deepseek-harness/.github/workflows/ci.yml

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# Cancel a superseded run on every event EXCEPT push.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# to the whole superseded run, so a job-level group cannot exempt its job.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

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:

  # TODO(hosted-serial-ci): Re-enable the three hosted serial reference jobs before release.
  # The self-hosted standby remains active on every master push.

  # Three enterprise jobs isolate coverage, static analysis, and the
  # build-backed consumer tail. The consumer job owns the only Linux build so
  # all three jobs enter runner allocation independently.
  #
  # FAILOVER (Linux): each Linux enterprise job resolves its pool through the
  # DSH_CI_FAILOVER_LINUX repository variable. Unset (normal), the expressions
  # pick the hosted enterprise pools below. Setting the variable to
  # 'selfhosted' (repo Settings → Actions → Variables; writer-manageable
  # repository state — not PR-editable, no merge required) retargets all
  # three onto the in-house
  # 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.
  node-24:
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / static
    env:
      DSH_GATE_CONCURRENCY: '8'
    steps:
      # Fetch complete history so the archive gate can read the trusted PR base from a reused shallow checkout.
      - uses: actions/checkout@v6
        with:
          fetch-depth: 0
          persist-credentials: false

      - 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 pnpm store path
        id: pnpm-store
        run: |
          store_root="$HOME/.local/share/pnpm/store"
          echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV"
          store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent)
          echo "path=$store_path" >> "$GITHUB_OUTPUT"

      # Pull requests consume the default-branch cache but do not put cache
      # compression and upload on the paid latency-critical path. Skipped
      # under failover — see the coverage lane's identical rationale.
      - uses: actions/cache/restore@v4
        if: vars.DSH_CI_FAILOVER_LINUX != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-

      - name: Install (immutable)
        run: pnpm install --frozen-lockfile

      - name: Run static gates
        env:
          DSH_ARCHIVE_BASE_REF: ${{ github.event.pull_request.base.sha }}
        run: pnpm run check:ci:static

  node-24-coverage:
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / coverage
    env:
      # The hosted 16-core runner uses six coverage workers. The failover pool
      # shares one 64-core VM across six always-on runner instances, so each
      # instance may use eight while keeping the worst case at 8 × 6 = 48
      # workers; process-bound suites remain isolated in forks.
      DSH_COVERAGE_MAX_WORKERS: ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '8' || '6' }}
      DSH_GATE_CONCURRENCY: '3'
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

      - 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 pnpm store path
        id: pnpm-store
        run: |
          store_root="$HOME/.local/share/pnpm/store"
          echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV"
          store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent)
          echo "path=$store_path" >> "$GITHUB_OUTPUT"

      # Skipped under failover: the self-hosted VM's persistent pnpm store
      # already serves warm installs, while restoring the hosted archive
      # would spend ~52 s pulling ~180 MB into that populated store.
      - uses: actions/cache/restore@v4
        if: vars.DSH_CI_FAILOVER_LINUX != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-

      - name: Install dependencies and prepare bubblewrap
        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: Run exhaustive coverage
        run: pnpm run check:ci:coverage

  node-24-consumers:
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
          || 'dsh-ubuntu-24-04-16core' }}
    name: node 24 / snapshots and artifacts
    env:
      DSH_GATE_CONCURRENCY: '8'
      DSH_NODE_COMPAT_SKIP_TYPECHECK: '1'
      DSH_OXLINT_THREADS: '8'
      DSH_PUBLINT_CONCURRENCY: '8'
      # Failover halves snapshot concurrency for the shared 64-core VM.
      DSH_SNAPSHOT_MAX_CONCURRENCY: ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]' && '12' || '32' }}
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

      - 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 pnpm store path
        id: pnpm-store
        run: |
          store_root="$HOME/.local/share/pnpm/store"
          echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV"
          store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent)
          echo "path=$store_path" >> "$GITHUB_OUTPUT"

      # Skipped under failover — see the coverage lane's identical rationale.
      - uses: actions/cache/restore@v4
        if: vars.DSH_CI_FAILOVER_LINUX != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-

      # Pull requests restore the cache normally produced by serial-linux on
      # master; they do not pay compression and upload on the required path.
      - uses: actions/cache/restore@v4
        if: vars.DSH_CI_FAILOVER_LINUX != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        with:
          path: ~/.cache/ms-playwright
          key: ${{ runner.os }}-playwright-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-playwright-

      - name: Install dependencies and prepare bubblewrap
        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 Playwright Chromium and hosted dependencies
        if: vars.DSH_CI_FAILOVER_LINUX != 'selfhosted' || github.event.pull_request.user.login == 'dependabot[bot]'
        run: pnpm --filter @deepseek-ai/dsh-web-frontend exec playwright install --with-deps chromium

      # The persistent VM image owns Playwright's Linux system packages; do
      # not mutate the shared host with apt on every failover run.
      - name: Install Playwright Chromium on the failover VM
        if: vars.DSH_CI_FAILOVER_LINUX == 'selfhosted' && github.event.pull_request.user.login != 'dependabot[bot]'
        run: pnpm --filter @deepseek-ai/dsh-web-frontend exec playwright install chromium

      - name: Run compatibility, snapshot, and artifact gates
        run: pnpm run check:ci:consumers


  node-compat:
    if: github.event_name == 'pull_request'
    # Each compatibility contract receives an independent standard hosted job.
    runs-on: ${{ matrix.runner }}
    name: ${{ matrix.name }}
    env:
      DSH_GATE_CONCURRENCY: ${{ matrix.gate_concurrency }}
      DSH_NODE_COMPAT_SKIP_TYPECHECK: '1'
    strategy:
      fail-fast: false
      matrix:
        include:
          - node: '22.19'
            name: node 22.19
            runner: ubuntu-latest
            gate_concurrency: '1'
          - node: 26
            name: node 26
            runner: ubuntu-latest
            gate_concurrency: '1'
    steps:
      - uses: actions/checkout@v6

      - uses: pnpm/action-setup@v4
        with:
          dest: ${{ runner.temp }}/setup-pnpm

      - uses: actions/setup-node@v6
        with:
          node-version: ${{ matrix.node }}
          cache: pnpm

      - name: Install (immutable)
        run: pnpm install --frozen-lockfile

      - name: Run compatibility smokes
        run: pnpm run check:node-compat

  python-sdk:
    if: github.event_name == 'pull_request'
    runs-on: ubuntu-latest
    name: python 3.10 / keyless SDK
    steps:
      - uses: actions/checkout@v6

      - uses: actions/setup-python@v6.3.0
        with:
          python-version: '3.10'
          cache: pip

      - name: Install uv
        run: python -m pip install uv==0.11.23

      - name: Run complete keyless Python suite
        run: uv run --python 3.10 --group test --project python/sdk pytest

  # One native target makes the complete release-shaped Python path required
  # without duplicating platform-independent behavior across the release matrix.
  # The reusable builder owns the executable, snapshot, wheel, clean-install,
  # GLIBC, and manylinux checks; release validation retains all native targets.
  python-runtime:
    if: github.event_name == 'pull_request'
    name: python runtime / release-shaped Linux x64
    uses: ./.github/workflows/build-exe-for-python-sdk.yml
    with:
      targets: node24-linux-x64
      ci: true

  # The required pull-request Windows signal: the two blocking win32 surfaces
  # (workspace build, production site) execute with real, checksum-verified
  # Windows Node under Wine on standard hosted Linux. The independent
  # windows-native job below keeps the complete native-kernel inventory —
  # including the observational portability gates this lane does not run —
  # on real Windows. This job only provisions runner state (caches,
  # apt); scripts/wine-windows-gates.sh owns the gate logic and is the same
  # script the optional local gate `pnpm run check:windows-wine` runs.
  # Current topology and fidelity limits live in
  # .agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md
  windows:
    if: github.event_name == 'pull_request'
    runs-on: ubuntu-latest
    name: windows node 24 / wine blocking
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

      - 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 pnpm store path
        id: pnpm-store
        run: |
          store_root="$HOME/.local/share/pnpm/store"
          echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV"
          store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent)
          echo "path=$store_path" >> "$GITHUB_OUTPUT"

      - uses: actions/cache/restore@v4
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          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.
      - 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
        with:
          path: ~/wine-debs
          key: ${{ steps.wine-cache-key.outputs.key }}

      # Runner provisioning only — a developer machine installs Wine through
      # its own package manager; the gate script assumes a wine binary and
      # fails loud without one. Wine from the apt cache when present; else
      # download the full dependency closure once and keep it for the next
      # run. The `wine` dispatcher package (not bare `wine64`) is what puts a
      # binary on PATH.
      - name: Install Wine
        run: |
          if compgen -G "$HOME/wine-debs/*.deb" > /dev/null; then
            sudo apt-get install -y --no-install-recommends "$HOME"/wine-debs/*.deb
          else
            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/" 2>/dev/null || true
            sudo apt-get install -y --no-install-recommends wine
          fi

      - name: Run the Wine Windows gates
        run: bash scripts/wine-windows-gates.sh

      - name: Shut down wineserver
        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
  # verdict. Under normal operation it runs on the hosted larger runner; under
  # Windows failover (DSH_CI_FAILOVER_WINDOWS=selfhosted) it retargets onto the
  # in-house self-hosted Windows pool. Dependabot PRs are excluded from the
  # self-hosted pool and stay queued for the hosted runner — see the failover
  # runbook. This Windows switch is independent of the Linux
  # DSH_CI_FAILOVER_LINUX variable that retargets the three required Linux jobs
  # and the all-checks-passed verdict above.
  windows-native:
    if: github.event_name == 'pull_request'
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER_WINDOWS == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "dsh-win-ci", "windows"]')
          || 'dsh-windows-2025-16core' }}
    name: windows node 24 / native complete
    timeout-minutes: 120
    env:
      DSH_COVERAGE_MAX_WORKERS: '2'
      # Instrumented process and polling fixtures can exceed Vitest's defaults
      # under the complete lane's concurrent gate load.
      DSH_COVERAGE_TEST_TIMEOUT_MS: '30000'
      DSH_GATE_CONCURRENCY: '2'
      DSH_PUBLINT_CONCURRENCY: '8'
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

      - 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 }}

      # Extracting the many-file pnpm store cache is slower than a clean
      # install on hosted Windows runners, and saving it adds latency after
      # the gates. The self-hosted VM's persistent store makes caching
      # redundant.
      - name: Install (immutable)
        shell: pwsh
        run: pnpm install --frozen-lockfile

      - name: Run complete native Windows gate inventory
        shell: pwsh
        run: pnpm run check:ci:windows-complete

  # The hosted reference jobs below are temporarily disabled; the self-hosted
  # standby remains active. Each enabled host executes the complete, unsharded
  # primary Node aggregate with one gate worker, giving reviewers a simple
  # cross-platform oracle for completeness and timing.
  serial-linux:
    if: false
    name: serial / linux
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v6
        with:
          fetch-depth: 2

      - 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 pnpm store path
        id: pnpm-store
        run: |
          store_root="$HOME/.local/share/pnpm/store"
          echo "PNPM_CONFIG_STORE_DIR=$store_root" >> "$GITHUB_ENV"
          store_path=$(PNPM_CONFIG_STORE_DIR="$store_root" pnpm store path --silent)
          echo "path=$store_path" >> "$GITHUB_OUTPUT"

      # Master refreshes the pnpm store cache that pull requests restore without saving.
      # The store cache stays a hand-rolled actions/cache step rather than
      # setup-node's `cache: pnpm`: the enterprise pull-request jobs above
      # restore exactly this key and path, and setup-node's built-in cache
      # uses its own key format — converting this producer would silently
      # starve their documented restore-only optimization.
      - uses: actions/cache@v4
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-pnpm-

      # Master produces the hosted Chromium cache restored by pull requests.
      - uses: actions/cache@v4
        with:
          path: ~/.cache/ms-playwright
          key: ${{ runner.os }}-playwright-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-playwright-

      - name: Install (immutable)
        run: pnpm install --frozen-lockfile

      - name: Install Playwright Chromium and system dependencies
        run: pnpm --filter @deepseek-ai/dsh-web-frontend exec playwright install --with-deps 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

  # 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:
      # Full history + DSH_ARCHIVE_BASE_REF below: same frozen-archive
      # comparison as serial-linux. Depth 2 would miss github.event.before
      # 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

  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.)
  # `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
  # 'cancelled' and 'skipped'.
  all-checks-passed:
    name: all checks passed
    # This bookkeeping-only verdict must not depend on custom-pool
    # provisioning — and under Linux failover it follows the same selector as
    # the worker jobs it aggregates, so a standard-hosted outage cannot strand
    # the branch-protection verdict either. It retargets with the Linux switch
    # (DSH_CI_FAILOVER_LINUX), not the Windows one, because it aggregates the
    # required Linux workers and runs on the vm-backup pool.
    runs-on: >-
      ${{ vars.DSH_CI_FAILOVER_LINUX == 'selfhosted'
          && github.event.pull_request.user.login != 'dependabot[bot]'
          && fromJSON('["self-hosted", "linux", "x64", "vm-backup"]')
          || 'ubuntu-latest' }}
    needs: [node-24, node-24-coverage, node-24-consumers, node-compat, python-sdk, python-runtime, windows]
    if: always() && github.event_name == 'pull_request'
    steps:
      - name: Fail if any needed job did not succeed
        if: contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') || contains(needs.*.result, 'skipped')
        run: |
          echo "::error::Needed job results: ${{ join(needs.*.result, ', ') }}"
          exit 1
      - name: All checks passed
        run: echo "All needed jobs succeeded (${{ join(needs.*.result, ', ') }})"