experiment(confidence-engine): reinforce outcome preservation salience

docs/current-handoff.md

@@ -110,6 +110,12 @@
 - C — the late-delivery versus product-defect distinction — remains the clearest repeated semantic weakness. Rule 5a is now isolated as the first semantic experiment variable; unrelated prompt formatting changes were removed from the experimental diff.
 - No live calls occurred in this increment. Next experiment may add a separate pre-output semantic preservation self-check on top of this clean baseline.
 
+## Outcome-preservation salience variant
+
+- `5c9f94c` established the clean Rule 5a baseline. C — the late-delivery versus product-defect distinction — remains the targeted semantic weakness.
+- This increment adds only a final semantic-preservation self-check, testing instruction salience rather than missing semantic specification. No live model calls were made.
+- Next boundary: one manual fixed-scenario Postman production run, scoring C first while checking A/B/D1/D2/E and unsupported expansion or causal strengthening for regressions.
+
 ## Current product architecture
 
 Three distinct routes, not a single page: