The cell.
Optionalfailover?: booleanOptionalinputPricePer1M?: numberUSD per million input tokens, for the cost estimate only.
Names the cell. It becomes the bracketed part of every record's name.
OptionalmodelId?: stringOptionaloutputPricePer1M?: numberUSD per million output tokens, for the cost estimate only.
OptionalpromptName?: stringOptionalseed?: numberOptionaltemperature?: numberOptionalvendorId?: stringWhich decision builder. A discovery test has its own schema (DiscoveryEvalConfigSchema).
Optionalfailover?: boolean | nullWhether the runner may fail over. Defaults to false when the cell pins a model or vendor.
OptionalmodelId?: string | nullPins the MJ: AI Models row that must answer.
The oracles to run.
OptionalpromptName?: string | nullThe decision prompt. Defaults to DEFAULT_DECISION_PROMPT_NAME.
Optionalseed?: number | nullRequested sampling seed. Recorded; see the driver for whether it reaches the model.
production sends BuildRoutingState; structured sends BuildRoutingStateStructured.
Optionaltemperature?: number | nullRequested sampling temperature. Recorded; see the driver for whether it reaches the model.
OptionalvendorId?: string | nullPins the vendor.
A cell's test
Configuration. Thedecision-label-matchoracle scores thecontinuesLikelihood against the label at 0.5.