Add diagnosis eval baseline diff
This commit is contained in:
@@ -0,0 +1,85 @@
|
||||
{
|
||||
"baselineTotalCases" : 5,
|
||||
"currentTotalCases" : 5,
|
||||
"baselinePassedCases" : 5,
|
||||
"currentPassedCases" : 4,
|
||||
"baselinePassRate" : 1.0,
|
||||
"currentPassRate" : 0.8,
|
||||
"regressionCount" : 6,
|
||||
"improvementCount" : 0,
|
||||
"changedCount" : 2,
|
||||
"hasRegression" : true,
|
||||
"items" : [ {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "aggregate",
|
||||
"caseId" : null,
|
||||
"metric" : "passRate",
|
||||
"baselineValue" : "1.0",
|
||||
"currentValue" : "0.8",
|
||||
"delta" : -0.19999999999999996,
|
||||
"message" : "passRate changed"
|
||||
}, {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "aggregate",
|
||||
"caseId" : null,
|
||||
"metric" : "averageToolCallCount",
|
||||
"baselineValue" : "2.0",
|
||||
"currentValue" : "3.0",
|
||||
"delta" : 1.0,
|
||||
"message" : "averageToolCallCount changed"
|
||||
}, {
|
||||
"type" : "CHANGED",
|
||||
"scope" : "aggregate",
|
||||
"caseId" : null,
|
||||
"metric" : "verdictDistribution.LOW_CONFID",
|
||||
"baselineValue" : "3",
|
||||
"currentValue" : "2",
|
||||
"delta" : -1.0,
|
||||
"message" : "verdict count changed for LOW_CONFID"
|
||||
}, {
|
||||
"type" : "CHANGED",
|
||||
"scope" : "aggregate",
|
||||
"caseId" : null,
|
||||
"metric" : "verdictDistribution.REJECT",
|
||||
"baselineValue" : "0",
|
||||
"currentValue" : "1",
|
||||
"delta" : 1.0,
|
||||
"message" : "verdict count changed for REJECT"
|
||||
}, {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "case",
|
||||
"caseId" : "redis-timeout",
|
||||
"metric" : "passed",
|
||||
"baselineValue" : "true",
|
||||
"currentValue" : "false",
|
||||
"delta" : null,
|
||||
"message" : "redis-timeout pass state changed"
|
||||
}, {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "case",
|
||||
"caseId" : "redis-timeout",
|
||||
"metric" : "verdict",
|
||||
"baselineValue" : "LOW_CONFID",
|
||||
"currentValue" : "REJECT",
|
||||
"delta" : -1.0,
|
||||
"message" : "redis-timeout verdict changed"
|
||||
}, {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "case",
|
||||
"caseId" : "redis-timeout",
|
||||
"metric" : "matchedKeywordCount",
|
||||
"baselineValue" : "2",
|
||||
"currentValue" : "1",
|
||||
"delta" : -1.0,
|
||||
"message" : "redis-timeout matchedKeywordCount changed"
|
||||
}, {
|
||||
"type" : "REGRESSION",
|
||||
"scope" : "case",
|
||||
"caseId" : "redis-timeout",
|
||||
"metric" : "evidenceCoverage.query_logs",
|
||||
"baselineValue" : "true",
|
||||
"currentValue" : "false",
|
||||
"delta" : null,
|
||||
"message" : "redis-timeout evidence coverage changed for query_logs"
|
||||
} ]
|
||||
}
|
||||
Reference in New Issue
Block a user