Whether the controller explicitly requested this judgement evaluation.
Current screenshot as base64 PNG
Current URL of the browser
The natural-language goal being pursued
Maximum steps configured for this run
Recent screenshots as base64 PNGs (bounded by ScreenshotHistoryDepth)
History of all steps executed so far
Current step number (1-indexed)
Everything the judge needs to evaluate whether the goal is met. Uses a "pull" pattern — the judge receives all context in one object rather than the engine pushing individual pieces.