dependabot[bot] opened a new pull request, #28837: URL: https://github.com/apache/camel/pull/28837
Bumps the langchain4j group with 17 updates: | Package | From | To | | --- | --- | --- | | [dev.langchain4j:langchain4j-core](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j-open-ai](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j-google-ai-gemini](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j-ollama](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j-azure-open-ai](https://github.com/langchain4j/langchain4j) | `1.22.0` | `1.23.0` | | [dev.langchain4j:langchain4j-mcp](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-guardrails](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-embeddings-bge-small-en-v15-q](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-hugging-face](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-embeddings](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-embeddings-all-minilm-l6-v2](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-qdrant](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-milvus](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-weaviate](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-web-search-engine-tavily](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | | [dev.langchain4j:langchain4j-web-search-engine-google-custom](https://github.com/langchain4j/langchain4j) | `1.22.0-beta32` | `1.23.0-beta33` | Updates `dev.langchain4j:langchain4j-core` from 1.22.0 to 1.23.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain4j/langchain4j/releases";>dev.langchain4j:langchain4j-core's releases</a>.</em></p> <blockquote> <h2>1.23.0 and 1.23.0-beta33</h2> <h2>Notable Changes</h2> <ul> <li>Add OllamaDecisionModel: Ollama decision models, including images by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6659";>langchain4j/langchain4j#6659</a></li> <li>Introduce Confidence Cascade agentic pattern by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6765";>langchain4j/langchain4j#6765</a></li> <li>Observability: AiServiceInvocationSummaryEvent with all events of one AI Service invocation by <a href="https://github.com/rayanahmed1215";><code>@rayanahmed1215</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5048";>langchain4j/langchain4j#5048</a></li> <li>langchain4j-test: LLM judges and assertions on chat requests by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6819";>langchain4j/langchain4j#6819</a></li> <li>Introduce decision agents by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6820";>langchain4j/langchain4j#6820</a></li> </ul> <h2>Other Changes</h2> <ul> <li>chore(deps): bump shell-quote from 1.10.0 to 1.12.0 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6602";>langchain4j/langchain4j#6602</a></li> <li>Propagate the caller's context to work offloaded by AI Services by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6623";>langchain4j/langchain4j#6623</a></li> <li>Docs: non-blocking calls with the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6621";>langchain4j/langchain4j#6621</a></li> <li>chore(deps): bump proxy-addr from 2.0.7 to 2.0.8 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6591";>langchain4j/langchain4j#6591</a></li> <li>docs: Extend MCP server guide with Streamable HTTP server options by <a href="https://github.com/kpavlov";><code>@kpavlov</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6622";>langchain4j/langchain4j#6622</a></li> <li>feat(micrometer-metrics): record chat operation duration by <a href="https://github.com/Snow7-G";><code>@Snow7-G</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6472";>langchain4j/langchain4j#6472</a></li> <li>Keep the conversation for output guardrail retries without chat memory by <a href="https://github.com/edeandrea";><code>@edeandrea</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6627";>langchain4j/langchain4j#6627</a></li> <li>Add Azure DocumentDB embedding store, deprecate Azure Cosmos DB Mongo vCore by <a href="https://github.com/SandraAhlgrimm";><code>@SandraAhlgrimm</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/4426";>langchain4j/langchain4j#4426</a></li> <li>Azure DocumentDB docs: Spring Boot starter behaviour, migration defaults and client settings by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6635";>langchain4j/langchain4j#6635</a></li> <li>TypeSafe: make the System One API path configurable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6653";>langchain4j/langchain4j#6653</a></li> <li>JdkHttpClient: use HTTP/1.1 for plain http:// URLs by default by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6660";>langchain4j/langchain4j#6660</a></li> <li>Docs: HTTP version of SpringRestClient with the JDK client by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6668";>langchain4j/langchain4j#6668</a></li> <li>fix(guardrails): keep clean JSON a plain success in JsonExtractorOutputGuardrail by <a href="https://github.com/fengyue-xve";><code>@fengyue-xve</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6600";>langchain4j/langchain4j#6600</a></li> <li>chore(google-genai): update Google GenAI SDK to 1.77.0 and expose new SDK features by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6680";>langchain4j/langchain4j#6680</a></li> <li>feat(google-genai): support raw/recursive JSON schemas, multimodal tool results, async chat, and streaming cancellation by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6681";>langchain4j/langchain4j#6681</a></li> <li>test(google-genai): migrate tests from gemini-2.5-flash to gemini-3.8-flash by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6682";>langchain4j/langchain4j#6682</a></li> <li>Use MeterProvider for performance reasons by <a href="https://github.com/brunobat";><code>@brunobat</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6704";>langchain4j/langchain4j#6704</a></li> <li>fix(agentic): make HTML report formatting locale-independent by <a href="https://github.com/Mihir-Rabari";><code>@Mihir-Rabari</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6632";>langchain4j/langchain4j#6632</a></li> <li>OpenAI decision models: support images referenced by URL by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6715";>langchain4j/langchain4j#6715</a></li> <li>Streaming cancellation: no callbacks after cancel(), make StreamingHandle discoverable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6717";>langchain4j/langchain4j#6717</a></li> <li>feat(decision-models): custom body parameters for all decision models by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6718";>langchain4j/langchain4j#6718</a></li> <li>Fix ITs hanging/flaking on slow providers; expose provider errors returned with HTTP 200 by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6716";>langchain4j/langchain4j#6716</a></li> <li>Allow TokenStream to process complete responses on a custom executor by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6724";>langchain4j/langchain4j#6724</a></li> <li>OpenAiStreamingChatModel: fail on provider errors sent inside the stream by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6722";>langchain4j/langchain4j#6722</a></li> <li>Docs: fix ClassPathSkillLoader snippet types and custom patterns count by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6729";>langchain4j/langchain4j#6729</a></li> <li>Require exactly one subagent for ParallelMapperService by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6662";>langchain4j/langchain4j#6662</a></li> <li>fix(agentic): count every tool-loop model call in agent token usage by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6691";>langchain4j/langchain4j#6691</a></li> <li>Fixes <a href="https://redirect.github.com/langchain4j/langchain4j/issues/6665";>#6665</a> Untyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentExceptionUntyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentException by <a href="https://github.com/kamisheng";><code>@kamisheng</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6666";>langchain4j/langchain4j#6666</a></li> <li>Allow to generate the agentic context summarization also using a StreamingChatModel by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6721";>langchain4j/langchain4j#6721</a></li> <li>feat(bedrock): add guardContent placement support by <a href="https://github.com/DragonFSKY";><code>@DragonFSKY</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5030";>langchain4j/langchain4j#5030</a></li> <li>feat(google-genai): support code execution in the chat models by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6709";>langchain4j/langchain4j#6709</a></li> <li>Docs: Spring Boot's HTTP client settings in the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6740";>langchain4j/langchain4j#6740</a></li> <li>fix(agentic): always release the response an agent keeps per scope by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6693";>langchain4j/langchain4j#6693</a></li> <li>Fix the NullPointerException when an optional agent has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6697";>langchain4j/langchain4j#6697</a></li> <li>Stop supervisor planning while a SuspendedResponse is pending by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6636";>langchain4j/langchain4j#6636</a></li> <li>Decision models: conversation input for OpenAI and a typed DecisionInput by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6739";>langchain4j/langchain4j#6739</a></li> <li>Decision models: conversations for all providers, and conversation context for routers, tool filtering and output guardrails by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6741";>langchain4j/langchain4j#6741</a></li> <li>feat(google-genai): add GoogleGenAiTextToSpeechModel for Gemini text-to-speech by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6674";>langchain4j/langchain4j#6674</a></li> <li>Allow any agent or agentic pattern to declare an activation condition by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6731";>langchain4j/langchain4j#6731</a></li> <li>Fail fast when a BlackboardPlanner or GoalOrientedPlanner has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6720";>langchain4j/langchain4j#6720</a></li> <li>Add model name to generated agentic execution html report by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6761";>langchain4j/langchain4j#6761</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain4j/langchain4j/commit/32561faea052031811a9a6d8a21c5844ab44d1ef";><code>32561fa</code></a> Release versions 1.23.0 and 1.23.0-beta33</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/8f6e2210f1a9f8ad92a53e6211861d2b0fbd2802";><code>8f6e221</code></a> Validate the types of metadata filter comparison values (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6896";>#6896</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/055468af94754c981958bbadad45eb282d86efce";><code>055468a</code></a> Bind metadata filter values as parameters (pgvector, MariaDB) and map them st...</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ae86799436eb2759baf3bf5901376367a5ffdcbd";><code>ae86799</code></a> Update dependency com.google.guava:guava to v33 [SECURITY] (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6877";>#6877</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ab1dacc5dc573b71c60d53c57ee769bd8878eb5f";><code>ab1dacc</code></a> Docs: explain the Windows msvcp140.dll requirement of ONNX Runtime</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/61edab58958bfc5677debf18e07c7222986b7ce0";><code>61edab5</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6871";>#6871</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/215b41fdf9718a9ea87d563176cf53936ce2a543";><code>215b41f</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6870";>#6870</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/aa372e5f0d45aea1fb6660fada8c655487fb6205";><code>aa372e5</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6863";>#6863</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/afe99bac61f4e4d360c4a4a90763d45c0bb5802a";><code>afe99ba</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6864";>#6864</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/e80b454017775c2596a60d8530dc3bc1a047e57b";><code>e80b454</code></a> Also skip Vespa integration test when the flag -DskipITs is used (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6879";>#6879</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain4j/langchain4j/compare/1.22.0...1.23.0";>compare view</a></li> </ul> </details> <br /> Updates `dev.langchain4j:langchain4j` from 1.22.0 to 1.23.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain4j/langchain4j/releases";>dev.langchain4j:langchain4j's releases</a>.</em></p> <blockquote> <h2>1.23.0 and 1.23.0-beta33</h2> <h2>Notable Changes</h2> <ul> <li>Add OllamaDecisionModel: Ollama decision models, including images by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6659";>langchain4j/langchain4j#6659</a></li> <li>Introduce Confidence Cascade agentic pattern by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6765";>langchain4j/langchain4j#6765</a></li> <li>Observability: AiServiceInvocationSummaryEvent with all events of one AI Service invocation by <a href="https://github.com/rayanahmed1215";><code>@rayanahmed1215</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5048";>langchain4j/langchain4j#5048</a></li> <li>langchain4j-test: LLM judges and assertions on chat requests by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6819";>langchain4j/langchain4j#6819</a></li> <li>Introduce decision agents by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6820";>langchain4j/langchain4j#6820</a></li> </ul> <h2>Other Changes</h2> <ul> <li>chore(deps): bump shell-quote from 1.10.0 to 1.12.0 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6602";>langchain4j/langchain4j#6602</a></li> <li>Propagate the caller's context to work offloaded by AI Services by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6623";>langchain4j/langchain4j#6623</a></li> <li>Docs: non-blocking calls with the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6621";>langchain4j/langchain4j#6621</a></li> <li>chore(deps): bump proxy-addr from 2.0.7 to 2.0.8 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6591";>langchain4j/langchain4j#6591</a></li> <li>docs: Extend MCP server guide with Streamable HTTP server options by <a href="https://github.com/kpavlov";><code>@kpavlov</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6622";>langchain4j/langchain4j#6622</a></li> <li>feat(micrometer-metrics): record chat operation duration by <a href="https://github.com/Snow7-G";><code>@Snow7-G</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6472";>langchain4j/langchain4j#6472</a></li> <li>Keep the conversation for output guardrail retries without chat memory by <a href="https://github.com/edeandrea";><code>@edeandrea</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6627";>langchain4j/langchain4j#6627</a></li> <li>Add Azure DocumentDB embedding store, deprecate Azure Cosmos DB Mongo vCore by <a href="https://github.com/SandraAhlgrimm";><code>@SandraAhlgrimm</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/4426";>langchain4j/langchain4j#4426</a></li> <li>Azure DocumentDB docs: Spring Boot starter behaviour, migration defaults and client settings by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6635";>langchain4j/langchain4j#6635</a></li> <li>TypeSafe: make the System One API path configurable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6653";>langchain4j/langchain4j#6653</a></li> <li>JdkHttpClient: use HTTP/1.1 for plain http:// URLs by default by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6660";>langchain4j/langchain4j#6660</a></li> <li>Docs: HTTP version of SpringRestClient with the JDK client by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6668";>langchain4j/langchain4j#6668</a></li> <li>fix(guardrails): keep clean JSON a plain success in JsonExtractorOutputGuardrail by <a href="https://github.com/fengyue-xve";><code>@fengyue-xve</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6600";>langchain4j/langchain4j#6600</a></li> <li>chore(google-genai): update Google GenAI SDK to 1.77.0 and expose new SDK features by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6680";>langchain4j/langchain4j#6680</a></li> <li>feat(google-genai): support raw/recursive JSON schemas, multimodal tool results, async chat, and streaming cancellation by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6681";>langchain4j/langchain4j#6681</a></li> <li>test(google-genai): migrate tests from gemini-2.5-flash to gemini-3.8-flash by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6682";>langchain4j/langchain4j#6682</a></li> <li>Use MeterProvider for performance reasons by <a href="https://github.com/brunobat";><code>@brunobat</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6704";>langchain4j/langchain4j#6704</a></li> <li>fix(agentic): make HTML report formatting locale-independent by <a href="https://github.com/Mihir-Rabari";><code>@Mihir-Rabari</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6632";>langchain4j/langchain4j#6632</a></li> <li>OpenAI decision models: support images referenced by URL by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6715";>langchain4j/langchain4j#6715</a></li> <li>Streaming cancellation: no callbacks after cancel(), make StreamingHandle discoverable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6717";>langchain4j/langchain4j#6717</a></li> <li>feat(decision-models): custom body parameters for all decision models by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6718";>langchain4j/langchain4j#6718</a></li> <li>Fix ITs hanging/flaking on slow providers; expose provider errors returned with HTTP 200 by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6716";>langchain4j/langchain4j#6716</a></li> <li>Allow TokenStream to process complete responses on a custom executor by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6724";>langchain4j/langchain4j#6724</a></li> <li>OpenAiStreamingChatModel: fail on provider errors sent inside the stream by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6722";>langchain4j/langchain4j#6722</a></li> <li>Docs: fix ClassPathSkillLoader snippet types and custom patterns count by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6729";>langchain4j/langchain4j#6729</a></li> <li>Require exactly one subagent for ParallelMapperService by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6662";>langchain4j/langchain4j#6662</a></li> <li>fix(agentic): count every tool-loop model call in agent token usage by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6691";>langchain4j/langchain4j#6691</a></li> <li>Fixes <a href="https://redirect.github.com/langchain4j/langchain4j/issues/6665";>#6665</a> Untyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentExceptionUntyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentException by <a href="https://github.com/kamisheng";><code>@kamisheng</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6666";>langchain4j/langchain4j#6666</a></li> <li>Allow to generate the agentic context summarization also using a StreamingChatModel by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6721";>langchain4j/langchain4j#6721</a></li> <li>feat(bedrock): add guardContent placement support by <a href="https://github.com/DragonFSKY";><code>@DragonFSKY</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5030";>langchain4j/langchain4j#5030</a></li> <li>feat(google-genai): support code execution in the chat models by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6709";>langchain4j/langchain4j#6709</a></li> <li>Docs: Spring Boot's HTTP client settings in the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6740";>langchain4j/langchain4j#6740</a></li> <li>fix(agentic): always release the response an agent keeps per scope by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6693";>langchain4j/langchain4j#6693</a></li> <li>Fix the NullPointerException when an optional agent has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6697";>langchain4j/langchain4j#6697</a></li> <li>Stop supervisor planning while a SuspendedResponse is pending by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6636";>langchain4j/langchain4j#6636</a></li> <li>Decision models: conversation input for OpenAI and a typed DecisionInput by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6739";>langchain4j/langchain4j#6739</a></li> <li>Decision models: conversations for all providers, and conversation context for routers, tool filtering and output guardrails by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6741";>langchain4j/langchain4j#6741</a></li> <li>feat(google-genai): add GoogleGenAiTextToSpeechModel for Gemini text-to-speech by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6674";>langchain4j/langchain4j#6674</a></li> <li>Allow any agent or agentic pattern to declare an activation condition by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6731";>langchain4j/langchain4j#6731</a></li> <li>Fail fast when a BlackboardPlanner or GoalOrientedPlanner has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6720";>langchain4j/langchain4j#6720</a></li> <li>Add model name to generated agentic execution html report by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6761";>langchain4j/langchain4j#6761</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain4j/langchain4j/commit/32561faea052031811a9a6d8a21c5844ab44d1ef";><code>32561fa</code></a> Release versions 1.23.0 and 1.23.0-beta33</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/8f6e2210f1a9f8ad92a53e6211861d2b0fbd2802";><code>8f6e221</code></a> Validate the types of metadata filter comparison values (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6896";>#6896</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/055468af94754c981958bbadad45eb282d86efce";><code>055468a</code></a> Bind metadata filter values as parameters (pgvector, MariaDB) and map them st...</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ae86799436eb2759baf3bf5901376367a5ffdcbd";><code>ae86799</code></a> Update dependency com.google.guava:guava to v33 [SECURITY] (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6877";>#6877</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ab1dacc5dc573b71c60d53c57ee769bd8878eb5f";><code>ab1dacc</code></a> Docs: explain the Windows msvcp140.dll requirement of ONNX Runtime</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/61edab58958bfc5677debf18e07c7222986b7ce0";><code>61edab5</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6871";>#6871</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/215b41fdf9718a9ea87d563176cf53936ce2a543";><code>215b41f</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6870";>#6870</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/aa372e5f0d45aea1fb6660fada8c655487fb6205";><code>aa372e5</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6863";>#6863</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/afe99bac61f4e4d360c4a4a90763d45c0bb5802a";><code>afe99ba</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6864";>#6864</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/e80b454017775c2596a60d8530dc3bc1a047e57b";><code>e80b454</code></a> Also skip Vespa integration test when the flag -DskipITs is used (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6879";>#6879</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain4j/langchain4j/compare/1.22.0...1.23.0";>compare view</a></li> </ul> </details> <br /> Updates `dev.langchain4j:langchain4j-open-ai` from 1.22.0 to 1.23.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain4j/langchain4j/releases";>dev.langchain4j:langchain4j-open-ai's releases</a>.</em></p> <blockquote> <h2>1.23.0 and 1.23.0-beta33</h2> <h2>Notable Changes</h2> <ul> <li>Add OllamaDecisionModel: Ollama decision models, including images by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6659";>langchain4j/langchain4j#6659</a></li> <li>Introduce Confidence Cascade agentic pattern by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6765";>langchain4j/langchain4j#6765</a></li> <li>Observability: AiServiceInvocationSummaryEvent with all events of one AI Service invocation by <a href="https://github.com/rayanahmed1215";><code>@rayanahmed1215</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5048";>langchain4j/langchain4j#5048</a></li> <li>langchain4j-test: LLM judges and assertions on chat requests by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6819";>langchain4j/langchain4j#6819</a></li> <li>Introduce decision agents by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6820";>langchain4j/langchain4j#6820</a></li> </ul> <h2>Other Changes</h2> <ul> <li>chore(deps): bump shell-quote from 1.10.0 to 1.12.0 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6602";>langchain4j/langchain4j#6602</a></li> <li>Propagate the caller's context to work offloaded by AI Services by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6623";>langchain4j/langchain4j#6623</a></li> <li>Docs: non-blocking calls with the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6621";>langchain4j/langchain4j#6621</a></li> <li>chore(deps): bump proxy-addr from 2.0.7 to 2.0.8 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6591";>langchain4j/langchain4j#6591</a></li> <li>docs: Extend MCP server guide with Streamable HTTP server options by <a href="https://github.com/kpavlov";><code>@kpavlov</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6622";>langchain4j/langchain4j#6622</a></li> <li>feat(micrometer-metrics): record chat operation duration by <a href="https://github.com/Snow7-G";><code>@Snow7-G</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6472";>langchain4j/langchain4j#6472</a></li> <li>Keep the conversation for output guardrail retries without chat memory by <a href="https://github.com/edeandrea";><code>@edeandrea</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6627";>langchain4j/langchain4j#6627</a></li> <li>Add Azure DocumentDB embedding store, deprecate Azure Cosmos DB Mongo vCore by <a href="https://github.com/SandraAhlgrimm";><code>@SandraAhlgrimm</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/4426";>langchain4j/langchain4j#4426</a></li> <li>Azure DocumentDB docs: Spring Boot starter behaviour, migration defaults and client settings by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6635";>langchain4j/langchain4j#6635</a></li> <li>TypeSafe: make the System One API path configurable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6653";>langchain4j/langchain4j#6653</a></li> <li>JdkHttpClient: use HTTP/1.1 for plain http:// URLs by default by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6660";>langchain4j/langchain4j#6660</a></li> <li>Docs: HTTP version of SpringRestClient with the JDK client by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6668";>langchain4j/langchain4j#6668</a></li> <li>fix(guardrails): keep clean JSON a plain success in JsonExtractorOutputGuardrail by <a href="https://github.com/fengyue-xve";><code>@fengyue-xve</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6600";>langchain4j/langchain4j#6600</a></li> <li>chore(google-genai): update Google GenAI SDK to 1.77.0 and expose new SDK features by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6680";>langchain4j/langchain4j#6680</a></li> <li>feat(google-genai): support raw/recursive JSON schemas, multimodal tool results, async chat, and streaming cancellation by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6681";>langchain4j/langchain4j#6681</a></li> <li>test(google-genai): migrate tests from gemini-2.5-flash to gemini-3.8-flash by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6682";>langchain4j/langchain4j#6682</a></li> <li>Use MeterProvider for performance reasons by <a href="https://github.com/brunobat";><code>@brunobat</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6704";>langchain4j/langchain4j#6704</a></li> <li>fix(agentic): make HTML report formatting locale-independent by <a href="https://github.com/Mihir-Rabari";><code>@Mihir-Rabari</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6632";>langchain4j/langchain4j#6632</a></li> <li>OpenAI decision models: support images referenced by URL by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6715";>langchain4j/langchain4j#6715</a></li> <li>Streaming cancellation: no callbacks after cancel(), make StreamingHandle discoverable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6717";>langchain4j/langchain4j#6717</a></li> <li>feat(decision-models): custom body parameters for all decision models by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6718";>langchain4j/langchain4j#6718</a></li> <li>Fix ITs hanging/flaking on slow providers; expose provider errors returned with HTTP 200 by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6716";>langchain4j/langchain4j#6716</a></li> <li>Allow TokenStream to process complete responses on a custom executor by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6724";>langchain4j/langchain4j#6724</a></li> <li>OpenAiStreamingChatModel: fail on provider errors sent inside the stream by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6722";>langchain4j/langchain4j#6722</a></li> <li>Docs: fix ClassPathSkillLoader snippet types and custom patterns count by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6729";>langchain4j/langchain4j#6729</a></li> <li>Require exactly one subagent for ParallelMapperService by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6662";>langchain4j/langchain4j#6662</a></li> <li>fix(agentic): count every tool-loop model call in agent token usage by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6691";>langchain4j/langchain4j#6691</a></li> <li>Fixes <a href="https://redirect.github.com/langchain4j/langchain4j/issues/6665";>#6665</a> Untyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentExceptionUntyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentException by <a href="https://github.com/kamisheng";><code>@kamisheng</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6666";>langchain4j/langchain4j#6666</a></li> <li>Allow to generate the agentic context summarization also using a StreamingChatModel by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6721";>langchain4j/langchain4j#6721</a></li> <li>feat(bedrock): add guardContent placement support by <a href="https://github.com/DragonFSKY";><code>@DragonFSKY</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5030";>langchain4j/langchain4j#5030</a></li> <li>feat(google-genai): support code execution in the chat models by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6709";>langchain4j/langchain4j#6709</a></li> <li>Docs: Spring Boot's HTTP client settings in the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6740";>langchain4j/langchain4j#6740</a></li> <li>fix(agentic): always release the response an agent keeps per scope by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6693";>langchain4j/langchain4j#6693</a></li> <li>Fix the NullPointerException when an optional agent has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6697";>langchain4j/langchain4j#6697</a></li> <li>Stop supervisor planning while a SuspendedResponse is pending by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6636";>langchain4j/langchain4j#6636</a></li> <li>Decision models: conversation input for OpenAI and a typed DecisionInput by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6739";>langchain4j/langchain4j#6739</a></li> <li>Decision models: conversations for all providers, and conversation context for routers, tool filtering and output guardrails by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6741";>langchain4j/langchain4j#6741</a></li> <li>feat(google-genai): add GoogleGenAiTextToSpeechModel for Gemini text-to-speech by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6674";>langchain4j/langchain4j#6674</a></li> <li>Allow any agent or agentic pattern to declare an activation condition by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6731";>langchain4j/langchain4j#6731</a></li> <li>Fail fast when a BlackboardPlanner or GoalOrientedPlanner has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6720";>langchain4j/langchain4j#6720</a></li> <li>Add model name to generated agentic execution html report by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6761";>langchain4j/langchain4j#6761</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain4j/langchain4j/commit/32561faea052031811a9a6d8a21c5844ab44d1ef";><code>32561fa</code></a> Release versions 1.23.0 and 1.23.0-beta33</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/8f6e2210f1a9f8ad92a53e6211861d2b0fbd2802";><code>8f6e221</code></a> Validate the types of metadata filter comparison values (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6896";>#6896</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/055468af94754c981958bbadad45eb282d86efce";><code>055468a</code></a> Bind metadata filter values as parameters (pgvector, MariaDB) and map them st...</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ae86799436eb2759baf3bf5901376367a5ffdcbd";><code>ae86799</code></a> Update dependency com.google.guava:guava to v33 [SECURITY] (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6877";>#6877</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ab1dacc5dc573b71c60d53c57ee769bd8878eb5f";><code>ab1dacc</code></a> Docs: explain the Windows msvcp140.dll requirement of ONNX Runtime</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/61edab58958bfc5677debf18e07c7222986b7ce0";><code>61edab5</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6871";>#6871</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/215b41fdf9718a9ea87d563176cf53936ce2a543";><code>215b41f</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6870";>#6870</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/aa372e5f0d45aea1fb6660fada8c655487fb6205";><code>aa372e5</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6863";>#6863</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/afe99bac61f4e4d360c4a4a90763d45c0bb5802a";><code>afe99ba</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6864";>#6864</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/e80b454017775c2596a60d8530dc3bc1a047e57b";><code>e80b454</code></a> Also skip Vespa integration test when the flag -DskipITs is used (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6879";>#6879</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain4j/langchain4j/compare/1.22.0...1.23.0";>compare view</a></li> </ul> </details> <br /> Updates `dev.langchain4j:langchain4j-google-ai-gemini` from 1.22.0 to 1.23.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain4j/langchain4j/releases";>dev.langchain4j:langchain4j-google-ai-gemini's releases</a>.</em></p> <blockquote> <h2>1.23.0 and 1.23.0-beta33</h2> <h2>Notable Changes</h2> <ul> <li>Add OllamaDecisionModel: Ollama decision models, including images by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6659";>langchain4j/langchain4j#6659</a></li> <li>Introduce Confidence Cascade agentic pattern by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6765";>langchain4j/langchain4j#6765</a></li> <li>Observability: AiServiceInvocationSummaryEvent with all events of one AI Service invocation by <a href="https://github.com/rayanahmed1215";><code>@rayanahmed1215</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5048";>langchain4j/langchain4j#5048</a></li> <li>langchain4j-test: LLM judges and assertions on chat requests by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6819";>langchain4j/langchain4j#6819</a></li> <li>Introduce decision agents by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6820";>langchain4j/langchain4j#6820</a></li> </ul> <h2>Other Changes</h2> <ul> <li>chore(deps): bump shell-quote from 1.10.0 to 1.12.0 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6602";>langchain4j/langchain4j#6602</a></li> <li>Propagate the caller's context to work offloaded by AI Services by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6623";>langchain4j/langchain4j#6623</a></li> <li>Docs: non-blocking calls with the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6621";>langchain4j/langchain4j#6621</a></li> <li>chore(deps): bump proxy-addr from 2.0.7 to 2.0.8 in /docs by <a href="https://github.com/dependabot";><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6591";>langchain4j/langchain4j#6591</a></li> <li>docs: Extend MCP server guide with Streamable HTTP server options by <a href="https://github.com/kpavlov";><code>@kpavlov</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6622";>langchain4j/langchain4j#6622</a></li> <li>feat(micrometer-metrics): record chat operation duration by <a href="https://github.com/Snow7-G";><code>@Snow7-G</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6472";>langchain4j/langchain4j#6472</a></li> <li>Keep the conversation for output guardrail retries without chat memory by <a href="https://github.com/edeandrea";><code>@edeandrea</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6627";>langchain4j/langchain4j#6627</a></li> <li>Add Azure DocumentDB embedding store, deprecate Azure Cosmos DB Mongo vCore by <a href="https://github.com/SandraAhlgrimm";><code>@SandraAhlgrimm</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/4426";>langchain4j/langchain4j#4426</a></li> <li>Azure DocumentDB docs: Spring Boot starter behaviour, migration defaults and client settings by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6635";>langchain4j/langchain4j#6635</a></li> <li>TypeSafe: make the System One API path configurable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6653";>langchain4j/langchain4j#6653</a></li> <li>JdkHttpClient: use HTTP/1.1 for plain http:// URLs by default by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6660";>langchain4j/langchain4j#6660</a></li> <li>Docs: HTTP version of SpringRestClient with the JDK client by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6668";>langchain4j/langchain4j#6668</a></li> <li>fix(guardrails): keep clean JSON a plain success in JsonExtractorOutputGuardrail by <a href="https://github.com/fengyue-xve";><code>@fengyue-xve</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6600";>langchain4j/langchain4j#6600</a></li> <li>chore(google-genai): update Google GenAI SDK to 1.77.0 and expose new SDK features by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6680";>langchain4j/langchain4j#6680</a></li> <li>feat(google-genai): support raw/recursive JSON schemas, multimodal tool results, async chat, and streaming cancellation by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6681";>langchain4j/langchain4j#6681</a></li> <li>test(google-genai): migrate tests from gemini-2.5-flash to gemini-3.8-flash by <a href="https://github.com/glaforge";><code>@glaforge</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6682";>langchain4j/langchain4j#6682</a></li> <li>Use MeterProvider for performance reasons by <a href="https://github.com/brunobat";><code>@brunobat</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6704";>langchain4j/langchain4j#6704</a></li> <li>fix(agentic): make HTML report formatting locale-independent by <a href="https://github.com/Mihir-Rabari";><code>@Mihir-Rabari</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6632";>langchain4j/langchain4j#6632</a></li> <li>OpenAI decision models: support images referenced by URL by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6715";>langchain4j/langchain4j#6715</a></li> <li>Streaming cancellation: no callbacks after cancel(), make StreamingHandle discoverable by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6717";>langchain4j/langchain4j#6717</a></li> <li>feat(decision-models): custom body parameters for all decision models by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6718";>langchain4j/langchain4j#6718</a></li> <li>Fix ITs hanging/flaking on slow providers; expose provider errors returned with HTTP 200 by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6716";>langchain4j/langchain4j#6716</a></li> <li>Allow TokenStream to process complete responses on a custom executor by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6724";>langchain4j/langchain4j#6724</a></li> <li>OpenAiStreamingChatModel: fail on provider errors sent inside the stream by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6722";>langchain4j/langchain4j#6722</a></li> <li>Docs: fix ClassPathSkillLoader snippet types and custom patterns count by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6729";>langchain4j/langchain4j#6729</a></li> <li>Require exactly one subagent for ParallelMapperService by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6662";>langchain4j/langchain4j#6662</a></li> <li>fix(agentic): count every tool-loop model call in agent token usage by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6691";>langchain4j/langchain4j#6691</a></li> <li>Fixes <a href="https://redirect.github.com/langchain4j/langchain4j/issues/6665";>#6665</a> Untyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentExceptionUntyped A2A client agent with a missing input fails with a NullPointerException instead of MissingArgumentException by <a href="https://github.com/kamisheng";><code>@kamisheng</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6666";>langchain4j/langchain4j#6666</a></li> <li>Allow to generate the agentic context summarization also using a StreamingChatModel by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6721";>langchain4j/langchain4j#6721</a></li> <li>feat(bedrock): add guardContent placement support by <a href="https://github.com/DragonFSKY";><code>@DragonFSKY</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5030";>langchain4j/langchain4j#5030</a></li> <li>feat(google-genai): support code execution in the chat models by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6709";>langchain4j/langchain4j#6709</a></li> <li>Docs: Spring Boot's HTTP client settings in the Spring Boot starters by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6740";>langchain4j/langchain4j#6740</a></li> <li>fix(agentic): always release the response an agent keeps per scope by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6693";>langchain4j/langchain4j#6693</a></li> <li>Fix the NullPointerException when an optional agent has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6697";>langchain4j/langchain4j#6697</a></li> <li>Stop supervisor planning while a SuspendedResponse is pending by <a href="https://github.com/L00PLeGeNd";><code>@L00PLeGeNd</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6636";>langchain4j/langchain4j#6636</a></li> <li>Decision models: conversation input for OpenAI and a typed DecisionInput by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6739";>langchain4j/langchain4j#6739</a></li> <li>Decision models: conversations for all providers, and conversation context for routers, tool filtering and output guardrails by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6741";>langchain4j/langchain4j#6741</a></li> <li>feat(google-genai): add GoogleGenAiTextToSpeechModel for Gemini text-to-speech by <a href="https://github.com/subhashpolisetti";><code>@subhashpolisetti</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6674";>langchain4j/langchain4j#6674</a></li> <li>Allow any agent or agentic pattern to declare an activation condition by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6731";>langchain4j/langchain4j#6731</a></li> <li>Fail fast when a BlackboardPlanner or GoalOrientedPlanner has no output key by <a href="https://github.com/ryanmeowy";><code>@ryanmeowy</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6720";>langchain4j/langchain4j#6720</a></li> <li>Add model name to generated agentic execution html report by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6761";>langchain4j/langchain4j#6761</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/langchain4j/langchain4j/commit/32561faea052031811a9a6d8a21c5844ab44d1ef";><code>32561fa</code></a> Release versions 1.23.0 and 1.23.0-beta33</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/8f6e2210f1a9f8ad92a53e6211861d2b0fbd2802";><code>8f6e221</code></a> Validate the types of metadata filter comparison values (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6896";>#6896</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/055468af94754c981958bbadad45eb282d86efce";><code>055468a</code></a> Bind metadata filter values as parameters (pgvector, MariaDB) and map them st...</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ae86799436eb2759baf3bf5901376367a5ffdcbd";><code>ae86799</code></a> Update dependency com.google.guava:guava to v33 [SECURITY] (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6877";>#6877</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/ab1dacc5dc573b71c60d53c57ee769bd8878eb5f";><code>ab1dacc</code></a> Docs: explain the Windows msvcp140.dll requirement of ONNX Runtime</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/61edab58958bfc5677debf18e07c7222986b7ce0";><code>61edab5</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6871";>#6871</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/215b41fdf9718a9ea87d563176cf53936ce2a543";><code>215b41f</code></a> Update dependency org.postgresql:postgresql to v42.7.14 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6870";>#6870</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/aa372e5f0d45aea1fb6660fada8c655487fb6205";><code>aa372e5</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6863";>#6863</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/afe99bac61f4e4d360c4a4a90763d45c0bb5802a";><code>afe99ba</code></a> Update dependency org.mariadb.jdbc:mariadb-java-client to v3.5.11 (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6864";>#6864</a>)</li> <li><a href="https://github.com/langchain4j/langchain4j/commit/e80b454017775c2596a60d8530dc3bc1a047e57b";><code>e80b454</code></a> Also skip Vespa integration test when the flag -DskipITs is used (<a href="https://redirect.github.com/langchain4j/langchain4j/issues/6879";>#6879</a>)</li> <li>Additional commits viewable in <a href="https://github.com/langchain4j/langchain4j/compare/1.22.0...1.23.0";>compare view</a></li> </ul> </details> <br /> Updates `dev.langchain4j:langchain4j-ollama` from 1.22.0 to 1.23.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/langchain4j/langchain4j/releases";>dev.langchain4j:langchain4j-ollama's releases</a>.</em></p> <blockquote> <h2>1.23.0 and 1.23.0-beta33</h2> <h2>Notable Changes</h2> <ul> <li>Add OllamaDecisionModel: Ollama decision models, including images by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6659";>langchain4j/langchain4j#6659</a></li> <li>Introduce Confidence Cascade agentic pattern by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6765";>langchain4j/langchain4j#6765</a></li> <li>Observability: AiServiceInvocationSummaryEvent with all events of one AI Service invocation by <a href="https://github.com/rayanahmed1215";><code>@rayanahmed1215</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/5048";>langchain4j/langchain4j#5048</a></li> <li>langchain4j-test: LLM judges and assertions on chat requests by <a href="https://github.com/dliubarskyi";><code>@dliubarskyi</code></a> in <a href="https://redirect.github.com/langchain4j/langchain4j/pull/6819";>langchain4j/langchain4j#6819</a></li> <li>Introduce decision agents by <a href="https://github.com/mariofusco";><code>@mariofusco</code></a> in <a... _Description has been truncated_ -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
