mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-08-29 04:26:38 +00:00
Merge pull request #2768 from deepseek-harness/ci/split-master-workflows
ci: split master-only jobs into ci-master.yml
This commit is contained in:
Chinesezjc
+1
-1
@@ -1,3 +1,3 @@
|
||||
# AGENTS.md — GitHub Actions
|
||||
|
||||
Run jobs on Windows runners (`windows-*` labels) under native `pwsh`. The pull-request `windows` job is the deliberate exception: it runs Windows Node under Wine on hosted Linux and blocks `all checks passed`; `windows-native` runs automatically on `windows-2025` (or the self-hosted `[self-hosted, dsh-win-ci, windows]` pool under `DSH_CI_FAILOVER_WINDOWS=selfhosted`) but reports independently. The master `serial-windows` standby continuously validates the self-hosted failover target — see the [failover runbook](../.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md).
|
||||
Run jobs on Windows runners (`windows-*` labels) under native `pwsh`. The pull-request `windows` job is the deliberate exception: it runs Windows Node under Wine on hosted Linux and blocks `all checks passed`; `windows-native` runs automatically on `windows-2025` (or the self-hosted `[self-hosted, dsh-win-ci, windows]` pool under `DSH_CI_FAILOVER_WINDOWS=selfhosted`) but reports independently. `ci.yml` is pull-request-only; the master `serial-windows` standby, the Linux `serial-linux-selfhosted` standby, the `wine-apt-cache` seeder, and the two manual runner benchmarks live in `ci-master.yml` (master-push + `workflow_dispatch`). Because `ci-master.yml` does not listen to `pull_request`, those master-only jobs never appear in PR check panels (a job a workflow defines for a given event is listed and shows `skipped` when its `if` is false); keeping them in a separate workflow is what stops PR check circles from showing gray segments. The master `serial-windows` standby continuously validates the self-hosted failover target — see the [failover runbook](../.agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md).
|
||||
|
||||
@@ -0,0 +1,407 @@
|
||||
name: CI master
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [master]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
suite:
|
||||
description: Manual CI suite to run
|
||||
required: true
|
||||
default: larger-runner-benchmark
|
||||
type: choice
|
||||
options:
|
||||
- larger-runner-benchmark
|
||||
- consolidated-runner-benchmark
|
||||
|
||||
# A master push may carry only the two self-hosted standby drills and the Wine
|
||||
# apt cache seeder; those drills outlast the interval between master merges, so
|
||||
# push is exempt from cancellation (see ci-failover-runbook). workflow_dispatch
|
||||
# keeps cancelling: a re-dispatched runner benchmark holds up to 12 larger
|
||||
# runners for 15 minutes in this same group.
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: ${{ github.event_name != 'push' }}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
env:
|
||||
PRIMARY_NODE_VERSION: '24'
|
||||
# CI runs must never report to the production telemetry endpoint baked
|
||||
# into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
|
||||
DSH_TELEMETRY_DISABLED: '1'
|
||||
|
||||
jobs:
|
||||
# Master seeds the Wine apt-archive cache in the default-branch scope,
|
||||
# which every pull request's windows job can restore; saves from
|
||||
# pull-request runs are scoped to their own merge ref and help nobody
|
||||
# else. Runs in seconds when the image version already has a cache.
|
||||
wine-apt-cache:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: wine apt cache
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
steps:
|
||||
- name: Compose Wine apt cache key
|
||||
id: wine-cache-key
|
||||
run: echo "key=wine-debs-${ImageOS:-linux}-${ImageVersion:-v0}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- uses: actions/cache@v4
|
||||
id: wine-cache
|
||||
with:
|
||||
path: ~/wine-debs
|
||||
key: ${{ steps.wine-cache-key.outputs.key }}
|
||||
|
||||
- name: Download the Wine dependency closure
|
||||
if: steps.wine-cache.outputs.cache-hit != 'true'
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y --no-install-recommends --download-only wine
|
||||
mkdir -p "$HOME/wine-debs"
|
||||
cp /var/cache/apt/archives/*.deb "$HOME/wine-debs/"
|
||||
du -sh "$HOME/wine-debs"
|
||||
|
||||
# Hot-standby drill for the in-house self-hosted pool: every master move
|
||||
# re-runs the complete unsharded aggregate on the persistent 64-core VM,
|
||||
# continuously proving that environment can take over a required lane if
|
||||
# the hosted pools degrade (the switch is then setting the writer-manageable
|
||||
# DSH_CI_FAILOVER_LINUX variable — see the failover runbook, no merge required).
|
||||
# Push-triggered, so this lane always executes the base branch's own
|
||||
# workflow definition. This workflow never listens to pull_request, so the
|
||||
# drill does not appear in PR checks. No cache steps because the VM's
|
||||
# persistent pnpm store and tool caches make them redundant (and saving here
|
||||
# would poison the hosted cache namespace with self-hosted paths).
|
||||
serial-linux-selfhosted:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: serial / linux (self-hosted standby)
|
||||
runs-on: [self-hosted, linux, x64, vm-backup]
|
||||
steps:
|
||||
# DSH_ARCHIVE_BASE_REF below compares the frozen-archive gate against
|
||||
# github.event.before, so full history is required: depth 2 would miss it
|
||||
# on multi-commit or force pushes; full fetch is cheap here because
|
||||
# checkout resolves against the VM's local mirror.
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Configure persistent pnpm store
|
||||
run: echo "PNPM_CONFIG_STORE_DIR=$HOME/.local/share/pnpm/store" >> "$GITHUB_ENV"
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
# The persistent VM image owns Playwright's Linux system packages; this
|
||||
# step also proves that browser provisioning remains usable for failover.
|
||||
- name: Install Playwright Chromium
|
||||
run: pnpm --filter @deepseek-ai/dsh-web-frontend exec playwright install chromium
|
||||
|
||||
- name: Prepare bubblewrap (unrestrict userns)
|
||||
run: bash scripts/prepare-ci-bubblewrap.sh
|
||||
|
||||
- name: Run complete unsharded primary Node CI serially
|
||||
env:
|
||||
DSH_ARCHIVE_BASE_REF: ${{ github.event.before }}
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_E2E_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_OXLINT_THREADS: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci:linux-primary
|
||||
|
||||
# TODO(hosted-serial-ci): Re-enable the one remaining disabled hosted serial
|
||||
# reference job (serial-macos) before release. Re-enabling serial-macos does
|
||||
# not restore a Linux hosted-cache producer: decide whether to add a master
|
||||
# seeder or remove the restore-only steps if cold starts become a concern.
|
||||
serial-macos:
|
||||
if: false
|
||||
name: serial / macos
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded primary Node CI serially
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_E2E_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci
|
||||
|
||||
# Hot-standby drill for the in-house self-hosted Windows pool: every master
|
||||
# move re-runs the complete unsharded Windows gate inventory on the persistent
|
||||
# VM, continuously proving that environment can take over the required
|
||||
# `windows` lane if the hosted pool degrades (the switch is setting the
|
||||
# writer-manageable DSH_CI_FAILOVER_WINDOWS variable — see the failover
|
||||
# runbook, no merge required). Push-triggered, so this lane always executes
|
||||
# the base branch's own workflow definition. This workflow never listens to
|
||||
# pull_request, so the drill does not appear in PR checks. No cache steps
|
||||
# because the VM's persistent pnpm store and tool caches make them redundant
|
||||
# (and saving here would poison the hosted cache namespace with self-hosted
|
||||
# paths).
|
||||
serial-windows:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: serial / windows (self-hosted standby)
|
||||
runs-on: [self-hosted, dsh-win-ci, windows]
|
||||
timeout-minutes: 120
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Enable Developer Mode (symlink support)
|
||||
shell: pwsh
|
||||
run: >-
|
||||
reg add "HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\AppModelUnlock"
|
||||
/t REG_DWORD /f /v "AllowDevelopmentWithoutDevLicense" /d "1"
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Configure persistent pnpm store
|
||||
shell: pwsh
|
||||
run: |
|
||||
$storeRoot = "$env:LOCALAPPDATA\pnpm\store"
|
||||
echo "PNPM_CONFIG_STORE_DIR=$storeRoot" >> $env:GITHUB_ENV
|
||||
|
||||
- name: Install (immutable)
|
||||
shell: pwsh
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded Windows gate inventory serially
|
||||
shell: pwsh
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci:windows-complete
|
||||
|
||||
# Manual, bounded comparison of the actual critical Linux and Windows lanes.
|
||||
# The named pools are restricted at the organization level to this repository.
|
||||
larger-runner-benchmark:
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.suite == 'larger-runner-benchmark'
|
||||
runs-on: ${{ matrix.runner }}
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 12
|
||||
matrix:
|
||||
include:
|
||||
- platform: linux
|
||||
cores: '4'
|
||||
runner: dsh-ubuntu-24-04-4core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '8'
|
||||
runner: dsh-ubuntu-24-04-8core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '16'
|
||||
runner: dsh-ubuntu-24-04-16core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '32'
|
||||
runner: dsh-ubuntu-24-04-32core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '64'
|
||||
runner: dsh-ubuntu-24-04-64core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '96'
|
||||
runner: dsh-ubuntu-24-04-96core
|
||||
workload: typecheck
|
||||
- platform: windows
|
||||
cores: '4'
|
||||
runner: dsh-windows-2025-4core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '8'
|
||||
runner: dsh-windows-2025-8core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '16'
|
||||
runner: dsh-windows-2025-16core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '32'
|
||||
runner: dsh-windows-2025-32core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '64'
|
||||
runner: dsh-windows-2025-64core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '96'
|
||||
runner: dsh-windows-2025-96core
|
||||
workload: production-site
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
# The benchmark's Windows lanes deliberately skip the store cache like
|
||||
# the independent native Windows job; an empty input disables caching.
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
cache: ${{ matrix.platform == 'linux' && 'pnpm' || '' }}
|
||||
|
||||
- name: Report runner capacity
|
||||
run: >-
|
||||
node -e "const os = require('node:os');
|
||||
console.log(JSON.stringify({ arch: process.arch, cpus: os.cpus().length,
|
||||
memoryGiB: Math.round(os.totalmem() / 2 ** 30) }))"
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run critical Linux typecheck lane
|
||||
if: matrix.platform == 'linux'
|
||||
run: pnpm run typecheck
|
||||
|
||||
- name: Run critical Windows production-site lane
|
||||
if: matrix.platform == 'windows'
|
||||
run: pnpm run docs:build
|
||||
|
||||
# Manual comparison of the intended low-fanout topology. Linux runs the
|
||||
# complete unsharded primary aggregate with bounded in-runner parallelism;
|
||||
# Windows runs both blocking build targets concurrently through run-gates.
|
||||
consolidated-runner-benchmark:
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.suite == 'consolidated-runner-benchmark'
|
||||
runs-on: ${{ matrix.runner }}
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 12
|
||||
matrix:
|
||||
include:
|
||||
- platform: linux
|
||||
cores: '4'
|
||||
runner: dsh-ubuntu-24-04-4core
|
||||
workers: '4'
|
||||
- platform: linux
|
||||
cores: '8'
|
||||
runner: dsh-ubuntu-24-04-8core
|
||||
workers: '8'
|
||||
- platform: linux
|
||||
cores: '16'
|
||||
runner: dsh-ubuntu-24-04-16core
|
||||
workers: '16'
|
||||
- platform: linux
|
||||
cores: '32'
|
||||
runner: dsh-ubuntu-24-04-32core
|
||||
workers: '32'
|
||||
- platform: linux
|
||||
cores: '64'
|
||||
runner: dsh-ubuntu-24-04-64core
|
||||
workers: '32'
|
||||
- platform: linux
|
||||
cores: '96'
|
||||
runner: dsh-ubuntu-24-04-96core
|
||||
workers: '32'
|
||||
- platform: windows
|
||||
cores: '4'
|
||||
runner: dsh-windows-2025-4core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '8'
|
||||
runner: dsh-windows-2025-8core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '16'
|
||||
runner: dsh-windows-2025-16core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '32'
|
||||
runner: dsh-windows-2025-32core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '64'
|
||||
runner: dsh-windows-2025-64core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '96'
|
||||
runner: dsh-windows-2025-96core
|
||||
workers: '2'
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
# Unlike the larger-runner suite, both platforms cache the store here:
|
||||
# the consolidated topology measures cache mechanics as workload.
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
cache: pnpm
|
||||
|
||||
- name: Report runner capacity
|
||||
run: >-
|
||||
node -e "const os = require('node:os');
|
||||
console.log(JSON.stringify({ arch: process.arch, cpus: os.cpus().length,
|
||||
memoryGiB: Math.round(os.totalmem() / 2 ** 30) }))"
|
||||
|
||||
- name: Install and prepare Linux
|
||||
if: matrix.platform == 'linux'
|
||||
run: |
|
||||
pnpm install --frozen-lockfile &
|
||||
install_pid=$!
|
||||
bash scripts/prepare-ci-bubblewrap.sh &
|
||||
sandbox_pid=$!
|
||||
install_status=0
|
||||
wait "$install_pid" || install_status=$?
|
||||
sandbox_status=0
|
||||
wait "$sandbox_pid" || sandbox_status=$?
|
||||
if (( install_status != 0 )); then exit "$install_status"; fi
|
||||
exit "$sandbox_status"
|
||||
|
||||
- name: Install (immutable)
|
||||
if: matrix.platform == 'windows'
|
||||
shell: pwsh
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded primary Node CI concurrently
|
||||
if: matrix.platform == 'linux'
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: ${{ matrix.workers }}
|
||||
DSH_GATE_CONCURRENCY: ${{ matrix.workers }}
|
||||
DSH_OXLINT_THREADS: ${{ matrix.workers }}
|
||||
DSH_PUBLINT_CONCURRENCY: ${{ matrix.workers }}
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ matrix.workers }}
|
||||
run: pnpm run check:ci
|
||||
|
||||
- name: Run blocking Windows builds concurrently
|
||||
if: matrix.platform == 'windows'
|
||||
shell: pwsh
|
||||
env:
|
||||
DSH_GATE_CONCURRENCY: ${{ matrix.workers }}
|
||||
run: pnpm run check:ci:windows-blocking
|
||||
+15
-416
@@ -1,36 +1,7 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [master]
|
||||
pull_request:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
suite:
|
||||
description: Manual CI suite to run
|
||||
required: true
|
||||
default: larger-runner-benchmark
|
||||
type: choice
|
||||
options:
|
||||
- larger-runner-benchmark
|
||||
- consolidated-runner-benchmark
|
||||
|
||||
# Cancel a superseded run on every event EXCEPT push. A push run carries the two
|
||||
# self-hosted standby drills, which take longer than the interval between master
|
||||
# merges, so cancelling supersedes a drill before it reaches a verdict and the
|
||||
# lane yields no readiness evidence. Must be decided here: cancellation applies
|
||||
# to the whole superseded run, so a job-level group cannot exempt its job.
|
||||
# Negated rather than `== 'pull_request'` so workflow_dispatch keeps cancelling:
|
||||
# a re-dispatched runner benchmark holds up to 12 larger runners for 15 minutes
|
||||
# and shares this group with the drills on master, so queueing it would delay
|
||||
# them. The guarantee is narrow — evaluated against the newly triggered run, so a
|
||||
# dispatch on master still cancels a mid-flight drill, and a newer pending push
|
||||
# displaces an older one. Bounds and rationale:
|
||||
# .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: ${{ github.event_name != 'push' }}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
@@ -40,13 +11,14 @@ env:
|
||||
# into apps/cli/cordis.yml (AppCLIEntry disables the row when set).
|
||||
DSH_TELEMETRY_DISABLED: '1'
|
||||
|
||||
jobs:
|
||||
# Cancel a superseded pull-request run on a new push so a fresh head does not
|
||||
# queue a second full 9-job run behind a stale one (paid enterprise runners
|
||||
# would otherwise stack with no auto-cancellation).
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
# TODO(hosted-serial-ci): Re-enable the one remaining disabled hosted serial
|
||||
# reference job (serial-macos) before release. The self-hosted standby lane
|
||||
# below remains active on every master push. Re-enabling serial-macos does not
|
||||
# restore a Linux hosted-cache producer: decide whether to add a master seeder
|
||||
# or remove the restore-only steps if cold starts become a concern.
|
||||
jobs:
|
||||
|
||||
# Three enterprise jobs isolate coverage, static analysis, and the
|
||||
# build-backed consumer tail. The consumer job owns the only Linux build so
|
||||
@@ -61,8 +33,9 @@ jobs:
|
||||
# vm-backup pool and re-running the failed jobs is the entire switch —
|
||||
# see .agents/notes/implemented/process/2026-07-26-ci-failover-runbook.md. The
|
||||
# in-house pool's readiness is re-proven on every master push by the
|
||||
# serial-linux-selfhosted standby lane below. The Windows failover switch is
|
||||
# the separate DSH_CI_FAILOVER_WINDOWS variable on the windows-native job below.
|
||||
# serial-linux-selfhosted standby lane in ci-master.yml. The Windows failover
|
||||
# switch is the separate DSH_CI_FAILOVER_WINDOWS variable on the windows-native
|
||||
# job below.
|
||||
node-24:
|
||||
if: github.event_name == 'pull_request'
|
||||
runs-on: >-
|
||||
@@ -376,9 +349,9 @@ jobs:
|
||||
restore-keys: |
|
||||
${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-
|
||||
|
||||
# Master's wine-apt-cache job seeds the default-branch scope every pull
|
||||
# request can read; a save from this job only reaches reruns of the
|
||||
# same merge ref.
|
||||
# Master's wine-apt-cache job in ci-master.yml seeds the default-branch
|
||||
# scope every pull request can read; a save from this job only reaches
|
||||
# reruns of the same merge ref.
|
||||
- name: Compose Wine apt cache key
|
||||
id: wine-cache-key
|
||||
run: echo "key=wine-debs-${ImageOS:-linux}-${ImageVersion:-v0}" >> "$GITHUB_OUTPUT"
|
||||
@@ -423,35 +396,6 @@ jobs:
|
||||
if: always()
|
||||
run: wineserver -k 2>/dev/null || true
|
||||
|
||||
# Master seeds the Wine apt-archive cache in the default-branch scope,
|
||||
# which every pull request's windows job can restore; saves from
|
||||
# pull-request runs are scoped to their own merge ref and help nobody
|
||||
# else. Runs in seconds when the image version already has a cache.
|
||||
wine-apt-cache:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: wine apt cache
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 10
|
||||
steps:
|
||||
- name: Compose Wine apt cache key
|
||||
id: wine-cache-key
|
||||
run: echo "key=wine-debs-${ImageOS:-linux}-${ImageVersion:-v0}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- uses: actions/cache@v4
|
||||
id: wine-cache
|
||||
with:
|
||||
path: ~/wine-debs
|
||||
key: ${{ steps.wine-cache-key.outputs.key }}
|
||||
|
||||
- name: Download the Wine dependency closure
|
||||
if: steps.wine-cache.outputs.cache-hit != 'true'
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y --no-install-recommends --download-only wine
|
||||
mkdir -p "$HOME/wine-debs"
|
||||
cp /var/cache/apt/archives/*.deb "$HOME/wine-debs/"
|
||||
du -sh "$HOME/wine-debs"
|
||||
|
||||
# Every pull request also gets a real Windows-kernel signal. This job keeps
|
||||
# its own unmasked conclusion but is deliberately absent from
|
||||
# all-checks-passed.needs, so it never delays or changes that required
|
||||
@@ -510,358 +454,13 @@ jobs:
|
||||
shell: pwsh
|
||||
run: pnpm run check:ci:windows-complete
|
||||
|
||||
# Hot-standby drill for the in-house self-hosted pool: every master move
|
||||
# re-runs the complete unsharded aggregate on the persistent 64-core VM,
|
||||
# continuously proving that environment can take over a required lane if
|
||||
# the hosted pools degrade (the switch is then setting the writer-manageable
|
||||
# DSH_CI_FAILOVER_LINUX variable — see the failover runbook, no merge required).
|
||||
# Push-triggered, so this lane always executes the base branch's own
|
||||
# workflow definition. (Under failover, pull_request jobs do reach these
|
||||
# runners with the PR merge ref's workflow — the boundary there is
|
||||
# repository membership: private, forking disabled, Dependabot excluded.)
|
||||
# Non-blocking for
|
||||
# pull requests; no cache steps because the VM's persistent pnpm store and
|
||||
# tool caches make them redundant (and saving here would poison the hosted
|
||||
# cache namespace with self-hosted paths).
|
||||
serial-linux-selfhosted:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: serial / linux (self-hosted standby)
|
||||
runs-on: [self-hosted, linux, x64, vm-backup]
|
||||
steps:
|
||||
# DSH_ARCHIVE_BASE_REF below compares the frozen-archive gate against
|
||||
# github.event.before, so full history is required: depth 2 would miss it
|
||||
# on multi-commit or force pushes; full fetch is cheap here because
|
||||
# checkout resolves against the VM's local mirror.
|
||||
- uses: actions/checkout@v6
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Configure persistent pnpm store
|
||||
run: echo "PNPM_CONFIG_STORE_DIR=$HOME/.local/share/pnpm/store" >> "$GITHUB_ENV"
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
# The persistent VM image owns Playwright's Linux system packages; this
|
||||
# step also proves that browser provisioning remains usable for failover.
|
||||
- name: Install Playwright Chromium
|
||||
run: pnpm --filter @deepseek-ai/dsh-web-frontend exec playwright install chromium
|
||||
|
||||
- name: Prepare bubblewrap (unrestrict userns)
|
||||
run: bash scripts/prepare-ci-bubblewrap.sh
|
||||
|
||||
- name: Run complete unsharded primary Node CI serially
|
||||
env:
|
||||
DSH_ARCHIVE_BASE_REF: ${{ github.event.before }}
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_E2E_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_OXLINT_THREADS: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci:linux-primary
|
||||
|
||||
# The one remaining disabled hosted serial reference job; see
|
||||
# TODO(hosted-serial-ci) above.
|
||||
serial-macos:
|
||||
if: false
|
||||
name: serial / macos
|
||||
runs-on: macos-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded primary Node CI serially
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_E2E_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci
|
||||
|
||||
# Hot-standby drill for the in-house self-hosted Windows pool: every master
|
||||
# move re-runs the complete unsharded Windows gate inventory on the persistent
|
||||
# VM, continuously proving that environment can take over the required
|
||||
# `windows` lane if the hosted pool degrades (the switch is setting the
|
||||
# writer-manageable DSH_CI_FAILOVER_WINDOWS variable — see the failover
|
||||
# runbook, no merge required). Push-triggered, so this lane always executes
|
||||
# the base branch's own workflow definition. Non-blocking for pull requests;
|
||||
# absent from all-checks-passed.needs by design — the required `windows` job
|
||||
# owns the PR verdict. No cache steps because the VM's persistent pnpm store
|
||||
# and tool caches make them redundant (and saving here would poison the
|
||||
# hosted cache namespace with self-hosted paths).
|
||||
serial-windows:
|
||||
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
name: serial / windows (self-hosted standby)
|
||||
runs-on: [self-hosted, dsh-win-ci, windows]
|
||||
timeout-minutes: 120
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Enable Developer Mode (symlink support)
|
||||
shell: pwsh
|
||||
run: >-
|
||||
reg add "HKLM\SOFTWARE\Microsoft\Windows\CurrentVersion\AppModelUnlock"
|
||||
/t REG_DWORD /f /v "AllowDevelopmentWithoutDevLicense" /d "1"
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
|
||||
- name: Configure persistent pnpm store
|
||||
shell: pwsh
|
||||
run: |
|
||||
$storeRoot = "$env:LOCALAPPDATA\pnpm\store"
|
||||
echo "PNPM_CONFIG_STORE_DIR=$storeRoot" >> $env:GITHUB_ENV
|
||||
|
||||
- name: Install (immutable)
|
||||
shell: pwsh
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded Windows gate inventory serially
|
||||
shell: pwsh
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: '1'
|
||||
DSH_GATE_CONCURRENCY: '1'
|
||||
DSH_PUBLINT_CONCURRENCY: '1'
|
||||
run: pnpm run check:ci:windows-complete
|
||||
|
||||
# Manual, bounded comparison of the actual critical Linux and Windows lanes.
|
||||
# The named pools are restricted at the organization level to this repository.
|
||||
larger-runner-benchmark:
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.suite == 'larger-runner-benchmark'
|
||||
runs-on: ${{ matrix.runner }}
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 12
|
||||
matrix:
|
||||
include:
|
||||
- platform: linux
|
||||
cores: '4'
|
||||
runner: dsh-ubuntu-24-04-4core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '8'
|
||||
runner: dsh-ubuntu-24-04-8core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '16'
|
||||
runner: dsh-ubuntu-24-04-16core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '32'
|
||||
runner: dsh-ubuntu-24-04-32core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '64'
|
||||
runner: dsh-ubuntu-24-04-64core
|
||||
workload: typecheck
|
||||
- platform: linux
|
||||
cores: '96'
|
||||
runner: dsh-ubuntu-24-04-96core
|
||||
workload: typecheck
|
||||
- platform: windows
|
||||
cores: '4'
|
||||
runner: dsh-windows-2025-4core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '8'
|
||||
runner: dsh-windows-2025-8core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '16'
|
||||
runner: dsh-windows-2025-16core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '32'
|
||||
runner: dsh-windows-2025-32core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '64'
|
||||
runner: dsh-windows-2025-64core
|
||||
workload: production-site
|
||||
- platform: windows
|
||||
cores: '96'
|
||||
runner: dsh-windows-2025-96core
|
||||
workload: production-site
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
# The benchmark's Windows lanes deliberately skip the store cache like
|
||||
# the independent native Windows job; an empty input disables caching.
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
cache: ${{ matrix.platform == 'linux' && 'pnpm' || '' }}
|
||||
|
||||
- name: Report runner capacity
|
||||
run: >-
|
||||
node -e "const os = require('node:os');
|
||||
console.log(JSON.stringify({ arch: process.arch, cpus: os.cpus().length,
|
||||
memoryGiB: Math.round(os.totalmem() / 2 ** 30) }))"
|
||||
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run critical Linux typecheck lane
|
||||
if: matrix.platform == 'linux'
|
||||
run: pnpm run typecheck
|
||||
|
||||
- name: Run critical Windows production-site lane
|
||||
if: matrix.platform == 'windows'
|
||||
run: pnpm run docs:build
|
||||
|
||||
# Manual comparison of the intended low-fanout topology. Linux runs the
|
||||
# complete unsharded primary aggregate with bounded in-runner parallelism;
|
||||
# Windows runs both blocking build targets concurrently through run-gates.
|
||||
consolidated-runner-benchmark:
|
||||
if: github.event_name == 'workflow_dispatch' && inputs.suite == 'consolidated-runner-benchmark'
|
||||
runs-on: ${{ matrix.runner }}
|
||||
timeout-minutes: 15
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 12
|
||||
matrix:
|
||||
include:
|
||||
- platform: linux
|
||||
cores: '4'
|
||||
runner: dsh-ubuntu-24-04-4core
|
||||
workers: '4'
|
||||
- platform: linux
|
||||
cores: '8'
|
||||
runner: dsh-ubuntu-24-04-8core
|
||||
workers: '8'
|
||||
- platform: linux
|
||||
cores: '16'
|
||||
runner: dsh-ubuntu-24-04-16core
|
||||
workers: '16'
|
||||
- platform: linux
|
||||
cores: '32'
|
||||
runner: dsh-ubuntu-24-04-32core
|
||||
workers: '32'
|
||||
- platform: linux
|
||||
cores: '64'
|
||||
runner: dsh-ubuntu-24-04-64core
|
||||
workers: '32'
|
||||
- platform: linux
|
||||
cores: '96'
|
||||
runner: dsh-ubuntu-24-04-96core
|
||||
workers: '32'
|
||||
- platform: windows
|
||||
cores: '4'
|
||||
runner: dsh-windows-2025-4core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '8'
|
||||
runner: dsh-windows-2025-8core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '16'
|
||||
runner: dsh-windows-2025-16core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '32'
|
||||
runner: dsh-windows-2025-32core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '64'
|
||||
runner: dsh-windows-2025-64core
|
||||
workers: '2'
|
||||
- platform: windows
|
||||
cores: '96'
|
||||
runner: dsh-windows-2025-96core
|
||||
workers: '2'
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: pnpm/action-setup@v4
|
||||
with:
|
||||
dest: ${{ runner.temp }}/setup-pnpm
|
||||
|
||||
# Unlike the larger-runner suite, both platforms cache the store here:
|
||||
# the consolidated topology measures cache mechanics as workload.
|
||||
- uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: ${{ env.PRIMARY_NODE_VERSION }}
|
||||
cache: pnpm
|
||||
|
||||
- name: Report runner capacity
|
||||
run: >-
|
||||
node -e "const os = require('node:os');
|
||||
console.log(JSON.stringify({ arch: process.arch, cpus: os.cpus().length,
|
||||
memoryGiB: Math.round(os.totalmem() / 2 ** 30) }))"
|
||||
|
||||
- name: Install and prepare Linux
|
||||
if: matrix.platform == 'linux'
|
||||
run: |
|
||||
pnpm install --frozen-lockfile &
|
||||
install_pid=$!
|
||||
bash scripts/prepare-ci-bubblewrap.sh &
|
||||
sandbox_pid=$!
|
||||
install_status=0
|
||||
wait "$install_pid" || install_status=$?
|
||||
sandbox_status=0
|
||||
wait "$sandbox_pid" || sandbox_status=$?
|
||||
if (( install_status != 0 )); then exit "$install_status"; fi
|
||||
exit "$sandbox_status"
|
||||
|
||||
- name: Install (immutable)
|
||||
if: matrix.platform == 'windows'
|
||||
shell: pwsh
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
- name: Run complete unsharded primary Node CI concurrently
|
||||
if: matrix.platform == 'linux'
|
||||
env:
|
||||
DSH_COVERAGE_MAX_WORKERS: ${{ matrix.workers }}
|
||||
DSH_GATE_CONCURRENCY: ${{ matrix.workers }}
|
||||
DSH_OXLINT_THREADS: ${{ matrix.workers }}
|
||||
DSH_PUBLINT_CONCURRENCY: ${{ matrix.workers }}
|
||||
DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ matrix.workers }}
|
||||
run: pnpm run check:ci
|
||||
|
||||
- name: Run blocking Windows builds concurrently
|
||||
if: matrix.platform == 'windows'
|
||||
shell: pwsh
|
||||
env:
|
||||
DSH_GATE_CONCURRENCY: ${{ matrix.workers }}
|
||||
run: pnpm run check:ci:windows-blocking
|
||||
|
||||
# Single stable required check for branch protection: require "all checks
|
||||
# passed" instead of enumerating matrix legs whose names change as lanes and
|
||||
# node versions evolve. Every blocking job in THIS workflow must be listed in
|
||||
# `needs`. The required Wine job is listed as `windows`; `windows-native` is
|
||||
# deliberately absent so its independent result never delays or changes this
|
||||
# verdict. (`needs` cannot reach across workflow files; e2e.yml stays its own
|
||||
# check.)
|
||||
# verdict. (`needs` cannot reach across workflow files; the master-only jobs in
|
||||
# ci-master.yml are intentionally not part of this PR verdict.)
|
||||
# `if: always()` is load-bearing: without it a failed dependency
|
||||
# would SKIP this job, and GitHub counts a skipped required check as passing
|
||||
# — so this job always runs and fails on any non-success result, including
|
||||
|
||||
@@ -107,7 +107,8 @@ jobs:
|
||||
run: pnpm run build:official
|
||||
|
||||
# Real-API end-to-end tests only. The keyless gates (lint/typecheck/
|
||||
# coverage/snapshot/etc.) already run in ci.yml on every push/PR.
|
||||
# coverage/snapshot/etc.) already run in ci.yml (pull requests) and
|
||||
# ci-master.yml (master push standby).
|
||||
# DEEPSEEK_BASE_URL is pinned to the external API; the secret is scoped to
|
||||
# this step (and preflight) only — never exposed to checkout/setup/install.
|
||||
- name: E2E tests (real DeepSeek API)
|
||||
|
||||
Reference in New Issue
Block a user