Built-in Judges

Judge judge = new FileExistsJudge("src/main/java/App.java");
Judgment result = judge.judge(context);

// Exact match
Judge exact = new FileContentJudge("config.json", expectedContent);

// Contains substring
Judge contains = new FileContentJudge("output.log", "BUILD SUCCESS", FileContentJudge.MatchMode.CONTAINS);

// Regex pattern
Judge regex = new FileContentJudge("version.txt", "\\d+\\.\\d+\\.\\d+", FileContentJudge.MatchMode.REGEX);

Judge judge = new SupersetDiffJudge();

// Maven — auto-detects ./mvnw wrapper
Judge maven = BuildSuccessJudge.maven("clean", "compile");

// Gradle — auto-detects ./gradlew wrapper
Judge gradle = BuildSuccessJudge.gradle("build", "test");

// Custom command string
Judge custom = new BuildSuccessJudge("make all");

// Default: expect exit code 0, 2 minute timeout
Judge simple = new CommandJudge("ls README.md");

// Custom exit code and timeout
Judge custom = new CommandJudge("grep -c TODO src/App.java", 0, Duration.ofSeconds(30));

// With custom sandbox factory (e.g., Docker-based execution)
Judge sandboxed = new CommandJudge("mvn test", 0, Duration.ofMinutes(5), sandboxFactory);

// Java 17 = class version 61
Judge judge = new ClassVersionJudge(61);

// Allow up to 5% coverage drop (default threshold)
Judge judge = new CoveragePreservationJudge();

// Custom threshold
Judge strict = new CoveragePreservationJudge(2.0);

// Score normalized against max improvement of 50 percentage points (default)
Judge judge = new CoverageImprovementJudge();

// Custom normalization ceiling: 20pp improvement = score 1.0
Judge custom = new CoverageImprovementJudge(20.0);

// With minimum coverage floor: fail if below 60% regardless of improvement
Judge withFloor = new CoverageImprovementJudge(20.0, 60.0);

Judge judge = new FileComparisonJudge();

Judge judge = new JavaSemanticJudge();

Judge judge = new MavenSemanticJudge();

Judge judge = new XmlSemanticJudge();

Judge judge = new TextFileJudge();

CorrectnessJudge judge = new CorrectnessJudge(chatClientBuilder);
Judgment result = judge.judge(context);

public class QualityJudge extends LLMJudge {

    public QualityJudge(ChatClient.Builder chatClientBuilder) {
        super("quality", "Rates code quality 0-10", chatClientBuilder);
    }

    @Override
    protected String buildPrompt(JudgmentContext context) {
        return "Rate this code quality 0-10:\n" +
            context.agentOutput().orElse("");
    }

    @Override
    protected Judgment parseResponse(String response, JudgmentContext context) {
        double score = extractScore(response);
        return Judgment.builder()
            .score(new NumericalScore(score, 0, 10))
            .status(score >= 7 ? JudgmentStatus.PASS : JudgmentStatus.FAIL)
            .reasoning(response)
            .build();
    }
}

Judge judge = new FaithfulnessJudge(chatClientBuilder);
Judgment result = judge.judge(context);

Judge judge = new ContextualRelevanceJudge(chatClientBuilder);
Judgment result = judge.judge(context);

Judge judge = new HallucinationJudge(chatClientBuilder);
Judgment result = judge.judge(context);

SimpleJury relevanceTier = SimpleJury.builder()
    .judge(new ContextualRelevanceJudge(chatClientBuilder))
    .votingStrategy(new MajorityVotingStrategy())
    .build();

SimpleJury faithfulnessTier = SimpleJury.builder()
    .judge(new FaithfulnessJudge(chatClientBuilder))
    .judge(new HallucinationJudge(chatClientBuilder))
    .votingStrategy(new ConsensusStrategy())
    .build();

CascadedJury ragJury = CascadedJury.builder()
    .tier("relevance", relevanceTier, TierPolicy.REJECT_ON_ANY_FAIL)
    .tier("grounding", faithfulnessTier, TierPolicy.FINAL_TIER)
    .build();

Verdict verdict = ragJury.vote(context);