Files
PaperClipAI/.github/workflows/release-verify.yml
Devin FoleyandPaperclip 02bac43f91 ci: spread cloud server verification across ten runners
Keep the same tests and one worker per job while reducing the longest verification lane. Preserve the separate chat partition and normal PR test grouping.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-09-11 06:51:23 -07:00

320 lines
9.8 KiB
YAML

name: Release Verify
on:
workflow_call:
inputs:
ref:
description: Commit SHA, branch, or tag to verify
required: true
type: string
jobs:
runner_chaos_evals:
name: Pre-release Runner chaos evals
uses: ./.github/workflows/runner-chaos-evals.yml
with:
ref: ${{ inputs.ref }}
typecheck:
name: Typecheck
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
cache: pnpm
- name: Validate release package manifest
run: node ./scripts/release-package-map.mjs check
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Typecheck
run: pnpm -r typecheck
general_tests:
name: General tests (${{ matrix.group_label }})
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
strategy:
fail-fast: false
matrix:
include:
# Split the long chat file by collected test locations, and balance
# the remaining server files across ten runners. Normal PR/local
# invocations retain their complete general-server group.
- group: general-server-without-chat
group_label: server (1/10)
shard_index: 0
shard_count: 10
- group: general-server-without-chat
group_label: server (2/10)
shard_index: 1
shard_count: 10
- group: general-server-without-chat
group_label: server (3/10)
shard_index: 2
shard_count: 10
- group: general-server-without-chat
group_label: server (4/10)
shard_index: 3
shard_count: 10
- group: general-server-without-chat
group_label: server (5/10)
shard_index: 4
shard_count: 10
- group: general-server-without-chat
group_label: server (6/10)
shard_index: 5
shard_count: 10
- group: general-server-without-chat
group_label: server (7/10)
shard_index: 6
shard_count: 10
- group: general-server-without-chat
group_label: server (8/10)
shard_index: 7
shard_count: 10
- group: general-server-without-chat
group_label: server (9/10)
shard_index: 8
shard_count: 10
- group: general-server-without-chat
group_label: server (10/10)
shard_index: 9
shard_count: 10
- group: general-chat
group_label: chat (1/3)
shard_index: 0
shard_count: 3
- group: general-chat
group_label: chat (2/3)
shard_index: 1
shard_count: 3
- group: general-chat
group_label: chat (3/3)
shard_index: 2
shard_count: 3
# Keep parity with pr.yml: workspaces-a is split with Vitest's
# native --shard because the ui project dominates the lane.
- group: general-workspaces-a
group_label: workspaces-a (1/2)
shard_index: 0
shard_count: 2
- group: general-workspaces-a
group_label: workspaces-a (2/2)
shard_index: 1
shard_count: 2
- group: general-workspaces-b
group_label: workspaces-b
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
cache: pnpm
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Run grouped general test suites
run: |
if [ -n "${{ matrix.shard_count }}" ]; then
pnpm test:run:general -- --group '${{ matrix.group }}' \
--shard-index ${{ matrix.shard_index }} --shard-count ${{ matrix.shard_count }}
else
pnpm test:run:general -- --group '${{ matrix.group }}'
fi
serialized_tests:
name: Serialized tests (${{ matrix.shard_label }})
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
strategy:
fail-fast: false
matrix:
include:
- shard_index: 0
shard_count: 5
shard_label: 1/5
- shard_index: 1
shard_count: 5
shard_label: 2/5
- shard_index: 2
shard_count: 5
shard_label: 3/5
- shard_index: 3
shard_count: 5
shard_label: 4/5
- shard_index: 4
shard_count: 5
shard_label: 5/5
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
cache: pnpm
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Run serialized server test shard
run: pnpm test:run:serialized -- --shard-index ${{ matrix.shard_index }} --shard-count ${{ matrix.shard_count }}
runner_workflow_evals:
name: Runner workflow eval scorer contract
runs-on: ubuntu-latest
timeout-minutes: 10
permissions:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
cache: pnpm
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Run deterministic Runner workflow scorer tests
run: pnpm test:runner-workflow-evals
verify_paperclip_runner:
name: Verify Paperclip Runner
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
cache: pnpm
- name: Select the pinned Runner Rust toolchain
working-directory: packages/paperclip-runner
run: |
set -euo pipefail
rustup show
toolchain="$(rustup show active-toolchain | awk '{print $1}')"
echo "RUSTUP_TOOLCHAIN=$toolchain" >> "$GITHUB_ENV"
- name: Cache Runner Rust dependencies
# Restore and save only within trusted master-push verification. GitHub
# isolates branch/PR caches from master; other callers compile afresh.
if: ${{ github.repository == 'paperclipai/paperclip' && github.event_name == 'push' && github.ref == 'refs/heads/master' && inputs.ref == github.sha }}
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
workspaces: packages/paperclip-runner/runner -> target
shared-key: release-runner-v1
# Rebuild workspace code and rerun every check. Cache only compiled
# dependencies; never restore installed executables from cargo/bin.
cache-workspace-crates: false
cache-bin: false
# The step guard also restricts restores. Save only after a successful
# master-push verification of that push's exact commit.
save-if: ${{ github.repository == 'paperclipai/paperclip' && github.event_name == 'push' && github.ref == 'refs/heads/master' && inputs.ref == github.sha }}
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Verify Paperclip Runner
run: pnpm --filter @paperclipai/paperclip-runner check:all
build:
name: Build
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
with:
ref: ${{ inputs.ref }}
persist-credentials: false
- name: Setup pnpm
uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
with:
version: 9.15.4
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
with:
node-version: 24
- name: Install dependencies
run: pnpm install --no-frozen-lockfile
- name: Build
run: pnpm build