Update langchain4j monorepo to v1 (major)

[renovate]

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package	Change	Age	Confidence
dev.langchain4j:langchain4j-open-ai (source)	0.32.0 → 1.11.0
dev.langchain4j:langchain4j (source)	0.32.0 → 1.11.0

---

Release Notes

langchain4j/langchain4j (dev.langchain4j:langchain4j-open-ai)

v1.11.0: and 1.11.0-beta19

Compare Source

Notable Changes

• Agentic: support streaming by @​mariofusco in #​4350
• Agentic: support multimodality by @​mariofusco in #​4436
• Bedrock: support Guardrails by @​jonathannaguin in #​3988
• Elasticsearch: hybrid search implementation by @​l-trotta in #​4069
• Gemini: support Nano Banana and Nano Banana Pro by @​Bram-- in #​4380
• Gemini: support Google Search tool (Issue #​4453) by @​mohankumar27 in #​4456
• MCP: Injecting context into header providers & support for listeners by @​jmartisk in #​4467
• Mistral: support reasoning models by @​dskarzh in #​4474
• Observability: allow to listen for tool executions in both AiServices and agents by @​mariofusco in #​4368
• Observability: add listeners for embedding model, embedding store and content retriever by @​LucasGois1 in #​4349
• OpenAI: experimental Responses API support by @​maxlepikhin in #​3816
• PgVector: hybrid search implementation by @​YongGoose in #​4288

Other Changes

• docu: update versions to 1.10.0 and 1.10.0-beta18 by @​dliubarskyi in #​4284
• Update versions to 1.11.0-SNAPSHOT and 1.11.0-beta19-SNAPSHOT by @​dliubarskyi in #​4285
• [BUG] DefaultPromptTemplateFactory not took space brackets into consi… by @​omarmahamid in #​4291
• Tool Should Support Empty Return String by @​omarmahamid in #​4301
• JUnit 6 by @​dliubarskyi in #​4305
• feat: InMemoryEmbeddingStore add size() and isEmpty() by @​wangxuanni in #​4289
• [feature] ChatMemory always keep system message on index 0 by @​mr-cloud in #​4304
• isNullOrBlank check on wrong field Type by @​omarmahamid in #​4319
• fix typo method on AiServiceTokenStreamParameters by @​omarmahamid in #​4321
• Method has poor performance InMemoryEmbeddingStore by @​omarmahamid in #​4323
• [BUG] Azure ACADS documentation missing Examples section and broken link in code by @​thswlsqls in #​4325
• [BUG] Azure and GCS document loaders do not skip failed documents in loadDocuments() by @​thswlsqls in #​4327
• fix(workers-ai): fix deserialization error due to missing fields by @​jujn in #​4336
• [BUG] Missing interrupt status restoration in InterruptedException handlers by @​thswlsqls in #​4340
• [BUG] Missing interrupt status restoration in InterruptedException handlers #​2 by @​thswlsqls in #​4342
• [BUG] AnthropicChatModelBuilder.toolChoiceName() does not assign parameter to field by @​thswlsqls in #​4346
• Gemini 3 thinking level configuration by @​omarmahamid in #​4357
• Fix float bound check in tool by @​omarmahamid in #​4356
• [DOCS] Add OceanBase embedding store documentation by @​xxsc0529 in #​4359
• [BUG] 4250 - set media resolution in gemini generate content request by @​partarstu in #​4337
• [BUG] DefaultAiServices creates new ExecutorService per instance causing resource leak by @​thswlsqls in #​4344
• feat: Add onPartialToolCall callbacks to TokenStream by @​adrianolaselva in #​4292
• Upgrade to OpenAi Java SDK v4.13.0 by @​jdubois in #​4367
• Disallows json deserialization of AgenticScope containing non-final cl… by @​mariofusco in #​4377
• Avoid overwriting a structured state with an unstructured argument generated from supervisor's LLM response by @​mariofusco in #​4381
• docs: Support Spring Boot 3.5 by @​ThomasVitale in #​4384
• refactor(mcp): extract protocol types and shared stdio JSON-RPC IO handler by @​qicesun in #​4371
• Fix registration of subagents in conditional pattern when using the declarative API by @​mariofusco in #​4387
• Add support for AiServiceRequestIssuedEvent and corresponding listener functionality by @​edeandrea in #​4386
• Add omni-moderation models to OpenAiModerationModelName by @​ghtjr410 in #​4390
• Introduce langchain4j.http.clientBuilderFactory system property by @​geoand in #​4397
• update prompt caching availability docs by @​nitinramvelraj in #​4374
• [BUG] Remove duplicate tool description in Bedrock API requests (#​4035) by @​TylerBarkley in #​4376
• [BUG] 4299 - Make BatchResponse#operations nullable and handle it. by @​Bram-- in #​4382
• Add nano banana documentation by @​Bram-- in #​4395
• Feat: Use streaming I/O for JSON serialization in InMemoryEmbeddingStore by @​wangxuanni in #​4401
• fix handling of multimodal Content parameters in AiServices by @​jujn in #​4353
• Add Supplier support for customHeaders in OpenAI models by @​ghtjr410 in #​4403
• Using the local AWS region instead of cross region inferences to have… by @​jonathannaguin in #​4412
• fix: handle empty embeddings in OnnxBertBiEncoder by @​csbiy in #​4406
• #​4413 - PGVector does not escape values in an IN (notIn) filter by @​odelpozo-denodo in #​4414
• [DOCS] Add Amazon S3 Vectors embedding store documentation by @​ss-bhatt in #​4421
• Add Supplier support for customHeaders in Ollama models by @​ghtjr410 in #​4419
• Avoid unnecessary connection creation for PGVector store by @​musketyr in #​4422
• Allow to optionally add a description to lambda predicates in loop and conditional agentic workflows by @​mariofusco in #​4425
• docs: add complete RAG example to pgvector documentation by @​sumeetmehra-dev in #​4409
• Remove api key validation from Google AI Gemini by @​geoand in #​4429
• [BUG] 4250 - integration tests fix by @​partarstu in #​4389
• feat: add ChatMemory.set method by @​chirino in #​4416
• Allow describing lambda predicates in agentic declarative API by @​mariofusco in #​4433
• Add system message into metadata, revert #​4126 by @​YSZhuoyang in #​4431
• Support OpenSearch store removal and metadata filtering by @​musketyr in #​4430
• Invoke the agentic workflow SPI also when using the declarative API by @​mariofusco in #​4445
• Allows to define untyped agents dynamically without the need of an interface by @​mariofusco in #​4462
• Allows to use a StreamingChatModel for agents also through the declarative API by @​mariofusco in #​4472
• Update the MCP specification version to 2025-11-25 by @​jmartisk in #​4447
• Improve agent name resolution in supervisor by @​mariofusco in #​4494
• Add Supplier support for customHeaders in Voyage models by @​ghtjr410 in #​4427
• Support Gemini URL Context tool (Issue #​4475) by @​mohankumar27 in #​4478
• Add ModelCatalog support in watsonx.ai by @​andreadimaio in #​4477
• [BUG] Fixes 'NPE when retreiving Gemini Batch API job results #​4423' by @​Bram-- in #​4441
• Minor fix for automatic image type cast by @​mariofusco in #​4495
• Missing interrupt status handling in RetryUtils (issue #​4479) by @​isergeymd in #​4480
• MCP: listeners error handling by @​jmartisk in #​4507
• Allow to create LangChain4j contents from a path + agentic test for pdf ingestion by @​mariofusco in #​4497
• Make (some) Anthropic classes testable, add tests for DefaultAnthropicClient and add docs by @​Bram-- in #​4392
• Disable multimodal agents flaky tests by @​mariofusco in #​4504
• docs: clarify RAG as a tool with conditional retrieval by @​zzarbttoo in #​4404
• MCP: Replace raw Thread() with ExecutorService in StdioMcpTransport by @​farzad-sedaghatbin in #​4486
• feature(google-ai-gemini): add Google Maps Grounding tool support by @​mohankumar27 in #​4502
• Fix Cosmos Mongo vCore for MongoDB driver 5.x by @​SandraAhlgrimm in #​4510
• Exceptions during AiServiceEvents are eaten by @​edeandrea in #​4500
• Update Playwright version to 1.57.0 by @​vesense in #​4448
• Revert "MCP: Replace raw Thread() with ExecutorService in StdioMcpTransport" by @​dliubarskyi in #​4522
• Some more MCP client fixes by @​jmartisk in #​4523
• feat: add support for Google Search grounded image generation in Gemi… by @​glaforge in #​4512
• docs(mcp): add Java stdio server guide (community MCP server) by @​qicesun in #​4518
• feat(anthropic): add support for caching UserMessage by @​hetvi3012 in #​4487
• fix: Avoid exception in HierarchicalDocumentSplitter when estimating size of blank strings by @​jujn in #​4440
• feat: propagate isError from ToolExecutionResultMessage to Anthropic by @​farzad-sedaghatbin in #​4483
• [BUG] FileSystemDocumentLoaderExtensions.loadDocuments() does not skip failed documents by @​thswlsqls in #​4348
• fix: include enum values in List, Set, and array format instructions (#​4464) by @​abhishek9773 in #​4468
• Revert "[BUG] FileSystemDocumentLoaderExtensions.loadDocuments() does not skip failed documents" by @​dliubarskyi in #​4527
• Per-part media resolution in Gemini by @​partarstu in #​4457
• feat(bedrock): Add granular cache points support for system messages by @​karanb192 in #​4277
• 修复流式响应时，tool call id重复的问题 by @​chq562656437 in #​4530
• MistralAi: return raw HTTP response and SSE events by @​HostedDinner in #​4405
• Add Apache HttpClient5 implementation for HTTP client by @​techoc in #​4410
• 4432 - Added docs for Gemini Media Resolution by @​partarstu in #​4531
• fix: handle illegal URI characters in web search engines by @​hadalin in #​4532
• Migrate from Azure OpenAi to Microsoft Foundry by @​jdubois in #​4415

New Contributors

• @​mr-cloud made their first contribution in #​4304
• @​thswlsqls made their first contribution in #​4325
• @​xxsc0529 made their first contribution in #​4359
• @​partarstu made their first contribution in #​4337
• @​qicesun made their first contribution in #​4371
• @​ghtjr410 made their first contribution in #​4390
• @​nitinramvelraj made their first contribution in #​4374
• @​TylerBarkley made their first contribution in #​4376
• @​csbiy made their first contribution in #​4406
• @​ss-bhatt made their first contribution in #​4421
• @​musketyr made their first contribution in #​4422
• @​sumeetmehra-dev made their first contribution in #​4409
• @​chirino made their first contribution in #​4416
• @​mohankumar27 made their first contribution in #​4456
• @​isergeymd made their first contribution in #​4480
• @​l-trotta made their first contribution in #​4069
• @​zzarbttoo made their first contribution in #​4404
• @​farzad-sedaghatbin made their first contribution in #​4486
• @​hetvi3012 made their first contribution in #​4487
• @​abhishek9773 made their first contribution in #​4468
• @​karanb192 made their first contribution in #​4277
• @​chq562656437 made their first contribution in #​4530
• @​HostedDinner made their first contribution in #​4405
• @​techoc made their first contribution in #​4410
• @​hadalin made their first contribution in #​4532

Full Changelog: langchain4j/langchain4j@1.10.0...1.11.0

v1.10.0: and 1.10.0-beta18

Compare Source

Notable Changes

• Model Catalog support for Anthropic, Gemini, OpenAI and Mistral by @​haumacher in #​4240
• Agentic: Add observability and monitoring by @​mariofusco in #​4181
• Anthropic: support latest tool features by @​dliubarskyi in #​4211
• Anthropic: support structured outputs by @​diegoberriosr in #​4220
• Anthropic: return raw HTTP response and SSE events by @​dliubarskyi in #​4225
• OpenAI: add transcription support by @​anunnakian in #​4101
• AI Services: allow to pass ChatRequestParameters as method argument by @​mariofusco in #​4226

Other Changes

• docu: update versions to 1.9.1 and 1.9.1-beta17 by @​dliubarskyi in #​4151
• Update versions to 1.10.0-SNAPSHOT and 1.10.0-beta18-SNAPSHOT by @​dliubarskyi in #​4152
• Always make sure query transformer has access to system message in memory by @​YSZhuoyang in #​4126
• Allow to configure a default value for a key in the agentic scope by @​mariofusco in #​4153
• Fix supervisor usage as subagent by @​mariofusco in #​4161
• Jvector docs by @​odysseaspenta in #​4163
• Bump mdast-util-to-hast from 13.2.0 to 13.2.1 in /docs by @​dependabot[bot] in #​4164
• Bump express from 4.21.2 to 4.22.1 in /docs by @​dependabot[bot] in #​4168
• docs: add jlama vm options by @​vesense in #​4155
• Bump node-forge from 1.3.1 to 1.3.2 in /docs by @​dependabot[bot] in #​4141
• Update chat message types count in documentation by @​ratomidev in #​4138
• Add documentation for Local code execution engine by @​vesense in #​4159
• Test for MCP registry server parsing by @​jmartisk in #​4149
• Support tools definition via Map in agents by @​mariofusco in #​4169
• Whoops; Make GoogleAiGeminiBatchChatModel.builder() public. by @​Bram-- in #​4156
• Adding a new MessageModeratorInputGuardrail by @​agoncal in #​4160
• Updates to Infinispan 16.0.3 by @​karesti in #​4171
• fix(sql-filter-parser): handle Function expressions in WHERE clause #​3667 by @​Wanyi9988 in #​4170
• Migrate in-process embedding modules into main repo by @​dliubarskyi in #​4179
• Fill name support in PromptTemplate by @​angelozerr in #​4180
• Fix anthropic token count estimator empty messages by @​HamzaElzarw-2022 in #​3952
• fix(ai-service): append output format instructions to last TextContent #​3581 by @​Wanyi9988 in #​4184
• fix:NPE in SupervisorPlanner#result() when 'response' is missing(#​4196) by @​wangxuanni in #​4199
• fix: #​3091 change single parameter detection logic and add tests by @​raphidlee in #​4186
• Fix agentic conditional planner when no condition is matched by @​mariofusco in #​4202
• Update the Azure and OpenAI dependencies by @​jdubois in #​4203
• Issue #​4190 : [BUG] AwsDocumentConverter adds all parameters as required instead of using "required" list by @​ncilib-ssc in #​4214
• feat: add HttpClient customization hooks to MCP HTTP & WebSocket transports by @​LucasGois1 in #​4189
• Fix BatchSuccess mapping for Gemini BatchResponse by @​Bram-- in #​4175
• feat: Support PDF input via URL for Anthropic Claude API by @​adrianolaselva in #​4216
• feat: add Anthropic strictTools for tool definitions by @​wangxuanni in #​4223
• Fix supervisor test after agentIDs refactor by @​mariofusco in #​4231
• Add support for return behavior.immediate with dynamically tools by @​sabob in #​4224
• Fix use of default chat memory with agents by @​mariofusco in #​4234
• fix: NPE with explicit response formats in Ollama by @​dskarzh in #​4238
• refactor(ToolService, AiServiceStreamingResponseHandler): Add maxSequentialToolsInvocations handling by @​Ivan97 in #​4204
• Deprecate the langchain4j-github-models module by @​jdubois in #​4243
• fix: enhance PartsMapper to handle various tool result formats by @​karsta26 in #​4244
• Fix MCP client permanent disconnection after temporary network failure by @​dongfeng3692 in #​4249
• Anthropic server tool result returned to attributes by @​ejstuart in #​4245
• docs(ehancement): Add spacing to the feature lists by @​HamDean in #​4254
• Update watsonx-ai dependency to 0.16.0 by @​andreadimaio in #​4251
• Feature/hybrid retrieval by @​Ivan97 in #​4124
• AiServiceResponseReceivedEvent containing ChatRequest by @​stanlayze in #​4215
• Revisit AiServices.tools() validation by @​oscerd in #​4208
• Updates to Infinispan 16.0.5 by @​karesti in #​4259
• Allow to pass ChatRequestParameters to streaming AIServices by @​mariofusco in #​4264
• Bump org.apache.logging.log4j:log4j-core from 2.22.0 to 2.25.3 in /document-loaders/langchain4j-document-loader-github by @​dependabot[bot] in #​4260
• Todo task/added additional date functions in sql filter parser class by @​sumanth-reddy13 in #​4269
• Increasing system prompt size to be above 1K to get reliable results. by @​jonathannaguin in #​4270
• docs: springboot-integration add automatic Component ToolProvider by @​zzx1314 in #​3075
• Adds support of JsonRawSchema for Gemini API by @​ichristod in #​4150
• feat: including reasoning content by @​commandf1 in #​4200
• feat:Adjust chat memory storage for augmented user messages by @​YongGoose in #​4272
• Fix #​4278 by @​dliubarskyi in #​4281
• Fix 4282: Do not fail deserialization when new fields are added to the MCP responses by @​dliubarskyi in #​4283

New Contributors

• @​ratomidev made their first contribution in #​4138
• @​Wanyi9988 made their first contribution in #​4170
• @​angelozerr made their first contribution in #​4180
• @​wangxuanni made their first contribution in #​4199
• @​ncilib-ssc made their first contribution in #​4214
• @​LucasGois1 made their first contribution in #​4189
• @​adrianolaselva made their first contribution in #​4216
• @​sabob made their first contribution in #​4224
• @​dskarzh made their first contribution in #​4238
• @​Ivan97 made their first contribution in #​4204
• @​diegoberriosr made their first contribution in #​4220
• @​karsta26 made their first contribution in #​4244
• @​dongfeng3692 made their first contribution in #​4249
• @​ejstuart made their first contribution in #​4245
• @​HamDean made their first contribution in #​4254
• @​stanlayze made their first contribution in #​4215
• @​oscerd made their first contribution in #​4208
• @​sumanth-reddy13 made their first contribution in #​4269
• @​zzx1314 made their first contribution in #​3075
• @​ichristod made their first contribution in #​4150
• @​commandf1 made their first contribution in #​4200
• @​YongGoose made their first contribution in #​4272
• @​haumacher made their first contribution in #​4240

Full Changelog: langchain4j/langchain4j@1.9.1...1.10.0

v1.9.1: and 1.9.1-beta17

Compare Source

What's Changed

• docu: update versions to 1.9.0 and 1.9.0-beta16 by @​dliubarskyi in #​4139
• Update versions to 1.10.0-SNAPSHOT and 1.10.0-beta17-SNAPSHOT by @​dliubarskyi in #​4140
• added LangChain4j workshop to additional material - reviewed by @​dliubarskyi by @​roryp in #​4142
• Update gemini batch docs by @​Bram-- in #​4130
• Avoid NPE when an agent has no output by @​mariofusco in #​4145
• Disable GlobalTestRetryExtension by default and remove junit-platform.properties by @​dliubarskyi in #​4147

Full Changelog: langchain4j/langchain4j@1.9.0...1.9.1

v1.9.0: and 1.9.0-beta16

Compare Source

Notable Changes

• Agentic: Introduce a generic agentic planner and reimplement all agentic patterns through it by @​mariofusco in #​3929
• MCP: WebSocket transport support by @​jmartisk in #​4032
• Gemini: Batch API by @​Bram-- in #​3942
• Anthropic: support through Vertex AI #​3193 by @​pbykovcoginiti in #​3362

Other Changes

• docu: update versions to 1.8.0 and 1.8.0-beta15 by @​dliubarskyi in #​3950
• Update versions to 1.9.0-SNAPSHOT and 1.9.0-beta16-SNAPSHOT by @​dliubarskyi in #​3951
• Fix a typo in the OutputGuardrails annotation by @​edeandrea in #​3948
• Remove unnecessary MCP registry client creation during test by @​jmartisk in #​3963
• docs: add Agentic AI to intro by @​vesense in #​3966
• Fix typos in annotation and documentation by @​justinchoi929 in #​3997
• Generate consistent and reproducible unique names for agents by @​mariofusco in #​3965
• Reflect recent MCP registry updates by @​jmartisk in #​4016
• vertex-ai-gemini: Expose vertex apiEndpoint in builder by @​eiselems in #​4021
• Fix wrong method name in AgentBuilder by @​mariofusco in #​4033
• Update Quarkus documentation link for Easy RAG by @​wadajo in #​4034
• Update playwright version to 1.56.0 by @​vesense in #​4025
• Doc: Added SQLServer 2025 embedding store integration by @​odelpozo-denodo in #​3992
• Add WatsonxModerationModel and refactor LangChain4j integration by @​andreadimaio in #​3982
• MCP: Supply custom headers via a supplier method by @​maff in #​4036
• Flatten request response objects by @​Bram-- in #​3955
• Initializing the guardrails module by @​agoncal in #​3928
• Fix OpenAi token usage class cast exception by @​linnaung in #​3912
• Refactor ToolExecutionResult to support lazy evaluation of result tex… by @​hemanthsavasere in #​3960
• Fixes #​3968 by @​dliubarskyi in #​4026
• test: add edge case and error handling tests for ParsingUtil by @​alxkm in #​3959
• chore(deps): update dependency org.codehaus.mojo:flatten-maven-plugin to v1.7.2 by @​renovate[bot] in #​3433
• CompressingQueryTransformer NullPointException by @​zxyyang in #​1120
• Ignoring Claude Code CLI markdown file CLAUDE.md by @​agoncal in #​4041
• Updates to Latest Infinispan and Jackson Versions by @​karesti in #​4038
• Enable case-insensitive enum deserialization in structured output parsing by @​mariofusco in #​4049
• Propagate root exception when json parsing fails by @​mariofusco in #​4046
• feat: Enable reasoning effort control for GPT-5 (o1 series) by @​caio-carne1ro in #​4052
• Add GPT_5_1 to open ai enum. by @​Bram-- in #​4054
• GitHub Models: support structured output by @​hrhrng in #​1917
• Allow different types of object in the argument of the agent invocation generated by the supervisor by @​mariofusco in #​4053
• Update qdrant client by @​boris-petrov in #​4077
• Refactor value classes to (nested) records in google-ai-gemini by @​Bram-- in #​4070
• programmatic tools return behavior by @​Yoann-philippe in #​4064
• feat(memory): implement dynamic window sizing for chat memory by @​PaperFly-web in #​4058
• Make the supervisor aware of the argument types of its subagents by @​mariofusco in #​4079
• feat: add video content type support to OpenAI integration by @​ldaugusto in #​4078
• Get rid of @​Subagent annotation in declarative agentic API by @​mariofusco in #​4081
• #​4067 Add BedrockTokenUsage with cache token usage by @​blaZ3 in #​4080
• Implement tool hallucination handling for streaming by @​vesense in #​3773
• Gemini batch chat model delete and cancel by @​Bram-- in #​3945
• Bump A2A SDK to version 0.3.2.Final by @​mariofusco in #​4090
• Add Gemini among possible model providers in agentic tests by @​mariofusco in #​4091
• add: implementation of removeAll(Filter) for WeaviateEmbeddingStore by @​AminAK11 in #​3555
• fix badge style by @​vesense in #​4094
• Receive and expose MCP tool metadata by @​jmartisk in #​4089
• Update gemini docs by @​Bram-- in #​4082
• Expose agentic system as tree and check key types consistency by @​mariofusco in [#​4100](https://r

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.