Files
paperclip/scripts/run-vitest-stable.mjs
T
Devin Foley 81d18f2d77 ci: speed up PR verify workflow (#6137)
## Thinking Path

> - Paperclip orchestrates AI agents through a control-plane repo that
relies on GitHub Actions as part of its release and verification safety
net.
> - The PR workflow in `.github/workflows/pr.yml` is the core CI path
protecting pull requests before merge.
> - Baseline measurement work in [PAPA-335](/PAPA/issues/PAPA-335)
showed the old single `verify` job was the critical-path bottleneck,
with general tests and build serialized together.
> - Follow-up implementation in [PAPA-338](/PAPA/issues/PAPA-338) and
[PAPA-339](/PAPA/issues/PAPA-339) split that work into parallel lanes
and removed redundant clean-runner prebuild work.
> - [PAPA-340](/PAPA/issues/PAPA-340) now needs real post-change PR
workflow evidence, not local inference, to compare against the May 15,
2026 baseline and decide whether phase-2 work is still justified.
> - This pull request publishes the already-implemented CI speedup
branch so GitHub can run the actual `PR` workflow against it.
> - The benefit is that CI timing decisions are based on measured runs
from the exact workflow shape we intend to ship.

## What Changed

- Split the PR workflow so `policy` fans out into separate `Typecheck +
Release Registry`, grouped `General tests`, and `Build` jobs.
- Kept the serialized server matrix, canary dry run, and e2e jobs intact
while removing the old monolithic `verify` bottleneck.
- Reworked grouped general-test execution in
`scripts/run-vitest-stable.mjs` so the workflow can run balanced
non-serialized lanes.
- Replaced redundant clean-runner prebuild gates with the idempotent
`ensure-build-deps` path used by the relevant CI entrypoints.

## Verification

- `ruby -e "require 'yaml'; YAML.load_file('.github/workflows/pr.yml');
puts 'yaml-ok'"`
- `node scripts/run-vitest-stable.mjs --mode general --dry-run`
- `node scripts/run-vitest-stable.mjs --mode general --group
general-server --dry-run`
- `node scripts/run-vitest-stable.mjs --mode general --group
general-workspaces-a --dry-run`
- `node scripts/run-vitest-stable.mjs --mode general --group
general-workspaces-b --dry-run`
- `pnpm test:run:general -- --group general-workspaces-b`
- `pnpm test:run:general -- --group general-workspaces-a`
- `pnpm test:run:general -- --group general-server`
- `pnpm run typecheck:build-gaps`
- `pnpm --filter @paperclipai/plugin-hello-world-example typecheck`

## Risks

- Required-check and branch-protection settings may still reference the
old single `verify` job name.
- Parallel CI lanes can expose hidden ordering assumptions or
clean-runner bootstrap gaps that local grouped dry-runs did not surface.
- Because the branch is behind current `master`, merge conflicts or
unrelated upstream drift could affect the measured runtime until the
branch is rebased.

> Checked `ROADMAP.md`; this work is CI throughput maintenance for the
existing PR verification path, not duplicate feature work.

## Model Used

- OpenAI Codex via Paperclip `codex_local`, GPT-5-class coding agent
with repository read/write, shell execution, and GitHub CLI/tool use.
The runtime does not expose a more specific backend model ID in-session.

## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-05-16 11:28:25 -07:00

362 lines
11 KiB
JavaScript

#!/usr/bin/env node
import { spawnSync } from "node:child_process";
import { mkdirSync, mkdtempSync, readdirSync, statSync } from "node:fs";
import os from "node:os";
import path from "node:path";
const repoRoot = process.cwd();
const serverRoot = path.join(repoRoot, "server");
const serverTestsDir = path.join(repoRoot, "server", "src", "__tests__");
const nonServerProjects = [
"@paperclipai/shared",
"@paperclipai/db",
"@paperclipai/adapter-utils",
"@paperclipai/adapter-acpx-local",
"@paperclipai/adapter-codex-local",
"@paperclipai/adapter-opencode-local",
"@paperclipai/plugin-sdk",
"@paperclipai/ui",
"paperclipai",
];
const routeTestPattern = /[^/]*(?:route|routes|authz)[^/]*\.test\.ts$/;
const additionalSerializedServerTests = new Set([
"server/src/__tests__/approval-routes-idempotency.test.ts",
"server/src/__tests__/assets.test.ts",
"server/src/__tests__/authz-company-access.test.ts",
"server/src/__tests__/companies-route-path-guard.test.ts",
"server/src/__tests__/company-portability.test.ts",
"server/src/__tests__/costs-service.test.ts",
"server/src/__tests__/express5-auth-wildcard.test.ts",
"server/src/__tests__/health-dev-server-token.test.ts",
"server/src/__tests__/health.test.ts",
"server/src/__tests__/heartbeat-dependency-scheduling.test.ts",
"server/src/__tests__/heartbeat-issue-liveness-escalation.test.ts",
"server/src/__tests__/heartbeat-process-recovery.test.ts",
"server/src/__tests__/invite-accept-existing-member.test.ts",
"server/src/__tests__/invite-accept-gateway-defaults.test.ts",
"server/src/__tests__/invite-accept-replay.test.ts",
"server/src/__tests__/invite-expiry.test.ts",
"server/src/__tests__/invite-join-manager.test.ts",
"server/src/__tests__/invite-onboarding-text.test.ts",
"server/src/__tests__/issues-checkout-wakeup.test.ts",
"server/src/__tests__/issues-service.test.ts",
"server/src/__tests__/opencode-local-adapter-environment.test.ts",
"server/src/__tests__/project-routes-env.test.ts",
"server/src/__tests__/redaction.test.ts",
"server/src/__tests__/routines-e2e.test.ts",
]);
let invocationIndex = 0;
const serializedModeName = "serialized";
const generalModeName = "general";
const allModeName = "all";
const generalServerGroupName = "general-server";
const generalWorkspacesAGroupName = "general-workspaces-a";
const generalWorkspacesBGroupName = "general-workspaces-b";
const generalWorkspacesAProjects = ["@paperclipai/ui", "paperclipai"];
const generalWorkspacesBProjects = nonServerProjects.filter((project) => !generalWorkspacesAProjects.includes(project));
const generalGroupNames = [generalServerGroupName, generalWorkspacesAGroupName, generalWorkspacesBGroupName];
function walk(dir) {
const entries = readdirSync(dir);
const files = [];
for (const entry of entries) {
const absolute = path.join(dir, entry);
const stats = statSync(absolute);
if (stats.isDirectory()) {
files.push(...walk(absolute));
} else if (stats.isFile()) {
files.push(absolute);
}
}
return files;
}
function toRepoPath(file) {
return path.relative(repoRoot, file).split(path.sep).join("/");
}
function toServerPath(file) {
return path.relative(serverRoot, file).split(path.sep).join("/");
}
function isRouteOrAuthzTest(file) {
if (routeTestPattern.test(file)) {
return true;
}
return additionalSerializedServerTests.has(file);
}
function fail(message) {
console.error(`[test:run] ${message}`);
process.exit(1);
}
function readOptionValue(argv, index, argName) {
const value = argv[index + 1];
if (value === undefined) {
fail(`Missing value for ${argName}`);
}
return value;
}
function parseNonNegativeInteger(value, argName) {
const parsed = Number(value);
if (value.trim() === "" || !Number.isInteger(parsed) || parsed < 0) {
fail(`${argName} must be a non-negative integer. Received "${value}".`);
}
return parsed;
}
function parsePositiveInteger(value, argName) {
const parsed = Number(value);
if (value.trim() === "" || !Number.isInteger(parsed) || parsed < 1) {
fail(`${argName} must be a positive integer. Received "${value}".`);
}
return parsed;
}
function parseCliOptions(argv) {
let mode = allModeName;
let shardIndex = null;
let shardCount = null;
let group = null;
let dryRun = false;
for (let index = 0; index < argv.length; index += 1) {
const arg = argv[index];
if (arg === "--") {
continue;
}
if (arg === "--mode") {
mode = readOptionValue(argv, index, arg);
index += 1;
continue;
}
if (arg.startsWith("--mode=")) {
mode = arg.slice("--mode=".length);
continue;
}
if (arg === "--shard-index") {
shardIndex = parseNonNegativeInteger(readOptionValue(argv, index, arg), arg);
index += 1;
continue;
}
if (arg.startsWith("--shard-index=")) {
shardIndex = parseNonNegativeInteger(arg.slice("--shard-index=".length), "--shard-index");
continue;
}
if (arg === "--shard-count") {
shardCount = parsePositiveInteger(readOptionValue(argv, index, arg), arg);
index += 1;
continue;
}
if (arg.startsWith("--shard-count=")) {
shardCount = parsePositiveInteger(arg.slice("--shard-count=".length), "--shard-count");
continue;
}
if (arg === "--dry-run") {
dryRun = true;
continue;
}
if (arg === "--group") {
group = readOptionValue(argv, index, arg);
index += 1;
continue;
}
if (arg.startsWith("--group=")) {
group = arg.slice("--group=".length);
continue;
}
fail(`Unknown argument "${arg}".`);
}
if (!new Set([allModeName, generalModeName, serializedModeName]).has(mode)) {
fail(`Unknown mode "${mode}". Expected one of: ${allModeName}, ${generalModeName}, ${serializedModeName}.`);
}
if ((shardIndex === null) !== (shardCount === null)) {
fail("--shard-index and --shard-count must be provided together.");
}
if (mode !== serializedModeName && shardIndex !== null) {
fail("--shard-index/--shard-count are only valid with --mode serialized.");
}
if (group !== null && mode !== generalModeName) {
fail("--group is only valid with --mode general.");
}
if (group !== null && !generalGroupNames.includes(group)) {
fail(`Unknown group "${group}". Expected one of: ${generalGroupNames.join(", ")}.`);
}
if (mode === serializedModeName) {
const resolvedShardCount = shardCount ?? 1;
const resolvedShardIndex = shardIndex ?? 0;
if (resolvedShardIndex >= resolvedShardCount) {
fail(`--shard-index must be less than --shard-count. Received ${resolvedShardIndex} of ${resolvedShardCount}.`);
}
return {
mode,
shardIndex: resolvedShardIndex,
shardCount: resolvedShardCount,
group: null,
dryRun,
};
}
return {
mode,
shardIndex: null,
shardCount: null,
group,
dryRun,
};
}
function selectSerializedSuites(routeTests, shardIndex, shardCount) {
return routeTests.filter((_, index) => index % shardCount === shardIndex);
}
function runVitest(args, label) {
console.log(`\n[test:run] ${label}`);
invocationIndex += 1;
const tempRootParent = process.platform === "win32" ? os.tmpdir() : "/tmp";
const testRoot = mkdtempSync(path.join(tempRootParent, `pcvt-${process.pid}-${invocationIndex}-`));
// Keep per-run paths compact so Unix socket fixtures stay under macOS path limits.
const env = {
...process.env,
PAPERCLIP_HOME: path.join(testRoot, "h"),
PAPERCLIP_INSTANCE_ID: `vt-${process.pid}-${invocationIndex}`,
TMPDIR: path.join(testRoot, "t"),
};
mkdirSync(env.PAPERCLIP_HOME, { recursive: true });
mkdirSync(env.TMPDIR, { recursive: true });
const result = spawnSync("pnpm", ["exec", "vitest", "run", ...args], {
cwd: repoRoot,
env,
stdio: "inherit",
});
if (result.error) {
console.error(`[test:run] Failed to start Vitest: ${result.error.message}`);
process.exit(1);
}
if (result.status !== 0) {
process.exit(result.status ?? 1);
}
}
function runGeneralSuites(routeTests) {
for (const groupName of generalGroupNames) {
runGeneralGroup(routeTests, groupName);
}
}
function runProjectGroup(projects, groupName) {
for (const project of projects) {
runVitest(["--project", project], `${groupName} project ${project}`);
}
}
function runGeneralGroup(routeTests, groupName) {
if (groupName === generalServerGroupName) {
const excludeRouteArgs = routeTests.flatMap((file) => ["--exclude", file.serverPath]);
runVitest(
["--project", "@paperclipai/server", ...excludeRouteArgs],
`${groupName} server suites excluding ${routeTests.length} serialized suites`,
);
return;
}
if (groupName === generalWorkspacesAGroupName) {
runProjectGroup(generalWorkspacesAProjects, groupName);
return;
}
if (groupName === generalWorkspacesBGroupName) {
runProjectGroup(generalWorkspacesBProjects, groupName);
return;
}
fail(`Unknown group "${groupName}".`);
}
function runSerializedSuites(routeTests, shardIndex, shardCount) {
const shardTests = selectSerializedSuites(routeTests, shardIndex, shardCount);
console.log(
`\n[test:run] serialized shard ${shardIndex + 1}/${shardCount} running ${shardTests.length} of ${routeTests.length} suites`,
);
for (const routeTest of shardTests) {
runVitest(
[
"--project",
"@paperclipai/server",
routeTest.repoPath,
"--pool=forks",
"--poolOptions.forks.isolate=true",
],
routeTest.repoPath,
);
}
}
const routeTests = walk(serverTestsDir)
.filter((file) => isRouteOrAuthzTest(toRepoPath(file)))
.map((file) => ({
repoPath: toRepoPath(file),
serverPath: toServerPath(file),
}))
.sort((a, b) => a.repoPath.localeCompare(b.repoPath));
const options = parseCliOptions(process.argv.slice(2));
if (options.dryRun) {
const serializedSuites =
options.mode === serializedModeName
? selectSerializedSuites(routeTests, options.shardIndex, options.shardCount)
: routeTests;
console.log(
JSON.stringify(
{
mode: options.mode,
shardIndex: options.shardIndex,
shardCount: options.shardCount,
group: options.group,
availableGeneralGroups: generalGroupNames,
serializedSuiteCount: routeTests.length,
selectedSerializedSuites: serializedSuites.map((routeTest) => routeTest.repoPath),
},
null,
2,
),
);
process.exit(0);
}
if (options.mode === generalModeName || options.mode === allModeName) {
if (options.group) {
runGeneralGroup(routeTests, options.group);
} else {
runGeneralSuites(routeTests);
}
}
if (options.mode === serializedModeName || options.mode === allModeName) {
runSerializedSuites(routeTests, options.shardIndex ?? 0, options.shardCount ?? 1);
}