CalvinBackup/gstack
1
0 Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-11-08 09:48:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: pre-landing review fixes

Browse Source 
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed 2026-10-26 21:53:37 +00:00
1 parent 97d562c37f
commit a681c00a2b
10 files changed
+96 -36
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

test/helpers/carve-guards.ts
+1 -1
View File
@@ -168,7 +168,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// wave's headline capability) grows the union to 1.195x. Deliberate:
// the section is on-demand (loads only for Apple store targets), so
// per-invocation cost for non-iOS ships is one manifest line.
maxSizeRatio: 1.7250, // Shared advisory identity/dedup + critical-severity validation: 248,065 union bytes / 187,706 baseline = 1.3216 (2026-09-17). + test value bar in the lazy Step 7 section (value cards, weak paths, gate table, base control, machine checks; ~13.6KB): measured 1.396 (2026-09-29). + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.401 (2026-09-30). + the shared QA review step's plan-check timing rule (plan checks and their revalidation run on --timeout-ms after smoke expiry); measured 1.4022 (2026-09-30). + the shared TEST_BOOTSTRAP owned-change undo rules (s03 H1-H3, M1) and the value-bar coverage wording (s03 M2/M3); measured 1.4044 (2026-10-02). + severe fix wave ship-review lane: G1 NO_VERSION dispatch, title and CHANGELOG arms (versionless repos ship without inventing a version), F1 parent-side plan binding before the audit dispatch (binding, docs/designs candidates, exact not-run line) and D3's data-not-instructions line; +2,126 union bytes, measured 1.4135 (2026-10-03). + INV-1 consumer lines (outside review `unverified`/`unavailable` is missing coverage in the readiness note and PR body); measured 1.4148 (2026-10-03). + v1.91.19.0 severe fix wave: verdict-form outside-review callers with sandbox preflight and first-use notice (INV-1/B1/Q2), P0/P1 gate and unverified wording, bound-plan discovery (F1), visible LEARNINGS failures (B5), carved external pointers; measured 267,752 / 187,706 = 1.4264 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 267,874 / 187,706 = 1.4271 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051) and quoted-heredoc issue template (#3046); measured 268,199 / 187,706 = 1.4288 (2026-10-06). + Step 10's inline no-PR check before the Greptile dispatch (#3020); measured 268,655 / 187,706 = 1.4313 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 275,422 / 187,706 = 1.4673 (2026-10-06). Combined Oct 6 wave head (B free-text files + D measure loop + A rework): measured 280,363 / 187,706 = 1.4936 (2026-10-06). + gate-once push rule (no second paid gate after a CI push); measured 280,573 / 187,706 = 1.4947 (2026-10-06). + the measurement bar's decision step (exit-code branches for MEETS, MEETS-qualified, needs-classify with the qualifying and fix-round classes, EXTEND once; the measure prose was tightened to offset most of it); measured 281,058 / 187,706 = 1.4973 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 281,438 / 187,706 = 1.4994 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 281,556 / 187,706 = 1.5000 (2026-10-07). + Oct 7 wave B4: /ship publishes through gstack-post (title prepared in a file in the pr-body section, compose block plus gstack-post exit-code branches replacing the two scans); measured 281,894 / 187,706 = 1.5018 (2026-10-07). + B2 early Greptile PR (lazy Step 6.5 section: detect, public-repo consent, push, provisional title file, open; Step 10's bounded wait; the stop-leaves-the-draft rule); measured 286,626 / 187,706 = 1.5270 (2026-10-07). B3, the classifier, B4 and B2 merged: measured 287,128 / 187,706 = 1.5297 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 281,370 / 187,706 = 1.4990 (2026-10-07). Merged with the guard area: measured 287,440 / 187,706 = 1.5313 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 288,783 / 187,706 = 1.5385 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): the shared GATE_SCAN_BLOCK in the core checklist (2.5) and after Step 7's child, the four-option gate question and record fields in 9.4, tests_ran states in Step 5, Gate edits and per-lane counts in the PR body with draft-while-open; measured 300,143 / 187,706 = 1.5990 (2026-10-10). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave PR E2 (ship/sections/handoff.md: the no-PR automation handoff, with its Section-index row and STOP pointer in the skeleton), offset by tightening Steps 1–3, 12, 14–17 and 20–21 prose so the skeleton stays under 81,000 bytes (80,997); C-pregate landed 1,123 union bytes in tests.md in between; measured 308,619 / 187,706 = 1.6442 on the integra Line truncated
maxSizeRatio: 1.7250, // Shared advisory identity/dedup + critical-severity validation: 248,065 union bytes / 187,706 baseline = 1.3216 (2026-09-17). + test value bar in the lazy Step 7 section (value cards, weak paths, gate table, base control, machine checks; ~13.6KB): measured 1.396 (2026-09-29). + W1 guarded state-root resolution (`eval gstack-paths; : "${GSTACK_STATE_ROOT:?…}"`) in the Context Recovery preamble, the eureka log and each state-writing bash block; measured 1.401 (2026-09-30). + the shared QA review step's plan-check timing rule (plan checks and their revalidation run on --timeout-ms after smoke expiry); measured 1.4022 (2026-09-30). + the shared TEST_BOOTSTRAP owned-change undo rules (s03 H1-H3, M1) and the value-bar coverage wording (s03 M2/M3); measured 1.4044 (2026-10-02). + severe fix wave ship-review lane: G1 NO_VERSION dispatch, title and CHANGELOG arms (versionless repos ship without inventing a version), F1 parent-side plan binding before the audit dispatch (binding, docs/designs candidates, exact not-run line) and D3's data-not-instructions line; +2,126 union bytes, measured 1.4135 (2026-10-03). + INV-1 consumer lines (outside review `unverified`/`unavailable` is missing coverage in the readiness note and PR body); measured 1.4148 (2026-10-03). + v1.91.19.0 severe fix wave: verdict-form outside-review callers with sandbox preflight and first-use notice (INV-1/B1/Q2), P0/P1 gate and unverified wording, bound-plan discovery (F1), visible LEARNINGS failures (B5), carved external pointers; measured 267,752 / 187,706 = 1.4264 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 267,874 / 187,706 = 1.4271 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051) and quoted-heredoc issue template (#3046); measured 268,199 / 187,706 = 1.4288 (2026-10-06). + Step 10's inline no-PR check before the Greptile dispatch (#3020); measured 268,655 / 187,706 = 1.4313 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 275,422 / 187,706 = 1.4673 (2026-10-06). Combined Oct 6 wave head (B free-text files + D measure loop + A rework): measured 280,363 / 187,706 = 1.4936 (2026-10-06). + gate-once push rule (no second paid gate after a CI push); measured 280,573 / 187,706 = 1.4947 (2026-10-06). + the measurement bar's decision step (exit-code branches for MEETS, MEETS-qualified, needs-classify with the qualifying and fix-round classes, EXTEND once; the measure prose was tightened to offset most of it); measured 281,058 / 187,706 = 1.4973 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 281,438 / 187,706 = 1.4994 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 281,556 / 187,706 = 1.5000 (2026-10-07). + Oct 7 wave B4: /ship publishes through gstack-post (title prepared in a file in the pr-body section, compose block plus gstack-post exit-code branches replacing the two scans); measured 281,894 / 187,706 = 1.5018 (2026-10-07). + B2 early Greptile PR (lazy Step 6.5 section: detect, public-repo consent, push, provisional title file, open; Step 10's bounded wait; the stop-leaves-the-draft rule); measured 286,626 / 187,706 = 1.5270 (2026-10-07). B3, the classifier, B4 and B2 merged: measured 287,128 / 187,706 = 1.5297 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 281,370 / 187,706 = 1.4990 (2026-10-07). Merged with the guard area: measured 287,440 / 187,706 = 1.5313 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 288,783 / 187,706 = 1.5385 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W3): the shared GATE_SCAN_BLOCK in the core checklist (2.5) and after Step 7's child, the four-option gate question and record fields in 9.4, tests_ran states in Step 5, Gate edits and per-lane counts in the PR body with draft-while-open; measured 300,143 / 187,706 = 1.5990 (2026-10-10). + Honest Work wave merged (W2/W3 gate integrity in review/ship, W4 kernel + DONE line in every tier-2+ skill, W5/W7 in spec/ship): re-measured on the integrated tree (2026-10-10). + Oct 10 multi-agent wave PR E2 (ship/sections/handoff.md: the no-PR automation handoff, with its Section-index row and STOP pointer in the skeleton), offset by tightening Steps 1–3, 12, 14–17 and 20–21 prose so the skeleton stays under 81,000 bytes (80,997); C-pregate landed 1,123 union bytes in tests.md in between; measured 308,619 / 187,706 = 1.6442 on the integra Line truncated
},
'plan-ceo-review': {
skill: 'plan-ceo-review',
test/prose-lint.test.ts
+36 -8
View File
@@ -10,7 +10,7 @@ import { spawnSync } from 'node:child_process';
import * as fs from 'node:fs';
import * as os from 'node:os';
import * as path from 'node:path';
import { addedOnly, lintProse, maskProse, renderProseLint, unreleasedBlock } from '../lib/prose-lint';
import { addedOnly, lintProse, maskProse, renderProseLint, sectionsOnly, unreleasedBlock } from '../lib/prose-lint';
const ROOT = path.resolve(import.meta.dir, '..');
const FIXTURES = path.join(ROOT, 'test', 'fixtures', 'prose-lint');
@@ -125,6 +125,31 @@ describe('lintProse: each rule, positive and negative', () => {
});
describe('selections', () => {
// Value: protects=the Step 19 compose gate reads only the sections an author writes, so a verbatim tool section (a review line such as "Problem → what you did") can never dead-end /ship; fails_when=a tool section's text is linted, an author section is skipped, heading case is significant, or a body with none of the headings reads as scanned; why_new=new selection; seam=none; no_claim=the compose block's heading list itself is pinned by the wiring test
test('sectionsOnly keeps only the named ## sections, line numbers intact, and is null when none is present', () => {
const body = [
'## Summary', 'The parser showcases a vibrant result.', '',
'## Pre-Landing Review', '[AUTO-FIXED] [x.ts:1] Problem → what you did', '',
'## blast radius', 'Touches the compose block only.', 'Caller -> callee is the only arrow here.',
'## Test plan', '- [x] bun test → 20 pass',
].join('\n');
const picked = sectionsOnly(body, ['Summary', 'Blast radius'])!;
expect(picked.split('\n')).toHaveLength(body.split('\n').length);
expect(lintProse(picked, 'b.md').map(f => [f.rule, f.line])).toEqual([['vocabulary', 2], ['vocabulary', 2], ['arrow', 9]]);
expect(sectionsOnly(body, ['Why'])).toBeNull();
const gated = run([path.join(FIXTURES, 'slopped-changelog.md'), '--sections', '[1.0.0] - 2026-10-01', '--gate']);
expect(gated.code).toBe(1);
expect(gated.out).toMatch(/^PROSE: \S+slopped-changelog\.md:16 /m);
expect(gated.out).not.toMatch(/^PROSE: \S+slopped-changelog\.md:(5|8|9|10) /m);
expect(run([path.join(FIXTURES, 'clean-changelog.md'), '--sections', 'Nope', '--gate']).out).toContain('PROSE_LINT: none');
});
// Value: protects=an HTML comment that spans lines is never read, as the header promises; fails_when=the second line of a comment, or the text before its closing marker, produces a finding, or prose after the close is skipped; why_new=the mask test above covers one-line comments only; seam=none; no_claim=none beyond protects
test('a multi-line HTML comment is masked through its closing marker and prose after it is read', () => {
const text = ['Plain start. <!-- a vibrant', 'multi-line crucial comment', 'still pivotal --> The parser showcases it.', 'Showcasing a vibrant end.'].join('\n');
expect(lintProse(text, 'x.md').map(f => [f.rule, f.line])).toEqual([['vocabulary', 3], ['vocabulary', 4], ['vocabulary', 4]]);
});
test('unreleasedBlock returns the block with its heading line, or null', () => {
const text = fs.readFileSync(path.join(FIXTURES, 'slopped-changelog.md'), 'utf8');
const block = unreleasedBlock(text)!;
@@ -225,6 +250,8 @@ describe('bin/gstack-prose-lint', () => {
expect(run([path.join(FIXTURES, 'missing.md')]).code).toBe(2);
expect(run([path.join(FIXTURES, 'clean-changelog.md'), '--nope']).code).toBe(2);
expect(run([path.join(FIXTURES, 'clean-changelog.md'), '--unreleased', '--base', 'main']).code).toBe(2);
expect(run([path.join(FIXTURES, 'clean-changelog.md'), '--sections', 'Added', '--base', 'main']).code).toBe(2);
expect(run([path.join(FIXTURES, 'clean-changelog.md'), '--sections', '--gate']).code).toBe(2);
const dir = run([FIXTURES]);
expect(dir.code).toBe(2);
expect(dir.err).toContain('cannot read');
@@ -243,7 +270,8 @@ describe('wiring', () => {
expect(changelog).toContain('gstack-prose-lint CHANGELOG.md --base origin/<base> --gate');
const prBody = read('ship/sections/pr-body.md.tmpl');
const compose = prBody.slice(prBody.indexOf(': "${DOCS_SECTION_FILE:?'), prBody.indexOf('echo "PR_BODY_FILE: $PR_BODY_FILE"'));
expect(compose).toContain('gstack-prose-lint "$BODY_TOP_FILE" "$BODY_REST_FILE" --gate');
expect(compose).toContain(`gstack-prose-lint "$BODY_TOP_FILE" --sections 'What changed,Why,Summary,Blast radius' --gate`);
expect(compose).not.toContain('"$BODY_REST_FILE" --gate');
expect(compose.indexOf('gstack-prose-lint')).toBeGreaterThan(compose.indexOf('is empty, so the body was never written'));
expect(compose.indexOf('gstack-prose-lint')).toBeLessThan(compose.indexOf('{ awk 1 "$BODY_TOP_FILE"'));
for (const host of ['claude', 'codex', 'factory', 'agy']) expect(fs.existsSync(path.join(ROOT, 'test', 'fixtures', 'golden', host + '-ship-SKILL.md'))).toBe(true);
@@ -258,14 +286,14 @@ describe('wiring', () => {
expect(summary).toContain('## Blast radius');
expect(summary).toContain('the one fact that makes that safe');
expect(summary).toContain('file:line read, walked failure path, script ran, repro');
expect(summary).toContain('investigate/sections/blast-radius.md');
expect(summary).toContain('`~/.claude/skills/gstack/investigate/sections/blast-radius.md`, when present');
expect(prBody).toContain('names what the user gets, not the mechanism');
const capy = read('ship/sections/capy-pr.md.tmpl');
expect(capy).toContain('`## Why`, `## Blast radius` and `## Approvals`');
expect(capy).toMatch(/\*\*`## Why`:\*\* two or three sentences\. The first states the problem in the person's words/);
expect(capy).toMatch(/BAD "[\s\S]+" GOOD "/);
expect(capy).toContain("**`## Blast radius`:** the body template's item, written once");
expect(capy).toContain('investigate/sections/blast-radius.md');
expect(capy).toContain('`~/.claude/skills/gstack/investigate/sections/blast-radius.md`, when present');
});
test('the quality gate runs the lint over the [Unreleased] block, and NOTICE.md credits unslop', () => {
@@ -275,11 +303,11 @@ describe('wiring', () => {
expect(read('docs/troubleshooting.md')).toContain('<a id="prose-lint-found"></a>');
});
test('the shipped templates pass their own lint as a report (no gate), and the current [Unreleased] block gates clean', () => {
// Value: protects=a template run is a report (exit 0 and a trailer) even when the templates carry findings, so a template's em dashes and BAD examples never fail a check; fails_when=report mode exits nonzero on a finding; why_new=the earlier row accepted ok or found and proved nothing; seam=none; no_claim=the templates' own findings count is not pinned (it moves with every prose edit)
test('the shipped templates get a report, never a gate: exit 0 with a trailer even with findings', () => {
const r = run(['ship/sections/changelog.md.tmpl', 'ship/sections/capy-pr.md.tmpl', 'ship/sections/pr-body.md.tmpl']);
expect(r.code).toBe(0);
expect(r.out).toMatch(/PROSE_LINT: (ok|found=\d+) files=3\n$/);
const cl = run(['CHANGELOG.md', '--unreleased', '--gate']);
expect(cl.code).toBe(0);
expect(r.out).toMatch(/PROSE_LINT: found=\d+ files=3\n$/);
expect(r.err).toBe('');
});
});