Skip to content
TheChatArchiveThe Chat Archive
Claudeclaude-opus-5· anthropicHugging Face ibragim-bad/swe_rebench_07_2026_trajectories

ISSUE DESCRIPTION [BUG] Duplicate activate_skill tool definition error when using…

  1. User

    ISSUE DESCRIPTION

    [BUG] Duplicate activate_skill tool definition error when using AgenticServices.createAgenticSystem() Describe the bug When creating an agentic system with AgenticServices.createAgenticSystem(), even with a single agent, the application throws an IllegalConfigurationException: Duplicated definition for tool: activate_skill during execution, caused by multiple registrations of non-dynamic ToolProvider instances.

    Log and Stack trace

    Caused by: dev.langchain4j.service.IllegalConfigurationException: Duplicated definition for tool: activate_skill
            at dev.langchain4j.service.tool.ToolService.addTools(ToolService.java:398)
            at dev.langchain4j.service.tool.ToolService.lambda$createContextFromStaticToolsAndProviders$0(ToolService.java:378)
            at java.base/java.lang.Iterable.forEach(Iterable.java:75)
            at dev.langchain4j.service.tool.ToolService.createContextFromStaticToolsAndProviders(ToolService.java:371)
            at dev.langchain4j.service.tool.ToolService.createContext(ToolService.java:338)
            at dev.langchain4j.service.DefaultAiServices$1.invoke(DefaultAiServices.java:260)
            at dev.langchain4j.service.DefaultAiServices$1.invoke(DefaultAiServices.java:154)
            at jdk.proxy2/jdk.proxy2.$Proxy5.test(Unknown Source)
            at java.base/jdk.internal.reflect.DirectMethodHandleAccessor.invoke(DirectMethodHandleAccessor.java:104)
            ... 5 more
    

    To Reproduce

    public class Main {
    
        public static void main(String[] args) {
            var result=AgenticServices.createAgenticSystem(FooAgent.class).test();
            // var result=AgenticServices.agentBuilder(FooAgent.class).build().test();
            System.out.println(result);
        }
        public interface FooAgent {
            @Agent
            @UserMessage("Hello")
            String test();
    
            @ToolProviderSupplier
            static ToolProvider testTool() {
                return Skills.builder()
                        .skills(Skill.builder().name("test").description("test").content("test").build())
                        .build().toolProvider();
            }
    
            @ChatModelSupplier
            static ChatModel chatModel() {
    
            return OpenAiChatModel.builder()
                    .baseUrl("http://192.168.31.32:8000/v1")
                    .apiKey("none")
                    .modelName("qwen3.6")
                    .logRequests(true)
                    .logResponses(true)
                    .build();
            }
        }
    
    }
    

    Expected behavior The agentic system should run successfully, properly deduplicating tools (including the built-in activate_skill tool) when registering non-dynamic ToolProvider instances.

    Please complete the following information:

    • LangChain4j version: latest agentic snapshot
    • LLM(s) used: Qwen 3.6 (via OpenAiChatModel)
    • Java version: 25
    • Spring Boot version (if applicable): N/A

    Additional context The bug is caused by createAgenticSystem registering non-dynamic ToolProvider instances multiple times. The activate_skill tool is automatically added for every SkillProvider instance, leading to duplicate registration even with a single agent.

    Interface

    Type: Function Name: createAgenticSystem Path: langchain4j-agentic/src/main/java/dev/langchain4j/agentic/AgenticServices.java Input: Class agentServiceClass, AgentConfigurator agentConfigurator Output: T (the created agentic system instance of the requested type) Description: Creates an agentic system from a declarative agent service class, applying the provided configurator to each agent. This overload resolves the default chat model from the agent class and deduplicates tool registrations across the system.

    ADDITIONAL ADVICE

    Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use git checkout <file> to restore the file to its original state. You can also reset all changes in the repository using git reset --hard command. Additionally, you can use git stash and git stash pop to temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you call submit) using git status or git diff commands. However you don't need to use git add or git commit before submitting your changes. In fact, submit only submits currently unstaged changes because it uses git diff to get the changes that need to be submitted.

    CHECKLIST

    Before submitting your solution, please go over the following checklist and make sure you've done everything:

    • If an error was reported in the issue description, I have successfully reproduced it.
    • If an error was reported in the issue description, I have confirmed that my fix resolves the error.
    • I have thought about edge cases and made sure my fix handles them as well.
    • I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.

    Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!

    (Current directory: /langchain4j, current file: none) bash-$

  2. Claude Assistant

    Now let me write a temporary reproduction test.

  3. Claude Assistant

    Now let me restructure the method.

  4. Claude Assistant

    Now split out the chat model block and the listener block.

  5. Claude Assistant

    Now remove the leftover listener block and configurator line at lines 165-172.

  6. Claude Assistant

    Final state is clean — only the source fix remains. Here is my checklist review:

    • [x] If an error was reported in the issue description, I have successfully reproduced it. I wrote a temporary test (TmpDupToolProviderTest) in langchain4j-agentic that declares an agent with @ToolProviderSupplier returning a new non-dynamic ToolProvider instance exposing an activate_skill tool, and invoked it via AgenticServices.createAgenticSystem(...). It failed exactly with IllegalConfigurationException: Duplicated definition for tool: activate_skill. Stack-trace instrumentation showed the supplier being invoked twice: once from AgentBuilder's constructor (DeclarativeUtil.configureAgent(type, builder)) and once from AgenticServices.createAgenticSystem/createSubagent (configureAgent(type, chatModel, builder, configurator)), registering two distinct providers that each contribute the same tool.

    • [x] If an error was reported in the issue description, I have confirmed that my fix resolves the error. I split DeclarativeUtil.configureAgent so the declarative features (tools, tool providers, content retriever, retrieval augmentor, chat memory/provider, listeners) are configured only once — when the AgentBuilder is created — while the 4-arg overload used by AgenticServices now only resolves/overrides the chat model and applies the AgentConfigurator. After the change the reproduction test passes and the request sent to the model contains exactly one activate_skill tool.

    • [x] I have thought about edge cases and made sure my fix handles them as well. I verified: (1) the single-agent path createAgenticSystem(FooAgent.class); (2) the sub-agent path (@SequenceAgent parent with a sub-agent declaring a tool provider), which suffered from the same double registration; (3) @AgentListenerSupplier listeners are no longer registered twice (previously composed twice, causing duplicate callbacks) — verified a listener fires exactly once; (4) the AgentConfigurator is still applied exactly once and last; (5) the chat-model resolution semantics are unchanged, including the IllegalArgumentException when no model is available for a sub-agent, and the parameterized @ChatModelSupplier resolvers; (6) all call sites of the 4-arg configureAgent (repo-wide grep, including other modules) always create the builder through AgenticServices.agentBuilder(...), whose constructor performs the feature configuration, so nothing is lost.

    • [x] I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. mvn -pl langchain4j-agentic test → 45 tests, all green (including ChatSupplierParameterResolverTest, which exercises declarative agent creation). The remaining agentic tests are *IT integration tests requiring live LLM endpoints and cannot run in this environment. I did not modify or add any repository tests — the reproduction test was temporary and has been deleted.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.