feat(demo): add interview quality audit
This commit is contained in:
@@ -1,28 +1,30 @@
|
||||
# Diagnosis Eval Report
|
||||
|
||||
- Total cases: 10
|
||||
- Passed cases: 10
|
||||
- Total cases: 12
|
||||
- Passed cases: 12
|
||||
- Pass rate: 100.00%
|
||||
- Average tool calls: 1.50
|
||||
- Average duration ms: 39800.00
|
||||
- Average tool calls: 1.42
|
||||
- Average duration ms: 38500.00
|
||||
|
||||
## Verdict Distribution
|
||||
|
||||
- PASS: 4
|
||||
- LOW_CONFID: 5
|
||||
- PASS: 5
|
||||
- LOW_CONFID: 6
|
||||
- REJECT: 1
|
||||
|
||||
## Cases
|
||||
|
||||
| Case | Result | Verdict | Gatekeeper | Rule Set | Composer | Claim Checks | Keywords | Tool Calls | Duration ms | Failed Checks |
|
||||
| --- | --- | --- | --- | --- | --- | ---: | --- | ---: | ---: | --- |
|
||||
| narrow-highcpu-observation | PASS | PASS | pass | gatekeeper-rules-v1 | valid | 1 | 3/3 | 1 | 18000 | - |
|
||||
| hikari-no-evidence-negative-observation | PASS | PASS | pass | gatekeeper-rules-v1 | valid | 1 | 3/3 | 1 | 21000 | - |
|
||||
| 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 | - |
|
||||
| Case | Result | Verdict | Gatekeeper | Rule Set | Prompt Audit | Composer | Claim Checks | Rules | Keywords | Tool Calls | Duration ms | Failed Checks |
|
||||
| --- | --- | --- | --- | --- | --- | --- | ---: | ---: | --- | ---: | ---: | --- |
|
||||
| narrow-highcpu-observation | PASS | PASS | pass | gatekeeper-rules-v1 | - | valid | 1 | 1 | 3/3 | 1 | 18000 | - |
|
||||
| prompt-gatekeeper-audit-closure | PASS | PASS | pass | gatekeeper-rules-v1 | chat-prompts-v1 | valid | 1 | 2 | 3/3 | 1 | 19000 | - |
|
||||
| hikari-no-evidence-negative-observation | PASS | PASS | pass | gatekeeper-rules-v1 | - | valid | 1 | 1 | 3/3 | 1 | 21000 | - |
|
||||
| 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 | - |
|
||||
| audit-metadata-low-confid | PASS | LOW_CONFID | pass | gatekeeper-rules-v1 | chat-prompts-v1 | valid | 2 | 2 | 2/2 | 1 | 45000 | - |
|
||||
| composer-fallback-no-raw-json | PASS | LOW_CONFID | pass | - | - | composer_malformed | 2 | - | 2/2 | 1 | 47000 | - |
|
||||
|
||||
Reference in New Issue
Block a user