Files
SuperBizAgent-java/mvp/eval/reports/baseline-report.json

246 lines
6.8 KiB
JSON

{
"totalCases" : 12,
"passedCases" : 12,
"passRate" : 1.0,
"verdictDistribution" : {
"PASS" : 5,
"LOW_CONFID" : 6,
"REJECT" : 1
},
"averageToolCallCount" : 1.4166666666666667,
"averageDurationMs" : 38500.0,
"results" : [ {
"caseId" : "narrow-highcpu-observation",
"title" : "Narrow HighCPU observation",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "PASS",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"query_metrics" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
"promptAuditVersion" : null,
"composerStatus" : "valid",
"claimCheckCount" : 1,
"gatekeeperRuleCount" : 1,
"toolCallCount" : 1,
"durationMs" : 18000
}, {
"caseId" : "prompt-gatekeeper-audit-closure",
"title" : "Prompt and Gatekeeper audit closure",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "PASS",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"query_metrics" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
"promptAuditVersion" : "chat-prompts-v1",
"composerStatus" : "valid",
"claimCheckCount" : 1,
"gatekeeperRuleCount" : 2,
"toolCallCount" : 1,
"durationMs" : 19000
}, {
"caseId" : "hikari-no-evidence-negative-observation",
"title" : "Hikari no-evidence negative observation",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "PASS",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"query_logs" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
"promptAuditVersion" : null,
"composerStatus" : "valid",
"claimCheckCount" : 1,
"gatekeeperRuleCount" : 1,
"toolCallCount" : 1,
"durationMs" : 21000
}, {
"caseId" : "payment-timeout",
"title" : "Payment API timeout",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "PASS",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"lookup_knowledge" : true,
"query_logs" : true,
"query_metrics" : true
},
"gatekeeperStatus" : null,
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : null,
"claimCheckCount" : null,
"gatekeeperRuleCount" : null,
"toolCallCount" : 3,
"durationMs" : 42000
}, {
"caseId" : "mysql-pool-exhausted",
"title" : "MySQL connection pool exhausted",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"lookup_knowledge" : true,
"query_logs" : true
},
"gatekeeperStatus" : null,
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : null,
"claimCheckCount" : null,
"gatekeeperRuleCount" : null,
"toolCallCount" : 2,
"durationMs" : 51000
}, {
"caseId" : "redis-timeout",
"title" : "Redis timeout",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 2,
"requiredKeywordCount" : 2,
"evidenceCoverage" : {
"query_logs" : true
},
"gatekeeperStatus" : null,
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : null,
"claimCheckCount" : null,
"gatekeeperRuleCount" : null,
"toolCallCount" : 1,
"durationMs" : 36000
}, {
"caseId" : "slow-response",
"title" : "Slow response",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "PASS",
"matchedKeywordCount" : 2,
"requiredKeywordCount" : 2,
"evidenceCoverage" : {
"query_metrics" : true,
"query_logs" : true
},
"gatekeeperStatus" : null,
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : null,
"claimCheckCount" : null,
"gatekeeperRuleCount" : null,
"toolCallCount" : 2,
"durationMs" : 47000
}, {
"caseId" : "jvm-memory-risk",
"title" : "JVM memory risk",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"query_metrics" : true,
"query_logs" : true
},
"gatekeeperStatus" : null,
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : null,
"claimCheckCount" : null,
"gatekeeperRuleCount" : null,
"toolCallCount" : 2,
"durationMs" : 53000
}, {
"caseId" : "gatekeeper-fabricated-invocation",
"title" : "Gatekeeper fabricated invocation",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "REJECT",
"matchedKeywordCount" : 3,
"requiredKeywordCount" : 3,
"evidenceCoverage" : {
"query_logs" : true
},
"gatekeeperStatus" : "fail",
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : "valid",
"claimCheckCount" : 1,
"gatekeeperRuleCount" : null,
"toolCallCount" : 1,
"durationMs" : 39000
}, {
"caseId" : "unsupported-claim-filtering",
"title" : "Unsupported claim filtering",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 2,
"requiredKeywordCount" : 2,
"evidenceCoverage" : {
"query_logs" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : "valid",
"claimCheckCount" : 2,
"gatekeeperRuleCount" : null,
"toolCallCount" : 1,
"durationMs" : 44000
}, {
"caseId" : "audit-metadata-low-confid",
"title" : "Audit metadata low confidence",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 2,
"requiredKeywordCount" : 2,
"evidenceCoverage" : {
"query_logs" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : "gatekeeper-rules-v1",
"promptAuditVersion" : "chat-prompts-v1",
"composerStatus" : "valid",
"claimCheckCount" : 2,
"gatekeeperRuleCount" : 2,
"toolCallCount" : 1,
"durationMs" : 45000
}, {
"caseId" : "composer-fallback-no-raw-json",
"title" : "Composer fallback no raw JSON",
"passed" : true,
"failedChecks" : [ ],
"verdict" : "LOW_CONFID",
"matchedKeywordCount" : 2,
"requiredKeywordCount" : 2,
"evidenceCoverage" : {
"query_metrics" : true
},
"gatekeeperStatus" : "pass",
"gatekeeperRuleSetVersion" : null,
"promptAuditVersion" : null,
"composerStatus" : "composer_malformed",
"claimCheckCount" : 2,
"gatekeeperRuleCount" : null,
"toolCallCount" : 1,
"durationMs" : 47000
} ]
}