feat: archive mvp demo trace acceptance
This commit is contained in:
@@ -85,6 +85,43 @@ class ChatServiceSupervisorAgentTest {
|
||||
assertEquals(List.of("chat_planner", "chat_executor", "chat_verifier", "FINISH"), chatModel.decisions);
|
||||
}
|
||||
|
||||
@Test
|
||||
void executeChatComplexInvokesVerifierFallbackWhenSupervisorSkipsVerifier() throws Exception {
|
||||
ChatService chatService = createChatService();
|
||||
ScriptedChatModel chatModel = new ScriptedChatModel(
|
||||
List.of("chat_planner", "chat_executor", "FINISH"),
|
||||
"""
|
||||
{
|
||||
"verdict": "PASS",
|
||||
"groundedness_score": 1.0,
|
||||
"critical_fact_count": 1,
|
||||
"facts_checked": [
|
||||
{
|
||||
"fact": "executor answer generated",
|
||||
"is_critical": true,
|
||||
"verification": "direct_evidence",
|
||||
"detail": "covered by fallback verifier",
|
||||
"evidence_refs": []
|
||||
}
|
||||
],
|
||||
"rationale": "fallback verifier pass"
|
||||
}
|
||||
"""
|
||||
);
|
||||
|
||||
ChatService.ChatResult result = chatService.executeChatComplex(
|
||||
chatModel,
|
||||
new ToolCallback[0],
|
||||
"请分析订单支付超时的原因,并给出修复建议",
|
||||
List.of(),
|
||||
"supervisor-verifier-fallback-session"
|
||||
);
|
||||
|
||||
assertEquals("EXECUTOR_FINAL_ANSWER", result.answer());
|
||||
assertEquals(List.of("chat_planner", "chat_executor", "FINISH"), chatModel.decisions);
|
||||
assertTrue(chatModel.sawVerifierPrompt);
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildMethodToolsArrayIncludesLogsAndMetricsWhenAvailable() {
|
||||
ChatService chatService = new ChatService();
|
||||
@@ -153,7 +190,7 @@ class ChatServiceSupervisorAgentTest {
|
||||
}
|
||||
|
||||
private static final class ScriptedChatModel implements ChatModel {
|
||||
private final List<String> decisionScript = List.of("chat_planner", "chat_executor", "chat_verifier", "FINISH");
|
||||
private final List<String> decisionScript;
|
||||
private final java.util.ArrayList<String> decisions = new java.util.ArrayList<>();
|
||||
private int decisionIndex;
|
||||
private String promptText = "";
|
||||
@@ -161,7 +198,7 @@ class ChatServiceSupervisorAgentTest {
|
||||
private final String verifierOutput;
|
||||
|
||||
private ScriptedChatModel() {
|
||||
this("""
|
||||
this(List.of("chat_planner", "chat_executor", "chat_verifier", "FINISH"), """
|
||||
{
|
||||
"verdict": "PASS",
|
||||
"groundedness_score": 1.0,
|
||||
@@ -181,6 +218,11 @@ class ChatServiceSupervisorAgentTest {
|
||||
}
|
||||
|
||||
private ScriptedChatModel(String verifierOutput) {
|
||||
this(List.of("chat_planner", "chat_executor", "chat_verifier", "FINISH"), verifierOutput);
|
||||
}
|
||||
|
||||
private ScriptedChatModel(List<String> decisionScript, String verifierOutput) {
|
||||
this.decisionScript = decisionScript;
|
||||
this.verifierOutput = verifierOutput;
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,119 @@
|
||||
package com.superbiz.agent.service;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import com.superbiz.agent.domain.entity.AgentStep;
|
||||
import com.superbiz.agent.domain.entity.DiagnosisSession;
|
||||
import com.superbiz.agent.domain.entity.ToolInvocation;
|
||||
import com.superbiz.agent.dto.DiagnosisTraceResponse;
|
||||
import com.superbiz.agent.exception.SessionNotFoundException;
|
||||
import com.superbiz.agent.repository.AgentStepRepository;
|
||||
import com.superbiz.agent.repository.DiagnosisSessionRepository;
|
||||
import com.superbiz.agent.repository.ToolInvocationRepository;
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import java.time.LocalDateTime;
|
||||
import java.util.List;
|
||||
import java.util.Optional;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
import static org.mockito.Mockito.*;
|
||||
|
||||
class DiagnosisTraceServiceTest {
|
||||
|
||||
private final DiagnosisSessionRepository diagnosisSessionRepository = mock(DiagnosisSessionRepository.class);
|
||||
private final AgentStepRepository agentStepRepository = mock(AgentStepRepository.class);
|
||||
private final ToolInvocationRepository toolInvocationRepository = mock(ToolInvocationRepository.class);
|
||||
private final DiagnosisTraceService service = new DiagnosisTraceService(
|
||||
diagnosisSessionRepository,
|
||||
agentStepRepository,
|
||||
toolInvocationRepository,
|
||||
new ObjectMapper()
|
||||
);
|
||||
|
||||
@Test
|
||||
void getTraceAggregatesSessionStepsAndTools() {
|
||||
String sessionId = "trace-session-001";
|
||||
LocalDateTime now = LocalDateTime.of(2026, 7, 3, 14, 30);
|
||||
DiagnosisSession session = DiagnosisSession.builder()
|
||||
.id(1L)
|
||||
.sessionId(sessionId)
|
||||
.query("payment timeout")
|
||||
.status("SUCCESS")
|
||||
.agentFlow("COMPLEX")
|
||||
.totalDurationMs(1200)
|
||||
.totalTokenCount(300)
|
||||
.stepCount(2)
|
||||
.toolCallCount(1)
|
||||
.answer("restart payment gateway pool")
|
||||
.selfEvaluation("{\"verifier_evaluation\":{\"verdict\":\"PASS\"}}")
|
||||
.feedback("useful")
|
||||
.createdAt(now)
|
||||
.updatedAt(now)
|
||||
.build();
|
||||
AgentStep step = AgentStep.builder()
|
||||
.id(10L)
|
||||
.sessionId(sessionId)
|
||||
.stepIndex(1)
|
||||
.agentName("chat_executor")
|
||||
.modelInput("input")
|
||||
.modelOutput("output")
|
||||
.thought("executor finished")
|
||||
.hasToolCall(true)
|
||||
.durationMs(500)
|
||||
.tokenCount(100)
|
||||
.createdAt(now)
|
||||
.build();
|
||||
ToolInvocation invocation = ToolInvocation.builder()
|
||||
.id(20L)
|
||||
.sessionId(sessionId)
|
||||
.stepId(10L)
|
||||
.toolName("lookup_knowledge")
|
||||
.inputParams("{\"query\":\"ERR_TIMEOUT\"}")
|
||||
.outputPreview("payment timeout doc")
|
||||
.outputLength(19)
|
||||
.retrievalLayer("L0")
|
||||
.l0MatchCount(1)
|
||||
.l1MatchCount(0)
|
||||
.isTruncated(false)
|
||||
.relevanceLevel("HIGHLY_RELEVANT")
|
||||
.dedupReason("FIRST_HIT")
|
||||
.retrievalDetails("{\"documents\":[\"payment-errors.md\"]}")
|
||||
.durationMs(80)
|
||||
.success(true)
|
||||
.createdAt(now)
|
||||
.build();
|
||||
|
||||
when(diagnosisSessionRepository.findBySessionId(sessionId)).thenReturn(Optional.of(session));
|
||||
when(agentStepRepository.findBySessionIdOrderByStepIndex(sessionId)).thenReturn(List.of(step));
|
||||
when(toolInvocationRepository.findBySessionIdOrderByIdAsc(sessionId)).thenReturn(List.of(invocation));
|
||||
|
||||
DiagnosisTraceResponse response = service.getTrace(sessionId);
|
||||
|
||||
assertEquals(sessionId, response.getSession().getSessionId());
|
||||
assertEquals("payment timeout", response.getSession().getQuery());
|
||||
assertEquals("PASS", ((java.util.Map<?, ?>) response.getSession()
|
||||
.getSelfEvaluation()
|
||||
.get("verifier_evaluation")).get("verdict"));
|
||||
assertEquals(1, response.getSteps().size());
|
||||
assertEquals("chat_executor", response.getSteps().get(0).getAgentName());
|
||||
assertEquals(1, response.getToolInvocations().size());
|
||||
assertEquals("ERR_TIMEOUT", response.getToolInvocations().get(0).getInputParams().get("query"));
|
||||
assertEquals(2, response.getSummary().getPersistedStepCount());
|
||||
assertEquals(1, response.getSummary().getReturnedStepCount());
|
||||
assertEquals(1, response.getSummary().getPersistedToolCallCount());
|
||||
assertEquals(1, response.getSummary().getReturnedToolCallCount());
|
||||
assertTrue(response.getSummary().isHasVerifierEvaluation());
|
||||
assertTrue(response.getSummary().isHasFeedback());
|
||||
}
|
||||
|
||||
@Test
|
||||
void getTraceThrowsWhenSessionMissing() {
|
||||
String sessionId = "missing-session";
|
||||
when(diagnosisSessionRepository.findBySessionId(sessionId)).thenReturn(Optional.empty());
|
||||
|
||||
assertThrows(SessionNotFoundException.class, () -> service.getTrace(sessionId));
|
||||
|
||||
verify(diagnosisSessionRepository).findBySessionId(sessionId);
|
||||
verifyNoInteractions(agentStepRepository, toolInvocationRepository);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user