docs: revert README SEO rewrite, keep only Cli → CLI fix

README.en.md

@@ -18,9 +18,9 @@
 
 ---
 
-Open-source AI agent that autonomously writes, audits, and revises novels from the command line. A pipeline of 10 specialized AI agents handles planning, writing, fact-extraction, state management, continuity auditing (33 dimensions), and revision — with human review gates that keep you in control.
+Open-source CLI agent that autonomously writes, audits, and revises novels — with human review gates that keep you in control. Supports LitRPG, Progression Fantasy, Isekai, Romantasy, Sci-Fi, and more. Continuation, spinoff, fanfic, and style imitation workflows built in.
 
-Supports LitRPG, Progression Fantasy, Isekai, Romantasy, Sci-Fi, and 10 more genres. Continuation, spinoff, fanfic, and style imitation workflows built in. Published as an [OpenClaw](https://clawhub.ai) skill.
+**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
 
@@ -100,6 +100,23 @@ inkos config show-models        # View current routing
 
 Agents without explicit overrides fall back to the global model.
 
+### v0.6 Update
+
+**Structured State + Hook Governance + Length Governance**
+
+Addresses three systemic long-form writing problems: **context bloat after 20+ chapters causing slowdowns and 400 errors** (Settler full injection → JSON delta + selective retrieval), **hooks only accumulate, never resolve, ~0% payoff rate** (Planner scheduling + Settler blind spot fix + audit debt tracking), **word count deviation 50%+ and normalizer destroying chapters** (LengthSpec + safety net).
+
+- Pipeline upgraded to 10 agents: adds Planner, Composer, Observer, Reflector, Normalizer
+- Truth files moved to `story/state/*.json` (Zod validated); Settler outputs JSON delta instead of full markdown; legacy books auto-migrate
+- SQLite temporal memory database on Node 22+ for relevance-based retrieval
+- Planner generates `hookAgenda` to schedule hook advancement and payoff; Settler working set expanded to cover dormant debt
+- New `mention` semantics prevents fake hook advancement; `analyzeHookHealth` audits hook debt; `evaluateHookAdmission` blocks duplicate hooks
+- Length governance: `LengthSpec` + Normalizer single-pass correction with safety net against destructive normalization
+- User `INKOS_LLM_MAX_TOKENS` acts as global cap; reserved keys in `llm.extra` auto-stripped
+- Cross-chapter repetition detection, dialogue-driven guidance, English variance brief, multi-character scene resistance
+- Chapter summary dedup, ESM node:sqlite fix, consolidate full-width parenthesis support
+- Bilingual CLI output and logging
+
 ### Write Your First Book
 
 English is the default for English genre profiles. Pick a genre and go:
@@ -146,26 +163,12 @@ Every genre includes a **fatigue word list** (e.g., "delve", "tapestry", "testam
 
 ## Key Features
 
-### 10-Agent Pipeline
-
-Each chapter is produced by 10 specialized AI agents in sequence: Radar → Planner → Composer → Architect → Writer → Observer → Reflector → Normalizer → Continuity Auditor → Reviser. Each agent has one job. Failed audits trigger automatic revise → re-audit loops until all critical issues are resolved.
-
 ### 33-Dimension Audit + De-AI-ification
 
-The Continuity Auditor agent checks every draft across 33 dimensions: character memory, resource continuity, hook payoff, outline adherence, narrative pacing, emotional arcs, and more. Built-in AI-tell detection automatically catches "LLM voice" — overused words, monotonous sentence patterns, excessive summarization. Failed audits trigger an automatic revision loop.
+The Continuity Auditor checks every draft across 33 dimensions: character memory, resource continuity, hook payoff, outline adherence, narrative pacing, emotional arcs, and more. Built-in AI-tell detection automatically catches "LLM voice" — overused words, monotonous sentence patterns, excessive summarization. Failed audits trigger an automatic revision loop.
 
 De-AI-ification rules are baked into the Writer agent's prompts: fatigue word lists, banned patterns, style fingerprint injection — reducing AI traces at the source. `revise --mode anti-detect` runs dedicated anti-detection rewriting on existing chapters.
 
-### Structured State + Temporal Memory (v0.6)
-
-Truth files are stored as Zod-validated JSON (`story/state/*.json`). The Reflector agent outputs JSON deltas — not full markdown rewrites — applied immutably with structural validation. Corrupted data is rejected, not propagated.
-
-On Node 22+, a SQLite temporal memory database (`story/memory.db`) enables relevance-based retrieval of historical facts, hooks, and chapter summaries — preventing context bloat that causes slowdowns and 400 errors after 20+ chapters.
-
-### Hook Governance (v0.6)
-
-The Planner agent generates a `hookAgenda` to schedule hook advancement and payoff. `analyzeHookHealth` audits hook debt, `evaluateHookAdmission` blocks duplicate hooks, and `mention` semantics prevents fake advancement. Hooks now actually resolve instead of accumulating to 40+ open threads.
-
 ### Style Cloning
 
 `inkos style analyze` examines reference text and extracts a statistical fingerprint (sentence length distribution, word frequency patterns, rhythm profiles) plus an LLM-readable style guide. `inkos style import` injects this fingerprint into a book — all future chapters adopt the style, and the Reviser audits against it.

README.md

@@ -18,9 +18,9 @@
 
 ---
 
-开源 AI Agent，自主写小说。10 个专职 AI Agent 组成流水线，负责规划、写作、事实提取、状态管理、33 维连续性审计和修订——人工审核门控确保你始终掌控全局。覆盖玄幻、仙侠、都市、科幻等多种风格，支持续写、番外、同人、仿写等创作形式。已发布为 [OpenClaw](https://clawhub.ai) skill。
+Agent 写小说。写、审、改，全程接管。覆盖玄幻、仙侠、都市、科幻等多种风格，支持续写、番外、同人、仿写等创作形式。
 
-**English novel writing supported.** Set `--lang en` to write in English. See [English README](README.en.md) for details.
+**Native English novel writing now supported！** Set `--lang en` to write in English. See [English README](README.en.md) for details.
 
 ## 快速开始