Files
gstack/test/skill-e2e-ship-section-loading.test.ts
T
Garry Tan e722c5bf89 v1.57.0.0 feat: carve-guard system + carve cso/document-release/design-consultation (#1907)
* test: canonical CARVE_GUARDS registry; derive parity + size-budget from it

Single source of truth for the carved-skill set + per-skill invariants
(EQ1). parity-harness.ts sectioned entries and skill-size-budget.ts
SECTIONS_EXTRACTED now derive from it instead of hand-maintained lists.
Closes a pre-existing drift: plan-devex-review was in SECTIONS_EXTRACTED
but had no sectioned parity invariant; now generated. carve-guards.ts is
a pure leaf data module (import type only) to avoid an import cycle.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: shared carve-guard check fns with injectable root

discoverCarvedSkills/checkOrdering/checkCompleteness take a root param so
the negative tests can point the real guards at a fixture dir.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: E2 data-driven carve static ordering guard (gate)

Per-PR backstop for every carved skill, one test() per skill, driven by
CARVE_GUARDS staticInvariants. Generalizes + retires the ceo-specific
ordering test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: E1 carve-guard completeness meta-guard (gate)

Asserts filesystem carved set == CARVE_GUARDS set both directions, so a
future carve without a registry entry fails CI.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: ET1 guard-of-guards negative tests (gate)

Temp fixture broken 3 ways proves E1/E2 actually throw, via the injectable
root. Kills the silent-pass-guard failure class.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: T2 data-driven behavioral section-loading guard (periodic)

One file iterating CARVE_GUARDS, one test() per skill with GSTACK_CARVE_SKILL
cost-scoping (D-CODEX A). external carves (ship, plan-ceo) keep bespoke
tests; testNames aligned to their touchfile keys. Registered in touchfiles.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: defer E3 real-session carve canary to TODOS

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat: carve document-release into skeleton + on-demand section

Steps 2-9 (per-file audit, auto-updates, risky-change asks, CHANGELOG
voice polish, cross-doc consistency, TODOS cleanup, VERSION bump, commit +
PR body) move to sections/release-body.md, read on demand after the Step
1.5 coverage map. Skeleton 59,256 -> 45,797 B (-23%); union preserved.
Adds the CARVE_GUARDS entry (auto-extends parity + size-budget via EQ1).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat: carve design-consultation into skeleton + on-demand section

Phases 3-6 (complete proposal, drill-downs, design preview, writing
DESIGN.md) move to sections/proposal-and-preview.md, read on demand after
product context + research. Skeleton 80,719 -> 59,229 B (-27%); union
preserved. Adds the CARVE_GUARDS entry.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat: carve cso into skeleton + on-demand section (security-safe)

Scope-dependent audit Phases 2-11 move to sections/audit-phases.md. Mode
dispatch (## Arguments, ## Mode Resolution), always-run Phases 0/1, and the
Phase 12 false-positive-filtering exceptions stay ALWAYS-LOADED in the
skeleton. Skeleton 79,383 -> 65,117 B (-18%); union preserved.

Adds a cso CARVE_GUARDS entry with an earliest-use invariant (mustPrecedeStop):
mode dispatch must appear before any STOP-Read, so a directive that decides
which sections to read can't be stranded behind the STOP that reads them
(codex outside-voice #6). carve-guard-checks gains the mustPrecedeStop check.
parity moves cso monolith -> generated carved entry. cso-preserved.test.ts
strengthened: phrases checked against the union, plus an always-loaded
contract on the skeleton (dispatch + FP-filtering, codex #5).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: make redaction/taxonomy tests union-aware for cso + document-release carves

The cso carve moved Secrets Archaeology (prefixes, lib/redact-patterns.ts
pointer, git-history scan) into sections/audit-phases.md, and the
document-release carve moved the Step 9 PR-body redaction scan into
sections/release-body.md. Three content-presence tests asserted that content
in the skeleton SKILL.md/.md.tmpl; they now read the skeleton+sections union
(same fix as cso-preserved + parity).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v1.57.0.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix: address pre-landing review (codex) on the carve

- cso section: add a scope-gate header so '--owasp' (and other scoped modes)
  run only their selected phases, not every phase bundled in the section
  ('execute in full' no longer overrides Mode Resolution).
- carve-guard-checks: gateAfterStop now compares against the LAST STOP, not the
  first, so a gate stranded between two STOPs in a multi-STOP skeleton fails.
- TODOS: behavioral section-loading hermeticity (verifier matches global-install
  path, not the fixture) — pre-existing in auq-sdk-capture.ts, deferred.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-07 19:13:24 -07:00

84 lines
3.8 KiB
TypeScript

/**
* /ship section-loading E2E (periodic, paid, SDK capture) — v2 plan T9 mitigation
* layer 5: the behavioral guard that a real agent Reads the carved sections a
* version-changing ship requires instead of working from the skeleton's memory.
*
* Detection is LOSSLESS. Earlier this test drove a real PTY and scraped the ANSI
* screen buffer for `sections/<file>.md` paths, which silently saw nothing in a
* Conductor PTY (cursor-positioned tool renders + an unanswered question loop
* defeat the regex — it reported `read: []` even when the agent did the work). It
* now runs the skill through `claude -p` (the SDK path the AUQ matrix uses) and
* detects section reads from the tool-use stream (`Read` calls whose file_path
* contains `sections/review-army.md` / `sections/changelog.md`).
*
* Hermetic, not install-mutating: the freshly-generated worktree skeleton +
* sections are copied into a throwaway fixture dir and the absolute path is pinned,
* so the test validates the current carve without touching the user's active
* ~/.claude install. (Install-layout linking is covered by
* setup-sections-linking.test.ts.)
*
* The agent is told AskUserQuestion is unavailable and is given the version-changing
* situation explicitly (no Bash, so it can't and needn't probe git), so it follows
* the skeleton's STOP-Read directives for that situation. Cost: ~$1-2/run.
* Periodic tier.
*/
import { describe, test, expect } from 'bun:test';
import {
setupSkillDir,
skillFromWorktree,
captureSectionReads,
} from './helpers/auq-sdk-capture';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
const describeE2E = shouldRun ? describe : describe.skip;
const runId = `ship-section-loading-${process.env.EVALS_RUN_ID ?? 'local'}`;
// Sections every version-changing ship must consult.
const REQUIRED_SECTIONS = ['review-army.md', 'changelog.md'];
const FIXTURES: Record<string, string> = {
VERSION: '0.0.1\n',
'package.json': JSON.stringify({ name: 'fx', version: '0.0.1', private: true }, null, 2) + '\n',
'CHANGELOG.md': '# Changelog\n\n## [0.0.1] - 2026-01-01\n\n- Initial release\n',
'app.js': '// base\nexport function newThing() { return 42; }\n',
'app.test.js': 'test("newThing", () => {});\n',
};
describeE2E('/ship section-loading E2E (periodic, SDK capture)', () => {
test(
'fresh version-changing ship Reads the required sections',
async () => {
const { skillMd, sectionsFrom } = skillFromWorktree('ship');
const planDir = setupSkillDir({
skillName: 'ship',
skillMd,
sectionsFrom,
fixtures: FIXTURES,
tmpPrefix: 'gstack-ship-secload-',
});
const { readSections, reportProduced, output } = await captureSectionReads({
planDir,
skillName: 'ship',
scenario:
'This is a FRESH version-changing ship: the branch has a real code change (app.js gained a new function with a test), VERSION still equals the base version (0.0.1, so it needs a bump), and CHANGELOG.md needs a new entry. Follow the skill\'s flow for a version-changing ship: run the pre-landing review and prepare the CHANGELOG entry. Produce the ship plan / review report. Do NOT actually commit, push, or open a PR.',
requiredSections: REQUIRED_SECTIONS,
reportMarker: /version|changelog|review|ship/i,
testName: 'ship-section-loading',
runId,
});
const missing = REQUIRED_SECTIONS.filter(s => !readSections.has(s));
expect({ reportProduced, read: [...readSections], missing }).toEqual({
reportProduced: true,
read: expect.any(Array),
missing: [],
});
// Guard against an empty pass: the report must have real content.
expect(output.trim().length).toBeGreaterThan(200);
},
360_000,
);
});