feat(bot): unified topic processor replacing router+interpreter stack

Replace 3-layer architecture (gpt-5-nano router + gpt-4o-mini interpreter) with
single unified topic processor (gpt-4o-mini) for simplified message handling.

New components:
- HouseholdContextCache: TTL-based caching (5 min) for household config data
- TopicProcessor: Unified classification + parsing with structured JSON output

Key changes:
- Renamed ASSISTANT_ROUTER_MODEL → TOPIC_PROCESSOR_MODEL
- Added TOPIC_PROCESSOR_TIMEOUT_MS (default 10s)
- Refactored save() → saveWithInterpretation() for pre-parsed interpretations
- Removed deprecated createOpenAiTopicMessageRouter and ~300 lines legacy code
- Fixed typing indicator to only start when needed (purchase routes)
- Fixed amount formatting: convert minor units to major for rawText

Routes: silent, chat_reply, purchase, purchase_clarification, payment,
payment_clarification, topic_helper, dismiss_workflow

All 212 bot tests pass. Typecheck, lint, format, build clean.

apps/bot/src/config.ts

@@ -17,7 +17,8 @@ export interface BotRuntimeConfig {
   openaiApiKey?: string
   purchaseParserModel: string
   assistantModel: string
-  assistantRouterModel: string
+  topicProcessorModel: string
+  topicProcessorTimeoutMs: number
   assistantTimeoutMs: number
   assistantMemoryMaxTurns: number
   assistantRateLimitBurst: number
@@ -129,7 +130,12 @@ export function getBotRuntimeConfig(env: NodeJS.ProcessEnv = process.env): BotRu
     reminderJobsEnabled,
     purchaseParserModel: env.PURCHASE_PARSER_MODEL?.trim() || 'gpt-4o-mini',
     assistantModel: env.ASSISTANT_MODEL?.trim() || 'gpt-4o-mini',
-    assistantRouterModel: env.ASSISTANT_ROUTER_MODEL?.trim() || 'gpt-5-nano',
+    topicProcessorModel: env.TOPIC_PROCESSOR_MODEL?.trim() || 'gpt-4o-mini',
+    topicProcessorTimeoutMs: parsePositiveInteger(
+      env.TOPIC_PROCESSOR_TIMEOUT_MS,
+      10_000,
+      'TOPIC_PROCESSOR_TIMEOUT_MS'
+    ),
     assistantTimeoutMs: parsePositiveInteger(
       env.ASSISTANT_TIMEOUT_MS,
       20_000,