Interface: FormalJudgeRequest
@kortexya/reasoninglayer / FormalJudgeRequest
Interface: FormalJudgeRequest
Section titled “Interface: FormalJudgeRequest”Defined in: src/types/oversight.ts:42
Request to run the FormalJudge oversight pipeline.
Properties
Section titled “Properties”config?
Section titled “config?”
optionalconfig?:JudgeConfigDto|null
Defined in: src/types/oversight.ts:52
Optional pipeline configuration overrides.
executionLog?
Section titled “executionLog?”
optionalexecutionLog?:string
Defined in: src/types/oversight.ts:50
Raw execution log (for full provenance).
finalOutput?
Section titled “finalOutput?”
optionalfinalOutput?:string
Defined in: src/types/oversight.ts:48
Agent’s final output/answer.
riskCategories?
Section titled “riskCategories?”
optionalriskCategories?:string[]
Defined in: src/types/oversight.ts:59
Risk categories from the benchmark dataset (e.g.,
["Lead to property loss", "Violate laws"]). Used by the
3-agent per-task decomposition pipeline to generate
task-specific atomic conditions.
trajectory
Section titled “trajectory”trajectory:
TrajectoryStepDto[]
Defined in: src/types/oversight.ts:46
Agent execution trajectory (ordered list of tool calls + results).
userIntent
Section titled “userIntent”userIntent:
string
Defined in: src/types/oversight.ts:44
User instruction (what the agent was asked to do).