Update langchain4j monorepo to v1.18.0

[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
dev.langchain4j:langchain4j-ollama (source)	1.17.2 → 1.18.0
dev.langchain4j:langchain4j-open-ai (source)	1.17.2 → 1.18.0
dev.langchain4j:langchain4j (source)	1.17.2 → 1.18.0

---

Release Notes

langchain4j/langchain4j (dev.langchain4j:langchain4j-ollama)

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

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

v1.18.0

Compare Source

langchain4j/langchain4j (dev.langchain4j:langchain4j)

v1.18.0

Compare Source

---

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.