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

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

# New master pushes and manual runs replace obsolete checks in this workflow/ref.
# Standby drills share cancellation; use completed runs as readiness evidence.
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

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:
  # These native runtime carriers are post-merge checks; release keeps all targets.
  python-runtime:
    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
    name: python runtime / macOS and Linux ARM64
    uses: ./.github/workflows/build-exe-for-python-sdk.yml
    with:
      targets: node24-linux-arm64,node24-macos-arm64,node24-macos-x64
      ci: true
    secrets:
      DEEPSEEK_API_KEY_EXTERNAL: ${{ secrets.DEEPSEEK_API_KEY_EXTERNAL }}

  # Wine runs once here, independently of the native serial standby aggregates.
  windows:
    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
    runs-on: ubuntu-latest
    name: windows node 24 / wine
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

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

      - 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 CI restores and seeds the image-specific Wine dependency cache.
      - 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 "$HOME/wine-debs/*.deb" > /dev/null; then
            # The restored archive is the full --download-only closure of
            # `wine` for this runner image, so installing the .debs directly
            # with dpkg needs no repository access. apt-get would instead
            # re-download the same 100+ MB closure from the mirror, which has
            # stalled the job past its budget on a degraded runner network.
            # If the archive cannot satisfy the closure, fall back to the apt
            # network install.
            if ! sudo DEBIAN_FRONTEND=noninteractive dpkg -i "$HOME"/wine-debs/*.deb; then
              sudo DEBIAN_FRONTEND=noninteractive dpkg --configure -a || true
              sudo apt-get install -y --no-install-recommends "$HOME"/wine-debs/*.deb
            fi
          else
            sudo apt-get update
            sudo apt-get install -y --no-install-recommends --download-only wine
            mkdir -p "$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

  # 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

      # Redirect the Node compile cache (enabled by pnpm and TypeScript) off
      # the root partition's /tmp before the first pnpm call in this lane —
      # see .agents/notes/implemented/process/2026-08-28-ci-node-compile-cache-data-disk.md.
      - name: Redirect Node compile cache to runner temp
        run: echo "NODE_COMPILE_CACHE=${{ runner.temp }}/node-compile-cache" >> "$GITHUB_ENV"

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

      - 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: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }}

      - 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: ${{ runner.temp }}/setup-pnpm-${{ github.run_id }}-${{ github.run_attempt }}

      - uses: actions/setup-node@v6
        with:
          node-version: ${{ env.PRIMARY_NODE_VERSION }}

      - name: Configure persistent pnpm store
        shell: pwsh
        # The store must share the ReFS workspace volume for the clone
        # import method below. Runner workspaces can reside on different drives.
        run: |
          $storeRoot = Join-Path ([IO.Path]::GetPathRoot($env:GITHUB_WORKSPACE)) '.pnpm-store'
          echo "PNPM_CONFIG_STORE_DIR=$storeRoot" >> $env:GITHUB_ENV

      - name: Install (immutable)
        shell: pwsh
        # See 2026-08-30-windows-refs-store-block-clone-install for the
        # ReFS block-clone rationale; use clone only on ReFS.
        run: >-
          $drive = (Split-Path -Qualifier $env:GITHUB_WORKSPACE).TrimEnd(':');
          $fs = (Get-Volume -DriveLetter $drive).FileSystem;
          if ($fs -eq 'ReFS') {
            corepack pnpm install --frozen-lockfile --package-import-method=clone
          } else {
            pnpm install --frozen-lockfile
          }

      - name: Run complete unsharded Windows gate inventory serially
        shell: pwsh
        env:
          DSH_COVERAGE_MAX_WORKERS: '1'
          DSH_COVERAGE_TEST_TIMEOUT_MS: '90000'
          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'
    # Default measures the repository's own fleet tiers; under the matching
    # platform's blacksmith failover value the tiers Blacksmith offers (up to
    # 32 vCPU) move onto their Blacksmith equivalents, while the 64/96-core
    # rows keep the fleet labels because Blacksmith has no such tier.
    runs-on: >-
      ${{ (matrix.platform == 'linux' && vars.DSH_CI_FAILOVER_LINUX == 'blacksmith'
            || matrix.platform == 'windows' && vars.DSH_CI_FAILOVER_WINDOWS == 'blacksmith')
          && matrix.blacksmith
          || matrix.runner }}
    timeout-minutes: 15
    strategy:
      fail-fast: false
      max-parallel: 12
      matrix:
        include:
          - platform: linux
            cores: '4'
            runner: dsh-ubuntu-24-04-4core
            blacksmith: blacksmith-4vcpu-ubuntu-2404
            workload: typecheck
          - platform: linux
            cores: '8'
            runner: dsh-ubuntu-24-04-8core
            blacksmith: blacksmith-8vcpu-ubuntu-2404
            workload: typecheck
          - platform: linux
            cores: '16'
            runner: dsh-ubuntu-24-04-16core
            blacksmith: blacksmith-16vcpu-ubuntu-2404
            workload: typecheck
          - platform: linux
            cores: '32'
            runner: dsh-ubuntu-24-04-32core
            blacksmith: blacksmith-32vcpu-ubuntu-2404
            workload: typecheck
          - platform: linux
            cores: '64'
            runner: dsh-ubuntu-24-04-64core
            blacksmith: ''
            workload: typecheck
          - platform: linux
            cores: '96'
            runner: dsh-ubuntu-24-04-96core
            blacksmith: ''
            workload: typecheck
          - platform: windows
            cores: '4'
            runner: dsh-windows-2025-4core
            blacksmith: blacksmith-4vcpu-windows-2025
            workload: production-site
          - platform: windows
            cores: '8'
            runner: dsh-windows-2025-8core
            blacksmith: blacksmith-8vcpu-windows-2025
            workload: production-site
          - platform: windows
            cores: '16'
            runner: dsh-windows-2025-16core
            blacksmith: blacksmith-16vcpu-windows-2025
            workload: production-site
          - platform: windows
            cores: '32'
            runner: dsh-windows-2025-32core
            blacksmith: blacksmith-32vcpu-windows-2025
            workload: production-site
          - platform: windows
            cores: '64'
            runner: dsh-windows-2025-64core
            blacksmith: ''
            workload: production-site
          - platform: windows
            cores: '96'
            runner: dsh-windows-2025-96core
            blacksmith: ''
            workload: production-site
    steps:
      - uses: actions/checkout@v6

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

      # 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'
    # Default measures the repository's own fleet tiers; under the matching
    # platform's blacksmith failover value the tiers Blacksmith offers (up to
    # 32 vCPU) move onto their Blacksmith equivalents, while the 64/96-core
    # rows keep the fleet labels because Blacksmith has no such tier.
    runs-on: >-
      ${{ (matrix.platform == 'linux' && vars.DSH_CI_FAILOVER_LINUX == 'blacksmith'
            || matrix.platform == 'windows' && vars.DSH_CI_FAILOVER_WINDOWS == 'blacksmith')
          && matrix.blacksmith
          || matrix.runner }}
    timeout-minutes: 15
    strategy:
      fail-fast: false
      max-parallel: 12
      matrix:
        include:
          - platform: linux
            cores: '4'
            runner: dsh-ubuntu-24-04-4core
            blacksmith: blacksmith-4vcpu-ubuntu-2404
            workers: '4'
          - platform: linux
            cores: '8'
            runner: dsh-ubuntu-24-04-8core
            blacksmith: blacksmith-8vcpu-ubuntu-2404
            workers: '8'
          - platform: linux
            cores: '16'
            runner: dsh-ubuntu-24-04-16core
            blacksmith: blacksmith-16vcpu-ubuntu-2404
            workers: '16'
          - platform: linux
            cores: '32'
            runner: dsh-ubuntu-24-04-32core
            blacksmith: blacksmith-32vcpu-ubuntu-2404
            workers: '32'
          - platform: linux
            cores: '64'
            runner: dsh-ubuntu-24-04-64core
            blacksmith: ''
            workers: '32'
          - platform: linux
            cores: '96'
            runner: dsh-ubuntu-24-04-96core
            blacksmith: ''
            workers: '32'
          - platform: windows
            cores: '4'
            runner: dsh-windows-2025-4core
            blacksmith: blacksmith-4vcpu-windows-2025
            workers: '2'
          - platform: windows
            cores: '8'
            runner: dsh-windows-2025-8core
            blacksmith: blacksmith-8vcpu-windows-2025
            workers: '2'
          - platform: windows
            cores: '16'
            runner: dsh-windows-2025-16core
            blacksmith: blacksmith-16vcpu-windows-2025
            workers: '2'
          - platform: windows
            cores: '32'
            runner: dsh-windows-2025-32core
            blacksmith: blacksmith-32vcpu-windows-2025
            workers: '2'
          - platform: windows
            cores: '64'
            runner: dsh-windows-2025-64core
            blacksmith: ''
            workers: '2'
          - platform: windows
            cores: '96'
            runner: dsh-windows-2025-96core
            blacksmith: ''
            workers: '2'
    steps:
      - uses: actions/checkout@v6

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

      # 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