面试题库

14 天用 Agent 搭一条 AI 短剧生产线

D2 剧本 Agent：把一句话变成人物卡、场景与分镜的结构化数据

• 多集内容要保持人物设定一致，你会把这份设定放在哪、怎么用？To keep character definitions consistent across many episodes, where do you store that state and how do you use it?

  国内高频海外高频进阶#state-management#consistency

  分析过程 · 先想清楚再作答

  1. 这题的题眼是「模型没有记忆」。答成「把前一集的输出拼进上下文」的人会被追问到崩——上下文会随集数线性膨胀，第五集时你在为前四集的全文反复付费，而且模型仍然可能漏读。
  2. 怎么拆：先分辨哪些是「跨集不变」的，哪些是「每集重算」的。不变的是世界观、人物外貌、性格、音色与几条硬规则；每集重算的是场景与分镜。把不变的那部分抽成单独的档案文件，每一集生成前原样读进去。
  3. 接着说一个容易被忽略的点：档案里的字段不只是设定，还是**下游的输入参数**。外貌描述要原样进图像提示词，音色 id 要原样进语音接口。所以它们必须和名字放在同一份档案里，一致性问题才是在一个文件里解决的，而不是散在三处各写一遍。
  4. 存放位置的判据是写入频率：档案一次生成、多次读取，分镜每跑一次就重写。生命周期不同的数据放同一个文件，你就没法只重跑一集而不动其他集。按写入频率切分文件，是这类流水线最省事的一条习惯。
  5. 结论与代价：档案本身也会漂——中途改了人物外貌，之前生成的资产就对不上了。所以档案要有版本，且资产的缓存键要包含档案版本，改档案等于让相关资产失效。这条也是把它单独存放才做得到的。
  6. 可预期的追问：那要不要上向量库做检索？多数情况下不需要。跨集共享的设定是**有限的、结构化的、必须全量注入的**，检索反而可能漏掉关键一条。检索适合的是「素材库很大且只需要相关几条」的场景。

  How to reason about it · think before answering

  1. The crux is that models have no memory. Answering just concatenate previous episodes into the context invites a fatal follow-up: context grows linearly with episode count, so by episode five you pay repeatedly for four full episodes, and the model may still miss details.
  2. Break it down by separating what is invariant across episodes from what is recomputed each time. Invariant: the world, each character's appearance, personality, voice id, and a few hard rules. Recomputed: scenes and shots. Extract the invariant part into its own file and load it verbatim before generating each episode.
  3. Add the commonly missed point: the fields in that file are not only lore, they are downstream input parameters. Appearance text goes straight into image prompts, the voice id goes straight into the speech API. Keeping them beside the name means consistency is solved in one file rather than restated in three places.
  4. Choose the storage boundary by write frequency: the profile is written once and read many times, while the shot list is rewritten on every run. Mixing lifetimes in one file makes it impossible to rerun one episode without disturbing the others.
  5. Conclusion and cost: the profile itself can drift. Change a character's appearance mid-season and previously generated assets no longer match, so version the profile and include that version in the asset cache key — editing the profile then invalidates exactly the affected assets. That is only possible because it lives on its own.
  6. Likely follow-up: should you use a vector store? Usually not. Cross-episode canon is small, structured, and must be injected in full; retrieval risks dropping the one line that matters. Retrieval fits large corpora where only a few relevant items are needed.

  答题要点

  • 模型没有记忆，跨集一致性靠外部档案而不是把前几集拼进上下文
  • 按「跨集不变」与「每集重算」切分：世界观与人物卡是档案，场景与分镜每集重来
  • 档案里的外貌与音色 id 同时是下游的输入参数，所以必须和名字放在一起
  • 按写入频率切分文件，档案读多写少，分镜每次重写，混在一起就没法只重跑一集
  • 档案要有版本并进资产缓存键，改设定才能精确地让相关资产失效

  Key points

  • Models are stateless; cross-episode consistency comes from an external profile, not from stuffing prior episodes into context
  • Split by invariant versus recomputed: world and character profiles persist, scenes and shots are regenerated per episode
  • Appearance text and voice id are downstream input parameters, so they belong beside the character's name
  • Split files by write frequency — a read-mostly profile versus a rewritten shot list — or you cannot rerun one episode alone
  • Version the profile and fold that version into the asset cache key so edits invalidate exactly the affected assets