mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Roger Barreto
afd2739e38
* .NET: Surface x-ms-served-model header as ChatResponse.ModelId for Foundry agents Mirrors Python PR #5910. Adds an internal SCM PipelinePolicy that reads the x-ms-served-model HTTP response header on Azure OpenAI Responses calls and writes it into an AsyncLocal box. A DelegatingChatClient sits between OpenTelemetry and the MEAI OpenAIResponsesChatClient and overwrites ChatResponse.ModelId with the served snapshot so OTel spans report the actual model rather than the deployment alias. Wired through all AsAIAgent paths in Microsoft.Agents.AI.Foundry. * .NET: Fix line endings and BOM on ResponsesAgentServedModelTests * .NET: Address Copilot review on Foundry served-model PR - Restore previous ServedModelScope in finally to avoid AsyncLocal leak into caller execution context. - Make served-model integration test assertion robust to deployment names that already match the snapshot pattern. - Broaden UnitTests csproj comment to cover all conditional removals (net8.0+ requirement). * .NET: Split ServedModelTests into per-SUT files with regions Split the combined ServedModelTests.cs into one test class per SUT: - ServedModelScopeTests.cs (AsyncLocal carrier) - ServedModelPolicyTests.cs (SCM pipeline policy) - ServedModelChatClientTests.cs (delegating client, with regions for Non-streaming / Streaming / End-to-end) Shared helpers and fake clients moved into ServedModelTestHelpers.cs. Csproj net8.0+ exclusion list updated accordingly. * .NET: Consolidate served-model logic into FoundryChatClient Move x-ms-served-model header capture from the standalone ServedModelChatClient decorator directly into FoundryChatClient, eliminating a separate wrapper that had to be applied at every Foundry entry point via WireServedModel(). - Register ServedModelPolicy in FoundryChatClient constructors (alongside the existing AgentFrameworkUserAgentPolicy registration) - Add StrongBox push/read logic to FoundryChatClient.GetResponseAsync and GetStreamingResponseAsync - Delete ServedModelChatClient.cs and its unit tests - Remove WireServedModel() from FoundryAgent and AIProjectClientExtensions - Update ServedModelPolicy/Scope XML docs to reference FoundryChatClient - Simplify ServedModelTestHelpers to use FoundryChatClient directly Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
81 lines
2.8 KiB
C#
81 lines
2.8 KiB
C#
// Copyright (c) Microsoft. All rights reserved.
|
|
|
|
using System;
|
|
using System.ClientModel.Primitives;
|
|
using System.Net;
|
|
using System.Net.Http;
|
|
using System.Text;
|
|
using System.Threading;
|
|
using System.Threading.Tasks;
|
|
using Azure.AI.Projects;
|
|
using Microsoft.Extensions.AI;
|
|
|
|
#pragma warning disable OPENAI001, MEAI001, MAAI001, SCME0001
|
|
|
|
namespace Microsoft.Agents.AI.Foundry.UnitTests;
|
|
|
|
/// <summary>
|
|
/// Shared helpers and fake clients used by the served-model test suite
|
|
/// (<see cref="ServedModelScopeTests"/>, <see cref="ServedModelPolicyTests"/>).
|
|
/// </summary>
|
|
internal static class ServedModelTestHelpers
|
|
{
|
|
public static string MinimalResponseJson() => """
|
|
{
|
|
"id":"resp_1","object":"response","created_at":1700000000,"status":"completed",
|
|
"model":"fake","output":[],"usage":{"input_tokens":1,"output_tokens":1,"total_tokens":2}
|
|
}
|
|
""";
|
|
|
|
/// <summary>
|
|
/// Creates a <see cref="FoundryChatClient"/> backed by a real OpenAI Responses pipeline
|
|
/// routed through the supplied <paramref name="handler"/>. The <see cref="ServedModelPolicy"/>
|
|
/// is registered automatically by the <see cref="FoundryChatClient"/> constructor.
|
|
/// </summary>
|
|
public static IChatClient CreateChatClientWithPolicy(HttpMessageHandler handler)
|
|
{
|
|
#pragma warning disable CA5399
|
|
var http = new HttpClient(handler);
|
|
#pragma warning restore CA5399
|
|
|
|
var projectClient = new AIProjectClient(
|
|
new Uri("https://test.openai.azure.com/"),
|
|
new FakeAuthenticationTokenProvider(),
|
|
new AIProjectClientOptions { Transport = new HttpClientPipelineTransport(http) });
|
|
|
|
return new FoundryChatClient(projectClient, "fake");
|
|
}
|
|
|
|
/// <summary>
|
|
/// An <see cref="HttpClientHandler"/> that returns a fixed response body and optionally
|
|
/// includes the <c>x-ms-served-model</c> response header.
|
|
/// </summary>
|
|
public sealed class ServedModelHandler : HttpClientHandler
|
|
{
|
|
private readonly string _body;
|
|
private readonly string? _servedModel;
|
|
|
|
public ServedModelHandler(string body, string? servedModel)
|
|
{
|
|
this._body = body;
|
|
this._servedModel = servedModel;
|
|
}
|
|
|
|
protected override Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken cancellationToken)
|
|
{
|
|
var resp = new HttpResponseMessage(HttpStatusCode.OK)
|
|
{
|
|
Content = new StringContent(this._body, Encoding.UTF8, "application/json"),
|
|
RequestMessage = request,
|
|
};
|
|
|
|
if (this._servedModel is not null)
|
|
{
|
|
resp.Headers.Add("x-ms-served-model", this._servedModel);
|
|
}
|
|
|
|
return Task.FromResult(resp);
|
|
}
|
|
}
|
|
}
|