dsh-novel-writer 4.3.1 → 5.1.0

package/README.en.md

@@ -1,6 +1,4 @@
-# 📚 dsh-novel-writer — on-device style checkup for novel writers
-
-> 🌐 **[Project site](https://siweina.github.io/dsh-novel-writer/)** · [Technical docs — implementation details, formulas and limits for all 16 tools](https://siweina.github.io/dsh-novel-writer/tools/)
+# 📚 dsh-novel-writer — an on-device writing workstation for novel writers
 
 English | [中文](./README.md)
 
@@ -12,21 +10,41 @@ English | [中文](./README.md)
 [![GitHub stars](https://img.shields.io/github/stars/siweina/dsh-novel-writer.svg?style=flat-square&color=orange)](https://github.com/siweina/dsh-novel-writer/stargazers)
 [![siweina/dsh-novel-writer MCP server](https://glama.ai/mcp/servers/siweina/dsh-novel-writer/badges/score.svg)](https://glama.ai/mcp/servers/siweina/dsh-novel-writer)
 
-**16 tools that turn "my writing drifted" into numbers you can act on.**
-Sentence, emotion and style-baseline analysis all run **on your machine**: a 24MB Chinese model ships with the package,
+**18 tools covering the whole loop: gather inputs before you write → quantify & self-check → work a prioritised fix list → audit the cross-chapter structure.**
+One call before writing gathers **16 inputs** (missing one is how style drift starts); after you write, you don't just get numbers — you get a **priority-ordered to-do list** (line-anchored original text, current vs. target values, reference passages, **direction only, never ghost-written prose**); across chapters you can finally see "the thread snapped, a character vanished, a hook was forgotten".
+Sentence, emotion and semantic analysis all run **on your machine**: a 24MB Chinese model ships with the package,
 **zero API cost, your manuscript never leaves the device**. Built for DeepSeek Harness (DSH); the same engine is also
 exposed as a **stdio MCP server** for Claude Desktop / Cursor.
 
-[Install](#install) · [60-second start](#60-second-start) · [See the output](#see-the-output) · [The 16 tools](#provided-tools-16) · [MCP server](#mcp-server-usable-outside-dsh)
+[Install](#install) · [The writing loop](#the-writing-loop-end-to-end) · [60-second start](#60-second-start) · [See the output](#see-the-output) · [The 18 tools](#provided-tools-18) · [MCP server](#mcp-server-usable-outside-dsh)
 
 ---
 
+## The writing loop (end to end)
+
+| Step | What you say | Tool | What you get |
+|---|---|---|---|
+| ① **Gather** | "gather material for the next chapter" | `novel_chapter_brief` | **One call, 16 inputs**: previous chapter's closing text (hand-off) / its hook / this chapter's outline direction / relevant character cards / open plot threads with **how long they've been open** / worldview wording rules + banned words / six-metric baseline / reference passages & sentence skeletons / previous chapter's self-check / avoid-list / writing checklist — anything missing is reported in `degraded` with the reason and the fix |
+| ② **Write** | "write chapter N" | `novel_new_chapter` · `write` | The new chapter file (with the baseline μ attached and the reference pack); the anchors are for **calibrating feel only** (never copy the skeletons), the numbers are for verifying afterwards |
+| ③ **Self-check** | "check chapter N" | `novel_style_check` · `novel_sentence_analysis` | Similarity + deviation list + six-metric comparison (in band ✓ / out of band ⚠). **Only fix when the deviation is obvious (≥2× tolerance) or the passage genuinely reads wrong** — a single dimension drifting slightly is normal variance, don't rewrite to please the numbers |
+| ④ **Revise** | "turn chapter N into a fix list" | `novel_fix_plan` | A to-do list sorted by severity → effort → line (capped at **12 items** by default): line-anchored text, current/target values, anchors, rewrite direction; **work it in batches** (merge same-paragraph items) and run `verify` at most once |
+| ⑤ **Audit** | "show me the book's structure" | `novel_plot { action: "graph" }` | Plot-thread spans / consecutive character absences / largest thread gap / timeline order / outline-vs-body drift |
+
+> **Everything local, read-only by default**: the brief and the structure view **write no files at all**; the fix desk writes only its own list file, **never touches your prose and never writes prose for you**; semantic search and emotion analysis cost zero tokens.
+
+> **Token-saving mode (new in v5.1.0)**: the sidebar's **Lean workflow** switch (or `novel_sentence_config` with `leanWorkflow=true`) keeps exactly one rule — **call tools on demand**: no automatic self-checks, no re-checking fix lists, no registry updates; report tools return the brief form unless you explicitly pass `brief` (style report: 181 chars vs 1725 for the full one).
+>
+> **v5.1.0 cost & feel fixes**: v5.0.0 had turned "always run a self-check after writing + the closing trio" and "mark every item + verify repeatedly" into mandatory checklists — one chapter went from 3 tool calls to 6, and revising took 30+. Together with "build sentences to the skeletons" and "fix any out-of-band dimension", that made prose stiff. This release makes all of it **on demand**: a chapter now takes **2 calls and up**, the fix-list cap dropped **40 → 12** with only the worst paragraph per dimension, and it now says plainly that **out-of-band ≠ defect** (keep lyrical / psychological / elliptical passages when they read fine — `mark` them `skip`).
+
 ## What problem does it solve
 
 | Your pain | What you get here |
 |---|---|
 | "This passage I just wrote doesn't sound like me" | **Six-metric style baseline**: μ±σ of the original measured per chapter across syntactic complexity / modifier density / abstraction / action density / hedging / gap index; a new chapter is compared dimension by dimension and flagged ⚠ when out of band |
 | "The AI says my style changed but can't say where" | **Style check**: similarity score + a deviation list (which sentence types increased, how far sentence length drifted, whether the dominant emotion changed) |
+| "I have to poke six or seven tools before writing, and I still miss one" | **Chapter brief**: 16 inputs in one call; whatever can't be found is explained in `degraded` — **missing an input is the number one source of style drift and setting contradictions** |
+| "I can see the chapter has problems but not which one to fix first" | **Fix plan**: to-dos sorted by severity → effort → line, each with line-anchored text, current vs. target values, a reference passage and a rewrite direction; re-checkable in three states after editing |
+| "A thread snapped, a character vanished, a hook was forgotten — and it only shows up 50 chapters later" | **Structure view**: cross-chapter plot-thread spans, consecutive character-absence intervals, largest thread gap, timeline order, and outline-vs-body overlap |
 | "Analysing a novel means paying for API calls" | Semantic search and emotion analysis run **fully local** — zero token cost |
 | "I planted a plot thread and forgot to pay it off" | **Plot registry**: add / list / scan / done, automatically recording which chapters mention each thread |
 | "Character settings contradict each other" | **Five settings tables + continuity audit** (bridge / OOC / outline drift) |
@@ -57,7 +75,14 @@ appears in the sidebar.
 mkdir -p novels/my-novel     # put chapter files inside (第01章.md, 第02章.md, …)
 ```
 
-Then just ask in chat: **"run novel_style_report on my novel"** and you get:
+Then ask, in order (this is one complete chapter):
+
+1. **"gather material for the next chapter"** → `novel_chapter_brief` returns all 16 inputs in one call (it does the work of 6–8 tools, and **cannot miss one**)
+2. **"write chapter 7"** → write by the returned anchors and skeletons; `novel_new_chapter` attaches the baseline μ
+3. **"check chapter 7"** → `novel_style_check` returns similarity, a deviation list and the six-metric comparison
+4. **"turn chapter 7 into a fix list"** → `novel_fix_plan` returns the prioritised to-dos; run `verify` afterwards to re-check the three states
+
+To just look at the baseline first, ask **"run novel_style_report on my novel"** and you get:
 
 ```text
 全书 1329 字：六维基线 μ=句法复杂度:2.3 修饰密度:35.6 抽象度:0.5 动作密度:101.7 不确定性:2.1 留白指数:7.0
@@ -68,6 +93,38 @@ Then just ask in chat: **"run novel_style_report on my novel"** and you get:
 
 ## See the output
 
+**Chapter brief** (`novel_chapter_brief`, one call before writing):
+
+```text
+目标：第 8 章《（无标题）》（尚未创建，文件名推导为 第08章.md）
+
+【上一章结尾原文·承接口】…（previous chapter's last 300 / 600 chars, per budget）
+【待回收伏笔】
+  - [mu5kjla…] 琥珀色齿轮怀表的来历与停摆的指针（high｜第 1 章埋下，已过 6 章）
+【相关人物】- 林昭：守码头的女人，父亲失踪后回到旧宅
+【世界观用语】欧式中世纪沿海城邦；点烛不烧香｜禁用：上香、烧香、时辰、老夫
+【风格基线】complexity μ=2.42  modifierDensity μ=22.2  abstractDensity μ=10.06 …
+【原著锚段·照这个味道写】[对话] …  [心理] …
+【上一章自检】第 7 章六维对照：全部维度在容差带内 ✓
+【本章禁用清单】- 禁词：上香（建议改用：点烛）
+【开写清单】□ 先读锚段再动笔　□ 承接上一章结尾　□ …（共 8 步）
+【降级/提示】- 钩子记录里没有第 7 章的钩子（上一章钩子未回填）
+```
+
+**Fix plan** (`novel_fix_plan`, diagnostics turned into an ordered to-do list):
+
+```text
+改稿台：共 13 项待办（严重度降序 → 难度升序）。抽象度过高 ×3、衔接缺失 ×1、禁用词 ×3、语用不符 ×5、句式偏离 ×1。
+备注：留白指数 虽出带但差值 8.36 < 门槛 12，已按「无量级差异」忽略 ← the absolute-magnitude gate: no false positives
+
+  - [抽象度过高] 严重度 5 / 难度 2（第 5 行）
+      id：fix-abstract-5-c2c156d4
+      现状：abstractDensity 47.9　目标：0.55~6.95
+      原句：林昭大概说不清那种感觉。她隐隐觉得…
+      方向：抽象度偏离：全章 47.9（基线 3.75，偏差 +1177.3%），本段 74.38。这句抽象词过密，改成具体动作或物件。
+      锚段：林昭把它捏在掌心，翻过来看背面。背面刻着一行小字，被磨得只剩半边。她认出了父亲的名字。
+```
+
 **Style check** (new chapter vs. book baseline):
 
 ```text
@@ -94,7 +151,7 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 | Cost | **0 (local inference)** | Billed per token | Self-hosted |
 | Purpose-built for Chinese fiction | **Yes** | Generic | No |
 | Style baseline (μ±σ) | **Yes** | Rare | No |
-| DSH integration | **16 tools + sidebar toggles** | None | None |
+| DSH integration | **18 tools + sidebar toggles** | None | None |
 | Usable without DSH | **Yes (MCP)** | Yes | You wrap it yourself |
 
 > **A note for non-Chinese users**: this plugin is designed for analysing and writing Chinese fiction — the sentence-pattern,
@@ -106,22 +163,23 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 
 ## Features
 
-1. **Style portrait report** (`novel_style_report`): 6-dimension measurement — style fingerprint / high-frequency lexicon / genre-theme / emotion quantification / 12-axis vibe spectrum / semantic style distance. **Measurement-judgment separation**: the plugin only reports numbers, never labels; AI judgment can be saved back to `.novel-writer/style-reports/` for consistent continuation writing.
-2. **12-axis vibe spectrum**: nightmare / angst / heartwarming / fluff / tearjerker / dark / mystery / blaze / absurd / lonesome / aesthetic / sensual — with traceable evidence, 0 token.
-3. **Local semantic engine**: bge-small-zh Chinese model (24MB, shipped with the plugin) local CPU inference — `novel_semantic_search` finds semantically related passages with natural language (with chapter location), semantic style comparison, semantic implicit emotion; lazy loading + graceful fallback.
-4. **Sentence-pattern analysis**: 9 categories, arrangement patterns, rhythm, emotion curve, style fingerprint + guidance, with cache & report export.
-5. **Emotion purification & quantification**: strong/weak emotion-word grading, pollution detection, caveat warning + AI re-verification; Valence sliding window → variance V / delta Δ / conflict index C + implicit imagery carriers.
-6. **Worldview & pragmatics detection**: auto cultural-baseline detection with confidence; speechStyle title/honorifics/rituals/tone norms; genre & theme + webnovel signals.
-7. **Writing toolkit**: plot tracking / five settings tables (characters·locations·items·timeline·worldview) / chapter summaries / continuity audit / batch import / style check / continuation writing.
-8. **Per-tool UI toggles**: 「写作助手功能」 ("Writing Assistant") sidebar panel (master + grouped tool toggles + feature toggles), plain-language labels, data-dir usage & semantic-engine status display.
-9. **Style Baseline**: Six writing metrics (syntactic complexity / modifier density / abstraction / action density / hedging / gap index) + per-chapter μ±σ baseline band; `novel_style_report` outputs the band, `novel_style_check` compares new chapters (in-band ✓ / out-of-band ⚠); per-metric ±% tolerance configurable in the sidebar (**recommended = 1.5× σ of the book's chapter variance**, rounded, clamped to ±10%~100%; leave blank to use recommended) — free theme, writing style kept inside the band.
-10. **Writing sentinels**: `novel_continuity_check` extended — ①**bridge check** (`chapter`: time jumps / semantic distance / character continuity / hook handoff, with quoted evidence) ②**OOC check** (`ooc`: per-character emotion baseline deviation) ③**outline drift** (`outline`: direction vs body keyword overlap); **brief mode** for report tools.
-11. **Original mode & creation files**: fill in creation settings in the sidebar (worldview/characters/forbidden/main conflict/genre/extras, blank = model decides, per-book profile library); novel_outline maintains creation files (bible/characters/outline/hooks/status), enforcing the bible → outline → hook chain with dynamic batches (10→20→30 chapters) to prevent plot jumps and OOC.
-12. **Experience & stats**: main panel **library stats** (per-book chapters/total chars/7-day active chars, 🔥 green), **🎬 demo** (built-in sample, no files, runs the 6-dim baseline), **📊 report history** (analysis/style-reports browsing); actionable error hints; slimmer tool descriptions.
+1. **The writing-desk trio**: `novel_chapter_brief` (**chapter brief**) — **one call** before you start writing gathers every input (previous-chapter hand-off / chapter direction / relevant characters / open plot threads / wording rules / style baseline / anchors & skeletons / avoid-list / checklist; two `budget` modes: compact / full); anything unavailable lands in `degraded` with the reason; read-only, writes nothing. `novel_fix_plan` (**fix plan**) — turns style diagnostics into a priority-ordered to-do list (line-anchored original text + current vs. target values + reference passages + rewrite direction) with `plan` / `verify` / `mark` and a three-state re-check, **direction only, never generates prose**. `novel_plot { action: "graph" }` (**structure view**) — plot-thread spans / consecutive character absences / thread gaps / timeline order / outline-vs-body overlap. Plus **scene-scoped prompts** (general / writing / revising / auditing / setup; `general` is the old behaviour).
+2. **Style portrait report** (`novel_style_report`): 6-dimension measurement — style fingerprint / high-frequency lexicon / genre-theme / emotion quantification / 12-axis vibe spectrum / semantic style distance. **Measurement-judgment separation**: the plugin only reports numbers, never labels; AI judgment can be saved back to `.novel-writer/style-reports/` for consistent continuation writing.
+3. **12-axis vibe spectrum**: nightmare / angst / heartwarming / fluff / tearjerker / dark / mystery / blaze / absurd / lonesome / aesthetic / sensual — with traceable evidence, 0 token.
+4. **Local semantic engine**: bge-small-zh Chinese model (24MB, shipped with the plugin) local CPU inference — `novel_semantic_search` finds semantically related passages with natural language (with chapter location), semantic style comparison, semantic implicit emotion; lazy loading + graceful fallback.
+5. **Sentence-pattern analysis**: 9 categories, arrangement patterns, rhythm, emotion curve, style fingerprint + guidance, with cache & report export.
+6. **Emotion purification & quantification**: strong/weak emotion-word grading, pollution detection, caveat warning + AI re-verification; Valence sliding window → variance V / delta Δ / conflict index C + implicit imagery carriers.
+7. **Worldview & pragmatics detection**: auto cultural-baseline detection with confidence; speechStyle title/honorifics/rituals/tone norms; genre & theme + webnovel signals.
+8. **Writing toolkit**: plot tracking / five settings tables (characters·locations·items·timeline·worldview) / chapter summaries / continuity audit / batch import / style check / continuation writing.
+9. **Per-tool UI toggles**: 「写作助手功能」 ("Writing Assistant") sidebar panel (master + grouped tool toggles + feature toggles + prompt mode/scene/**lean workflow**), plain-language labels, data-dir usage & semantic-engine status display.
+10. **Style Baseline**: Six writing metrics (syntactic complexity / modifier density / abstraction / action density / hedging / gap index) + per-chapter μ±σ baseline band; `novel_style_report` outputs the band, `novel_style_check` compares new chapters (in-band ✓ / out-of-band ⚠); per-metric ±% tolerance configurable in the sidebar (**recommended = 1.5× σ of the book's chapter variance**, rounded, clamped to ±10%~100%; leave blank to use recommended) — free theme, writing style kept inside the band.
+11. **Writing sentinels**: `novel_continuity_check` extended — ①**bridge check** (`chapter`: time jumps / semantic distance / character continuity / hook handoff, with quoted evidence) ②**OOC check** (`ooc`: per-character emotion baseline deviation) ③**outline drift** (`outline`: direction vs body keyword overlap); **brief mode** for report tools.
+12. **Original mode & creation files**: fill in creation settings in the sidebar (worldview/characters/forbidden/main conflict/genre/extras, blank = model decides, per-book profile library); novel_outline maintains creation files (bible/characters/outline/hooks/status), enforcing the bible → outline → hook chain with dynamic batches (10→20→30 chapters) to prevent plot jumps and OOC.
+13. **Experience & stats**: main panel **library stats** (per-book chapters/total chars/7-day active chars, 🔥 green), **🎬 demo** (built-in sample, no files, runs the 6-dim baseline), **📊 report history** (analysis/style-reports browsing); actionable error hints; slimmer tool descriptions.
 
 ---
 
-## Provided Tools (16)
+## Provided Tools (18)
 
 | Tool | Description |
 |------|-------------|
@@ -132,21 +190,23 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 | `novel_new_chapter` | Create new chapter file |
 | `novel_import` | Batch import manuscripts |
 | `novel_sentence_analysis` | Sentence-pattern analysis |
-| `novel_sentence_config` | View/set tool & feature toggles |
+| `novel_sentence_config` | View/set tool & feature toggles (incl. prompt scene) |
 | `novel_style_check` | Style check (rule + semantic) |
 | `novel_style_report` | **Style portrait report** (6-dim measurement) |
-| `novel_plot` | Plot/foreshadowing tracker |
+| `novel_plot` | Plot/foreshadowing tracker; `action: "graph"` structure view (plot-thread spans / consecutive character absences / thread gaps / timeline order / outline-vs-body overlap) |
 | `novel_settings` | Settings management (+worldview) |
 | `novel_summary` | Chapter summaries |
 | `novel_continuity_check` | Continuity audit + **bridge/OOC/outline sentinels** |
 | `novel_semantic_search` | Semantic search (local embedding, 0 token) |
 | `novel_outline` | **Creation-file management** (bible/characters/outline/hooks/status) |
+| `novel_chapter_brief` | **Chapter brief** — one call before writing gathers everything (previous-chapter hand-off / chapter direction / characters / open threads / wording rules / style baseline / anchors & skeletons / avoid-list / checklist) |
+| `novel_fix_plan` | **Fix plan** — turns style diagnostics into a priority-ordered to-do list (line anchors + reference passages), re-checkable after edits; **direction only, never generates prose** |
 
 ---
 
 ## MCP server (usable outside DSH)
 
-The package ships a **stdio MCP server** (`mcp/server.mjs`) that exposes all 16 tools to any MCP client,
+The package ships a **stdio MCP server** (`mcp/server.mjs`) that exposes all 18 tools to any MCP client,
 e.g. Claude Desktop or Cursor. **It runs as a local process on your own machine — no server, no network, no daemon.**
 
 ```bash
@@ -188,7 +248,7 @@ start the server with `--allow-external-src`. Details: [mcp/README.md](./mcp/REA
 
 ## Data Directory
 
-Under `<library-root>/.novel-writer/`: `plots` / `settings` / `summaries` / `analysis` / `audits` / `embedding` / `style-reports`.
+Under `<library-root>/.novel-writer/`: `plots` / `settings` / `summaries` / `analysis` / `audits` (continuity audits + fix-plan lists) / `embedding` / `style-reports`.
 
 ---
 

package/README.md

@@ -1,6 +1,4 @@
-# 📚 dsh-novel-writer — 给网文作者的本地章节体检
-
-> 🌐 **[在线主页](https://siweina.github.io/dsh-novel-writer/)** · [完整技术文档（16 个工具的实现细节、公式与约束）](https://siweina.github.io/dsh-novel-writer/tools/)
+# 📚 dsh-novel-writer — 给网文作者的本地写作工作台
 
 [English](./README.en.md) | 中文
 
@@ -12,20 +10,40 @@
 [![GitHub stars](https://img.shields.io/github/stars/siweina/dsh-novel-writer.svg?style=flat-square&color=orange)](https://github.com/siweina/dsh-novel-writer/stargazers)
 [![siweina/dsh-novel-writer MCP server](https://glama.ai/mcp/servers/siweina/dsh-novel-writer/badges/score.svg)](https://glama.ai/mcp/servers/siweina/dsh-novel-writer)
 
-**16 个工具，把"文风跑偏"变成可量化的数字。**
-句式 / 情感 / 风格基线全部**在本地算**：24MB 中文模型随包分发，**零 API 花费、正文不出本机**。
+**18 个工具，覆盖「动笔前取材料 → 写完量化自检 → 改稿按优先级复测 → 跨章结构体检」整条流程。**
+动笔前**一次调用取齐 16 项材料**（漏读一样就漂移）；改稿不再只丢给你一堆数字，而是**按严重度排好的待办**（带原句行号、当前值与目标值、原著锚段，**只给方向不代写**）；跨章层面能查「线断了、人丢了、伏笔忘了」。
+句式 / 情感 / 语义全部**在本地算**：24MB 中文模型随包分发，**零 API 花费、正文不出本机**。
 为 DeepSeek Harness（DSH）打造；同一套能力也可作为 **MCP 服务器**给 Claude Desktop / Cursor 使用。
 
-[安装](#安装) · [60 秒上手](#60-秒上手) · [看看输出](#看看输出长什么样) · [16 个工具](#提供的工具16-个) · [MCP 服务器](#mcp-服务器非-dsh-用户也能用)
+[安装](#安装) · [写作流程](#写作流程一条能走完的闭环) · [60 秒上手](#60-秒上手) · [看看输出](#看看输出长什么样) · [18 个工具](#提供的工具18-个) · [MCP 服务器](#mcp-服务器非-dsh-用户也能用)
 
 ---
 
+## 写作流程（一条能走完的闭环）
+
+| 步骤 | 你说什么 | 用哪个工具 | 拿到什么 |
+|---|---|---|---|
+| ① **取材料** | 「给下一章取材料」 | `novel_chapter_brief` | **一次调用**取齐 16 项输入：上一章结尾原文（承接口）/ 上一章钩子 / 本章大纲方向 / 相关人物卡 / 待回收伏笔（含**埋了多久**）/ 世界观用语规范与禁词 / 六维基线 / 原著锚段与句式骨架 / 上一章自检结论 / 禁用清单 / 开写清单——缺哪项、为什么、怎么补写在 `degraded` 里 |
+| ② **动笔** | 「写第 N 章」 | `novel_new_chapter` · `write` | 新章文件（自动附基线 μ 摘要与原著锚包）；锚段只用来**校准语感**（不照骨架造句），数字只做事后校验 |
+| ③ **自检** | 「自检这一章」 | `novel_style_check` · `novel_sentence_analysis` | 相似度 + 偏差清单 + 六维对照（带内 ✓ / 出带 ⚠）。**只有偏离明显（≥2 倍容差）或读起来确实别扭时才改**——单一维度轻微出带属正常波动，不要为对齐数字改文 |
+| ④ **改稿** | 「把这章排成改稿清单」 | `novel_fix_plan` | 按「严重度 → 难度 → 行号」排序的待办（默认上限 **12 条**），每条带原句行号、当前值/目标值、锚段与改写方向；**分批改**（同段同类合并），改完最多 `verify` 一次 |
+| ⑤ **跨章体检** | 「看看全书结构」 | `novel_plot { action: "graph" }` | 伏笔埋设跨度 / 人物连续缺席区间 / 剧情线最大空档 / 时间线顺序 / 大纲方向与正文的偏离 |
+
+> **全程本地、只读优先**：开写包与结构视图**不写任何文件**；改稿台只写自己的清单文件、**从不改正文，也不代写正文**；语义检索与情感分析零 token。
+
+> **省 token 模式（v5.1.0 新增）**：侧边栏「精简工作流」开关（或 `novel_sentence_config` 传 `leanWorkflow=true`）打开后只保留一条原则——**工具按需调用**：不主动跑自检、不复测清单、不登记伏笔/钩子/摘要；报告类工具未显式传 `brief` 时默认走精简输出（风格画像实测 181 字符 vs 完整 1725 字符）。
+>
+> **v5.1.0 成本与手感修复**：v5.0.0 曾把「写完必须自检 + 收尾三件」「改稿逐条 mark + 反复 verify」写成必做清单，一章从 3 次调用涨到 6 次、改稿要 30+ 次；同时"照骨架造句"与"任一维度出带必改"会让文章越改越僵。本版全部改回**按需**：写一章 **2 次调用起**，改稿清单上限 **40 → 12 条**、同一维度只报最严重的 1 段，并明确了**出带不等于缺陷**（抒情/心理/留白段读起来不别扭就保留，可用 `mark` 标 `skip`）。
+
 ## 它解决什么问题
 
 | 你的困扰 | 这里给的答案 |
 |---|---|
 | "我续写的这段，读起来不像我自己写的" | **文笔六维基线**：从句法复杂度 / 修饰密度 / 抽象度 / 动作密度 / 不确定性 / 留白指数六个维度算出原著的 μ±σ，新章逐维对照，出带标 ⚠ |
 | "AI 说文风变了，但说不清哪儿变了" | **风格自检**：相似度 + 偏差清单（哪类句式多了、句长偏了多少、主导情绪有没有换） |
+| "动笔前要翻六七个工具，还老漏读一样" | **开写包**：一次调用取齐 16 项材料；取不到的在 `degraded` 里说明缺什么、怎么补——**漏读正是文风漂移与设定矛盾的头号来源** |
+| "知道这章有问题，但不知道先改哪句" | **改稿台**：按「严重度 → 难度 → 行号」排好待办，每条给原句行号 / 当前值与目标值 / 原著锚段 / 改写方向；改完可三态复测 |
+| "线断了、人丢了、伏笔忘了——写到后面才崩" | **结构视图**：跨章算出伏笔埋设跨度、人物连续缺席区间、剧情线最大空档、时间线顺序、大纲与正文的偏离 |
 | "分析小说要花钱调 API" | 语义检索与情感分析**全本地推理**，零 token 花费 |
 | "伏笔埋了忘了收" | **伏笔登记表**：add / list / scan / done，自动记录每条伏笔在哪些章被提到 |
 | "人物设定前后打架" | **设定五张表 + 连贯性审计**（衔接 / OOC / 大纲走偏三件套） |
@@ -55,7 +73,14 @@ dsh plugin --profile web add github:siweina/dsh-novel-writer#main
 mkdir -p novels/我的小说     # 把章节文件放进去（第01章.md、第02章.md …）
 ```
 
-然后在对话里说：**"用 novel_style_report 给我的小说做一次风格画像"**，你会拿到：
+然后在对话里依次说（这就是完整的一章）：
+
+1. **「给下一章取材料」** → `novel_chapter_brief` 一次给齐 16 项输入（等于替你跑了 6~8 个工具，且**不会漏读**）
+2. **「写第 7 章」** → 照返回的锚段与骨架写；`novel_new_chapter` 建文件时还会附上基线 μ
+3. **「自检第 7 章」** → `novel_style_check` 给出相似度、偏差清单与六维对照
+4. **「把第 7 章排成改稿清单」** → `novel_fix_plan` 给出按优先级排好的待办；改完再 `verify` 复测三态
+
+只想先看看家底，就说 **「用 novel_style_report 给我的小说做一次风格画像」**：
 
 ```text
 全书 1329 字：六维基线 μ=句法复杂度:2.3 修饰密度:35.6 抽象度:0.5 动作密度:101.7 不确定性:2.1 留白指数:7.0
@@ -64,6 +89,42 @@ mkdir -p novels/我的小说     # 把章节文件放进去（第01章.md、第0
 
 ## 看看输出长什么样
 
+**开写包**（`novel_chapter_brief`，动笔前一次调用）：
+
+```text
+目标：第 8 章《（无标题）》（尚未创建，文件名推导为 第08章.md）
+
+【上一章结尾原文·承接口】…（上一章末尾 300 / 600 字，按 budget 档位）
+【待回收伏笔】
+  - [mu5kjla…] 琥珀色齿轮怀表的来历与停摆的指针（high｜第 1 章埋下，已过 6 章）
+  - [mu5kjlb…] 海图上红铅笔圈的礁区坐标（high｜第 3 章埋下，已过 4 章）
+【相关人物】- 林昭：守码头的女人，父亲失踪后回到旧宅　- 沈砚：随船出海的人
+【世界观用语】欧式中世纪沿海城邦；点烛不烧香｜禁用：上香、烧香、时辰、老夫
+【风格基线】complexity μ=2.42  modifierDensity μ=22.2  abstractDensity μ=10.06  actionDensity μ=122.45 …
+【原著锚段·照这个味道写】[对话] …  [心理] …
+【上一章自检】第 7 章六维对照：全部维度在容差带内 ✓
+【本章禁用清单】- 禁词：上香（建议改用：点烛）　- 禁词：时辰（建议改用：钟点）
+【开写清单】□ 先读锚段再动笔　□ 承接上一章结尾　□ …（共 8 步）
+【降级/提示】- 钩子记录里没有第 7 章的钩子（上一章钩子未回填）
+```
+
+**改稿台**（`novel_fix_plan`，把诊断变成排好序的待办）：
+
+```text
+改稿台：共 13 项待办（严重度降序 → 难度升序）。抽象度过高 ×3、衔接缺失 ×1、禁用词 ×3、语用不符 ×5、句式偏离 ×1。
+备注：留白指数 虽出带但差值 8.36 < 门槛 12，已按「无量级差异」忽略 ← 不误报的绝对量级闸
+
+  - [抽象度过高] 严重度 5 / 难度 2（第 5 行）
+      id：fix-abstract-5-c2c156d4
+      现状：abstractDensity 47.9　目标：0.55~6.95
+      原句：林昭大概说不清那种感觉。她隐隐觉得…
+      方向：抽象度偏离：全章 47.9（基线 3.75，偏差 +1177.3%），本段 74.38。这句抽象词过密，改成具体动作或物件。
+      锚段：林昭把它捏在掌心，翻过来看背面。背面刻着一行小字，被磨得只剩半边。她认出了父亲的名字。
+  - [语用不符] 严重度 4 / 难度 2（第 15 行）
+      现状：客套禁词「承蒙」（第 15 行）　目标：避免该类客套表达
+      方向：「承蒙」属世界观说话方式规范里明确不用的客套表达（honorBad）。这是说法层面的替换，不要顺手改剧情。
+```
+
 **风格自检**（新章 vs 全书基线）：
 
 ```text
@@ -90,7 +151,7 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 | 花费 | **0（本地推理）** | 按 token 计费 | 自建 |
 | 中文小说专用 | **是** | 通用 | 否 |
 | 风格基线（μ±σ） | **有** | 少见 | 无 |
-| 与 DSH 集成 | **16 工具 + 侧边栏开关** | 无 | 无 |
+| 与 DSH 集成 | **18 工具 + 侧边栏开关** | 无 | 无 |
 | 非 DSH 用户可用 | **可以（MCP）** | 可以 | 需自己封装 |
 
 > **致非中文用户**：本插件为中文小说分析写作而设计——句式、情感、意象等核心能力以及内置的语义模型，全部针对中文语料构建与调优。在深耕中文的同时兼顾英文等其他语言，确实超出了我目前的能力范围。若因此给您带来不便，我深感抱歉，恳请谅解。
@@ -99,22 +160,23 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 
 ## 功能
 
-1. **风格画像报告**（novel_style_report）：6 维测量报告——文风指纹 / 高频词汇 / 题材流派 / 情感量化 / 氛围光谱 12 轴 / 语义风格距离。**测量与判断分离**：插件只报数不贴标签，AI 判断可回传存盘（`.novel-writer/style-reports/`），续写保持风格一致。
-2. **氛围光谱 12 轴**：噩梦感 / 焦虑压抑 / 温馨治愈 / 甜宠日常 / 催泪虐心 / 黑暗残酷 / 悬疑神秘 / 热血激昂 / 荒诞无厘头 / 孤独疏离 / 文艺唯美 / 情欲暧昧——证据链可追溯，0 token。
-3. **本地语义引擎**：bge-small-zh 中文模型（24MB 随插件分发）本地 CPU 推理——`novel_semantic_search` 自然语言搜全书语义相关段落（带章节定位），语义级风格对比、语义隐性情感，懒加载 + 自动回退。
-4. **句式模式分析**：九类句式分布、排列规律、句长节奏、情感曲线、风格指纹与节奏建议，带缓存与报告导出。
-5. **情感净化 + 量化**：强/弱情绪词分级、污染源检测、caveat 预警 + AI 复核；Valence 滑动窗口 → 方差 V / 斜率 Δ / 矛盾指数 C + 隐性意象载体。
-6. **世界观与语用检测**：文化基准自动判断（西/东/混合）+ 置信度；speechStyle 称谓/客套/仪式/语气规范；题材流派 + 网文信号。
-7. **写作辅助全家桶**：伏笔登记表 / 设定五张表（人物·地点·道具·时间线·世界观）/ 章节摘要 / 连贯性审计 / 批量导入 / 风格自检 / 续写辅助。
-8. **全工具 UI 开关**：侧边栏「写作助手功能」面板（总开关 + 工具开关分组 + 功能开关），大白话文案，显示数据目录占用与语义引擎状态。
-9. **风格基线**：文笔六维测量（句法复杂度/修饰密度/抽象度/动作密度/不确定性/留白指数）+ 按章节 μ±σ 基线带；`novel_style_report` 输出基线带，`novel_style_check` 对照新章偏差（带内 ✓ / 出带 ⚠）；侧边栏可自定义每维 ±% 容差（**推荐值 = 原著章节波动的 1.5 倍 σ**，自动取整、限 ±10%~100%；输入框留空即用推荐）——原创/续写时主题自由、写法保持在基线带内。
-10. **写作哨兵三件套**：`novel_continuity_check` 扩展——①**衔接检查**（chapter 参数：时间硬跳/语义距离/人物延续/钩子承接四路检测，带原文引用）②**OOC 检测**（ooc 参数：角色情绪基线偏离）③**大纲走偏**（outline 参数：方向行 vs 正文关键词重合）；报告工具支持 **brief 精简模式**。
-11. **原创模式与创作资料**：侧边栏填写创作设定（世界观/角色/禁忌/主线/题材/额外要求，留空=模型自定，多书独立设定库）；novel_outline 维护创作资料（创作设定/人物/剧情大纲/钩子记录/创作状态卡），原创强制「设定书→大纲→钩子」链，动态批次（10→20→30 章）防剧情跳跃与角色 OOC。
-12. **体验与统计**：主面板**书库统计卡**（每本章数/总字数/近 7 天活跃字数，活跃🔥标绿）、**🎬 体验演示**（内置示例不落盘跑六维基线）、**📊 报告历史**（analysis/style-reports 列表浏览）；错误提示带解决步骤；工具说明压缩省 token。
+1. **写作台三件套**：`novel_chapter_brief` **开写包**——动笔前**一次调用**取齐材料（上一章承接口 / 本章方向 / 相关人物 / 待回收伏笔 / 用语规范 / 风格基线 / 锚段与骨架 / 禁用清单 / 开写清单，两档 `budget`：compact / full），取不到的材料进 `degraded` 并说明原因，只读不写盘；`novel_fix_plan` **改稿台**——把风格诊断变成按优先级排好的待办（原句行号定位 + 当前值与目标值 + 原著锚段 + 改写方向），`plan` / `verify` / `mark` 三态复测，**只给方向、不生成正文**；`novel_plot { action: "graph" }` **结构视图**——伏笔埋设跨度 / 人物连续缺席 / 剧情线空档 / 时间线顺序 / 大纲对照。另有**场景化提示词**（general / writing / revising / auditing / setup，`general` 即旧行为）。
+2. **风格画像报告**（novel_style_report）：6 维测量报告——文风指纹 / 高频词汇 / 题材流派 / 情感量化 / 氛围光谱 12 轴 / 语义风格距离。**测量与判断分离**：插件只报数不贴标签，AI 判断可回传存盘（`.novel-writer/style-reports/`），续写保持风格一致。
+3. **氛围光谱 12 轴**：噩梦感 / 焦虑压抑 / 温馨治愈 / 甜宠日常 / 催泪虐心 / 黑暗残酷 / 悬疑神秘 / 热血激昂 / 荒诞无厘头 / 孤独疏离 / 文艺唯美 / 情欲暧昧——证据链可追溯，0 token。
+4. **本地语义引擎**：bge-small-zh 中文模型（24MB 随插件分发）本地 CPU 推理——`novel_semantic_search` 自然语言搜全书语义相关段落（带章节定位），语义级风格对比、语义隐性情感，懒加载 + 自动回退。
+5. **句式模式分析**：九类句式分布、排列规律、句长节奏、情感曲线、风格指纹与节奏建议，带缓存与报告导出。
+6. **情感净化 + 量化**：强/弱情绪词分级、污染源检测、caveat 预警 + AI 复核；Valence 滑动窗口 → 方差 V / 斜率 Δ / 矛盾指数 C + 隐性意象载体。
+7. **世界观与语用检测**：文化基准自动判断（西/东/混合）+ 置信度；speechStyle 称谓/客套/仪式/语气规范；题材流派 + 网文信号。
+8. **写作辅助全家桶**：伏笔登记表 / 设定五张表（人物·地点·道具·时间线·世界观）/ 章节摘要 / 连贯性审计 / 批量导入 / 风格自检 / 续写辅助。
+9. **全工具 UI 开关**：侧边栏「写作助手功能」面板（总开关 + 工具开关分组 + 功能开关 + 提示词档位/场景/**精简工作流**），大白话文案，显示数据目录占用与语义引擎状态。
+10. **风格基线**：文笔六维测量（句法复杂度/修饰密度/抽象度/动作密度/不确定性/留白指数）+ 按章节 μ±σ 基线带；`novel_style_report` 输出基线带，`novel_style_check` 对照新章偏差（带内 ✓ / 出带 ⚠）；侧边栏可自定义每维 ±% 容差（**推荐值 = 原著章节波动的 1.5 倍 σ**，自动取整、限 ±10%~100%；输入框留空即用推荐）——原创/续写时主题自由、写法保持在基线带内。
+11. **写作哨兵三件套**：`novel_continuity_check` 扩展——①**衔接检查**（chapter 参数：时间硬跳/语义距离/人物延续/钩子承接四路检测，带原文引用）②**OOC 检测**（ooc 参数：角色情绪基线偏离）③**大纲走偏**（outline 参数：方向行 vs 正文关键词重合）；报告工具支持 **brief 精简模式**。
+12. **原创模式与创作资料**：侧边栏填写创作设定（世界观/角色/禁忌/主线/题材/额外要求，留空=模型自定，多书独立设定库）；novel_outline 维护创作资料（创作设定/人物/剧情大纲/钩子记录/创作状态卡），原创强制「设定书→大纲→钩子」链，动态批次（10→20→30 章）防剧情跳跃与角色 OOC。
+13. **体验与统计**：主面板**书库统计卡**（每本章数/总字数/近 7 天活跃字数，活跃🔥标绿）、**🎬 体验演示**（内置示例不落盘跑六维基线）、**📊 报告历史**（analysis/style-reports 列表浏览）；错误提示带解决步骤；工具说明压缩省 token。
 
 ---
 
-## 提供的工具（16 个）
+## 提供的工具（18 个）
 
 | 工具 | 说明 |
 |------|------|
@@ -125,21 +187,23 @@ fixAnchors：3 条原著锚段（对话 / 心理 / 描写各一条，供逐句
 | `novel_new_chapter` | 创建新章节文件 |
 | `novel_import` | 原稿件批量导入/分类 |
 | `novel_sentence_analysis` | 句式模式分析（九类/情感净化/量化/曲线/指纹） |
-| `novel_sentence_config` | 查看/修改工具与功能开关 |
+| `novel_sentence_config` | 查看/修改工具与功能开关（含提示词场景） |
 | `novel_style_check` | 风格自检（规则+语义双维度） |
 | `novel_style_report` | **风格画像报告**（6 维测量 + AI 判断分离） |
-| `novel_plot` | 伏笔/剧情线登记表 |
+| `novel_plot` | 伏笔/剧情线登记表；`action: "graph"` 结构视图（伏笔埋设跨度 / 人物连续缺席 / 剧情线空档 / 时间线顺序 / 大纲对照） |
 | `novel_settings` | 设定管理（人物/地点/道具/时间线/世界观） |
 | `novel_summary` | 章节摘要（长书续写辅助） |
 | `novel_continuity_check` | 连贯性审计 + **衔接/OOC/大纲走偏哨兵** |
 | `novel_semantic_search` | 语义检索（本地 embedding，0 token） |
 | `novel_outline` | **创作资料管理**（创作设定/人物/大纲/钩子/状态卡） |
+| `novel_chapter_brief` | **开写包**——动笔前一次调用取齐材料（上一章承接口/本章方向/相关人物/待回收伏笔/用语规范/风格基线/锚段与骨架/禁用清单/开写清单） |
+| `novel_fix_plan` | **改稿台**——把风格诊断变成按优先级排好的待办（带行号定位与锚段），改完可复测；**只给方向不生成正文** |
 
 ---
 
 ## MCP 服务器（非 DSH 用户也能用）
 
-包里自带一个 **stdio MCP 服务器**（`mcp/server.mjs`），把 16 个工具原样暴露给任何 MCP 客户端，
+包里自带一个 **stdio MCP 服务器**（`mcp/server.mjs`），把 18 个工具原样暴露给任何 MCP 客户端，
 例如 Claude Desktop、Cursor。**它是跑在你自己电脑上的本地进程，不需要服务器、不需要联网、不需要常驻。**
 
 ```bash
@@ -177,7 +241,7 @@ npx -y -p dsh-novel-writer dsh-novel-writer-mcp --root /你的小说库路径
 
 ## 数据目录
 
-`<书库根>/.novel-writer/`：`plots`（伏笔）/ `settings`（设定）/ `summaries`（摘要）/ `analysis`（分析报告）/ `audits`（审计）/ `embedding`（语义索引）/ `style-reports`（风格画像）。
+`<书库根>/.novel-writer/`：`plots`（伏笔）/ `settings`（设定）/ `summaries`（摘要）/ `analysis`（分析报告）/ `audits`（连贯性审计 + 改稿清单 `fix-plan-*.json`）/ `embedding`（语义索引）/ `style-reports`（风格画像）。
 
 ---
 

package/cordis.patch.yml

@@ -1,4 +1,4 @@
-# dsh-novel-writer v4.3.1 bundle patch: 16 tools (incl. novel_semantic_search) + local embedding engine.
+# dsh-novel-writer v5.0.0 bundle patch: 18 tools (incl. novel_semantic_search) + local embedding engine.
 # dsh-novel-writer bundle patch: mounts the novel-writing assistant plugin
 # into the profile's loader tree. The entry's name is the plugin package
 # itself, resolved from the profile's node_modules.