Refactor the interview feature from XML-wrapped JSON to a plain-text format for LLM communication. This reduces token usage and simplifies the parsing logic.
Q1: What platform are you targeting?
- Web *
- Mobile
- Desktop
Q2: What is the timeline?
- 1 week
- 1 month *
- 3 months
parsePlainTextQuestions() function with regex patternssummary and title fields from InterviewAssistantStateformatInstructions importAll 50 tests pass:
bun test src/interview/interview.test.ts
This is a breaking change. Existing interviews using the old <interview_state> JSON format will need to be restarted with the new format.