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:

prompts/reconstruct-v0.5.md

@@ -125,6 +125,10 @@ Avoid questions that:
 - are too broad to produce useful information
 - combine many unrelated questions
 
+## Semantic preservation check before returning JSON
+
+Before returning the final JSON, compare the reconstruction against the supplied scenario. Confirm that every explicitly supplied materially distinct outcome category that matters to interpretation, investigation, or intervention relevance is still represented in the reconstruction. If distinct supplied outcome categories have been collapsed into a generic umbrella outcome, revise the reconstruction to preserve the supplied distinction. Do not create categories or distinctions the user did not supply.
+
 ## Output format — return this exact JSON structure
 
 Return a JSON object with exactly these four top-level keys (use **camelCase**):