feat(eval): add executor audit closure checks
This commit is contained in:
@@ -1,13 +1,14 @@
|
||||
{
|
||||
"totalCases" : 5,
|
||||
"passedCases" : 5,
|
||||
"totalCases" : 8,
|
||||
"passedCases" : 8,
|
||||
"passRate" : 1.0,
|
||||
"verdictDistribution" : {
|
||||
"PASS" : 2,
|
||||
"LOW_CONFID" : 3
|
||||
"LOW_CONFID" : 5,
|
||||
"REJECT" : 1
|
||||
},
|
||||
"averageToolCallCount" : 2.0,
|
||||
"averageDurationMs" : 45800.0,
|
||||
"averageToolCallCount" : 1.625,
|
||||
"averageDurationMs" : 44875.0,
|
||||
"results" : [ {
|
||||
"caseId" : "payment-timeout",
|
||||
"title" : "Payment API timeout",
|
||||
@@ -21,6 +22,9 @@
|
||||
"query_logs" : true,
|
||||
"query_metrics" : true
|
||||
},
|
||||
"gatekeeperStatus" : null,
|
||||
"composerStatus" : null,
|
||||
"claimCheckCount" : null,
|
||||
"toolCallCount" : 3,
|
||||
"durationMs" : 42000
|
||||
}, {
|
||||
@@ -35,6 +39,9 @@
|
||||
"lookup_knowledge" : true,
|
||||
"query_logs" : true
|
||||
},
|
||||
"gatekeeperStatus" : null,
|
||||
"composerStatus" : null,
|
||||
"claimCheckCount" : null,
|
||||
"toolCallCount" : 2,
|
||||
"durationMs" : 51000
|
||||
}, {
|
||||
@@ -48,6 +55,9 @@
|
||||
"evidenceCoverage" : {
|
||||
"query_logs" : true
|
||||
},
|
||||
"gatekeeperStatus" : null,
|
||||
"composerStatus" : null,
|
||||
"claimCheckCount" : null,
|
||||
"toolCallCount" : 1,
|
||||
"durationMs" : 36000
|
||||
}, {
|
||||
@@ -62,6 +72,9 @@
|
||||
"query_metrics" : true,
|
||||
"query_logs" : true
|
||||
},
|
||||
"gatekeeperStatus" : null,
|
||||
"composerStatus" : null,
|
||||
"claimCheckCount" : null,
|
||||
"toolCallCount" : 2,
|
||||
"durationMs" : 47000
|
||||
}, {
|
||||
@@ -76,7 +89,58 @@
|
||||
"query_metrics" : true,
|
||||
"query_logs" : true
|
||||
},
|
||||
"gatekeeperStatus" : null,
|
||||
"composerStatus" : null,
|
||||
"claimCheckCount" : 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",
|
||||
"composerStatus" : "valid",
|
||||
"claimCheckCount" : 1,
|
||||
"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",
|
||||
"composerStatus" : "valid",
|
||||
"claimCheckCount" : 2,
|
||||
"toolCallCount" : 1,
|
||||
"durationMs" : 44000
|
||||
}, {
|
||||
"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",
|
||||
"composerStatus" : "composer_malformed",
|
||||
"claimCheckCount" : 2,
|
||||
"toolCallCount" : 1,
|
||||
"durationMs" : 47000
|
||||
} ]
|
||||
}
|
||||
|
||||
@@ -1,22 +1,26 @@
|
||||
# Diagnosis Eval Report
|
||||
|
||||
- Total cases: 5
|
||||
- Passed cases: 5
|
||||
- Total cases: 8
|
||||
- Passed cases: 8
|
||||
- Pass rate: 100.00%
|
||||
- Average tool calls: 2.00
|
||||
- Average duration ms: 45800.00
|
||||
- Average tool calls: 1.63
|
||||
- Average duration ms: 44875.00
|
||||
|
||||
## Verdict Distribution
|
||||
|
||||
- PASS: 2
|
||||
- LOW_CONFID: 3
|
||||
- LOW_CONFID: 5
|
||||
- REJECT: 1
|
||||
|
||||
## 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 | - |
|
||||
| Case | Result | Verdict | Gatekeeper | Composer | Claim Checks | 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 | - |
|
||||
| gatekeeper-fabricated-invocation | PASS | REJECT | fail | valid | 1 | 3/3 | 1 | 39000 | - |
|
||||
| unsupported-claim-filtering | PASS | LOW_CONFID | pass | valid | 2 | 2/2 | 1 | 44000 | - |
|
||||
| composer-fallback-no-raw-json | PASS | LOW_CONFID | pass | composer_malformed | 2 | 2/2 | 1 | 47000 | - |
|
||||
|
||||
Reference in New Issue
Block a user