Update langchain4j monorepo to v1

[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 → 1.18.0
dev.langchain4j:langchain4j (source)	0.32.0 → 1.18.0

---

Release Notes

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

v1.18.0: and 1.18.0-beta28

Compare Source

Notable Changes

• Introduce Belief-Desire-Intention (BDI) agentic pattern by @​mariofusco in #​5730
• Add crash-resilient Human-in-the-Loop suspension and resume for agentic systems by @​mariofusco in #​5767
• Add OpenAI Text-to-Speech (TTS) support by @​anunnakian in #​4697
• Add MistralAiBatchChatModel for the Mistral Batch API by @​subhashpolisetti in #​5750
• EmbeddingModel: request/response API with per-call parameters, multimodal inputs, and observability by @​dliubarskyi in #​5735

Other Changes

• feat(anthropic): add midConversationSystemMessages option for mid-conversation system messages by @​nickmaddren in #​5604
• fix: Throw typed exception for null-valued required skill tool argument by @​thswlsqls in #​5612
• fix: mask apiKey in OvhAiEmbeddingModel builder toString by @​thswlsqls in #​5608
• fix: Include $defs in Vertex AI Anthropic tool input schema for tools using schema references by @​thswlsqls in #​5615
• fix: Map Vertex AI Gemini content-policy finish reasons to CONTENT_FILTER by @​thswlsqls in #​5616
• feat(anthropic): typed Skills support for document generation (#​5530 Phase 1) by @​PSchmitz-Valckenberg in #​5605
• fix: Guard empty input and validate id/embedding sizes in VespaEmbeddingStore.addAll by @​thswlsqls in #​5632
• fix: Skip search results with unresolvable URIs in GoogleCustomWebSearchEngine by @​thswlsqls in #​5628
• fix: Remove leading space from DEEPSEEK_CODER_MATH_7B_AWQ model id by @​thswlsqls in #​5637
• fix: Override equals, hashCode and toString in WatsonxChatRequestParameters by @​thswlsqls in #​5636
• fix: Decode Voyage AI base64 embeddings as little-endian by @​thswlsqls in #​5638
• fix: honor root metadata mode in Weaviate removeAll(Filter) by @​thswlsqls in #​5631
• feat(gemini): support per-request imageConfig override in GoogleAiGeminiChatModel by @​ZhangDT-sky in #​4913
• fix: Wrap the full last expression when fixing single-line JavaScript in Judge0 by @​thswlsqls in #​5650
• fix: Preserve binary bytes in Azure dynamic sessions file download by @​thswlsqls in #​5652
• Workaround HHH-20500 for runtimes that haven't updated to the latest Hibernate ORM bug fixes yet by @​beikov in #​5655
• fix: Paginate ListObjectsV2 in AmazonS3DocumentLoader to load all objects by @​thswlsqls in #​5662
• feat: Add prefix overload to AzureBlobStorageDocumentLoader.loadDocuments by @​thswlsqls in #​5669
• Anthropic: add cache diagnostics (beta) support by @​joshiste in #​5659
• fix: Encode page content as UTF-8 in SeleniumDocumentLoader by @​thswlsqls in #​5671
• fix: Guard against null content type in GcsSource metadata by @​thswlsqls in #​5673
• feat(gemini): support per-request cachedContentName override by @​PSchmitz-Valckenberg in #​5645
• Propagate image detail level in OpenAI official chat completions by @​smf-h in #​5617
• docs: use clearly fictional example data in structured-outputs tutorial by @​jialiuyang in #​5620
• fix: advance the planner when an agent error handler returns a result by @​subhashpolisetti in #​5682
• feat(google-genai): support context cache creation and management by @​subhashpolisetti in #​5694
• fix: Include failing file URL in GitHubDocumentLoader load-failure exception message by @​thswlsqls in #​5684
• feat(google-genai): support per-request cachedContent override by @​glaforge in #​5676
• fix: Use UTF-8 when encoding Playwright page content for the document parser by @​thswlsqls in #​5686
• fix: Support all date functions when extracting metadata key in SqlFilterParser by @​thswlsqls in #​5699
• fix: mask apiKey in Cohere builder toString by @​lixuanqun in #​5691
• fix: guard against null function in streamed OpenAI tool-call deltas by @​farzad-sedaghatbin in #​5712
• fix: defensively copy input list in ChatMemory.set(...) before eviction by @​farzad-sedaghatbin in #​5714
• fix: align IsIn/IsNotIn numeric comparison with IsEqualTo/IsNotEqualTo by @​farzad-sedaghatbin in #​5717
• Improve visualization of execution history in agentic html report by @​mariofusco in #​5606
• Allow to use non-public and inherited methods as agentic methods by @​mariofusco in #​5704
• Allow to configure A2A transport by @​mariofusco in #​5678
• fix: ClassCastException when an MCP tool inputSchema contains anyOf alongside type "object" by @​subhashpolisetti in #​5726
• fix: avoid IllegalArgumentException in RetryPolicy jitter when bound is 0 by @​Ayomipo18 in #​5722
• fix: Anthropic honors cache_control on AiMessage and ToolExecutionResultMessage by @​joshiste in #​5729
• fix: Avoid StringIndexOutOfBoundsException when cleaning unclosed code fence in HibernateContentRetriever by @​thswlsqls in #​5732
• fix: Avoid StringIndexOutOfBoundsException when cleaning unclosed code fence in SqlDatabaseContentRetriever by @​PSchmitz-Valckenberg in #​5737
• Follow up on AgentsRegistry implementation by @​mariofusco in #​5719
• Allow a zero-args non-AI agent to also produce an output by @​mariofusco in #​5734
• fix: Paginate ListObjects in TencentCosDocumentLoader to load all obj… by @​chensishang in #​5709
• Surface async agent failures as AgentInvocationException by @​subhashpolisetti in #​5746
• feat(guardrails): add PromptInjectionGuardrail by @​ArvindAkula in #​5619
• fix: Skills: Declare shell tool timeout_seconds as integer and route bad values through typed exception by @​thswlsqls in #​5752
• fix: preserve precision of long/BigInteger/BigDecimal tool arguments by @​farzad-sedaghatbin in #​5755
• Fix race condition in AgentMonitor.onAgentInvocationError with parallel sub-agents by @​mariofusco in #​5759
• Allow to declaratively define beforeCall method on agentic patterns by @​mariofusco in #​5741
• Add jsonSchema() to Byte/Short/BigInteger/BigDecimal output parsers by @​angus-guo in #​5690
• Migrate Tavily and SearchApi web search engines from Retrofit/OkHttp to the HttpClient abstraction by @​dliubarskyi in #​5772
• Migrate Nomic, Jina, OVH AI, and Judge0 from Retrofit/OkHttp to the HttpClient abstraction by @​dliubarskyi in #​5773
• fix: preserve Ollama-specific parameters set via defaultRequestParameters by @​wushiyuanmaimob in #​5776
• Migrate Cohere, HuggingFace, and Workers AI from Retrofit/OkHttp to the HttpClient abstraction by @​dliubarskyi in #​5780
• fix: make enum tool-argument coercion locale-independent by @​wushiyuanmaimob in #​5778
• Allow to dinamically configure the A2A server URL by @​mariofusco in #​5766
• Fix error propagation and tracing in MonitoredExecution by @​mariofusco in #​5782
• Map provider errors to LangChain4j exceptions in Google GenAI, Vertex AI Gemini, Vertex AI Anthropic, Workers AI and Cohere by @​dliubarskyi in #​5785
• chore: upgrade google-genai dependency to 1.62.0 by @​glaforge in #​5748
• fix: pass builder skipCreateVectorExtension to PgVectorEmbeddingStore by @​subhashpolisetti in #​5788
• feat(google-genai): add generateContentConfigCustomizer to the chat models by @​subhashpolisetti in #​5646
• Updated Jackson to 2.22.1 by @​dliubarskyi in #​5793
• Apply output function also to supervisor result by @​mariofusco in #​5786

New Contributors

• @​nickmaddren made their first contribution in #​5604
• @​jialiuyang made their first contribution in #​5620
• @​lixuanqun made their first contribution in #​5691
• @​Ayomipo18 made their first contribution in #​5722
• @​chensishang made their first contribution in #​5709
• @​wushiyuanmaimob made their first contribution in #​5776

Full Changelog: langchain4j/langchain4j@1.17.2...1.18.0

v1.17.2: and 1.17.2-beta27

Compare Source

Full Changelog: langchain4j/langchain4j@1.17.1...1.17.2

v1.17.1: and 1.17.1-beta27

Compare Source

Workaround HHH-20500 for runtimes that haven't updated to the latest Hibernate ORM bug fixes yet by @​beikov

Full Changelog: langchain4j/langchain4j@1.17.0...1.17.1

v1.17.0: and 1.17.0-beta27

Compare Source

Notable Changes

• Introduce new Debate agentic pattern by @​mariofusco in #​5382
• Allow a tool to declare its compensating action and invoke it when it fails by @​mariofusco in #​5171
• Add Oracle Database for Chat Memory by @​psilberk in #​5351
• Expose unmapped raw streaming events by @​dliubarskyi in #​5589

Other Changes

• Migrate OpenAI image models from DALL-E to new GPT image API by @​edeandrea in #​5373
• Document non-Result IMMEDIATE behavior by @​patriot1burke in #​5372
• fix(elasticsearch): apply hybrid filters to full-text retriever by @​SJvaca30 in #​5387
• Update dependency io.netty:netty-codec-http2 to v4.1.135.Final [SECURITY] by @​renovate[bot] in #​5392
• Surface MCP icons in MCP client models by @​DragonFSKY in #​5381
• Fix filtering for non-TextSegment entries in InMemoryEmbeddingStore by @​Q1Xuan in #​5405
• Add an agent factory to the AgentConfigurator allowing to wire agents generated through the Quarkus extension by @​mariofusco in #​5397
• feat(agentic): generalise SupplierParameterResolver to all supplier types by @​mdproctor in #​5394
• Add support for IBM watsonx.ai deployed models by @​andreadimaio in #​5344
• chore: update google-genai dependency to 1.58.0 by @​glaforge in #​5420
• Allow to declaratively create an agentic system with a single A2A agent by @​mariofusco in #​5408
• Upgrade A2A to version 1.0.0.Final by @​mariofusco in #​5414
• Allow to use InvocationParameters with agents by @​mariofusco in #​5417
• Allow to optionally propagate the exception raised by a tool execution by @​mariofusco in #​5413
• docs: Remove broken PaLM 2 link from language models comparison table by @​thswlsqls in #​5432
• Expose MCP server instructions by @​fw-coder-tl in #​5425
• feat(agentic): support SupplierParameterResolver for @​ParallelExecutor by @​DragonFSKY in #​5437
• Fix: Log exceptions when tool execution fails by @​Q1Xuan in #​5427
• fix: infinite loop in OnnxBertBiEncoder.partition for oversized subword runs by @​thswlsqls in #​5454
• fix: Throw typed exception for null-valued required shell tool argument by @​thswlsqls in #​5456
• Fix broken Anthropic documentation links by @​angus-guo in #​5460
• Add tests demonstrating how guardrails work with agents by @​mariofusco in #​5450
• Allow to set user and system message providers declaratively on agents by @​mariofusco in #​5448
• chore(deps): bump dompurify from 3.4.0 to 3.4.10 in /docs by @​dependabot[bot] in #​5459
• fix: Validate bucket and key in TencentCosDocumentLoader.loadDocument by @​thswlsqls in #​5434
• fix: swapped account and container names in Azure Blob Storage document source URL by @​thswlsqls in #​5430
• fix: Decode Markdown as UTF-8 instead of the platform default charset by @​thswlsqls in #​5436
• docs: fix 'allows to' grammar in Guardrail Javadocs by @​aswego123 in #​5438
• docs: fix 'allow(s) to' grammar across docs and Javadocs by @​aswego123 in #​5439
• fix(tests): normalize JAR entry path separators for Windows compatibility by @​Demonese in #​5422
• docs: add Javadoc to VoyageAiEmbeddingModel and VoyageAiScoringModel … by @​vjayakumarvjk-art in #​5412
• docs: add Javadoc to Watsonx builder methods across all model classes by @​vjayakumarvjk-art in #​5415
• chore(deps): bump shell-quote from 1.8.3 to 1.8.4 in /docs by @​dependabot[bot] in #​5411
• chore(deps): bump launch-editor from 2.13.2 to 2.14.1 in /docs by @​dependabot[bot] in #​5461
• Fix Milvus L2 relevance score mapping by @​Q1Xuan in #​5428
• feat: implement image token estimation for HIGH/AUTO detail levels by @​RuleViz in #​5388
• docs: add Hazelcast embedding store and chat memory store integration by @​arodionov in #​5449
• fix: LoopAgent subAgents() Javadoc: sub-agents run in sequence, not in parallel by @​thswlsqls in #​5475
• fix: Coerce Number values to short and byte target types in agentic argument adaptation by @​thswlsqls in #​5469
• fix: declarative agentic Javadoc. replace removed @SubAgent with the array form by @​thswlsqls in #​5473
• chore(deps): bump ws in /docs by @​dependabot[bot] in #​5463
• fix: make Byte/Short/BigInteger/BigDecimal output parsers consistent with the other numeric parsers by @​subhashpolisetti in #​5465
• fix: omit blank/null Content-Type part header in JDK multipart body by @​Q1Xuan in #​5480
• fix: Omit blank/null Content-Type part header in Apache multipart body by @​thswlsqls in #​5467
• introduce AnthropicChatRequestParameters for per-call overrides (#​5301) by @​imyash2004 in #​5390
• Update OpenAI Java SDK to 4.41.0 by @​jdubois in #​5485
• chore(deps): bump webpack-dev-server from 5.2.3 to 5.2.5 in /docs by @​dependabot[bot] in #​5482
• chore: update google-genai dependency to 1.59.0 by @​glaforge in #​5488
• Update Dev Container support by @​jdubois in #​5489
• fix: Surface failed A2A tasks as exceptions instead of empty results by @​thswlsqls in #​5471
• fix: Throw MissingArgumentException for missing required input in McpClientAgentInvoker by @​thswlsqls in #​5477
• fix: unanimousLastWord convergence to normalize verdict token by @​thswlsqls in #​5479
• fix: Include $defs in Anthropic tool input schema for tools using schema references by @​thswlsqls in #​5499
• fix: prevent integer overflow in AwsDocumentConverter for long and BigInteger tool arguments by @​thswlsqls in #​5503
• fix: add langchain4j-document-parser-docling to BOM by @​thswlsqls in #​5505
• fix: wmv MIME type mapping key in CustomMimeTypesFileTypeDetector by @​thswlsqls in #​5511
• fix: Make ElasticsearchContentRetriever minScore boundary inclusive by @​thswlsqls in #​5513
• Preserve response whitespace when parsing GPULlama3 thinking content by @​thswlsqls in #​5517
• Render Gemini executable code as a valid Markdown fenced block by @​thswlsqls in #​5520
• Report total token count from Google GenAI usage metadata by @​thswlsqls in #​5519
• fix: Escape SQL LIKE single-character wildcard in Hibernate metadata contains filter by @​thswlsqls in #​5522
• fix: Ensure custom HuggingFace base URL ends with a trailing slash by @​thswlsqls in #​5534
• fix: Map model download exceptions for all Jlama models by @​thswlsqls in #​5536
• fix: mask apiKey in JinaScoringModel and JinaClient builder toString by @​thswlsqls in #​5539
• Forward enableEnhancedCivicAnswers to the Gemini generation config by @​subhashpolisetti in #​5547
• Fix NPE in OpenAiOfficialChatModel/StreamingChatModel with user-supplied OpenAIClient by @​PSchmitz-Valckenberg in #​5548
• OpenAiImageModel: implement edits by @​dliubarskyi in #​5549
• docs: add Javadoc to AgentBuilder methods by @​vjayakumarvjk-art in #​5543
• Update Azure SDK BOM to 1.3.7 and migrate to azure-search-documents 12.0.0 by @​jdubois in #​5486
• fix: run tool loop before re-validating output guardrails on reprompt by @​PSchmitz-Valckenberg in #​5082
• fix: Map ContainsString filter to regex in MongoDB Atlas metadata filter mapper by @​thswlsqls in #​5553
• fix: Add space separator in chat model observation span contextual name by @​thswlsqls in #​5557
• fix: mask apiKey in NomicEmbeddingModel builder toString by @​thswlsqls in #​5559
• fix: Populate logProbs in OpenAI streaming response metadata by @​thswlsqls in #​5561
• fix: Preserve BigInteger values when converting MCP structured content by @​thswlsqls in #​5572
• fix: skip recording token usage metric when token count is null by @​thswlsqls in #​5574
• fix: Add dockerTlsVerify builder method and deprecate misspelled dockerTslVerify by @​thswlsqls in #​5575
• fix: Escape backslashes in Milvus metadata filter values by @​thswlsqls in #​5577
• fix: Parse Ollama timestamps with variable-length fractional seconds by @​thswlsqls in #​5579
• fix: Guard against null content in Mistral FIM streaming event listener by @​thswlsqls in #​5581
• fix: Honor strictJsonSchema option in MistralAiStreamingChatModel by @​thswlsqls in #​5583
• Add Oracle chat memory store integration link by @​psilberk in #​5555
• Allow to programmatically set the A2AService implementation by @​mariofusco in #​5567
• fix: Escape double quotes and backslashes in Cosmos DB NoSQL filter values by @​thswlsqls in #​5501
• test: add unit tests for Google AI Gemini FinishReasonMapper by @​gaoxiaolei-s59 in #​5492
• http-client-jdk: set Content-Type for multipart/form-data requests by @​mohit-twelvelabs in #​5566
• fix: Generate native IN clause for single-type IN/NOT IN filters in Oracle store by @​thswlsqls in #​5563
• chore(deps): bump dompurify from 3.4.10 to 3.4.11 in /docs by @​dependabot[bot] in #​5490
• docs: add Javadoc to GoogleGenAiChatModel and GoogleGenAiStreamingCha… by @​vjayakumarvjk-art in #​5374
• test: add HTTP response verification for Ollama thinking mode by @​RuleViz in #​5389
• feat(bedrock): add enableAdaptiveReasoning for Claude Opus 4.7+ by @​Aditya-Pimpalkar in #​5358
• fix(anthropic): gracefully skip [DONE] and unknown SSE frames (GH-5384) by @​anuragg-saxenaa in #​5398
• fix(anthropic): support replaying malformed JSON in tool_use arguments by @​Baqirrizvidev in #​5335
• fix(gemini): add IMAGE_RECITATION to GeminiFinishReason enum by @​Pahkho in #​5256
• fix: throw on unsupported Azure OpenAI service version instead of silently falling back by @​PSchmitz-Valckenberg in #​5260
• fix(qdrant): use Query RPC instead of legacy Search RPC to retrieve vectors by @​sam-hey in #​5314
• Onnxruntime.dll: Dynamic Link Library (DLL) initialization routine failed by @​moaedy in #​5242
• fix(vespa): rethrow exception in VespaEmbeddingStoreIT#deployVespaApp by @​serelli in #​5266
• fix(gpullama3): replace System.err.println with SLF4J logger by @​serelli in #​5265
• fix(deps): update hibernate-orm monorepo to v7.4.2.final - autoclosed by @​renovate[bot] in #​5254
• (docs) Support to SQLServer's half-precision float support in vector data type by @​odelpozo-denodo in #​5418
• fix: Escape single quotes in Infinispan metadata filter Ickle queries by @​thswlsqls in #​5540
• Bound to an upper limit the number of entries retained by the AgentMonitor by @​mariofusco in #​5587
• fix: Set required input_audio format from audio mime type in OpenAI official chat model by @​thswlsqls in #​5591
• chore(deps): update actions/checkout digest to df4cb1c by @​renovate[bot] in #​5586
• Escape LIKE wildcards in Milvus containsString filter (match #​5522/#​5553) by @​greymoth-jp in #​5600
• fix: Validate ids/embeddings/textSegments size in PineconeEmbeddingStore.addAll by @​thswlsqls in #​5593
• fix: match ContainsString as a literal substring in PgVector filter by @​thswlsqls in #​5595
• fix: support Float and Double values in Qdrant equality metadata filters by @​thswlsqls in #​5598
• Support input_image format for OpenAI-compatible images by @​smf-h in #​5564
• Allow specifying only a subset of MCP clients considered in the tool provider by @​jmartisk in #​5602

New Contributors

• @​SJvaca30 made their first contribution in #​5387
• @​Q1Xuan made their first contribution in #​5405
• @​mdproctor made their first contribution in #​5394
• @​fw-coder-tl made their first contribution in #​5425
• @​angus-guo made their first contribution in #​5460
• @​aswego123 made their first contribution in #​5438
• @​Demonese made their first contribution in #​5422
• @​RuleViz made their first contribution in #​5388
• @​arodionov made their first contribution in #​5449
• @​subhashpolisetti made their first contribution in #​5465
• @​imyash2004 made their first contribution in #​5390
• @​gaoxiaolei-s59 made their first contribution in #​5492
• @​mohit-twelvelabs made their first contribution in #​5566
• @​Aditya-Pimpalkar made their first contribution in #​5358
• @​anuragg-saxenaa made their first contribution in #​5398
• @​Baqirrizvidev made their first contribution in #​5335
• @​Pahkho made their first contribution in #​5256
• @​sam-hey made their first contribution in #​5314
• @​moaedy made their first contribution in #​5242
• @​serelli made their first contribution in #​5266
• @​greymoth-jp made their first contribution in #​5600
• @​smf-h made their first contribution in #​5564

Full Changelog: langchain4j/langchain4j@1.16.3...1.17.0

v1.16.3: and 1.16.3-beta26

Compare Source

• Fix SQL injection via metadata filters in langchain4j-mariadb and langchain4j-pgvector

Full Changelog: langchain4j/langchain4j@1.16.2...1.16.3

v1.16.2: and 1.16.2-beta26

Compare Source

Full Changelog: langchain4j/langchain4j@1.16.1...1.16.2

v1.16.1: and 1.16.1-beta26

Compare Source

• Migrate OpenAI image models from DALL-E to new GPT image API in #​5373 by @​edeandrea

Full Changelog: langchain4j/langchain4j@1.16.0...1.16.1

v1.16.0: and 1.16.0-beta26

Compare Source

Notable Changes

• Allow @​Tool methods to also be inherited from superclasses and interfaces by @​mariofusco in #​5328
• Introduce Blackboard agentic pattern by @​mariofusco in #​5243
• Unify Batch API Response Model by @​Bram-- in #​4529
• feat(google-genai): introduce batch processing, grounding metadata, and image labels by @​glaforge in #​5255
• support non Result return type for IMMEDIATE by @​patriot1burke in #​5367

Breaking Changes

• Allow @​Tool methods to also be inherited from superclasses and interfaces by @​mariofusco in #​5328
• Unify Batch API Response Model by @​Bram-- in #​4529

Other Changes

• Introduce a new AgentConfigurator allowing to define an external function for agents retrieval or creation by @​mariofusco in #​5269
• fix: eliminate race condition in ChatMemoryService.getOrCreateChatMemory by @​PSchmitz-Valckenberg in #​5253
• Fix empty ReturnBehavior list crash and add ReturnBehavior to ToolSpecification by @​pedrovieira in #​5279
• Allow custom resolution of agentic parameters suppliers by @​geoand in #​5286
• MCP: surface tool outputSchema on ToolSpecification by @​farzad-sedaghatbin in #​5293
• Filter away non serializable state from DefaultAgenticScope when serializing it by @​mariofusco in #​5290
• Revert "Fix empty ReturnBehavior list crash and add ReturnBehavior to ToolSpecification" by @​dliubarskyi in #​5318
• Fix #​5277: ToolService.shouldReturnImmediately() crashes on empty ReturnBehavior list by @​dliubarskyi in #​5319
• fix: make AgentMonitor thread-safe under concurrent invocations by @​PSchmitz-Valckenberg in #​5297
• fix(agentic): avoid duplicate declarative tool providers by @​DragonFSKY in #​5315
• docs: Add CockroachDB embedding store integration page by @​amineelkouhen in #​5262
• Upgrade pdfbox to version 3.0.7 by @​mariofusco in #​5276
• Skills: add DefaultFileSystemSkill.toBuilder() and round-trip tools correctly via builder by @​gaurav0107 in #​5272
• ChatRequest: allow individual setters to override parameters by @​dliubarskyi in #​5325
• Add guardrailName() to GuardrailExecutedEvent for observability by @​nhthinh-axonivy in #​4940
• feat: allow OutputGuardrail failures to remove violating AiMessage from memory by @​PSchmitz-Valckenberg in #​5155
• fix: drain responseBuffer to BiConsumer handler when OutputGuardrails are active by @​PSchmitz-Valckenberg in #​5252
• fix: preserve Google AI Gemini tool call ids by @​DragonFSKY in #​5308
• Fix counting of max interation in agentic loop pattern by @​mariofusco in #​5323
• MCP: handle inbound notifications/cancelled from server by @​farzad-sedaghatbin in #​5294
• chore: remove unused imports across multiple modules by @​EvanYao826 in #​5338
• fix: add null check for chatResponse.usage() in Watsonx models by @​EvanYao826 in #​5337
• docs: add Javadoc to AnthropicTokenCountEstimator and AnthropicModelC… by @​vjayakumarvjk-art in #​5334
• Document Tuning Engines OpenAI-compatible endpoint by @​cerebrixos in #​5333
• lock m-jar-p plugin version by @​hboutemy in #​5332
• Docs/anthropic builder javadoc by @​vjayakumarvjk-art in #​5331
• docs: add Javadoc to exception hierarchy in langchain4j-core by @​ArvindAkula in #​5322
• Bump langchain4j-agentic-a2a to A2A ver

✂ Note

PR body was truncated to here.

---

Configuration

📅 Schedule: (UTC)

• 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.