Files
PaperClipAI/scripts/__tests__/release-verify-workflow.test.mjs
T
Devin Foley 2da6a248c3 fix(release): surface recovery commands when a lane tag push is rejected (#11208)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - The release subsystem's promotion lanes publish to npm, then push a
lane tag and dispatch the Docker image build at that tag
> - The first nightly of the beta-tooling merge published to npm and
then died at the tag push: GITHUB_TOKEN may not create refs pointing at
workflow-modifying commits from dispatch or scheduled runs
> - The failure was a bare `remote rejected` with no guidance, leaving
the release half-finished (npm live, no tag, no images) until an
operator reverse-engineered the recovery
> - This pull request makes every lane's tag push degrade into exact
recovery instructions in the job summary
> - The benefit is that a rare platform-permission rejection becomes a
two-minute runbook operation instead of a forensic exercise

## Linked Issues or Issue Description

Refs #11008 — the incident occurred promoting that change's own merge
commit, the first workflow-modifying commit to flow through the lanes it
introduced.

**Subsystem affected**

Release automation: `.github/workflows/release.yml`, `doc/RELEASING.md`,
workflow wiring tests.

**Problem or motivation**

Run 31445344811 published `2026.811.0-nightly.0` to npm, then failed
pushing `nightly/v2026.811.0-nightly.0`: `refusing to allow a GitHub App
to create or update workflow .github/workflows/release.yml without
workflows permission`. The tagged commit modifies workflow files, and
GITHUB_TOKEN may not create refs pointing at such commits from dispatch
or scheduled runs (push-event runs are exempt, which is why the canary
tag on the same commit succeeded). The job failed with no explanation
and the Docker dispatch never ran.

**Proposed solution**

Wrap the nightly, beta, and stable tag pushes: on rejection, write the
exact recovery commands into the job summary — create and push the tag
with maintainer credentials, dispatch `docker.yml` at the tag, and for
stable also run `create-github-release.sh` — then fail the job. Document
the cause and recovery in the failure playbooks and pin the three
recovery blocks with a wiring test.

## What Changed

- `.github/workflows/release.yml`: recovery-summary wrappers on the
nightly, beta, and stable tag-push steps
- `doc/RELEASING.md`: failure-playbook entry for the
workflows-permission rejection
- `scripts/__tests__/release-verify-workflow.test.mjs`: wiring test
asserting all three lanes carry the recovery summary

## Verification

- Wiring tests: 6 pass; YAML parse of the workflow
- The recovery commands are exactly the ones used to resolve the real
incident (tag push + `docker.yml` dispatch for
`nightly/v2026.811.0-nightly.0`)

## Risks

- Low. The happy path is unchanged (a successful push skips the
wrapper); the failure path trades a bare error for actionable output and
still fails the job, since the release state is genuinely incomplete

## Model Used

Claude Fable 5 (`claude-fable-5`, Anthropic) in Claude Code, with
extended thinking and full tool use. All changes model-authored under
human direction.

## 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 (pending — will confirm before
merge)
- [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
(pending — will confirm before merge)
- [x] I will address all Greptile and reviewer comments before
requesting merge
2026-08-11 08:48:13 -07:00

109 lines
5.1 KiB
JavaScript

import assert from "node:assert/strict";
import { readFileSync } from "node:fs";
import path from "node:path";
import { fileURLToPath } from "node:url";
import test from "node:test";
const repoRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..", "..");
function readWorkflow(name) {
return readFileSync(path.join(repoRoot, ".github/workflows", name), "utf8");
}
test("release workflow delegates stable and canary verification to the reusable workflow", () => {
const releaseWorkflow = readWorkflow("release.yml");
assert.match(
releaseWorkflow,
/verify_canary:\n\s+if: github\.event_name == 'push'\n\s+uses: \.\/\.github\/workflows\/release-verify\.yml\n\s+with:\n\s+ref: \$\{\{ github\.sha \}\}/,
);
// The stable lane is gated on the stable channel since the nightly lane
// was added; a `needs:` line (for example a preflight job) may sit between
// the gate and the delegation.
// The stable preflight resolves source_ref to an immutable SHA exactly
// once; verification must consume that pin, not re-resolve the ref.
assert.match(
releaseWorkflow,
/verify_stable:\n\s+if: github\.event_name == 'workflow_dispatch' && inputs\.channel == 'stable'\n(?:\s+needs: [^\n]+\n)?\s+uses: \.\/\.github\/workflows\/release-verify\.yml\n\s+with:\n\s+ref: \$\{\{ needs\.preflight_stable\.outputs\.sha \}\}/,
);
assert.doesNotMatch(releaseWorkflow, /verify_(?:canary|stable):[\s\S]*?pnpm test:run(?:\n|$)/);
});
test("onboard smoke container binds beyond loopback so the mapped port is reachable", () => {
const dockerfile = readFileSync(path.join(repoRoot, "docker/Dockerfile.onboard-smoke"), "utf8");
// `onboard --yes` without an explicit --bind prefers trusted-local
// defaults and writes a loopback bind, which Docker port mapping cannot
// reach. The smoke container must pin a non-loopback preset.
assert.match(dockerfile, /onboard --yes --bind lan/);
});
test("promotion selection guards against sources that predate their channel tooling", () => {
const releaseWorkflow = readWorkflow("release.yml");
// Promotions run the source commit's release.sh, so selection must reject
// sources whose tooling does not know the target channel yet.
assert.match(releaseWorkflow, /git show "\$\{sha\}:scripts\/release\.sh" \| grep -qF 'canary\|nightly'/);
assert.match(releaseWorkflow, /git show "\$\{sha\}:scripts\/release\.sh" \| grep -qF 'canary\|nightly\|beta\|stable\)'/);
});
test("every lane's tag push degrades to recovery instructions when rejected", () => {
const releaseWorkflow = readWorkflow("release.yml");
// GITHUB_TOKEN may not create refs pointing at workflow-modifying commits
// from dispatch or scheduled runs; a rejected tag push after a successful
// npm publish must surface runbook recovery commands, not a bare error.
const occurrences = releaseWorkflow.match(/## Tag push rejected/g) ?? [];
assert.equal(occurrences.length, 3, "nightly, beta, and stable each carry the recovery summary");
});
test("release smoke workflow extends the container readiness budget for CI", () => {
const smokeWorkflow = readWorkflow("release-smoke.yml");
const harness = readFileSync(path.join(repoRoot, "scripts/docker-onboard-smoke.sh"), "utf8");
// CI containers cold-install paperclipai and embedded postgres, so the
// workflow must extend the harness's local-default readiness budget.
assert.match(smokeWorkflow, /SMOKE_READY_TIMEOUT_SECONDS=\d+/);
const ciBudget = Number(smokeWorkflow.match(/SMOKE_READY_TIMEOUT_SECONDS=(\d+)/)[1]);
assert.ok(ciBudget >= 300, `CI readiness budget ${ciBudget}s should be at least 300s`);
assert.match(harness, /SMOKE_READY_TIMEOUT_SECONDS="\$\{SMOKE_READY_TIMEOUT_SECONDS:-\d+\}"/);
assert.match(harness, /wait_for_http "\$PAPERCLIP_PUBLIC_URL\/api\/health" "\$SMOKE_READY_TIMEOUT_SECONDS" 1/);
});
test("release verify workflow covers the same split test surface as stable PR verification", () => {
const verifyWorkflow = readWorkflow("release-verify.yml");
assert.match(verifyWorkflow, /workflow_call:/);
assert.match(verifyWorkflow, /node \.\/scripts\/release-package-map\.mjs check/);
assert.match(verifyWorkflow, /pnpm -r typecheck/);
assert.match(verifyWorkflow, /pnpm build/);
for (const group of ["general-server", "general-workspaces-a", "general-workspaces-b"]) {
assert.match(verifyWorkflow, new RegExp(`group: ${group}`));
}
for (const shardIndex of [0, 1, 2]) {
assert.match(
verifyWorkflow,
new RegExp(`group: general-server[\\s\\S]*?shard_index: ${shardIndex}[\\s\\S]*?shard_count: 3`),
);
}
for (const shardIndex of [0, 1, 2, 3, 4]) {
assert.match(verifyWorkflow, new RegExp(`shard_index: ${shardIndex}[\\s\\S]*?shard_count: 5`));
}
// workspaces-a splits with Vitest native --shard in pr.yml; release
// verification must keep the same two-shard coverage.
for (const shardIndex of [0, 1]) {
assert.match(
verifyWorkflow,
new RegExp(`group: general-workspaces-a[\\s\\S]*?shard_index: ${shardIndex}\\n\\s+shard_count: 2`),
);
}
assert.match(verifyWorkflow, /pnpm test:run:general -- --group/);
assert.match(verifyWorkflow, /pnpm test:run:serialized -- --shard-index/);
});