mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
aee1acbf8b
* Foundry Evals integration for .NET - Core evaluation framework: EvalItem, LocalEvaluator, FunctionEvaluator, EvalChecks - IAgentEvaluator interface with MeaiEvaluatorAdapter bridge - AgentEvaluationExtensions for agent.EvaluateAsync() overloads - FoundryEvals wrapping MEAI quality/safety evaluators - ConversationSplitters (LastTurn, Full) and IConversationSplitter - EvalItem.PerTurnItems() for multi-turn decomposition - HasImageContent for multimodal content detection - WorkflowEvaluationExtensions for per-agent workflow evaluation - 7 eval samples mirroring Python parity: 02-agents/Evaluation: SimpleEval, ExpectedOutputs, Multimodal 03-workflows/Evaluation: WorkflowEval 05-end-to-end/Evaluation: FoundryQuality, MixedProviders, ConversationSplits - Comprehensive unit tests (1958 passing) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Rewrite FoundryEvals to use real Foundry Evals API Replace MEAI evaluator shim with actual OpenAI EvaluationClient protocol methods. FoundryEvals now creates eval definitions, submits runs, polls for completion, and fetches per-item results server-side. - New constructor: FoundryEvals(AIProjectClient, model, evaluators) - Add FoundryEvalConverter for MEAI ChatMessage -> Foundry JSON format - Add EvalId, RunId, ReportUrl to AgentEvaluationResults - All 20 built-in evaluator constants now work (agent, tool, quality, safety) - Remove Microsoft.Extensions.AI.Evaluation.Quality/Safety dependencies - Update all samples for new constructor (no more ChatConfiguration) - Replace BuildEvaluators tests with ResolveEvaluator tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add response output to CustomEvals and ExpectedOutputs samples Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: pagination, validation, error handling, tests FoundryEvals fixes: - Add pagination for output items (has_more/after cursor) - Add guard clauses for pollIntervalSeconds/timeoutSeconds <= 0 - Fix double TryGetProperty for passed field parsing - Throw on all-tool-evaluators with no tool definitions - Fix XML doc (default 300s, not 180s) New tests (30 added, 1989 total): - EvalChecks: NonEmpty, ContainsExpected (pass/fail/skip/case), HasImageContent, ToolCallsPresent - FoundryEvalConverter: ConvertMessage (text, image, function call, function results fan-out, empty fallback, mixed content), ConvertEvalItem, BuildTestingCriteria (quality/agent/tool/groundedness data mappings), BuildItemSchema Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix review: null-refs, Data.ToString() bug, ContainsExpected, add tests - Fix NullReferenceException in sample Response display (pattern matching) - Fix WorkflowEvaluationExtensions Data?.ToString() producing type names instead of message text (pattern-match ChatMessage/AgentResponse/list) - Change EvalChecks.ContainsExpected to return Passed=false when no ExpectedOutput (was silently passing, masking misconfiguration) - Add EvalItem constructor tests with LastTurn/Full/null splitters - Add FoundryEvalConverter.ConvertMessage DataContent (base64 image) test - Add ExtractAgentData tests with ChatMessage, list, and AgentResponse data Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix review: conversation fidelity, eval caching, fallback tests - WorkflowEvaluationExtensions: preserve full response messages (tool calls, intermediate) instead of synthetic 2-message conversation. Cast completed Data to AgentResponse and use Messages when available, fallback to text. - FoundryEvals: cache evalId per schema shape (hasContext, hasTools) so subsequent EvaluateAsync calls create runs under the same eval definition. - MeaiEvaluatorAdapter: code already correctly passes queryMessages (not full conversation) to IEvaluator — no change needed, verified by inspection. - Add tests: AgentResponse full messages preservation, unknown object ToString() fallback for ExtractAgentData. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Rename AzureAI→Foundry: move eval files, update references - Move FoundryEvals.cs and FoundryEvalConverter.cs from Microsoft.Agents.AI.AzureAI to Microsoft.Agents.AI.Foundry - Update namespace from AzureAI to Foundry in both files - Add explicit usings required by Foundry project (no implicit usings) - Move FoundryEvalConverter tests to Foundry.UnitTests project (avoids ReplacingRedactor type conflict from dual project refs) - Update all sample csproj references and using statements - Remove Foundry project reference from AI UnitTests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * PR review round 4: wire up tool extraction, remove eval cache, fix null safety - BuildEvalItem: extract tools from agent via GetService<ChatOptions>() into EvalItem.Tools (Python parity) - FoundryEvals: remove eval ID cache - each call creates fresh definition (matches Python behavior) - FoundryEvals: replace null-forgiving operators with descriptive InvalidOperationException - MixedProviders sample: remove unnecessary explicit PackageReferences (transitively provided) - FoundryEvalConverter: document that tool results take precedence over text content - Add LocalEvaluator zero-checks test documenting 0 metrics = failed behavior Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Python-dotnet parity: 9 feature gaps filled New checks: - ToolCallArgsMatch() — verify tool call names + argument subset match - ToolCalledCheck(ToolCalledMode.Any, ...) — match any of the specified tools - ToolCalledMode enum (All/Any) FoundryEvals enhancements: - Default evaluators now [Relevance, Coherence, TaskAdherence] (was Relevance, Coherence) - Auto-add ToolCallAccuracy when items have tool definitions - EvaluateTracesAsync — evaluate by response_ids, trace_ids, or agent_id - EvaluateFoundryTargetAsync — evaluate deployed Foundry targets Result type enrichment: - AgentEvaluationResults: added Status, Error, PerEvaluator, DetailedItems - New EvalItemResult/EvalScoreResult/PerEvaluatorResult types - FoundryEvals populates all new fields from API responses Workflow fix: - Skip internal executors (_*, input-conversation, end-conversation, end) Tests: 8 new tests covering ToolCallArgsMatch, ToolCalledMode.Any, internal executor filtering Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add MeaiEvaluatorAdapter and PerTurnItems edge case tests - 3 tests for MeaiEvaluatorAdapter: query message forwarding, synthetic response fallback, multiple items aggregation - 3 tests for EvalItem.PerTurnItems: empty conversation, no user messages, system+assistant only - StubEvaluator and StubChatClient test helpers Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Blocking link check for outdated package in DevUI. * Replace Dictionary<string, object> payloads with typed wire models Introduce internal FoundryEvalWireModels.cs with compile-time-safe types for the OpenAI Evals API wire format. The OpenAI .NET SDK (2.9.1) only provides protocol-level methods with BinaryContent/ClientResult — no typed request models. These internal models replace scattered dictionary literals with [JsonPropertyName]-annotated classes, giving: - Compile-time safety (typos become build errors) - Single point of change when the API evolves - IntelliSense discoverability - Cleaner serialization via JsonPolymorphic for content items Models: WireContentItem hierarchy (text, image, tool_call, tool_result), WireMessage, WireEvalItemPayload, WireTestingCriterion, WireItemSchema, WireCreateEvalRequest, WireCreateRunRequest, and data source variants. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Skip metric when Foundry returns neither score nor passed When an evaluator returns no score and no passed value, the previous code created BooleanMetric(name, false), which falsely failed items via ItemPassed. Now we skip the MEAI metric entirely for indeterminate results — the raw data remains available in DetailedItems for diagnostics. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR #4914 review comments: fix tool evaluator bug and add tests - Fix duplicate ToolCallAccuracy: resolve evaluator names before checking against ToolEvaluators set (Comment 2) - Make FilterToolEvaluators internal for testability; add tests for the ArgumentException edge case when all evaluators are tool-type (Comment 3) - Add CancellationToken test for LocalEvaluator (Comment 4) - Add EvaluateAsync integration test on Run with sequential workflow and per-agent SubResults verification (Comment 5) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address Peter's review comments on PR #4914 - Add trailing newline to Evaluation_FoundryQuality.csproj (Comment 6) - Make evaluator name lookups case-insensitive: switch BuiltinEvaluators, ToolEvaluators, AgentEvaluators, and ResolveEvaluator's StartsWith check from Ordinal to OrdinalIgnoreCase (Comment 7) - Add Trace.TraceWarning when Foundry returns fewer results than submitted items, indicating expected vs actual count before padding (Comment 8) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add Microsoft.Extensions.AI.Evaluation packages to Directory.Packages.props These were removed in #5269 as unused, but are needed by the Foundry and core evaluation integration added in this PR. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: alliscode <bentho@microsoft.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
309 lines
11 KiB
C#
309 lines
11 KiB
C#
// Copyright (c) Microsoft. All rights reserved.
|
|
|
|
using System;
|
|
using System.Collections.Generic;
|
|
using Microsoft.Extensions.AI;
|
|
|
|
namespace Microsoft.Agents.AI.Foundry.UnitTests;
|
|
|
|
/// <summary>
|
|
/// Tests for <see cref="FoundryEvalConverter"/>.
|
|
/// </summary>
|
|
public sealed class FoundryEvalConverterTests
|
|
{
|
|
// ---------------------------------------------------------------
|
|
// ResolveEvaluator tests
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void ResolveEvaluator_QualityShortNames_ResolvesToBuiltin()
|
|
{
|
|
Assert.Equal("builtin.relevance", FoundryEvalConverter.ResolveEvaluator("relevance"));
|
|
Assert.Equal("builtin.coherence", FoundryEvalConverter.ResolveEvaluator("coherence"));
|
|
}
|
|
|
|
[Fact]
|
|
public void ResolveEvaluator_FullyQualifiedName_ReturnsSame()
|
|
{
|
|
Assert.Equal("builtin.relevance", FoundryEvalConverter.ResolveEvaluator("builtin.relevance"));
|
|
}
|
|
|
|
[Fact]
|
|
public void ResolveEvaluator_UnknownName_ThrowsArgumentException()
|
|
{
|
|
var ex = Assert.Throws<ArgumentException>(
|
|
() => FoundryEvalConverter.ResolveEvaluator("gobblygook"));
|
|
Assert.Contains("gobblygook", ex.Message);
|
|
}
|
|
|
|
[Fact]
|
|
public void ResolveEvaluator_AgentEvaluators_ResolveCorrectly()
|
|
{
|
|
Assert.Equal("builtin.intent_resolution", FoundryEvalConverter.ResolveEvaluator("intent_resolution"));
|
|
Assert.Equal("builtin.tool_call_accuracy", FoundryEvalConverter.ResolveEvaluator("tool_call_accuracy"));
|
|
}
|
|
// ---------------------------------------------------------------
|
|
// FoundryEvalConverter.ConvertMessage tests
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void ConvertMessage_PlainText_ProducesTextContent()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.User, "Hello world");
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
Assert.Equal("user", output[0].Role);
|
|
var text = Assert.IsType<WireTextContent>(Assert.Single(output[0].Content));
|
|
Assert.Equal("Hello world", text.Text);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_ImageUri_ProducesInputImage()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.User,
|
|
[
|
|
new UriContent(new Uri("https://example.com/img.png"), "image/png"),
|
|
]);
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
Assert.IsType<WireImageContent>(Assert.Single(output[0].Content));
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_FunctionCall_ProducesToolCallContent()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.Assistant,
|
|
[
|
|
new FunctionCallContent("c1", "get_weather", new Dictionary<string, object?> { ["city"] = "Seattle" }),
|
|
]);
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
var toolCall = Assert.IsType<WireToolCallContent>(Assert.Single(output[0].Content));
|
|
Assert.Equal("c1", toolCall.ToolCallId);
|
|
Assert.Equal("get_weather", toolCall.Name);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_FunctionCallWithoutArguments_OmitsArguments()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.Assistant,
|
|
[
|
|
new FunctionCallContent("c1", "list_items"),
|
|
]);
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
var toolCall = Assert.IsType<WireToolCallContent>(Assert.Single(output[0].Content));
|
|
Assert.Null(toolCall.Arguments);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_FunctionResults_FanOutToSeparateMessages()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.Tool,
|
|
[
|
|
new FunctionResultContent("c1", "72F sunny"),
|
|
new FunctionResultContent("c2", "Paris 68F"),
|
|
]);
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Equal(2, output.Count);
|
|
Assert.All(output, m => Assert.Equal("tool", m.Role));
|
|
Assert.Equal("c1", output[0].ToolCallId);
|
|
Assert.Equal("c2", output[1].ToolCallId);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_EmptyContent_ProducesEmptyTextFallback()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.Assistant, Array.Empty<AIContent>());
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
var text = Assert.IsType<WireTextContent>(Assert.Single(output[0].Content));
|
|
Assert.Equal(string.Empty, text.Text);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertMessage_MixedContent_ProducesAllContentTypes()
|
|
{
|
|
var msg = new ChatMessage(ChatRole.User,
|
|
[
|
|
new TextContent("Describe this"),
|
|
new UriContent(new Uri("https://example.com/img.png"), "image/png"),
|
|
]);
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
Assert.Equal(2, output[0].Content.Count);
|
|
Assert.IsType<WireTextContent>(output[0].Content[0]);
|
|
Assert.IsType<WireImageContent>(output[0].Content[1]);
|
|
}
|
|
|
|
// ---------------------------------------------------------------
|
|
// FoundryEvalConverter.ConvertEvalItem tests
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void ConvertEvalItem_BasicItem_HasQueryAndResponse()
|
|
{
|
|
var item = new EvalItem(query: "What is AI?", response: "Artificial Intelligence.");
|
|
var payload = FoundryEvalConverter.ConvertEvalItem(item);
|
|
|
|
Assert.Equal("What is AI?", payload.Query);
|
|
Assert.Equal("Artificial Intelligence.", payload.Response);
|
|
Assert.NotNull(payload.QueryMessages);
|
|
Assert.NotNull(payload.ResponseMessages);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertEvalItem_WithContext_IncludesContextField()
|
|
{
|
|
var item = new EvalItem(query: "q", response: "r")
|
|
{
|
|
Context = "Some grounding context",
|
|
};
|
|
var payload = FoundryEvalConverter.ConvertEvalItem(item);
|
|
|
|
Assert.Equal("Some grounding context", payload.Context);
|
|
}
|
|
|
|
[Fact]
|
|
public void ConvertEvalItem_WithoutContext_OmitsContextField()
|
|
{
|
|
var item = new EvalItem(query: "q", response: "r");
|
|
var payload = FoundryEvalConverter.ConvertEvalItem(item);
|
|
|
|
Assert.Null(payload.Context);
|
|
}
|
|
|
|
// ---------------------------------------------------------------
|
|
// FoundryEvalConverter.BuildTestingCriteria tests
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void BuildTestingCriteria_QualityEvaluator_UsesStringDataMapping()
|
|
{
|
|
var criteria = FoundryEvalConverter.BuildTestingCriteria(
|
|
["relevance"], "gpt-4o-mini", includeDataMapping: true);
|
|
|
|
Assert.Single(criteria);
|
|
var entry = criteria[0];
|
|
Assert.Equal("azure_ai_evaluator", entry.Type);
|
|
Assert.Equal("builtin.relevance", entry.EvaluatorName);
|
|
|
|
Assert.NotNull(entry.DataMapping);
|
|
var mapping = entry.DataMapping;
|
|
Assert.Equal("{{item.query}}", mapping["query"]);
|
|
Assert.Equal("{{item.response}}", mapping["response"]);
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildTestingCriteria_AgentEvaluator_UsesConversationArrayMapping()
|
|
{
|
|
var criteria = FoundryEvalConverter.BuildTestingCriteria(
|
|
["intent_resolution"], "gpt-4o-mini", includeDataMapping: true);
|
|
|
|
Assert.Single(criteria);
|
|
var mapping = criteria[0].DataMapping;
|
|
Assert.NotNull(mapping);
|
|
Assert.Equal("{{item.query_messages}}", mapping["query"]);
|
|
Assert.Equal("{{item.response_messages}}", mapping["response"]);
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildTestingCriteria_ToolEvaluator_IncludesToolDefinitions()
|
|
{
|
|
var criteria = FoundryEvalConverter.BuildTestingCriteria(
|
|
["tool_call_accuracy"], "gpt-4o-mini", includeDataMapping: true);
|
|
|
|
Assert.Single(criteria);
|
|
var mapping = criteria[0].DataMapping;
|
|
Assert.NotNull(mapping);
|
|
Assert.True(mapping.ContainsKey("tool_definitions"));
|
|
Assert.Equal("{{item.tool_definitions}}", mapping["tool_definitions"]);
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildTestingCriteria_GroundednessEvaluator_IncludesContext()
|
|
{
|
|
var criteria = FoundryEvalConverter.BuildTestingCriteria(
|
|
["groundedness"], "gpt-4o-mini", includeDataMapping: true);
|
|
|
|
Assert.Single(criteria);
|
|
var mapping = criteria[0].DataMapping;
|
|
Assert.NotNull(mapping);
|
|
Assert.True(mapping.ContainsKey("context"));
|
|
Assert.Equal("{{item.context}}", mapping["context"]);
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildTestingCriteria_WithoutDataMapping_OmitsMappingField()
|
|
{
|
|
var criteria = FoundryEvalConverter.BuildTestingCriteria(
|
|
["relevance"], "gpt-4o-mini", includeDataMapping: false);
|
|
|
|
Assert.Single(criteria);
|
|
Assert.Null(criteria[0].DataMapping);
|
|
}
|
|
|
|
// ---------------------------------------------------------------
|
|
// FoundryEvalConverter.BuildItemSchema tests
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void BuildItemSchema_Default_HasQueryResponseAndConversationFields()
|
|
{
|
|
var schema = FoundryEvalConverter.BuildItemSchema();
|
|
|
|
Assert.True(schema.Properties.ContainsKey("query"));
|
|
Assert.True(schema.Properties.ContainsKey("response"));
|
|
Assert.True(schema.Properties.ContainsKey("query_messages"));
|
|
Assert.True(schema.Properties.ContainsKey("response_messages"));
|
|
Assert.False(schema.Properties.ContainsKey("context"));
|
|
Assert.False(schema.Properties.ContainsKey("tool_definitions"));
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildItemSchema_WithContext_IncludesContextProperty()
|
|
{
|
|
var schema = FoundryEvalConverter.BuildItemSchema(hasContext: true);
|
|
|
|
Assert.True(schema.Properties.ContainsKey("context"));
|
|
}
|
|
|
|
[Fact]
|
|
public void BuildItemSchema_WithTools_IncludesToolDefinitionsProperty()
|
|
{
|
|
var schema = FoundryEvalConverter.BuildItemSchema(hasTools: true);
|
|
|
|
Assert.True(schema.Properties.ContainsKey("tool_definitions"));
|
|
}
|
|
|
|
// ---------------------------------------------------------------
|
|
// FoundryEvalConverter.ConvertMessage DataContent test
|
|
// ---------------------------------------------------------------
|
|
|
|
[Fact]
|
|
public void ConvertMessage_DataContent_ProducesInputImage()
|
|
{
|
|
var imageBytes = new byte[] { 0x89, 0x50, 0x4E, 0x47 }; // PNG magic bytes
|
|
var msg = new ChatMessage(ChatRole.User,
|
|
[
|
|
new TextContent("Describe this image"),
|
|
new DataContent(imageBytes, "image/png"),
|
|
]);
|
|
|
|
var output = FoundryEvalConverter.ConvertMessage(msg);
|
|
|
|
Assert.Single(output);
|
|
Assert.Equal(2, output[0].Content.Count);
|
|
var text = Assert.IsType<WireTextContent>(output[0].Content[0]);
|
|
Assert.Equal("Describe this image", text.Text);
|
|
var image = Assert.IsType<WireImageContent>(output[0].Content[1]);
|
|
Assert.Contains("data:image/png;base64,", image.ImageUrl);
|
|
}
|
|
}
|