Spring AI Next Release Release Notes

🎯 Highlights

This release includes 47 new features, 106 bug fixes, 70 documentation improvements, 120 other improvements.

⏪ Breaking Changes

Auto-configuration classes for Model Context Protocol (MCP) have been renamed with 'Mcp' prefix for consistency 21c4283
maxTokens and maxCompletionTokens parameters are now mutually exclusive in OpenAI ChatOptions, requiring users to choose one option 13c39f1
Changed UserMessage to use metadata instead of properties for better API consistency #3980
Extracted VectorStoreRetriever interface from VectorStore which may require code updates for custom implementations #3827 via #1290

⚠️ Upgrading Notes

Update imports for MCP auto-configuration classes that have been renamed with 'Mcp' prefix 21c4283
When configuring OpenAI ChatOptions, ensure you use either maxTokens or maxCompletionTokens, but not both simultaneously 13c39f1
Update code to use metadata instead of properties when working with UserMessage objects #3980
Custom VectorStore implementations may need to be updated to implement the new VectorStoreRetriever interface #3827

📢 Noteworthy

Removed support for the deprecated Mistral AI Codestral Mamba model as part of code cleanup #4225
Significantly improved test coverage for MistralAiBindingsPropertiesProcessor to ensure robust MistralAI integration #4165
Improved test coverage for EmbeddingModelObservationContext and SyncMcpToolCallback edge cases to ensure better reliability #4157
Significantly improved test coverage for QdrantObjectFactory.toObjectMap, SimpleVectorStore filter conditions, and various other components #4095
Removed hardcoded topK value in BedrockConverseProxyChatProperties for better configuration flexibility #3621
Refactored MessageAggregator to properly handle and include tool calls in message aggregation df90b9c
Cleaned up QdrantVectorStoreIT by removing unnecessary environment variable validation #3615
Temporarily reverted a fix for OpenAI function callback integration test 3bce15a
Temporarily reverted a parameter order fix in validateToolContextSupport method f0c128c
Temporarily reverted changes to resolve OpenAI API key for every request due to compatibility issues 313aae0

⭐ New Features

Tool callbacks now expose the original tool name in both synchronous and asynchronous operations, providing better visibility into tool execution 6678035
Added support for sending labels with chat requests in Google Generative AI integration 1dd686b
Added comprehensive annotation-based configuration support for Model Context Protocol (MCP) clients and servers 534c6af
Added support for OpenAI service_tier parameter in OpenAiChatOptions to enable control over service quality levels ad2e1bc
Refactored MCP (Model Control Protocol) server auto-configuration to use consolidated modules with protocol-based configuration approach e71da4e
Added missing Spring Boot starters for Google GenAI integration, enabling easier autoconfiguration 528155a
Improved Unicode property union handling for robust Chinese character processing 35486e9
Use latest CI scripts when testing old commits for improved testing reliability a9f93b0
Restructured MCP server auto-configurations and added streamable-http support for improved streaming capabilities 0b96f4c
Added support for new GPT-5 models with verbosity parameter configuration #4086
Added comprehensive debugging capabilities to improve maintenance branch workflow reliability and troubleshooting 3ce6d38
Added support for fast CI builds when cherry-picking changes to maintenance branches 29ac7d9
Added autoconfiguration for MCP client with support for async HTTP request customization 7ad7150
Configured McpSyncServer to use immediate execution when running in a servlet context 568ca96
Added support for GPT-5 model enum with updated documentation 1a3ed95
Added KotlinModule support and tests for schema generation in BeanOutputConverter to improve Kotlin integration #3900
ChatClient now supports adding metadata to both PromptUserSpec and PromptSystemSpec, enabling richer message context and processing capabilities #3989
Added Google GenAI embedding module with unified SDK support for enhanced integration capabilities 085446c
Added ability to use custom templates with KeywordMetadataEnricher for enhanced metadata enrichment capabilities c122fe1
Added new spring-ai-google-genai module using Google's latest GenAI SDK for improved Google AI model integration daf1274
Added log probabilities support for Vertex AI Gemini models e557081
Added streamable HTTP transport support for Model Context Protocol (MCP) client 656395e
Added BedrockChatOptions to Bedrock integration for improved configuration 99e59a2
Introduces a standardized interface for audio transcription across different model providers 4cf2377
Enhances ZhiPu AI integration with fluent builder pattern for easier configuration d865c9e
ZhiPuAI embedding model now supports configurable custom dimensions #3668 via #1857
Added configuration option for meta field prefix in Weaviate vector store properties #3585
Improved function capabilities through @tool annotation improvements for better function calling integration 22fc730
Enhanced MistralChatOptions with updated configuration capabilities a2a92bb
Added selective exception rethrowing capability to DefaultToolExecutionExceptionProcessor for better error handling control beb1d05
ChatClient#mutate now creates copies of advisors and advisorParams instead of referencing the originals f391ff2
Made the content field configurable in Weaviate vector store properties to provide more flexibility in vector store configuration 24de06e
Added integration with ElevenLabs for text-to-speech functionality 9398850
Expanded Mistral AI integration with support for additional chat models #3523
Enhanced OllamaChatModel with retry template support for improved reliability cfbefee
Improved MiniMaxChatOptions with proper equality methods and deep copy functionality d9e3037
Added support for streaming thinking events in the Anthropic model provider, enabling real-time access to model reasoning processes 12f19db
Enhanced OpenAI integration with updated supported voice enums for text-to-speech and chat completions #3411
Neo4j module now automatically determines default embedding dimensions from the model cb97d9c
Added support for dynamically providing API keys for Anthropic requests on a per-request basis 0a1cf81
Added support for the latest Claude Opus-4 and Sonnet-4 models in the Anthropic chat model integration #3351
Enhanced OpenAI integration to support PDF files as media input for chat models 1f2bd08
Added MySQL database schema support for the SPRING_AI_CHAT_MEMORY table 9f58520
Improved handling and testing of complex metadata values in Chroma vector store integration 7466cb9
Added comprehensive metadata support for various vector store types to enable richer data storage and retrieval f78b549
Added configurable exception handling mechanisms for tool execution to improve error management and debugging capabilities 6f61fee
Added comprehensive integration tests for Chat Memory functionality when using SQL Server as the backend 4cac3ff

🪲 Bug Fixes

Resolved issue with toolAnnotationWeatherForecast test in BedrockNovaChatClientIT 58a527d
Resolved code style violations to maintain code quality standards 01c4b14
Corrected spelling error in STATELESS constant reference deffe80
Cleaned up unnecessary exception handling in JDBC chat memory implementation #4288
Resolved issue with FunctionCallWithPromptFunctionIT test for Anthropic provider c8a75ab
Resolved streamFunctionCallUsageTest failure in AzureOpenAiChatModelFunctionCallIT 7840139
Fixed chatCompletionStreamError handling in AnthropicApiIT integration tests e1228a7
Removed unnecessary null checks in template variable validation logic #4104
Resolved reordering problems in AzureOpenAi chat model implementation that affected message processing #4156
Enhanced error handling in ToolCallingAutoConfiguration to only log class names on ClassNotFoundException for better debugging befaf87
Resolved null pointer exception that occurred when converting MCP tools to async tool specifications 36a97d3
Fixed issues with calling stateless MCP (Model Control Protocol) tools 1df5f5c
Cleaned up duplicate code in AzureOpenAiChatOptions class c9ad1c7
Replaced SimpleDateFormat with thread-safe DateTimeFormatter to prevent concurrency issues b4348e6
Resolved issues with MCP client auto-configuration tests and added comprehensive documentation 2c6e448
Fixed test execution to only run tests for affected modules, not their dependencies, improving build efficiency 97eb1c9
Correctly exclude root module from affected modules list and handle empty string cases properly 77a704f
Prevent root module from appearing in affected modules list during build processes b8eac35
Add -am flag to properly build required dependencies during the build process 8f45ca1
Fixed main-push-fast workflow module detection and prevented recursive triggers to ensure stable CI operations b9cc239
Simplified commit SHA checkout to avoid git fetch issues and added enhanced run context a8cf2c9
Resolved infinite recursion in MongoDbAtlasLocalContainerConnectionDetails.getSslBundle() method #4149 via #4133
Corrected issue where actual model version used for chat was not being returned properly #4152
Properly handle merge operations when 'current' parameter is null #4153
Resolved NullPointerException when metadata is null in MilvusVectorStore operations #4116 via #4115
Fixed metadata immutability issue in Azure AI Search vector store implementation #4131 via #4117
Improved bean naming convention for streamable HTTP WebFlux client transports #4146
Resolved an issue where empty string finish_reason values in OpenAI streaming responses were not handled correctly #4132 via #1358
Resolved flaky test issues in streaming response aggregation functionality #4135 via #4134
Fixed maintenance branch detection to prioritize branch detection over explicit base_ref configuration f80a71c
Streamlined git operations to use 'git show HEAD' approach for better maintenance branch handling 007809b
Fixed excessive CI triggering and git history issues on maintenance branches c5d2ccd
Added fail-fast fallback mechanism and single-commit git diff strategy for improved reliability cfd9095
Improved retry handling for ResourceAccessException when encountering network connectivity issues #4094
Enhanced null checking using Optional to prevent NullPointerException occurrences #4063
Enhanced null checking using Optional to avoid NullPointerException #4064
Use Map#putAll instead of individual put operations for better performance #4062
Added strict option to Azure ChatCompletionsJsonSchemaResponseFormat to fix JSON schema handling #3931
Fixed pass check behavior for evaluators and prevented null pointer exceptions #3975
Similarity searches with the MariaDBVectorStore now properly provide similarity scores 891ef2a
Eliminates one deserialization step in the majority of scenarios when parsing model responses, improving performance when handling JSON string parameters #4003
Properly rethrow ToolExecutionException for non-RuntimeException cases, ensuring consistent exception handling behavior #3915
Tool function runtime exceptions are now properly wrapped in ToolExecutionException and re-thrown for better error handling and debugging #3918 via #2857
Corrected documentation and code comments for the Model Context Protocol (MCP) Client and Server components #4011 via #4010
Improved null checking in DefaultChatClient using Optional for better safety #3976
Enhanced code quality with better empty checks, method references, and pattern matching usage #3977 #3978 #3979
Corrected example code in documentation to ensure accuracy for users #3993
Resolved issues with Maven Central publication process 8366fa8
Made embedding options builder methods consistent across Bedrock providers for improved developer experience #3906
Corrected spelling of frequencyPenalty property in Google builders for proper parameter handling 128c45a
Fixed continuous integration failures to improve build stability and reliability #3844
Fixed issue where method tool calls would throw errors when multiple methods had the same name #2774
Resolves issues in MCP server auto-configuration integration tests #3792
Resolves null pointer exception in Anthropic API streaming functionality #3755 via #3740
Corrects SystemPromptTemplate builder to return proper SystemPromptTemplate.Builder instead of generic PromptTemplate.Builder dbaa608
Resolves parameter ordering issues in JSON schema generation functionality #3733
Corrected annotation package configuration issues #3716
Fixed issue where audio filename was lost when requesting OpenAI /transcriptions and /translations interfaces af07517
Fixed issue preventing streaming tool calling responses when internal execution is enabled for Anthropic provider 879c5e2
Added validation for documents text/media check when adding to vector store #3687 via #3609
Corrected assert message in SimpleApiKey for better error reporting #3656
Fixed various typos throughout the codebase for improved clarity #3695
Removed unused configuration options from ZhiPu AI model implementation #3669
Removed incorrect @nullable annotation from VectorStore similaritySearch method #3613
Fixed incorrect changes in Ollama auto-configuration that were causing issues #3645
Fixed getTextBetweenParagraphs method to properly handle invalid page numbers in outline items d92a2ea
Corrected naming inconsistencies in the Mistral package for better consistency #3652
Removed unnecessary null check in OpenAiApi.Builder#apiKey(String) method #3654
Added required license header to FileDocumentWriterTest class #3651
Resolved issue with streaming tool calls that have no input parameters in Anthropic integration f575051
Fixed streaming tool calling functionality when no input arguments are provided in Bedrock integration 8107612
Corrected autoconfiguration class name and added ElevenLabs speech documentation link #3610
Prevents incorrect ToolCall merging caused by empty id and name strings in DeepSeek integration d61192a
Resolved exception in OpenAiAudioTranscriptionResponseMetadata.toString method that was causing runtime errors #3575
Resolved infinite recursion issue in getMimeType(Path) method that could cause stack overflow errors ab04e27
Resolved test failure in ChromaVectorStoreAutoConfigurationIT due to updated exception message #3581
Corrected logic for determining output modalities when using streaming mode d9a5337
Improved logging for ChromaDB collection creation to provide clearer feedback 0d8eebd
Enhanced error handling in McpToolCallback to properly handle root exceptions d6924b6
Resolved issue preventing proper generation of configuration metadata for Spring AI tools observations #3539 via #3550
Corrected parameter order in ClassUtils.isAssignable call within validateToolContextSupport method 76c7018
Resolved test configuration issues in Ollama embedding auto-configuration tests 66324a6
Corrected similarity option parsing in ElasticsearchVectorStore for proper functionality f8d0503
Corrected version alignment for ElevenLabs starter and autoconfiguration artifacts 15775f1
Refactored parameter naming for better code clarity in ChatGenerationMetadata #3507
Resolved configuration issue where embeddingFieldName was not properly set when configuring ElasticsearchVectorStore #3501 via #3500
Corrected issue where Bedrock Titan embeddings were not returning proper usage statistics c4e434a
Corrected parameter order error in validateToolContextSupport method that was causing incorrect validation results 59d2661
Improved logic for checking functional types in MethodToolCallbackProvider to properly identify function implementations fe4f0d1
Resolved SQL error in the isTableExists method of MariaDBSchemaValidator that was preventing proper table validation b925c50
Resolved issues in OpenAiChatClientMethodInvokingFunctionCallbackIT test to ensure proper integration testing 95b3df7
Fixed Qdrant vector database integration to properly handle Long type values in payload by converting them to String f0d4cbf
Fixed OpenAiChatOptions to properly support transfer of webSearchOptions 4621c81
Refactored QdrantObjectFactory to properly handle null metadata values 8b45f41
Fixed missing properties in the ChromaVectorStore AutoConfiguration that were preventing proper initialization #3435 via #3427
Added compatibility for Spring Framework 7.x to RetryUtils ResponseErrorHandler #3416 via #3415
Resolved issue where an extra system message was incorrectly added when the system message was not the first one in the message list 902fc09
Removed unreachable code branch that could cause confusion in chat memory advisor logic #3395
Avoided unnecessary looping through all page tree when there is no destination page in PDF document reader #3396
Fixed null pointer exception when accessing duration metadata from Ollama chat model responses 72fe3bf
Corrected the CustomerTools documentation example to reference proper existing methods #3390
Added protection against empty unicode strings during PDF document processing #3271 via #3054
Fixed issue where already valid JSON strings were being double-serialized in JsonParser.toJson method 18ae16e
Corrected typo in ToolCallback class to improve code clarity #3352
Resolved critical connection leak issue when using JdbcChatMemoryRepository that could cause resource exhaustion #3283 via #3281
Updated useAutoConfiguredJdbcChatMemoryRepository test to work correctly after the connection leak fix 029e8a1

📓 Documentation

Comprehensive documentation for the new Spring AI Google GenAI integration modules e26120a
Corrected git log command syntax in project documentation #4272
Updated tools.adoc documentation with latest information #4278
Improved documentation for Docker services setup and configuration #4253
Updated project README with latest information and improvements #4161
Fixed typo from 'are' to 'and' in advisors.adoc documentation #4219
Added more detailed explanation in observability documentation about metrics configuration and usage a0ad921
Various small improvements to documentation content and formatting ad93613
Added extensive validation and functionality tests for the Document class to improve test coverage 2bca047
Added new model names in Anthropic documentation #4077
Added reference documentation for MariaDBVectorStore similarity score functionality 9d19181
Added comprehensive documentation for the new metadata support feature in ChatClient c328ef6
Enhanced readability by formatting documentation with one sentence per line 54a2dc3
Updated getting-started.adoc documentation to reflect 1.0.0 release changes and improvements #3920
Improved chat-memory.adoc documentation with updated information and examples #3917
Fixed various typos in comments and improved overall documentation quality #3936
Updated outdated information in project documentation to reflect current state 056c261
Updated ChromaDB configuration details to include comprehensive support for Chroma Cloud deployment #4008
Enhanced documentation for the call() method in ChatClient with clearer examples and usage guidelines #3963
Fixed bug in example code to provide accurate documentation for users #3993
Applied consistent AsciiDoc styling to CONTRIBUTING.adoc for improved documentation formatting #3883
Optimized Bedrock documentation to keep it synchronized with current code implementation #3843 via #3842
Fixed typo in PropmptTemplate reference within structured-output-api.jpg documentation #3304 via #3295
Added example demonstrating dynamic Model Context Protocol client selection #3751
Updated Model Context Protocol specification documentation link #3810
Fixed example code in streaming responses documentation #3802
Improves documentation for ChatClient advisor configuration and usage 965b1d2
Updates Model Context Protocol documentation to reference current implementation patterns #3760
Updated documentation for Anthropic chat integration #2723
Updated contributing guidelines to use Developer Certificate of Origin instead of Contributor License Agreement #3228 via #3094
Corrected typographical errors in token configuration documentation #3677
Updated documentation with current code examples and removed deprecated references #3717 via #3713
Fixed property name from is-auto-id to auto-id in Milvus vector store documentation #3704 via #3702
Cleaned up duplicated dependency instructions in opensearch.adoc documentation #3712
Corrected incorrect default embedding model reference in ollama-embeddings.adoc #3686
Enhanced README with Elasticsearch vector store documentation and integration details #3688
Fixed broken link in javadoc to Message source in Content class #3672
Fixed various spelling errors and typos in documentation and code comments #3678
Fixed documentation for SimpleLoggerAdvisor to provide accurate usage information #3638
Updated tools documentation to provide correct usage examples and guidance 585f554
Updated tools.adoc with improved documentation #3624
Corrected toolDefinition parameter transfer error in documentation #3468
Corrected broken link to ChatModel in documentation #3583
Improved clarity and formatting in Weaviate vector store documentation 12c725d
Improved documentation for Spring AI advisors functionality #3552
Enhanced documentation for MCP Server Boot Starter selection and configuration guidance #3511
Updated ZhipuAI chat integration documentation #3531
Corrected documentation examples showing proper usage of tools and defaultTools configuration #3533
Repaired broken links to ChatOptions and ChatOptions#builder() in web documentation #3447
Corrected code examples in the openai-chat.adoc documentation to ensure accuracy and proper implementation guidance #3493
Updated Hugging Face integration documentation with improvements and clarifications #3445
Fixed documentation typos in cloud bindings configuration #3436
Corrected ToolDefinition.builder() usage examples in documentation #3431
Updated Azure OpenAI chat documentation to reflect response format changes #3434 via #3354
Revised and improved documentation for DeepSeek and Minimax chat model integrations #3408
Corrected video MIME type specifications and standardized formatting in Bedrock Converse documentation #3413
Cleaned up duplicate reference to NoOpTemplateRenderer in ChatClient documentation #3414
Enhanced Elasticsearch documentation with detailed description of the embedding-field-name configuration property #3399 via #2082
Corrected spelling error in the contribution guidelines documentation #3378
Enhanced documentation with checkstyle configuration and usage instructions #3277
Updated advisor documentation to reference correct dependencies a0d187d
Improved documentation for Mistral AI embeddings integration #3362
Corrected broken links in documentation pointing to Media.java class #3322
Updated link to point to official awesome-spring-ai repository #3328
Updated documentation with improved example using OpenAiChatModel.builder() for custom API key configuration #3335
Fixed and improved documentation for function calling and tool integration #3292
Improved documentation for the MCP Server Boot Starter configuration and usage #3279
Corrected incorrect external link formatting in the effective agents documentation #3275
Corrected various typos throughout the documentation to improve readability #3263
Added proper title to documentation that was missing title metadata 09dd973

🔨 Dependency Upgrades

Added spring-ai-mcp-annotations dependency to MCP auto-configurations ef71e4e
Updated MCP SDK to version 0.11.3 for improved functionality and compatibility 09d2a91
Updated io.swagger.core.v3:swagger-annotations from version 2.2.25 to 2.2.30 #4187 via #4185
Upgraded MCP SDK version to 0.11.1 #4048
Updated Tika, pdfbox and jsoup to latest versions for improved document reading capabilities #3912
Updated Ollama integration to use the latest API version for improved compatibility and features 3ee33c1
Updated PostgreSQL JDBC driver from version 42.7.5 to 42.7.7 #3934
Updated io.modelcontextprotocol from 0.11.0-SNAPSHOT to stable 0.11.0 release #3990
Updates Model Context Protocol library to latest snapshot version #3781
Enhanced schema initialization logic and updated deprecated code for Milvus vector database integration #3705
Updated JdbcChatMemoryRepositoryHsqldbAutoConfigIT from JUnit 4 to JUnit 5 #3633
Replaced swagger-annotations with swagger-annotations-jakarta for Jakarta EE compatibility 3e02edc
Updated Spring Boot dependency to version 3.5.0 for latest features and improvements 2be1e42
Updated org.apache.pdfbox dependency to version 3.0.4 for improved PDF processing #3271 via #3265

⚡ Performance

Improved performance of the from method in JdbcChatMemoryRepositoryDialect 1607eb8
Improved fast workflow performance with better logging and optimization for true no-op builds b339f56
Eliminates unnecessary deserialization step when parsing JSON string parameters in model responses #4003
Reuse DocumentRowMapper instance to reduce redundant object creation and improve performance af1ce67
Improved performance by optimizing debug logging operations in the chat memory advisor #3448

🔩 Build Updates

Enhanced test coverage for HTTP client transport auto-configuration with MCP support #4147
Updated VS Code formatting configurations for improved developer experience 80228af
Improved test coverage for tool execution components #4268
Applied code style fixes and formatting improvements to maintain code quality standards 6880753
Added extensive test coverage for tool calling observation components to improve code reliability #4259
Restored Groq API integration tests to ensure proper testing coverage for Groq provider functionality 39c5c38
Restored Maven settings.xml configuration file required for continuous integration builds 72f7c63
Improved test coverage for ChatClient response handling and builder functionality #4216
Code formatting improvements in test files e119eb7
Restructured MCP server auto-configuration modules for improved modularity and maintainability a38aad8
Comprehensive test coverage improvements across Spring AI modules with additional edge case testing d67a3cd
Enabled manual triggering for maintenance workflows and optimized builds by skipping when no new commits exist 23242ca
Added missing run-name configuration to maintenance-fast.yml workflow ab826e4
Enhanced continuous integration workflow with better concurrency control, run naming improvements, and duplicate schedule removal 349a9e5
Updated main-push-fast.yml to test only affected modules, improving build efficiency 77d0058
Optimized deployment process by skipping tests during the deploy phase to improve build performance da0f92a
Enhanced build visibility with progress indicators for different build phases d4d95b9
Exclude Python cache files from CI script copying to prevent build contamination 6998de9
Enable verbose output to better trace and debug root module issues during builds feb5bf3
Ignore all .github changes in main push fast workflow to reduce unnecessary build triggers 6c8ecd9
Optimized CI/CD pipeline to provide faster feedback on pull request merges and improved build performance de5cd35
Always exclude root pom.xml from fast workflow module detection to improve build accuracy b767954
Added workflow_dispatch capability to test specific commits in the fast workflow for better debugging 5204e04
Resolved issues with artifactory build and release automation pipeline 90f636e
Enhanced test coverage for chat client observation functionality #4124
Implemented intelligent path-based build triggering to optimize CI/CD pipeline efficiency 4df281c
Added clearer naming conventions for documentation deployment workflows ecc3317
Fixed git state problems that were triggering unnecessary full project builds 4ea7c5c
Synchronized build workflows with the streamlined 1.0.x branch configuration 26e0983
Updated .gitignore to exclude pycache directories from version control b6cda1c
Corrected CI workflow to use ../mvnw for assembly generation in spring-ai-docs #4072
Improved test coverage in Anthropic provider with comprehensive validation and edge cases dffec8d
Improved test coverage across various classes 8748a8d
Enabled manual workflow dispatch for CI/CD build processes f17dfa1
Improved CI/CD by using Maven wrapper and batch-mode in GitHub Actions #3841
Added comprehensive edge case tests for tool result conversion and Redis filter expressions #4043
Updated test class naming to follow Spring framework conventions 9bbde2a
Enhanced test coverage with comprehensive tests for AzureOpenAiChatOptions and PostgresMlEmbeddingOptions #4042
Added extensive test coverage for OCICohereChatOptions, AzureEmbeddingsOptions, and WeaviateVectorStoreOptions classes #4041
Improved test coverage for output conversion and streaming utilities #4039
Enhanced test coverage for OllamaChatModel and OllamaEmbeddingModel implementations #4038
Added extensive unit tests for Query class validation and equality behavior, Spring AI builders, runtime hints registration, and PgVector embedding dimensions #4036
Added extensive test coverage for Spring AI core runtime hints registration to ensure proper native compilation support #4024
Added comprehensive tests for ChatClientRequest mutation and context handling functionality #4022
Added edge case tests for VertexAI Gemini runtime hints registration to improve native image compatibility #4013
Added comprehensive test coverage for Ollama runtime hints registration to ensure proper GraalVM native image support #4014
Enhanced test coverage for VectorStore runtime hints registration to validate native compilation compatibility #4015
Added comprehensive test coverage for PDF Reader runtime hints to ensure proper native image support #4016
Added comprehensive test coverage for multiple vector database filter expression converters including PgVector, MongoDB Atlas, Milvus, Pinecone, MariaDB, Neo4j, and OpenSearch AI Search #3916, #3919, #3922, #3932, #3943, #3957, #3950
Enhanced test coverage for OpenAI Chat Options component #3959
Removed unused import statements to improve code quality #3921
Comprehensive test coverage improvements for MistralAi, Anthropic chat options, VectorStoreChatMemoryAdvisor, and QdrantVectorStore builders #3968 #3973 #3985 #3986
Added comprehensive test coverage for MistralAi, Anthropic, AzureOpenAi, OpenAi, and MCP client runtime hints configurations #3987
Updated MCP server auto-configuration settings for improved functionality 1256eaf
Refactored builder pattern in VertexAiGeminiSafetySetting for improved code structure and maintainability 49e5c63
Updated .gitignore file to improve version control handling and exclude unnecessary files 44816fb
Refactored MethodToolCallbackProviderTests and updated OpenAI audio tests due to safety settings changes a216bf1
Clean up unnecessary files from the codebase 8a5635d
Applied diamond operator usage, null checks, string joining optimizations, and added JavaDocs across the codebase #3458 and #3663 and #3013
Converted Qdrant vector store integration tests to use OpenAI embedding model #3671
Improved reactive Context propagation to AsyncMcpToolCallback for better async handling 9a52182
Updated AzureOpenAiAudioTranscriptionModelIT to use OkHttpClient for improved testing #3665
Removed redundant SOURCE_METADATA assignments and simplified conditional checks in TextReader #3627
Cleaned up useless properties tags in configuration files #3634
Updated backport-issue.yml to use main branch for reusable workflows 5aa8940
Added comprehensive test coverage for FileDocumentWriter default constructor and various configuration options 089c3eb
Improved logging consistency by replacing System.err.println calls with proper log output #3600
Removed unused import statements to improve code cleanliness #3599
Cleaned up unused messageHistory implementation #3574
Standardized the order of getter and setter methods in WeaviateVectorStoreProperties #3582
Cleaned up test dependency management by removing explicit version declaration for jackson-dataformat-xml d8c728e
Added comprehensive unit testing for multiple method tool callbacks functionality with tool context support b9a6834
Corrected @Formatter:onn to @Formatter:on to ensure proper code formatting in test files #3477
Added comprehensive test coverage for embeddingFieldName configuration in ElasticsearchVectorStore 6451fef
Made auto-configuration dependencies optional in the docker compose module for better modularity #3502
Made auto-configuration dependencies optional in the testcontainers module for improved flexibility #3465
Replaced spring-webflux with spring-web dependency in the spring-ai-retry module cecc046
Fixed GitHub Actions CI/CD pipeline to properly trigger for the 1.0.x branch 5f23dca
Enhanced CI build configuration to support non-main branches a385ed4
Moved speech1.mp3 test file to proper src/test/resources location ab88fea
Updated gitignore to exclude Qodana static analysis configuration file 5b49036
Enhanced test coverage for OpenAI streaming function calling helper functionality #3312
Added automated workflows for cherry-picking commits and handling backport issues bfaa6be
Improved OpenAI API key resolution to handle dynamic key retrieval per request 3a527ee
Applied checkstyle fixes to improve code formatting and consistency b6f29a4
Updated project version for next development iteration d93ab77

🔐 Security

Updated Protobuf Java from 3.25.2 to 3.25.8 to address security vulnerability CVE-2024-7254 #3996

🙏 Contributors

Thanks to all contributors who made this release possible:

spring-projects/spring-ai v1.1.0-M1 Spring AI 1.1.0-M1 on GitHub

Spring AI Next Release Release Notes

🎯 Highlights

⏪ Breaking Changes

⚠️ Upgrading Notes

📢 Noteworthy

⭐ New Features

🪲 Bug Fixes

📓 Documentation

🔨 Dependency Upgrades

⚡ Performance

🔩 Build Updates

🔐 Security

🙏 Contributors

spring-projects/spring-ai v1.1.0-M1
Spring AI 1.1.0-M1

on GitHub