Tighten review prompt flow

pm/tasks.org

@@ -677,7 +677,7 @@ replace the old observed/canonical workflow with a review-first pipeline that us
 - Existing auto-generated catalog rows are no longer carried forward by default; only deliberate catalog entries survive. That keeps the new `catalog.csv` conservative, but it also means prior observed-based auto-links do not migrate into the new model.
 - Live rerun after the refactor produced `627` purchase rows, `387` review-queue rows, `407` distinct normalized items, `0` linked normalized items, and `0` unresolved rows missing from the review queue.
 
-* [ ] t1.16: cleanup review process and format
+* [x] t1.16: cleanup review process and format
 
 ** acceptance criteria
 1. Add intro text explaining:
@@ -709,11 +709,14 @@ replace the old observed/canonical workflow with a review-first pipeline that us
    
 
 ** evidence
-- commit:
-- tests:
-- date:
+- commit: pending
+- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python review_products.py --refresh-only`; `./venv/bin/python review_products.py --help`
+- datetime: 2026-03-20 12:45:25 EDT
 
 ** notes
+- The main flow change is operational rather than architectural: each review decision now persists immediately to `review_resolutions.csv`, `catalog.csv`, `product_links.csv`, and the on-disk `review_queue.csv`.
+- Direct numeric selection works well for suggestion-heavy review, while `[l]ink existing` remains available as a fallback when the suggestion list is empty or incomplete.
+- I kept the review data model unchanged from `t1.15`; this task only tightened the prompt format, field order, and save behavior.
 
 
 #+END_*