Ilker ManapandClaude Opus 5 ec943f9587 Stop a one-in-sixty-two test from failing once in a while ...

TestRejections built a "wrong" key by replacing a valid one's last character
with X. Keys are base62, so one in sixty-two already ends in X and the wrong
key was the right one, which authenticated and failed the assertion.

It passed locally all day and failed in CI, which is how long a flake of that
shape takes to look like a real bug — long enough that the instinct on seeing
it is to go looking in the authenticator.

The replacement is now chosen to differ from what it replaces, with a test on
the helper itself: a mutation that can return its input turns the test it
serves into one that quietly checks nothing.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-09-16 09:42:20 +02:00

..

auth_test.go

Stop a one-in-sixty-two test from failing once in a while

2026-09-16 09:42:20 +02:00

auth.go

Close the gateway: API keys, tenancy and model allowlists

2026-09-16 08:44:33 +02:00

middleware.go

Add a landing page and a read-only cluster dashboard

2026-09-16 08:58:05 +02:00