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"
|
||||
} ]
|
||||
}
|
||||
@@ -0,0 +1,22 @@
|
||||
# Diagnosis Eval Baseline Diff
|
||||
|
||||
- Baseline pass rate: 100.00%
|
||||
- Current pass rate: 80.00%
|
||||
- Baseline passed cases: 5/5
|
||||
- Current passed cases: 4/5
|
||||
- Regressions: 6
|
||||
- Improvements: 0
|
||||
- Other changes: 2
|
||||
|
||||
## Diff Items
|
||||
|
||||
| Type | Scope | Case | Metric | Baseline | Current | Delta | Message |
|
||||
| --- | --- | --- | --- | --- | --- | ---: | --- |
|
||||
| REGRESSION | aggregate | - | passRate | 1.0 | 0.8 | -0.200 | passRate changed |
|
||||
| REGRESSION | aggregate | - | averageToolCallCount | 2.0 | 3.0 | 1.000 | averageToolCallCount changed |
|
||||
| CHANGED | aggregate | - | verdictDistribution.LOW_CONFID | 3 | 2 | -1.000 | verdict count changed for LOW_CONFID |
|
||||
| CHANGED | aggregate | - | verdictDistribution.REJECT | 0 | 1 | 1.000 | verdict count changed for REJECT |
|
||||
| REGRESSION | case | redis-timeout | passed | true | false | - | redis-timeout pass state changed |
|
||||
| REGRESSION | case | redis-timeout | verdict | LOW_CONFID | REJECT | -1.000 | redis-timeout verdict changed |
|
||||
| REGRESSION | case | redis-timeout | matchedKeywordCount | 2 | 1 | -1.000 | redis-timeout matchedKeywordCount changed |
|
||||
| REGRESSION | case | redis-timeout | evidenceCoverage.query_logs | true | false | - | redis-timeout evidence coverage changed for query_logs |
|
||||
Reference in New Issue
Block a user