- Interactive routine generation wizard with AI refinement loop (generate-draft,
refine, save-draft endpoints + RoutineWizard modal component)
- Replace +/- stepper buttons with slider controls for reps/weight during workout
- Persist user-modified reps/weight across sets of the same exercise
- Add pause/resume by tapping timer dials, with back-button confirmation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Converted frontend codebase from JavaScript to TypeScript, including pages, components, and context. Added new layout and UI kit components. Updated backend user model and schemas to support profile fields (firstname, lastname, age, gender, height, weight, unit_preference) and added endpoints for reading/updating current user. Introduced food log listing endpoint and migration script for user table. Updated dependencies and build configs for TypeScript and Tailwind v4.
Introduces DSPy-based nutrition and plan generation modules, including image analysis for nutritional info and personalized diet/exercise plans. Adds new API endpoints for health metrics/goals, nutrition image analysis, and plan management. Updates models, schemas, and backend structure to support these features, and includes initial training data and configuration for prompt optimization.
Set up backend and frontend structure for a health and fitness tracker using Python (FastAPI, SQLModel, DSPy) and React. Includes Docker and Compose configs, authentication, nutrition AI module, health/nutrition/user endpoints, database models, and basic frontend with routing and context. Enables tracking nutrition, health metrics, and user management, with architecture ready for future mobile and cloud deployment.
