Files
SuperBizAgent-java/mvp/eval/cases/diagnosis-cases.json
T

199 lines
8.4 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
[
{
"id": "narrow-highcpu-observation",
"title": "Narrow HighCPU observation",
"question": "确认 payment-service 当前是否存在 HighCPUUsage 告警。",
"traceFixture": "narrow-highcpu-observation-pass.json",
"expectedRootCauseKeywords": ["payment-service", "HighCPUUsage", "92%"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_metrics"],
"allowedVerdicts": ["PASS"],
"forbiddenAnswerKeywords": ["根因", "修复建议", "通常情况下"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["数据库连接池"]
},
{
"id": "prompt-gatekeeper-audit-closure",
"title": "Prompt and Gatekeeper audit closure",
"question": "确认 payment-service 当前是否存在 HighCPUUsage 告警,并检查审计元数据是否完整。",
"traceFixture": "prompt-gatekeeper-audit-closure-pass.json",
"expectedRootCauseKeywords": ["payment-service", "HighCPUUsage", "92%"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_metrics"],
"allowedVerdicts": ["PASS"],
"forbiddenAnswerKeywords": ["根因", "修复建议", "通常情况下"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["数据库连接池"],
"requirePromptAudit": true,
"expectedPromptAuditVersion": "chat-prompts-v1",
"expectedPromptVersions": {
"chat_planner": "chat-planner-v1",
"chat_executor": "chat-executor-v2",
"chat_verifier": "chat-verifier-v2",
"chat_composer": "chat-composer-v1"
},
"requireGatekeeperRules": true
},
{
"id": "hikari-no-evidence-negative-observation",
"title": "Hikari no-evidence negative observation",
"question": "确认 inventory-service 当前是否有 HikariCP 连接池耗尽日志。",
"traceFixture": "hikari-no-evidence-negative-observation-pass.json",
"expectedRootCauseKeywords": ["未检索到", "HikariCP", "匹配证据"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_logs"],
"allowedVerdicts": ["PASS"],
"forbiddenAnswerKeywords": ["已排除", "确认没有", "日志层面已排除"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["已排除 HikariCP"]
},
{
"id": "payment-timeout",
"title": "Payment API timeout",
"question": "支付接口最近出现超时,请结合知识库、日志和指标判断可能原因,并给出修复建议。",
"traceFixture": "payment-timeout-pass.json",
"expectedRootCauseKeywords": ["支付", "超时", "连接池"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["lookup_knowledge", "query_logs", "query_metrics"],
"allowedVerdicts": ["PASS", "LOW_CONFID"],
"forbiddenAnswerKeywords": ["无证据确定"]
},
{
"id": "mysql-pool-exhausted",
"title": "MySQL connection pool exhausted",
"question": "订单服务大量请求超时,请判断是否和 MySQL 连接池有关。",
"traceFixture": "mysql-pool-low-confid.json",
"expectedRootCauseKeywords": ["mysql", "连接池", "超时"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["lookup_knowledge", "query_logs"],
"allowedVerdicts": ["LOW_CONFID", "PASS"],
"forbiddenAnswerKeywords": ["已经完全确认"]
},
{
"id": "redis-timeout",
"title": "Redis timeout",
"question": "支付服务出现 Redis 连接超时,请定位可能原因。",
"traceFixture": "redis-timeout-low-confid.json",
"expectedRootCauseKeywords": ["redis", "超时"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_logs"],
"allowedVerdicts": ["LOW_CONFID", "PASS"],
"forbiddenAnswerKeywords": ["无需进一步排查"]
},
{
"id": "slow-response",
"title": "Slow response",
"question": "用户服务 P99 响应时间升高,请结合指标和日志分析。",
"traceFixture": "slow-response-pass.json",
"expectedRootCauseKeywords": ["p99", "慢响应"],
"minKeywordMatches": 1,
"requiredEvidenceTools": ["query_metrics", "query_logs"],
"allowedVerdicts": ["LOW_CONFID", "PASS"],
"forbiddenAnswerKeywords": ["没有风险"]
},
{
"id": "jvm-memory-risk",
"title": "JVM memory risk",
"question": "订单服务内存使用率过高,请判断是否存在 OOM 风险。",
"traceFixture": "jvm-memory-risk-low-confid.json",
"expectedRootCauseKeywords": ["jvm", "内存", "oom"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_metrics", "query_logs"],
"allowedVerdicts": ["LOW_CONFID", "PASS"],
"forbiddenAnswerKeywords": ["可以忽略"]
},
{
"id": "gatekeeper-fabricated-invocation",
"title": "Gatekeeper fabricated invocation",
"question": "支付失败是否能确认由日志中的连接池耗尽导致?",
"traceFixture": "gatekeeper-fabricated-invocation-reject.json",
"expectedRootCauseKeywords": ["证据", "引用", "失败"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_logs"],
"allowedVerdicts": ["REJECT", "LOW_CONFID"],
"forbiddenAnswerKeywords": ["已经完全确认"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["fail"],
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["连接池耗尽导致支付失败"]
},
{
"id": "unsupported-claim-filtering",
"title": "Unsupported claim filtering",
"question": "订单超时是否可以确认由数据库主库故障导致?",
"traceFixture": "unsupported-claim-filtering-low-confid.json",
"expectedRootCauseKeywords": ["超时", "证据"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_logs"],
"allowedVerdicts": ["LOW_CONFID"],
"forbiddenAnswerKeywords": ["已经确认"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["主库故障"]
},
{
"id": "audit-metadata-low-confid",
"title": "Audit metadata low confidence",
"question": "订单超时是否可以确认由数据库主库故障导致,并检查审计元数据是否完整?",
"traceFixture": "audit-metadata-low-confid.json",
"expectedRootCauseKeywords": ["超时", "证据"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_logs"],
"allowedVerdicts": ["LOW_CONFID"],
"forbiddenAnswerKeywords": ["已经确认"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedGatekeeperRuleSetVersion": "gatekeeper-rules-v1",
"expectedComposerStatuses": ["valid"],
"forbiddenConfirmedClaimKeywords": ["主库故障"],
"requirePromptAudit": true,
"expectedPromptAuditVersion": "chat-prompts-v1",
"expectedPromptVersions": {
"chat_planner": "chat-planner-v1",
"chat_executor": "chat-executor-v2",
"chat_verifier": "chat-verifier-v2",
"chat_composer": "chat-composer-v1"
},
"requireGatekeeperRules": true
},
{
"id": "composer-fallback-no-raw-json",
"title": "Composer fallback no raw JSON",
"question": "库存服务慢响应是否可以直接输出 Executor JSON?",
"traceFixture": "composer-fallback-no-raw-json-low-confid.json",
"expectedRootCauseKeywords": ["慢响应", "证据"],
"minKeywordMatches": 2,
"requiredEvidenceTools": ["query_metrics"],
"allowedVerdicts": ["LOW_CONFID"],
"forbiddenAnswerKeywords": ["executor_evidence_v2", "answer_version", "claim_id"],
"requireV2AuditClosure": true,
"requireClaimChecks": true,
"requireComposerOutput": true,
"expectedGatekeeperStatuses": ["pass"],
"expectedComposerStatuses": ["composer_malformed"],
"forbiddenConfirmedClaimKeywords": ["线程池已经耗尽"]
}
]