- Create AISafetyService with keyword detection for emergency, medical, crisis, developmental, and stress triggers
- Add emergency response templates (911, poison control, medical disclaimer)
- Add crisis hotline integration (988, Postpartum Support, Crisis Text Line, Childhelp)
- Add medical disclaimer and developmental disclaimer templates
- Add stress support resources for overwhelmed parents
- Implement output safety checking for unsafe patterns (dosages, diagnoses)
- Add safety response injection based on trigger type
- Integrate safety checks into AI chat flow with immediate overrides for emergencies/crises
- Add base safety prompt with critical safety rules and guardrails
- Add medical and crisis safety override prompts
- Enhance system prompt with safety guardrails dynamically based on query triggers
- Export AISafetyService from AIModule for use in other modules
- All safety metrics logged for monitoring dashboard (TODO: database storage)
Safety coverage:
✅ Emergency keyword detection (not breathing, choking, seizure, etc.)
✅ Medical concern keywords (fever, vomiting, rash, medication, etc.)
✅ Crisis keywords (suicide, self-harm, PPD, abuse, etc.)
✅ Parental stress keywords (overwhelmed, burned out, isolated, etc.)
✅ Developmental concern keywords (delay, autism, ADHD, regression, etc.)
✅ Output moderation patterns (dosages, diagnoses, definitive medical statements)
✅ Crisis hotline templates with 4 major US resources
✅ Medical disclaimers with red flags and when to seek care
✅ Stress support with self-care reminders
Tested: Backend compiles and runs successfully with 0 errors
