Zonghao Yuan
0e4c2ebef4
Squash-merge the cloudflare-migration branch (7 commits by Kai ki) into staging with conflict resolution, feature integration, and bug fixes. Engine: - Paradigm D: single-stream Writer replacing dual-phase Plan/Beats - Delete Architect agent; story bible generated via Writer <plan> tag - Modular prompt architecture (segments/registry/builder) - StreamRouter for tagged stream splitting (<plan>/<story>/<choices>) Infrastructure: - Cloudflare Workers deployment (wrangler.jsonc, OpenNext adapter) - D1 database schema + Drizzle ORM (scaffolded, not yet active) - R2 storage helpers (scaffolded, not yet active) - Story persistence API routes + client-side persistence BYOK (Bring Your Own Key): - /api/llm/user-proxy with SSRF-protected LLM proxy (+ requireUser auth) - CORS-aware fetch in ai-client: auto-detect CORS failure, fallback to server proxy transparently via OpenAI SDK custom fetch - BYO config support added to classify-freeform and vision routes - SettingsModal CORS privacy notice (keys never logged/stored) SSE streaming: - engineClient.ts: fetchSSE helper for progressive scene events - startSession/requestScene accept optional emit callback - Fix SSE error event field name (error → message) in scene/start routes i18n integration: - Wire buildLanguageDirective into paradigm D's prompt builder - Update corsNotice i18n keys (zh-CN/en/ja) with CORS proxy privacy text - Preserve Session.language + LanguageSwitcher from i18n commit Co-authored-by: Kai ki <155355644+zbf1009@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
35 lines
1.9 KiB
TypeScript
35 lines
1.9 KiB
TypeScript
import type { PromptSegment } from "../../types";
|
|
|
|
export const WRITER_NARRATIVE_RULES: PromptSegment = {
|
|
id: "writer-narrative-rules",
|
|
name: "叙事创作准则",
|
|
type: "narrative-guideline",
|
|
agent: "writer",
|
|
zone: "stable",
|
|
order: 120,
|
|
enabled: true,
|
|
editable: true,
|
|
category: "叙事",
|
|
content: `═══════════════════════════════════════════════════════════════════
|
|
创作准则（剧情质量底线）
|
|
═══════════════════════════════════════════════════════════════════
|
|
# 故事结尾方式：
|
|
- 剧情结尾不得留下余韵 / 情感升华 / 回顾性收束 / 与前文雷同 / 擅自令主角脱离情景
|
|
- 剧情结尾**没有任何收尾感**，像是自然暂停在小说某一章途中的进行时，且结尾没有意外或突发状况
|
|
|
|
# 多样性：
|
|
- 不得重复前文的台词 / 桥段 / 场景
|
|
- 叙事发展意味着变化——剧情推进后不得采用重复的关键元素
|
|
|
|
# 连贯性：
|
|
- 如无指示，情景连贯持续，不应产生他者介入 / 意外打断 / 主要人物擅自离开
|
|
- 新场景从上一刻自然承接——承接情绪、地点逻辑、人物状态与未收悬念
|
|
- 若给了转场种子 nextSceneSeed，把它当命题兑现
|
|
- 沿用主线记忆里的人物关系与情绪温度
|
|
|
|
# 角色认知分级：
|
|
- **公共知识**：故事中角色普遍知晓的常识、世界观和基本情报
|
|
- **私有知识**：仅特定角色掌握的情报（私密计划 / 个人梦境 / 内心秘密），除非主动公开否则不会被他人知晓
|
|
- **创作者情报**：包括"资料"、"设定"、"用户"等元词汇以及其他元概念，不会在叙事中出现，也不应被任何角色知晓`,
|
|
};
|