Skip to content

FailureAnalysis

reference
1 min readUpdated

Kind: Interface

Source: atloria-monorepo/libs/agent-core/src/benchmark/benchmark-monitor.ts

Properties

PropertyType
totalTasksnumber
passednumber
failednumber
timedOutnumber
passRatenumber
byCategoryRecord<string, number>
correctAreaButFailedTaskResult[]
noChangesTaskResult[]
timedOutWithChangesTaskResult[]
patternsFailurePattern[]
toolComparison`{
passing: Record<string, number>;
failing: Record<string, number>;

}| |avgTurns|{ passing: number; failing: number }| |summary|string` |

Was this page helpful?

Download as PDF