v1.26.4.0 fix: GSTACK REVIEW REPORT delete-then-append (no more mid-file leftovers) (#1335)

* fix: GSTACK REVIEW REPORT delete-then-append flow

Replaces contradictory "replace it entirely" + "always last section / move
if mid-file" bullets in scripts/resolvers/review.ts with a single
delete-then-append rule. Adds Read-tool verification step so the agent
self-checks before continuing.

Affected SKILL.md files (regenerated): plan-ceo-review, plan-design-review,
plan-devex-review, plan-eng-review, codex, devex-review.

* test: static template assertions for delete-then-append + revert autoplan E2E shape

5 new static tests in test/gen-skill-docs.test.ts (4 plan-review SKILL.md
files + 1 source resolver) verify the new prompt language is present and
the old contradictory bullets are absent. Synthetic regression check
confirmed all 5 fail when the prompt fix is reverted.

The autoplan E2E (skill-e2e-autoplan-auto-mode.test.ts) reverts to its
original AUQ-blocked-gate-surface shape. The mid-file regression scenario
the plan briefly proposed isn't reachable in the current PTY harness because
--disallowedTools AskUserQuestion makes autoplan bail at the Phase 1
premise gate before any review-write code path runs. Static prompt-text
verification covers the load-bearing change.

* chore: bump version and changelog (v1.26.4.0)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-05-05 21:18:35 -07:00
committed by GitHub
parent db9447c333
commit 19e699ab9b
12 changed files with 244 additions and 65 deletions

View File

@@ -18,6 +18,16 @@
* Filename keeps `auto-mode` for branch-history continuity. Auto-mode (the
* AUTO_DECIDE preamble path when QUESTION_TUNING=true) is a related but
* distinct silencing mechanism; both share the same fix surface.
*
* Note on report-at-bottom contract: the GSTACK REVIEW REPORT delete-then-
* append flow lives in `scripts/resolvers/review.ts` and is exercised when
* reviews actually run. The PTY harness can't drive autoplan through its
* review phases without auto-progression of AUQs (see runPlanSkillCounting),
* and `--disallowedTools AskUserQuestion` makes autoplan bail at the
* premise gate via the plan-file fallback before any review runs. The
* report-at-bottom prompt change is verified statically in
* `test/gen-skill-docs.test.ts` instead — that's the load-bearing
* verification for the contradictory-prompt fix.
*/
import { describe, test, expect } from 'bun:test';