elizaos--eliza/.github/workflows/mobile-resource-workbench.yml

name: mobile-resource-workbench

# On-device resource profiling for local inference (issue #8800): battery, RSS,
# prefill/decode tok/s, TTFT, thermal timeline — per-tier budgets + a report.
#
# Layered like local-inference-bench, because the device lanes are slow and
# hardware-bound:
#
#   1. harness-smoke  (PR path-filtered + nightly + dispatch): runs the pure
#      aggregation/budget unit tests and the runner's off-device skip path on a
#      GitHub-hosted runner. Fast, no device — the only lane that can touch PRs,
#      and only when the workbench files change.
#   2. android-device (dispatch only): builds the WebView-debuggable APK and runs
#      the workbench against a real arm64 device on the self-hosted pool, then
#      uploads the report + raw results.
#   3. ios-sim        (dispatch only): boots a simulator, runs the workbench
#      (RSS/tok-s/TTFT; battery/thermal are physical-only), pulls MetricKit, and
#      uploads the report.
#
# Device lanes are kept OFF PR-blocking lanes until per-device baselines in
# budgets.json are stable (most budgets are still `null` = no-baseline).

on:
  schedule:
    # 05:30 UTC — after the nightly publish window, like local-inference-bench.
    - cron: "30 5 * * *"
  pull_request:
    branches: [main]
    paths:
      - "packages/benchmarks/mobile-resource/**"
      - ".github/workflows/mobile-resource-workbench.yml"
  workflow_dispatch:
    inputs:
      tier:
        description: "Eliza-1 tier to profile"
        type: choice
        options: [eliza-1-2b, eliza-1-4b]
        default: eliza-1-2b
      run_android:
        description: "Run the Android device lane (self-hosted arm64)."
        type: boolean
        default: false
      run_ios_sim:
        description: "Run the iOS simulator lane."
        type: boolean
        default: false
      android_runner:
        description: "runs-on label set for the Android device lane (JSON array)."
        default: '["self-hosted","linux","arm64","android-device"]'

concurrency:
  group: mobile-resource-workbench-${{ github.ref }}
  cancel-in-progress: true

jobs:
  harness-smoke:
    name: harness smoke (no device)
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with:
          node-version: "24"
      - name: Unit tests (aggregation + budgets)
        run: node --test packages/benchmarks/mobile-resource/metrics.test.mjs
      - name: Runner off-device skip path
        run: |
          set -e
          # No device + unreachable agent → must record { skipped } and exit 2.
          set +e
          MOBILE_RESOURCE_BASE_URL=http://127.0.0.1:59999 \
            node packages/benchmarks/mobile-resource/run-workbench.mjs --platform=android
          code=$?
          set -e
          if [ "$code" != "2" ]; then
            echo "expected exit 2 (skipped) off-device, got $code"; exit 1
          fi
      - name: Report generation
        run: node packages/benchmarks/mobile-resource/report.mjs
      - name: Upload report
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: mobile-resource-report-smoke
          path: packages/benchmarks/mobile-resource/results/report/
          if-no-files-found: ignore

  android-device:
    name: android device profile
    if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.run_android == 'true' }}
    runs-on: ${{ fromJSON(github.event.inputs.android_runner) }}
    timeout-minutes: 120
    env:
      ELIZA_MOBILE_REPO_ROOT: ${{ github.workspace }}
      ELIZA_WEBVIEW_DEBUG: "1"
      MOBILE_RESOURCE_TIER: ${{ github.event.inputs.tier }}
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: recursive
      - uses: oven-sh/setup-bun@v2
      - uses: actions/setup-java@v5
        with:
          distribution: temurin
          java-version: "21"
      - uses: android-actions/setup-android@v4
      - name: Install workspace
        run: bun install
      - name: Build WebView-debuggable APK
        run: bun run --cwd packages/app build:android
      - name: Run workbench (Android device)
        run: |
          node packages/benchmarks/mobile-resource/run-workbench.mjs \
            --platform=android --tier="$MOBILE_RESOURCE_TIER" \
            --device-class=android-phone || true
      - name: Report
        if: always()
        run: node packages/benchmarks/mobile-resource/report.mjs
      - name: Upload report + results
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: mobile-resource-android-${{ github.event.inputs.tier }}
          path: packages/benchmarks/mobile-resource/results/
          if-no-files-found: ignore

  ios-sim:
    name: ios simulator profile
    if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.run_ios_sim == 'true' }}
    runs-on: [self-hosted, eliza-e2e-macos]
    timeout-minutes: 120
    env:
      MOBILE_RESOURCE_TIER: ${{ github.event.inputs.tier }}
    steps:
      - uses: actions/checkout@v4
        with:
          submodules: recursive
      - uses: oven-sh/setup-bun@v2
      - name: Install workspace
        run: bun install
      - name: Boot a simulator
        run: |
          xcrun simctl boot "iPhone 16 Pro" || true
          xcrun simctl list devices booted
      - name: Run workbench (iOS simulator)
        run: |
          node packages/benchmarks/mobile-resource/run-workbench.mjs \
            --platform=ios --tier="$MOBILE_RESOURCE_TIER" \
            --device-class=ios-phone || true
      - name: Report
        if: always()
        run: node packages/benchmarks/mobile-resource/report.mjs
      - name: Upload report + results
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: mobile-resource-ios-${{ github.event.inputs.tier }}
          path: packages/benchmarks/mobile-resource/results/
          if-no-files-found: ignore