Files
agent-framework/dotnet/src/Microsoft.Agents.AI.Foundry/FoundryAgent.cs
T
Roger BarretoandGitHub b12109b7e4 .NET: Bump MEAI to 10.5.1 and add Foundry per-call x-client header support (#5652)
* Bump MEAI to 10.5.1 and add per-call x-client header support

Replaces the brittle UserAgentResponsesClient subclass with a clean
per-call x-client-* header pipeline built on the new Microsoft.Extensions.AI
10.5.1 OpenAIRequestPolicies hook.

Public surface (Microsoft.Agents.AI.Foundry, [Experimental(MAAI001)]):
* chatOptions.WithClientHeader(name, value) and .WithClientHeaders(IEnumerable)
  validate the x-client- prefix (case-insensitive), apply all-or-nothing on
  bulk, and throw InvalidOperationException on foreign-typed slot collision
* myAgent.AsBuilder().UseClientHeaders().Build() opts a customer-built agent
  into the pipeline; idempotent via agent.GetService<ClientHeadersAgent>()
* Foundry-built agents (FoundryAgent.Create*) pre-wire automatically

Internals:
* ClientHeadersAgent decorator snapshots the dict at scope-push time so
  concurrent runs sharing a ChatOptions reference do not leak headers
* ClientHeadersScope is an AsyncLocal<IReadOnlyDictionary<string,string>?>
  with LIFO push/dispose semantics
* ClientHeadersPolicy singleton stamps headers via Headers.Set so per-call
  values overwrite any same-name header from earlier policies and so
  duplicate registration is value-stable
* OpenAIRequestPoliciesReflection dedups against MEAI's private _entries
  field and falls back to AddPolicy on any reflection failure; a CI test
  asserts the field shape on every MEAI bump

Hosting cleanup:
* Deleted UserAgentResponsesClient and its dummy throwing pipeline
* HostedAgentUserAgentPolicy is now registered via OpenAIRequestPolicies
  in FoundryHostingExtensions.TryApplyUserAgent

Tests:
* 19 new unit tests in ClientHeadersExtensionsTests.cs covering validation,
  AsyncLocal isolation, snapshot semantics, end-to-end wire stamping, and
  shared-chat-client dedup
* Updated OpenTelemetryAgentTests for MEAI 10.5.1 changes to web_search
  serialization and the reduced tool definition payload when sensitive
  data capture is disabled

Microsoft.Extensions.Compliance.Abstractions stays at 10.5.0 because no
10.5.1 release exists on nuget.org.

* Address PR review: pre-wire AsAIAgent path and dedup TryApplyUserAgent

* FoundryAgent: extract WireClientHeaders helper and call it from the
  internal (AIProjectClient, ChatClientAgent) constructor used by
  AzureAIProjectChatClientExtensions.AsAIAgent so those Foundry-built
  agents also pre-wire the x-client header pipeline.
* Foundry.Hosting TryApplyUserAgent: dedup HostedAgentUserAgentPolicy
  registration per OpenAIRequestPolicies instance via
  ConditionalWeakTable so per-request resolution does not grow the
  policy list unboundedly on singleton agents.

* Add tests covering AsAIAgent pre-wire and TryApplyUserAgent dedup

Backs the PR review fixes from a4c8f91 with regression tests:
* ClientHeadersExtensionsTests: AsAIAgent_FoundryAgent_HasPreWiredClientHeadersAgent
  asserts the FoundryAgent built via AzureAIProjectChatClientExtensions.AsAIAgent
  contains a ClientHeadersAgent in its delegating chain (catches future
  regressions of the bypass).
* ClientHeadersExtensionsTests: FoundryAgent_PublicConstructor_HasPreWiredClientHeadersAgent
  covers the public constructor path the same way.
* ClientHeadersExtensionsTests: UseClientHeaders_RepeatedRegistrations_OnSameChatClient_OnlyRegistersOnce
  invokes UseClientHeaders 25 times on a shared chat client and asserts via
  reflection that OpenAIRequestPolicies._entries length is exactly 1.
* HostedTryApplyUserAgentDedupTests: two tests asserting
  FoundryHostingExtensions.TryApplyUserAgent stays at one entry per
  OpenAIRequestPolicies instance after 50 calls on the same agent and across
  distinct agents on different chat clients.

* Move tests next to their SUT

Removes the dedicated HostedTryApplyUserAgentDedupTests.cs test class.
Tests are co-located with the SUT they exercise:

* FoundryAgentTests.cs gains the Constructor_PreWiresClientHeadersAgent
  and Constructor_FromAsAIAgentExtension_PreWiresClientHeadersAgent
  cases, since FoundryAgent is the SUT for the pre-wire behavior.
* HostedOutboundUserAgentTests.cs gains the two TryApplyUserAgent dedup
  cases, since FoundryHostingExtensions.TryApplyUserAgent is the SUT
  it already covers.
* ClientHeadersExtensionsTests.cs keeps only the
  UseClientHeaders_RepeatedRegistrations_OnSameChatClient_OnlyRegistersOnce
  case, which exercises the public ClientHeadersExtensions surface.

* Remove redundant WithCancellation on inner streaming call

ct is already passed to InnerAgent.RunStreamingAsync, so
.WithCancellation(ct) on the resulting IAsyncEnumerable is a no-op.
Caught by Sergey on PR review.

* Address PR review: surface downstream MEAI experimental ID

* Add AIOpenAIRequestPolicies = MEAIExperiments alias to
  DiagnosticIds.Experiments (matches the existing AIResponseContinuations,
  AIMcpServers, AIFunctionApprovals pattern).
* Mark public ClientHeadersExtensions with [Experimental(AIOpenAIRequestPolicies)]
  instead of AgentsAIExperiments. Consumers now see the MEAI001 warning,
  surfacing the dependency on MEAI's experimental OpenAIRequestPolicies hook.
* Mark internal OpenAIRequestPoliciesReflection with the same alias to
  suppress warnings at the source rather than via project-wide NoWarn.
* Remove MEAI001 from Foundry csproj NoWarn (kept on Foundry.Hosting where
  pre-PR usages remain).
* Clarify ClientHeadersScope XML doc: AsyncLocal flows values forward but
  does NOT auto-restore on method return; explicit using/Dispose is what
  gives stack-style LIFO semantics.
2026-05-06 14:43:08 +00:00

287 lines
12 KiB
C#

// Copyright (c) Microsoft. All rights reserved.
using System;
using System.ClientModel;
using System.Collections.Generic;
using System.Diagnostics.CodeAnalysis;
using System.Threading;
using System.Threading.Tasks;
using Azure.AI.Extensions.OpenAI;
using Azure.AI.Projects;
using Microsoft.Extensions.AI;
using Microsoft.Extensions.Logging;
using Microsoft.Shared.DiagnosticIds;
using Microsoft.Shared.Diagnostics;
namespace Microsoft.Agents.AI.Foundry;
/// <summary>
/// Provides an <see cref="AIAgent"/> that uses Microsoft Foundry for AI agent capabilities.
/// </summary>
/// <remarks>
/// <para>
/// <see cref="FoundryAgent"/> connects to a pre-configured server-side agent in Microsoft Foundry,
/// wrapping it as an <see cref="AIAgent"/> for use with Agent Framework. Unlike the direct
/// <c>AIProjectClient.AsAIAgent(model, instructions)</c> approach (which creates a local agent
/// backed by the Responses API without any server-side agent definition), <see cref="FoundryAgent"/>
/// works with agents that are managed and versioned in the Foundry service.
/// </para>
/// <para>
/// This class provides convenient access to Foundry-specific features such as server-side
/// conversation management via <see cref="CreateConversationSessionAsync(CancellationToken)"/>.
/// </para>
/// <para>
/// Instances can be created directly via public constructors or through
/// <c>AsAIAgent</c> extension methods on <see cref="AIProjectClient"/>.
/// </para>
/// </remarks>
[Experimental(DiagnosticIds.Experiments.AIOpenAIResponses)]
public sealed class FoundryAgent : DelegatingAIAgent
{
private readonly AIProjectClient _aiProjectClient;
/// <summary>
/// Initializes a new instance of the <see cref="FoundryAgent"/> class using the direct Responses API path.
/// </summary>
/// <param name="projectEndpoint">The Microsoft Foundry project endpoint.</param>
/// <param name="credential">The authentication credential.</param>
/// <param name="model">The model deployment name.</param>
/// <param name="instructions">The instructions that guide the agent's behavior.</param>
/// <param name="clientOptions">Optional configuration options for the <see cref="AIProjectClient"/>.</param>
/// <param name="name">Optional name for the agent.</param>
/// <param name="description">Optional description for the agent.</param>
/// <param name="tools">Optional tools to use when interacting with the agent.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/>.</param>
/// <param name="loggerFactory">Optional logger factory for creating loggers used by the agent.</param>
/// <param name="services">Optional service provider for resolving dependencies required by AI functions.</param>
public FoundryAgent(
Uri projectEndpoint,
AuthenticationTokenProvider credential,
string model,
string instructions,
AIProjectClientOptions? clientOptions = null,
string? name = null,
string? description = null,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
ILoggerFactory? loggerFactory = null,
IServiceProvider? services = null)
: base(CreateInnerAgent(
CreateProjectClient(projectEndpoint, credential, clientOptions),
model, instructions, name, description, tools, clientFactory, loggerFactory, services,
out var aiProjectClient))
{
this._aiProjectClient = aiProjectClient;
}
/// <summary>
/// Initializes a new instance of the <see cref="FoundryAgent"/> class from an agent-specific endpoint.
/// </summary>
/// <param name="agentEndpoint">The agent-specific endpoint URI (must contain the agent name in the path).</param>
/// <param name="credential">The authentication credential.</param>
/// <param name="clientOptions">Optional configuration options for the <see cref="AIProjectClient"/>.</param>
/// <param name="tools">Optional tools to use when interacting with the agent.</param>
/// <param name="clientFactory">Provides a way to customize the creation of the underlying <see cref="IChatClient"/>.</param>
/// <param name="services">Optional service provider for resolving dependencies required by AI functions.</param>
public FoundryAgent(
Uri agentEndpoint,
AuthenticationTokenProvider credential,
AIProjectClientOptions? clientOptions = null,
IList<AITool>? tools = null,
Func<IChatClient, IChatClient>? clientFactory = null,
IServiceProvider? services = null)
: base(CreateInnerAgentFromEndpoint(
CreateProjectClient(agentEndpoint, credential, clientOptions),
agentEndpoint, tools, clientFactory, services,
out var aiProjectClient))
{
this._aiProjectClient = aiProjectClient;
}
/// <summary>
/// Internal constructor used by <c>AsAIAgent</c> extension methods that already have an <see cref="AIProjectClient"/> and a configured <see cref="ChatClientAgent"/>.
/// </summary>
internal FoundryAgent(AIProjectClient aiProjectClient, ChatClientAgent innerAgent)
: base(WireClientHeaders(Throw.IfNull(innerAgent)))
{
this._aiProjectClient = Throw.IfNull(aiProjectClient);
}
#region Convenience methods
/// <summary>
/// Creates a new agent session instance using an existing conversation identifier to continue that conversation.
/// </summary>
/// <param name="conversationId">The identifier of an existing conversation to continue.</param>
/// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests.</param>
/// <returns>
/// A value task representing the asynchronous operation. The task result contains a new <see cref="AgentSession"/> instance configured to work with the specified conversation.
/// </returns>
/// <remarks>
/// <para>
/// This method creates an <see cref="AgentSession"/> that relies on server-side chat history storage, where the chat history
/// is maintained by the underlying AI service rather than by a local <see cref="ChatHistoryProvider"/>.
/// </para>
/// <para>
/// Agent sessions created with this method will only work with <see cref="FoundryAgent"/>
/// instances that support server-side conversation storage through their underlying <see cref="IChatClient"/>.
/// </para>
/// </remarks>
public ValueTask<AgentSession> CreateSessionAsync(string conversationId, CancellationToken cancellationToken = default)
=> this.GetInnerChatClientAgent().CreateSessionAsync(conversationId, cancellationToken);
/// <summary>
/// Creates a server-side conversation session that appears in the Foundry Project UI.
/// </summary>
/// <param name="cancellationToken">A token to monitor for cancellation requests.</param>
/// <returns>A <see cref="ChatClientAgentSession"/> linked to the newly created server-side conversation.</returns>
public async Task<ChatClientAgentSession> CreateConversationSessionAsync(CancellationToken cancellationToken = default)
{
var conversationsClient = this._aiProjectClient
.GetProjectOpenAIClient()
.GetProjectConversationsClient();
var conversation = (await conversationsClient.CreateProjectConversationAsync(options: null, cancellationToken).ConfigureAwait(false)).Value;
return (ChatClientAgentSession)await this.GetInnerChatClientAgent().CreateSessionAsync(conversation.Id, cancellationToken).ConfigureAwait(false);
}
/// <summary>Walks the delegating chain to find the inner <see cref="ChatClientAgent"/>.</summary>
private ChatClientAgent GetInnerChatClientAgent() =>
this.GetService<ChatClientAgent>()
?? throw new InvalidOperationException("FoundryAgent inner chain does not contain a ChatClientAgent.");
#endregion
/// <inheritdoc/>
public override object? GetService(Type serviceType, object? serviceKey = null)
{
if (serviceKey is null && serviceType == typeof(AIProjectClient))
{
return this._aiProjectClient;
}
return base.GetService(serviceType, serviceKey);
}
#region Private helpers
private static AIAgent CreateInnerAgent(
AIProjectClient aiProjectClient,
string model, string instructions,
string? name, string? description,
IList<AITool>? tools,
Func<IChatClient, IChatClient>? clientFactory,
ILoggerFactory? loggerFactory,
IServiceProvider? services,
out AIProjectClient outClient)
{
Throw.IfNullOrWhitespace(model);
Throw.IfNullOrWhitespace(instructions);
outClient = aiProjectClient;
ChatClientAgentOptions options = new()
{
Name = name,
Description = description,
ChatOptions = new ChatOptions
{
ModelId = model,
Instructions = instructions,
Tools = tools,
},
};
return CreateResponsesChatClientAgent(aiProjectClient, options, clientFactory, loggerFactory, services);
}
private static AIAgent CreateResponsesChatClientAgent(
AIProjectClient aiProjectClient,
ChatClientAgentOptions agentOptions,
Func<IChatClient, IChatClient>? clientFactory,
ILoggerFactory? loggerFactory,
IServiceProvider? services)
{
Throw.IfNull(aiProjectClient);
Throw.IfNull(agentOptions);
Throw.IfNull(agentOptions.ChatOptions);
Throw.IfNullOrWhitespace(agentOptions.ChatOptions.ModelId);
IChatClient chatClient = new AzureAIProjectResponsesChatClient(aiProjectClient, agentOptions.ChatOptions.ModelId);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return WireClientHeaders(new ChatClientAgent(chatClient, agentOptions, loggerFactory, services));
}
/// <summary>
/// Registers <see cref="ClientHeadersPolicy"/> on the agent's underlying chat client (if it
/// exposes <see cref="OpenAIRequestPolicies"/>) and wraps the agent in a
/// <see cref="ClientHeadersAgent"/> so per-call <c>x-client-*</c> headers stamped via
/// <see cref="ClientHeadersExtensions.WithClientHeader(ChatOptions, string, string)"/> reach
/// the wire. Idempotent: if the chain already contains a <see cref="ClientHeadersAgent"/>,
/// the original instance is returned unchanged.
/// </summary>
private static AIAgent WireClientHeaders(ChatClientAgent innerAgent)
{
if (innerAgent.GetService<ClientHeadersAgent>() is not null)
{
return innerAgent;
}
if (innerAgent.ChatClient.GetService<OpenAIRequestPolicies>() is { } policies)
{
OpenAIRequestPoliciesReflection.AddPolicyIfMissing(
policies,
ClientHeadersPolicy.Instance,
System.ClientModel.Primitives.PipelinePosition.PerCall);
}
return new ClientHeadersAgent(innerAgent);
}
private static AIAgent CreateInnerAgentFromEndpoint(
AIProjectClient aiProjectClient,
Uri agentEndpoint,
IList<AITool>? tools,
Func<IChatClient, IChatClient>? clientFactory,
IServiceProvider? services,
out AIProjectClient outClient)
{
outClient = aiProjectClient;
AgentReference agentReference = agentEndpoint.Segments[^1].TrimEnd('/');
ChatClientAgentOptions agentOptions = new()
{
Name = agentReference.Name,
ChatOptions = new() { Tools = tools },
};
IChatClient chatClient = new AzureAIProjectChatClient(aiProjectClient, agentReference, defaultModelId: null, agentOptions.ChatOptions);
if (clientFactory is not null)
{
chatClient = clientFactory(chatClient);
}
return WireClientHeaders(new ChatClientAgent(chatClient, agentOptions, services: services));
}
private static AIProjectClient CreateProjectClient(Uri endpoint, AuthenticationTokenProvider credential, AIProjectClientOptions? clientOptions = null)
{
Throw.IfNull(endpoint);
Throw.IfNull(credential);
clientOptions ??= new AIProjectClientOptions();
clientOptions.AddPolicy(RequestOptionsExtensions.UserAgentPolicy, System.ClientModel.Primitives.PipelinePosition.PerCall);
return new AIProjectClient(endpoint, credential, clientOptions);
}
#endregion
}