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

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

env:
  PRIMARY_NODE_VERSION: '24'

jobs:

  # One large runner pays hosted setup once, then the repository scheduler
  # overlaps the complete unsharded primary Node inventory. Build starts eagerly;
  # only consumers of emitted output wait for it.
  node-24:
    if: github.event_name == 'pull_request'
    runs-on: dsh-ubuntu-24-04-96core
    name: node 24 / complete
    env:
      DSH_COVERAGE_MAX_WORKERS: '16'
      DSH_ESLINT_CONCURRENCY: '16'
      DSH_GATE_CONCURRENCY: '12'
      DSH_PUBLINT_CONCURRENCY: '16'
      DSH_SNAPSHOT_MAX_CONCURRENCY: '8'
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false

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

      - name: Enable corepack and resolve pnpm store path
        id: pnpm-store
        run: |
          corepack enable
          echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"

      # Pull requests consume the default-branch cache but do not put cache
      # compression and upload on the paid latency-critical path.
      - 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-

      - 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 complete unsharded primary Node CI concurrently
        run: pnpm run check:ci


  node-compat:
    if: github.event_name == 'pull_request'
    # Distinct larger-runner pools avoid both standard-runner setup outliers and
    # delayed allocation when independent environment contracts share one pool.
    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: dsh-ubuntu-24-04-4core
            gate_concurrency: '2'
          - node: 26
            name: node 26
            runner: dsh-ubuntu-24-04-32core
            gate_concurrency: '2'
    steps:
      - uses: actions/checkout@v6

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

      - name: Enable corepack and resolve pnpm store path
        id: pnpm-store
        run: |
          corepack enable
          echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"

      - uses: actions/cache@v4
        with:
          path: ${{ steps.pnpm-store.outputs.path }}
          key: ${{ runner.os }}-node-${{ matrix.node }}-pnpm-${{ hashFiles('pnpm-lock.yaml') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ matrix.node }}-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: dsh-ubuntu-24-04-8core
    name: python 3.10 / keyless SDK
    steps:
      - uses: actions/checkout@v6

      - uses: actions/setup-python@v6
        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 Windows box shares setup across the required build/site checks and the
  # complete observational portability inventory. run-gates reports failures
  # from observational gates without allowing them to fail the required job.
  windows:
    if: github.event_name == 'pull_request'
    runs-on: dsh-windows-2025-32core
    name: windows node 24 / complete
    env:
      # Keep ESLint itself single-threaded: 16 ESLint workers took 174 seconds on
      # this image. The outer scheduler still overlaps lint with the other gates.
      DSH_COVERAGE_MAX_WORKERS: '12'
      DSH_ESLINT_CACHE: '1'
      DSH_GATE_CONCURRENCY: '16'
      DSH_PUBLINT_CONCURRENCY: '16'
    steps:
      - uses: actions/checkout@v6

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

      - uses: actions/cache/restore@v4
        with:
          path: .cache/eslint
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-

      # Extracting the many-file pnpm store cache is slower on this image than
      # a clean parallel install, and saving it adds more latency after gates.
      - name: Enable corepack and install (immutable)
        shell: pwsh
        run: |
          corepack enable
          pnpm install --frozen-lockfile

      - name: Run blocking and observational Windows gates concurrently
        shell: pwsh
        run: pnpm run check:ci:windows-complete

  # Master pushes run only the serial reference jobs below.
  # Each 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: github.event_name == 'push' && github.ref == 'refs/heads/master'
    name: serial / linux
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v6

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

      - name: Enable corepack and resolve pnpm store path
        id: pnpm-store
        run: |
          corepack enable
          echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"

      # Master refreshes the caches that pull requests restore without saving.
      - 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-

      - uses: actions/cache@v4
        with:
          path: .cache/eslint
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-

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

      - name: Prepare bubblewrap (unrestrict userns)
        run: bash scripts/prepare-ci-bubblewrap.sh

      - name: Run complete unsharded primary Node CI serially
        env:
          DSH_COVERAGE_MAX_WORKERS: '1'
          DSH_E2E_MAX_WORKERS: '1'
          DSH_ESLINT_CACHE: '1'
          DSH_GATE_CONCURRENCY: '1'
          DSH_PUBLINT_CONCURRENCY: '1'
          DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
        run: pnpm run check:ci

  serial-macos:
    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
    name: serial / macos
    runs-on: macos-latest
    steps:
      - uses: actions/checkout@v6

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

      - name: Enable corepack (pnpm)
        run: corepack enable

      - 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

  serial-windows:
    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
    name: serial / windows
    runs-on: windows-2025
    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: actions/setup-node@v6
        with:
          node-version: ${{ env.PRIMARY_NODE_VERSION }}

      - name: Enable corepack (pnpm)
        shell: pwsh
        run: corepack enable

      # Master refreshes the small cache that pull requests restore without
      # putting package-store extraction back on the Windows critical path.
      - uses: actions/cache@v4
        with:
          path: .cache/eslint
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-

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

      - name: Run complete unsharded primary Node CI serially
        shell: pwsh
        env:
          DSH_COVERAGE_MAX_WORKERS: '1'
          DSH_E2E_MAX_WORKERS: '1'
          DSH_ESLINT_CACHE: '1'
          DSH_GATE_CONCURRENCY: '1'
          DSH_PUBLINT_CONCURRENCY: '1'
          DSH_SNAPSHOT_MAX_CONCURRENCY: '1'
        run: pnpm run check:ci

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

      - 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: Enable corepack (pnpm)
        run: corepack enable

      - name: Resolve pnpm store path
        if: matrix.platform == 'linux'
        id: pnpm-store
        run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"

      - uses: actions/cache@v4
        if: matrix.platform == 'linux'
        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 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 surfaces 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: actions/setup-node@v6
        with:
          node-version: ${{ env.PRIMARY_NODE_VERSION }}

      - 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: Enable corepack (pnpm)
        run: corepack enable

      - name: Resolve pnpm store path (Linux)
        if: matrix.platform == 'linux'
        id: pnpm-store-linux
        run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"

      - name: Resolve pnpm store path (Windows)
        if: matrix.platform == 'windows'
        id: pnpm-store-windows
        shell: pwsh
        run: '"path=$(pnpm store path --silent)" >> $env:GITHUB_OUTPUT'

      - uses: actions/cache@v4
        with:
          path: ${{ steps.pnpm-store-linux.outputs.path || steps.pnpm-store-windows.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-

      - uses: actions/cache@v4
        if: matrix.platform == 'linux'
        with:
          path: .cache/eslint
          key: ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-${{ hashFiles('pnpm-lock.yaml', 'eslint.config.mjs', 'tsconfig.json', 'packages/*/*/tsconfig.json', 'examples/*/tsconfig.json') }}
          restore-keys: |
            ${{ runner.os }}-node-${{ env.PRIMARY_NODE_VERSION }}-eslint-full-

      - 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_ESLINT_CACHE: '1'
          DSH_ESLINT_CONCURRENCY: ${{ matrix.workers }}
          DSH_GATE_CONCURRENCY: ${{ 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`; observational Windows gates share the required Windows job but are
  # marked non-blocking inside run-gates. (`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
    runs-on: ubuntu-latest
    needs: [node-24, node-compat, python-sdk, 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, ', ') }})"