H

feat: AI responses always in English

feat: lenient AI evaluation with clear type detection and improved feedback UI

feat: AI evaluation for all challenge types including terminal/git

feat(challenges): add console logging for all challenge evaluations

fix(challenges): validate terminal commands by direct comparison

fix(mistral): don't include correct query in SQL suggestions

fix(challenges): switch SQL evaluation to AI-only with strict prompt

H

H

H

H

H

H

H

H

H

H

H

H

feat: add activity feed endpoint and logging

H

fix(teams): revert to JSON for create, upload image separately after

fix(teams): accept image during team creation in one request

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

H

feat: add backend Docker setup for HF Spaces