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/AiSettingsUncheckedCreateWithoutUserInput.schema.ts

@@ -4,7 +4,8 @@ import type { Prisma } from '../../../generated/prisma';
 
 const makeSchema = () => z.object({
   id: z.number().int().optional(),
-  apiKey: z.string()
+  apiKey: z.string(),
+  afterHoursEnabled: z.boolean().optional()
 }).strict();
 export const AiSettingsUncheckedCreateWithoutUserInputObjectSchema: z.ZodType<Prisma.AiSettingsUncheckedCreateWithoutUserInput> = makeSchema() as unknown as z.ZodType<Prisma.AiSettingsUncheckedCreateWithoutUserInput>;
 export const AiSettingsUncheckedCreateWithoutUserInputObjectZodSchema = makeSchema();