Adds minimal token estimation based on text length/4 to the structured logging.
Adds token estimation based on the OpenAI rule of thumb:
A helpful rule of thumb is that one token generally corresponds to ~4 characters of text for common English text. This translates to roughly ¾ of a word (so 100 tokens ~= 75 words).
Added in for keyword selection, section selection, quote selection. Into consideration are taken instructions, context data and replies.