Files
PaperClipAI/scripts/__tests__/public-install-registry.test.mjs
T
c3715e74a6 perf(ci): let the public-install registry reuse warmed scoped metadata (#16838)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Every pull request runs the `ci / Build` check. This check was the
slowest check in recent green runs: 432s in run 39254079691, 480s in run
39251304886 and 472s in run 39245233967.
> - The slowest step in Build is "Verify built-in Grok from a clean
public npm install" (162s and 207s). Its consumer `npm install` took 69s
and 75s, even though a background step fills the npm cache first.
> - The loopback registry in `scripts/public-install-registry.mjs` sends
packages that it does not serve to npmjs with a 302 redirect. It escaped
scoped names with `encodeURIComponent` (`%40scope%2Fname`). npm requests
and caches the same metadata as `@scope%2fname`, and npm keys cached
metadata by URL.
> - Thus the consumer install could not use the scoped metadata that the
warm-up had just put in the cache. It downloaded and parsed all 291
scoped packuments again (about 285 MB of full packument JSON) inside the
4-vCPU container.
> - This pull request makes the redirect use the same escaping as npm.
> - The benefit is a shorter Build check on every pull request. The
installed bytes do not change.

## Linked Issues or Issue Description

**Describe the bug**
The consumer install in the public-install verifier does not use cached
scoped package metadata. The warm-up step
(`scripts/warm-public-install-npm-cache.mjs`) caches this metadata
through direct npm requests.

**Steps to reproduce**
1. Run `PAPERCLIP_PUBLIC_INSTALL_NPM_CACHE=/tmp/c node
scripts/warm-public-install-npm-cache.mjs`.
2. Install the same dependency set through the loopback registry with
`npm_config_cache=/tmp/c` and `--loglevel http`.
3. Count the `(cache miss)` lines.

**Expected behavior**
No cache misses for metadata that the warm-up already fetched.

**Actual behavior**
291 cache misses. All of them are scoped packages that are requested as
`https://registry.npmjs.org/%40scope%2Fname`. The cache holds them as
`https://registry.npmjs.org/@scope%2fname`.

Related: #16513 changes when the verifier waits for the warm-up. This
pull request does not overlap with it, and the two changes add together.

## What Changed

- `scripts/public-install-registry.mjs`: the 302 redirect for packages
that the registry does not serve now uses npm's own escaping
(`name.replace('/', '%2f')`, the same as npm-package-arg `escapedName`).
The `packageName` check already allows only characters that need no
other escaping.
- `scripts/__tests__/public-install-registry.test.mjs`: the test now
expects `@other%2fpkg` for a scoped redirect. A new assertion covers an
unscoped redirect.

## Verification

- `node --test scripts/__tests__/public-install-registry.test.mjs`: 3 of
3 pass. This includes the real npm install test that compares installed
bytes from file installs and registry installs.
- Local replay (Linux, npm 11.12.1). I filled a fresh cache with the
warm-up script, then installed the same 62-dependency set (627 packages)
through the registry:
  - Before: 291 cache misses, 28.3s.
  - After: 0 cache misses, 19.8s.
- I also ran the real `scripts/public-install-registry.mjs` with a
packed root package that depends on the full public dependency set.
Result: 2 misses (only the loopback package and its tarball, as
expected) and 1438 cache hits.
- To compare on CI, look at `consumer_install_ms` in the
`paperclip.public-npm-install.timing.v1` line of the Build log.
Baseline: 68822 ms (run 39254079691) and 75175 ms (run 39251304886).

## Risks

- Low risk. The redirect target is the same npmjs document. Only the URL
escaping changes. npm still checks every tarball against the integrity
in the packument.
- If the npm cache holds stale scoped metadata, npm revalidates it the
same way as it does for direct requests (`cache-control: max-age=300`).
- The expected time saving comes from a local measurement. The real
Build saving depends on the network and CPU of the runner. I expect
about 10–20s per Build run. The CI timing line will confirm the number.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`), Anthropic, used through Claude
Code as a Paperclip agent with tool use (shell, file edit). I did the
root-cause analysis, the local replays and the code change with this
model.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [ ] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: devinfoley <139239+devinfoley@users.noreply.github.com>
Co-authored-by: Paperclip <noreply@paperclip.ing>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 12:10:00 -08:00

145 lines
9.5 KiB
JavaScript

import assert from 'node:assert/strict';
import { execFileSync, spawn } from 'node:child_process';
import { createHash } from 'node:crypto';
import { existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, readlinkSync, rmSync, writeFileSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { fileURLToPath } from 'node:url';
import test from 'node:test';
import { grokPublicInstallVersion } from '../grok-public-install-sandbox.mjs';
import { startPackedRegistry, writePackedRegistryCatalog } from '../public-install-registry.mjs';
const script = fileURLToPath(new URL('../public-install-registry.mjs', import.meta.url));
const scratch = async body => {
const root = mkdtempSync(join(tmpdir(), 'public-install-registry-'));
try { await body(root); } finally { rmSync(root, { recursive: true, force: true }); }
};
const environment = root => ({ ...process.env, HOME: root, npm_config_cache: join(root, 'cache'),
npm_config_userconfig: join(root, 'no-npmrc'), npm_config_audit: 'false', npm_config_fund: 'false', npm_config_update_notifier: 'false', npm_config_fetch_retries: '0', npm_config_fetch_timeout: '10000' });
const run = (command, args, cwd, env = environment(cwd)) => new Promise((resolve, reject) => {
const child = spawn(command, args, { cwd, env, stdio: ['ignore', 'pipe', 'pipe'] });
let output = '';
for (const stream of [child.stdout, child.stderr]) stream.on('data', chunk => { output += chunk; });
child.once('error', reject);
child.once('exit', (code, signal) => code === 0 ? resolve(output) : reject(new Error(`${command} exited ${signal ?? code}: ${output}`)));
});
const fixture = (root, { publicDependency = false } = {}) => {
const assets = join(root, 'assets'); mkdirSync(assets);
const packs = [
{ name: '@ci/leaf', version: '1.0.0', main: 'index.js' },
{ name: '@ci/optional', version: '1.0.0' },
{ name: '@ci/root', version: '1.0.0', dependencies: { '@ci/leaf': '1.0.0', 'bundled-leaf': '1.0.0', ...(publicDependency ? { 'is-number': '7.0.0' } : {}) },
optionalDependencies: { '@ci/optional': '1.0.0' }, bundleDependencies: ['bundled-leaf'], bin: { 'ci-root': 'index.js' },
scripts: { postinstall: "node -e \"require('node:fs').writeFileSync('lifecycle-ran', 'ok')\"" } },
];
for (const [index, manifest] of packs.entries()) {
const source = join(root, `source-${index}`); mkdirSync(source);
writeFileSync(join(source, 'package.json'), JSON.stringify(manifest));
writeFileSync(join(source, 'index.js'), '#!/usr/bin/env node\nmodule.exports = 42;\n');
if (manifest.bundleDependencies) {
const bundle = join(source, 'node_modules/bundled-leaf'); mkdirSync(bundle, { recursive: true });
writeFileSync(join(bundle, 'package.json'), JSON.stringify({ name: 'bundled-leaf', version: '1.0.0', main: 'index.js' }));
writeFileSync(join(bundle, 'index.js'), 'module.exports = "bundled";\n');
}
execFileSync('npm', ['pack', '--ignore-scripts', '--pack-destination', assets], { cwd: source, env: environment(root), stdio: 'pipe' });
writeFileSync(join(source, 'package.json'), JSON.stringify({ ...manifest, version: '9.9.9' }));
}
return assets;
};
const installedFiles = directory => {
const entries = [];
const walk = (root, relative = '') => {
for (const item of readdirSync(root, { withFileTypes: true })) {
if (item.name === '.package-lock.json') continue;
const name = join(relative, item.name), path = join(root, item.name);
if (item.isDirectory()) walk(path, name);
else entries.push([name, item.isSymbolicLink() ? `link:${readlinkSync(path)}` : createHash('sha256').update(readFileSync(path)).digest('hex')]);
}
};
walk(directory);
return entries.sort(([a], [b]) => a.localeCompare(b));
};
test('synthetic Grok versions install from packed bytes even when the hash starts with leading-zero digits', { timeout: 30_000 }, async () => scratch(async root => {
const sourceRevision = '096091501644cf20f2e35d1ab02b28c35579b973';
const cases = [
{ version: `0.0.0-grok-verify.${sourceRevision.slice(0, 12)}`, rejected: true },
{ version: grokPublicInstallVersion(sourceRevision) },
{ version: grokPublicInstallVersion('8fd48a8d52038fd0d8b286f3742ea13ce40a7ab9') },
];
for (const [index, { version, rejected }] of cases.entries()) {
const cwd = join(root, String(index)), source = join(cwd, 'source'), assets = join(cwd, 'assets'), consumer = join(cwd, 'consumer');
for (const directory of [join(source, 'package'), assets, consumer]) mkdirSync(directory, { recursive: true });
writeFileSync(join(source, 'package/package.json'), JSON.stringify({ name: '@ci/grok-version', version }));
execFileSync('tar', ['-czf', join(assets, 'package.tgz'), '-C', source, 'package']);
await writePackedRegistryCatalog(assets);
writeFileSync(join(consumer, 'package.json'), '{"private":true}');
const userconfig = join(cwd, 'user.npmrc'), globalconfig = join(cwd, 'global.npmrc');
writeFileSync(userconfig, ''); writeFileSync(globalconfig, '');
const env = { PATH: process.env.PATH, HOME: cwd, npm_config_cache: join(cwd, 'cache'),
npm_config_userconfig: userconfig, npm_config_globalconfig: globalconfig,
npm_config_audit: 'false', npm_config_fund: 'false', npm_config_update_notifier: 'false', npm_config_fetch_retries: '0' };
const registry = await startPackedRegistry(assets);
try {
const install = run('npm', ['install', '--registry', registry.url, '--replace-registry-host=never', '--ignore-scripts', '--omit=dev', ...registry.specs], consumer, env);
if (rejected) await assert.rejects(install, /ETARGET/);
else {
await install;
assert.equal(JSON.parse(readFileSync(join(consumer, 'node_modules/@ci/grok-version/package.json'))).version, version);
}
} finally { await registry.close(); }
}
}));
test('real npm installs identical packed bytes, bundles, optional dependencies and bins without running scripts early', { timeout: 90_000 }, async () => scratch(async root => {
const assets = fixture(root, { publicDependency: true }), catalog = await writePackedRegistryCatalog(assets);
assert.ok(catalog.every(entry => entry.manifest.version === '1.0.0'), 'metadata must come from packed bytes, not changed source');
const before = join(root, 'file-consumer'), after = join(root, 'registry-consumer');
for (const cwd of [before, after]) { mkdirSync(cwd); writeFileSync(join(cwd, 'package.json'), '{"private":true}'); }
await run('npm', ['install', '--ignore-scripts', '--omit=dev', ...catalog.map(entry => join(assets, entry.file))], before);
await run(process.execPath, [script, assets], after);
assert.deepEqual(installedFiles(join(after, 'node_modules')), installedFiles(join(before, 'node_modules')));
for (const cwd of [before, after]) {
const marker = join(cwd, 'node_modules/@ci/root/lifecycle-ran');
assert.equal(existsSync(marker), false);
const lock = readFileSync(join(cwd, 'package-lock.json'), 'utf8');
const publicPackage = JSON.parse(lock).packages['node_modules/is-number'];
assert.equal(publicPackage.version, '7.0.0');
assert.equal(publicPackage.resolved, 'https://registry.npmjs.org/is-number/-/is-number-7.0.0.tgz');
await run('npm', ['rebuild', '--offline', '--ignore-scripts=false', '--foreground-scripts'], cwd);
assert.equal(readFileSync(marker, 'utf8'), 'ok');
assert.equal(readFileSync(join(cwd, 'package-lock.json'), 'utf8'), lock);
}
assert.deepEqual(installedFiles(join(after, 'node_modules')), installedFiles(join(before, 'node_modules')));
}));
test('the registry exposes only known tarballs, redirects other packages to npm and closes its listener', async () => scratch(async root => {
const assets = join(root, 'assets'); mkdirSync(assets);
writeFileSync(join(assets, 'registry-packages.json'), JSON.stringify([{ file: 'pkg.tgz', manifest: { name: '@ci/pkg', version: '1.0.0' }, integrity: 'sha512-YQ==' }]));
writeFileSync(join(assets, 'pkg.tgz'), 'packed bytes');
const registry = await startPackedRegistry(assets);
try {
const metadata = await (await fetch(`${registry.url}/@ci%2fpkg`)).json();
assert.equal(metadata.versions['1.0.0'].dist.integrity, 'sha512-YQ==');
assert.equal(await (await fetch(metadata.versions['1.0.0'].dist.tarball)).text(), 'packed bytes');
const external = await fetch(`${registry.url}/@other%2fpkg`, { redirect: 'manual' });
assert.equal(external.status, 302);
assert.equal(external.headers.get('location'), 'https://registry.npmjs.org/@other%2fpkg');
const unscoped = await fetch(`${registry.url}/other-pkg`, { redirect: 'manual' });
assert.equal(unscoped.headers.get('location'), 'https://registry.npmjs.org/other-pkg');
assert.equal((await fetch(`${registry.url}/-/900.tgz`)).status, 404);
assert.equal((await fetch(`${registry.url}/some%2foutside%2ffile`)).status, 404);
assert.equal((await fetch(`${registry.url}/@ci%2fpkg`, { method: 'POST' })).status, 405);
} finally { await registry.close(); }
await assert.rejects(fetch(`${registry.url}/@ci%2fpkg`));
}));
test('npm rejects changed tarball bytes against the catalog integrity and the CLI reports failure', { timeout: 90_000 }, async () => scratch(async root => {
const assets = fixture(root), catalog = await writePackedRegistryCatalog(assets);
const archive = join(assets, catalog[0].file);
const bytes = readFileSync(archive);
bytes[4] ^= 1; writeFileSync(archive, bytes);
const consumer = join(root, 'consumer'); mkdirSync(consumer); writeFileSync(join(consumer, 'package.json'), '{"private":true}');
await assert.rejects(run(process.execPath, [script, assets], consumer), /EINTEGRITY/);
}));