server: improve user message detection and create checkpoints at every user message

[aldehir]

Overview

Scan for user message boundaries directly on the tokens and avoid doing a second pass that translates from byte offsets.

Create checkpoints at the start of every user message, as opposed to only the last message.

cc. @ggerganov @jacekpoplawski

Additional information

The checkpoint logic makes sense to me, but I haven't thoroughly tested it for edge cases.

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure: Yes - used to update the chat params for every model. Also used to review the checkpoint changes.

[aldehir]

Looks like rebasing onto master broke something...

Nevermind, looks like an unrelated regression on Windows, will investigate later.