Files
imccyu 8d6f5164ab fix(release): make publication retry, space out, and skip what landed
A landlock publication failed with `E409 Failed to save packument` on the
second of three packages. The registry answers a write it could not commit that
way, and publishing several packages back to back is what provokes it.

Neither publish path could recover. The native sequence published from a shell
loop of bare `npm publish` calls: no retry, and no way to resume, because the
registry rejects a repeat of an existing version permanently — so a failure
partway through left the release stuck. publish.ts skipped versions already
present, which made a re-run safe, but had no retry either.

Both paths now attempt a tarball up to four times, space writes at least two
seconds apart, and back off 2s/4s/8s between attempts. Every retry re-reads the
registry first, because a reported failure can answer a write that landed
anyway: a version that now exists with this tarball's integrity counts as
published rather than as one to place again. That same re-read is what turns a
mid-run `E403 cannot publish over the previously published versions` into a
skip when the bytes match, and leaves it a hard failure when they do not.

The native sequence gets the registry comparison publish.ts already had, through
its own script rather than shared code — the two sequences keep separate
publication paths. Its publish job now checks out the repository, which the
shell loop did not need.

Verified against a scripted registry: a clean publish, one E409 then success, an
E409 whose write landed anyway, E409 on every attempt (fails after four), and a
version already present with matching integrity (publishes nothing).
2026-08-13 15:31:09 +08:00

170 lines
7.0 KiB
TypeScript

/**
* Publish one packed release family from the tarballs the pack step produced.
*
* Publication is decided per package against the registry, never from a list of
* "what this release includes": a version the registry lacks is published, a
* version whose published tarball has the same integrity is skipped, and a
* version whose published tarball differs fails the run — that last case means
* the content changed without a version bump
* ([rationale](../../.agents/notes/implemented/process/2026-08-10-npm-release-sequences.md)).
*
* Skipping on identical integrity is what makes re-running the publish step over
* the same artifact safe.
*/
import { createHash } from 'node:crypto'
import { readFileSync } from 'node:fs'
import { join, resolve } from 'node:path'
import { setTimeout as sleep } from 'node:timers/promises'
import { parseArgs } from 'node:util'
import { releaseFamily } from './families.ts'
import { attempt, isEntry } from './process.ts'
import { packedIdentity, readPublishOrder } from './tarball.ts'
/**
* Registry codes that answer a write which did not settle, rather than a
* rejection of what was sent. `E409 Failed to save packument` is the one this
* sequence actually hits: publishing several packages in a row can outrun the
* registry's own processing. A rejected payload (`E403` over an existing
* version, a malformed manifest) never clears on a retry and must surface.
*/
const TRANSIENT_PUBLISH_CODES = ['E409', 'E429', 'E500', 'E502', 'E503', 'E504', 'ETIMEDOUT', 'ECONNRESET', 'EAI_AGAIN'] as const
/** How many times one tarball's publish is attempted before the run fails. */
const PUBLISH_ATTEMPTS = 4
/**
* Shortest gap between two publishes, and the first retry backoff.
*
* The registry needs a moment to commit a packument before the next write; back
* to back publishes are what produce `E409`.
*/
const PUBLISH_SPACING_MS = 2_000
/** What the registry knows about one version. */
type RegistryState =
| { readonly kind: 'absent' }
| { readonly kind: 'present'; readonly integrity: string }
/**
* Whether a failed publish is worth another attempt.
* @param output - combined npm output.
* @returns True when the registry reported a write it did not commit.
*/
function isTransientFailure(output: string): boolean {
return TRANSIENT_PUBLISH_CODES.some(code => output.includes(`code ${code}`))
}
/**
* The subresource integrity string npm records for a tarball.
* @param tarball - absolute tarball path.
* @returns A `sha512-<base64>` string.
*/
function integrityOf(tarball: string): string {
return `sha512-${createHash('sha512').update(readFileSync(tarball)).digest('base64')}`
}
/**
* Ask the registry whether a version exists, and with what integrity.
* @param name - package name.
* @param version - package version.
* @returns The registry state for that version.
*/
function registryState(name: string, version: string): RegistryState {
const result = attempt('npm', ['view', `${name}@${version}`, 'dist.integrity', '--json'])
if (result.status !== 0) {
const output = `${result.stdout}${result.stderr}`
if (output.includes('E404') || output.includes('404 Not Found')) return { kind: 'absent' }
throw new Error(`npm view ${name}@${version} failed:\n${output}`)
}
const parsed: unknown = JSON.parse(result.stdout)
if (typeof parsed !== 'string' || parsed === '') {
throw new Error(`registry reported no dist.integrity for ${name}@${version}`)
}
return { kind: 'present', integrity: parsed }
}
/**
* Publish one tarball, retrying a registry write that did not settle.
*
* Every retry re-reads the registry first, because `E409` can answer a write
* that landed anyway: republishing a version that now exists fails permanently,
* so the same integrity appearing under the failed attempt counts as success.
* @param tarball - absolute tarball path.
* @param name - package name the tarball declares.
* @param version - package version the tarball declares.
*/
async function publishTarball(tarball: string, name: string, version: string): Promise<void> {
// A prerelease version never takes the latest dist-tag.
const tagArgs = version.includes('-') ? ['--tag', 'next'] : []
for (let tries = 1; tries <= PUBLISH_ATTEMPTS; tries += 1) {
// No --access: the sequences do not share one access level, so a
// command-line flag could not serve both and would override the manifest
// that does. Each packed manifest decides, and
// check-workspace-constraints holds every manifest to its sequence's level.
const result = attempt('npm', ['publish', tarball, ...tagArgs])
const output = `${result.stdout}${result.stderr}`
if (result.status === 0) return
const settled = registryState(name, version)
if (settled.kind === 'present' && settled.integrity === integrityOf(tarball)) {
console.log(`release publish: ${name}@${version} landed despite a reported failure, continuing`)
return
}
if (tries === PUBLISH_ATTEMPTS || !isTransientFailure(output)) {
throw new Error(`npm publish ${name}@${version} failed:\n${output}`)
}
const backoff = PUBLISH_SPACING_MS * 2 ** (tries - 1)
console.log(
`release publish: ${name}@${version} hit a transient registry failure`
+ ` (attempt ${String(tries)} of ${String(PUBLISH_ATTEMPTS)}), retrying in ${String(backoff)}ms`,
)
await sleep(backoff)
}
}
/** Publish the family named by `--family` from the directory named by `--from`. */
async function main(): Promise<void> {
const { values } = parseArgs({
options: { family: { type: 'string' }, from: { type: 'string' } },
allowPositionals: false,
})
if (values.family === undefined || values.from === undefined) {
throw new Error('usage: publish.ts --family <dsh|vendor> --from <packed directory>')
}
const family = releaseFamily(values.family)
const directory = resolve(process.cwd(), values.from)
let published = 0
let skipped = 0
for (const filename of readPublishOrder(directory)) {
const tarball = join(directory, filename)
const { name, version } = packedIdentity(tarball)
const state = registryState(name, version)
if (state.kind === 'present') {
const local = integrityOf(tarball)
if (state.integrity !== local) {
throw new Error(
`${name}@${version} is already published with different content`
+ `\n registry: ${state.integrity}\n packed: ${local}`
+ '\nBump the version, or investigate why the build is not reproducible.',
)
}
console.log(`release publish: ${name}@${version} already published, skipping`)
skipped += 1
continue
}
// Space out the writes: the gap belongs between publishes, so a run that
// only skips does not wait at all.
if (published > 0) await sleep(PUBLISH_SPACING_MS)
await publishTarball(tarball, name, version)
console.log(`release publish: ${name}@${version} published`)
published += 1
}
console.log(`release publish: family ${family.id}, ${String(published)} published, ${String(skipped)} already present`)
}
if (isEntry(import.meta.url)) await main()