Use when the user asks to debug with ensemble judges, or explicitly requests the ensemble variant of deep-debug. Benchmark variant that uses three heterogeneous providers for hypothesis-plausibility judging instead of a single judge. Same triggers as deep-debug but with multi-provider ensemble scori
Use when the user asks to debug with ensemble judges, or explicitly requests the ensemble variant of deep-debug. Benchmark variant that uses three heterogeneous providers for hypothesis-plausibility judging instead of a single judge. Same triggers as deep-debug but with multi-provider ensemble scoring.