Files
agent-framework/dotnet/tests/Foundry.IntegrationTests/FoundryAgentExtensionsTests.cs
Roger Barreto a12cc3878e .NET: Promote FoundryChatClient to public, add file/vector-store helpers and ToPromptAgentAsync converter (#5940)
* Consolidate Foundry chat client decorators into FoundryChatClient

- Replace AzureAIProjectChatClient and AzureAIProjectResponsesChatClient with a single internal sealed FoundryChatClient that covers three modes (pure responses, server-side agent reference, hosted agent endpoint).
- Rename AzureAIProjectChatClientExtensions to AIProjectClientExtensions to reflect that it extends AIProjectClient.
- All four AsAIAgent extension overloads and both FoundryAgent constructors now construct FoundryChatClient internally so the microsoft.foundry telemetry tag is uniform across paths.
- Introduce AgentFrameworkUserAgentPolicy that stamps agent-framework-dotnet/{version} on outbound requests, mirroring the Python agent-framework-python/{version} contract.
- Delete the Foundry-local MeaiUserAgentPolicy duplicate; rely on MEAI 10.5.1 to stamp MEAI/{version} automatically.
- HostedAgentUserAgentPolicy keeps the combined foundry-hosting/agent-framework-dotnet/{version} segment (Python parity) and upgrades the bare segment in place to avoid duplication.
- Tests reorganized: FoundryChatClientTests, AIProjectClientExtensionsTests, AgentFrameworkUserAgentPolicyTests, MeaiAutoUserAgentVerificationTests, plus in-place upgrade unit tests in HostedOutboundUserAgentTests.

* Promote FoundryChatClient to public; add file/vector-store helpers and ToPromptAgentAsync converter

- Promote FoundryChatClient from internal sealed to public sealed for Python parity, so .NET developers can hold and pass a FoundryChatClient directly the way Python developers do.
- Mode 3 (hosted agent endpoint) now materializes an AIProjectClient from the parsed project root, making GetService<AIProjectClient>() non-null across all three construction modes. This eliminates the per-mode asymmetry that previously hid project-level helpers from agents constructed via an agent endpoint URL.
- Add four new instance methods on FoundryChatClient mirroring Python's spec: UploadFileAsync, DeleteFileAsync, CreateVectorStoreAsync (bundles upload + create + wait), DeleteVectorStoreAsync. Single overload each, path-only inputs to start; additional overloads can be added later without breaking callers. All are Experimental, consistent with the rest of the Foundry package.
- Add ToPromptAgentAsync extension methods on ChatClientAgent and FoundryAgent for the agent-to-prompt-agent converter described in the Foundry spec. Mode 1 (responses API) synthesizes a DeclarativeAgentDefinition from the agent's ChatOptions; mode 2 (server-side agent reference, version, or record) returns the cached or freshly fetched Definition; mode 3 throws InvalidOperationException because no local definition exists to convert.
- Strict AITool to ResponseTool mapping for mode 1: AIFunction becomes CreateFunctionTool with the function's JSON schema; AITool instances that wrap a ResponseTool unwrap via GetService(typeof(ResponseTool)); anything else throws InvalidOperationException naming the offending tool type. Matches the Python spec's unsupported-tools-raise-ValueError contract.
- New unit tests: FoundryChatClientVectorStoreTests (22 tests covering all four helpers across the three FoundryChatClient construction modes plus validation and cancellation), FoundryPromptAgentConverterTests (16 tests covering both extension entry points across mode 1 synthesis, mode 2 cached and fetched paths, all failure modes, and a Python-parity guard asserting both extensions produce equivalent definitions for equivalent inputs), plus four new tests in FoundryChatClientTests for the mode 3 AIProjectClient materialization.

* Stop building duplicate ProjectOpenAIClient in FoundryAgent agent-endpoint ctor

After Plan #2's mode-3 AIProjectClient materialization, the inner FoundryChatClient already exposes a project-level AIProjectClient (via GetService) that internally provides the project-level ProjectOpenAIClient via GetProjectOpenAIClient(). FoundryAgent's agent-endpoint constructor was still independently constructing a second project-level ProjectOpenAIClient via the now-redundant CreateProjectLevelOpenAIClientFromAgentEndpoint helper — two handles to the same logical resource.

Refactor: the agent-endpoint constructor now reads the inner FoundryChatClient's materialized AIProjectClient via base.GetService(typeof(AIProjectClient)) and derives the project-level ProjectOpenAIClient from it. The dead helper on both FoundryAgent (private static wrapper) and FoundryChatClient (the actual implementation) is removed. The user-supplied per-agent ClientPipelineOptions primitives (Transport, RetryPolicy, NetworkTimeout, UserAgentApplicationId) are propagated into the materialized AIProjectClientOptions so test-injected transports and explicit retry / timeout / user-agent settings reach the project-level pipeline — preserving the behavior the dead helper used to provide.

Updated AgentEndpointConstructor_GetServiceAIProjectClient_ReturnsNull to its now-correct counterpart AgentEndpointConstructor_GetServiceAIProjectClient_ReturnsNonNull, since after Plan #2 the agent-endpoint ctor surfaces a non-null AIProjectClient (per user direction in Plan #2 Q2).

* Strip duplicated AIProjectClient/ProjectOpenAIClient state from FoundryAgent

Both _aiProjectClient and _projectOpenAIClient fields on FoundryAgent were redundant:

- _aiProjectClient: FoundryAgent's GetService<AIProjectClient> override returned this field, but DelegatingAIAgent.GetService → ChatClientAgent.GetService → FoundryChatClient.GetService<AIProjectClient> already returns the same instance through the delegating chain. Field + override are pure duplication.

- _projectOpenAIClient: only used by FoundryAgent's own GetService<ProjectOpenAIClient> override and by CreateConversationSessionAsync. Per user direction, ProjectOpenAIClient is no longer exposed via GetService on either FoundryChatClient or FoundryAgent — callers retrieve it from the AIProjectClient themselves (aiProjectClient.GetProjectOpenAIClient()) the same way the framework does internally. This eliminates the mode-3 asymmetry where the chat client's stored ProjectOpenAIClient was per-agent (URL /agents/{name}/endpoint/protocols/openai) while the agent's was project-level.

Refactor:
- Delete both fields on FoundryAgent and the GetService override.
- Delete the ProjectOpenAIClient branch from FoundryChatClient.GetService.
- CreateConversationSessionAsync now resolves AIProjectClient at call time via this.GetService<AIProjectClient>() and derives the conversations client from it.
- Update FoundryChatClient tests that asserted on GetService<ProjectOpenAIClient> to assert Null (deliberate removal).
- Update FoundryAgent tests AgentEndpointConstructor_GetServiceProjectOpenAIClient_ReturnsNonNull and ProjectEndpointConstructor_GetServiceProjectOpenAIClient_ReturnsNonNull to ...ReturnsNull, and rewrite AgentEndpointConstructor_PropagatesUserAgentApplicationId_ToProjectLevelClient to look up AIProjectClient instead.

No production code (only tests) referenced GetService<ProjectOpenAIClient>, so this is a safe surface reduction. Net: 30 insertions, 61 deletions; FoundryAgent shrinks to a pure delegator with only the two convenience methods (CreateSessionAsync, CreateConversationSessionAsync) on top of the delegating chain.

* Rename FoundryChatClient.HostedAgentName to AgentName and populate it for mode 2

The previous name implied a mode 3 only property tied to the hosted-agent endpoint URL. Today only hosted endpoints surface this name, but conceptually an agent name exists for every server-side agent the client talks to. Renaming to AgentName makes the property general-purpose and ready for future modes where the same chat client may target other server-side agent shapes that are not necessarily 'hosted'.

Mode 2 (server-side agent reference) now mirrors AgentReference.Name into AgentName so callers have a uniform handle regardless of construction mode:

* Mode 1 (pure responses): AgentName is null. There is no agent.
* Mode 2 (AgentReference): AgentName == AgentReference.Name.
* Mode 3 (agent endpoint URL): AgentName is parsed from the URL segment as before.

Converter discriminator update: FoundryPromptAgentConverter previously used 'HostedAgentName is not null' to detect mode 3 and reject it. Now that mode 2 also populates AgentName, the mode 3 guard moves to the end of the resolution chain and uses the unambiguous 'AgentName is set AND no AgentReference exists' test. The user-visible error message and behavior are preserved.

Dead-state cleanup spotted during format verify:

* IDE0052 surfaced that FoundryChatClient._projectOpenAIClient is never read since the prior refactor stopped exposing ProjectOpenAIClient via GetService and rewired CreateConversationSessionAsync to resolve the AIProjectClient through the delegating chain. The field is deleted and its three ctor assignments removed.
* HostedAgentEndpointInner.PerAgentClient only existed to plumb the per-agent ProjectOpenAIClient into that now-deleted field, so the property and its ctor parameter are removed. The local 'perAgentClient' variable inside BuildHostedAgentEndpointInner is still needed to derive the inner IChatClient, but no longer escapes the helper.

Tests:

* Mode1_PureResponses_ReturnsNullForAgentSpecificServices now also asserts AgentName is null.
* New Mode2_AgentReference_PopulatesAgentNameFromAgentReference asserts the mode 2 mirror.
* Mode3_HostedAgentEndpoint_ParsesAgentNameFromUrl renamed assertion target HostedAgentName to AgentName.

Verification: 335/335 net10.0, 273/273 net472 Foundry unit; 229/229 Foundry.Hosting unit; format-verify (WSL2 + Docker mcr.microsoft.com/dotnet/sdk:10.0) clean on Microsoft.Agents.AI.Foundry.

* Adopt canonical mode names: Responses Agent, Prompt Agent, Agent Endpoint

Three FoundryChatClient construction modes now have one canonical noun used everywhere.

* Responses Agent (Mode 1): inline ChatClientAgent, project-level Responses API, no server-side def.
* Prompt Agent (Mode 2): server-side ProjectsAgentDefinition invoked by AgentReference.
* Agent Endpoint (Mode 3): per-agent URL /agents/{name}/endpoint/protocols/openai. Hosted-or-not.

'Hosted' stays the kind of agent (Microsoft.Agents.AI.Foundry.Hosting). Not synonym of Mode 3.

Rings:
1. XML docs + error messages use canonical names. en-GB to en-US: centralises, synthesise.
2. HostedAgentEndpointInner -> AgentEndpointInner, BuildHostedAgentEndpointInner -> BuildAgentEndpointInner.
3. Tests: Mode1_PureResponses_* -> Mode1_ResponsesAgent_*, Mode2_AgentReference_* -> Mode2_PromptAgent_*, Mode3_HostedAgentEndpoint_* -> Mode3_AgentEndpoint_*.

Pure rename. No behavior change. 335/335 net10 + 273/273 net472 unit, format clean.

* Address PR #5940 design feedback (Q-A through Q-F)

Q-A: poll vector store til status leaves InProgress before return. Exp backoff 250ms-2s. Honor cancel.
Q-B: try/catch upload loop. Mid-fail = best-effort DeleteFileAsync on already-uploaded ids. Swallow cleanup errors.
Q-C: pinned AgentReference.Version uses GetAgentVersionAsync. Empty/whitespace/'latest' = GetLatest path.
Q-D: HostedAgentUserAgentPolicy detects existing combined 'foundry-hosting/...' segment. No double prefix.
Q-E: mode-3 vector-store test uses fake transport. No DNS to example.com.
Q-F: no shim. Class always [Experimental] (since 8015e00f5, before dotnet-1.0.0). No compat contract. Callers rename to AIProjectClientExtensions.

Rebase onto origin/main reconciliation: aad20c2b3 added public AsAIAgent(this AIProjectClient, Uri agentEndpoint, ...) extension that calls an internal FoundryAgent(AIProjectClient, Uri, ...) ctor. Reintroduced that ctor + a new FoundryChatClient(AIProjectClient, Uri, ProjectOpenAIClientOptions?) overload that reuses the supplied AIProjectClient's pipeline (via GetProjectResponsesClientForAgentEndpoint) instead of stamping a fresh credential.

Verified: 346/346 net10 + 284/284 net472 Foundry unit, 230/230 Foundry.Hosting unit, format clean.

* Add FoundryAgent helper extensions: UploadFile/DeleteFile/CreateVectorStore/DeleteVectorStore

4 thin forwarders on FoundryAgent that route to the inner FoundryChatClient's helpers via agent.GetService<FoundryChatClient>().X(). Live in existing FoundryAgentExtensions.cs alongside ToPromptAgentAsync.

Throws InvalidOperationException when agent does not expose a FoundryChatClient via GetService (same pattern as ToPromptAgentAsync).

Unit tests: FoundryAgentExtensionsTests covers all 4 forwarders + null-agent ArgumentNullException for each. 8 new tests, 354/354 net10 + 292/292 net472.

Integration tests: parallel FoundryAgentExtensionsTests under Foundry.IntegrationTests mirrors the existing CreateAgent_CreatesAgentWithVectorStoresAsync shape (upload -> create vector store -> FileSearch tool answers question -> cleanup), but routes every helper call through the new FoundryAgent extensions. 4 new IT tests, all verified pass live against the real Foundry project (12-30s each). Skipped by default like the existing vector-store IT.

* Address Sergey's PR review comments

#1 (FoundryAgent.cs:139): drop unused aiProjectClient param from internal FoundryAgent(AIProjectClient, ChatClientAgent) ctor. Was discarded after null-check. Inner FoundryChatClient already surfaces AIProjectClient via GetService. 3 call sites in AIProjectClientExtensions updated.

#2 (FoundryChatClient.cs:376): add pollingTimeout param to CreateVectorStoreAsync. Defaults to 5 min, configurable, Timeout.InfiniteTimeSpan disables. Throws TimeoutException with vector store id and elapsed seconds when bound exceeded. CancellationToken still wins. New unit test PollingTimeout_ThrowsTimeoutExceptionAsync. FoundryAgentExtensions forwarder updated to plumb the new param.

Verified: 355/355 net10 + 293/293 net472 Foundry unit, 230/230 Foundry.Hosting unit, format clean.
2026-05-21 10:05:58 +00:00

230 lines
9.5 KiB
C#

// Copyright (c) Microsoft. All rights reserved.
using System;
using System.IO;
using System.Threading.Tasks;
using AgentConformance.IntegrationTests.Support;
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Foundry;
using OpenAI.Files;
using OpenAI.Responses;
using OpenAI.VectorStores;
using Shared.IntegrationTests;
namespace Foundry.IntegrationTests;
/// <summary>
/// Integration tests for the file and vector-store forwarder extensions on
/// <see cref="FoundryAgent"/> declared in <see cref="FoundryAgentExtensions"/>. End-to-end
/// counterparts of the unit tests in
/// <c>FoundryAgentExtensionsTests</c> that exercise the live Foundry project pipeline.
/// </summary>
/// <remarks>
/// Mirrors <see cref="FoundryVersionedAgentCreateTests.CreateAgent_CreatesAgentWithVectorStoresAsync(string)"/>
/// in shape (file upload → vector store creation → FileSearchTool answer → cleanup), but routes
/// every helper call through the new <see cref="FoundryAgent"/> extensions instead of the raw
/// <c>projectOpenAIClient.GetProjectFilesClient()</c> / <c>GetProjectVectorStoresClient()</c>
/// path. Skipped by default for the same reasons as the existing vector-store IT (cost and
/// runtime); flip Skip to run manually after seeding the right Foundry project.
/// </remarks>
public class FoundryAgentExtensionsTests
{
private readonly AIProjectClient _client = new(
new Uri(TestConfiguration.GetRequiredValue(TestSettings.AzureAIProjectEndpoint)),
TestAzureCliCredentials.CreateAzureCliCredential());
[Fact(Skip = "For manual testing only")]
public async Task UploadFileAsync_ViaAgentExtension_UploadsToProjectAsync()
{
// Arrange — non-versioned Responses Agent (Mode 1) so we do not have to provision a server-side agent.
var agent = this._client.AsAIAgent(
model: TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName),
instructions: "Be helpful.");
var foundryAgent = this.WrapAsFoundryAgent(agent);
var filePath = Path.GetTempFileName() + ".txt";
File.WriteAllText(filePath, "agent-extensions integration test payload");
OpenAIFile? uploaded = null;
try
{
// Act.
uploaded = await foundryAgent.UploadFileAsync(filePath, FileUploadPurpose.Assistants);
// Assert.
Assert.NotNull(uploaded);
Assert.False(string.IsNullOrEmpty(uploaded.Id));
Assert.Equal(Path.GetFileName(filePath), uploaded.Filename);
}
finally
{
if (uploaded is not null)
{
await foundryAgent.DeleteFileAsync(uploaded.Id);
}
File.Delete(filePath);
}
}
[Fact(Skip = "For manual testing only")]
public async Task DeleteFileAsync_ViaAgentExtension_RemovesUploadedFileAsync()
{
var agent = this._client.AsAIAgent(
model: TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName),
instructions: "Be helpful.");
var foundryAgent = this.WrapAsFoundryAgent(agent);
var filePath = Path.GetTempFileName() + ".txt";
File.WriteAllText(filePath, "delete-me payload");
try
{
var uploaded = await foundryAgent.UploadFileAsync(filePath, FileUploadPurpose.Assistants);
// Act.
var result = await foundryAgent.DeleteFileAsync(uploaded.Id);
// Assert.
Assert.NotNull(result);
Assert.Equal(uploaded.Id, result.FileId);
Assert.True(result.Deleted);
}
finally
{
File.Delete(filePath);
}
}
[Fact(Skip = "For manual testing only")]
public async Task CreateVectorStoreAsync_ViaAgentExtension_BuildsStoreAndAnswersFileSearchQuestionAsync()
{
// Mirrors CreateAgent_CreatesAgentWithVectorStoresAsync but the upload-then-create-store
// sequence routes through the FoundryAgent.CreateVectorStoreAsync extension (single call
// that uploads, creates the store, and polls until ready). The resulting vector store id
// is then wired to a versioned agent's FileSearch tool and queried for a known value.
string AgentName = FoundryVersionedAgentFixture.GenerateUniqueAgentName("VectorStoreExtAgent");
const string AgentInstructions = """
You are a helpful agent that can help fetch data from files you know about.
Use the File Search Tool to look up codes for words.
Do not answer a question unless you can find the answer using the File Search Tool.
""";
// Non-versioned helper agent that owns the upload pipeline.
var helperAgent = this._client.AsAIAgent(
model: TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName),
instructions: "Be helpful.");
var helperFoundryAgent = this.WrapAsFoundryAgent(helperAgent);
var searchFilePath = Path.GetTempFileName() + "wordcodelookup.txt";
File.WriteAllText(searchFilePath, "The word 'apple' uses the code 442345, while the word 'banana' uses the code 673457.");
VectorStore? vectorStore = null;
FoundryAgent? versionedAgent = null;
try
{
// Act — single agent-level helper call uploads, creates, and waits until ready.
vectorStore = await helperFoundryAgent.CreateVectorStoreAsync(
"WordCodeLookup_ExtensionVectorStore",
new[] { searchFilePath });
Assert.NotNull(vectorStore);
Assert.False(string.IsNullOrEmpty(vectorStore.Id));
Assert.NotEqual(VectorStoreStatus.InProgress, vectorStore.Status);
// Wire the store id into a versioned agent's FileSearch tool to prove it is actually usable.
var definition = new DeclarativeAgentDefinition(TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName))
{
Instructions = AgentInstructions,
Tools = { ResponseTool.CreateFileSearchTool(vectorStoreIds: [vectorStore.Id]) },
};
var agentVersion = await this._client.AgentAdministrationClient.CreateAgentVersionAsync(
AgentName,
new ProjectsAgentVersionCreationOptions(definition));
versionedAgent = this._client.AsAIAgent(agentVersion);
// Assert.
var result = await versionedAgent.RunAsync("Can you give me the documented code for 'banana'?");
Assert.Contains("673457", result.ToString());
}
finally
{
if (versionedAgent is not null)
{
await this._client.AgentAdministrationClient.DeleteAgentAsync(versionedAgent.Name);
}
// Cleanup the vector store via the new extension too.
if (vectorStore is not null)
{
await helperFoundryAgent.DeleteVectorStoreAsync(vectorStore.Id);
}
File.Delete(searchFilePath);
}
}
[Fact(Skip = "For manual testing only")]
public async Task DeleteVectorStoreAsync_ViaAgentExtension_RemovesStoreAsync()
{
var agent = this._client.AsAIAgent(
model: TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName),
instructions: "Be helpful.");
var foundryAgent = this.WrapAsFoundryAgent(agent);
var filePath = Path.GetTempFileName() + ".txt";
File.WriteAllText(filePath, "delete-store payload");
VectorStore? vectorStore = null;
try
{
vectorStore = await foundryAgent.CreateVectorStoreAsync(
"DeleteVectorStore_ExtensionTest",
new[] { filePath });
// Act.
var result = await foundryAgent.DeleteVectorStoreAsync(vectorStore.Id);
// Assert.
Assert.NotNull(result);
Assert.Equal(vectorStore.Id, result.VectorStoreId);
Assert.True(result.Deleted);
vectorStore = null;
}
finally
{
if (vectorStore is not null)
{
await foundryAgent.DeleteVectorStoreAsync(vectorStore.Id);
}
File.Delete(filePath);
}
}
/// <summary>
/// Resolves the underlying <see cref="FoundryAgent"/> from an <see cref="AIAgent"/> handle
/// returned by <c>AIProjectClient.AsAIAgent(model, instructions)</c>. The Mode 1 overload
/// returns a <see cref="ChatClientAgent"/>; the extension forwarders we test live on
/// <see cref="FoundryAgent"/>, so callers wanting them through this entry point need to
/// reach for the FoundryAgent constructor instead. This helper makes the test setup
/// consistent across the four IT scenarios.
/// </summary>
private FoundryAgent WrapAsFoundryAgent(AIAgent agent)
{
// The Mode 1 AsAIAgent overload returns ChatClientAgent rather than FoundryAgent; use
// the FoundryAgent projectEndpoint+model+instructions ctor to get the same underlying
// FoundryChatClient surfaced through a FoundryAgent typed handle.
_ = agent;
return new FoundryAgent(
projectEndpoint: new Uri(TestConfiguration.GetRequiredValue(TestSettings.AzureAIProjectEndpoint)),
credential: TestAzureCliCredentials.CreateAzureCliCredential(),
model: TestConfiguration.GetRequiredValue(TestSettings.AzureAIModelDeploymentName),
instructions: "Be helpful.");
}
}