feat(api): 访谈人格/回复长度策略、口述归一、背景语气与输入净稿全链路

Chat 访谈
- 新增 persona 系统（default / warm_listener / curious_guide）与 background_voice 语气层
- 回复长度由 compute_reply_plan 统一决策（brief / standard / expanded），融合信息密度启发式
- 输入净稿（input_normalize）：编排层可选 rules/llm 归一用户口语后再喂模型与记忆检索
- 记忆证据注入：按用户话检索 memory evidence 并注入 prompt

Memoir 回忆录
- 口述归一（oral_normalize）：segment 原文保留，story 管线取派生净稿作叙事输入
- segment 入队批次门闸：累计字数 + 最长等待秒数，减少零碎提交
- fidelity_check / prompts / narrative_agent 微调
- Alembic 0005：清理跨章节 story 外键

Infra
- Dockerfile 加入 ffmpeg
- pyproject.toml 新增依赖并同步 uv.lock
- .env.example / .env.production 补全新配置项

Tests
- 新增 test_background_voice、test_chat_input_normalize、test_experience_regressions
- 扩展 test_interview_prompts、test_interview_reply_length、test_story_route_oral_invariant

Made-with: Cursor

api/app/agents/memoir/narrative_agent.py

@@ -67,6 +67,7 @@ class NarrativeAgent:
         user_profile: str = "",
         birth_year: Optional[int] = None,
         llm: Any = None,
+        background_voice: str = "default",
     ) -> str:
         """将新对话改写为叙述。若无 LLM 则直接拼接。
 
@@ -86,6 +87,7 @@ class NarrativeAgent:
                     existing_content=existing_content,
                     user_profile=user_profile,
                     birth_year=birth_year,
+                    background_voice=background_voice,
                 )
                 max_tokens = 8192
                 agent_name = "NarrativeAgent.generate_narrative_merge"
@@ -97,6 +99,7 @@ class NarrativeAgent:
                     existing_content=existing_content,
                     user_profile=user_profile,
                     birth_year=birth_year,
+                    background_voice=background_voice,
                 )
                 max_tokens = 4096
                 agent_name = "NarrativeAgent.generate_narrative"