ci.yml

name: CI

on:
  pull_request:
  push:
    branches:
      - main

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

# CI is not a user. Without this, executor's own product telemetry reports to the
# production PostHog project from every e2e shard: the analytics layer
# (integration_added, execution_completed, artifact_*) and the
# integrations-registry fetch, which lands as a `hit` event. Each shard is a
# fresh container, so it mints a fresh anonymous id and arrives on a fresh
# runner IP — inflating machine and user counts by roughly an order of
# magnitude. Both opt-outs are the packages' documented CI/test hooks.
env:
  DO_NOT_TRACK: "1"
  EXECUTOR_DISABLE_ANALYTICS: "1"
  EXECUTOR_DISABLE_INTEGRATIONS_FETCH: "1"

jobs:
  changes:
    name: Changed paths
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 10
    outputs:
      desktop_smoke: ${{ github.event_name != 'pull_request' || steps.filter.outputs.desktop_smoke == 'true' }}
      selfhost_docker_smoke: ${{ github.event_name != 'pull_request' || steps.filter.outputs.selfhost_docker_smoke == 'true' }}
      cloud_closure: ${{ github.event_name != 'pull_request' || steps.filter.outputs.cloud_closure == 'true' }}
    steps:
      - uses: actions/checkout@v4

      - name: Filter changed paths
        id: filter
        if: github.event_name == 'pull_request'
        uses: dorny/paths-filter@v3
        with:
          filters: |
            desktop_smoke:
              - ".github/workflows/**"
              - "bun.lock"
              - "package.json"
              - "turbo.json"
              - "apps/desktop/**"
              - "apps/local/**"
              - "apps/cli/**"
              - "packages/app/**"
              - "packages/core/**"
              - "packages/hosts/mcp/**"
              - "packages/kernel/runtime-quickjs/**"
              - "packages/plugins/**"
              - "packages/react/**"
            cloud_closure:
              - ".github/workflows/**"
              - "bun.lock"
              - "package.json"
              - "turbo.json"
              - "apps/cloud/**"
              - "packages/**"

            selfhost_docker_smoke:
              - ".github/workflows/**"
              - ".dockerignore"
              - "bun.lock"
              - "package.json"
              - "turbo.json"
              - "apps/host-selfhost/**"
              - "packages/app/**"
              - "packages/core/**"
              - "packages/hosts/mcp/**"
              - "packages/kernel/runtime-quickjs/**"
              - "packages/plugins/**"
              - "packages/react/**"

  format:
    name: Format
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      - run: bun install --frozen-lockfile --ignore-scripts

      - run: bun run format:check

  lint:
    name: Lint
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      - run: bun install --frozen-lockfile --ignore-scripts

      - run: bun run lint

  typecheck:
    name: Typecheck
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 15
    env:
      TURBO_API: ${{ vars.TURBO_API }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_REMOTE_CACHE_SIGNATURE_KEY: ${{ secrets.TURBO_REMOTE_CACHE_SIGNATURE_KEY }}
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      # No prebuilt better-sqlite3 binary matches this runner, so `bun install`
      # builds it from source via node-gyp, whose undici needs Node 22.10+
      # (webidl.markAsUncloneable). Pin the same Node 24 runtime used by release.
      - uses: actions/setup-node@v4
        with:
          node-version: 24

      - run: bun install --frozen-lockfile

      - run: bun run typecheck

      # The committed routeTree.gen.ts files are generated but checked in, and
      # they carry @ts-nocheck — so the typecheck above structurally CANNOT see
      # a route that the contract declares and the tree lacks. That drift has
      # already shipped a live 404 once. Regenerate and diff instead.
      - run: bun run check:routes

  test:
    name: Test
    runs-on: blacksmith-16vcpu-ubuntu-2404
    timeout-minutes: 15
    # Run eight independent packages at once and cap each Vitest process at two
    # workers. This uses all 16 vCPUs without every nested runner seeing the
    # whole machine and oversubscribing it.
    env:
      TURBO_API: ${{ vars.TURBO_API }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_REMOTE_CACHE_SIGNATURE_KEY: ${{ secrets.TURBO_REMOTE_CACHE_SIGNATURE_KEY }}
      TURBO_TEST_CONCURRENCY: 8
      VITEST_MAX_WORKERS: 2
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      # apps/cloud's test script invokes `node` directly; undici 8.x (pulled
      # in by @cloudflare/vitest-pool-workers) calls webidl.markAsUncloneable
      # which only exists in Node 22.10+. Pin the Node 24 CI runtime.
      - uses: actions/setup-node@v4
        with:
          node-version: 24

      - run: bun install --frozen-lockfile

      # Fail loudly if a load-bearing patched dependency (e.g. the agents MCP
      # transport hang fix) resolved to a stale, unpatched dist. Without this,
      # a bun cache edge case can leave the patch unapplied while everything
      # still builds and tests green, and prod ships the pre-fix transport with
      # no signal. This is just a few file reads plus greps, so ~zero cost.
      - run: bun run check:patches

      - run: bun run --cwd e2e test:ci-shard

      - run: bun run test

  e2e:
    name: E2E (${{ matrix.target }}${{ matrix['shard-name'] && format(' {0}', matrix['shard-name']) || '' }})
    strategy:
      fail-fast: false
      matrix:
        include:
          # The planner assigns every file exactly once using recorded slow-file
          # durations plus a conservative weight for new tests. The cloud DB's
          # connection teardown and concurrent socket protocol have dedicated
          # regression tests; these shards balance wall clock, not hide retries.
          - { target: cloud, shard-index: 1, shard-name: 1of16 }
          - { target: cloud, shard-index: 2, shard-name: 2of16 }
          - { target: cloud, shard-index: 3, shard-name: 3of16 }
          - { target: cloud, shard-index: 4, shard-name: 4of16 }
          - { target: cloud, shard-index: 5, shard-name: 5of16 }
          - { target: cloud, shard-index: 6, shard-name: 6of16 }
          - { target: cloud, shard-index: 7, shard-name: 7of16 }
          - { target: cloud, shard-index: 8, shard-name: 8of16 }
          - { target: cloud, shard-index: 9, shard-name: 9of16 }
          - { target: cloud, shard-index: 10, shard-name: 10of16 }
          - { target: cloud, shard-index: 11, shard-name: 11of16 }
          - { target: cloud, shard-index: 12, shard-name: 12of16 }
          - { target: cloud, shard-index: 13, shard-name: 13of16 }
          - { target: cloud, shard-index: 14, shard-name: 14of16 }
          - { target: cloud, shard-index: 15, shard-name: 15of16 }
          - { target: cloud, shard-index: 16, shard-name: 16of16 }
          - { target: selfhost, shard-index: 1, shard-name: 1of10 }
          - { target: selfhost, shard-index: 2, shard-name: 2of10 }
          - { target: selfhost, shard-index: 3, shard-name: 3of10 }
          - { target: selfhost, shard-index: 4, shard-name: 4of10 }
          - { target: selfhost, shard-index: 5, shard-name: 5of10 }
          - { target: selfhost, shard-index: 6, shard-name: 6of10 }
          - { target: selfhost, shard-index: 7, shard-name: 7of10 }
          - { target: selfhost, shard-index: 8, shard-name: 8of10 }
          - { target: selfhost, shard-index: 9, shard-name: 9of10 }
          - { target: selfhost, shard-index: 10, shard-name: 10of10 }
          # Local files own their server, browser and data directory. Separate
          # runners preserve that isolation while removing its 69-second serial
          # lane from the two-minute critical path.
          - { target: local, shard-index: 1, shard-name: 1of2 }
          - { target: local, shard-index: 2, shard-name: 2of2 }
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      # The dev stacks spawn Node sidecars (vite/workerd tooling); pin the
      # same Node 24 runtime the release and publish workflows use.
      - uses: actions/setup-node@v4
        with:
          node-version: 24

      - run: bun install --frozen-lockfile

      - name: Cache Playwright browsers
        uses: actions/cache@v4
        with:
          path: ~/.cache/ms-playwright
          key: ${{ runner.os }}-playwright-1.60.0
          restore-keys: |
            ${{ runner.os }}-playwright-

      # Install from e2e so bunx resolves ITS pinned playwright (the version
      # the tests run against) rather than floating to the latest.
      # Blacksmith's Ubuntu image carries the official GitHub runner system
      # dependencies. Restore the pinned browser binaries without apt-updating
      # every matrix machine.
      - name: Install Playwright Chromium
        run: bunx playwright install chromium chromium-headless-shell
        working-directory: e2e

      # Each target either boots its own shared dev server or lets each file own
      # its server. Ports and data paths are hermetic in both cases.
      # Do not retry scenarios: retries hide flakes and multiply slow timeout
      # failures. The fixtures and process lifecycle are deterministic enough
      # that the first result is the result.
      - name: Run cloud shard
        if: matrix.target == 'cloud'
        env:
          MCP_SESSION_TIMEOUT_MS: "3000"
          MCP_PAUSED_SESSION_IDLE_TIMEOUT_MS: "6000"
        run: bun scripts/run-ci-shard.ts cloud ${{ matrix['shard-index'] }}
        working-directory: e2e

      - name: Run scenarios
        if: matrix.target != 'cloud'
        run: bun scripts/run-ci-shard.ts ${{ matrix.target }} ${{ matrix['shard-index'] }}
        working-directory: e2e

      # Failed runs keep their trace.zip / session.mp4 / step screenshots in
      # runs/<target>/<slug>/ — surface them instead of a bare red X.
      - name: Upload run artifacts
        if: failure()
        uses: actions/upload-artifact@v4
        with:
          name: e2e-runs-${{ matrix.target }}${{ matrix['shard-name'] && format('-{0}', matrix['shard-name']) || '' }}
          path: e2e/runs/
          retention-days: 7

  cloud-closure:
    name: Cloud evaluated closure
    needs: changes
    if: needs.changes.outputs.cloud_closure == 'true'
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 20
    env:
      TURBO_API: ${{ vars.TURBO_API }}
      TURBO_TEAM: ${{ vars.TURBO_TEAM }}
      TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
      TURBO_REMOTE_CACHE_SIGNATURE_KEY: ${{ secrets.TURBO_REMOTE_CACHE_SIGNATURE_KEY }}
      # Every cold isolate evaluates this closure before it can answer a
      # request, and it only ever grows by accident - a barrel export or a new
      # module-scope import quietly pulls megabytes into the server graph. The
      # budget is a ratchet just above today's size, not a discovered limit:
      # when it trips, make the new dependency lazy rather than raising it.
      START_CLOSURE_BUDGET_MB: 13.5
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      - uses: actions/setup-node@v4
        with:
          node-version: 24

      - run: bun install --frozen-lockfile

      - run: bun run build
        working-directory: apps/cloud

      - run: node scripts/start-closure.mjs
        working-directory: apps/cloud

  desktop-smoke:
    name: Desktop smoke build
    needs: changes
    if: needs.changes.outputs.desktop_smoke == 'true'
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@v4

      - uses: oven-sh/setup-bun@v2
        with:
          bun-version: 1.3.11

      - name: Cache Bun package cache
        uses: actions/cache@v4
        with:
          path: ~/.bun/install/cache
          key: ${{ runner.os }}-bun-1.3.11-${{ hashFiles('bun.lock') }}
          restore-keys: |
            ${{ runner.os }}-bun-1.3.11-

      # No prebuilt better-sqlite3 binary matches this runner, so `bun install`
      # builds it from source via node-gyp, whose undici needs Node 22.10+
      # (webidl.markAsUncloneable). Pin the same Node 24 CI runtime.
      - uses: actions/setup-node@v4
        with:
          node-version: 24

      - run: bun install --frozen-lockfile

      - name: Build web app
        run: bun run --filter @executor-js/local build

      - name: Build bundled executor
        env:
          BUN_TARGET: bun-linux-x64
        run: bun ./scripts/build-sidecar.ts
        working-directory: apps/desktop

      # Run the compiled sidecar in a clean container where the build
      # workspace does not exist. bun --compile bakes build-machine paths
      # into __dirname for runtime-loaded assets; running the binary on the
      # build machine hides that entire failure class (this exact gap
      # shipped a broken 1Password SDK: its sdk-core wasm was read from the
      # CI runner's node_modules path at runtime, ENOENT on every user
      # machine). Pass condition: the 1Password endpoint reaches real
      # credential validation, not a module-load or empty-namespace error.
      - name: Run sidecar outside the workspace
        working-directory: apps/desktop
        run: |
          docker run --rm -d --name sidecar-smoke -p 45841:45841 -e HOME=/tmp \
            -v "$PWD/resources/executor:/opt/executor:ro" \
            debian:bookworm-slim /opt/executor/executor daemon run --foreground \
            --port 45841 --hostname 0.0.0.0 --auth-token=ci-smoke
          for i in $(seq 1 60); do
            code=$(curl -s -o /dev/null -w '%{http_code}' -H "Authorization: Bearer ci-smoke" http://127.0.0.1:45841/api/onepassword/vaults || true)
            [ "$code" != "000" ] && break
            docker ps -q -f name=sidecar-smoke | grep -q . || { docker logs sidecar-smoke; exit 1; }
            sleep 1
          done
          body=$(curl -s -H "Authorization: Bearer ci-smoke" \
            "http://127.0.0.1:45841/api/onepassword/vaults?authKind=service-account&account=ops_ci_fake_token")
          docker stop sidecar-smoke
          echo "$body"
          if echo "$body" | grep -qE "sdk module load|ENOENT|is not a function|not a constructor"; then
            echo "::error::1Password SDK failed to load inside the compiled binary (baked build path or missing sibling asset)"
            exit 1
          fi
          if ! echo "$body" | grep -q "invalid service account token"; then
            echo "::error::sidecar did not reach 1Password credential validation; unexpected response above"
            exit 1
          fi

      - name: Build Electron main/preload/renderer
        run: bunx --bun electron-vite build
        working-directory: apps/desktop

  selfhost-docker-smoke:
    name: Self-host Docker image
    needs: changes
    if: needs.changes.outputs.selfhost_docker_smoke == 'true'
    runs-on: blacksmith-4vcpu-ubuntu-2404
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@v4

      - name: Setup Blacksmith Builder
        uses: useblacksmith/setup-docker-builder@v1

      - name: Build self-host image
        uses: useblacksmith/build-push-action@v2
        with:
          context: .
          file: apps/host-selfhost/Dockerfile
          push: false
          load: true
          tags: executor-selfhost:ci

      # Building alone doesn't catch startup crashes (e.g. a runtime-resolved
      # package missing from the packaged runtime), so boot the container and
      # require a healthy /api/health before calling the image good.
      - name: Boot image and check health
        shell: bash
        run: |
          set -euo pipefail
          docker run -d --name selfhost-smoke -p 4788:4788 \
            -e BETTER_AUTH_SECRET="$(openssl rand -hex 32)" \
            -e EXECUTOR_BOOTSTRAP_ADMIN_EMAIL=smoke@example.com \
            -e EXECUTOR_BOOTSTRAP_ADMIN_PASSWORD="$(openssl rand -hex 16)" \
            -e EXECUTOR_WEB_BASE_URL=http://localhost:4788 \
            executor-selfhost:ci
          for i in $(seq 1 30); do
            if [ "$(docker inspect -f '{{.State.Running}}' selfhost-smoke)" != "true" ]; then
              echo "container exited during startup"
              docker logs selfhost-smoke
              exit 1
            fi
            if curl -fsS http://localhost:4788/api/health >/dev/null 2>&1; then
              echo "healthy after ${i}s"
              docker logs selfhost-smoke
              exit 0
            fi
            sleep 1
          done
          echo "health check never passed"
          docker logs selfhost-smoke
          exit 1