project-settings
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseProject Settings v2.5
项目设置 v2.5
Some decisions belong to the project rather than to a scene or a plan. POV, tense, and how much the agent may decide alone are configuration, not prose. Keeping them in a plan means they get re-litigated every session.
有些决策应归属于项目,而不是某个场景或计划。POV、时态,以及 Agent 可以独自决定的事项范围,都属于配置,而不是叙事性文本。把它们放在计划中,意味着每次会话都会重新讨论这些决定。
Record
记录
Configuration lives in . Every field the author has decided is authoritative; every field they have not is , and an unresolved setting is never guessed.
PROJECT_SETTINGS.mdUNRESOLVED配置存放在 中。作者已经作出决定的每个字段均为权威值;尚未决定的每个字段均为 ,并且绝不会猜测未解决的设置。
PROJECT_SETTINGS.mdUNRESOLVEDFields that change agent behaviour
改变 Agent 行为的字段
POV model and tense — read by and . An unset value means the narrator has not been chosen yet, which is different from third limited.
narrative-voicescene-writingApproval strictness — the most consequential field, because it governs how much proceeds unattended:
| Level | MEDIUM risk | HIGH risk |
|---|---|---|
| Ask before acting | Ask before acting |
| Proceed when clearly local and reversible | Ask before acting |
| Proceed | Ask before acting |
HIGH-risk work always requires approval at every level. Permissive relaxes only MEDIUM, and never below the guarantee that canon and structure are not changed unattended. There is no setting that waives the HIGH gate.
Autonomy ceiling — caps what may proceed even when a risk level would allow it. Useful when an author wants narrow scope for a while.
Enabled engines — restricts which engines may run. When an author wants canon frozen mid-draft, disabling and is clearer than relying on instructions not to use them.
canon-managerversion-controlPOV 模型与时态 — 由 和 读取。未设置的值表示尚未选定叙述者,这与第三人称限知视角不同。
narrative-voicescene-writing审批严格度 — 这是后果最严重的字段,因为它决定哪些操作可以在无人询问的情况下继续:
| 级别 | | |
|---|---|---|
| 执行前询问 | 执行前询问 |
| 如果操作明确属于局部操作且可逆,则继续 | 执行前询问 |
| 继续执行 | 执行前询问 |
无论处于哪个级别, 风险工作始终需要审批。 仅放宽 风险限制,并且绝不会低于确保 canon 和结构不会在无人监督的情况下被更改这一底线。不存在任何可以豁免 风险门槛的设置。
HIGHpermissiveMEDIUMHIGH自主权上限 — 即使某项操作的风险等级原本允许其继续,也会限制可以继续执行的操作范围。当作者希望在一段时间内收窄范围时,此设置很有用。
已启用的引擎 — 限制可以运行的引擎。当作者希望在草稿写到中途时冻结 canon,禁用 和 比仅依赖“不要使用它们”的指示更清晰。
canon-managerversion-controlRules
规则
- Settings never override the author. A setting is a standing instruction that the author can change at any time, and a current instruction beats a stored one.
- A setting never overrides canon. outranks any configuration.
PERMANENT_CANON - Record why a setting changed. Approval strictness is usually changed because something nearly went wrong, and the reason is the useful part.
- Do not set a field to make a validation pass. Unresolved is a valid state.
- Settings are project-scoped. Cross-project behaviour belongs in .
author-profile
- 设置永远不会凌驾于作者之上。设置是一项长期指令,作者可以随时更改;当前指令优先于已存储的设置。
- 设置永远不会覆盖 canon。的优先级高于任何配置。
PERMANENT_CANON - 记录设置发生变更的原因。审批严格度通常是因为某件事差点出错而被更改,而原因才是最有用的信息。
- 不要为了让校验通过而设置某个字段。是有效状态。
UNRESOLVED - 设置的作用范围限定在项目内。跨项目行为应归入 。
author-profile
Coordination
协调
Read by for every routing decision, by for classification, by and for POV and tense, and by when judging whether an action was in scope. Report a setting that contradicts observed practice as a finding rather than silently reconciling it.
novel-orchestratorcanon-managernarrative-voicescene-writingquality-gatenovel-orchestratorcanon-managernarrative-voicescene-writingquality-gate