4 Pull requests merged by 3 people

• Fix McpServerAutoConfigurationIT

  #3792 merged Jul 11, 2025

• Upgrade io.modelcontextprotocol 0.10.0 -> 0.11.0-SNAPSHOT

  #3781 merged Jul 10, 2025

• Improve the MCP document to stop referring to outdated DefaultMcpSession

  #3760 merged Jul 8, 2025

• Fix NPE in AnthropicApi StreamHelper

  #3755 merged Jul 7, 2025

14 Pull requests opened by 11 people

• docs(mcp): add dynamic MCP client selection example

  #3751 opened Jul 6, 2025

• Fix string return conversion in DefaultToolCallResultConverter

  #3756 opened Jul 7, 2025

• feat(SimpleLoggerAdvisor): Add log level configuration function

  #3764 opened Jul 8, 2025

• Support responseSchema in VertexAiGeminiChatOptions

  #3765 opened Jul 8, 2025

• refactor: GH-3620 Add `BedrockChatOptions` to Bedrock

  #3770 opened Jul 9, 2025

• refactor: Simplifies VectorStoreChatMemoryAdvisor code

  #3773 opened Jul 9, 2025

• fix: update default sse-message-endpoint from /mcp/message to /mcp/messages

  #3779 opened Jul 10, 2025

• Feature (TokenTextCplitter): Add overlapping function for text segmentation #2123

  #3780 opened Jul 10, 2025

• fix: Handling default implementation of ToolCallback#call(String,ToolContext)

  #3784 opened Jul 10, 2025

• fix: Fixed the issue where the returnDirect attribute was not effective on the MCP server side.

  #3787 opened Jul 11, 2025

• Feat(rerank): Add Cohere Reranker with topN filtering and fallback support

  #3791 opened Jul 11, 2025

• McpSyncServer: set immediate execution when in a servlet context

  #3794 opened Jul 11, 2025

• GH-3690: Support customization of RedisVectorStore via builder customizer

  #3795 opened Jul 11, 2025

• feat(zhipuai): Support glm-4.1v-thinking-flash model

  #3796 opened Jul 11, 2025

22 Issues closed by 4 people

• could not found io.modelcontextprotocol.sdk:mcp:jar:0.11.0-SNAPSHOT in repo

  #3789 closed Jul 11, 2025

• When I use Gemini, if I am not configured in the configuration file, I cannot start how to close it, because I want to create it through the application.

  #3774 closed Jul 10, 2025

• Support for OpenAI /v1/responses

  #3766 closed Jul 9, 2025

• Support for Azure OpenAI Assistants API

  #3772 closed Jul 9, 2025

• Will `returnDirect = true` effect in mcp server?

  #3400 closed Jul 9, 2025

• Git clone with error: Filename too long

  #3125 closed Jul 9, 2025

• How to dynamically add McpSyncServer in a project and add sseendpoint as needed, such as /sse1, /sse2, /sse3....

  #3771 closed Jul 9, 2025

• Feature Request: Java Stream HTTP Support for MCP SDK

  #3752 closed Jul 9, 2025

• mcp-client-stdio-test bug

  #3598 closed Jul 8, 2025

• Support Foundry local https://github.com/microsoft/Foundry-Local

  #3628 closed Jul 8, 2025

• EsVectorStore Search NoSuchMethodError

  #3632 closed Jul 8, 2025

• When version 1.0.0-M5 uses elastic as vectorstore, the query will report that the method cannot be found

  #2220 closed Jul 8, 2025

• Docs: spring docs retrieval wrong method name

  #2296 closed Jul 8, 2025

• Improve the MCP document to stop referring to outdated DefaultMcpSession

  #3762 closed Jul 8, 2025

• Problems with the use of the chat memory function

  #3759 closed Jul 8, 2025

• AnthropicChatModel#stream produces too much output when calling tools

  #3650 closed Jul 7, 2025

• Please help improve the response speed of the model when using tools.

  #3676 closed Jul 7, 2025

• How to make tools/list return specific tool sets according to different business areas

  #3719 closed Jul 7, 2025

• Chat memory questions during use！

  #3754 closed Jul 7, 2025

• SystemPromptTemplate removes double curly braces {{...}} when rendering prompts

  #3721 closed Jul 7, 2025

• Anthropic Error Responses Can Cause NPE In StreamHelper

  #3757 closed Jul 7, 2025

• Anthropic Error Responses Can Cause NPE In StreamHelper

  #3740 closed Jul 7, 2025

18 Issues opened by 18 people

• Doc: Wrong dependency info in the RAG doc

  #3798 opened Jul 11, 2025

• Feature Request: Allow configuration of payload content key for QdrantVectorStore

  #3797 opened Jul 11, 2025

• open ai + vllm 工具调用模型死循环不返回

  #3793 opened Jul 11, 2025

• Add ChatClient getChatModel() method

  #3790 opened Jul 11, 2025

• response.getEvalDuration(); threw a NullPointerException.

  #3788 opened Jul 11, 2025

• Add Support for OpenAI based64 format embedding responses

  #3786 opened Jul 11, 2025

• Unable to start app after setting up opensearch vector store

  #3785 opened Jul 10, 2025

• Official Claude 4 Support

  #3783 opened Jul 10, 2025

• Add MCP Client Streamable HTTP transport auto-configuration

  #3782 opened Jul 10, 2025

• Does it support video inference

  #3777 opened Jul 10, 2025

• Question about Tool Call Information in Multi-Turn Conversations

  #3776 opened Jul 10, 2025

• Please confirm if it is a bug,Springai encountered an error while calling VLLM

  #3775 opened Jul 10, 2025

• mcp illegal jsonrpc

  #3769 opened Jul 9, 2025

• Streaming with tools not working with Anthropic ChatClient

  #3767 opened Jul 8, 2025

• A few minutes after the mcp client connects, the server will be disconnected

  #3763 opened Jul 8, 2025

• TransformersEmbeddingModel and configuration of Threads

  #3761 opened Jul 8, 2025

• Make the setting spring.ai.openai.api-key optional

  #3753 opened Jul 7, 2025

• Can this Spring AI compete official Typescript AI SDKs?

  #3750 opened Jul 5, 2025

69 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• ToolCallingChatOptions support internalToolExecutionMaxIterations, to limit the maximum number of tool calls and prevent infinite recursive calls to LLM in special cases

  #3380 commented on Jul 8, 2025 • 2 new comments

• feat: Add Mistral AI OCR API integration

  #2404 commented on Jul 11, 2025 • 0 new comments

• feat(redis): Add Redis-based semantic caching and chat memory implementations

  #2295 commented on Jul 11, 2025 • 0 new comments

• feature: Add common TranscriptionModel interface for audio transcription

  #1484 commented on Jul 11, 2025 • 0 new comments

• Support StabilityAi Image Edit Api

  #1344 commented on Jul 11, 2025 • 0 new comments

• Added new VertexAI Anthropic's model module

  #1213 commented on Jul 11, 2025 • 0 new comments

• feat: add hugging face text to image integration

  #1162 commented on Jul 11, 2025 • 0 new comments

• Add self-query advisor

  #1019 commented on Jul 11, 2025 • 0 new comments

• After the mcp server restarts, the client will return 404.

  #3337 commented on Jul 11, 2025 • 0 new comments

• Request to Make ChatOptions Runtime-Validated Instead of Required at Startup

  #3404 commented on Jul 11, 2025 • 0 new comments

• VectorStore interface should be split, with readonly operations becoming a super interface

  #1290 commented on Jul 11, 2025 • 0 new comments

• I need a solution to instable tool calling behavior in deepseek

  #3602 commented on Jul 11, 2025 • 0 new comments

• Support A2A Protocol

  #2911 commented on Jul 11, 2025 • 0 new comments

• Reasoning options documented in docs

  #3725 commented on Jul 11, 2025 • 0 new comments

• RedisVectorStore auto-configuration does not support metadataFields, causing chat memory retrieval failure

  #3690 commented on Jul 11, 2025 • 0 new comments

• Spring AI MCP Streamable HTTP

  #3145 commented on Jul 11, 2025 • 0 new comments

• com.google.api.gax.rpc.UnknownException: java.net.SocketTimeoutException: Read timed out

  #1577 commented on Jul 11, 2025 • 0 new comments

• block()/blockFirst()/blockLast() are blocking, which is not supported in thread reactor-http-nio-3

  #2533 commented on Jul 11, 2025 • 0 new comments

• feat: support the chat_template_kwargs, with OpenAI-Compatible Server…

  #3744 commented on Jul 11, 2025 • 0 new comments

• Add `ISNULL`, `ISNOTNULL` Filter Expression

  #3706 commented on Jul 8, 2025 • 0 new comments

• enhanced-deepseek cot

  #3703 commented on Jul 11, 2025 • 0 new comments

• Oracle: add OracleChatMemory support

  #3601 commented on Jul 10, 2025 • 0 new comments

• Add a method to delete all chat memories in ChatMemory

  #3590 commented on Jul 10, 2025 • 0 new comments

• GH-3540: Allow user-provided embeddings in VectorStore

  #3541 commented on Jul 11, 2025 • 0 new comments

• Add docker/mcp-gateway docker compose service connection

  #3536 commented on Jul 9, 2025 • 0 new comments

• fix(streaming): Remove retry wrapper from chat model stream methods

  #3524 commented on Jul 9, 2025 • 0 new comments

• Ollama: Support custom Ollama API paths

  #3470 commented on Jul 8, 2025 • 0 new comments

• An implementation of ChatMemory based on token size control

  #3424 commented on Jul 10, 2025 • 0 new comments

• Fix PropmptTemplate typo in structured-output-api.jpg

  #3304 commented on Jul 11, 2025 • 0 new comments

• Add Spring SpEL implementation of TemplateRenderer

  #3262 commented on Jul 11, 2025 • 0 new comments

• Provides a Jinja2 implementation for TemplateRenderer

  #3259 commented on Jul 11, 2025 • 0 new comments

• add aws bedrock prompt-caching support

  #3213 commented on Jul 11, 2025 • 0 new comments

• feat(memory): First commit of file-based memory repository

  #3210 commented on Jul 11, 2025 • 0 new comments

• Add filter query support for GemFireVectorStore

  #2753 commented on Jul 8, 2025 • 0 new comments

• Create MongoDB chat memory implementation

  #2679 commented on Jul 11, 2025 • 0 new comments

• sse client doesn't support like reconnect

  #3742 commented on Jul 9, 2025 • 0 new comments

• Is the `embeddingDistance` Method in `PgVectorStore` Necessary?

  #3630 commented on Jul 8, 2025 • 0 new comments

• Is it considered to support AG-UI Protocol?

  #3260 commented on Jul 8, 2025 • 0 new comments

• How can I obtain the information before and after the tool call using the streaming call tool?

  #3639 commented on Jul 8, 2025 • 0 new comments

• Feature Request: Add public getters for configuration fields in TokenTextSplitter

  #3644 commented on Jul 8, 2025 • 0 new comments

• Support Vector Databases Multiple indexes or collections

  #468 commented on Jul 8, 2025 • 0 new comments

• Question about sglang + deepseek

  #3657 commented on Jul 7, 2025 • 0 new comments

• FilterExpressionTextParser does not support 'null' values

  #3694 commented on Jul 7, 2025 • 0 new comments

• Cannot Set Image detail Option (e.g., "low") When Using Multimodal Input in Spring AI

  #3710 commented on Jul 7, 2025 • 0 new comments

• Spring AI Kotlin Coroutines

  #3718 commented on Jul 7, 2025 • 0 new comments

• Vertex AI Gemini logprobs support

  #3723 commented on Jul 7, 2025 • 0 new comments

• AssistantMessage doesn't support 'name' property

  #3737 commented on Jul 7, 2025 • 0 new comments

• Hope to provide support for Ollama's thinking mode

  #3738 commented on Jul 7, 2025 • 0 new comments

• VectorStore filter improve

  #3739 commented on Jul 7, 2025 • 0 new comments

• Consider caching JSON schema generation in function calling

  #3403 commented on Jul 7, 2025 • 0 new comments

• MCP server: Authentication lost in tool execution

  #2506 commented on Jul 5, 2025 • 0 new comments

• Supporting multiple LLMs in auto-config

  #2610 commented on Jul 5, 2025 • 0 new comments

• spring ai supports tool chaining

  #3691 commented on Jul 11, 2025 • 0 new comments

• openai options support extra params

  #3409 commented on Jul 11, 2025 • 0 new comments

• ToolCallback fails if tool context is provided

  #3389 commented on Jul 10, 2025 • 0 new comments

• After migrating from milestones to stable, Observability stopped exposing input/output (null)

  #3401 commented on Jul 10, 2025 • 0 new comments

• Support for Text Chunking with Overlap in TokenTextSplitter

  #2123 commented on Jul 10, 2025 • 0 new comments

• I hope the next version can provide the functionality of openai request and response formats

  #3560 commented on Jul 10, 2025 • 0 new comments

• @Tool returnDirect Attribute Ignored

  #3481 commented on Jul 10, 2025 • 0 new comments

• Can multiple MCP servers with different endpoints be published in one service?

  #3299 commented on Jul 10, 2025 • 0 new comments

• spring ai bedrock converse properties auto completion doesn't auto complete

  #3620 commented on Jul 9, 2025 • 0 new comments

• Support image moderation in OpenAI

  #2832 commented on Jul 9, 2025 • 0 new comments

• Vertex AI Streaming not working

  #3313 commented on Jul 9, 2025 • 0 new comments

• Ollama thinking mode

  #3543 commented on Jul 9, 2025 • 0 new comments

• Should allow to override the column name 'content' for pgvector, weaviate

  #3547 commented on Jul 9, 2025 • 0 new comments

• PgVectorStore does not handle ANDs and ORs together properly when using the FilterExpressionBuilder

  #3577 commented on Jul 9, 2025 • 0 new comments

• Most of classes implementing BaseAdvisor lacks logs

  #3587 commented on Jul 9, 2025 • 0 new comments

• JdbcChatMemoryRepository do not persist Media in UserMessage

  #3597 commented on Jul 9, 2025 • 0 new comments

• "Request was interrupted: null" error when VectorStore.save is called with a List<Document> whose size is large

  #3370 commented on Jul 9, 2025 • 0 new comments