chore(release): prepare v1.3.7

Author: Narcooo

CHANGELOG.md

@@ -1,5 +1,24 @@
 # Changelog
 
+## v1.3.7
+
+### Release Focus
+
+长篇写作质量收紧：把近期验证过的网文写法规则落到 Writer、Planner、Architect 与后置校验中，重点改善开篇抓人、章节密度、伏笔兑现、段落节奏和架构稿完整性。
+
+### Improvements
+
+- **网文写作规则入链路**：Writer prompt 新增看点密度、移动端段落、开篇第一屏、章节断章和人物行动动机等写作约束，让模型更少写空转铺垫和报告式正文
+- **Planner / Architect 对齐写作目标**：章节规划和书籍架构稿更明确地承接黄金开篇、章节目标、hook 账和段落式 foundation 输出要求
+- **Hook 兑现更具体**：hook ledger 要求 advance / resolve 项在正文里有可定位的动作、物件、对话或事件兑现，减少“账本里有、正文里没有”的断层
+- **段落密度规则收紧**：强调密度来自语义和场景推进，不是把正文切成电报体；连续短段会被后置规则识别
+
+### Bug Fixes
+
+- 修复 Architect 在扩展输出时可能漏掉 5 个 foundation SECTION 块的问题
+- 修复 hook ledger payoff 检查过于宽松，导致侧面暗示也可能被误判为兑现的问题
+- 修复写作 prompt 对段落尺寸描述不够明确，模型容易在“1-3 点密度”规则下过度碎段的问题
+
 ## v1.3.6
 
 ### Release Focus

README.en.md

@@ -25,6 +25,8 @@ Open-source AI Agent that autonomously writes, audits, and revises novels — wi
 
 **InkOS TUI is here!** — run `inkos tui` to launch a full-screen interactive dashboard. Conversational creation, natural-language book operations, slash command autocomplete, themed animations — TUI, Studio, and OpenClaw share the same interaction kernel.
 
+**v1.3.7 writing-quality update** — the long-form Writer / Planner / Architect now put more weight on first-screen hooks, chapter density, hook-ledger payoff, mobile paragraph rhythm, and complete prose foundation output, reducing empty setup, ledger/prose drift, and overly fragmented paragraphs.
+
 **Native English novel writing now supported！** — 10 built-in English genre profiles with dedicated pacing rules, fatigue word lists, and audit dimensions. Set `--lang en` and go.
 
 ## Quick Start

README.ja.md

@@ -25,6 +25,8 @@
 
 **InkOS TUI 正式リリース！** — `inkos tui` を実行してフルスクリーンのインタラクティブダッシュボードを起動。会話型創作、自然言語での書籍操作、スラッシュコマンド自動補完、テーマアニメーション——TUI、Studio、OpenClaw が同一のインタラクションカーネルを共有。
 
+**v1.3.7 執筆品質アップデート** — 長編向け Writer / Planner / Architect が、冒頭1画面の引き、章ごとの見せ場密度、hook ledger の本文内回収、モバイル向け段落リズム、段落式 foundation の完全性をより重視します。空回りする説明、台帳と本文のズレ、細切れすぎる段落を減らします。
+
 **英語ネイティブ小説執筆に対応！** — 10種類の英語ジャンルプロファイルを内蔵し、専用のペーシングルール、疲労語リスト、監査ディメンションを搭載。`--lang en` を設定するだけですぐに始められます。
 
 ## クイックスタート

README.md

@@ -25,6 +25,8 @@ AI Agent 自主写小说——写、审、改，全程接管。覆盖玄幻、
 
 **InkOS TUI 正式发布！** — 运行 `inkos tui` 进入全屏交互仪表盘。对话式创作、自然语言操作书籍、slash 命令补全、主题动效——TUI、Studio、OpenClaw 共享同一套交互内核。
 
+**v1.3.7 写作质量更新** — 长篇 Writer / Planner / Architect 现在更重视开篇第一屏、章节看点密度、hook 兑现、段落节奏和段落式架构稿完整性，减少空转铺垫、账本与正文脱节、以及过碎的电报体段落。
+
 **Native English novel writing now supported！** Set `--lang en` to write in English. See [English README](README.en.md) for details.
 
 ## 欢迎交流

package.json

@@ -1,6 +1,6 @@
 {
   "name": "inkos",
-  "version": "1.3.6",
+  "version": "1.3.7",
   "private": true,
   "description": "Autonomous AI novel writing CLI agent — 10-agent pipeline that writes, audits, and revises novels with continuity tracking",
   "keywords": [

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@actalk/inkos",
-  "version": "1.3.6",
+  "version": "1.3.7",
   "description": "Autonomous AI novel writing CLI agent — 10-agent pipeline that writes, audits, and revises novels with continuity tracking. Supports LitRPG, Progression Fantasy, Isekai, Romantasy, Sci-Fi and more.",
   "keywords": [
     "ai-novel-writing",

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@actalk/inkos-core",
-  "version": "1.3.6",
+  "version": "1.3.7",
   "description": "InkOS core engine — multi-agent novel writing pipeline with 33-dimension continuity audit, style cloning, and de-AI-ification",
   "keywords": [
     "ai-novel-writing",

packages/studio/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@actalk/inkos-studio",
-  "version": "1.3.6",
+  "version": "1.3.7",
   "description": "InkOS Studio — Web workbench for novel writing",
   "type": "module",
   "main": "dist/api/index.js",

skills/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: inkos
-description: Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, and fan fiction. Native English support with 10 built-in English genre profiles (LitRPG, Progression Fantasy, Isekai, Cultivation, System Apocalypse, Dungeon Core, Romantasy, Sci-Fi, Tower Climber, Cozy Fantasy). Also supports Chinese web novel genres (xuanhuan, xianxia, urban, horror, other). Multi-agent pipeline, two-phase writer (creative + settlement), 33-dimension auditing, token usage analytics, creative brief input, structured logging (JSON Lines), multi-model routing, custom OpenAI-compatible provider support, and InkOS Studio web UI for visual book management, chapter review, real-time writing progress, market radar, and analytics.
-version: 2.3.2
+description: Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, and fan fiction. Native English support with 10 built-in English genre profiles (LitRPG, Progression Fantasy, Isekai, Cultivation, System Apocalypse, Dungeon Core, Romantasy, Sci-Fi, Tower Climber, Cozy Fantasy). Also supports Chinese web novel genres (xuanhuan, xianxia, urban, horror, other). Multi-agent pipeline, two-phase writer (creative + settlement), stronger long-form chapter craft rules, hook-ledger payoff checks, 33-dimension auditing, token usage analytics, creative brief input, structured logging (JSON Lines), multi-model routing, custom OpenAI-compatible provider support, and InkOS Studio web UI for visual book management, chapter review, real-time writing progress, market radar, and analytics.
+version: 2.3.3
 metadata: { "openclaw": { "emoji": "📖", "requires": { "bins": ["inkos", "node"], "env": ["OPENAI_API_KEY"] }, "primaryEnv": "OPENAI_API_KEY", "homepage": "https://github.com/Narcooo/inkos", "install": [{ "id": "npm", "kind": "node", "package": "@actalk/inkos", "label": "Install InkOS (npm)" }] } }
 ---
 
@@ -10,7 +10,7 @@ metadata: { "openclaw": { "emoji": "📖", "requires": { "bins": ["inkos", "node
 InkOS is a CLI tool for autonomous fiction writing powered by LLM agents. It orchestrates a multi-agent pipeline (Radar → Planner → Composer → Architect → Writer → Observer → Reflector → Normalizer → Auditor → Reviser) to generate, audit, and revise novel content with zero human intervention per chapter.
 
 The pipeline operates in three phases:
-- **Phase 1 (Creative Writing, temp 0.7)**: Planner generates chapter intent with hook agenda, Composer selects relevant context, Writer produces prose with length governance and dialogue-driven guidance.
+- **Phase 1 (Creative Writing, temp 0.7)**: Planner generates chapter intent with hook agenda, Composer selects relevant context, Writer produces prose with length governance, first-screen hooks, semantic density, hook-ledger payoff, and mobile paragraph rhythm guidance.
 - **Phase 2 (State Settlement, temp 0.3)**: Observer over-extracts 9 categories of facts, Reflector outputs a JSON delta (not full markdown), code-layer applies Zod schema validation and immutable state update. Hook operations use upsert/mention/resolve/defer semantics.
 - **Phase 3 (Quality Loop)**: Normalizer adjusts chapter length, Auditor runs 33-dimension check including hook health analysis, Reviser auto-fixes critical issues. Self-correction loop runs until all critical issues clear.