[11:24:23] <elukey>	 accraze: I was too curious and I merged your change plus mines, everything seems to work fine and I don't see the 30s timeout anymore (no IPv6 record for the discovery endpoint)
[11:24:43] <elukey>	 \o/
[11:27:05] <wikibugs>	 10Machine-Learning-Team: revscoring model should be able to query an internal mw endpoint - https://phabricator.wikimedia.org/T289778 (10elukey) The changes that we did to the editquality image worked! I had to configure (via kubectl) the following in the InferenceService specs:  ` spec:   predictor:     contain...