voyage/lib
Kjell Tore Guttormsen 6b44be4c43
feat(review): stop rule in the review rounds (decision 217, 220)
prepare (also --dry-run) judges the previous round's archive and
review.md when it would open round 3: blocking = BLOCKER + counting MAJOR
with the verdict gate's pre-existing reading, new = no carried_from, class
= classOf. Fired -> exit 1, `review-stop-rule: <describeStop line>` and
`stop_rule`, nothing archived. The cap stays. A round with no readable
JSON block gives no summary and the rule is not judged.

countingMajors moves from review-answers.mjs into review-rounds.mjs and is
re-exported by review-answers (as isSecurityFinding is); review-rounds
still imports nothing from review-answers.

Existing test updated for the planned rule: the [CRY] occurrence case adds
a third round-1 MAJOR resolved in round 2, so its round-3 control is not
stopped by "not fewer".

Part 1, step 1.3 of the E plan.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 07:13:07 +01:00
..
parsers fix(cleanup): R-b review round — retired flags in the prose parsers 2026-11-07 21:36:13 +01:00
review feat(review): stop rule in the review rounds (decision 217, 220) 2026-11-08 07:13:07 +01:00
skills refactor(cleanup): simplify pass on the R-a diff 2026-11-07 13:31:30 +01:00
util chore(cleanup): R-b R2 — STORM loop, cap hook and the --engine research choice removed 2026-11-07 20:32:38 +01:00
validators feat(gate): stop rule in the plan gate (decision 217, 220) 2026-11-08 07:04:48 +01:00
verification chore(cleanup): remove the June trials, orchestrator docs, dormant agent, caller-less code and the fix-round chain 2026-11-07 12:51:54 +01:00