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>
This commit is contained in:
Devin Foley
@@ -62,7 +62,8 @@ jobs:
|
||||
pnpm install --lockfile-only --ignore-scripts --no-frozen-lockfile
|
||||
fi
|
||||
|
||||
verify:
|
||||
typecheck_release_registry:
|
||||
name: Typecheck + Release Registry
|
||||
needs: [policy]
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
@@ -88,12 +89,89 @@ jobs:
|
||||
- name: Typecheck workspaces whose build scripts skip TypeScript
|
||||
run: pnpm run typecheck:build-gaps
|
||||
|
||||
- name: Run general test suites
|
||||
run: pnpm test:run:general
|
||||
|
||||
- name: Verify release registry test coverage
|
||||
run: pnpm run test:release-registry
|
||||
|
||||
general_tests:
|
||||
name: General tests (${{ matrix.group_label }})
|
||||
needs: [policy]
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- group: general-server
|
||||
group_label: server
|
||||
- group: general-workspaces-a
|
||||
group_label: workspaces-a
|
||||
- group: general-workspaces-b
|
||||
group_label: workspaces-b
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup pnpm
|
||||
uses: pnpm/action-setup@v4
|
||||
with:
|
||||
version: 9.15.4
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 24
|
||||
cache: pnpm
|
||||
|
||||
- name: Install dependencies
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run grouped general test suites
|
||||
run: pnpm test:run:general -- --group '${{ matrix.group }}'
|
||||
|
||||
verify:
|
||||
# Preserve the legacy required-check name while the underlying work runs in parallel.
|
||||
name: verify
|
||||
if: ${{ always() }}
|
||||
needs: [typecheck_release_registry, general_tests, build]
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
|
||||
steps:
|
||||
- name: Fail if any split verify lane failed
|
||||
env:
|
||||
TYPECHECK_RELEASE_REGISTRY_RESULT: ${{ needs.typecheck_release_registry.result }}
|
||||
GENERAL_TESTS_RESULT: ${{ needs.general_tests.result }}
|
||||
BUILD_RESULT: ${{ needs.build.result }}
|
||||
run: |
|
||||
test "$TYPECHECK_RELEASE_REGISTRY_RESULT" = "success"
|
||||
test "$GENERAL_TESTS_RESULT" = "success"
|
||||
test "$BUILD_RESULT" = "success"
|
||||
|
||||
build:
|
||||
name: Build
|
||||
needs: [policy]
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup pnpm
|
||||
uses: pnpm/action-setup@v4
|
||||
with:
|
||||
version: 9.15.4
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: 24
|
||||
cache: pnpm
|
||||
|
||||
- name: Install dependencies
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Build
|
||||
run: pnpm build
|
||||
|
||||
|
||||
+2
-2
@@ -19,8 +19,8 @@
|
||||
"test": "pnpm run test:run",
|
||||
"test:watch": "pnpm run preflight:workspace-links && vitest",
|
||||
"test:run": "pnpm run preflight:workspace-links && node scripts/run-vitest-stable.mjs",
|
||||
"test:run:general": "pnpm run preflight:workspace-links && pnpm --filter @paperclipai/plugin-sdk build && node scripts/run-vitest-stable.mjs --mode general",
|
||||
"test:run:serialized": "pnpm run preflight:workspace-links && pnpm --filter @paperclipai/plugin-sdk build && node scripts/run-vitest-stable.mjs --mode serialized",
|
||||
"test:run:general": "pnpm run preflight:workspace-links && pnpm --filter @paperclipai/plugin-sdk ensure-build-deps && node scripts/run-vitest-stable.mjs --mode general",
|
||||
"test:run:serialized": "pnpm run preflight:workspace-links && pnpm --filter @paperclipai/plugin-sdk ensure-build-deps && node scripts/run-vitest-stable.mjs --mode serialized",
|
||||
"db:generate": "pnpm --filter @paperclipai/db generate",
|
||||
"db:migrate": "pnpm --filter @paperclipai/db migrate",
|
||||
"issue-references:backfill": "pnpm run preflight:workspace-links && tsx scripts/backfill-issue-reference-mentions.ts",
|
||||
|
||||
@@ -3,13 +3,26 @@ set -euo pipefail
|
||||
|
||||
# prepare-server-ui-dist.sh — Build the UI and copy it into server/ui-dist.
|
||||
# This keeps @paperclipai/server publish artifacts self-contained for static UI serving.
|
||||
# When PAPERCLIP_RELEASE_REUSE_UI_DIST=1 and ui/dist already exists, reuse that
|
||||
# output instead of rebuilding it again inside the release packaging flow.
|
||||
|
||||
REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
||||
UI_DIST="$REPO_ROOT/ui/dist"
|
||||
SERVER_UI_DIST="$REPO_ROOT/server/ui-dist"
|
||||
|
||||
echo " -> Building @paperclipai/ui..."
|
||||
pnpm --dir "$REPO_ROOT" --filter @paperclipai/ui build
|
||||
should_reuse_existing_ui_dist=false
|
||||
case "${PAPERCLIP_RELEASE_REUSE_UI_DIST:-}" in
|
||||
1|true|TRUE|yes|YES)
|
||||
should_reuse_existing_ui_dist=true
|
||||
;;
|
||||
esac
|
||||
|
||||
if [ "$should_reuse_existing_ui_dist" = true ] && [ -f "$UI_DIST/index.html" ]; then
|
||||
echo " -> Reusing existing @paperclipai/ui dist output"
|
||||
else
|
||||
echo " -> Building @paperclipai/ui..."
|
||||
pnpm --dir "$REPO_ROOT" --filter @paperclipai/ui build
|
||||
fi
|
||||
|
||||
if [ ! -f "$UI_DIST/index.html" ]; then
|
||||
echo "Error: UI build output missing at $UI_DIST/index.html"
|
||||
|
||||
@@ -198,6 +198,10 @@ fi
|
||||
|
||||
set_cleanup_trap
|
||||
|
||||
# The release flow already prepares ui/dist before packaging. Reuse that output
|
||||
# so server prepack does not rebuild the UI a second time during preview/publish.
|
||||
export PAPERCLIP_RELEASE_REUSE_UI_DIST=1
|
||||
|
||||
if [ "$skip_verify" = false ]; then
|
||||
release_info ""
|
||||
release_info "==> Step 1/7: Verification gate..."
|
||||
|
||||
@@ -86,7 +86,7 @@ if (buildGapPackages.length === 0) {
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
run("pnpm", ["--filter", "@paperclipai/plugin-sdk", "build"]);
|
||||
run("pnpm", ["--filter", "@paperclipai/plugin-sdk", "ensure-build-deps"]);
|
||||
|
||||
for (const workspacePkg of buildGapPackages) {
|
||||
run("pnpm", ["--filter", workspacePkg.name, "typecheck"]);
|
||||
|
||||
@@ -49,6 +49,12 @@ 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);
|
||||
@@ -117,6 +123,7 @@ 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) {
|
||||
@@ -163,6 +170,17 @@ function parseCliOptions(argv) {
|
||||
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 "${arg}".`);
|
||||
}
|
||||
|
||||
@@ -178,6 +196,14 @@ function parseCliOptions(argv) {
|
||||
fail("--shard-index/--shard-count are only valid with --mode serialized.");
|
||||
}
|
||||
|
||||
if (group !== null && mode !== generalModeName) {
|
||||
fail("--group is only valid with --mode general.");
|
||||
}
|
||||
|
||||
if (group !== null && !generalGroupNames.includes(group)) {
|
||||
fail(`Unknown group "${group}". Expected one of: ${generalGroupNames.join(", ")}.`);
|
||||
}
|
||||
|
||||
if (mode === serializedModeName) {
|
||||
const resolvedShardCount = shardCount ?? 1;
|
||||
const resolvedShardIndex = shardIndex ?? 0;
|
||||
@@ -189,6 +215,7 @@ function parseCliOptions(argv) {
|
||||
mode,
|
||||
shardIndex: resolvedShardIndex,
|
||||
shardCount: resolvedShardCount,
|
||||
group: null,
|
||||
dryRun,
|
||||
};
|
||||
}
|
||||
@@ -197,6 +224,7 @@ function parseCliOptions(argv) {
|
||||
mode,
|
||||
shardIndex: null,
|
||||
shardCount: null,
|
||||
group,
|
||||
dryRun,
|
||||
};
|
||||
}
|
||||
@@ -208,12 +236,14 @@ function selectSerializedSuites(routeTests, shardIndex, shardCount) {
|
||||
function runVitest(args, label) {
|
||||
console.log(`\n[test:run] ${label}`);
|
||||
invocationIndex += 1;
|
||||
const testRoot = mkdtempSync(path.join(os.tmpdir(), `paperclip-vitest-${process.pid}-${invocationIndex}-`));
|
||||
const tempRootParent = process.platform === "win32" ? os.tmpdir() : "/tmp";
|
||||
const testRoot = mkdtempSync(path.join(tempRootParent, `pcvt-${process.pid}-${invocationIndex}-`));
|
||||
// Keep per-run paths compact so Unix socket fixtures stay under macOS path limits.
|
||||
const env = {
|
||||
...process.env,
|
||||
PAPERCLIP_HOME: path.join(testRoot, "home"),
|
||||
PAPERCLIP_INSTANCE_ID: `vitest-${process.pid}-${invocationIndex}`,
|
||||
TMPDIR: path.join(testRoot, "tmp"),
|
||||
PAPERCLIP_HOME: path.join(testRoot, "h"),
|
||||
PAPERCLIP_INSTANCE_ID: `vt-${process.pid}-${invocationIndex}`,
|
||||
TMPDIR: path.join(testRoot, "t"),
|
||||
};
|
||||
mkdirSync(env.PAPERCLIP_HOME, { recursive: true });
|
||||
mkdirSync(env.TMPDIR, { recursive: true });
|
||||
@@ -232,15 +262,38 @@ function runVitest(args, label) {
|
||||
}
|
||||
|
||||
function runGeneralSuites(routeTests) {
|
||||
const excludeRouteArgs = routeTests.flatMap((file) => ["--exclude", file.serverPath]);
|
||||
for (const project of nonServerProjects) {
|
||||
runVitest(["--project", project], `non-server project ${project}`);
|
||||
for (const groupName of generalGroupNames) {
|
||||
runGeneralGroup(routeTests, groupName);
|
||||
}
|
||||
}
|
||||
|
||||
function runProjectGroup(projects, groupName) {
|
||||
for (const project of projects) {
|
||||
runVitest(["--project", project], `${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;
|
||||
}
|
||||
|
||||
runVitest(
|
||||
["--project", "@paperclipai/server", ...excludeRouteArgs],
|
||||
`server suites excluding ${routeTests.length} serialized suites`,
|
||||
);
|
||||
if (groupName === generalWorkspacesAGroupName) {
|
||||
runProjectGroup(generalWorkspacesAProjects, groupName);
|
||||
return;
|
||||
}
|
||||
|
||||
if (groupName === generalWorkspacesBGroupName) {
|
||||
runProjectGroup(generalWorkspacesBProjects, groupName);
|
||||
return;
|
||||
}
|
||||
|
||||
fail(`Unknown group "${groupName}".`);
|
||||
}
|
||||
|
||||
function runSerializedSuites(routeTests, shardIndex, shardCount) {
|
||||
@@ -283,6 +336,8 @@ if (options.dryRun) {
|
||||
mode: options.mode,
|
||||
shardIndex: options.shardIndex,
|
||||
shardCount: options.shardCount,
|
||||
group: options.group,
|
||||
availableGeneralGroups: generalGroupNames,
|
||||
serializedSuiteCount: routeTests.length,
|
||||
selectedSerializedSuites: serializedSuites.map((routeTest) => routeTest.repoPath),
|
||||
},
|
||||
@@ -294,7 +349,11 @@ if (options.dryRun) {
|
||||
}
|
||||
|
||||
if (options.mode === generalModeName || options.mode === allModeName) {
|
||||
runGeneralSuites(routeTests);
|
||||
if (options.group) {
|
||||
runGeneralGroup(routeTests, options.group);
|
||||
} else {
|
||||
runGeneralSuites(routeTests);
|
||||
}
|
||||
}
|
||||
|
||||
if (options.mode === serializedModeName || options.mode === allModeName) {
|
||||
|
||||
Reference in New Issue
Block a user