Skip to content

chore: bump the minor-and-patch group with 8 updates - #402

Open
dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/gradle/minor-and-patch-4fc2ea7284
Open

dependabot[bot] wants to merge 1 commit into
mainfrom
dependabot/gradle/minor-and-patch-4fc2ea7284

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Sep 14, 2026

Copy link
Copy Markdown
Contributor

Bumps the minor-and-patch group with 8 updates:

Package From To
com.diffplug.spotless 8.10.1 8.10.2
dev.langchain4j:langchain4j 1.19.0 1.20.0
dev.langchain4j:langchain4j-core 1.19.0 1.20.0
dev.langchain4j:langchain4j-open-ai 1.19.0 1.20.0
dev.langchain4j:langchain4j-mcp 1.19.0-beta29 1.20.0-beta30
dev.toonformat:jtoon 2.0.2 2.0.4
org.slf4j:slf4j-api 2.0.18 2.0.19
org.slf4j:slf4j-simple 2.0.18 2.0.19

Updates com.diffplug.spotless from 8.10.1 to 8.10.2

Updates dev.langchain4j:langchain4j from 1.19.0 to 1.20.0

Release notes

Sourced from dev.langchain4j:langchain4j's releases.

1.20.0 and 1.20.0-beta30

Notable Changes

Non-blocking / reactive support by @​dliubarskyi in langchain4j/langchain4j#5527

An AI Service method used to hold its thread for the whole interaction - the model call, tool execution, memory I/O and guardrails. It can now return CompletableFuture<T>/CompletionStage<T> for a single response, or Flow.Publisher<AiServiceStreamingEvent>/Flow.Publisher<String> for streaming, and the interaction runs without blocking a thread. You choose the mode by the method's return type; nothing else about the interface changes.

Non-blocking goes all the way down, because a blocking gap at any layer re-blocks the whole call: tool calling (sync and CompletableFuture tools, sequential or concurrent), chat memory, guardrails, and the full retrieval graph including EmbeddingModel, EmbeddingStore, ScoringModel and WebSearchEngine.

The work is additive and marked @Experimental: the synchronous and TokenStream APIs are untouched. A few defaults deliberately differ on the async path - multiple tool calls run concurrently, a tool execution error fails the invocation rather than being sent to the LLM, and a tool argument-parse error is sent to the LLM rather than failing. See Non-blocking and Reactive.

Jackson 3 opt-in support by @​dliubarskyi in langchain4j/langchain4j#6184

Add langchain4j-jackson3 to your classpath and LangChain4j's JSON runs on Jackson 3. There is nothing to configure and no API to call, and removing the dependency puts everything back on Jackson 2. Nothing changes for anyone who does not opt in.

With the opt-in in place, Jackson 2 can be excluded outright from most of the dependency graph; the modules that still need it are listed in the documentation. The one deliberate behaviour change is that a JSON failure surfaces as JsonReadException or JsonWriteException (both LangChain4jException) instead of a RuntimeException wrapping Jackson's own - catching RuntimeException works either way. See Using Jackson 3.

Other Changes

... (truncated)

Commits
  • 3a2f4dc Release versions 1.20.0 and 1.20.0-beta30
  • affc81f feat(a2a): add @​A2ATenantId for multi-tenant agent routing (#6303)
  • 02ff1cf Give SupervisorAgentIT's Invoice a toString, so its agent gets a usable prompt
  • 883c74b Fix NullPointerException when completing a pending response with a null value...
  • d08cadc Fix three Jackson 3 defects the nightly integration run found (#6301)
  • f5133fe Make SupervisorAgentIT's Invoice constructible from the planner's arguments (...
  • 6a49340 Jackson 3 opt-in support (#6184)
  • 15f16f6 Upgrade mutiny-zero to 1.3.1 and drop the demand-decoupling workaround
  • c0c2fd2 feat(document-parser-docling): DocumentRequest templates, async parsing, and ...
  • 2f27d4c fix(agentic): include inherited fields in supervisor argument descriptions (#...
  • Additional commits viewable in compare view

Updates dev.langchain4j:langchain4j-core from 1.19.0 to 1.20.0

Release notes

Sourced from dev.langchain4j:langchain4j-core's releases.

1.20.0 and 1.20.0-beta30

Notable Changes

Non-blocking / reactive support by @​dliubarskyi in langchain4j/langchain4j#5527

An AI Service method used to hold its thread for the whole interaction - the model call, tool execution, memory I/O and guardrails. It can now return CompletableFuture<T>/CompletionStage<T> for a single response, or Flow.Publisher<AiServiceStreamingEvent>/Flow.Publisher<String> for streaming, and the interaction runs without blocking a thread. You choose the mode by the method's return type; nothing else about the interface changes.

Non-blocking goes all the way down, because a blocking gap at any layer re-blocks the whole call: tool calling (sync and CompletableFuture tools, sequential or concurrent), chat memory, guardrails, and the full retrieval graph including EmbeddingModel, EmbeddingStore, ScoringModel and WebSearchEngine.

The work is additive and marked @Experimental: the synchronous and TokenStream APIs are untouched. A few defaults deliberately differ on the async path - multiple tool calls run concurrently, a tool execution error fails the invocation rather than being sent to the LLM, and a tool argument-parse error is sent to the LLM rather than failing. See Non-blocking and Reactive.

Jackson 3 opt-in support by @​dliubarskyi in langchain4j/langchain4j#6184

Add langchain4j-jackson3 to your classpath and LangChain4j's JSON runs on Jackson 3. There is nothing to configure and no API to call, and removing the dependency puts everything back on Jackson 2. Nothing changes for anyone who does not opt in.

With the opt-in in place, Jackson 2 can be excluded outright from most of the dependency graph; the modules that still need it are listed in the documentation. The one deliberate behaviour change is that a JSON failure surfaces as JsonReadException or JsonWriteException (both LangChain4jException) instead of a RuntimeException wrapping Jackson's own - catching RuntimeException works either way. See Using Jackson 3.

Other Changes

... (truncated)

Commits
  • 3a2f4dc Release versions 1.20.0 and 1.20.0-beta30
  • affc81f feat(a2a): add @​A2ATenantId for multi-tenant agent routing (#6303)
  • 02ff1cf Give SupervisorAgentIT's Invoice a toString, so its agent gets a usable prompt
  • 883c74b Fix NullPointerException when completing a pending response with a null value...
  • d08cadc Fix three Jackson 3 defects the nightly integration run found (#6301)
  • f5133fe Make SupervisorAgentIT's Invoice constructible from the planner's arguments (...
  • 6a49340 Jackson 3 opt-in support (#6184)
  • 15f16f6 Upgrade mutiny-zero to 1.3.1 and drop the demand-decoupling workaround
  • c0c2fd2 feat(document-parser-docling): DocumentRequest templates, async parsing, and ...
  • 2f27d4c fix(agentic): include inherited fields in supervisor argument descriptions (#...
  • Additional commits viewable in compare view

Updates dev.langchain4j:langchain4j-open-ai from 1.19.0 to 1.20.0

Release notes

Sourced from dev.langchain4j:langchain4j-open-ai's releases.

1.20.0 and 1.20.0-beta30

Notable Changes

Non-blocking / reactive support by @​dliubarskyi in langchain4j/langchain4j#5527

An AI Service method used to hold its thread for the whole interaction - the model call, tool execution, memory I/O and guardrails. It can now return CompletableFuture<T>/CompletionStage<T> for a single response, or Flow.Publisher<AiServiceStreamingEvent>/Flow.Publisher<String> for streaming, and the interaction runs without blocking a thread. You choose the mode by the method's return type; nothing else about the interface changes.

Non-blocking goes all the way down, because a blocking gap at any layer re-blocks the whole call: tool calling (sync and CompletableFuture tools, sequential or concurrent), chat memory, guardrails, and the full retrieval graph including EmbeddingModel, EmbeddingStore, ScoringModel and WebSearchEngine.

The work is additive and marked @Experimental: the synchronous and TokenStream APIs are untouched. A few defaults deliberately differ on the async path - multiple tool calls run concurrently, a tool execution error fails the invocation rather than being sent to the LLM, and a tool argument-parse error is sent to the LLM rather than failing. See Non-blocking and Reactive.

Jackson 3 opt-in support by @​dliubarskyi in langchain4j/langchain4j#6184

Add langchain4j-jackson3 to your classpath and LangChain4j's JSON runs on Jackson 3. There is nothing to configure and no API to call, and removing the dependency puts everything back on Jackson 2. Nothing changes for anyone who does not opt in.

With the opt-in in place, Jackson 2 can be excluded outright from most of the dependency graph; the modules that still need it are listed in the documentation. The one deliberate behaviour change is that a JSON failure surfaces as JsonReadException or JsonWriteException (both LangChain4jException) instead of a RuntimeException wrapping Jackson's own - catching RuntimeException works either way. See Using Jackson 3.

Other Changes

... (truncated)

Commits
  • 3a2f4dc Release versions 1.20.0 and 1.20.0-beta30
  • affc81f feat(a2a): add @​A2ATenantId for multi-tenant agent routing (#6303)
  • 02ff1cf Give SupervisorAgentIT's Invoice a toString, so its agent gets a usable prompt
  • 883c74b Fix NullPointerException when completing a pending response with a null value...
  • d08cadc Fix three Jackson 3 defects the nightly integration run found (#6301)
  • f5133fe Make SupervisorAgentIT's Invoice constructible from the planner's arguments (...
  • 6a49340 Jackson 3 opt-in support (#6184)
  • 15f16f6 Upgrade mutiny-zero to 1.3.1 and drop the demand-decoupling workaround
  • c0c2fd2 feat(document-parser-docling): DocumentRequest templates, async parsing, and ...
  • 2f27d4c fix(agentic): include inherited fields in supervisor argument descriptions (#...
  • Additional commits viewable in compare view

Updates dev.langchain4j:langchain4j-core from 1.19.0 to 1.20.0

Release notes

Sourced from dev.langchain4j:langchain4j-core's releases.

1.20.0 and 1.20.0-beta30

Notable Changes

Non-blocking / reactive support by @​dliubarskyi in langchain4j/langchain4j#5527

An AI Service method used to hold its thread for the whole interaction - the model call, tool execution, memory I/O and guardrails. It can now return CompletableFuture<T>/CompletionStage<T> for a single response, or Flow.Publisher<AiServiceStreamingEvent>/Flow.Publisher<String> for streaming, and the interaction runs without blocking a thread. You choose the mode by the method's return type; nothing else about the interface changes.

Non-blocking goes all the way down, because a blocking gap at any layer re-blocks the whole call: tool calling (sync and CompletableFuture tools, sequential or concurrent), chat memory, guardrails, and the full retrieval graph including EmbeddingModel, EmbeddingStore, ScoringModel and WebSearchEngine.

The work is additive and marked @Experimental: the synchronous and TokenStream APIs are untouched. A few defaults deliberately differ on the async path - multiple tool calls run concurrently, a tool execution error fails the invocation rather than being sent to the LLM, and a tool argument-parse error is sent to the LLM rather than failing. See Non-blocking and Reactive.

Jackson 3 opt-in support by @​dliubarskyi in langchain4j/langchain4j#6184

Add langchain4j-jackson3 to your classpath and LangChain4j's JSON runs on Jackson 3. There is nothing to configure and no API to call, and removing the dependency puts everything back on Jackson 2. Nothing changes for anyone who does not opt in.

With the opt-in in place, Jackson 2 can be excluded outright from most of the dependency graph; the modules that still need it are listed in the documentation. The one deliberate behaviour change is that a JSON failure surfaces as JsonReadException or JsonWriteException (both LangChain4jException) instead of a RuntimeException wrapping Jackson's own - catching RuntimeException works either way. See Using Jackson 3.

Other Changes

... (truncated)

Commits
  • 3a2f4dc Release versions 1.20.0 and 1.20.0-beta30
  • affc81f feat(a2a): add @​A2ATenantId for multi-tenant agent routing (#6303)
  • 02ff1cf Give SupervisorAgentIT's Invoice a toString, so its agent gets a usable prompt
  • 883c74b Fix NullPointerException when completing a pending response with a null value...
  • d08cadc Fix three Jackson 3 defects the nightly integration run found (#6301)
  • f5133fe Make SupervisorAgentIT's Invoice constructible from the planner's arguments (...
  • 6a49340 Jackson 3 opt-in support (#6184)
  • 15f16f6 Upgrade mutiny-zero to 1.3.1 and drop the demand-decoupling workaround
  • c0c2fd2 feat(document-parser-docling): DocumentRequest templates, async parsing, and ...
  • 2f27d4c fix(agentic): include inherited fields in supervisor argument descriptions (#...
  • Additional commits viewable in compare view

Updates dev.langchain4j:langchain4j-open-ai from 1.19.0 to 1.20.0

Release notes

Sourced from dev.langchain4j:langchain4j-open-ai's releases.

1.20.0 and 1.20.0-beta30

Notable Changes

Non-blocking / reactive support by @​dliubarskyi in langchain4j/langchain4j#5527

An AI Service method used to hold its thread for the whole interaction - the model call, tool execution, memory I/O and guardrails. It can now return CompletableFuture<T>/CompletionStage<T> for a single response, or Flow.Publisher<AiServiceStreamingEvent>/Flow.Publisher<String> for streaming, and the interaction runs without blocking a thread. You choose the mode by the method's return type; nothing else about the interface changes.

Non-blocking goes all the way down, because a blocking gap at any layer re-blocks the whole call: tool calling (sync and CompletableFuture tools, sequential or concurrent), chat memory, guardrails, and the full retrieval graph including EmbeddingModel, EmbeddingStore, ScoringModel and WebSearchEngine.

The work is additive and marked @Experimental: the synchronous and TokenStream APIs are untouched. A few defaults deliberately differ on the async path - multiple tool calls run concurrently, a tool execution error fails the invocation rather than being sent to the LLM, and a tool argument-parse error is sent to the LLM rather than failing. See Non-blocking and Reactive.

Jackson 3 opt-in support by @​dliubarskyi in langchain4j/langchain4j#6184

Add langchain4j-jackson3 to your classpath and LangChain4j's JSON runs on Jackson 3. There is nothing to configure and no API to call, and removing the dependency puts everything back on Jackson 2. Nothing changes for anyone who does not opt in.

With the opt-in in place, Jackson 2 can be excluded outright from most of the dependency graph; the modules that still need it are listed in the documentation. The one deliberate behaviour change is that a JSON failure surfaces as JsonReadException or JsonWriteException (both LangChain4jException) instead of a RuntimeException wrapping Jackson's own - catching RuntimeException works either way. See Using Jackson 3.

Other Changes

Bumps the minor-and-patch group with 8 updates:

| Package | From | To |
| --- | --- | --- |
| com.diffplug.spotless | `8.10.1` | `8.10.2` |
| [dev.langchain4j:langchain4j](https://github.com/langchain4j/langchain4j) | `1.19.0` | `1.20.0` |
| [dev.langchain4j:langchain4j-core](https://github.com/langchain4j/langchain4j) | `1.19.0` | `1.20.0` |
| [dev.langchain4j:langchain4j-open-ai](https://github.com/langchain4j/langchain4j) | `1.19.0` | `1.20.0` |
| [dev.langchain4j:langchain4j-mcp](https://github.com/langchain4j/langchain4j) | `1.19.0-beta29` | `1.20.0-beta30` |
| [dev.toonformat:jtoon](https://github.com/toon-format/toon-java) | `2.0.2` | `2.0.4` |
| org.slf4j:slf4j-api | `2.0.18` | `2.0.19` |
| org.slf4j:slf4j-simple | `2.0.18` | `2.0.19` |


Updates `com.diffplug.spotless` from 8.10.1 to 8.10.2

Updates `dev.langchain4j:langchain4j` from 1.19.0 to 1.20.0
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](langchain4j/langchain4j@1.19.0...1.20.0)

Updates `dev.langchain4j:langchain4j-core` from 1.19.0 to 1.20.0
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](langchain4j/langchain4j@1.19.0...1.20.0)

Updates `dev.langchain4j:langchain4j-open-ai` from 1.19.0 to 1.20.0
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](langchain4j/langchain4j@1.19.0...1.20.0)

Updates `dev.langchain4j:langchain4j-core` from 1.19.0 to 1.20.0
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](langchain4j/langchain4j@1.19.0...1.20.0)

Updates `dev.langchain4j:langchain4j-open-ai` from 1.19.0 to 1.20.0
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](langchain4j/langchain4j@1.19.0...1.20.0)

Updates `dev.langchain4j:langchain4j-mcp` from 1.19.0-beta29 to 1.20.0-beta30
- [Release notes](https://github.com/langchain4j/langchain4j/releases)
- [Commits](https://github.com/langchain4j/langchain4j/commits)

Updates `dev.toonformat:jtoon` from 2.0.2 to 2.0.4
- [Release notes](https://github.com/toon-format/toon-java/releases)
- [Changelog](https://github.com/toon-format/toon-java/blob/main/CHANGELOG.md)
- [Commits](toon-format/toon-java@v2.0.2...v2.0.4)

Updates `org.slf4j:slf4j-api` from 2.0.18 to 2.0.19

Updates `org.slf4j:slf4j-simple` from 2.0.18 to 2.0.19

Updates `org.slf4j:slf4j-simple` from 2.0.18 to 2.0.19

---
updated-dependencies:
- dependency-name: com.diffplug.spotless
  dependency-version: 8.10.2
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j
  dependency-version: 1.20.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j-core
  dependency-version: 1.20.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j-open-ai
  dependency-version: 1.20.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j-core
  dependency-version: 1.20.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j-open-ai
  dependency-version: 1.20.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.langchain4j:langchain4j-mcp
  dependency-version: 1.20.0-beta30
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: minor-and-patch
- dependency-name: dev.toonformat:jtoon
  dependency-version: 2.0.4
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: org.slf4j:slf4j-api
  dependency-version: 2.0.19
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: org.slf4j:slf4j-simple
  dependency-version: 2.0.19
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
- dependency-name: org.slf4j:slf4j-simple
  dependency-version: 2.0.19
  dependency-type: direct:production
  update-type: version-update:semver-patch
  dependency-group: minor-and-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot added dependencies Pull requests that update a dependency file java Pull requests that update java code labels Sep 14, 2026
@github-actions

Copy link
Copy Markdown
Contributor

Test Results

4 552 tests   4 546 ✅  4m 32s ⏱️
  364 suites      6 💤
  364 files        0 ❌

Results for commit 9182fe4.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

dependencies Pull requests that update a dependency file java Pull requests that update java code

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants