From 9cc40e0d03eed66cd74cd57f463bdbb420e84990 Mon Sep 17 00:00:00 2001 From: Garry Tan Date: Mon, 2 Nov 2026 11:33:38 -0800 Subject: [PATCH] v1.93.16.0 fix(review): Step 11.5 bind ignores untracked root dot-dir scratch (GST-985) (#3873) * fix(review): Step 11.5 bind ignores untracked root dot-dir scratch, keeps .github/ and .gstack/ (GST-985) gstack-review-log and gstack-review-read fingerprint with gstack-wtree --review, which leaves out root dot-directories that hold no tracked file. A test lane's .review-units-test-* scratch appearing or vanishing mid-review no longer unbinds the Step 9 row; .github/ and .gstack/ always count, and every other gstack-wtree caller keeps the whole tree. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (Step 11: read-tree fallback and ..x root dirs) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: GST-985 changelog fragment and troubleshooting note Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): keep review-army.md at its no-loss-pinned bytes (GST-985) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- CHANGELOG.md | 6 +++ VERSION | 2 +- agents-digest/gstack-AGENTS.md | 2 +- bin/gstack-review-log | 2 +- bin/gstack-review-read | 4 +- bin/gstack-wtree | 29 ++++++++++- docs/troubleshooting.md | 3 ++ package.json | 2 +- test/review-start-evidence.test.ts | 77 ++++++++++++++++++++++++++++++ 9 files changed, 120 insertions(+), 7 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 17c0eceee..f306cfa43 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,11 @@ # Changelog +## [1.93.16.0] - 2026-11-02 + +### Fixed + +- **A test lane's scratch folder no longer breaks the /ship review bind.** When an untracked `.review-units-test-*/` folder appeared or vanished while reviewers ran, Step 11.5 saw a different tree and the only repair was rerunning Steps 9 to 11.5 (about 20M tokens). Review records now fingerprint with `gstack-wtree --review`, which leaves out root dot-folders that hold no tracked file. `.github/` and `.gstack/` always count, and any change to a tracked file still breaks the bind. The pregate, test evidence and every other caller keep the whole tree. (GST-985) + ## [1.93.15.0] - 2026-11-02 **Pregate stops blaming a clean branch for a missing pytest, Playwright specs and mixed-language root tests, and the literals check stops flagging stray digits (#3598, #3492, gstack-evals#97).** A machine without pytest reported "fix the in-branch failure". Playwright specs in a vitest repo went to vitest, which found no tests and failed. Root tests in `.mjs` and `.py` got no runner at all. And any lone `2` in a file that named a changed constant (a comment, a `$2` in a shell stub, a fixture) failed `literals`. A wrapper bump from 3 to 4 would have raised 5 false hits here, and gstack-evals#97 hit 11. Rewritten from outside PRs #3639 and #3600 by @vilano93 and #3629 by @nfitzsimmons. diff --git a/VERSION b/VERSION index 854f27d1b..7cdafd83e 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.93.15.0 +1.93.16.0 diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md index bd3ae8bb9..2926a4a45 100644 --- a/agents-digest/gstack-AGENTS.md +++ b/agents-digest/gstack-AGENTS.md @@ -1,4 +1,4 @@ -# gstack digest v1.93.15.0 — regenerate/re-copy after upgrading gstack +# gstack digest v1.93.16.0 — regenerate/re-copy after upgrading gstack Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed for agent hosts without a full skill install. The full skills add workflows, diff --git a/bin/gstack-review-log b/bin/gstack-review-log index 1fabcc3b2..b469ee1a4 100755 --- a/bin/gstack-review-log +++ b/bin/gstack-review-log @@ -69,7 +69,7 @@ if [ -n "$COMMIT_FULL" ]; then esac trap 'rm -rf "$WTREE_OBJECTS"' EXIT trap 'exit 130' INT TERM - WTREE=$(GSTACK_WTREE_OBJECT_DIR="$WTREE_OBJECTS" "$SCRIPT_DIR/gstack-wtree" || true) + WTREE=$(GSTACK_WTREE_OBJECT_DIR="$WTREE_OBJECTS" "$SCRIPT_DIR/gstack-wtree" --review || true) export GIT_ALTERNATE_OBJECT_DIRECTORIES="$WTREE_OBJECTS${GIT_ALTERNATE_OBJECT_DIRECTORIES:+:$GIT_ALTERNATE_OBJECT_DIRECTORIES}" else echo "gstack-review-log: cannot create a private object directory under ${TMPDIR:-/tmp}; no working-tree fingerprint. Set TMPDIR to a writable directory." >&2 diff --git a/bin/gstack-review-read b/bin/gstack-review-read index e673640ab..9b1530c62 100755 --- a/bin/gstack-review-read +++ b/bin/gstack-review-read @@ -4,7 +4,7 @@ # # Emits, in order: reviews JSONL with computed review_freshness, ---CONFIG--- (skip_eng_review), # ---HEAD--- (short sha), ---WTREE--- (current working-tree fingerprint from -# bin/gstack-wtree, or "unknown"), ---TREE--- (HEAD tree, informational) and +# bin/gstack-wtree --review, or "unknown"), ---TREE--- (HEAD tree, informational) and # ---DIRTY--- (tracked-file dirty flag). Consumers grade diff-scoped review # rows using review_freshness; legacy or uncaptured diff evidence cannot fall # back to HEAD equality. Plan rows are unchanged. @@ -19,7 +19,7 @@ SLUG=$("$SCRIPT_DIR/gstack-slug" --get REPO_SLUG 2>/dev/null || true) . "$(dirname "$0")/gstack-state-root.sh" 2>/dev/null || { echo "$0: cannot resolve the gstack state root: $(dirname "$0")/gstack-state-root.sh is missing. fix: reinstall with ./setup or /gstack-upgrade (docs/state-root.md)" >&2; exit 1; } gstack_state_root_select GSTACK_HOME="$_gstack_sr_root" -WTREE=$("$SCRIPT_DIR/gstack-wtree" 2>/dev/null || echo "unknown") +WTREE=$("$SCRIPT_DIR/gstack-wtree" --review 2>/dev/null || echo "unknown") if [ -f "$GSTACK_HOME/projects/$SLUG/$BRANCH-reviews.jsonl" ]; then GSTACK_REVIEW_LIB="$SCRIPT_DIR/../lib/review-evidence.ts" GSTACK_REVIEW_WTREE="$WTREE" bun --no-env-file --config="${GSTACK_BUN_CONFIG:-/dev/null}" -e ' const { reviewFreshness } = await import(process.env.GSTACK_REVIEW_LIB); diff --git a/bin/gstack-wtree b/bin/gstack-wtree index c8034e375..3df71b05c 100755 --- a/bin/gstack-wtree +++ b/bin/gstack-wtree @@ -9,6 +9,12 @@ # look like a mid-run edit (GST-421); tracked files under it still count, and a # tree without that folder (or with it gitignored) hashes exactly as a plain # `git add -A` would. +# +# --review (gstack-review-log and gstack-review-read only, GST-985) also leaves +# out every root dot-directory that holds no tracked file, such as a test +# lane's `.review-units-test-*/` scratch, so scratch appearing or vanishing +# mid-review cannot unbind a review. `.github/` and `.gstack/` always stay in: +# they hold CI and gate policy. Every other caller keeps the whole tree. # Properties that make this the right staleness fingerprint, vs # `git rev-parse HEAD^{tree}`: # @@ -40,6 +46,13 @@ # treat that as "no fingerprint"; a partial hash is never printed. set -euo pipefail +REVIEW="" +case "$#:${1:-}" in + 0:) ;; + 1:--review) REVIEW=1 ;; + *) echo "Usage: gstack-wtree [--review]" >&2; exit 2 ;; +esac + TOP=$(git rev-parse --show-toplevel 2>/dev/null) || exit 1 # Resolve the REAL index path BEFORE exporting GIT_INDEX_FILE — with the env # var set, `git rev-parse --git-path index` returns the temp index itself and @@ -95,7 +108,21 @@ fi # call .bun not ignored. EXCLUDE_BUN="" if [ -e "$TOP/.bun" ] && ! git -C "$TOP" check-ignore --no-index -q .bun 2>/dev/null; then EXCLUDE_BUN=':(exclude,top).bun'; fi -if ! ERR=$(git -C "$TOP" add -u 2>&1 >/dev/null) || ! ERR=$(git -C "$TOP" add -A -- . ${EXCLUDE_BUN:+"$EXCLUDE_BUN"} 2>&1 >/dev/null); then +EXCLUDES=() +if [ -n "$EXCLUDE_BUN" ]; then EXCLUDES+=("$EXCLUDE_BUN"); fi +if [ -n "$REVIEW" ]; then + TRACKED_INDEX="$TMPIDX" + if [ -n "$REAL_INDEX" ] && [ -f "$REAL_INDEX" ]; then TRACKED_INDEX="$REAL_INDEX"; fi + for DOTDIR in "$TOP"/.[!.]* "$TOP"/..?*; do + NAME=${DOTDIR##*/} + case "$NAME" in .git|.github|.gstack|.bun) continue ;; esac + if [ ! -d "$DOTDIR" ] || [ -L "$DOTDIR" ]; then continue; fi + if GIT_INDEX_FILE="$TRACKED_INDEX" git -C "$TOP" ls-files --error-unmatch -- ":(top,literal)$NAME" >/dev/null 2>&1; then continue; fi + if git -C "$TOP" check-ignore --no-index -q -- "$NAME" 2>/dev/null; then continue; fi + EXCLUDES+=(":(exclude,top,literal)$NAME") + done +fi +if ! ERR=$(git -C "$TOP" add -u 2>&1 >/dev/null) || ! ERR=$(git -C "$TOP" add -A -- . ${EXCLUDES[@]+"${EXCLUDES[@]}"} 2>&1 >/dev/null); then echo "gstack-wtree: cannot stage the working tree: $(printf '%s' "$ERR" | head -1)" >&2 exit 1 fi diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md index 86e0a0a66..c7f63bba6 100644 --- a/docs/troubleshooting.md +++ b/docs/troubleshooting.md @@ -570,6 +570,9 @@ the base has moved. **Meaning.** The working tree changed between the pass's `gstack-review-log --start` and its logged row: an edit, commit or merge landed while reviewers were still reading. The reviewers may not have seen that change, so the row's `review_binding.state` is `changed`. +Review records fingerprint with `gstack-wtree --review`, which skips untracked root dot-folders +that hold no tracked file (never `.github/` or `.gstack/`), so a test lane's scratch folder alone +does not move the tree. Step 11.5 cannot bind it and inserts `9 → 10 → 11 → 11.5`. Logging the same results again cannot repair it. diff --git a/package.json b/package.json index 639048db5..f4902d325 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "gstack", - "version": "1.93.15", + "version": "1.93.16", "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.", "license": "MIT", "type": "module", diff --git a/test/review-start-evidence.test.ts b/test/review-start-evidence.test.ts index eae485fd4..848784512 100644 --- a/test/review-start-evidence.test.ts +++ b/test/review-start-evidence.test.ts @@ -166,6 +166,83 @@ describe('review start/end binding (#2803)', () => { }); } + for (const when of ['created', 'removed']) { + test(`GST-985: an untracked scratch dir ${when} mid-review still binds; a tracked edit still breaks it`, () => { + const scratchDir = join(repo, '.review-units-test-x'); + if (when === 'removed') { mkdirSync(scratchDir); writeFileSync(join(scratchDir, 'unit.json'), '{}\n'); } + const token = cli('gstack-review-log', ['--start', 'review']); + if (when === 'created') { mkdirSync(scratchDir); writeFileSync(join(scratchDir, 'unit.json'), '{}\n'); } + else rmSync(scratchDir, { recursive: true, force: true }); + const row = log(token); + expect(row.review_binding.state).toBe('verified'); + expect(row.review_binding.start_wtree).toBe(row.review_binding.end_wtree); + expect(row.review_freshness.status).toBe('CURRENT'); + expect(git('diff', '--name-only', row.wtree, cli('gstack-wtree'))).toBe(when === 'created' ? '.review-units-test-x/unit.json' : ''); + + const edited = cli('gstack-review-log', ['--start', 'review']); + writeFileSync(join(repo, 'source.ts'), 'export const unreviewed = true;\n'); + expect(log(edited).review_binding.state).toBe('changed'); + }); + } + + test('GST-985: ignored root dot-directories still fingerprint under --review', () => { + writeFileSync(join(repo, '.git', 'info', 'exclude'), '.cache/\n'); + mkdirSync(join(repo, '.cache')); + writeFileSync(join(repo, '.cache', 'blob'), 'x\n'); + expect(cli('gstack-wtree', ['--review'])).toBe(cli('gstack-wtree')); + }); + + test('GST-985: an untracked file in a dot-directory that holds a tracked file still breaks the bind', () => { + mkdirSync(join(repo, '.tool')); + writeFileSync(join(repo, '.tool', 'a.json'), '{}\n'); + git('add', '.tool/a.json'); + git('commit', '-qm', 'tool'); + const token = cli('gstack-review-log', ['--start', 'review']); + writeFileSync(join(repo, '.tool', 'b.json'), '{}\n'); + expect(log(token).review_binding.state).toBe('changed'); + }); + + test('GST-985: a root ..x scratch dir created mid-review still binds', () => { + const token = cli('gstack-review-log', ['--start', 'review']); + mkdirSync(join(repo, '..x')); + writeFileSync(join(repo, '..x', 'unit.json'), '{}\n'); + expect(log(token).review_binding.state).toBe('verified'); + }); + + test('GST-985: a git add -N file in a new dot-directory counts under the read-tree HEAD fallback', () => { + mkdirSync(join(repo, '.newdir')); + writeFileSync(join(repo, '.newdir', 'a.ts'), 'export const a = 1;\n'); + git('add', '-N', '.newdir/a.ts'); + const fakeBin = mkdtempSync(join(tmpdir(), 'review-start-faketouch-')); + writeFileSync(join(fakeBin, 'touch'), '#!/bin/sh\nexit 1\n'); + chmodSync(join(fakeBin, 'touch'), 0o755); + try { + const env = { PATH: `${fakeBin}:${process.env.PATH}` }; + expect(cli('gstack-wtree', ['--review'], repo, env)).toBe(cli('gstack-wtree', [], repo, env)); + } finally { + rmSync(fakeBin, { recursive: true, force: true }); + } + }); + + test('GST-985: gstack-wtree refuses an unknown or extra argument', () => { + for (const args of [['--bogus'], ['--review', 'x']]) { + const r = spawnSync(join(ROOT, 'bin', 'gstack-wtree'), args, { cwd: repo, encoding: 'utf8', timeout: 10_000 }); + expect(r.status).toBe(2); + expect(r.stderr).toContain('Usage: gstack-wtree [--review]'); + } + }); + + for (const file of ['.github/workflows/x.yml', '.gstack/ship-policy.json']) { + test(`GST-985: an untracked ${file} added mid-review still breaks the bind`, () => { + const token = cli('gstack-review-log', ['--start', 'review']); + mkdirSync(join(repo, file, '..'), { recursive: true }); + writeFileSync(join(repo, file), '{}\n'); + const row = log(token); + expect(row.review_binding.state).toBe('changed'); + expect(git('diff', '--name-only', row.review_binding.start_wtree, row.review_binding.end_wtree)).toBe(file); + }); + } + test('fix commits do not certify the final tree until a new unchanged pass', () => { const token = cli('gstack-review-log', ['--start', 'review']); writeFileSync(join(repo, 'source.ts'), 'export const fixed = true;\n');