Defect Identity Determines When Verifier Feedback Should Constrain Search

Localized verifier feedback carries a control signal: it indicates how broadly a critique system should search next. We formulate post-verifier repair as defect-conditioned search control, with defect identity serving as the routing state. Defect-Preserving Repair (DPR) restricts admissible updates to evidence-grounded edits that preserve failure family, target span, and evidence type; a boundary router renews search when the diagnosis indicates a transition. Across the reported matched-budget comparisons, DPR reaches $58.3\pm 1.8$ Correction Accuracy on a $3,814$-instance correction study panel, $3.7$ points above unrestricted post-feedback rewriting. A replay-frozen comparison retains a $2.9$-point advantage, while citation-grounded QA and instruction-following study panels preserve positive utility effects. The count-derived action effect changes from $+5.5$ points on same-defect cases to $-3.0$ on transition-or-switch cases. A five-fold cross-fitted router on $1,624$ replay-frozen states uses this boundary to reach $58.7\pm 1.5$ Corr-ACC, $1.4$ points above always applying DPR. These results establish defect identity as an actionable state variable for allocating post-verifier search.