- Add llm-factory.ts: unified LLM provider abstraction (Google/Claude/OpenAI)
- Install @langchain/anthropic and @langchain/openai packages
- resolveAiProvider picks active provider from DB settings (Claude > OpenAI > Google)
- All AI graphs (reminder, new-patient, reschedule, internal-chat) now accept provider+model params
- Add claudeAiModel, openAiModel, googleAiModel columns to ai_settings table
- New PUT /api/ai/provider-model route to save selected model per provider
- UI model dropdowns for Claude (Haiku/Sonnet/Opus), OpenAI (GPT-5.x series), Google (Gemini 2.5/3.x)
- Google AI section also gets model selector alongside existing API key field
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add PLAN_NOT_ACCEPTED to PatientStatus enum (prisma schema + db push)
- Selenium: return "plan not accepted" eligibility text instead of collapsing to inactive
- Backend processor: map "plan not accepted" → PLAN_NOT_ACCEPTED, fix insuranceProvider label
- _shared.ts: save DOB for existing patients when field is currently empty
- Frontend: show amber "Plan Not Accepted" badge in patient table and detail panel
- patient-form.tsx: display "Plan Not Accepted" label in status dropdown
- BullMQ: set attempts=1 (no retry on selenium failure)
- DDMA: remove first/last name from search (member ID + DOB only)
- patient-types.ts: allow alphanumeric insurance IDs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
