feat: persist AI conversation state in DB and fix LangGraph flow bugs

- Replace in-memory Maps in aiHandoffStore with DB-backed async functions
  using new patient_conversation table (stage + aiHandoff per patient)
- Add afterHoursEnabled to ai_settings table (persists across restarts)
- Fix runtime crash in reschedule-graph: mon/tue/wed variables were out
  of scope in the next-week fallback branch (ReferenceError)
- Wire rescheduleGreeting and generalFallback chat templates through to
  LangGraph nodes so user-configured messages take effect
- Add otherNode to reminder-graph to handle unclassified patient replies
  (e.g. "I want another appointment") and route to booking flow
- Fetch chatTemplates once per webhook request instead of per stage

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

packages/db/shared/schemas/findFirstUser.schema.ts

@@ -34,6 +34,7 @@ export const UserFindFirstSelectSchema: z.ZodType<Prisma.UserSelect> = z.object(
     officeContact: z.boolean().optional(),
     procedureTimeslot: z.boolean().optional(),
     insuranceContacts: z.boolean().optional(),
+    patientConversations: z.boolean().optional(),
     _count: z.boolean().optional()
   }).strict() as unknown as z.ZodType<Prisma.UserSelect>;
 
@@ -62,6 +63,7 @@ export const UserFindFirstSelectZodSchema = z.object({
     officeContact: z.boolean().optional(),
     procedureTimeslot: z.boolean().optional(),
     insuranceContacts: z.boolean().optional(),
+    patientConversations: z.boolean().optional(),
     _count: z.boolean().optional()
   }).strict();