Fix JSON response parsing in ux_testing_fsm function to directly access the response object.

added ux_testing api

Enhance answer generation by adding optional context parameter to relevant functions and update .gitignore to include test directory.

using litellm - for now shuffle disabled

forced focus on questions in prompts

temperature to 0.5 for answers

now using 4.1mini with temperature 1

fixed models and temp for prod

restored function for parameters generation - just for completeness

added possibility to ask questions in bulk - now default

modified prompts for ask question and build personas - fixed temperature to 0 and model to 4.1 nano for testing

modified persona generation logic: now fixed set of parameters

prompts in a separated file

explicit parameters in call_llm function

fixed n of parameters

fix on split

increased to 20 params per user

added language in prompt for chat with persona

fix prompt report

all questions and users go in parallel when asking questions

fixed call_llm and models in apis

cleaned code - improved response format - splitted generate users adding new api for parameters

handling llm errors generate-users

added previous_users in generate_users

removed print in core

added guardrail prompt report chat

added audience_name in the output of main api

added limits on users and questions

added chat_with_report and fixed generate_content

added api chat-with-persona

added new api re-generate

updated prompts

divided code in files and working api