From d79ce16bbc4ca08786e46e5f3b0e679c5a775549 Mon Sep 17 00:00:00 2001 From: Pasi Vuorio Date: Mon, 28 Sep 2026 19:09:21 +0300 Subject: [PATCH] process: a later review round reviews what changed since the last recorded round A second round re-read the whole packet. It now reviews the records and sections whose fingerprints moved, the open findings and what they touch, and carries the unchanged remainder at the previous verdict; its trace still pins the full aggregate, so legality is unchanged (USER:2026-09-28, Pasi: re-review only what changed). Co-Authored-By: Claude Opus 5.5 --- PROCESS.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/PROCESS.md b/PROCESS.md index 04f200d..e73e954 100644 --- a/PROCESS.md +++ b/PROCESS.md @@ -491,7 +491,11 @@ as a closure carried from an earlier round. A round whose material findings fall on mechanisms an earlier round's resolutions introduced is evidence that the packet was reviewed incomplete, not that the review is thorough. -Cold review converges or stops. At most two rounds run on one change. A small +Cold review converges or stops. At most two rounds run on one change. A later +round reviews what changed since the previous round's recorded trace — the +records and sections whose fingerprints moved, the findings still open, and +what those touch — and carries the unchanged remainder at that round's verdict; +its trace still pins the full current aggregate. A small change gets one narrow pass from an independent context — the boundary against the code, the RED plan, and the eligibility — and no second round: a blocking finding sends it out of the lane. When a