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/objects/AiSettingsOrderByWithAggregationInput.schema.ts

@@ -11,6 +11,7 @@ const makeSchema = () => z.object({
   id: SortOrderSchema.optional(),
   userId: SortOrderSchema.optional(),
   apiKey: SortOrderSchema.optional(),
+  afterHoursEnabled: SortOrderSchema.optional(),
   _count: z.lazy(() => AiSettingsCountOrderByAggregateInputObjectSchema).optional(),
   _avg: z.lazy(() => AiSettingsAvgOrderByAggregateInputObjectSchema).optional(),
   _max: z.lazy(() => AiSettingsMaxOrderByAggregateInputObjectSchema).optional(),