Split mobile e2e workflow by platform

[transphorm]

Summary

• split mobile E2E workflow into separate Android and iOS jobs
• explicitly set Maestro platform flags for each job

Testing

• yarn lint
• yarn build
• yarn workspace @selfxyz/contracts build (fails: Invalid account config)
• yarn types
• yarn workspace @selfxyz/common test
• yarn workspace @selfxyz/circuits test (fails: Cannot read properties of undefined 'rsa')
• yarn workspace @selfxyz/mobile-app test

---

https://chatgpt.com/codex/tasks/task_b_68913b6b8a4c832da206d559260c34ff

Summary by CodeRabbit

• Chores
  • Split mobile end-to-end testing workflow into separate Android and iOS jobs for improved clarity.
  • Each platform now runs independent setup, build, test, and artifact upload steps.
  • Maestro test results are uploaded separately for Android and iOS.

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

🗂️ Base branches to auto review (2)

• main
• dev

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Walkthrough

The mobile end-to-end workflow was restructured by splitting the combined matrix-based job into two separate jobs: one for Android and one for iOS. Platform-specific setup, build, testing, and artifact upload steps were duplicated and made explicit for each job, eliminating conditional logic and matrix configurations.

Changes

Cohort / File(s)	Change Summary
Workflow Split & Refactor .github/workflows/mobile-e2e.yml	Replaced single matrix-based E2E job with two explicit jobs: e2e-android and e2e-ios. Removed matrix and conditional steps; duplicated and tailored setup, build, test, and artifact upload steps for each platform. Maestro test commands now specify platform flags.

Sequence Diagram(s)

sequenceDiagram
    participant GitHub Actions
    participant Android Runner
    participant iOS Runner

    GitHub Actions->>Android Runner: Start e2e-android job (ubuntu-latest)
    Android Runner->>Android Runner: Setup Java, Android SDK, NDK, Emulator
    Android Runner->>Android Runner: Build and install app
    Android Runner->>Android Runner: Run Maestro tests (--platform android)
    Android Runner->>GitHub Actions: Upload maestro-results-android artifact

    GitHub Actions->>iOS Runner: Start e2e-ios job (macos-latest)
    iOS Runner->>iOS Runner: Setup CocoaPods, Boot Simulator
    iOS Runner->>iOS Runner: Build and install app
    iOS Runner->>iOS Runner: Run Maestro tests (--platform ios)
    iOS Runner->>GitHub Actions: Upload maestro-results-ios artifact

Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

Two jobs now run side by side,
Android and iOS, no need to hide.
No more matrix, no more fuss,
Each platform’s flow—clear and robust.
Artifacts split, results in tow,
E2E tests, ready to go!
🚀📱

✨ Finishing Touches

🧪 Generate unit tests

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch codex/analyze-e2e-workflows-for-ios-and-android

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai generate unit tests to generate unit tests for this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[transphorm]

@coderabbitai full review

[coderabbitai]

✅ Actions performed

Full review triggered.

[coderabbitai]

✅ Actions performed

Full review triggered.

[coderabbitai]

Actionable comments posted: 2

🔭 Outside diff range comments (1)

.github/workflows/mobile-e2e.yml (1)

38-44: Pin the Maestro install script for supply-chain safety
curl | bash against get.maestro.mobile.dev always pulls latest; a malicious/latest change could break CI. Fetch a specific commit hash or verify the SHA-256 before execution.

[security]

♻️ Duplicate comments (1)

.github/workflows/mobile-e2e.yml (1)

106-115: Mirror Yarn-level caching on the iOS job
Same rationale as the Android job—don’t download the lockfile’s 1 000+ packages twice.

🧹 Nitpick comments (4)

.github/workflows/mobile-e2e.yml (4)

31-38: Leverage built-in Yarn cache in actions/setup-node
actions/setup-node@v4 supports cache: 'yarn'. Enabling it (and optionally caching the .yarn/cache folder for Yarn v4) cuts >5 min of network time on every job.

-      - uses: actions/setup-node@v4
+      - uses: actions/setup-node@v4
         with:
           node-version: 18
+          cache: 'yarn'

---

45-56: Add Gradle & Android SDK caching to cut build time
The Android job builds a full release APK each run. Caching $HOME/.gradle/caches and the AVD image (supported by android-emulator-runner) typically saves 6-10 minutes per run.

[performance]

---

131-134: Cache CocoaPods to shave ~2 minutes per macOS run
Wrap pod install with an actions/cache keyed on Podfile.lock & Xcode version (e.g., pods-${{ hashFiles('app/ios/Podfile.lock') }}-${{ runner.os }}-${{ env.XCODE_VERSION }}).

---

140-146: Hard-coded “iPhone 15” simulator risks build breaks
macos-latest occasionally ships Xcode versions without that runtime. Safer: resolve the latest iPhone device dynamically (xcrun simctl list devices | grep -Eo 'iPhone 1[4-6] .* (available)' | head -1 | cut -d '(' -f1 | xargs).

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e84dc99 and 67fb297.

📒 Files selected for processing (1)

• .github/workflows/mobile-e2e.yml (3 hunks)

🧰 Additional context used

🧠 Learnings (2)

📓 Common learnings

Learnt from: transphorm
PR: selfxyz/self#795
File: app/android/app/build.gradle:157-158
Timestamp: 2025-07-29T01:08:28.530Z
Learning: For this React Native project, the team prefers build flexibility over fail-fast behavior for release builds in app/android/app/build.gradle. They intentionally allow fallback to debug signing for local development runs, relying on Google Play Console validation to catch any improperly signed releases during upload.

📚 Learning: for this react native project, the team prefers build flexibility over fail-fast behavior for releas...

Learnt from: transphorm
PR: selfxyz/self#795
File: app/android/app/build.gradle:157-158
Timestamp: 2025-07-29T01:08:28.530Z
Learning: For this React Native project, the team prefers build flexibility over fail-fast behavior for release builds in app/android/app/build.gradle. They intentionally allow fallback to debug signing for local development runs, relying on Google Play Console validation to catch any improperly signed releases during upload.

Applied to files:

• .github/workflows/mobile-e2e.yml

🔇 Additional comments (1)

.github/workflows/mobile-e2e.yml (1)

55-56: sdkmanager NDK install may hang on license prompt
Some runners occasionally ignore the global licence acceptance and wait for stdin. Pre-answer with yes | sdkmanager ... or run sdkmanager --install ... --licenses to guarantee non-interactive execution.