MJ prompt entity for the judge
OptionalcustomPrompt: stringOptional custom prompt text override
Get the MJ prompt entity associated with this judge. Used by MJComputerUseEngine to determine which prompt entity to use when executing the judge via AIPromptRunner.
Human-readable identifier for this judge strategy
ProtectedbuildOverride to include additional MJ context in the judge prompt request. The base request is built the same way; this extension point exists for future MJ-specific context injection (e.g., requirement tracking, domain-specific evaluation criteria).
ProtectedCreateCreate a verdict with standard fields populated. Utility for subclasses to avoid boilerplate.
Optionalfeedback: stringOptionalimpossible: booleanEvaluate the current state and determine whether the goal is met.
Full context including goal, screenshots, step history
Verdict with Done, Confidence, Feedback, and Reason
ProtectedparseParse the LLM response into a JudgeVerdict. Protected so Layer 2 can override if the prompt format changes.
Expects JSON with: done (boolean), confidence (number), reason (string), feedback (string). Handles both raw JSON and JSON wrapped in markdown code blocks.
Callback to execute the judge prompt (from the engine)