feat(i18n): persist language preference and thread through chat, memoir, TTS

- Add users.language_preference (Alembic 0018, default zh); capture at signup/SMS
  only; expose on auth and profile APIs
- Lite English prompts for chat and memoir; localized stage labels and agent
  names (Life Echo / 岁月知己)
- Tencent TTS: language-aware synthesis, ModelType=1 for 501004, English chunking
- WebSocket pipeline: emit all AGENT_RESPONSE segments when TTS cancels; INFO logs
  for tts_this_turn and TTS decisions; on-demand TTS logging
- Expo: device language on auth, i18n tiers/agent name, [SPLIT] streaming UX fixes
- Tests for migration, prompts, pipeline, router tts_this_turn, reply segments

Co-authored-by: Cursor <cursoragent@cursor.com>

api/app/agents/chat/prompt_context.py

@@ -29,6 +29,7 @@ class ChatPromptContext:
     persona_threads: List[PersonaThread] | None = None
     recent_questions: List[str] | None = None
     turn_plan: InterviewTurnPlan | None = None
+    language: str = "zh"
 
     def guided_system_prompt(self) -> str:
         """用户原话仅以对话历史 + HumanMessage 注入模型。
@@ -60,4 +61,5 @@ class ChatPromptContext:
             persona_threads=self.persona_threads or [],
             recent_questions=self.recent_questions or [],
             turn_directive_block=directive,
+            language=self.language,
         )