Brummel
8b2defa653
`aura mc <bp.json>` builds a per-seed synthetic price walk with a fixed 60-bar SyntheticSpec. A deeper-lookback loaded blueprint warms poorly over that walk, so every seed can collapse to a bit-identical draw and the family was returned as an Ok result — a single point masquerading as a distribution, a wrong result with no error. Guard it: with >= 2 seeds, if every draw's metrics equal the first draw's, refuse with a named error (C10 refuse-don't-guess), rather than auto-sizing the walk (which would have to guess a warm-up depth the harness does not surface). Compares `report.metrics`, not the whole RunReport — the manifest seed differs per draw by construction, so a whole-report compare could never detect the collapse. RED-first; the existing `blueprint_mc_family_seeds_differ` pins that a legitimate (differing-draw) MC is not falsely rejected. Interim guard only — the real-data moving-block-bootstrap headline stays gated on the DataServer seam. refs #172