orca/.github/workflows/e2e.yml

name: E2E

run-name: E2E ${{ inputs.ref || github.ref }}

# Why: checkout + artifact upload only; callers can only further restrict.
permissions:
  contents: read

on:
  workflow_call:
    inputs:
      ref:
        description: Ref to check out (defaults to the calling workflow's ref)
        required: false
        type: string
      test_files:
        description: JSON array of changed specs; empty runs the full suite
        required: false
        type: string
      ssh_source_changed:
        description: '"true" when the PR touches SSH execution source; gates the Docker-SSH lane'
        required: false
        type: string
  workflow_dispatch:
    inputs:
      ref:
        description: Ref to check out (defaults to the workflow ref)
        required: false
        type: string
      test_files:
        description: JSON array of specs to run; empty runs the full suite
        required: false
        type: string
  schedule:
    # Why: GitHub cron uses UTC; these slots map to 10am and 3pm
    # America/Phoenix for the default-branch E2E run.
    - cron: '0 17,22 * * *'

jobs:
  build:
    name: build e2e app
    runs-on: ubuntu-latest
    timeout-minutes: 10

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}

      # Why: the build's plain-Node daemon smoke load resolves node-pty.
      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: node

      # Why: building here avoids parallel builds inside Playwright globalSetup;
      # paired-browser specs also need the standalone web bundle.
      - name: Build E2E outputs
        env:
          VITE_EXPOSE_STORE: 'true'
        run: |
          status=0
          pnpm run build:relay &
          relay_pid=$!
          npx electron-vite build --mode e2e || status=1
          pnpm run build:web-from-renderer || status=1
          wait "$relay_pid" || status=1
          exit "$status"

      - name: Upload E2E build output
        uses: actions/upload-artifact@v7
        with:
          name: e2e-build-out
          path: out/
          # Why: build-relay.mjs writes each relay's marker as `out/relay/<platform>/.version`,
          # and upload-artifact drops dotfiles by default — consumers then fail SSH specs with
          # "local relay build is missing its version marker".
          include-hidden-files: true
          retention-days: 1
          if-no-files-found: error

  # Build Electron-native dependencies once per workflow. Consumer shards restore
  # this immutable cache instead of compiling the same ABI concurrently.
  prepare-native-cache:
    name: prepare Electron native cache
    runs-on: ubuntu-latest
    timeout-minutes: 15

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}

      - name: Install native build tools
        run: sudo apt-get update && sudo apt-get install -y build-essential python3

      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: electron

  e2e:
    name: e2e ${{ matrix.shard_name }}
    needs: [build, prepare-native-cache]
    if: inputs.test_files == ''
    runs-on: ubuntu-latest
    timeout-minutes: 30
    strategy:
      fail-fast: false
      matrix:
        include:
          # Fourteen scheduled runs averaged 24.6 minutes per shard; shards 4
          # and 9 repeatedly hit the 30-minute cap. A 12-way trial still left
          # one 30-minute shard, so 14 gives the suite enough failure headroom.
          - shard: '1/14'
            shard_name: 1-of-14
          - shard: '2/14'
            shard_name: 2-of-14
          - shard: '3/14'
            shard_name: 3-of-14
          - shard: '4/14'
            shard_name: 4-of-14
          - shard: '5/14'
            shard_name: 5-of-14
          - shard: '6/14'
            shard_name: 6-of-14
          - shard: '7/14'
            shard_name: 7-of-14
          - shard: '8/14'
            shard_name: 8-of-14
          - shard: '9/14'
            shard_name: 9-of-14
          - shard: '10/14'
            shard_name: 10-of-14
          - shard: '11/14'
            shard_name: 11-of-14
          - shard: '12/14'
            shard_name: 12-of-14
          - shard: '13/14'
            shard_name: 13-of-14
          - shard: '14/14'
            shard_name: 14-of-14

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}

      # Native cache misses need the compiler, Electron needs Xvfb, and paired
      # Quick Open needs ripgrep. Install them in one apt transaction per shard.
      - name: Install native build and headless UI tools
        run: sudo apt-get update && sudo apt-get install -y build-essential fonts-noto-cjk python3 ripgrep xvfb zsh openbox x11-utils

      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: electron

      - name: Download E2E build output
        uses: actions/download-artifact@v8
        with:
          name: e2e-build-out
          path: out/

      # Why: the Electron suite is wall-clock constrained on OSS runners, but
      # multiple Electron apps on one Xvfb VM contend on git/Chromium resources.
      # Sharding keeps each VM at one Playwright worker while splitting the
      # headless suite across separate runners.
      # SKIP_BUILD makes Playwright globalSetup reuse the single build job's
      # artifact instead of starting five concurrent electron-vite builds.
      # ORCA_E2E_FORWARD_APP_LOGS keeps startup failures visible when Electron
      # launches but never creates a BrowserWindow.
      - name: Balance E2E shard from timing evidence
        env:
          ORCA_BACKGROUND_LAUNCH: '1'
          SKIP_BUILD: '1'
          ORCA_E2E_FORWARD_APP_LOGS: '1'
          ORCA_E2E_WEB_CLIENT: '1'
          ORCA_RELAY_PATH: ${{ github.workspace }}/out/relay
        run: |
          mkdir -p ci-shards
          pnpm exec playwright test --config tests/playwright.config.ts --project=electron-headless --list --reporter=json > ci-shards/discovery.json
          export ORCA_SHARD_SOURCE_SHA="$(git rev-parse HEAD)"
          node config/scripts/ci-e2e-shard-plan.mjs ci-shards/discovery.json '${{ matrix.shard }}' ci-shards
          pnpm exec playwright test --config tests/playwright.config.ts --project=electron-headless --test-list=ci-shards/selected.txt --list --reporter=json > ci-shards/selected-discovery.json
          node config/scripts/ci-e2e-shard-plan.mjs --verify ci-shards/assignment.json ci-shards/selected-discovery.json

      - name: Run E2E tests (${{ matrix.shard_name }})
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 ORCA_E2E_WEB_CLIENT=1 ORCA_RELAY_PATH="$GITHUB_WORKSPACE/out/relay" pnpm run test:e2e --test-list=ci-shards/selected.txt

      - name: Upload E2E shard assignment
        if: always()
        # Diagnostic upload outages must not change the test verdict.
        continue-on-error: true
        uses: actions/upload-artifact@v7
        with:
          name: e2e-shard-${{ matrix.shard_name }}-attempt-${{ github.run_attempt }}
          path: ci-shards/
          retention-days: 14
          if-no-files-found: warn

      # The frame benchmark needs a mapped window, which the headless shards exclude.
      - name: Run worktree first-paint benchmark
        if: matrix.shard == '1/14'
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm exec playwright test tests/e2e/worktree-switch-first-paint.spec.ts --config tests/playwright.config.ts --project=electron-headful --workers=1

      # Why: Playwright retains traces/screenshots only on failure. Uploading
      # them as an artifact makes post-mortem debugging on CI possible without
      # re-running locally.
      - name: Upload Playwright traces
        if: failure()
        uses: actions/upload-artifact@v7
        with:
          name: playwright-traces-${{ matrix.shard_name }}
          path: test-results/
          retention-days: 7
          if-no-files-found: ignore

  changed-e2e:
    name: changed e2e specs
    needs: [build, prepare-native-cache]
    if: inputs.test_files != ''
    runs-on: ubuntu-latest
    # Why 45: pr.yml now maps SSH source edits onto Docker-backed specs, so this lane can
    # pay a container image build plus ~22 serial SSH tests on top of the changed specs.
    timeout-minutes: 45

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}

      - name: Install native build and headless UI tools
        # Why ripgrep: Quick Open's bounded host-side search requires rg instead of an
        # unbounded inventory fallback; the paired fixture exercises that real boundary.
        # Why openssh-client: the Docker-SSH fixture shells out to ssh/ssh-keygen, and this
        # lane now receives those specs from pr.yml's SSH source mapping.
        run: sudo apt-get update && sudo apt-get install -y build-essential fonts-noto-cjk openssh-client python3 ripgrep xvfb zsh openbox x11-utils

      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: electron

      - name: Download E2E build output
        uses: actions/download-artifact@v8
        with:
          name: e2e-build-out
          path: out/

      - name: Run changed E2E specs
        env:
          TEST_FILES_JSON: ${{ inputs.test_files }}
        run: |
          # Why the native IME spec is dropped: it test.skip()s itself without
          # ORCA_E2E_NATIVE_IBUS_HANGUL, which this lane cannot set because it has no ibus
          # session. Running it here reported a green skip as coverage.
          mapfile -t TEST_FILES < <(jq -r '.[] | select(
            . != "tests/e2e/ssh-startup-exec-readiness.spec.ts" and
            . != "tests/e2e/paired-startup-exec-readiness.spec.ts" and
            . != "tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts" and
            . != "tests/e2e/local-ssh-browser-routing.spec.ts" and
            . != "tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts" and
            . != "tests/e2e/ssh-localhost.spec.ts" and
            . != "tests/e2e/ssh-client-hosted-browser-drop-reconnect.spec.ts" and
            . != "tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts" and
            . != "tests/e2e/terminal-ibus-hangul-native.spec.ts"
          )' <<<"$TEST_FILES_JSON")
          if [ "${#TEST_FILES[@]}" -eq 0 ]; then
            echo "Changed specs are all owned by dedicated lanes."
            exit 0
          fi
          E2E_ENV=(SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 ORCA_E2E_WEB_CLIENT=1 ORCA_RELAY_PATH="$GITHUB_WORKSPACE/out/relay")
          # Second clause: a spec that reads ORCA_E2E_SSH_DOCKER test.skip()s itself without it, so
          # naming only one trigger silently skipped every other Docker-SSH spec in this lane.
          # The first clause stays because that spec needs Docker without referencing the variable.
          if printf '%s\n' "${TEST_FILES[@]}" | grep -qx 'tests/e2e/ephemeral-vm-provisioned-root.spec.ts' \
            || grep -l 'ORCA_E2E_SSH_DOCKER' "${TEST_FILES[@]}" >/dev/null 2>&1; then
            E2E_ENV+=(ORCA_E2E_SSH_DOCKER=1)
          fi
          E2E_PROJECT_ARGS=()
          if grep -l '@headful' "${TEST_FILES[@]}" >/dev/null; then
            E2E_PROJECT_ARGS+=(--project=electron-headful)
          fi
          xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env "${E2E_ENV[@]}" \
            pnpm run test:e2e "${TEST_FILES[@]}" --workers=1 "${E2E_PROJECT_ARGS[@]}"

      - name: Upload Playwright traces
        if: failure()
        uses: actions/upload-artifact@v7
        with:
          name: playwright-traces-changed
          path: test-results/
          retention-days: 7
          if-no-files-found: ignore

  ssh-docker-watcher-isolation:
    name: ssh docker watcher isolation
    needs: [build, prepare-native-cache]
    # effect of one route listing a startup-readiness spec — pruning that spec would have
    # silently retired the whole lane. The signal is now derived from the SSH routes directly.
    # The explicit spec clauses stay for their honest purpose: changed-e2e hands these specs to this
    # lane, so editing one must still run it here.
    if: >-
      inputs.test_files == '' ||
      inputs.ssh_source_changed == 'true' ||
      contains(inputs.test_files, 'tests/e2e/ssh-docker-five-pane-input-under-flood.spec.ts') ||
      contains(inputs.test_files, 'tests/e2e/local-ssh-browser-routing.spec.ts') ||
      contains(inputs.test_files, 'tests/e2e/ssh-client-hosted-browser-drop-reconnect.spec.ts') ||
      contains(inputs.test_files, 'tests/e2e/ssh-startup-exec-readiness.spec.ts') ||
      contains(inputs.test_files, 'tests/e2e/ssh-docker-bulk-open-freeze-repro.spec.ts') ||
      contains(inputs.test_files, 'tests/e2e/paired-startup-exec-readiness.spec.ts')
    runs-on: ubuntu-latest
    # Why 60: this lane now also runs the remaining Docker-SSH specs serially. They average
    # ~18s but several budget 4-10 minutes per test, so a slow run lands far above the old 35
    # — and the sharded lanes already show that a lane which times out is a lane nobody trusts.
    timeout-minutes: 60

    steps:
      - name: Checkout
        uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}

      - name: Install native build and headless UI tools
        run: sudo apt-get update && sudo apt-get install -y build-essential fonts-noto-cjk openssh-client python3 ripgrep xvfb zsh openbox x11-utils

      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: electron

      - name: Download E2E build output
        uses: actions/download-artifact@v8
        with:
          name: e2e-build-out
          path: out/

      # Why: this is the release-path proof that the deployed Linux relay keeps
      # its PTY and explorer live across a real watcher SIGSEGV.
      - name: Run Docker SSH watcher isolation E2E
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm run test:e2e:ssh-docker-watcher-isolation

      # Why: Playwright empties test-results/ when it starts, so each step here used to
      # destroy the previous step's traces. Only the last lane's failure was ever
      # diagnosable from the artifact; set each lane aside before the next one runs.
      - name: Keep watcher-isolation traces
        if: always()
        run: |
          if [ -d test-results ]; then
            mkdir -p e2e-traces
            mv test-results "e2e-traces/watcher-isolation"
          fi

      # Why always(): this lane gates SSH parking/retention plus startup-exec
      # readiness across live SSH, headed paired, and headless serve topologies.
      - name: Run Docker SSH terminal parking + startup readiness E2E
        if: always()
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm run test:e2e:ssh-docker-terminal-parking

      - name: Keep terminal-parking traces
        if: always()
        run: |
          if [ -d test-results ]; then
            mkdir -p e2e-traces
            mv test-results "e2e-traces/terminal-parking"
          fi

      # Why here rather than the sharded lanes: the shards set no ORCA_E2E_SSH_DOCKER, so every
      # spec below skipped itself while the shard still reported green. Running them on this one
      # VM pays the fixture image build once instead of ten times, and keeps an SSH regression
      # legible as an SSH-named failure.
      - name: Run remaining Docker SSH E2E
        if: always()
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh env SKIP_BUILD=1 ORCA_E2E_FORWARD_APP_LOGS=1 pnpm run test:e2e:ssh-docker

      - name: Keep remaining-ssh-docker traces
        if: always()
        run: |
          if [ -d test-results ]; then
            mkdir -p e2e-traces
            mv test-results "e2e-traces/remaining-ssh-docker"
          fi

      - name: Upload watcher isolation traces
        if: failure()
        uses: actions/upload-artifact@v7
        with:
          name: playwright-traces-ssh-docker-watcher-isolation
          path: e2e-traces/
          retention-days: 7
          if-no-files-found: ignore

  ssh-browser-network-route:
    name: ssh browser network route
    if: inputs.test_files == '' || contains(inputs.test_files, 'tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts')
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}
      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: node
      - name: Install SSH client
        run: sudo apt-get update && sudo apt-get install -y openssh-client
      - name: Run Docker SSH browser network route journeys
        env:
          ORCA_BACKGROUND_LAUNCH: '1'
          ORCA_RUN_DOCKER_SSH_BROWSER_E2E: '1'
        run: node_modules/.bin/vitest run --config config/vitest.config.ts tests/e2e/ssh-browser-network-execution-route.docker.unit.test.ts

  ssh-localhost:
    name: localhost SSH terminal and hooks
    needs: [build, prepare-native-cache]
    if: inputs.test_files == '' || contains(inputs.test_files, 'tests/e2e/ssh-localhost.spec.ts')
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@v6
        with:
          ref: ${{ inputs.ref || github.ref }}
      - name: Install SSH server and headless tools
        run: sudo apt-get update && sudo apt-get install -y build-essential openssh-client openssh-server python3 ripgrep xvfb zsh openbox x11-utils
      - uses: ./.github/actions/install-node-dependencies
        with:
          native-runtime: electron
      - uses: actions/download-artifact@v8
        with:
          name: e2e-build-out
          path: out/
      - name: Start isolated localhost SSH server
        shell: bash
        run: |
          # Bare shells install Pi extensions only for an existing agent home.
          mkdir -p "$HOME/.pi/agent"
          fixture="$RUNNER_TEMP/orca-localhost-sshd"
          mkdir -p "$fixture"
          ssh-keygen -q -t ed25519 -N '' -f "$fixture/host_key"
          ssh-keygen -q -t ed25519 -N '' -f "$fixture/client_key"
          cat > "$fixture/sshd_config" <<EOF
          Port 22222
          ListenAddress 127.0.0.1
          HostKey $fixture/host_key
          PidFile $fixture/sshd.pid
          AuthorizedKeysFile $fixture/client_key.pub
          StrictModes no
          PasswordAuthentication no
          KbdInteractiveAuthentication no
          UsePAM yes
          AllowUsers $(id -un)
          Subsystem sftp internal-sftp
          EOF
          sudo mkdir -p /run/sshd
          sudo /usr/sbin/sshd -f "$fixture/sshd_config" -E "$fixture/sshd.log"
          ssh -i "$fixture/client_key" -p 22222 -o BatchMode=yes -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null 127.0.0.1 true || { sudo cat "$fixture/sshd.log"; exit 1; }
          {
            echo "ORCA_E2E_SSH_PORT=22222"
            echo "ORCA_E2E_SSH_USER=$(id -un)"
            echo "ORCA_E2E_SSH_IDENTITY_FILE=$fixture/client_key"
          } >> "$GITHUB_ENV"
      - name: Run localhost SSH terminal and hook journey
        env:
          SKIP_BUILD: '1'
          ORCA_E2E_SSH_LOCALHOST: '1'
          ORCA_FEATURE_REMOTE_AGENT_HOOKS: '1'
          ORCA_E2E_FORWARD_APP_LOGS: '1'
        run: xvfb-run --auto-servernum bash .github/scripts/e2e-with-window-manager.sh pnpm exec playwright test --config tests/playwright.config.ts tests/e2e/ssh-localhost.spec.ts --project=electron-headless --workers=1
      - uses: actions/upload-artifact@v7
        if: failure()
        with:
          name: localhost-ssh-traces
          path: test-results/
          retention-days: 7
          if-no-files-found: ignore