Ревью шло по ветке как есть, слияние делало ребейз: проверенный SHA и
слитый SHA были разными коммитами. Текстовое расхождение ловил конфликт,
смысловое git склеивал молча — так пришёл регресс #234. Заодно конфликт
обнаруживался после сорока минут работы ревьюера, хотя виден до них.
Новый шаг для этапа code, сразу после выбора ветки: потомок dev —
ничего; отстала и ребейзится — ребейз, push с --force-with-lease, ревью
приведённого состояния и запись о ребейзе в промпт (§7.2 требует полного
разбора); конфликт — возврат в S6-in-progress без запуска ревью.
Issue: #257
User-Visible: no
The previous change replaced the document path with REVIEW_DOC and left a
parenthetical hanging: the prompt jumped from "create no files in the
repository" straight into "(SPEC for the spec stage, CODE for code): scope,
how it was checked…", with the sentence that introduced the document
structure gone. The prompt now says plainly that the publish step derives
the name in docs/reviews, and the content requirements start a paragraph of
their own.
Issue: #220
User-Visible: no
Three code-review rounds on #220 published a verdict and then failed the
run: the document never reached the branch, so the #171 guard refused
before the label step and neither the merge nor S8-merged happened. The
cause was structural. The document lived as an untracked file inside the
very checkout the reviewer edits while proving that a test can fail, and
restoring that tree — git checkout, git clean — deletes an untracked file.
Spec rounds survived only because they never mutate anything.
The reviewer now writes to REVIEW_DOC under RUNNER_TEMP, outside the
repository, and the publish step copies it into docs/reviews before
committing. Tree cleanup can no longer destroy the artefact, and the
reviewer no longer needs to touch docs/reviews at all.
Verified against a local git fixture on five paths: document outside the
repo with a mutated tree (published, and the code mutation does not leak),
nothing anywhere (loud failure, exit 1), document only in the working copy
(still published — the clean exclusion stays for exactly this), document
already committed by the reviewer (recognised, no duplicate), and a branch
that moved during the review (rebased, both commits kept).
Issue: #220
User-Visible: no
The pipeline punished what it prescribed: after a failed merge it tells the
author to rebase and restore S7-code-review, and that attempt finished the
budget. On #225 (light track, limit 2) the sequence yellow, green, rebase
produced review-4 on a task whose code review was green and whose CI was
green, with no product change after the verdict — the owner had to
arbitrate work that was already accepted.
A cycle under section 4 is a verdict with blocking findings followed by a
return to the author, so only yellow and red verdicts spend the budget now.
A green verdict returned nothing and consumes nothing, which also removes
any need to mark rebase re-runs specially.
Attempts and cycles are now separate quantities. The attempt number keeps
naming the document, because two runs sharing a number would overwrite each
other's review artefact, while the limit compares blocking cycles only. The
exhaustion comment lists the verdicts it counted, and the guard no longer
strips review-4 — it reports the recount and leaves the decision with the
owner.
Rule 7 of the process gate follows: its document threshold rises above the
cycle limit, because legitimate attempts can exceed cycles and a threshold
equal to the limit would refuse the very rebase the pipeline demands.
Issue: #227
User-Visible: no
The reviewer prompt was identical for every round, and the canon said
nothing about the scope of a repeat pass, so r2 re-derived the product
framing and re-checked acceptance criteria the fix never touched: the r2
pass on #150 cost a full pipeline run over one line in a test fixture.
From the second cycle on, the subject is the delta against the SHA the
previous verdict was given on: each earlier finding must be shown closed
by a line of code or text, only the criteria the delta can reach are
re-verified, and whatever is carried over is listed with the round and SHA
it came from. Cheap gates still run every round.
The scope shrinks, the strictness does not. A fix can break a criterion an
earlier round accepted — that is how regression #102 happened — so the
boundary is the findings plus everything the delta can reach, and a
non-local delta (a rebase onto a moved dev, a behaviour contract change, a
new subsystem) still gets the full pass.
Issue: #214
User-Visible: no
The reviewer prompt was identical for every round, and the canon said
nothing about the scope of a repeat pass, so r2 re-derived the product
framing and re-checked acceptance criteria the fix never touched: the r2
pass on #150 cost a full pipeline run over one line in a test fixture.
From the second cycle on, the subject is the delta against the SHA the
previous verdict was given on: each earlier finding must be shown closed
by a line of code or text, only the criteria the delta can reach are
re-verified, and whatever is carried over is listed with the round and SHA
it came from. Cheap gates still run every round.
The scope shrinks, the strictness does not. A fix can break a criterion an
earlier round accepted — that is how regression #102 happened — so the
boundary is the findings plus everything the delta can reach, and a
non-local delta (a rebase onto a moved dev, a behaviour contract change, a
new subsystem) still gets the full pass.
Issue: #214
User-Visible: no
Claude