The command parser was returning needs_clarification for advice/how-to
questions that didn't explicitly reference a book. Updated ai_config.json
to classify any question that isn't about meds or routines as a knowledge
query, added book hints for DBT vs ADHD, and added concrete examples
(e.g. "how do I do things I don't want to do?").
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Create knowledge.py handler with dynamic book selection
- Support list/select/query actions for multiple books
- Implement vector search with cosine similarity
- Add knowledge detection to AI parser config
- Cache embeddings per-book for performance
- Added delete action to medications handler with confirmation flow
- Added delete action to routines handler with confirmation flow
- Updated AI config with delete examples for both meds and routines
- Added 'delete', 'remove', 'get rid of' to action recognition
- Enhanced AI prompts with time/frequency conversion rules and 20+ examples
- Added smart medication name resolution and confirmation flows
- New medication commands: today, refills, snooze, adherence
- New routine commands: create_with_steps, add_steps, steps, schedule
- Added active session awareness with shortcuts (done, skip, pause, resume)
- Confirmation handling for destructive/create actions
- Improved help message with natural language examples
