New RunLLM response generated: >>>*# Question* I'm trying to configure auth on my flyte-binary helm build. I can authenticate with the UI, flytectl, and pyflyte. But all of the workflow executions show a status of "UNKNOWN" and I'm seeing these repeated errors in the pod logs. "7 workers.go:103] error syncing 'model-development/a8spkcsnvc8dt799rkjb Workflow[] failed. ErrorRecordingError: failed to publish event, caused by: authentication error! Original Error: <nil>, Auth Error: failed to issue token. Error: failed to get token: oauth2: "invalid_client" "Client authentication failed (e.g., unknown client, no client authentication included, or unsupported authentication method)." I'm not sure how to resolve this. My helm auth values seem good to me. If I were to have corrected this, would these errors automatically resolve or would they continue to error if initiated with faulty config prior? # Answer The error "invalid_client" suggests a client authentication issue, possibly due to incorrect client ID or secret configuration. Ensure that the client ID and secret are correctly set in your Flyte configuration, particularly in the

auth

section of your Helm values file. According to Flyte GitHub Issue #3659, if

auth.externalAuthServer

is true, ensure

auth.internal.clientId

is defined correctly. If you correct the configuration, new executions should resolve the error, but existing ones initiated with faulty config may continue to fail. Would you like more detail on how to verify and update your configuration? Sources: - Flyte GitHub Issue #3659 Slack Link https://.slack.com/archives/CP2HDHKE1/p1730228743.978469 👍 0 button 👎 0 button 💡 Hint: Mention @runllm in the thread for followups.