fix(agent): harden live diagnosis skill observability
This commit is contained in:
@@ -62,6 +62,7 @@ class ToolTraceSummaryServiceTest {
|
||||
assertEquals("direct", logsSummary.get("evidence_level"));
|
||||
assertEquals(2, logsSummary.get("invocation_count"));
|
||||
assertEquals(1, logsSummary.get("no_hit_invocation_count"));
|
||||
assertTrue(String.valueOf(logsSummary.get("output_summary")).contains("payment timeout stack trace"));
|
||||
|
||||
Map<String, Object> metricsSummary = summaries.stream()
|
||||
.filter(item -> "query_metrics".equals(item.get("tool_name")))
|
||||
@@ -72,4 +73,111 @@ class ToolTraceSummaryServiceTest {
|
||||
assertEquals(1, metricsSummary.get("failed_invocation_count"));
|
||||
assertTrue(String.valueOf(metricsSummary.get("output_summary")).contains("call failed"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildVerifierTraceSummaryPreservesConcreteFactsFromTruncatedLogAndMetricRows() {
|
||||
ToolInvocationRepository repository = mock(ToolInvocationRepository.class);
|
||||
String logPreview = """
|
||||
{
|
||||
"success" : true,
|
||||
"logs" : [ {
|
||||
"timestamp" : "2026-07-06 22:15:45",
|
||||
"level" : "ERROR",
|
||||
"service" : "order-service",
|
||||
"message" : "数据库连接池耗尽: Cannot acquire connection from pool, active: 50/50, waiting: 23, timeout: 30000ms"
|
||||
} ]
|
||||
}
|
||||
""";
|
||||
String metricPreview = """
|
||||
{
|
||||
"success" : true,
|
||||
"alerts" : [ {
|
||||
"alert_name" : "HighCPUUsage",
|
||||
"service" : "payment-service",
|
||||
"description" : "服务 payment-service 的 CPU 使用率持续超过 80%,当前值为 92%。"
|
||||
} ]
|
||||
}
|
||||
""";
|
||||
when(repository.findBySessionIdOrderByIdAsc("session-2")).thenReturn(List.of(
|
||||
ToolInvocation.builder()
|
||||
.id(10L)
|
||||
.sessionId("session-2")
|
||||
.toolName("query_logs")
|
||||
.inputParams("{\"query\":\"pool\"}")
|
||||
.outputPreview(logPreview)
|
||||
.retrievalDetails("{\"retrieved_domains\":[\"application-logs\"],\"evidence_status\":\"supported\"}")
|
||||
.isTruncated(true)
|
||||
.success(true)
|
||||
.build(),
|
||||
ToolInvocation.builder()
|
||||
.id(11L)
|
||||
.sessionId("session-2")
|
||||
.toolName("query_metrics")
|
||||
.inputParams("{\"query\":\"active_prometheus_alerts\"}")
|
||||
.outputPreview(metricPreview)
|
||||
.retrievalDetails("{\"retrieved_domains\":[\"prometheus_alerts\"],\"evidence_status\":\"supported\"}")
|
||||
.isTruncated(true)
|
||||
.success(true)
|
||||
.build()
|
||||
));
|
||||
|
||||
ToolTraceSummaryService service = new ToolTraceSummaryService(repository);
|
||||
|
||||
List<Map<String, Object>> summaries = service.buildVerifierTraceSummary("session-2", "连接池耗尽 HighCPUUsage");
|
||||
|
||||
Map<String, Object> logsSummary = summaries.stream()
|
||||
.filter(item -> "query_logs".equals(item.get("tool_name")))
|
||||
.findFirst()
|
||||
.orElseThrow();
|
||||
assertTrue(String.valueOf(logsSummary.get("output_summary")).contains("连接池耗尽"));
|
||||
assertTrue(String.valueOf(logsSummary.get("output_summary")).contains("active: 50/50"));
|
||||
assertEquals(List.of(10L), logsSummary.get("source_invocation_ids"));
|
||||
|
||||
Map<String, Object> metricsSummary = summaries.stream()
|
||||
.filter(item -> "query_metrics".equals(item.get("tool_name")))
|
||||
.findFirst()
|
||||
.orElseThrow();
|
||||
assertTrue(String.valueOf(metricsSummary.get("output_summary")).contains("HighCPUUsage"));
|
||||
assertTrue(String.valueOf(metricsSummary.get("output_summary")).contains("payment-service"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void buildVerifierTraceSummaryDoesNotTreatGenericMockLogsAsDirectEvidence() {
|
||||
ToolInvocationRepository repository = mock(ToolInvocationRepository.class);
|
||||
String genericLogPreview = """
|
||||
{
|
||||
"success" : true,
|
||||
"logs" : [ {
|
||||
"timestamp" : "2026-07-06 23:44:41",
|
||||
"level" : "ERROR",
|
||||
"service" : "generic-service",
|
||||
"message" : "日志消息 #0, 查询条件: service:payment-service"
|
||||
} ]
|
||||
}
|
||||
""";
|
||||
when(repository.findBySessionIdOrderByIdAsc("session-3")).thenReturn(List.of(
|
||||
ToolInvocation.builder()
|
||||
.id(20L)
|
||||
.sessionId("session-3")
|
||||
.toolName("query_logs")
|
||||
.inputParams("{\"query\":\"service:payment-service\"}")
|
||||
.outputPreview(genericLogPreview)
|
||||
.retrievalDetails("{\"retrieved_domains\":[\"system-metrics\"],\"evidence_status\":\"supported\"}")
|
||||
.success(true)
|
||||
.build()
|
||||
));
|
||||
|
||||
ToolTraceSummaryService service = new ToolTraceSummaryService(repository);
|
||||
|
||||
List<Map<String, Object>> summaries = service.buildVerifierTraceSummary("session-3", "payment-service timeout");
|
||||
|
||||
Map<String, Object> logsSummary = summaries.stream()
|
||||
.filter(item -> "query_logs".equals(item.get("tool_name")))
|
||||
.findFirst()
|
||||
.orElseThrow();
|
||||
assertEquals(Boolean.FALSE, logsSummary.get("success"));
|
||||
assertEquals("none", logsSummary.get("evidence_level"));
|
||||
assertEquals(1, logsSummary.get("no_hit_invocation_count"));
|
||||
assertTrue(String.valueOf(logsSummary.get("output_summary")).contains("日志消息 #0"));
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user