复用与扩展评估定义

import io.agentscope.extensions.judge.jev.JevJudge;
import io.agentscope.extensions.judge.jev.NoulQuestion;
import io.agentscope.extensions.judge.jev.evaluation.JevEvaluator;
import io.agentscope.extensions.judge.jev.evaluation.JevTraceEvaluator;
import io.agentscope.extensions.judge.jev.evaluation.JevTraceMetrics;
import java.time.Duration;
import java.util.ArrayList;
import java.util.List;

var definition = new JevJudge.Definition("refund-answer-v1", List.of(
    new JevJudge.Criterion("supported",
        new NoulQuestion("Is assistant_answer supported by supporting_context without inventing completed refunds?", null),
        true, 0.2, 0.8)));
var judge = new JevJudge(client, Duration.ofSeconds(2));
var evaluator = new JevEvaluator(judge, definition);

var thresholds = new JevTraceMetrics.Thresholds(0.2, 0.8);
var metrics = new ArrayList<>(JevTraceMetrics.agentMetrics(thresholds));
metrics.add(JevTraceMetrics.trajectoryMatch(
    JevTraceMetrics.MatchMode.STRICT, true));
var traceEvaluator = new JevTraceEvaluator(client, metrics,
    new JevTraceEvaluator.Limits(Duration.ofSeconds(3), 128, 100_000));

java -cp "$JEV_CP" io.agentscope.examples.jev.JevApplicationScenarios judge
java -cp "$JEV_CP" io.agentscope.examples.jev.JevApplicationScenarios evaluation