What's Changed

• Give FunctionInvokingChatClient span a more OTELy name by @verdie-g in #6911
• Update repository branding from 9.10 to 10.0 by @Copilot in #6907
• Clean up local function names in AIFunctionFactory by @Copilot in #6909
• Update OpenTelemetryChatClient to output data on all tools by @stephentoub in #6906
• Update ToChatResponse{Async} to also factor in AuthorName by @stephentoub in #6910
• add support for background responses by @SergeyMenshykh in #6854
• Fix METGEN004 error message: print return type in ErrorInvalidMethodReturnType by @eduherminio in #6905
• Fix OpenTelemetryChatClient failing on unknown content types by @stephentoub in #6915
• Add support for Connector ID and other follow ups by @jozkee in #6881
• Update AI lib changelogs by @stephentoub in #6920
• Merge internal changes by @joperezr in #6921
• Add Workstream, Stage, and PackageValidationBaselineVersion metadata to ServiceDiscovery libraries by @Copilot in #6919
• Add back Uri ctor to HostedMcpServerTool by @jozkee in #6926
• Set DisableNETStandardCompatErrors in ServiceDiscovery libraries by @eerhardt in #6927
• Update Package validation baseline version to 9.10.0 by @Copilot in #6922
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6802
• Extend service discovery to support Consul-based DNS lookups: by @bart-vmware in #6914
• Update AsOpenAIResponseItems to roundtrip User AIContent ResponseItems by @stephentoub in #6931
• Special-case AIContent returned from AIFunctionFactory.Create AIFunctions to not be serialized by @stephentoub in #6935
• Preserve function content in SummarizingChatReducer by @MackinnonBuck in #6908
• Tool reduction by @MackinnonBuck in #6781
• Fix coalescing of TextReasoningContent with ProtectedData by @stephentoub in #6936
• Doc updates by @gewarren in #6930
• Support DisplayNameAttribute for name resolution in AI libraries by @Copilot in #6942
• Fix EquivalenceEvaluator MaxOutputTokens to meet Azure OpenAI minimum requirement by @Copilot in #6948
• Support DefaultValueAttribute in AIFunctionFactory parameter handling by @Copilot in #6947
• Bump vite from 6.3.6 to 6.4.1 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot[bot] in #6938
• Introduce Microsoft.Extensions.DataIngestion.Abstractions by @adamsitnik in #6949
• Update to latest schema version (accepted by MCP registry) by @joelverhagen in #6956
• Introduce IngestionChunkWriter build on top of MEVD by @adamsitnik in #6951
• Update AI Chat Web dependencies by @MackinnonBuck in #6955
• Add AITool -> OpenAI.Responses.ResponseTool conversion utility by @rogerbarreto in #6958
• Update AI changelogs for 9.10.1 by @stephentoub in #6950
• Add Name property to OtelMessage to store ChatMessage.AuthorName per OpenTelemetry semantic conventions by @Copilot in #6953
• Fix serialization of UserInputRequest/ResponseContent by @stephentoub in #6962
• Expose building blocks for external service discovery implementations by @bart-vmware in #6946
• Bump validator from 13.15.0 to 13.15.20 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot[bot] in #6974
• Add eng/sdl-tsa-vars.config for TSA integration by @Copilot in #6980
• Add CodeInterpreterToolCall/ResultContent content types by @stephentoub in #6964
• Update to 1.38 of the otel genai standard convention by @stephentoub in #6981
• Introduce set of built-in Enrichers by @adamsitnik in #6957
• Allow ChatOptions.ConversationId to be an OpenAI conversation ID with Responses by @stephentoub in #6960
• Fix warning breaking official build, enable warningAsError in all pipelines by @ericstj in #6988
• Introduce HeaderChunker by @adamsitnik in #6979
• Introduce Markdown readers by @adamsitnik in #6969
• Add usage telemetry for aieval dotnet tool by @shyamnamboodiripad in #6773
• Update to OpenAI 2.6.0 by @stephentoub in #6996
• Don't specify MaxOutputTokens for EquivalenceEvaluator by @shyamnamboodiripad in #7006
• Fix Assert.Throws to validate parameter names by @stephentoub in #7007
• [MEDI] Remove collection key type workaround by @adamsitnik in #7010
• Enable binskim to extract packages by @ericstj in #6989
• Added net10.0 targeting to all packages and flowed RC2 dependency versions. by @joperezr in #6995
• [MEDI] Pipeline by @adamsitnik in #6993
• Add Semantic Similarity chunker by @KrystofS in #6994

New Contributors

• @SergeyMenshykh made their first contribution in #6854
• @bart-vmware made their first contribution in #6914

Full Changelog: v9.10.0...v10.0.0

What's Changed

• Branding updates for 9.10 by @Copilot in #6769
• Doc improvements by @gewarren in #6794
• Bump vite from 6.3.5 to 6.3.6 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot[bot] in #6793
• Updated changelogs for AI libs by @stephentoub in #6787
• Update MCP server template by @jeffkl in #6772
• Add support for using ConversationID for AzureOpenAI and OpenAI by @ViveliDuCh in #6770
• Merging internal commits by @joperezr in #6801
• Merge changes from release/9.9 branch by @joperezr in #6803
• Support keyed HybridCache with keyed DistributedCaches and named options by @kelly-yinn in #6694
• Inventory as code by @wtgodbe in #6820
• Increase output token limit for EquivalenceEvaluator by @shyamnamboodiripad in #6835
• Fix KeyNotFoundException on HttpRequestLatencyListener.OnEventWritten for uknown event sources by @ssmelov in #6821
• Add project name normalization to match aspire's code generator logic by @ViveliDuCh in #6818
• Disable really noisy analyzers, part 1 by @stephentoub in #6837
• Fix KeyNotFoundException in HttpRequestLatencyListener.OnEventWritten by @pentp in #6823
• Update global.json to use .NET 9.0.0 stable instead of RC 1 by @Copilot in #6846
• Add measures and tags with mediator object to the HttpClientLatencyLogEnricher by @rainsxng in #6783
• Add comprehensive .github/copilot-instructions.md for dotnet/extensions repository by @Copilot in #6792
• Update to .NET 10 SDK by @eerhardt in #6863
• Update Microsoft.Extensions.AI changelog files with current NuGet versions by @Copilot in #6849
• Fix GenerateImagesAsync_SingleImageGeneration integration test by @stephentoub in #6843
• Re-enable IDE0032 by @stephentoub in #6866
• Add OpenTelemetrySpeechToTextClient and friends by @stephentoub in #6845
• Update ModelContextProtocol version in MCP template by @MackinnonBuck in #6870
• Scope Ollama resilience settings to Web/Program.cs and restore ServiceDefaults by @ViveliDuCh in #6850
• Update Aspire by @Varorbc in #6858
• Update MCP template for new registry specification by @Copilot in #6796
• Add support for HostApplicationBuilder in AmbientMetadata extension by @eduherminio in #6867
• Fix mcpserver test baselines by @jeffhandley in #6874
• Move Microsoft.Extensions.ServiceDiscovery to dotnet/extensions by @eerhardt in #6868
• Add copy constructors to option types (ChatOptions, etc.) by @stephentoub in #6882
• Fix ChatMessage.CreatedAt being always overwritten by the latest timestamp. by @Copilot in #6885
• Small doc fixes by @gewarren in #6887
• Update AI changelogs with some recent additions by @stephentoub in #6886
• Fix Assistants IChatClient handling of unrelated tool calls in history by @stephentoub in #6891
• Fix duplication between OpenAI Assistants pre-configured tools by @stephentoub in #6896
• Update MCP Server Template to adhere to 2025-09-29 server.json schema by @joelverhagen in #6888
• Remove Azure.AI.OpenAI dependency from templates and tests by @Copilot in #6873
• Remove UnsafeRelaxedJsonEscaping by @peterwald in #6899
• Fix bug to yield remaining buffered FCC by @westey-m in #6903
• Fix serialization of [Experimental] AIContent-derived types by @stephentoub in #6900

New Contributors

• @westey-m made their first contribution in #6745
• @jeffkl made their first contribution in #6772
• @ViveliDuCh made their first contribution in #6770
• @kelly-yinn made their first contribution in #6694
• @ssmelov made their first contribution in #6821
• @Varorbc made their first contribution in #6858

Full Changelog: v9.9.0...v9.10.0

Highlights

AI

• Abstractions for remote MCP servers; response/approval flow support via new experimental types
• Function approvals via new experimental types (e.g., ApprovalRequiredAIFunction, user input/approval request & response content).
• Reasoning text streaming for OpenAI Responses ChatClient streaming.
• AIFunction split into a base class to improve extensibility.
• IChatReducer moved to Microsoft.Extensions.AI.Abstractions.
• Updated to OpenAI 2.4.0 and genai standard convention 1.37.
• Coalescing logic now treats ChatMessage.Role changes as new messages.
• GetResponseAsync<T> now reads only the last message (bug fix).
• OpenTelemetry ChatClient/EmbeddingGenerator logs raw additional properties (no key mangling).
• Fixed empty annotated text chunk handling in streaming with OpenAI Assistants.

Telemetry & Diagnostics

• HTTP diagnostics log query string params with proper redaction (emitted on url.query).
• server.address telemetry emits host only (per OpenTelemetry semantic conventions).
• Heuristics added to detect well-known model hosts.
• Resource monitoring can consider Environment.CpuUsage.

New Contributors

• @ykumashev made their first contribution in #6696

Full Changelog: v9.8.0...v9.9.0

What's Changed

• Align EventId generation with M.E.Logging source-gen by @xakep139 in #6566
• Add resiliency mechanism to CPU and memory utilization checks by @amadeuszl in #6528
• Suppress flaky test until fixed by @joelverhagen in #6568
• Create a project template for an MCP server by @joelverhagen in #6547
• Use dnx instead of dotnet tool exec in MCP server template README by @joelverhagen in #6571
• Add reporting tests that show NLP results. by @peterwald in #6574
• Branding updates for 9.8.0 by @joperezr in #6573
• Fix ConfigureEvaluationTests.ps1 script when $ConfigRoot is not supplied by @peterwald in #6575
• Refactor Resource Monitoring by @evgenyfedorov2 in #6554
• Update McpServer template for 0.3.0-preview.2 by @stephentoub in #6578
• Add container.cpu.time metric by @evgenyfedorov2 in #5806
• Add netstandard2.0 compatibility to Microsoft.Extensions.Diagnostics.Testing and dependencies by @bdovaz in #6219
• Add netstandard2.0 compatibility to Microsoft.Extensions.Telemetry and dependencies by @bdovaz in #6218
• Simplify Http.Diagnostics by @pentp in #6174
• Add netstandard2.0 compatibility to Microsoft.Extensions.Http.Resilience and dependencies by @bdovaz in #6582
• Ingore null loggers returned by LogProviders in ELoggerFactory by @petrroll in #6585
• Merging changes from internal by @joperezr in #6588
• [Logging] Fixes LogProperties and LogPropertyIgnore attributes to work if an object being logged resides in a different assembly than the logging method by @iliar-turdushev in #6600
• Add memory usage metric by @evgenyfedorov2 in #6586
• Add schema version to server.json in MCP template by @joelverhagen in #6606
• Merge release/9.7 into main by @joperezr in #6589
• Update MCP server template readme to show both VS Code and Visual Studio notes by @Copilot in #6591
• Update Azure Open AI package referenced by eval integration tests by @shyamnamboodiripad in #6609
• Target .NET 8 for more stable runtime requirement by @joelverhagen in #6617
• Add support for new Azure AI Foundry project type for Safety evals by @shyamnamboodiripad in #6621
• M.E.AI.AzureAIInference - Azure.AI.Inference Package Bump by @rogerbarreto in #6624
• Add DataContent.Name property by @stephentoub in #6616
• Fix handling of multiple responses messages by @stephentoub in #6627
• Expose additional chat model conversion helpers by @stephentoub in #6629
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6633
• [Http.Resilience] The DisableFor method should try to retrieve the request object from the resilience context by @iliar-turdushev in #6618
• Bump Package validation baseline version to 9.7.0 by @Copilot in #6650
• Fix internal package version detection for project templates by @MackinnonBuck in #6651
• Remove Microsoft.Extensions.AI.Ollama by @MackinnonBuck in #6655
• Fix M.E.AI package refs by @stephentoub in #6654
• Add [Description] to DataContent.Uri by @stephentoub in #6615
• Fix duplicate solution file when creating an AI Chat Web app from VS by @MackinnonBuck in #6653
• Add ChatMessage.CreatedAt by @stephentoub in #6657
• Add TextContent.Annotations by @stephentoub in #6619
• Add FunctionInvokingChatClient.AdditionalTools by @stephentoub in #6661
• Fix unintentional test env var change by @stephentoub in #6660
• Add more openai conversion helpers by @stephentoub in #6662
• Add OriginalRepoCommitHash to assemblies by @BrennanConroy in #6667
• Include a trivial items keyword if missing. by @eiriktsarpalis in #6669
• Add resolution of function parameter level data annotation attributes. by @eiriktsarpalis in #6671
• Fix issue with NetSourceIndexStage1 for dependency conflict versions by @joperezr in #6672
• Expose streaming conversion utility methods by @stephentoub in #6636
• Couple of fixes for MEAI.Evaluation by @shyamnamboodiripad in #6673
• Fix one more version conflict on the docs transport package by @joperezr in #6675
• Introduce metadata to identify built-in evaluation metrics by @shyamnamboodiripad in #6674
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6679
• Emit {OriginalFormat} in HttpClient logger by @iliar-turdushev in #6682
• Update to OpenAI 2.3.0 by @stephentoub in #6684
• Remove AdjustTime from experimental by @amadeuszl in #6668
• Allow custom filtering logic for FakeLogger by @Demo30 in #5848
• Mark packages as stable and update to .NET Servicing versions by @joperezr in #6700
• [release/9.8] Backport several AI-related PRs by @stephentoub in #6703
• [release/9.8] Update Azure.AI.OpenAI by @github-actions[bot] in #6710
• [release/9.8] Add support for text-to-image by @ericstj in #6711
• [release/9.8] Use Azure hosting integrations in Aspire AI Chat Web template by @MackinnonBuck in #6712
• [release/9.8] Add middleware for reducing chat history by @github-actions[bot] in #6713

New Contributors

• @joelverhagen made their first contribution in #6568
• @bdovaz made their first contribution in #6219
• @petrroll made their first contribution in #6585

Full Changelog: v9.7.0...v9.8.0

Packages Released

• Microsoft.Extensions.AI.Templates 9.7.2-preview.3.25366.2

What's Changed

• Target .NET 8 for more stable runtime requirement by @joelverhagen in #6617

Full Changelog: v9.7.1...v9.7.2

Packages Released

• Microsoft.Extensions.AI 9.7.1
• Microsoft.Extensions.AI.Abstractions 9.7.1
• Microsoft.Extensions.AI.OpenAI 9.7.1-preview.1.25365.4
• Microsoft.Extensions.AI.AzureAIInference 9.7.1-preview.1.25365.4
• Microsoft.Extensions.AI.Templates 9.7.1-preview.3.25365.4

What's Changed

• Merging changes from internal by @joperezr in #6588
• Bump FunctionInvokingChatClient.MaximumIterationsPerRequest from 10 to 40 by @stephentoub in #6599
• Expose M.E.AI.OpenAI input message conversions by @stephentoub in #6601
• Add schema version to server.json in MCP template by @joelverhagen in #6606
• Update MCP server template readme to show both VS Code and Visual Studio notes by @jeffhandley in #6591
• Fix schema generation for Nullable function parameters. by @eiriktsarpalis in #6596
• Branding updates for 9.7.1 by @joperezr in #6611
• Add DelegatingAIFunction by @stephentoub in #6565
• Add FunctionInvokingChatClient.FunctionInvoker delegate by @stephentoub in #6564
• Enable specifying "strict" for OpenAI clients via ChatOptions by @stephentoub in #6552
• AIFunctionFactory: tolerate JSON string function parameters. by @eiriktsarpalis in #6572
• AIFunctionFactory: add test coverage for JSON comments. by @eiriktsarpalis in #6576
• Update M.E.AI.OpenAI for latest OpenAI release by @stephentoub in #6577
• Update OpenTelemetry semantic conventions version from 1.35 to 1.36 by @Copilot in #6579
• AIFunctionFactory: add a flag for disabling return schema generation. by @eiriktsarpalis in #6551
• Bump FunctionInvokingChatClient.MaximumIterationsPerRequest from 10 to 40 by @stephentoub in #6599
• Expose M.E.AI.OpenAI input message conversions by @stephentoub in #6601
• Fix schema generation for Nullable function parameters. by @eiriktsarpalis in #6596

Full Changelog: v9.7.0...v9.7.1

What's Changed

• Branding updates for 9.7 by @joperezr in #6495
• Fix name of genai input/output tokens tag by @stephentoub in #6494
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6503
• Improve handling of RawRepresentation in OpenAI{Response}ChatClient by @stephentoub in #6500
• Bring back AsIChatClient for OpenAI AssistantClient by @stephentoub in #6501
• Add resiliency to Resource Monitoring in Linux by @amadeuszl in #6489
• Merging changes from the internal fork by @joperezr in #6508
• Workaround OpenAI assistant's RunCreationOption's tools override by @stephentoub in #6512
• Add ChatOptions.Instructions by @stephentoub in #6505
• Introduce evaluators for agentic workflows by @shyamnamboodiripad in #6514
• Allow a CachingChatClient to control per-request caching by @stephentoub in #6524
• Tweak OpenAI JSON schema transforms by @stephentoub in #6523
• Merging changes from release/9.6 branch by @joperezr in #6516
• Augment AIJsonUtilities.CreateJsonSchema for more types and annotations by @stephentoub in #6540
• Added conversions from AIFunction to various OpenAI tools by @KrzysztofCwalina in #6539
• Add SpeechToTextResponse.Usage by @stephentoub in #6546
• Implement BLEU score evaluation for NLP tests by @peterwald in #6537
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro[bot] in #6553
• #5962 Change to early return of OS instead of throwing by @juliankock in #5963
• Mark log sampling & buffering API as stable by @evgenyfedorov2 in #6534
• Update GenAI otel impl for v1.35 by @stephentoub in #6557
• Implement GLEU and F1 NLP evaluators by @peterwald in #6555
• Update tokenizer algorithm to use is [..] by @peterwald in #6561
• Rename some constants to match convention by @shyamnamboodiripad in #6562
• Add DistributedCachingChatClient/EmbeddingGenerator.AdditionalCacheKeyValues by @stephentoub in #6558

New Contributors

• @KrzysztofCwalina made their first contribution in #6539
• @juliankock made their first contribution in #5963

Full Changelog: v9.6.0...v9.7.0

What's Changed

• Branding updates for 9.6.0 by @joperezr in #6399
• Add log buffering info to README.md by @evgenyfedorov2 in #6403
• Fix dynamic config update for log buffering by @evgenyfedorov2 in #6435
• Remove unused select param from CreateRecordsForDocumentAsync by @jongalloway in #6341
• Merge internal changes by @joperezr in #6437
• Reduce per-lookup overhead from key validation in HybridCache by @MihaZupan in #6441
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6443
• Merge release/9.5 into main by @joperezr in #6448
• Fix up comments in eval API json files by @shyamnamboodiripad in #6452
• Remove preview tag on Azure DevOps extension by @peterwald in #6456
• Bump PackageValidation against 9.5.0 and enable for stable MEAI packages by @joperezr in #6458
• Fix paramref tag by @gewarren in #6459
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6462
• Add a script to diff the contents of folders that match a specific pattern across two branches by @shyamnamboodiripad in #6453
• Remove title and description keywords from root-level schemas in AIFunctionFactory. by @eiriktsarpalis in #6465
• Replace JSON vector store with SQLite by @MackinnonBuck in #6438
• Update chat template Microsoft.SemanticKernel dependency to 1.53.0 by @MackinnonBuck in #6470
• Update chat template external dependencies by @MackinnonBuck in #6471
• Exclude provider URI from cache key computation by default by @shyamnamboodiripad in #6473
• Make hashing stable w.r.t. indentation settings and property ordering. by @eiriktsarpalis in #6476
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6481
• Add default value for namedArg in Microsoft.Gen.Metrics.parser by @BowenYang666 in #6238
• Update OpenTelemetryChatClient to 1.34 by @stephentoub in #6466
• Delete M.E.AI changelog files by @stephentoub in #6467
• Add comma to remarks by @gewarren in #6485
• Implement disk io metrics for linux by @makazeu in #6374
• Add AIFunction.ReturnJsonSchema by @eiriktsarpalis in #6447

New Contributors

• @MihaZupan made their first contribution in #6441
• @BowenYang666 made their first contribution in #6238

Full Changelog: v9.5.0...v9.6.0

What's Changed

• Add TextReasoningContent by @stephentoub in #6222
• Use ErrorContent in OpenAIResponseChatClient by @stephentoub in #6231
• OpenAI: Parse detail additional property by @jozkee in #6225
• Branding updates for 9.5 by @joperezr in #6233
• In telemetry, treat AdditionalProperties as sensitive by @SteveSandersonMS in #6239
• Use SHA384 and make key more explicit by @SteveSandersonMS in #6237
• Disable STJ default reflection and fix a number of failing tests. by @eiriktsarpalis in #6241
• Add button to report to download dataset as JSON by @peterwald in #6243
• Introduce Content Safety evaluators by @shyamnamboodiripad in #6223
• Bump vite from 6.2.4 to 6.2.5 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6249
• Only display tags from the latest execution by @shyamnamboodiripad in #6251
• Avoid duplicate data in downloaded report file by @shyamnamboodiripad in #6252
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6253
• Remove use of ConfigureAwait from Microsoft.Extensions.AI.dll for AIFunction invocations by @stephentoub in #6250
• Update dev-server data import to reflect runtime import quirks by @peterwald in #6257
• [release/9.2] Merging internal changes by @joperezr in #6263
• Merging release/9.4 changes by @joperezr in #6264
• Add logging buffering by @evgenyfedorov2 in #5635
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6270
• Add test for optional parameters being required with RequireAllProperties by @jozkee in #6265
• Add fuzzy filtering to the evaluation reports by @peterwald in #6262
• Updating package validation version to 9.4.0 by @joperezr in #6272
• Adding reference to an unsupported built-in tool on OpenAI Chat API no longer throws by @artl93 in #6276
• Update M.E.AI changelogs by @stephentoub in #6269
• Add missing reference to M.E.AI.OpenAI in chat template by @MackinnonBuck in #6275
• Fix two paramref tags by @gewarren in #6281
• Support response caching for safety evaluators by @shyamnamboodiripad in #6277
• Bump vite from 6.2.5 to 6.2.6 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6287
• Display images in conversation for report by @shyamnamboodiripad in #6286
• Augment UseDistributedCache XML docs by @stephentoub in #6256
• Update README.md with keyless auth guidance by @jmatthiesen in #6261
• Augment AIFunctionFactory.Create XML docs by @stephentoub in #6255
• Rename EmbeddingGeneratorExtensions.GenerateEmbedding extension methods by @roji in #6295
• Augment FunctionInvokingChatClient's span with token counts by @stephentoub in #6296
• Rename ChatThreadId to ConversationId by @SteveSandersonMS in #6300
• Repackage azure-devops-extensions-api to fix Azure DevOps report plugin by @peterwald in #6299
• Fix build error by @shyamnamboodiripad in #6301
• Add note on extending timeout for Ollama client by @jongalloway in #6258
• Improve CPU metrics calculations for CgroupV2 by @nivebb8 in #6289
• Restore deleted members as obsolete by @jeffhandley in #6304
• move to AwesomeAssertions by @danmoseley in #6308
• Update chat template dependencies, fix OpenAI/Aspire config, and address build warnings by @MackinnonBuck in #6280
• Support [FromKeyedServices] in AIFunctionFactory by @stephentoub in #6310
• Introduce Context property on EvaluationMetric by @shyamnamboodiripad in #6316
• Utilize IServiceProviderIsService in AIFunctionFactory by @stephentoub in #6317
• Fix Process Metric calculation in CgroupsV2 by @nivebb8 in #6321
• Remove the abstraction for token counting from the main evaluation API by @shyamnamboodiripad in #6320
• Remove AsChatClient/AsEmbeddingGenerator APIs by @jeffhandley in #6327
• Add ChatOptions.AllowMultipleToolCalls by @SteveSandersonMS in #6326
• Disable default required property schema generation and OpenAI strict mode. by @eiriktsarpalis in #6285
• Accessibility fixes for the HTML report by @peterwald in #6329
• Add Windows disk I/O metrics to ResourceMonitoring by @makazeu in #6181
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6336
• Update prompts for quality evaluators by @shyamnamboodiripad in #6328
• Reduce allocations in LogSamplingRuleSelector by @evgenyfedorov2 in #6339
• A couple of minor fixes by @shyamnamboodiripad in #6340
• Update readmes by @shyamnamboodiripad in #6345
• Expose AIContent constructor by @stephentoub in #6346
• Add PDF support to OpenAI AsIChatClient by @stephentoub in #6344
• Make CreateJsonSchema tolerate JSO inputs that don't have a resolver set. by @eiriktsarpalis in #6348
• Skip messages that have no text when rendering conversations as part of evaluation prompts by @shyamnamboodiripad in #6349
• Enhance Function Invocation Extensibility for Microsoft.Extensions.AI by @rogerbarreto in #6325
• Upgrade to Issue Labeler v2.0.0 by @jeffhandley in #6357
• Issue Labeler - Predict PR labels for main and dev branches by @jeffhandley in #6358
• Update CHANGELOGS for M.E.AI libs by @stephentoub in #6359
• Add project template build tests + CG reporting by @MackinnonBuck in #6355
• Fix keys for EvaluationResult.Metrics dictionary to reflect the correct metric names for Safety evaluators by @shyamnamboodiripad in #6361
• Update branding for Azure service used by Safety evaluators by @shyamnamboodiripad in #6362
• Use ConversationId instead of ChatThreadId in README by @gewarren in #6367
• Add Disk IO time metric for Windows in ResourceMonitoring by @makazeu in #6338
• Fix an issue in OSFileSystem's ReadAllByLines method where last line may be dropped by @makazeu in #6373
• Update OpenTelemetryChatClient/EmbeddingGenerator to 1.33 by @stephentoub in #6366
• Add AsIEmbeddingGenerator for Azure.AI.Inference ImageEmbeddingsClient by @stephentoub in #6363
• Add DataContent.Base64Data by @stephentoub in #6365
• Fix AIFunctionFactory handling of default struct arguments by @eiriktsarpalis in #6381
• Add JS dependency update instructions to chat template README by @MackinnonBuck in #6376
• Add see also links to conceptual docs by @gewarren in #6368
• Using nr_periods from cpu.stat to get time elapsed by @nivebb8 in #6335
• Translate OpenAI refusals to ErrorContent by @stephentoub in #6393
• Rename useJsonSchema parameter by @stephentoub in #6394
• Add JSON schema transformation functionality to AIJsonUtilities by @eiriktsarpalis in #6383
• Remove CacheOptions from DiskBasedResponseCache by @shyamnamboodiripad in #6395
• Add back net9.0 version of the aieval dotnet tool by @shyamnamboodiripad i...

What's Changed

• Fix various build failures by @RussKie in #6039
• Proposal for tweaks to IChatClient contract by @stephentoub in #5998
• Onboard dotnet/issue-labeler workflows for automated area labels by @jeffhandley in #6047
• Only predict area labels for PRs into main and dev by @jeffhandley in #6049
• Upgrade workflows to issue-labeler v1.0.1 by @jeffhandley in #6050
• Fix evaluation report generation by @shyamnamboodiripad in #6061
• Automatically add 'untriaged' label to new issues without milestones by @jeffhandley in #6060
• Address M.E.VectorData feedback for IEmbeddingGenerator by @stephentoub in #6058
• Fix grouping of ChatResponseUpdate into ChatMessage by @SteveSandersonMS in #6074
• Fix handling of empty messages in AzureAIInferenceChatClient by @stephentoub in #6072
• Update OpenTelemetryChatClient/EmbeddingGenerator to v1.31 of genai standard convention by @stephentoub in #6073
• Merging internal changes by @joperezr in #6081
• Merging release/9.3 branch into main by @joperezr in #6082
• Update ordering in CODEOWNERS by @shyamnamboodiripad in #6085
• Bump Package Validation by @joperezr in #6084
• Add types from AIJsonUtilities.JsonContext to reporting JsonContext by @peterwald in #6078
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6097
• Introduce Reason property on EvaluationMetric by @shyamnamboodiripad in #6087
• [AI Evaluation] Add versioning to reporting and caching by @peterwald in #6070
• Add assignments for @dotnet/dotnet-extensions-ai-templates by @RussKie in #6105
• Test templates by @RussKie in #6086
• Add favicon for AiChatWeb template by @makazeu in #6104
• Move manual dependencies in correct group to reduce conflicts by @RussKie in #6108
• Memory usage in CG Slice path could be 0 by @makazeu in #6110
• Add an option to log unsupported route by @amadeuszl in #6077
• Fix tree expansion in evaluation report by @shyamnamboodiripad in #6107
• Use just-built packages in the AI chat template by default by @MackinnonBuck in #6096
• Avoid multiple enumerations of messages in FunctionInvokingChatClient by @stephentoub in #6119
• Add AsChatClient for OpenAIResponseClient by @stephentoub in #6103
• [AI extensions] Add jsonSchemaIsStrict option to OpenAI options mapping by @danielwinkler in #6064
• pin actions by @danmoseley in #6123
• Expose failed Verify asserts as CI artifacts by @RussKie in #6129
• Create a directory for the AIChatWeb template if name is specified by @makazeu in #6122
• Add AIJsonSchemaCreateOptions.IncludeParameter filter by @stephentoub in #6125
• Update html-reporting package dependencies by @peterwald in #6115
• [main] Update dependencies from dotnet/arcade by @dotnet-maestro in #6131
• Fix AIFunctionFactory functions to fail for missing required parameters by @stephentoub in #6135
• Update changelogs for M.E.AI by @stephentoub in #6079
• Fix chat template test version scrubbing by @MackinnonBuck in #6140
• [Telemetry, Logging] Emit {OriginalFormat} as the last property of the log record by @iliar-turdushev in #6111
• HybridCache: richer detection for field-only types (ref STJ) by @mgravell in #6118
• [Http Resilience] Update instructions how to fix a compatibility issue with App Insights by @iliar-turdushev in #6147
• Fix indentation in chat template readme by @SteveSandersonMS in #6134
• In chat template, display preformatted/code snippet outputs sensibly by @SteveSandersonMS in #6137
• Use only a single TFM for M.E.AI.Eval.Reporting.Console by @peterwald in #6148
• Update algorithm spelling in /// by @gewarren in #6149
• Fix to show AI template config options in VS Code - Update framework symbol casing in chat template by @timheuer in #6117
• Extend M.E.AI.Evaluation.Console to support Azure Storage options by @peterwald in #6152
• Add license info to the Azure DevOps package by @peterwald in #6160
• Change AIFunction.InvokeAsync to accept AIFunctionArguments by @stephentoub in #6158
• Add some comments clarifying model choice for quality evaluators by @shyamnamboodiripad in #6165
• Fix build failing when running ./build.cmd -vs AI multiple times by @MackinnonBuck in #6171
• Update tsaoptions.json by @danmoseley in #6170
• Add MessageId to ChatMessage and ChatResponseUpdate by @SteveSandersonMS in #6172
• Enable custom argument binding with AIFunctionFactory by @stephentoub in #6162
• Enable JSON-schema based structured output by default by @SteveSandersonMS in #6159
• Simplify function calling error handling by @SteveSandersonMS in #6169
• Update to latest OpenAI, Azure.AI.OpenAI, and Azure.AI.Inference packages by @stephentoub in #6178
• Add custom result marshaling support to AIFunctionFactory by @stephentoub in #6175
• Fix dynamic config update for Random probabilistic sampler by @evgenyfedorov2 in #6187
• Unit test to show how function calling already permits resumption by @SteveSandersonMS in #6186
• Add "see also" links to conceptual docs by @gewarren in #6177
• Fix chat template input form submission on Firefox by @MackinnonBuck in #6188
• Support adding tags to scenarios by @shyamnamboodiripad in #6189
• Couple of minor reporting layout fixes by @shyamnamboodiripad in #6192
• A couple more minor eval report fixes by @shyamnamboodiripad in #6197
• Bump vite from 6.2.2 to 6.2.3 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6190
• Enable AIFunctionFactory.Create to use Activator{Utilities}.Create by @stephentoub in #6193
• Remove experimental attribute from TagNameAttribute by @dariusclay in #6200
• Fix load order of ProjectStaging and restrict package version validation to only official builds by @RussKie in #6041
• Strip default keyword in generated schemas when RequireAllProperties is specified. by @eiriktsarpalis in #6204
• Template: Remove if'ed code for ollama by @jozkee in #6205
• Remove non-AsXx surface area from M.E.AI.OpenAI/AzureAIInference by @stephentoub in #6138
• Add Aspire support to chat template by @MackinnonBuck in #6102
• Add trending views for both leaf-level scenario runs and aggregated scenario groups. by @peterwald in #6207
• Update AI chat template dependencies by @MackinnonBuck in #6220
• Fix execution order when reporting from Azure by @peterwald in #6217
• Bump vite from 6.2.3 to 6.2.4 in /src/Libraries/Microsoft.Extensions.AI.Evaluation.Reporting/TypeScript by @dependabot in #6216
• Mirror integration tests for OllamaSharp by @jozkee in #6209
• Update otel semantic convention version in comment by @stephentoub in #6227
• Update README with Logging sampling information by @evgenyfedorov2 in #6226
• Lower M.E.AI ...