Langchain4j Testing Strategies

Testing LangChain4j apps means dealing with non-deterministic LLM responses, which makes traditional testing a pain. This skill gives you the full spectrum: mock ChatModel responses with Mockito for fast unit tests, spin up real Ollama instances with Testcontainers for integration tests, and validate complete RAG workflows end-to-end. The code samples show proper health checks and await patterns so your tests don't flake when containers are slow to start. Honestly, the 70/20/10 testing pyramid guidance is the most useful part here. It keeps you from over-relying on expensive integration tests while still catching real issues that mocks miss.

skills.sh installs: 3.8K
GitHub stars: 369
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-testing-strategies --agent claude-code

Installs into .claude/skills of the current project.

Files

LangChain4J Testing Strategies

Overview

Patterns for unit testing with mocks, integration testing with Testcontainers, and end-to-end validation of RAG systems, AI Services, and tool execution.

When to Use

Unit testing AI services: When you need fast, isolated tests for services using LangChain4j AiServices
Integration testing LangChain4j components: When testing real ChatModel, EmbeddingModel, or RAG pipelines with Testcontainers
Mocking AI models: When you need deterministic responses without calling external APIs
Testing LLM-based Java applications: When validating RAG workflows, tool execution, or retrieval chains

Instructions

1. Unit Testing with Mocks

Use mock models for fast, isolated testing. See references/unit-testing.md.

ChatModel mockModel = mock(ChatModel.class);
when(mockModel.generate(any(String.class)))
    .thenReturn(Response.from(AiMessage.from("Mocked response")));

var service = AiServices.builder(AiService.class)
        .chatModel(mockModel)
        .build();