I have an agent who I've instructed not to talk like this:
thought one
thought two
thought three
but instead like this:
thought one... thought two... thought three
Though despite troubleshooting it with my agent (asking them not to do that, including a no line break rule in the systemPrompt when on discord) it will still add line breaks, even if it swears up and down that its not.
It leads me to believe that some sort of formatting issue is happening here and I wondered if there's any mention of this in the docs or config? Is it my Kimi-code model doing this? Im pretty sure the behavior is consistant between models.. Using version 2026.2.21-2 and this behavior is consistent between direct webchat, group discord, direct dm discord, etc.