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>
45 lines
2.3 KiB
TypeScript
45 lines
2.3 KiB
TypeScript
import type { PromptSegment } from "../../types";
|
|
|
|
export const WRITER_COT: PromptSegment = {
|
|
id: "writer-cot",
|
|
name: "思维链",
|
|
type: "cot-instruction",
|
|
agent: "writer",
|
|
zone: "stable",
|
|
order: 105,
|
|
enabled: true,
|
|
editable: true,
|
|
category: "思维链",
|
|
content: `═══════════════════════════════════════════════════════════════════
|
|
创作前规划（在 <plan> 的 sceneSummary 中体现你的思考结果）
|
|
═══════════════════════════════════════════════════════════════════
|
|
在输出 <plan> 之前，请在脑中完成以下思考（不需要输出思考过程，直接体现在产出质量中）：
|
|
|
|
**Phase 1: 信息梳理**
|
|
- 分析当前情境：时间、地点、氛围、在场角色、关系与张力
|
|
- 梳理叙事线索：角色当前目标、隐藏动机、未解决冲突、时间线内关键事件
|
|
- 梳理本段所需的故事设定：世界观细节、特殊规则、已埋伏笔、待处理的叙事元素
|
|
- 区分知识层级：故事中的公共知识、特定角色掌握的私有知识、不应透露给读者的创作者情报
|
|
- **若这是故事开局**（尚无故事档案）：先在脑中搭好整部故事的脊梁（主线钩子、题材基调、第二人称主角卡、核心配角），它将写入 <plan> 的 storyBible，为后续每一幕定调
|
|
|
|
**Phase 2: 前文优化**
|
|
- 分析前文是否有情节/文风/角色刻画/段落结构/篇幅的不足
|
|
- 本轮创作中有针对性地调整和改善
|
|
|
|
**Phase 3: 挑战与对策**
|
|
- 预判潜在的逻辑不一致、角色连贯性问题、节奏困难
|
|
- 为每个挑战准备创作策略
|
|
|
|
**Phase 4: 定稿方向**
|
|
- 基于已有线索构想多个可能的叙事方向（转折 / 高潮 / 悬念 / 日常）
|
|
- 选定一条最贴合故事走向和玩家期待的路径
|
|
- 确定本段的语言风格、叙事节奏和情绪基调
|
|
|
|
**Phase 5: 对白打磨**
|
|
- 确保对白反映角色性格、背景和当前情绪
|
|
- 通过用词和说话习惯突出角色独特魅力
|
|
|
|
**Phase 6: 构建开场**
|
|
- 综合以上阶段，设计一个自然承接上文、引人入胜的开场`,
|
|
};
|