Expand diagnosis eval fixtures
This commit is contained in:
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"totalCases" : 5,
|
||||
"passedCases" : 5,
|
||||
"passRate" : 1.0,
|
||||
"verdictDistribution" : {
|
||||
"PASS" : 2,
|
||||
"LOW_CONFID" : 3
|
||||
},
|
||||
"averageToolCallCount" : 2.0,
|
||||
"averageDurationMs" : 45800.0,
|
||||
"results" : [ {
|
||||
"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
|
||||
},
|
||||
"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
|
||||
},
|
||||
"toolCallCount" : 2,
|
||||
"durationMs" : 51000
|
||||
}, {
|
||||
"caseId" : "redis-timeout",
|
||||
"title" : "Redis timeout",
|
||||
"passed" : true,
|
||||
"failedChecks" : [ ],
|
||||
"verdict" : "LOW_CONFID",
|
||||
"matchedKeywordCount" : 2,
|
||||
"requiredKeywordCount" : 2,
|
||||
"evidenceCoverage" : {
|
||||
"query_logs" : true
|
||||
},
|
||||
"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
|
||||
},
|
||||
"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
|
||||
},
|
||||
"toolCallCount" : 2,
|
||||
"durationMs" : 53000
|
||||
} ]
|
||||
}
|
||||
@@ -0,0 +1,22 @@
|
||||
# Diagnosis Eval Report
|
||||
|
||||
- Total cases: 5
|
||||
- Passed cases: 5
|
||||
- Pass rate: 100.00%
|
||||
- Average tool calls: 2.00
|
||||
- Average duration ms: 45800.00
|
||||
|
||||
## Verdict Distribution
|
||||
|
||||
- PASS: 2
|
||||
- LOW_CONFID: 3
|
||||
|
||||
## Cases
|
||||
|
||||
| Case | Result | Verdict | Keywords | Tool Calls | Duration ms | Failed Checks |
|
||||
| --- | --- | --- | --- | ---: | ---: | --- |
|
||||
| payment-timeout | PASS | PASS | 3/3 | 3 | 42000 | - |
|
||||
| mysql-pool-exhausted | PASS | LOW_CONFID | 3/3 | 2 | 51000 | - |
|
||||
| redis-timeout | PASS | LOW_CONFID | 2/2 | 1 | 36000 | - |
|
||||
| slow-response | PASS | PASS | 2/2 | 2 | 47000 | - |
|
||||
| jvm-memory-risk | PASS | LOW_CONFID | 3/3 | 2 | 53000 | - |
|
||||
Reference in New Issue
Block a user