Simple AI mentor chat logic

[milesha]

Motivation

The AI Mentor is supposed to improve the learning outcomes by guiding the student through a set of questions (current progress, faced challenges, future plans).

Description

This PR adds a simple prompt as well as persistent session thread memory to the LLM, so it can directly reference the human messages while still following the conversation steps.

• LangGraph is used for the thread memory implementation
  • LangGraph includes built-in persistence, enabling advanced memory features.
  • When we want to add actions like creating a GitHub issues as a Mentor it can be done easier.
• "The model on its own does not have any concept of state." (LangChain docs) - so we add a state class, which includes the current step in the chat with 0 being Project State, 1 Challenges and 2 Promises.
  • This approach makes it easier to monitor the current answer of the user (without analysing the actual input)
  • Currently the thread_id is a random number, which would be changed when integrating with Java Spring Boot

Additional

• GitHub lint workflow re-named to "intelligence service QA" for the consistency with webapp
• GitHub workflow for generation of intelligence api fixed (would fail because of the poetry lock update)

Checklist

General

• PR title is clear and descriptive
• PR description explains the purpose and changes
• Code follows project coding standards
• Self-review of the code has been done
• Changes have been tested locally
• Screenshots have been attached (if applicable)
• Documentation has been updated (if applicable)

Client (if applicable)

• UI changes look good on all screen sizes and browsers
• No console errors or warnings
• User experience and accessibility have been tested
• Added Storybook stories for new components
• Components follow design system guidelines (if applicable)

Server (if applicable)

• Code is performant and follows best practices
• No security vulnerabilities introduced
• Proper error handling has been implemented
• Added tests for new functionality
• Changes have been tested in different environments (if applicable)

[GODrums]

We tested this on Tuesday, looks good to me so far.

The Intelligence Service QA workflow still reports 1 style issue though :)

[FelixTJDietrich]

I will just merge this PR since you said you are working on a follow-up anyways.