward compat: without a display marker, behaviour is unchanged."""
-        from agent_framework_ag_ui._agent_run import _make_approval_tool_result_events
-
-        resolved = Content.from_function_result(call_id="call_plain", result="Sunny in Seattle")
-
-        events = _make_approval_tool_result_events([resolved])
-
-        assert len(events) == 1
-        assert events[0].content == "Sunny in Seattle"

python/packages/ag-ui/tests/ag_ui/test_run_common.py

@@ -15,7 +15,7 @@ from agent_framework_ag_ui._run_common import (
     _extract_tool_result_state,
     _normalize_resume_interrupts,
 )
-from agent_framework_ag_ui._state import TOOL_RESULT_DISPLAY_KEY, TOOL_RESULT_STATE_KEY
+from agent_framework_ag_ui._state import TOOL_RESULT_STATE_KEY
 
 
 class TestNormalizeResumeInterrupts:
@@ -140,15 +140,6 @@ class TestStateUpdateHelper:
             TOOL_RESULT_STATE_KEY: {"weather": {"temp": 14}},
         }
 
-    def test_builds_text_content_with_display_marker(self):
-        """state_update can carry a UI display payload without requiring state."""
-        c = state_update(text="14°C, foggy", tool_result={"temp": 14, "conditions": "foggy"})
-        assert c.type == "text"
-        assert c.text == "14°C, foggy"
-        assert c.additional_properties == {
-            TOOL_RESULT_DISPLAY_KEY: '{"temp": 14, "conditions": "foggy"}',
-        }
-
     def test_empty_text_is_allowed(self):
         """State-only tools can omit the text argument."""
         c = state_update(state={"steps": ["a", "b"]})
@@ -174,18 +165,6 @@ class TestStateUpdateHelper:
         inner = c.additional_properties[TOOL_RESULT_STATE_KEY]
         assert inner is not caller_state
 
-    def test_tool_result_without_text_falls_back_to_display_payload(self):
-        """Display-only tools use the serialized display payload as LLM text."""
-        c = state_update(tool_result={"temp": 14, "conditions": "foggy"})
-        assert c.text == '{"temp": 14, "conditions": "foggy"}'
-        assert c.additional_properties[TOOL_RESULT_DISPLAY_KEY] == '{"temp": 14, "conditions": "foggy"}'
-
-    def test_string_tool_result_is_not_json_encoded_again(self):
-        """A pre-serialized display string passes through verbatim."""
-        c = state_update(text="Weather summary", tool_result='{"temp":14}')
-        assert c.text == "Weather summary"
-        assert c.additional_properties[TOOL_RESULT_DISPLAY_KEY] == '{"temp":14}'
-
 
 class TestExtractToolResultState:
     """Tests for ``_extract_tool_result_state``."""
@@ -286,60 +265,6 @@ class TestEmitToolResultWithState:
         assert result_events[0].content == "Weather: 14°C"
         assert TOOL_RESULT_STATE_KEY not in result_events[0].content
 
-    def test_display_payload_routes_to_ui_only(self):
-        """A display marker overrides only the UI event, not the LLM-bound tool result."""
-        tool_return = state_update(
-            text="Weather: 14°C",
-            tool_result={"temp": 14, "conditions": "foggy"},
-        )
-        content = Content.from_function_result(call_id="c1", result=[tool_return])
-        flow = FlowState()
-
-        events = _emit_tool_result(content, flow)
-        result_events = [e for e in events if e.type == EventType.TOOL_CALL_RESULT]
-
-        assert len(result_events) == 1
-        assert result_events[0].content == '{"temp": 14, "conditions": "foggy"}'
-        assert flow.tool_results[-1]["content"] == "Weather: 14°C"
-        assert TOOL_RESULT_DISPLAY_KEY not in result_events[0].content
-        assert TOOL_RESULT_DISPLAY_KEY not in flow.tool_results[-1]["content"]
-
-    def test_plain_tool_result_uses_existing_content_for_both_channels(self):
-        """Without a display marker, UI and LLM channels keep the existing derivation."""
-        content = Content.from_function_result(call_id="c1", result="plain result")
-        flow = FlowState()
-
-        events = _emit_tool_result(content, flow)
-        result_events = [e for e in events if e.type == EventType.TOOL_CALL_RESULT]
-
-        assert len(result_events) == 1
-        assert result_events[0].content == "plain result"
-        assert flow.tool_results[-1]["content"] == "plain result"
-
-    def test_display_only_payload_falls_back_to_llm_content(self):
-        """When text is empty, both channels receive the serialized display payload."""
-        tool_return = state_update(tool_result={"temp": 14})
-        content = Content.from_function_result(call_id="c1", result=[tool_return])
-        flow = FlowState()
-
-        events = _emit_tool_result(content, flow)
-        result_events = [e for e in events if e.type == EventType.TOOL_CALL_RESULT]
-
-        assert result_events[0].content == '{"temp": 14}'
-        assert flow.tool_results[-1]["content"] == '{"temp": 14}'
-
-    def test_pre_serialized_display_string_routes_verbatim(self):
-        """String display payloads pass through without JSON double-encoding."""
-        tool_return = state_update(text="Weather summary", tool_result='{"temp":14}')
-        content = Content.from_function_result(call_id="c1", result=[tool_return])
-        flow = FlowState()
-
-        events = _emit_tool_result(content, flow)
-        result_events = [e for e in events if e.type == EventType.TOOL_CALL_RESULT]
-
-        assert result_events[0].content == '{"temp":14}'
-        assert flow.tool_results[-1]["content"] == "Weather summary"
-
     def test_coexists_with_active_predictive_state_handler(self):
         """Both predictive and deterministic state produce a single coalesced snapshot.
 
@@ -421,31 +346,3 @@ class TestEmitMcpToolResultWithState:
 
         events = _emit_mcp_tool_result(content, flow)
         assert all(e.type != EventType.STATE_SNAPSHOT for e in events)
-
-
-class TestEmitMcpToolResultWithDisplay:
-    """MCP tool results must honour the display marker so UI consumers can
-    render structured payloads while ``flow.tool_results`` keeps the LLM
-    string. MCP outputs do not pass through ``parse_result``; the marker
-    rides on the outer content's ``additional_properties``.
-    """
-
-    def test_mcp_tool_result_routes_display_payload_to_ui_only(self):
-        import json as _json
-
-        display_payload = {"rows": [{"id": 1, "name": "alpha"}, {"id": 2, "name": "beta"}]}
-        content = Content.from_mcp_server_tool_result(
-            call_id="mcp_disp",
-            output="2 rows returned",
-            additional_properties={TOOL_RESULT_DISPLAY_KEY: display_payload},
-        )
-        flow = FlowState()
-
-        events = _emit_mcp_tool_result(content, flow)
-        result_events = [e for e in events if e.type == EventType.TOOL_CALL_RESULT]
-
-        assert len(result_events) == 1
-        # UI event carries the structured display payload.
-        assert _json.loads(result_events[0].content) == display_payload
-        # LLM-side accumulator keeps the short text.
-        assert flow.tool_results[-1]["content"] == "2 rows returned"

python/packages/core/AGENTS.md

@@ -69,8 +69,7 @@ agent_framework/
 
 ### Skills (`_skills.py`)
 
-- **`Skill`** - Abstract base for a skill definition bundling instructions (`content`) with frontmatter metadata, resources, and scripts. Concrete subclasses (`InlineSkill`, `FileSkill`, `ClassSkill`) accept a `frontmatter=SkillFrontmatter(...)` argument carrying the spec fields. Adding new spec fields is done in one place — on `SkillFrontmatter` — keeping the subclass constructors stable.
-- **`SkillFrontmatter`** - L1 discovery metadata for a skill (`name`, `description`, `license`, `compatibility`, `allowed_tools`, `metadata`). All fields are mutable plain attributes; the constructor validates `name`, `description`, and `compatibility` against the spec but post-construction assignments are not re-validated. Spec fields are reachable on every skill via `skill.frontmatter`.
+- **`Skill`** - A skill definition bundling instructions (`content`) with metadata, resources, and scripts. Supports `@skill.resource` and `@skill.script` decorators for adding components.
 - **`SkillResource`** - Named supplementary content attached to a skill; holds either static `content` or a dynamic `function` (sync or async). Exactly one must be provided.
 - **`SkillScript`** - An executable script attached to a skill; holds either an inline `function` (code-defined, runs in-process) or a `path` to a file on disk (file-based, delegated to a runner). Exactly one must be provided.
 - **`SkillScriptRunner`** - Protocol for file-based script execution. Any callable matching `(skill, script, args) -> Any` satisfies it. Code-defined scripts do not use a runner.

python/packages/core/agent_framework/__init__.py

@@ -147,7 +147,6 @@ from ._skills import (
     InlineSkillScript,
     InMemorySkillsSource,
     Skill,
-    SkillFrontmatter,
     SkillResource,
     SkillScript,
     SkillScriptRunner,
@@ -433,7 +432,6 @@ __all__ = [
     "SessionContext",
     "SingleEdgeGroup",
     "Skill",
-    "SkillFrontmatter",
     "SkillResource",
     "SkillScript",
     "SkillScriptRunner",

python/packages/core/agent_framework/_mcp.py

@@ -10,7 +10,7 @@ import logging
 import re
 import sys
 from abc import abstractmethod
-from collections.abc import Callable, Collection, Coroutine, Sequence
+from collections.abc import Callable, Collection, Sequence
 from contextlib import AsyncExitStack, _AsyncGeneratorContextManager  # type: ignore
 from datetime import timedelta
 from functools import partial
@@ -264,7 +264,6 @@ class MCPTool:
         self.is_connected: bool = False
         self._tools_loaded: bool = False
         self._prompts_loaded: bool = False
-        self._pending_reload_tasks: set[asyncio.Task[None]] = set()
 
     def __str__(self) -> str:
         return f"MCPTool(name={self.name}, description={self.description})"
@@ -906,47 +905,12 @@ class MCPTool:
         if isinstance(message, types.ServerNotification):
             match message.root.method:
                 case "notifications/tools/list_changed":
-                    self._schedule_reload(self.load_tools())
+                    await self.load_tools()
                 case "notifications/prompts/list_changed":
-                    self._schedule_reload(self.load_prompts())
+                    await self.load_prompts()
                 case _:
                     logger.debug("Unhandled notification: %s", message.root.method)
 
-    def _schedule_reload(self, coro: Coroutine[Any, Any, None]) -> None:
-        """Schedule a reload coroutine as a background task.
-
-        Reloads (load_tools / load_prompts) triggered by MCP server
-        notifications must NOT be awaited inside the message handler because
-        the handler runs on the MCP SDK's single-threaded receive loop.
-        Awaiting a session request (e.g. ``list_tools``) from within that loop
-        deadlocks: the receive loop cannot read the response while it is
-        blocked waiting for the handler to return.
-
-        Instead we fire the reload as an independent ``asyncio.Task`` and keep
-        a strong reference in ``_pending_reload_tasks`` so it is not garbage-
-        collected before completion.  Only one reload per kind (tools / prompts)
-        is kept in flight; a new notification cancels the previous pending task
-        for the same coroutine name to avoid unbounded growth.
-        """
-        # Cancel-and-replace: only one reload per kind should be in flight.
-        reload_name = f"mcp-reload:{self.name}:{coro.__qualname__}"
-        for existing in list(self._pending_reload_tasks):
-            if existing.get_name() == reload_name and not existing.done():
-                logger.debug("Cancelling in-flight reload %s; superseded by new notification", reload_name)
-                existing.cancel()
-
-        async def _safe_reload() -> None:
-            try:
-                await coro
-            except asyncio.CancelledError:
-                raise
-            except Exception:
-                logger.warning("Background MCP reload failed", exc_info=True)
-
-        task = asyncio.create_task(_safe_reload(), name=reload_name)
-        self._pending_reload_tasks.add(task)
-        task.add_done_callback(self._pending_reload_tasks.discard)
-
     def _determine_approval_mode(
         self,
         *candidate_names: str,
@@ -1083,14 +1047,6 @@ class MCPTool:
             params = types.PaginatedRequestParams(cursor=tool_list.nextCursor)
 
     async def _close_on_owner(self) -> None:
-        # Cancel any pending reload tasks before tearing down the session.
-        tasks = list(self._pending_reload_tasks)
-        for task in tasks:
-            task.cancel()
-        self._pending_reload_tasks.clear()
-        if tasks:
-            await asyncio.gather(*tasks, return_exceptions=True)
-
         await self._safe_close_exit_stack()
         self._exit_stack = AsyncExitStack()
         self.session = None

python/packages/core/agent_framework/_skills.py

@@ -465,23 +465,41 @@ class Skill(ABC):
 
     A skill represents a domain-specific capability with instructions,
     resources, and scripts.  Concrete implementations include
-    :class:`FileSkill` (filesystem-backed), :class:`InlineSkill`
-    (code-defined), and :class:`ClassSkill` (class-based).
+    :class:`FileSkill` (filesystem-backed) and :class:`InlineSkill`
+    (code-defined).
 
-    Skill spec metadata (name, description, license, compatibility,
-    allowed_tools, metadata) is exposed via the :attr:`frontmatter`
-    property, which returns a :class:`SkillFrontmatter` instance.
+    Skill metadata follows the
+    `Agent Skills specification <https://agentskills.io/>`_.
+
+    Attributes:
+        name: Skill name (lowercase letters, numbers, hyphens only).
+        description: Human-readable description of the skill.
     """
 
-    @property
-    @abstractmethod
-    def frontmatter(self) -> SkillFrontmatter:
-        """The L1 discovery metadata for this skill.
+    def __init__(
+        self,
+        *,
+        name: str,
+        description: str,
+    ) -> None:
+        """Initialize a Skill.
 
-        Contains the name, description, and other spec fields as defined by
-        the `Agent Skills specification <https://agentskills.io/specification>`_.
+        Validates the skill name and description against specification rules.
+
+        Args:
+            name: Skill name (lowercase letters, numbers, hyphens only;
+                max 64 characters; no leading/trailing/consecutive hyphens).
+            description: Human-readable description of the skill
+                (≤1024 characters).
+
+        Raises:
+            ValueError: If the name or description is invalid.
         """
-        ...
+        _validate_skill_name(name)
+        _validate_skill_description(name, description)
+
+        self.name = name
+        self.description = description
 
     @property
     @abstractmethod
@@ -517,68 +535,6 @@ class Skill(ABC):
         return []
 
 
-@experimental(feature_id=ExperimentalFeature.SKILLS)
-class SkillFrontmatter:
-    """L1 discovery metadata for a :class:`Skill`.
-
-    Encapsulates all `Agent Skills specification <https://agentskills.io/specification>`_
-    frontmatter fields in a single object. All fields are mutable plain
-    attributes; callers may freely reassign them after construction.
-
-    The constructor validates ``name``, ``description``, and ``compatibility``
-    against specification rules and raises :class:`ValueError` on invalid
-    input. Assignments made after construction are **not** re-validated;
-    callers are expected to honor the spec.
-
-    Attributes:
-        name: Skill name (lowercase letters, numbers, hyphens only).
-        description: Human-readable description of the skill.
-        license: Optional license name or reference.
-        compatibility: Optional compatibility information (≤500 characters).
-        allowed_tools: Optional space-delimited pre-approved tool names.
-        metadata: Optional arbitrary key-value pairs (shallow-copied on
-            construction to avoid caller-owned dict aliasing).
-    """
-
-    def __init__(
-        self,
-        *,
-        name: str,
-        description: str,
-        license: str | None = None,
-        compatibility: str | None = None,
-        allowed_tools: str | None = None,
-        metadata: dict[str, str] | None = None,
-    ) -> None:
-        """Initialize a SkillFrontmatter.
-
-        Args:
-            name: Skill name (lowercase letters, numbers, hyphens only;
-                max 64 characters; no leading/trailing/consecutive hyphens).
-            description: Human-readable description of the skill
-                (≤1024 characters).
-            license: Optional license name or reference.
-            compatibility: Optional compatibility information
-                (≤500 characters).
-            allowed_tools: Optional space-delimited pre-approved tool names.
-            metadata: Optional arbitrary key-value pairs.
-
-        Raises:
-            ValueError: If the name, description, or compatibility is invalid.
-        """
-        _validate_skill_name(name)
-        _validate_skill_description(name, description)
-        _validate_compatibility(compatibility)
-
-        self.name = name
-        self.description = description
-        self.compatibility = compatibility
-        self.license = license
-        self.allowed_tools = allowed_tools
-        # Shallow-copy to avoid aliasing with caller-owned dict.
-        self.metadata: dict[str, str] | None = dict(metadata) if metadata is not None else None
-
-
 def _validate_skill_name(name: str) -> None:
     """Validate a skill name against specification rules.
 
@@ -617,21 +573,6 @@ def _validate_skill_description(name: str, description: str) -> None:
         )
 
 
-def _validate_compatibility(compatibility: str | None) -> None:
-    """Validate an optional compatibility value against specification rules.
-
-    Args:
-        compatibility: The optional compatibility value to validate.
-
-    Raises:
-        ValueError: If the value exceeds the maximum allowed length.
-    """
-    if compatibility is not None and len(compatibility) > MAX_COMPATIBILITY_LENGTH:
-        raise ValueError(
-            f"Skill compatibility must be {MAX_COMPATIBILITY_LENGTH} characters or fewer."
-        )
-
-
 def _build_skill_content(
     name: str,
     description: str,
@@ -698,17 +639,23 @@ class InlineSkill(Skill):
     All resources and scripts should be configured before the skill is
     registered with a :class:`SkillsProvider`.
 
+    Attributes:
+        name: Skill name (lowercase letters, numbers, hyphens only).
+        description: Human-readable description of the skill.
+        instructions: The skill instructions text.
+
     Examples:
+        With the decorator:
+
         .. code-block:: python
 
             skill = InlineSkill(
-                frontmatter=SkillFrontmatter(
-                    name="db-skill",
-                    description="Database operations",
-                ),
+                name="db-skill",
+                description="Database operations",
                 instructions="Use this skill for DB tasks.",
             )
 
+
             @skill.resource
             def get_schema() -> str:
                 return "CREATE TABLE ..."
@@ -717,7 +664,8 @@ class InlineSkill(Skill):
     def __init__(
         self,
         *,
-        frontmatter: SkillFrontmatter,
+        name: str,
+        description: str,
         instructions: str,
         resources: Sequence[SkillResource] | None = None,
         scripts: Sequence[SkillScript] | None = None,
@@ -725,25 +673,19 @@ class InlineSkill(Skill):
         """Initialize an InlineSkill.
 
         Args:
-            frontmatter: Skill specification metadata (name, description,
-                and optional spec fields). Construct a :class:`SkillFrontmatter`
-                with the desired fields.
+            name: Skill name (lowercase letters, numbers, hyphens only).
+            description: Human-readable description of the skill (≤1024 chars).
             instructions: The skill instructions text.
             resources: Pre-built resources to attach to this skill.
             scripts: Pre-built scripts to attach to this skill.
         """
-        self._frontmatter = frontmatter
+        super().__init__(name=name, description=description)
 
         self.instructions = instructions
         self._resources: list[SkillResource] = list(resources) if resources is not None else []
         self._scripts: list[SkillScript] = list(scripts) if scripts is not None else []
         self._cached_content: str | None = None
 
-    @property
-    def frontmatter(self) -> SkillFrontmatter:
-        """The L1 discovery metadata for this skill."""
-        return self._frontmatter
-
     @property
     def content(self) -> str:
         """Synthesized XML content with name, description, instructions, resources, and scripts.
@@ -755,11 +697,7 @@ class InlineSkill(Skill):
             return self._cached_content
 
         self._cached_content = _build_skill_content(
-            self._frontmatter.name,
-            self._frontmatter.description,
-            self.instructions,
-            self._resources,
-            self._scripts,
+            self.name, self.description, self.instructions, self._resources, self._scripts
         )
         return self._cached_content
 
@@ -994,6 +932,10 @@ class ClassSkill(Skill, ABC):
     Class-based skills can be distributed via shared libraries or PyPI
     packages, making them easy to reuse across projects.
 
+    Attributes:
+        name: Skill name (lowercase letters, numbers, hyphens only).
+        description: Human-readable description of the skill.
+
     Examples:
         Decorator-based (recommended):
 
@@ -1002,10 +944,8 @@ class ClassSkill(Skill, ABC):
             class UnitConverterSkill(ClassSkill):
                 def __init__(self) -> None:
                     super().__init__(
-                        frontmatter=SkillFrontmatter(
-                            name="unit-converter",
-                            description="Convert between common units.",
-                        ),
+                        name="unit-converter",
+                        description="Convert between common units.",
                     )
 
                 @property
@@ -1027,10 +967,8 @@ class ClassSkill(Skill, ABC):
             class UnitConverterSkill(ClassSkill):
                 def __init__(self) -> None:
                     super().__init__(
-                        frontmatter=SkillFrontmatter(
-                            name="unit-converter",
-                            description="Convert between common units.",
-                        ),
+                        name="unit-converter",
+                        description="Convert between common units.",
                     )
 
                 @property
@@ -1051,25 +989,22 @@ class ClassSkill(Skill, ABC):
     def __init__(
         self,
         *,
-        frontmatter: SkillFrontmatter,
+        name: str,
+        description: str,
     ) -> None:
         """Initialize a ClassSkill.
 
         Args:
-            frontmatter: Skill specification metadata (name, description,
-                and optional spec fields). Construct a :class:`SkillFrontmatter`
-                with the desired fields.
+            name: Skill name (lowercase letters, numbers, hyphens only;
+                max 64 characters).
+            description: Human-readable description of the skill
+                (≤1024 characters).
         """
-        self._frontmatter = frontmatter
+        super().__init__(name=name, description=description)
         self._cached_content: str | None = None
         self._cached_resources: list[SkillResource] | None = None
         self._cached_scripts: list[SkillScript] | None = None
 
-    @property
-    def frontmatter(self) -> SkillFrontmatter:
-        """The L1 discovery metadata for this skill."""
-        return self._frontmatter
-
     @staticmethod
     def resource(
         func: Callable[..., Any] | None = None,
@@ -1217,7 +1152,7 @@ class ClassSkill(Skill, ABC):
             resource_name = marker.get("name") or _make_method_name(attr_name)
             if resource_name in seen_names:
                 raise ValueError(
-                    f"Skill '{self._frontmatter.name}' already has a resource named '{resource_name}'. "
+                    f"Skill '{self.name}' already has a resource named '{resource_name}'. "
                     "Ensure each @ClassSkill.resource has a unique name."
                 )
             seen_names.add(resource_name)
@@ -1277,7 +1212,7 @@ class ClassSkill(Skill, ABC):
             script_name = marker.get("name") or _make_method_name(attr_name)
             if script_name in seen_names:
                 raise ValueError(
-                    f"Skill '{self._frontmatter.name}' already has a script named '{script_name}'. "
+                    f"Skill '{self.name}' already has a script named '{script_name}'. "
                     "Ensure each @ClassSkill.script has a unique name."
                 )
             seen_names.add(script_name)
@@ -1305,11 +1240,7 @@ class ClassSkill(Skill, ABC):
             return self._cached_content
 
         self._cached_content = _build_skill_content(
-            self._frontmatter.name,
-            self._frontmatter.description,
-            self.instructions,
-            self.resources,
-            self.scripts,
+            self.name, self.description, self.instructions, self.resources, self.scripts
         )
         return self._cached_content
 
@@ -1319,13 +1250,16 @@ class FileSkill(Skill):
     """A :class:`Skill` discovered from a filesystem directory backed by a SKILL.md file.
 
     Attributes:
+        name: Skill name (lowercase letters, numbers, hyphens only).
+        description: Human-readable description of the skill.
         path: Absolute path to the directory containing this skill.
     """
 
     def __init__(
         self,
         *,
-        frontmatter: SkillFrontmatter,
+        name: str,
+        description: str,
         content: str,
         path: str,
         resources: Sequence[SkillResource] | None = None,
@@ -1334,26 +1268,20 @@ class FileSkill(Skill):
         """Initialize a FileSkill.
 
         Args:
-            frontmatter: Skill specification metadata parsed from the
-                SKILL.md file's YAML frontmatter (name, description,
-                and optional spec fields).
+            name: Skill name (lowercase letters, numbers, hyphens only).
+            description: Human-readable description of the skill (≤1024 chars).
             content: The full raw SKILL.md file content including YAML frontmatter.
             path: Absolute path to the skill directory on disk.
             resources: Resources discovered for this skill.
             scripts: Scripts discovered for this skill.
         """
-        self._frontmatter = frontmatter
+        super().__init__(name=name, description=description)
 
         self._content = content
         self.path = path
         self._resources: list[SkillResource] = list(resources) if resources is not None else []
         self._scripts: list[SkillScript] = list(scripts) if scripts is not None else []
 
-    @property
-    def frontmatter(self) -> SkillFrontmatter:
-        """The L1 discovery metadata for this skill."""
-        return self._frontmatter
-
     @property
     def content(self) -> str:
         """The skill content provided at construction time."""
@@ -1418,7 +1346,6 @@ SKILL_FILE_NAME: Final[str] = "SKILL.md"
 MAX_SEARCH_DEPTH: Final[int] = 2
 MAX_NAME_LENGTH: Final[int] = 64
 MAX_DESCRIPTION_LENGTH: Final[int] = 1024
-MAX_COMPATIBILITY_LENGTH: Final[int] = 500
 DEFAULT_RESOURCE_EXTENSIONS: Final[tuple[str, ...]] = (
     ".md",
     ".json",
@@ -1439,24 +1366,10 @@ FRONTMATTER_RE = re.compile(
     re.MULTILINE | re.DOTALL,
 )
 
-# Matches top-level YAML "key: value" lines (unindented). Group 1 = key,
-# Group 2 = quoted value, Group 3 = unquoted value. Only matches keys at
-# column 0 so that indented children (e.g. under "metadata:") are not
-# mistakenly captured as top-level fields.
+# Matches YAML "key: value" lines. Group 1 = key, Group 2 = quoted value,
+# Group 3 = unquoted value.
 YAML_KV_RE = re.compile(
-    r"^([\w-]+)\s*:\s*(?:[\"'](.+?)[\"']|(.+?))\s*$",
-    re.MULTILINE,
-)
-
-# Matches a YAML "metadata:" block followed by indented key-value pairs.
-YAML_METADATA_BLOCK_RE = re.compile(
-    r"^metadata\s*:\s*$\n((?:[ \t]+\S.*\n?)+)",
-    re.MULTILINE,
-)
-
-# Matches indented "key: value" lines within a metadata block.
-YAML_INDENTED_KV_RE = re.compile(
-    r"^\s+([\w-]+)\s*:\s*(?:[\"'](.+?)[\"']|(.+?))\s*$",
+    r"^\s*(\w+)\s*:\s*(?:[\"'](.+?)[\"']|(.+?))\s*$",
     re.MULTILINE,
 )
 
@@ -1464,7 +1377,6 @@ YAML_INDENTED_KV_RE = re.compile(
 # must not start or end with a hyphen, and must not contain consecutive hyphens.
 VALID_NAME_RE = re.compile(r"^[a-z0-9]([a-z0-9]*-[a-z0-9])*[a-z0-9]*$")
 
-
 # Default system prompt template for advertising available skills to the model.
 # Use {skills} as the placeholder for the generated skills XML list.
 DEFAULT_SKILLS_INSTRUCTION_PROMPT = """\
@@ -1551,7 +1463,7 @@ class SkillsProvider(ContextProvider):
                         FileSkillsSource("./skills", script_runner=my_runner),
                         InMemorySkillsSource([my_code_skill]),
                     ]),
-                    predicate=lambda s: s.frontmatter.name != "internal",
+                    predicate=lambda s: s.name != "internal",
                 )
             )
             provider = SkillsProvider(source)
@@ -1786,10 +1698,10 @@ class SkillsProvider(ContextProvider):
 
         lines: list[str] = []
         # Sort by name for deterministic output
-        for skill in sorted(skills, key=lambda s: s.frontmatter.name):
+        for skill in sorted(skills, key=lambda s: s.name):
             lines.append("  <skill>")
-            lines.append(f"    <name>{xml_escape(skill.frontmatter.name)}</name>")
-            lines.append(f"    <description>{xml_escape(skill.frontmatter.description)}</description>")
+            lines.append(f"    <name>{xml_escape(skill.name)}</name>")
+            lines.append(f"    <description>{xml_escape(skill.description)}</description>")
             lines.append("  </skill>")
 
         return template.format(
@@ -2008,7 +1920,7 @@ class SkillsProvider(ContextProvider):
     def _find_skill(skills: Sequence[Skill], name: str) -> Skill | None:
         """Find a skill by name (case-insensitive linear scan)."""
         name_lower = name.lower()
-        return next((s for s in skills if s.frontmatter.name.lower() == name_lower), None)
+        return next((s for s in skills if s.name.lower() == name_lower), None)
 
     def _load_skill(self, skills: Sequence[Skill], skill_name: str) -> str:
         """Return the full content for the named skill.
@@ -2267,18 +2179,19 @@ class FileSkillsSource(SkillsSource):
             if parsed is None:
                 continue
 
-            frontmatter, content = parsed
+            name, description, content = parsed
 
-            if frontmatter.name in skills:
+            if name in skills:
                 logger.warning(
                     "Duplicate skill name '%s': skill from '%s' skipped in favor of existing skill",
-                    frontmatter.name,
+                    name,
                     skill_path,
                 )
                 continue
 
             file_skill = FileSkill(
-                frontmatter=frontmatter,
+                name=name,
+                description=description,
                 content=content,
                 path=skill_path,
             )
@@ -2295,8 +2208,8 @@ class FileSkillsSource(SkillsSource):
                     FileSkillScript(name=sn, full_path=script_full_path, runner=self._script_runner)
                 )
 
-            skills[file_skill.frontmatter.name] = file_skill
-            logger.info("Loaded skill: %s", file_skill.frontmatter.name)
+            skills[file_skill.name] = file_skill
+            logger.info("Loaded skill: %s", file_skill.name)
 
         logger.info("Successfully loaded %d skills", len(skills))
         return list(skills.values())
@@ -2525,9 +2438,8 @@ class FileSkillsSource(SkillsSource):
         name: str | None,
         description: str | None,
         source: str,
-        compatibility: str | None = None,
     ) -> str | None:
-        """Validate a skill's name, description, and compatibility against naming rules.
+        """Validate a skill's name and description against naming rules.
 
         Enforces length limits, character-set restrictions, and non-emptiness
         for both file-based and code-defined skills.
@@ -2537,7 +2449,6 @@ class FileSkillsSource(SkillsSource):
             description: Skill description to validate.
             source: Human-readable label for diagnostics (e.g. a file path
                 or ``"code skill"``).
-            compatibility: Optional compatibility value to validate.
 
         Returns:
             A diagnostic error string if validation fails, or ``None`` if valid.
@@ -2561,32 +2472,24 @@ class FileSkillsSource(SkillsSource):
                 f"Must be {MAX_DESCRIPTION_LENGTH} characters or fewer."
             )
 
-        if compatibility is not None and len(compatibility) > MAX_COMPATIBILITY_LENGTH:
-            return (
-                f"Skill '{name}' from '{source}' has an invalid compatibility: "
-                f"Must be {MAX_COMPATIBILITY_LENGTH} characters or fewer."
-            )
-
         return None
 
     @staticmethod
     def _extract_frontmatter(
         content: str,
         skill_file_path: str,
-    ) -> SkillFrontmatter | None:
+    ) -> tuple[str, str] | None:
         """Extract and validate YAML frontmatter from a SKILL.md file.
 
-        Parses the ``---``-delimited frontmatter block for all
-        `agentskills.io specification <https://agentskills.io/specification>`_
-        fields: ``name``, ``description``, ``license``, ``compatibility``,
-        ``allowed-tools``, and ``metadata``.
+        Parses the ``---``-delimited frontmatter block for ``name`` and
+        ``description`` fields.
 
         Args:
             content: Raw text content of the SKILL.md file.
             skill_file_path: Path to the file (used in diagnostic messages only).
 
         Returns:
-            A :class:`SkillFrontmatter` on success, or ``None`` if the
+            A ``(name, description)`` tuple on success, or ``None`` if the
             frontmatter is missing, malformed, or fails validation.
         """
         match = FRONTMATTER_RE.search(content)
@@ -2597,63 +2500,35 @@ class FileSkillsSource(SkillsSource):
         yaml_content = match.group(1).strip()
         name: str | None = None
         description: str | None = None
-        license_value: str | None = None
-        compatibility: str | None = None
-        allowed_tools: str | None = None
 
         for kv_match in YAML_KV_RE.finditer(yaml_content):
             key = kv_match.group(1)
             value = kv_match.group(2) if kv_match.group(2) is not None else kv_match.group(3)
 
-            key_lower = key.lower()
-            if key_lower == "name":
+            if key.lower() == "name":
                 name = value
-            elif key_lower == "description":
+            elif key.lower() == "description":
                 description = value
-            elif key_lower == "license":
-                license_value = value
-            elif key_lower == "compatibility":
-                compatibility = value
-            elif key_lower == "allowed-tools":
-                allowed_tools = value
 
-        # Parse metadata block (indented key-value pairs under "metadata:").
-        metadata: dict[str, str] | None = None
-        metadata_match = YAML_METADATA_BLOCK_RE.search(yaml_content)
-        if metadata_match:
-            metadata = {}
-            for kv_match in YAML_INDENTED_KV_RE.finditer(metadata_match.group(1)):
-                mk = kv_match.group(1)
-                mv = kv_match.group(2) if kv_match.group(2) is not None else kv_match.group(3)
-                metadata[mk] = mv
-
-        error = FileSkillsSource._validate_skill_metadata(name, description, skill_file_path, compatibility)
+        error = FileSkillsSource._validate_skill_metadata(name, description, skill_file_path)
         if error:
             logger.error(error)
             return None
 
-        # name and description are guaranteed non-None after validation;
-        # SkillFrontmatter re-validates as a defense-in-depth invariant.
-        return SkillFrontmatter(
-            name=cast(str, name),
-            description=cast(str, description),
-            license=license_value,
-            compatibility=compatibility,
-            allowed_tools=allowed_tools,
-            metadata=metadata,
-        )
+        # name and description are guaranteed non-None after validation
+        return name, description  # type: ignore[return-value]
 
     @staticmethod
     def _read_and_parse_skill_file(
         skill_dir_path: str,
-    ) -> tuple[SkillFrontmatter, str] | None:
+    ) -> tuple[str, str, str] | None:
         """Read and parse the SKILL.md file in *skill_dir_path*.
 
         Args:
             skill_dir_path: Absolute path to the directory containing ``SKILL.md``.
 
         Returns:
-            A ``(frontmatter, content)`` tuple where *content* is the
+            A ``(name, description, content)`` tuple where *content* is the
             full raw file text, or ``None`` if the file cannot be read or
             its frontmatter is invalid.
         """
@@ -2665,21 +2540,23 @@ class FileSkillsSource(SkillsSource):
             logger.error("Failed to read SKILL.md at '%s'", skill_file)
             return None
 
-        frontmatter = FileSkillsSource._extract_frontmatter(content, str(skill_file))
-        if frontmatter is None:
+        result = FileSkillsSource._extract_frontmatter(content, str(skill_file))
+        if result is None:
             return None
 
+        name, description = result
+
         dir_name = Path(skill_dir_path).name
-        if frontmatter.name != dir_name:
+        if name != dir_name:
             logger.error(
                 "SKILL.md at '%s' has frontmatter name '%s' that does not match the directory name '%s'; skipping.",
                 skill_file,
-                frontmatter.name,
+                name,
                 dir_name,
             )
             return None
 
-        return frontmatter, content
+        return name, description, content
 
     @staticmethod
     def _discover_skill_directories(skill_paths: Sequence[str]) -> list[str]:
@@ -2827,12 +2704,12 @@ class DeduplicatingSkillsSource(DelegatingSkillsSource):
         result: list[Skill] = []
 
         for skill in skills:
-            key = skill.frontmatter.name.lower()
+            key = skill.name.lower()
             if key in seen:
                 logger.warning(
                     "Duplicate skill name '%s': skill skipped in favor of existing skill '%s'",
-                    skill.frontmatter.name,
-                    seen[key].frontmatter.name,
+                    skill.name,
+                    seen[key].name,
                 )
                 continue
             seen[key] = skill
@@ -2853,7 +2730,7 @@ class FilteringSkillsSource(DelegatingSkillsSource):
 
             filtered = FilteringSkillsSource(
                 inner_source=my_source,
-                predicate=lambda s: s.frontmatter.name != "internal",
+                predicate=lambda s: s.name != "internal",
             )
             skills = await filtered.get_skills()
     """

python/packages/core/tests/core/test_mcp.py

@@ -1,7 +1,6 @@
 # Copyright (c) Microsoft. All rights reserved.
 # type: ignore[reportPrivateUsage]
 import asyncio
-import contextlib
 import json
 import logging
 import os
@@ -1616,7 +1615,7 @@ async def test_mcp_connection_reset_integration():
 
 async def test_mcp_tool_message_handler_notification():
     """Test that message_handler correctly processes tools/list_changed and prompts/list_changed
-    notifications by scheduling reloads as background tasks."""
+    notifications."""
     tool = MCPStdioTool(name="test_tool", command="python")
 
     # Mock the load_tools and load_prompts methods
@@ -1630,8 +1629,6 @@ async def test_mcp_tool_message_handler_notification():
 
     result = await tool.message_handler(tools_notification)
     assert result is None
-    # The reload is scheduled as a background task; let it run.
-    await asyncio.sleep(0)
     tool.load_tools.assert_called_once()
 
     # Reset mock
@@ -1644,7 +1641,6 @@ async def test_mcp_tool_message_handler_notification():
 
     result = await tool.message_handler(prompts_notification)
     assert result is None
-    await asyncio.sleep(0)
     tool.load_prompts.assert_called_once()
 
     # Test unhandled notification
@@ -1668,112 +1664,6 @@ async def test_mcp_tool_message_handler_error():
     assert result is None
 
 
-async def test_mcp_tool_message_handler_does_not_block_receive_loop():
-    """Test that message_handler does not deadlock the MCP receive loop.
-
-    Regression test for https://github.com/microsoft/agent-framework/issues/4828.
-    When the MCP server sends a ``notifications/tools/list_changed``
-    notification, the handler must NOT await ``load_tools()`` synchronously
-    because that would block the single-threaded MCP receive loop, preventing
-    it from delivering the ``list_tools`` response — a classic deadlock.
-    """
-    tool = MCPStdioTool(name="test_tool", command="python")
-
-    # Use an event to make load_tools block until we release it.
-    # This simulates load_tools waiting for a session response that the
-    # receive loop would need to deliver.
-    release = asyncio.Event()
-
-    async def slow_load_tools():
-        await release.wait()
-
-    tool.load_tools = slow_load_tools  # type: ignore[assignment]
-
-    tools_notification = Mock(spec=types.ServerNotification)
-    tools_notification.root = Mock()
-    tools_notification.root.method = "notifications/tools/list_changed"
-
-    # message_handler must return immediately even though load_tools blocks.
-    await tool.message_handler(tools_notification)
-
-    # If the handler had awaited load_tools synchronously, we would never
-    # reach this line (deadlock). Verify the reload task is pending.
-    assert len(tool._pending_reload_tasks) == 1
-
-    # Unblock the reload so the background task finishes cleanly.
-    release.set()
-    # Wait for the pending reload task(s) to complete so their done-callbacks
-    # have a chance to remove them from _pending_reload_tasks.
-    await asyncio.wait_for(asyncio.gather(*tool._pending_reload_tasks), timeout=1)
-    assert len(tool._pending_reload_tasks) == 0
-
-
-async def test_mcp_tool_message_handler_reload_failure_is_logged(caplog: pytest.LogCaptureFixture):
-    """Background reload errors are logged, not raised into the receive loop."""
-    tool = MCPStdioTool(name="test_tool", command="python")
-    tool.load_tools = AsyncMock(side_effect=RuntimeError("connection lost"))
-
-    tools_notification = Mock(spec=types.ServerNotification)
-    tools_notification.root = Mock()
-    tools_notification.root.method = "notifications/tools/list_changed"
-
-    await tool.message_handler(tools_notification)
-    # Let the background task run — it should not propagate the exception.
-    # Snapshot tasks and await them to ensure done-callbacks fire.
-    pending = list(tool._pending_reload_tasks)
-    if pending:
-        await asyncio.wait_for(asyncio.gather(*pending, return_exceptions=True), timeout=1)
-    tool.load_tools.assert_called_once()
-    assert len(tool._pending_reload_tasks) == 0
-
-    # Verify the warning was actually logged with exception info.
-    reload_warnings = [r for r in caplog.records if "Background MCP reload failed" in r.message]
-    assert len(reload_warnings) == 1
-    assert reload_warnings[0].levelname == "WARNING"
-    assert reload_warnings[0].exc_info is not None
-
-
-async def test_mcp_tool_message_handler_cancel_and_replace():
-    """Sending two notifications in quick succession cancels the first reload task."""
-    tool = MCPStdioTool(name="test_tool", command="python")
-
-    release = asyncio.Event()
-    call_count = 0
-
-    async def blocking_load_tools():
-        nonlocal call_count
-        call_count += 1
-        await release.wait()
-
-    tool.load_tools = blocking_load_tools  # type: ignore[assignment]
-
-    notification = Mock(spec=types.ServerNotification)
-    notification.root = Mock()
-    notification.root.method = "notifications/tools/list_changed"
-
-    # First notification — starts a blocking reload task.
-    await tool.message_handler(notification)
-    assert len(tool._pending_reload_tasks) == 1
-    first_task = next(iter(tool._pending_reload_tasks))
-
-    # Second notification — should cancel the first and replace it.
-    await tool.message_handler(notification)
-    # Yield to the event loop so the cancellation is processed.
-    with contextlib.suppress(asyncio.CancelledError):
-        await first_task
-
-    assert first_task.cancelled()
-
-    assert len(tool._pending_reload_tasks) == 1
-    second_task = next(iter(tool._pending_reload_tasks))
-    assert second_task is not first_task
-
-    # Unblock and let the second task finish.
-    release.set()
-    await asyncio.wait_for(asyncio.gather(*tool._pending_reload_tasks), timeout=1)
-    assert len(tool._pending_reload_tasks) == 0
-
-
 async def test_mcp_tool_sampling_callback_no_client():
     """Test sampling callback error path when no chat client is available."""
     tool = MCPStdioTool(name="test_tool", command="python")

python/samples/02-agents/skills/code_defined_skill/code_defined_skill.py

@@ -11,7 +11,7 @@ import os
 from textwrap import dedent
 from typing import Any
 
-from agent_framework import Agent, InlineSkill, InlineSkillResource, SkillFrontmatter, SkillsProvider
+from agent_framework import Agent, InlineSkill, InlineSkillResource, SkillsProvider
 from agent_framework.foundry import FoundryChatClient
 from azure.identity import AzureCliCredential
 from dotenv import load_dotenv
@@ -47,9 +47,8 @@ load_dotenv()
 # 1. Static Resources — inline content passed at construction time
 # ---------------------------------------------------------------------------
 unit_converter_skill = InlineSkill(
-    frontmatter=SkillFrontmatter(
-        name="unit-converter", description="Convert between common units using a conversion factor"
-    ),
+    name="unit-converter",
+    description="Convert between common units using a conversion factor",
     instructions=dedent("""\
         Use this skill when the user asks to convert between units.
 

python/samples/02-agents/skills/file_based_skill/skills/unit-converter/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: unit-converter
 description: Convert between common units using a multiplication factor. Use when asked to convert miles, kilometers, pounds, or kilograms.
-license: MIT
-compatibility: Works with any model that supports tool use.
-allowed-tools: convert
-metadata:
-  author: agent-framework-samples
-  version: "1.0"
 ---
 
 ## Usage

python/samples/02-agents/skills/mixed_skills/mixed_skills.py

@@ -21,7 +21,6 @@ from agent_framework import (
     FileSkillsSource,
     InlineSkill,
     InMemorySkillsSource,
-    SkillFrontmatter,
     SkillsProvider,
 )
 from agent_framework.foundry import FoundryChatClient
@@ -74,9 +73,8 @@ load_dotenv()
 # ---------------------------------------------------------------------------
 
 volume_converter_skill = InlineSkill(
-    frontmatter=SkillFrontmatter(
-        name="volume-converter", description="Convert between gallons and liters using a conversion factor"
-    ),
+    name="volume-converter",
+    description="Convert between gallons and liters using a conversion factor",
     instructions=dedent("""\
         Use this skill when the user asks to convert between gallons and liters.
 
@@ -120,7 +118,6 @@ def convert_volume(value: float, factor: float) -> str:
 # 2. Define a class-based skill for temperature conversion
 # ---------------------------------------------------------------------------
 
-
 class TemperatureConverterSkill(ClassSkill):
     """A temperature-converter skill defined as a Python class.
 
@@ -130,10 +127,8 @@ class TemperatureConverterSkill(ClassSkill):
 
     def __init__(self) -> None:
         super().__init__(
-            frontmatter=SkillFrontmatter(
-                name="temperature-converter",
-                description="Convert between temperature scales (Fahrenheit, Celsius, Kelvin).",
-            )
+            name="temperature-converter",
+            description="Convert between temperature scales (Fahrenheit, Celsius, Kelvin).",
         )
 
     @property
@@ -183,7 +178,6 @@ class TemperatureConverterSkill(ClassSkill):
 # 3. Wire everything together and run the agent
 # ---------------------------------------------------------------------------
 
-
 async def main() -> None:
     """Run the combined skills demo."""
     endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]

python/samples/02-agents/skills/mixed_skills/skills/unit-converter/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: unit-converter
 description: Convert between common units using a multiplication factor. Use when asked to convert miles, kilometers, pounds, or kilograms.
-license: MIT
-compatibility: Works with any model that supports tool use.
-allowed-tools: convert
-metadata:
-  author: agent-framework-samples
-  version: "1.0"
 ---
 
 ## Usage

python/samples/02-agents/skills/script_approval/script_approval.py

@@ -9,7 +9,7 @@ import os
 # warnings.filterwarnings("ignore", message=r"\[SKILLS\].*", category=FutureWarning)
 from textwrap import dedent
 
-from agent_framework import Agent, InlineSkill, SkillFrontmatter, SkillsProvider
+from agent_framework import Agent, InlineSkill, SkillsProvider
 from agent_framework.foundry import FoundryChatClient
 from azure.identity import AzureCliCredential
 from dotenv import load_dotenv
@@ -43,9 +43,8 @@ load_dotenv()
 
 # Define a code skill with a script that performs a sensitive operation
 deployment_skill = InlineSkill(
-    frontmatter=SkillFrontmatter(
-        name="deployment", description="Tools for deploying application versions to production"
-    ),
+    name="deployment",
+    description="Tools for deploying application versions to production",
     instructions=dedent("""\
         Use this skill when the user asks to deploy an application.
 

python/samples/02-agents/skills/skill_filtering/skill_filtering.py

@@ -75,7 +75,7 @@ async def main() -> None:
         FilteringSkillsSource(
             FileSkillsSource(str(skills_dir), script_runner=subprocess_script_runner),
             # Only keep the volume-converter skill
-            predicate=lambda s: s.frontmatter.name != "length-converter",
+            predicate=lambda s: s.name != "length-converter",
         )
     )
 

python/samples/02-agents/skills/skill_filtering/skills/length-converter/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: length-converter
 description: Convert between common length units (miles, km, feet, meters) using a multiplication factor.
-license: MIT
-compatibility: Works with any model that supports tool use.
-allowed-tools: convert
-metadata:
-  author: agent-framework-samples
-  version: "1.0"
 ---
 
 ## Usage

python/samples/02-agents/skills/skill_filtering/skills/volume-converter/SKILL.md

@@ -1,12 +1,6 @@
 ---
 name: volume-converter
 description: Convert between gallons and liters using a conversion factor.
-license: MIT
-compatibility: Works with any model that supports tool use.
-allowed-tools: convert
-metadata:
-  author: agent-framework-samples
-  version: "1.0"
 ---
 
 ## Usage

python/uv.lock

@@ -602,7 +602,7 @@ dependencies = [
 [package.metadata]
 requires-dist = [
     { name = "agent-framework-core", editable = "packages/core" },
-    { name = "github-copilot-sdk", marker = "python_full_version >= '3.11'", specifier = ">=1.0.0b2,<=1.0.0b2" },
+    { name = "github-copilot-sdk", marker = "python_full_version >= '3.11'", specifier = "<=1.0.0b2,>=1.0.0b2" },
 ]
 
 [[package]]