# 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 (and the special `broken` label) to order runner access. # Effective priority: `broken` => 10 (BOTTOM, below P9), overriding any P0–P9; # else the lowest-numbered P0–P9 label present (P0 = highest); else default P5. # # • P0 = EMERGENCY ONLY (app broken in production / emergency security update). # P0 PREEMPTS: it cancels the in-progress / queued CI runs of ALL strictly- # LOWER-priority OTHER open PRs to grab their runners immediately. A preempted # PR simply re-runs on its next push / autoupdate rebase. # # • `broken` = STUCK/FAILING PR — a MANUALLY-applied signal (maintainer / repo # owner only) meaning "deprioritise to the bottom so others aren't blocked # behind it while it's being fixed." Its effective priority is 10, so it NEVER # preempts (even if it's also labelled P0 — `broken` wins; a stuck PR can't be # an emergency merge) and ALWAYS yields: every other PR, even lower P-levels, # advances ahead of it. And because a broken PR's run is wasted (it can't # merge), ANY higher-priority PR — not just P0 — MAY cancel its in-progress run # to reclaim the runner. Removing the label restores its normal P-priority. # (Example: a P3 PR with failing CI was making lower-priority PRs wait behind # it; marking it `broken` lets them proceed — and reclaim its runner.) # # • P1–P9 = YIELD WITHOUT BUMPING. They NEVER cancel a NON-broken lower-priority # run that is already going — a higher-priority PR does not evict it, it just # takes the next free slot. Mechanism: a bounded hold-back. This job polls and # defers (up to HOLD_BACK_BUDGET_SECONDS, kept well under timeout-minutes) while # any strictly-higher-priority OTHER open PR still has an active/queued CI run, # so that PR's heavy jobs reach the runner queue ahead of this PR's. When the # budget elapses it proceeds anyway (a PR never blocks itself). # # Net preemption rule — a strictly-lower-priority OTHER PR's active run is cancelled # iff (THIS PR is P0) OR (that PR is `broken`); otherwise it is left to run and we # yield. So: P0 preempts ALL lower runs; ANY PR preempts lower `broken` runs; P1–P9 # never preempt a non-broken run. # # 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 strictly-lower, prio > self); # • P1–P9 cancel NO non-broken run — they only wait (bounded), then proceed. # # Honest limitation: GitHub Actions has no native priority queue and assigns # runners roughly FIFO, so the hold-back is a BEST-EFFORT head-start, not a hard # guarantee — under sustained contention the bounded wait can expire before a # higher-priority PR drains. The waiting job also occupies a (cheap, short-lived) # runner meanwhile, which is exactly why the wait is kept bounded. # # 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: 6 # hard backstop; the P1–P9 hold-back budget below stays well under this permissions: actions: write # cancel lower-priority runs (P0 emergencies + broken targets) pull-requests: read # read PR P0–P9 labels env: GH_TOKEN: ${{ github.token }} GH_REPO: ${{ github.repository }} SELF_PR: ${{ github.event.pull_request.number }} # P1–P9 bounded hold-back knobs. BUDGET must stay comfortably below # timeout-minutes so the poll loop always exits 0 before the hard job timeout # fires — a timed-out job would skip the heavy jobs and fail `ci-passed`. HOLD_BACK_BUDGET_SECONDS: "180" HOLD_BACK_POLL_SECONDS: "15" steps: # No checkout: this job only calls the gh CLI (auto-configured from GH_TOKEN / # GH_REPO), so it needs neither the repo contents nor the default contents:read. - name: Apply runner priority (P0/broken preempt; P1–P9 hold back) continue-on-error: true # belt-and-suspenders: never let this fail the run run: | # GitHub invokes run steps with `bash -eo pipefail`. Disable errexit so a # single failed API call can't abort the step; we guard every call and # always exit 0. Attacker-influenced values (branch names, labels) are only # ever read via env / gh JSON into shell vars — never interpolated as code. set +e if [ "${GITHUB_EVENT_NAME:-}" != "pull_request" ] || [ -z "${SELF_PR:-}" ]; then echo "Not a pull_request event (or no PR number) — nothing to do." exit 0 fi # Effective priority of a labels JSON array read on stdin: a `broken` label # => 10 (bottom, below P9), overriding any P0–P9; else the highest-priority # (lowest-numbered) P0–P9 label present; else 5. prio_of() { jq -r 'if any(.[]; .name == "broken") then 10 else ([ .[] | .name | select(test("^P[0-9]$")) | ltrimstr("P") | tonumber ] | if length == 0 then 5 else min end) end' 2>/dev/null } # Snapshot of every open PR (number, head branch, labels) to stdout. list_open_prs() { gh pr list --state open --limit 300 --json number,headRefName,labels } # Active (non-completed) CI run ids on head branch $1 — PR events only, never # main. Shared by the preemption pass (ids to cancel) and the hold-back # (presence => keep waiting). active_run_ids_for_head() { gh run list --workflow ci.yml --branch "$1" --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 } # One initial snapshot, used to read THIS PR's own priority. if ! list_open_prs > open_prs.json 2>err.txt; then echo "::warning::Could not list open PRs — skipping. $(cat err.txt 2>/dev/null)" exit 0 fi self_labels=$(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 if [ "$self_prio" -ge 10 ]; then prio_label="broken (below P9, bottom)"; else prio_label="P$self_prio"; fi echo "This PR #$SELF_PR effective priority: $prio_label (P0 = highest/emergency, P9 = lowest, 'broken' = bottom)." # ── PASS 1: PREEMPTION — cancel a strictly-lower OTHER PR's active runs ── # A strictly-lower-priority (prio > self) OTHER PR's active CI run is # cancelled iff keeping it running is wasteful, i.e. EITHER: # • THIS PR is P0 (emergency — reclaim every lower runner now), OR # • that OTHER PR is `broken` (its run can't merge, so ANY higher-priority # PR — not just P0 — may reclaim its runner). # Otherwise (we're P1–P9 and the target isn't broken) we DON'T cancel; we # only yield to genuinely-higher-priority PRs in PASS 2. # Emit "numberheadpriobroken(0|1)" for every OTHER open PR # (broken => effective prio 10, the bottom, overriding any P0–P9 label). jq -r --argjson self "$SELF_PR" ' .[] | select(.number != $self) | (any(.labels[]; .name == "broken")) as $b | [ .number, .headRefName, (if $b then 10 else ([ .labels[] | .name | select(test("^P[0-9]$")) | ltrimstr("P") | tonumber ] | if length == 0 then 5 else min end) end), (if $b then 1 else 0 end) ] | @tsv' open_prs.json 2>/dev/null > others.tsv cancelled_total=0 while IFS=$'\t' read -r num head prio isbroken; do [ -n "${num:-}" ] || continue case "$prio" in ''|*[!0-9]*) prio=5 ;; esac [ "$isbroken" = "1" ] || isbroken=0 # Never touch an equal-or-higher-priority PR — only strictly lower. if [ "$prio" -le "$self_prio" ]; then echo "· PR #$num (P$prio): equal-or-higher priority — left untouched." continue fi # Strictly lower, but only a P0 self OR a broken target is preemptible. if [ "$self_prio" -ne 0 ] && [ "$isbroken" != "1" ]; then echo "· PR #$num (P$prio): strictly lower, not broken, and we're not P0 — left to run (we don't cancel it)." continue fi if [ "$self_prio" -eq 0 ]; then reason="P0 emergency"; else reason="target is 'broken'"; fi tag="P$prio"; [ "$isbroken" = "1" ] && tag="broken" echo "· PR #$num ($tag, head '$head'): preemptible ($reason) — checking for active CI runs." run_ids=$(active_run_ids_for_head "$head") 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 $cancelled_total run(s)." # ── PASS 2: BOUNDED HOLD-BACK — yield to strictly-higher, cancel NOTHING ── # P0 is top priority: nothing outranks an emergency, so it never yields. if [ "$self_prio" -eq 0 ]; then echo "P0 emergency — not yielding; proceeding immediately." exit 0 fi # Defer this PR's heavy jobs (which `needs: traffic-control`) while any # strictly-higher-priority OTHER open PR still has an active/queued CI run, # so those heavy jobs reach the runner queue first. Cancel NOTHING here. # Bounded by budget; on expiry proceed regardless (never block ourselves, # never hit the hard job timeout). Fail-open: any API hiccup => stop waiting. case "$HOLD_BACK_BUDGET_SECONDS" in ''|*[!0-9]*) HOLD_BACK_BUDGET_SECONDS=180 ;; esac case "$HOLD_BACK_POLL_SECONDS" in ''|*[!0-9]*) HOLD_BACK_POLL_SECONDS=15 ;; esac deadline=$(( $(date +%s) + HOLD_BACK_BUDGET_SECONDS )) echo "$prio_label — holding back up to ${HOLD_BACK_BUDGET_SECONDS}s for strictly-higher-priority PRs (no cancellation)." while :; do remaining=$(( deadline - $(date +%s) )) if [ "$remaining" -le 0 ]; then echo "Hold-back budget elapsed — proceeding; higher-priority PRs got their head start." break fi # Refresh so newly opened higher-priority PRs are seen mid-wait. if ! list_open_prs > open_prs.json 2>err.txt; then echo "::warning::Could not refresh open PRs — proceeding. $(cat err.txt 2>/dev/null)" break fi # Strictly-higher-priority OTHER PRs (broken => 10, so a broken PR is never # higher than a non-broken one): "numberheadprio". jq -r --argjson self "$SELF_PR" --argjson me "$self_prio" ' .[] | select(.number != $self) | { n: .number, h: .headRefName, p: (if any(.labels[]; .name == "broken") then 10 else ([ .labels[] | .name | select(test("^P[0-9]$")) | ltrimstr("P") | tonumber ] | if length == 0 then 5 else min end) end) } | select(.p < $me) | [ .n, .h, .p ] | @tsv' open_prs.json 2>/dev/null > higher.tsv if [ ! -s higher.tsv ]; then echo "No strictly-higher-priority open PRs — proceeding." break fi blockers="" while IFS=$'\t' read -r num head prio; do [ -n "${num:-}" ] || continue if [ -n "$(active_run_ids_for_head "$head")" ]; then blockers="$blockers #$num(P$prio)" fi done < higher.tsv if [ -z "$blockers" ]; then echo "No strictly-higher-priority PR has active CI runs — proceeding." break fi sleep_s="$HOLD_BACK_POLL_SECONDS" [ "$remaining" -lt "$sleep_s" ] && sleep_s="$remaining" echo "Yielding to strictly-higher-priority PR(s) with active CI:${blockers} — re-checking in ${sleep_s}s (${remaining}s budget left)." [ "$sleep_s" -gt 0 ] && sleep "$sleep_s" done echo "Hold-back complete — this PR's heavy jobs may now start." exit 0 debug-build: name: Debug build needs: traffic-control # order after runner-priority orchestration (P0/broken preempt; P1–P9 hold-back) # 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 orchestration (P0/broken preempt; P1–P9 hold-back) 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), scoped to the JVM-testable # surface (issues #290/#292). The report is generated and uploaded first, then a no-regression # gate (issue #251) fails the job if overall LINE coverage drops below the floor pinned in # app/build.gradle.kts. Kept in this unit-test job so it is part of the `CI passed` gate. - 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 # No-regression coverage gate (issue #251): fails CI if scoped LINE coverage regresses below the # floor pinned in app/build.gradle.kts. Runs after the upload so the HTML/XML report is always # archived for triage even when this step goes red. - name: Verify JaCoCo coverage (no-regression floor) if: ${{ !cancelled() }} run: ./gradlew :app:jacocoTestCoverageVerification --stacktrace static-analysis: name: Static analysis needs: traffic-control # order after runner-priority orchestration (P0/broken preempt; P1–P9 hold-back) runs-on: ubuntu-latest steps: - name: Check out source uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 - name: Set up JDK 21 uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0 with: distribution: temurin java-version: "21" # AGP configuration needs the SDK even for ktlint/detekt (they run on the :app module). - name: Set up Android SDK uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1 - name: Install SDK platform and build-tools run: sdkmanager "$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: ${{ !cancelled() }} uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 with: name: static-analysis-reports path: | app/build/reports/ktlint/ app/build/reports/detekt/ if-no-files-found: warn e2e: name: E2E needs: traffic-control # order after runner-priority orchestration (P0/broken preempt; P1–P9 hold-back) runs-on: ubuntu-latest strategy: fail-fast: false matrix: # Every Android API level across the rolling ~7-year support window: minSdk (29 / Android 10, # 2019) through the latest stable. Each level boots its own emulator and runs the full # instrumented + Compose UI (E2E) suite; all of them fan in to the "CI passed" gate. When a # new Android ships, add it and drop the oldest level that has aged out of ~7 years. API 37 # (preview) is NOT in this matrix because emulator-runner can't provision its nonstandard # android-37.0 / google_apis_ps16k image (it would wedge the gate) — it's covered separately # by the custom-provisioned `e2e-preview` job below. Keep in sync with # testOptions.managedDevices in app/build.gradle.kts. api-level: [29, 30, 31, 32, 33, 34, 35, 36] steps: - name: Check out source uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 - name: Set up JDK 21 uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 # v5.4.0 with: distribution: temurin java-version: "21" - name: Set up Android SDK uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1 - name: Install SDK platform and build-tools run: sdkmanager "$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 orchestration (P0/broken preempt; P1–P9 hold-back) 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