Search
Posts
A Dead Socket Is Not a Dead Host
When two facts share one value, the signal cannot tell them apart. A socket race is not a host failure.
ReadThe Agent's Mistakes Were the Fast Ones
Six agent failures on a self-hosted team relay. Five traced back to a rule I wrote down and never made anything actually enforce.
ReadThree Copies of the Key, None of the Passphrase
Borg backup encrypted across three hosts: each copy holds the repokey, none holds the passphrase. Why redundancy hid a single point of failure.
ReadOnboarding One Person Audited the Whole Estate
Write down every grant for a new hire and the estate answers: grants that were not access, accounts we could not revoke, a fix that nearly broke a backup.
ReadThree Commits Between the Rule and the Violation
A changelog gate shipped inert: at fetch-depth 2, git tag --list is empty in CI, so the check exited 0. An AI reviewer caught what the author could not.
ReadNothing Read It, So Nothing Failed
Five defects in one day across five substrates, all the same shape: an artifact with a producer and no consumer. That is why none of them ever failed.
ReadThe Filesystem Was the Only Thing They Shared
Four models, nine threads, one disk. Two missed nights with two unrelated root causes, and a bug filed against a file another session already fixed.
ReadThe Check That Only Confirmed a Name
A default transport that only ever failed sent 2-5 fake outage emails an hour while the relay was healthy. Four checks that confirmed a name instead of a fact.
ReadWhen Live Numbers Argue Back
Live data surfaces bugs static builds never could. The jeremylongshore.com rebuild caught two in production.
ReadThe Version Number That Only Existed on the Client
When a vendor releases v0.5.3, how do you know if your self-hosted relay actually has it? The version number is not the answer.
Read