mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
.NET: Surface x-ms-served-model header as ChatResponse.ModelId for Foundry agents (#5979)
* .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>
This commit is contained in:
Roger Barreto
committed by
GitHub
Unverified
GitHub
parent
c8b8198af1
commit
afd2739e38
@@ -27,9 +27,9 @@ namespace Microsoft.Agents.AI.Foundry;
|
||||
/// Foundry chat-client decorator that unifies the three Foundry chat-client construction
|
||||
/// modes (Responses Agent, Prompt Agent, Agent Endpoint) behind a single type and centralizes
|
||||
/// Foundry-specific concerns: <c>microsoft.foundry</c> telemetry tagging,
|
||||
/// <c>agent-framework-dotnet/{version}</c> User-Agent stamping, and (for Prompt Agents)
|
||||
/// per-request payload mutation that injects the agent reference and strips per-request
|
||||
/// overrides that the server owns.
|
||||
/// <c>agent-framework-dotnet/{version}</c> User-Agent stamping, <c>x-ms-served-model</c>
|
||||
/// response-header capture, and (for Prompt Agents) per-request payload mutation that injects
|
||||
/// the agent reference and strips per-request overrides that the server owns.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// <para>
|
||||
@@ -78,6 +78,7 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
this._aiProjectClient = aiProjectClient;
|
||||
this._metadata = new ChatClientMetadata("microsoft.foundry", defaultModelId: modelId);
|
||||
TryRegisterAgentFrameworkUserAgentPolicy(this.InnerClient);
|
||||
TryRegisterServedModelPolicy(this.InnerClient);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
@@ -96,6 +97,7 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
this._baseChatOptions = baseChatOptions;
|
||||
this.AgentName = agentReference.Name;
|
||||
TryRegisterAgentFrameworkUserAgentPolicy(this.InnerClient);
|
||||
TryRegisterServedModelPolicy(this.InnerClient);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
@@ -161,6 +163,7 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
this.AgentName = inner.AgentName;
|
||||
this._metadata = new ChatClientMetadata("microsoft.foundry");
|
||||
TryRegisterAgentFrameworkUserAgentPolicy(this.InnerClient);
|
||||
TryRegisterServedModelPolicy(this.InnerClient);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
@@ -212,7 +215,25 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
? this.GetAgentEnabledChatOptions(options)
|
||||
: options;
|
||||
|
||||
return await base.GetResponseAsync(messages, effectiveOptions, cancellationToken).ConfigureAwait(false);
|
||||
var box = new StrongBox<string?>(null);
|
||||
var previous = ServedModelScope.Current;
|
||||
ServedModelScope.Current = box;
|
||||
|
||||
try
|
||||
{
|
||||
var response = await base.GetResponseAsync(messages, effectiveOptions, cancellationToken).ConfigureAwait(false);
|
||||
|
||||
if (box.Value is { } servedModel)
|
||||
{
|
||||
response.ModelId = servedModel;
|
||||
}
|
||||
|
||||
return response;
|
||||
}
|
||||
finally
|
||||
{
|
||||
ServedModelScope.Current = previous;
|
||||
}
|
||||
}
|
||||
|
||||
/// <inheritdoc/>
|
||||
@@ -222,9 +243,25 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
? this.GetAgentEnabledChatOptions(options)
|
||||
: options;
|
||||
|
||||
await foreach (var chunk in base.GetStreamingResponseAsync(messages, effectiveOptions, cancellationToken).ConfigureAwait(false))
|
||||
var box = new StrongBox<string?>(null);
|
||||
var previous = ServedModelScope.Current;
|
||||
ServedModelScope.Current = box;
|
||||
|
||||
try
|
||||
{
|
||||
yield return chunk;
|
||||
await foreach (var chunk in base.GetStreamingResponseAsync(messages, effectiveOptions, cancellationToken).ConfigureAwait(false))
|
||||
{
|
||||
if (box.Value is { } servedModel)
|
||||
{
|
||||
chunk.ModelId = servedModel;
|
||||
}
|
||||
|
||||
yield return chunk;
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
ServedModelScope.Current = previous;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -628,6 +665,25 @@ public sealed class FoundryChatClient : DelegatingChatClient
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Best-effort registration of <see cref="ServedModelPolicy"/> via the MEAI
|
||||
/// <see cref="OpenAIRequestPolicies"/> hook. The policy captures the
|
||||
/// <c>x-ms-served-model</c> response header from Azure OpenAI and writes it into
|
||||
/// <see cref="ServedModelScope"/> so the <see cref="GetResponseAsync"/> and
|
||||
/// <see cref="GetStreamingResponseAsync"/> overrides can overwrite
|
||||
/// <see cref="ChatResponse.ModelId"/> with the actual model snapshot.
|
||||
/// </summary>
|
||||
private static void TryRegisterServedModelPolicy(IChatClient? innerClient)
|
||||
{
|
||||
if (innerClient?.GetService<OpenAIRequestPolicies>() is { } policies)
|
||||
{
|
||||
OpenAIRequestPoliciesReflection.AddPolicyIfMissing(
|
||||
policies,
|
||||
ServedModelPolicy.Instance,
|
||||
PipelinePosition.PerCall);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>Default OAuth scope for the Azure AI resource. Matches the scope used by <c>Azure.AI.Extensions.OpenAI</c>'s internal authentication helper so the bearer token is accepted by the Foundry control plane.</summary>
|
||||
private const string AzureAiResourceScope = "https://ai.azure.com/.default";
|
||||
|
||||
|
||||
@@ -0,0 +1,67 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using System.ClientModel.Primitives;
|
||||
using System.Collections.Generic;
|
||||
using System.Threading.Tasks;
|
||||
|
||||
namespace Microsoft.Agents.AI.Foundry;
|
||||
|
||||
/// <summary>
|
||||
/// Pipeline policy that captures the <c>x-ms-served-model</c> response header from Azure OpenAI
|
||||
/// and stores it in <see cref="ServedModelScope"/> for consumption by <see cref="FoundryChatClient"/>.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// <para>
|
||||
/// Azure OpenAI Responses API returns the deployment alias in <c>response.model</c> but the actual
|
||||
/// model snapshot (e.g. <c>gpt-5-nano-2025-08-07</c>) in the <c>x-ms-served-model</c> response header.
|
||||
/// This policy extracts the header after the HTTP roundtrip so the <see cref="FoundryChatClient"/>
|
||||
/// can overwrite <c>ChatResponse.ModelId</c> with the true model name.
|
||||
/// </para>
|
||||
/// <para>
|
||||
/// Registered once per <c>OpenAIRequestPolicies</c> instance via the MEAI 10.5.1 extension hook.
|
||||
/// When the header is absent (non-Azure endpoints), the scope is not set and the
|
||||
/// <see cref="FoundryChatClient"/> preserves the original model name.
|
||||
/// </para>
|
||||
/// </remarks>
|
||||
internal sealed class ServedModelPolicy : PipelinePolicy
|
||||
{
|
||||
/// <summary>The Azure OpenAI response header that carries the actual served model name.</summary>
|
||||
internal const string ServedModelHeader = "x-ms-served-model";
|
||||
|
||||
public static ServedModelPolicy Instance { get; } = new ServedModelPolicy();
|
||||
|
||||
private ServedModelPolicy()
|
||||
{
|
||||
}
|
||||
|
||||
public override void Process(PipelineMessage message, IReadOnlyList<PipelinePolicy> pipeline, int currentIndex)
|
||||
{
|
||||
ProcessNext(message, pipeline, currentIndex);
|
||||
CaptureServedModel(message);
|
||||
}
|
||||
|
||||
public override async ValueTask ProcessAsync(PipelineMessage message, IReadOnlyList<PipelinePolicy> pipeline, int currentIndex)
|
||||
{
|
||||
await ProcessNextAsync(message, pipeline, currentIndex).ConfigureAwait(false);
|
||||
CaptureServedModel(message);
|
||||
}
|
||||
|
||||
private static void CaptureServedModel(PipelineMessage message)
|
||||
{
|
||||
if (message.Response is null)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
if (message.Response.Headers.TryGetValue(ServedModelHeader, out string? servedModel)
|
||||
&& !string.IsNullOrWhiteSpace(servedModel))
|
||||
{
|
||||
// Write into the box (reference-type mutation) so the value is visible to the
|
||||
// FoundryChatClient that pushed the box before calling the inner client.
|
||||
if (ServedModelScope.Current is { } box)
|
||||
{
|
||||
box.Value = servedModel.Trim();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,35 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using System.Runtime.CompilerServices;
|
||||
using System.Threading;
|
||||
|
||||
namespace Microsoft.Agents.AI.Foundry;
|
||||
|
||||
/// <summary>
|
||||
/// AsyncLocal carrier that bridges the <c>x-ms-served-model</c> response header value from the
|
||||
/// <see cref="ServedModelPolicy"/> running inside the SCM transport pipeline up to the
|
||||
/// <see cref="FoundryChatClient"/> decorator.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// <para>
|
||||
/// Because <see cref="AsyncLocal{T}"/> mutations inside a child <c>async</c> method do not propagate
|
||||
/// back to the caller (copy-on-write semantics), this scope uses <see cref="StrongBox{T}"/> as an
|
||||
/// indirection layer. The <see cref="FoundryChatClient"/> pushes a fresh box onto the scope
|
||||
/// before calling the inner client; the <see cref="ServedModelPolicy"/> writes into the box's
|
||||
/// <see cref="StrongBox{T}.Value"/> (a reference-type mutation visible to anyone holding the same box).
|
||||
/// After the inner call returns, the client reads the box's value.
|
||||
/// </para>
|
||||
/// </remarks>
|
||||
internal static class ServedModelScope
|
||||
{
|
||||
private static readonly AsyncLocal<StrongBox<string?>?> s_current = new();
|
||||
|
||||
/// <summary>
|
||||
/// Gets or sets the per-async-flow served model box.
|
||||
/// </summary>
|
||||
public static StrongBox<string?>? Current
|
||||
{
|
||||
get => s_current.Value;
|
||||
set => s_current.Value = value;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,85 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using System;
|
||||
using System.Text.RegularExpressions;
|
||||
using System.Threading.Tasks;
|
||||
using AgentConformance.IntegrationTests.Support;
|
||||
using Azure.AI.Projects;
|
||||
using Microsoft.Agents.AI;
|
||||
using Microsoft.Extensions.AI;
|
||||
using Shared.IntegrationTests;
|
||||
|
||||
namespace Foundry.IntegrationTests;
|
||||
|
||||
/// <summary>
|
||||
/// Integration tests validating that the <c>x-ms-served-model</c> response header
|
||||
/// returned by the Azure OpenAI Responses API is surfaced on <see cref="ChatResponse.ModelId"/>.
|
||||
/// </summary>
|
||||
public class ResponsesAgentServedModelTests
|
||||
{
|
||||
// Matches a dated served-model snapshot, e.g. "gpt-5-nano-2025-08-07".
|
||||
private static readonly Regex s_snapshotRegex = new(@"-\d{4}-\d{2}-\d{2}$", RegexOptions.Compiled);
|
||||
|
||||
private static Uri Endpoint => new(TestConfiguration.GetRequiredValue(TestSettings.AzureAIProjectEndpoint));
|
||||
|
||||
private static string DeploymentName => TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName);
|
||||
|
||||
private readonly AIProjectClient _client = new(Endpoint, TestAzureCliCredentials.CreateAzureCliCredential());
|
||||
|
||||
[Fact]
|
||||
public async Task GetResponseAsync_ReturnsServedModelSnapshotOnModelIdAsync()
|
||||
{
|
||||
// Arrange
|
||||
ChatClientAgent agent = this._client.AsAIAgent(
|
||||
model: DeploymentName,
|
||||
instructions: "You are a helpful assistant. Reply with a single short word.",
|
||||
name: "ServedModelTest");
|
||||
|
||||
IChatClient chatClient = agent.ChatClient;
|
||||
|
||||
// Act
|
||||
ChatResponse response = await chatClient.GetResponseAsync(
|
||||
[new ChatMessage(ChatRole.User, "Say hi.")],
|
||||
new ChatOptions { ModelId = DeploymentName });
|
||||
|
||||
// Assert
|
||||
AssertServedModel(response.ModelId);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task RunAsync_AgentResponseRawRepresentationCarriesServedModelAsync()
|
||||
{
|
||||
// Arrange
|
||||
ChatClientAgent agent = this._client.AsAIAgent(
|
||||
model: DeploymentName,
|
||||
instructions: "You are a helpful assistant. Reply with a single short word.",
|
||||
name: "ServedModelTestRun");
|
||||
|
||||
// Act
|
||||
AgentResponse agentResponse = await agent.RunAsync("Say hi.");
|
||||
|
||||
// Assert
|
||||
ChatResponse? chatResponse = agentResponse.RawRepresentation as ChatResponse;
|
||||
Assert.NotNull(chatResponse);
|
||||
AssertServedModel(chatResponse!.ModelId);
|
||||
}
|
||||
|
||||
private static void AssertServedModel(string? modelId)
|
||||
{
|
||||
Assert.False(string.IsNullOrWhiteSpace(modelId), "ChatResponse.ModelId must be populated.");
|
||||
|
||||
// Primary invariant: the served-model value must look like a dated snapshot
|
||||
// (e.g. "gpt-5-nano-2025-08-07"). This is what the x-ms-served-model header carries.
|
||||
// Only when the configured deployment name itself already matches the snapshot pattern
|
||||
// do we fall back to permitting equality with the deployment alias.
|
||||
bool aliasIsSnapshot = s_snapshotRegex.IsMatch(DeploymentName);
|
||||
|
||||
if (aliasIsSnapshot)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
Assert.Matches(s_snapshotRegex, modelId!);
|
||||
Assert.NotEqual(DeploymentName, modelId);
|
||||
}
|
||||
}
|
||||
@@ -555,20 +555,20 @@ public sealed class FoundryChatClientTests
|
||||
|
||||
#endregion
|
||||
|
||||
#region AgentFrameworkUserAgentPolicy registration + dedup
|
||||
#region AgentFrameworkUserAgentPolicy + ServedModelPolicy registration + dedup
|
||||
|
||||
[Fact]
|
||||
public void Register_AgentFrameworkUserAgentPolicy_OnUnderlyingOpenAIRequestPolicies()
|
||||
{
|
||||
// Arrange + Act: constructing a FoundryChatClient should register the
|
||||
// AgentFrameworkUserAgentPolicy on the inner chat client's OpenAIRequestPolicies.
|
||||
// AgentFrameworkUserAgentPolicy and ServedModelPolicy on the inner chat client's OpenAIRequestPolicies.
|
||||
var chatClient = new FoundryChatClient(CreateProjectClient(), "gpt-4o-mini");
|
||||
|
||||
// Assert: the inner chat client (MEAI's OpenAIResponsesChatClient) exposes
|
||||
// OpenAIRequestPolicies via GetService, and our policy is present in its entries.
|
||||
// OpenAIRequestPolicies via GetService, and both policies are present in its entries.
|
||||
var policies = chatClient.GetService<OpenAIRequestPolicies>();
|
||||
Assert.NotNull(policies);
|
||||
Assert.Equal(1, EntriesCount(policies!));
|
||||
Assert.Equal(2, EntriesCount(policies!));
|
||||
}
|
||||
|
||||
[Fact]
|
||||
@@ -576,7 +576,7 @@ public sealed class FoundryChatClientTests
|
||||
{
|
||||
// Arrange: construct via the ProjectsAgentVersion mode-2 variant, which chains via
|
||||
// :this(...) into the AgentReference ctor. If the policy registration code were
|
||||
// inadvertently called twice along the chain, we would see 2 entries.
|
||||
// inadvertently called twice along the chain, we would see more than 2 entries.
|
||||
var projectClient = CreateProjectClient();
|
||||
var agentVersion = ModelReaderWriter.Read<ProjectsAgentVersion>(
|
||||
BinaryData.FromString(TestDataUtil.GetAgentVersionResponseJson()))!;
|
||||
@@ -585,10 +585,10 @@ public sealed class FoundryChatClientTests
|
||||
var chatClient = new FoundryChatClient(projectClient, agentVersion, baseChatOptions: null);
|
||||
|
||||
// Assert: even though the version variant funnels through the AgentReference ctor
|
||||
// via :this(...), the policy is registered exactly once on the inner pipeline.
|
||||
// via :this(...), each policy is registered exactly once on the inner pipeline.
|
||||
var policies = chatClient.GetService<OpenAIRequestPolicies>();
|
||||
Assert.NotNull(policies);
|
||||
Assert.Equal(1, EntriesCount(policies!));
|
||||
Assert.Equal(2, EntriesCount(policies!));
|
||||
Assert.Same(agentVersion, chatClient.GetService<ProjectsAgentVersion>());
|
||||
Assert.NotNull(chatClient.GetService<AgentReference>());
|
||||
}
|
||||
|
||||
+4
-1
@@ -14,11 +14,14 @@
|
||||
<ProjectReference Include="..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
<!-- FoundryEval tests require net8.0+ (MEAI.Evaluation does not support legacy TFMs) -->
|
||||
<!-- Tests requiring net8.0+ (MEAI.Evaluation and some SCM pipeline APIs do not support legacy TFMs) -->
|
||||
<ItemGroup Condition="!$([MSBuild]::IsTargetFrameworkCompatible('$(TargetFramework)', 'net8.0'))">
|
||||
<Compile Remove="FoundryEvalConverterTests.cs" />
|
||||
<Compile Remove="FoundryEvalsTests.cs" />
|
||||
<Compile Remove="ClientHeadersExtensionsTests.cs" />
|
||||
<Compile Remove="ServedModelTestHelpers.cs" />
|
||||
<Compile Remove="ServedModelScopeTests.cs" />
|
||||
<Compile Remove="ServedModelPolicyTests.cs" />
|
||||
</ItemGroup>
|
||||
|
||||
<ItemGroup>
|
||||
|
||||
@@ -0,0 +1,84 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using System.Threading.Tasks;
|
||||
using Microsoft.Extensions.AI;
|
||||
|
||||
#pragma warning disable OPENAI001, MEAI001, MAAI001, SCME0001
|
||||
|
||||
namespace Microsoft.Agents.AI.Foundry.UnitTests;
|
||||
|
||||
/// <summary>
|
||||
/// Unit tests for <see cref="ServedModelPolicy"/>: the SCM pipeline policy that reads the
|
||||
/// <c>x-ms-served-model</c> response header and writes it into the active
|
||||
/// <see cref="ServedModelScope"/> box.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Tests drive the policy through a real OpenAI ResponsesClient SCM pipeline against a mock
|
||||
/// HTTP handler so the policy executes in its production configuration.
|
||||
/// </remarks>
|
||||
public sealed class ServedModelPolicyTests
|
||||
{
|
||||
[Fact]
|
||||
public void Instance_IsSingleton()
|
||||
{
|
||||
Assert.Same(ServedModelPolicy.Instance, ServedModelPolicy.Instance);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task ProcessAsync_HeaderPresent_SetsModelIdOnResponseAsync()
|
||||
{
|
||||
// Arrange
|
||||
using var handler = new ServedModelTestHelpers.ServedModelHandler(ServedModelTestHelpers.MinimalResponseJson(), servedModel: "gpt-5-nano-2025-08-07");
|
||||
IChatClient chatClient = ServedModelTestHelpers.CreateChatClientWithPolicy(handler);
|
||||
|
||||
// Act
|
||||
var response = await chatClient.GetResponseAsync("hi");
|
||||
|
||||
// Assert
|
||||
Assert.Equal("gpt-5-nano-2025-08-07", response.ModelId);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task ProcessAsync_HeaderAbsent_PreservesModelIdFromBodyAsync()
|
||||
{
|
||||
// Arrange
|
||||
using var handler = new ServedModelTestHelpers.ServedModelHandler(ServedModelTestHelpers.MinimalResponseJson(), servedModel: null);
|
||||
IChatClient chatClient = ServedModelTestHelpers.CreateChatClientWithPolicy(handler);
|
||||
|
||||
// Act
|
||||
var response = await chatClient.GetResponseAsync("hi");
|
||||
|
||||
// Assert: ModelId is the deployment alias from the JSON body ("fake").
|
||||
Assert.Equal("fake", response.ModelId);
|
||||
}
|
||||
|
||||
[Theory]
|
||||
[InlineData("")]
|
||||
[InlineData(" ")]
|
||||
public async Task ProcessAsync_EmptyOrWhitespaceHeader_PreservesModelIdFromBodyAsync(string headerValue)
|
||||
{
|
||||
// Arrange
|
||||
using var handler = new ServedModelTestHelpers.ServedModelHandler(ServedModelTestHelpers.MinimalResponseJson(), servedModel: headerValue);
|
||||
IChatClient chatClient = ServedModelTestHelpers.CreateChatClientWithPolicy(handler);
|
||||
|
||||
// Act
|
||||
var response = await chatClient.GetResponseAsync("hi");
|
||||
|
||||
// Assert: empty/whitespace header is rejected by the policy, ModelId stays as "fake".
|
||||
Assert.Equal("fake", response.ModelId);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task ProcessAsync_HeaderWithSurroundingWhitespace_TrimsValueAsync()
|
||||
{
|
||||
// Arrange
|
||||
using var handler = new ServedModelTestHelpers.ServedModelHandler(ServedModelTestHelpers.MinimalResponseJson(), servedModel: " gpt-5-nano-2025-08-07 ");
|
||||
IChatClient chatClient = ServedModelTestHelpers.CreateChatClientWithPolicy(handler);
|
||||
|
||||
// Act
|
||||
var response = await chatClient.GetResponseAsync("hi");
|
||||
|
||||
// Assert
|
||||
Assert.Equal("gpt-5-nano-2025-08-07", response.ModelId);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,40 @@
|
||||
// Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
using System.Runtime.CompilerServices;
|
||||
|
||||
namespace Microsoft.Agents.AI.Foundry.UnitTests;
|
||||
|
||||
/// <summary>
|
||||
/// Unit tests for <see cref="ServedModelScope"/>: the AsyncLocal carrier that bridges the
|
||||
/// served-model value from the SCM pipeline policy up to the delegating chat client.
|
||||
/// </summary>
|
||||
public sealed class ServedModelScopeTests
|
||||
{
|
||||
[Fact]
|
||||
public void Current_DefaultIsNull()
|
||||
{
|
||||
Assert.Null(ServedModelScope.Current);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public void Current_SetAndGet_ReturnsBox()
|
||||
{
|
||||
// Arrange
|
||||
var previous = ServedModelScope.Current;
|
||||
|
||||
try
|
||||
{
|
||||
// Act
|
||||
var box = new StrongBox<string?>("gpt-5-nano-2025-08-07");
|
||||
ServedModelScope.Current = box;
|
||||
|
||||
// Assert
|
||||
Assert.Same(box, ServedModelScope.Current);
|
||||
Assert.Equal("gpt-5-nano-2025-08-07", ServedModelScope.Current!.Value);
|
||||
}
|
||||
finally
|
||||
{
|
||||
ServedModelScope.Current = previous;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,80 @@
|
||||
// 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);
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user