mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-19 00:00:13 +02:00
test: migrate section-loading E2E to lossless SDK tool-stream detection
The /ship and /plan-ceo-review section-loading tests drove a real PTY and scraped the ANSI screen buffer for sections/<file>.md paths. That silently saw nothing in a Conductor PTY (cursor-positioned tool renders and an unanswered Step 0 question loop both defeat the regex), so both reported read: [] even when the agent did the work. They now run the skill through claude -p (the same SDK path the AUQ matrix uses) and detect section reads from the tool-use stream — Read calls whose file_path contains sections/<file>.md — with no rendering layer to mangle. The run is also hermetic: the freshly-generated worktree skeleton + sections are copied into a throwaway fixture with the absolute path pinned, so the test validates this branch's carve without mutating the user's ~/.claude install. Validated EVALS_TIER=periodic: both pass (plan-ceo Reads review-sections.md; ship Reads review-army.md + changelog.md), ~6.5 min for both vs ~23 min combined on the old PTY path where both were failing. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -1,120 +1,83 @@
|
||||
/**
|
||||
* /ship section-loading E2E (periodic, paid, real-PTY) — v2 plan T9 mitigation
|
||||
* layer 5, the ONLY CI-failing guard against silent section-skip.
|
||||
* /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.
|
||||
*
|
||||
* After the carve, ship is a skeleton whose STOP-Read directives point at
|
||||
* sections/*.md. This test runs the REAL /ship skill in plan mode against a
|
||||
* fresh version-changing fixture and asserts the agent actually Read the
|
||||
* sections its situation requires (review-army + changelog at minimum — every
|
||||
* version-changing ship needs the pre-landing review and a CHANGELOG entry).
|
||||
* 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`).
|
||||
*
|
||||
* Runs against the INSTALLED skill at ~/.claude/skills/gstack/ship (Codex
|
||||
* outside-voice #5: an E2E that reads repo paths would miss install-layout
|
||||
* 404s). Section reads are detected from the PTY scrollback — when the agent
|
||||
* Reads a section the tool render shows the `sections/<file>.md` path.
|
||||
* 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.)
|
||||
*
|
||||
* Plan-mode framing keeps the agent from committing/pushing; producing a plan
|
||||
* is the terminal signal. Cost: ~$2-4/run. Periodic tier.
|
||||
*
|
||||
* Situation matrix (T1 = B): this file covers the fresh version-changing ship;
|
||||
* the already-bumped re-run is covered by skill-e2e-ship-idempotency.test.ts,
|
||||
* and a no-plan-file variant can be added to FIXTURES below.
|
||||
* 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: ~$1-2/run.
|
||||
* Periodic tier.
|
||||
*/
|
||||
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { spawnSync } from 'child_process';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import * as os from 'os';
|
||||
import {
|
||||
launchClaudePty,
|
||||
isPermissionDialogVisible,
|
||||
isNumberedOptionListVisible,
|
||||
} from './helpers/claude-pty-runner';
|
||||
setupSkillDir,
|
||||
skillFromWorktree,
|
||||
captureSectionReads,
|
||||
} from './helpers/auq-sdk-capture';
|
||||
|
||||
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
|
||||
const describeE2E = shouldRun ? describe : describe.skip;
|
||||
|
||||
/** Fresh fixture: feature branch with a real change but VERSION still == base,
|
||||
* so /ship must bump (FRESH) and walk the full pre-landing + changelog flow. */
|
||||
function buildFreshFixture(): { workTree: string; root: string } {
|
||||
const root = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ship-secload-'));
|
||||
const workTree = path.join(root, 'workspace');
|
||||
const bareRemote = path.join(root, 'origin.git');
|
||||
fs.mkdirSync(workTree, { recursive: true });
|
||||
const sh = (cmd: string, cwd: string): void => {
|
||||
const r = spawnSync('bash', ['-c', cmd], { cwd, stdio: 'pipe', timeout: 15_000 });
|
||||
if (r.status !== 0) throw new Error(`fixture setup failed at "${cmd}":\n${r.stderr?.toString()}`);
|
||||
};
|
||||
sh(`git init --bare "${bareRemote}"`, root);
|
||||
sh('git init -b main', workTree);
|
||||
sh('git config user.email "t@t.com" && git config user.name "T" && git config commit.gpgsign false', workTree);
|
||||
fs.writeFileSync(path.join(workTree, 'VERSION'), '0.0.1\n');
|
||||
fs.writeFileSync(path.join(workTree, 'package.json'), JSON.stringify({ name: 'fx', version: '0.0.1', private: true }, null, 2) + '\n');
|
||||
fs.writeFileSync(path.join(workTree, 'CHANGELOG.md'), '# Changelog\n\n## [0.0.1] - 2026-01-01\n\n- Initial release\n');
|
||||
fs.writeFileSync(path.join(workTree, 'app.js'), '// base\n');
|
||||
sh('git add -A && git commit -m "chore: initial v0.0.1"', workTree);
|
||||
sh(`git remote add origin "${bareRemote}" && git push -u origin main`, workTree);
|
||||
// Feature branch: a real code change, VERSION untouched → FRESH (needs a bump).
|
||||
sh('git checkout -b feat/new-thing', workTree);
|
||||
fs.writeFileSync(path.join(workTree, 'app.js'), '// base\nexport function newThing() { return 42; }\n');
|
||||
fs.writeFileSync(path.join(workTree, 'app.test.js'), 'test("newThing", () => {});\n');
|
||||
sh('git add -A && git commit -m "feat: add newThing"', workTree);
|
||||
sh('git push -u origin feat/new-thing', workTree);
|
||||
return { workTree, root };
|
||||
}
|
||||
const runId = `ship-section-loading-${process.env.EVALS_RUN_ID ?? 'local'}`;
|
||||
|
||||
// Sections every version-changing ship must consult.
|
||||
const REQUIRED_SECTIONS = ['review-army.md', 'changelog.md'];
|
||||
|
||||
describeE2E('/ship section-loading E2E (periodic, real-PTY, installed skill)', () => {
|
||||
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 { workTree, root } = buildFreshFixture();
|
||||
const session = await launchClaudePty({
|
||||
permissionMode: 'plan',
|
||||
cwd: workTree,
|
||||
timeoutMs: 720_000,
|
||||
env: { GH_TOKEN: 'mock-not-real', NO_COLOR: '1' },
|
||||
const { skillMd, sectionsFrom } = skillFromWorktree('ship');
|
||||
const planDir = setupSkillDir({
|
||||
skillName: 'ship',
|
||||
skillMd,
|
||||
sectionsFrom,
|
||||
fixtures: FIXTURES,
|
||||
tmpPrefix: 'gstack-ship-secload-',
|
||||
});
|
||||
|
||||
const readSections = new Set<string>();
|
||||
let planReady = false;
|
||||
try {
|
||||
await Bun.sleep(8000);
|
||||
const since = session.mark();
|
||||
session.send('/ship\r');
|
||||
const start = Date.now();
|
||||
let lastPermSig = '';
|
||||
while (Date.now() - start < 600_000) {
|
||||
await Bun.sleep(3000);
|
||||
if (session.exited()) break;
|
||||
const visible = session.visibleSince(since);
|
||||
const tail = visible.slice(-1500);
|
||||
if (isNumberedOptionListVisible(tail) && isPermissionDialogVisible(tail)) {
|
||||
const sig = visible.slice(-500);
|
||||
if (sig !== lastPermSig) { lastPermSig = sig; session.send('1\r'); await Bun.sleep(1500); continue; }
|
||||
}
|
||||
// Detect section reads from the scrollback (tool render shows the path).
|
||||
for (const m of visible.matchAll(/sections\/([A-Za-z0-9._-]+\.md)/g)) readSections.add(m[1]);
|
||||
if (/ready to execute|Would you like to proceed|GSTACK REVIEW REPORT/i.test(visible)) {
|
||||
planReady = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
await session.close();
|
||||
try { fs.rmSync(root, { recursive: true, force: true }); } catch { /* ignore */ }
|
||||
}
|
||||
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({ planReady, read: [...readSections], missing }).toEqual({
|
||||
planReady: true,
|
||||
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);
|
||||
},
|
||||
900_000,
|
||||
360_000,
|
||||
);
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user