# SPDX-License-Identifier: GPL-3.0-or-later
name: CI

on:
  pull_request:
    branches: [main]

# A new push to a PR cancels any in-flight run for that PR.
concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

env:
  # SDK packages this project builds against (compileSdk 37 / build-tools 37.0.0).
  # Quote the package ids when passed to sdkmanager — the ';' is a shell separator.
  ANDROID_PLATFORM: "platforms;android-37.0"
  ANDROID_BUILD_TOOLS: "build-tools;37.0.0"

jobs:
  # ── Priority-based runner orchestration ──────────────────────────────────────
  # Runs FIRST (the heavy jobs below all `needs: traffic-control`). It reads THIS
  # PR's P0–P9 label — P0 = highest priority, P9 = lowest, default P5 when the PR
  # carries no P-label — and PREEMPTS: it cancels the in-progress / queued CI runs
  # of strictly-LOWER-priority OTHER open PRs, freeing their runners for this
  # higher-priority PR. A preempted PR simply re-runs on its next push / autoupdate
  # rebase.
  #
  # Hard safety rules, all enforced in the script below:
  #   • never cancels a run on main / a push event (filters --event pull_request);
  #   • never cancels THIS PR's own run (skips self by PR number + run id);
  #   • never cancels an equal-or-higher-priority PR (only prio > self);
  #   • only strictly-lower-priority OTHER open PRs' active runs are cancelled.
  #
  # It is deliberately NOT a merge-gate check: it is absent from `ci-passed`'s
  # needs, every API call is guarded, the script always exits 0, and the step is
  # `continue-on-error` — so a hiccup (API error, missing permission, fork PR)
  # can never fail or block CI. The heavy jobs only *order* after it via `needs`;
  # if it were ever skipped/failed they'd be skipped, which `ci-passed` now treats
  # as a gate failure (fail-safe: blocks merge, never spuriously passes).
  traffic-control:
    name: Traffic control (runner priority)
    runs-on: ubuntu-latest
    timeout-minutes: 5
    permissions:
      actions: write # cancel workflow runs on lower-priority PRs
      pull-requests: read # read PR P0–P9 labels
    env:
      GH_TOKEN: ${{ github.token }}
      GH_REPO: ${{ github.repository }}
      SELF_PR: ${{ github.event.pull_request.number }}
    steps:
      # No checkout: this job only calls the gh CLI (auto-configured from GH_TOKEN /
      # GH_REPO), so it needs neither the repo contents nor the default contents:read.
      - name: Preempt lower-priority PR runs
        continue-on-error: true # belt-and-suspenders: never let this fail the run
        run: |
          # GitHub invokes run steps with `bash -eo pipefail`. Disable errexit so a
          # single failed API call can't abort the step; we guard every call and
          # always exit 0. Attacker-influenced values (branch names, labels) are only
          # ever read via env / gh JSON into shell vars — never interpolated as code.
          set +e

          if [ "${GITHUB_EVENT_NAME:-}" != "pull_request" ] || [ -z "${SELF_PR:-}" ]; then
            echo "Not a pull_request event (or no PR number) — nothing to preempt."
            exit 0
          fi

          # Effective priority (0–9) of a labels JSON array read on stdin: the
          # highest-priority (lowest-numbered) P0–P9 label present, else 5.
          prio_of() {
            jq -r '[ .[] | .name | select(test("^P[0-9]$")) | ltrimstr("P") | tonumber ]
                   | if length == 0 then 5 else min end' 2>/dev/null
          }

          # One snapshot of every open PR (number, head branch, labels).
          if ! gh pr list --state open --limit 300 \
                 --json number,headRefName,labels > open_prs.json 2>err.txt; then
            echo "::warning::Could not list open PRs — skipping preemption. $(cat err.txt 2>/dev/null)"
            exit 0
          fi

          self_labels=$(jq -c --argjson pr "$SELF_PR" \
            '([ .[] | select(.number == $pr) | .labels ] | .[0]) // []' open_prs.json 2>/dev/null)
          self_prio=$(printf '%s' "${self_labels:-[]}" | prio_of)
          case "$self_prio" in ''|*[!0-9]*) self_prio=5 ;; esac
          echo "This PR #$SELF_PR has effective priority P$self_prio (P0 = highest, P9 = lowest)."

          if [ "$self_prio" -ge 9 ]; then
            echo "P$self_prio is the lowest tier — no strictly-lower-priority PRs to preempt."
            exit 0
          fi

          # "number<TAB>head<TAB>prio" for every OTHER open PR.
          jq -r --argjson self "$SELF_PR" '
            .[] | select(.number != $self)
            | [ .number, .headRefName,
                ([ .labels[] | .name | select(test("^P[0-9]$")) | ltrimstr("P") | tonumber ]
                  | if length == 0 then 5 else min end) ]
            | @tsv' open_prs.json 2>/dev/null > others.tsv

          cancelled_total=0
          while IFS=$'\t' read -r num head prio; do
            [ -n "${num:-}" ] || continue
            case "$prio" in ''|*[!0-9]*) prio=5 ;; esac

            if [ "$prio" -le "$self_prio" ]; then
              echo "· PR #$num (P$prio): equal-or-higher priority — left untouched."
              continue
            fi

            echo "· PR #$num (P$prio, head '$head'): strictly lower priority — checking for active CI runs."
            # Active (non-completed) CI runs on that PR's head branch, PR events only.
            run_ids=$(gh run list --workflow ci.yml --branch "$head" --event pull_request \
                        --limit 100 --json databaseId,status,headBranch,event 2>/dev/null \
                      | jq -r '.[]
                          | select(.event == "pull_request")
                          | select(.headBranch != "main")
                          | select(.status != "completed")
                          | .databaseId' 2>/dev/null)

            if [ -z "$run_ids" ]; then
              echo "    no active CI runs."
              continue
            fi

            while IFS= read -r run_id; do
              [ -n "$run_id" ] || continue
              [ "$run_id" = "${GITHUB_RUN_ID:-}" ] && continue # never cancel our own run
              if gh run cancel "$run_id" 2>err.txt; then
                echo "    cancelled run $run_id (freed its runner)."
                cancelled_total=$((cancelled_total + 1))
              else
                echo "::warning::could not cancel run $run_id — likely already finished. $(cat err.txt 2>/dev/null)"
              fi
            done <<< "$run_ids"
          done < others.tsv

          echo "Preemption pass complete — cancelled $cancelled_total lower-priority run(s)."
          exit 0

  debug-build:
    name: Debug build
    needs: traffic-control # order after runner-priority preemption
    # x86_64: Linux-arm64 runners can't set up this SDK — android-actions/setup-android's sdkmanager
    # fails (exit 1) on the android-37.0 preview platform, and the emulator package has no arm64-Linux
    # build. Build/unit-test results are host-arch-independent anyway (R8/AGP/JVM); real arm64
    # device-ABI coverage would need arm64 emulators, which require macOS hosts.
    runs-on: ubuntu-latest
    steps:
      - name: Check out source
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

      - name: Set up JDK 21
        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0
        with:
          distribution: temurin
          java-version: "21"

      - name: Set up Android SDK
        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1

      - name: Install SDK platform and build-tools
        run: sdkmanager "$ANDROID_PLATFORM" "$ANDROID_BUILD_TOOLS"

      - name: Set up Gradle
        uses: gradle/actions/setup-gradle@3f131e8634966bd73d06cc69884922b02e6faf92 # v6.2.0

      - name: Assemble debug APK
        run: ./gradlew assembleDebug --stacktrace

      - name: Upload debug APK
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: debug-apk
          path: app/build/outputs/apk/debug/*.apk
          if-no-files-found: error

  unit-tests:
    name: Unit tests
    needs: traffic-control # order after runner-priority preemption
    runs-on: ubuntu-latest
    steps:
      - name: Check out source
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

      - name: Set up JDK 21
        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0
        with:
          distribution: temurin
          java-version: "21"

      - name: Set up Android SDK
        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1

      - name: Install SDK platform and build-tools
        run: sdkmanager "$ANDROID_PLATFORM" "$ANDROID_BUILD_TOOLS"

      - name: Set up Gradle
        uses: gradle/actions/setup-gradle@3f131e8634966bd73d06cc69884922b02e6faf92 # v6.2.0

      - name: Run unit tests
        run: ./gradlew testDebugUnitTest --stacktrace

      - name: Upload unit test report
        if: ${{ !cancelled() }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: unit-test-report
          path: app/build/reports/tests/testDebugUnitTest/
          if-no-files-found: warn

      # JaCoCo XML + HTML coverage for the JVM unit tests (issue #192). Reporting only — no
      # threshold gate yet, so a coverage regression does not fail CI (a jacocoTestCoverageVerification
      # gate is a natural follow-up once there's a baseline to enforce).
      - name: Generate JaCoCo coverage report
        if: ${{ !cancelled() }}
        run: ./gradlew :app:jacocoTestReport --stacktrace

      - name: Upload coverage report
        if: ${{ !cancelled() }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: jacoco-coverage-report
          path: app/build/reports/jacoco/jacocoTestReport/
          if-no-files-found: warn

  static-analysis:
    name: Static analysis
    needs: traffic-control # order after runner-priority preemption
    runs-on: ubuntu-latest
    steps:
      - name: Check out source
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

      - name: Set up JDK 21
        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0
        with:
          distribution: temurin
          java-version: "21"

      # AGP configuration needs the SDK even for ktlint/detekt (they run on the :app module).
      - name: Set up Android SDK
        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1

      - name: Install SDK platform and build-tools
        run: sdkmanager "$ANDROID_PLATFORM" "$ANDROID_BUILD_TOOLS"

      - name: Set up Gradle
        uses: gradle/actions/setup-gradle@3f131e8634966bd73d06cc69884922b02e6faf92 # v6.2.0

      # --continue so a ktlint failure still lets detekt report (and vice versa).
      - name: Run ktlint and detekt
        run: ./gradlew :app:ktlintCheck :app:detekt --continue --stacktrace

      - name: Upload analysis reports
        if: ${{ !cancelled() }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: static-analysis-reports
          path: |
            app/build/reports/ktlint/
            app/build/reports/detekt/
          if-no-files-found: warn

  e2e:
    name: E2E
    needs: traffic-control # order after runner-priority preemption
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        # Every Android API level across the rolling ~7-year support window: minSdk (29 / Android 10,
        # 2019) through the latest stable. Each level boots its own emulator and runs the full
        # instrumented + Compose UI (E2E) suite; all of them fan in to the "CI passed" gate. When a
        # new Android ships, add it and drop the oldest level that has aged out of ~7 years. API 37
        # (preview) is NOT in this matrix because emulator-runner can't provision its nonstandard
        # android-37.0 / google_apis_ps16k image (it would wedge the gate) — it's covered separately
        # by the custom-provisioned `e2e-preview` job below. Keep in sync with
        # testOptions.managedDevices in app/build.gradle.kts.
        api-level: [29, 30, 31, 32, 33, 34, 35, 36]
    steps:
      - name: Check out source
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

      - name: Set up JDK 21
        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0
        with:
          distribution: temurin
          java-version: "21"

      - name: Set up Android SDK
        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1

      - name: Install SDK platform and build-tools
        run: sdkmanager "$ANDROID_PLATFORM" "$ANDROID_BUILD_TOOLS"

      - name: Set up Gradle
        uses: gradle/actions/setup-gradle@3f131e8634966bd73d06cc69884922b02e6faf92 # v6.2.0

      # The hardware-accelerated emulator needs KVM, which is gated behind a udev rule.
      - name: Enable KVM
        run: |
          echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' | sudo tee /etc/udev/rules.d/99-kvm4all.rules
          sudo udevadm control --reload-rules
          sudo udevadm trigger --name-match=kvm

      - name: Cache AVD snapshot
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        id: avd-cache
        with:
          path: |
            ~/.android/avd/*
            ~/.android/adb*
          key: avd-${{ matrix.api-level }}-google_apis-x86_64

      # On a cache miss, cold-boot the emulator once so its snapshot can be cached,
      # making subsequent runs start from a warm snapshot.
      - name: Create AVD and generate snapshot for caching
        if: steps.avd-cache.outputs.cache-hit != 'true'
        uses: reactivecircus/android-emulator-runner@e89f39f1abbbd05b1113a29cf4db69e7540cae5a # v2.37.0
        with:
          api-level: ${{ matrix.api-level }}
          target: google_apis
          arch: x86_64
          force-avd-creation: false
          emulator-options: -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none
          disable-animations: false
          script: echo "Generated AVD snapshot for caching."

      # reactivecircus/android-emulator-runner runs an un-guarded, fatal `adb shell input keyevent 82`
      # after boot. On snapshot resume that can race system_server (sys.boot_completed=1 before the
      # `input` binder service is republished), aborting the job before Gradle runs with
      # "No service published for: input" — an ~2%, API-29-only infra flake, not a test failure. Make
      # the step non-fatal and retry once: two independent boots drop the race to ~0.04%. The definitive
      # fix (adopt the e2e-preview job's manual-boot + `keyevent 82 || true`) is tracked separately.
      - name: Run E2E tests
        id: e2e
        continue-on-error: true
        uses: reactivecircus/android-emulator-runner@e89f39f1abbbd05b1113a29cf4db69e7540cae5a # v2.37.0
        with:
          api-level: ${{ matrix.api-level }}
          target: google_apis
          arch: x86_64
          force-avd-creation: false
          emulator-options: -no-snapshot-save -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none
          disable-animations: true
          script: ./gradlew connectedDebugAndroidTest --stacktrace

      - name: Run E2E tests (retry after emulator boot race)
        if: steps.e2e.outcome == 'failure'
        uses: reactivecircus/android-emulator-runner@e89f39f1abbbd05b1113a29cf4db69e7540cae5a # v2.37.0
        with:
          api-level: ${{ matrix.api-level }}
          target: google_apis
          arch: x86_64
          force-avd-creation: false
          emulator-options: -no-snapshot-save -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none
          disable-animations: true
          script: ./gradlew connectedDebugAndroidTest --stacktrace

      - name: Upload E2E test report
        if: ${{ !cancelled() }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: e2e-test-report-api${{ matrix.api-level }}
          path: app/build/reports/androidTests/connected/
          if-no-files-found: warn

  # API 37 (Android 17, preview) E2E. Its only system image is the nonstandard
  # android-37.0 / google_apis_ps16k (16 KB page size), which reactivecircus/android-emulator-runner
  # can't provision (it builds android-37 / google_apis, neither of which exists), so this job
  # CUSTOM-PROVISIONS the emulator with sdkmanager/avdmanager/emulator directly. It is REQUIRED:
  # part of the "CI passed" gate's needs (the preview emulator has proven stable in practice), so a
  # genuine failure blocks merges. When a stable, emulator-runner-friendly API 37 image ships, fold
  # 37 into the main `e2e` matrix and delete this job.
  e2e-preview:
    name: E2E (API 37 preview)
    needs: traffic-control # order after runner-priority preemption
    runs-on: ubuntu-latest
    timeout-minutes: 35
    env:
      API37_IMAGE: "system-images;android-37.0;google_apis_ps16k;x86_64"
    steps:
      - name: Check out source
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0

      - name: Set up JDK 21
        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0
        with:
          distribution: temurin
          java-version: "21"

      - name: Set up Android SDK
        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1

      - name: Set up Gradle
        uses: gradle/actions/setup-gradle@3f131e8634966bd73d06cc69884922b02e6faf92 # v6.2.0

      # The hardware-accelerated emulator needs KVM, which is gated behind a udev rule.
      - name: Enable KVM
        run: |
          echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' | sudo tee /etc/udev/rules.d/99-kvm4all.rules
          sudo udevadm control --reload-rules
          sudo udevadm trigger --name-match=kvm

      # Cache the ~1 GB preview system image so only the first run pays the download.
      - name: Cache API 37 system image
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
        with:
          # GitHub-hosted ubuntu runners install the SDK at /usr/local/lib/android/sdk; caching the
          # image dir (with its package metadata) lets sdkmanager treat it as installed and skip the
          # re-download on a cache hit.
          path: /usr/local/lib/android/sdk/system-images/android-37.0
          key: sysimg-android-37.0-google_apis_ps16k-x86_64

      - name: Install SDK packages + preview system image
        run: sdkmanager "$ANDROID_PLATFORM" "$ANDROID_BUILD_TOOLS" "platform-tools" "emulator" "$API37_IMAGE"

      - name: Create API 37 AVD
        run: |
          # avdmanager and the emulator disagree on the default AVD dir when ANDROID_SDK_HOME is set
          # on the runner (avdmanager writes $ANDROID_SDK_HOME/.android/avd; the emulator looks in
          # $ANDROID_SDK_HOME/avd), which made the boot step report "Unknown AVD name [api37]". Pin
          # ANDROID_AVD_HOME so both agree, and carry it to the boot step via $GITHUB_ENV.
          export ANDROID_AVD_HOME="$HOME/.android/avd"
          echo "ANDROID_AVD_HOME=$ANDROID_AVD_HOME" >> "$GITHUB_ENV"
          mkdir -p "$ANDROID_AVD_HOME"
          echo "no" | avdmanager create avd -n api37 -k "$API37_IMAGE" -d pixel_2 --force
          echo "AVDs visible to the emulator:"; "$ANDROID_SDK_ROOT/emulator/emulator" -list-avds

      - name: Boot emulator and run E2E
        run: |
          set -euo pipefail
          EMU_LOG="${RUNNER_TEMP:-/tmp}/emulator.log"

          boot_emulator() {
            echo "::group::Start API 37 emulator (attempt $1)"
            # Capture the emulator's own output — without this a boot failure is invisible.
            "$ANDROID_SDK_ROOT/emulator/emulator" -avd api37 \
              -no-window -no-audio -no-boot-anim -no-snapshot -accel on \
              -gpu swiftshader_indirect -camera-back none -camera-front none > "$EMU_LOG" 2>&1 &
            # ONE bounded wait covering both device registration and full boot, so a stuck emulator
            # fails fast instead of hanging the whole job until the 35-min cap (the original bug).
            if timeout 300 adb wait-for-device shell \
                'while [ "$(getprop sys.boot_completed | tr -d "\r")" != "1" ]; do sleep 2; done'; then
              echo "::endgroup::"; return 0
            fi
            echo "::endgroup::"
            echo "::warning::API 37 emulator did not boot within 300s (attempt $1)"
            adb devices || true
            echo "--- emulator.log (tail) ---"; tail -120 "$EMU_LOG" || true
            adb emu kill 2>/dev/null || true
            sleep 5
            return 1
          }

          booted=0
          for attempt in 1 2; do boot_emulator "$attempt" && { booted=1; break; }; done
          [ "$booted" = "1" ] || { echo "::error::API 37 preview emulator failed to boot after 2 attempts"; exit 1; }

          adb shell input keyevent 82 || true
          ./gradlew connectedDebugAndroidTest --stacktrace

      - name: Dump emulator log on failure
        if: failure()
        run: |
          echo "--- emulator.log ---"; tail -200 "${RUNNER_TEMP:-/tmp}/emulator.log" 2>/dev/null || echo "(none)"
          echo "--- logcat ---"; adb logcat -d 2>/dev/null | tail -120 || echo "(device unavailable)"

      - name: Shut down emulator
        if: always()
        run: adb emu kill || true

      - name: Upload E2E (API 37) report
        if: ${{ !cancelled() }}
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: e2e-test-report-api37-preview
          path: app/build/reports/androidTests/connected/
          if-no-files-found: warn

  # Single aggregating gate so branch protection can require ALL CI jobs with one stable status
  # check. It depends on every job — including each api-level of the E2E matrix — so adding/removing
  # a matrix level needs no change to branch protection (the per-"(api-level)" check names would
  # otherwise have to be re-listed each time).
  ci-passed:
    name: CI passed
    if: always()
    # `traffic-control` is intentionally NOT listed here — it is a best-effort
    # optimizer, not a merge requirement. But because the heavy jobs `needs:` it,
    # a (should-never-happen) traffic-control failure would mark them 'skipped';
    # treating 'skipped' as a gate failure below keeps that fail-safe (blocks the
    # merge rather than letting it through untested).
    needs: [static-analysis, debug-build, unit-tests, e2e, e2e-preview]
    runs-on: ubuntu-latest
    steps:
      - name: Verify every required job succeeded
        if: ${{ contains(needs.*.result, 'failure') || contains(needs.*.result, 'cancelled') || contains(needs.*.result, 'skipped') }}
        run: |
          echo "Required CI jobs did not all succeed:"
          echo "  static-analysis: ${{ needs.static-analysis.result }}"
          echo "  debug-build: ${{ needs.debug-build.result }}"
          echo "  unit-tests:  ${{ needs.unit-tests.result }}"
          echo "  e2e:         ${{ needs.e2e.result }}"
          echo "  e2e-preview: ${{ needs.e2e-preview.result }}"
          exit 1