docs: sync English README with v0.3.2 Chinese README

- Add v0.3 update section (genre customization, per-book rules, 19-dimension audit, de-AI-ification)
- Add three usage modes, .env configuration, full CLI reference
- Add production stats, key features, architecture
- Sync roadmap with AI detection review item

README.en.md

@@ -23,6 +23,94 @@
 
 Open-source multi-agent system that autonomously writes, audits, and revises novels — with human review gates that keep you in control.
 
+## v0.3 Update (2026-03-13)
+
+Three-layer rule separation: core guardrails → genre-specific rules → per-book custom rules.
+
+### Genre Customization
+
+5 built-in genres, each with a complete set of writing rules: chapter types, prohibition lists, fatigue words, language rules, and audit dimensions.
+
+| Genre | Built-in Rules |
+|-------|---------------|
+| Xuanhuan (Fantasy) | Numerical system, power scaling, same-type absorption decay formula, face-slap/upgrade/payoff pacing |
+| Xianxia (Cultivation) | Cultivation/enlightenment pacing, artifact system, heavenly dao rules |
+| Urban | Era research, business/social-driven plot, era-matched legal terminology, no numerical system |
+| Horror | Atmosphere progression, fear levels, restrained narration, no power scaling audit |
+| General | Minimal fallback |
+
+Specify a genre when creating a book and matching rules activate automatically:
+
+```bash
+inkos book create --title "Devouring Emperor" --genre xuanhuan
+```
+
+View, copy, or create genre rules:
+
+```bash
+inkos genre list                      # List all genres
+inkos genre show xuanhuan             # View full xuanhuan rules
+inkos genre copy xuanhuan             # Copy to project for customization
+inkos genre create wuxia --name Wuxia # Create a new genre from scratch
+```
+
+After copying to your project, add/remove prohibitions, adjust fatigue words, modify pacing rules, customize language rules — changes take effect on the next chapter.
+
+Each genre has dedicated language rules (with bad → good examples), enforced by both writer and auditor:
+
+- **Xuanhuan**: ✗ "Fire essence increased from 12 to 24 wisps" → ✓ "His arm felt stronger than before, knuckles tightening into a fist"
+- **Urban**: ✗ "Quickly analyzed the current debt situation" → ✓ "Flipped through the stack of wrinkled IOUs three times"
+- **Horror**: ✗ "Felt a wave of fear" → ✓ "The hairs on the back of his neck stood up one by one"
+
+### Per-Book Rules
+
+Each book has its own `book_rules.md`, auto-generated by the Architect agent when creating a book — also editable anytime. Rules here are injected into every chapter's prompt:
+
+```yaml
+protagonist:
+  name: Lin Jin
+  personalityLock: ["ruthlessly calm", "patient but lethal", "smart, not reckless"]
+  behavioralConstraints: ["no mercy, no hesitation", "warm to allies but never sentimental"]
+numericalSystemOverrides:
+  hardCap: 840000000
+  resourceTypes: ["particles", "bloodline density", "spirit stones"]
+prohibitions:
+  - protagonist goes soft at critical moments
+  - pointless harem romance dragging the plot
+  - side characters stealing the spotlight
+fatigueWordsOverride: ["pupils constricted", "disbelief"]   # Override genre defaults
+```
+
+Protagonist personality lock, numerical caps, custom prohibitions, fatigue word overrides — each book's rules are independent, without affecting the genre template.
+
+### 19-Dimension Audit
+
+Auditing is broken down into 19 dimensions, with genre-appropriate subsets auto-enabled:
+
+OOC check, timeline, setting conflicts, foreshadowing, pacing, writing style, information leaking, vocabulary fatigue, broken interest chains, side character intelligence drops, side character tool-ification, hollow payoffs, dialogue authenticity, padding detection, knowledge base contamination, POV consistency, power scaling collapse, numerical verification, era research
+
+Xuanhuan/Xianxia: all 19 dimensions. Urban: 17 dimensions (including era research). Horror: 15 dimensions.
+
+### De-AI-ification
+
+5 universal rules + genre-specific language rules to control AI marker word density and narration habits:
+
+- AI marker word frequency limit: "as if" / "suddenly" / "unexpectedly" / "couldn't help but" — max 1 per 3,000 words
+- Narrator never draws conclusions for the reader, only writes actions
+- No analytical report language ("core motivation", "information gap" never appear in prose)
+- Same imagery rendered no more than twice
+- Methodology jargon stays out of prose
+
+Vocabulary fatigue audit simultaneously checks marker word density — exceeding threshold triggers a warning.
+
+### Other
+
+- Supports OpenAI + Anthropic native + all OpenAI-compatible endpoints
+- Reviser supports polish / rewrite / rework modes
+- Genres without numerical systems skip resource ledger generation
+
+---
+
 ## Why InkOS?
 
 Writing a novel with AI isn't just "prompt and paste." Long-form fiction breaks down fast: characters forget things, items appear from nowhere, the same adjectives repeat every paragraph, and plot threads silently die. InkOS treats these as engineering problems.
@@ -35,23 +123,23 @@ Writing a novel with AI isn't just "prompt and paste." Long-form fiction breaks
 
 ## How It Works
 
-InkOS runs a multi-agent pipeline for each chapter:
+Each chapter is produced by five agents in sequence:
 
 <p align="center">
   <img src="assets/screenshot-pipeline.png" width="800" alt="Pipeline diagram">
 </p>
 
-### Agent Roles
-
 | Agent | Responsibility |
 |-------|---------------|
-| **Radar** | Scans platform trends and reader preferences to inform story direction |
+| **Radar** | Scans platform trends and reader preferences to inform story direction (pluggable, skippable) |
 | **Architect** | Plans chapter structure: outline, scene beats, pacing targets |
 | **Writer** | Produces prose from the plan + current world state |
-| **Continuity Auditor** | Validates the draft against three canonical truth files |
+| **Continuity Auditor** | Validates the draft against canonical truth files |
 | **Reviser** | Fixes issues found by the auditor — auto-fixes critical problems, flags others for human review |
 
-### Three Canonical Truth Files
+If the audit fails, the pipeline automatically enters a revise → re-audit loop until all critical issues are resolved.
+
+### Canonical Truth Files
 
 Every book maintains three files as the single source of truth:
 
@@ -67,13 +155,46 @@ The Continuity Auditor checks every draft against these files. If a character "r
   <img src="assets/screenshot-state.png" width="800" alt="Truth files snapshot">
 </p>
 
-## Quick Start
+### Writing Rule System
+
+The Writer agent has ~25 universal writing rules (character craft, narrative technique, logical consistency, language constraints, de-AI-ification), applicable to all genres.
+
+On top of that, each genre has dedicated rules (prohibitions, language rules, pacing, audit dimensions), and each book has its own `book_rules.md` (protagonist personality, numerical caps, custom prohibitions) and `story_bible.md` (worldbuilding), auto-generated by the Architect agent.
+
+See [v0.3 Update](#v03-update-2026-03-13) for details.
+
+## Three Usage Modes
+
+InkOS provides three interaction modes, all sharing the same atomic operations:
+
+### 1. Full Pipeline (One Command)
+
+```bash
+inkos write next my-book              # Draft → audit → auto-revise, all in one
+inkos write next my-book --count 5    # Write 5 chapters in sequence
+```
+
+### 2. Atomic Commands (Composable, External Agent Friendly)
+
+```bash
+inkos draft my-book --context "Focus on master-disciple conflict" --json
+inkos audit my-book 31 --json
+inkos revise my-book 31 --json
+```
 
-### Prerequisites
+Each command performs a single operation independently. `--json` outputs structured data. Can be called by OpenClaw or other AI agents via `exec`, or used in scripts.
+
+### 3. Natural Language Agent Mode
+
+```bash
+inkos agent "Write an urban cultivation novel with a programmer protagonist"
+inkos agent "Write the next chapter, focus on master-disciple conflict"
+inkos agent "Scan market trends first, then create a new book based on results"
+```
 
-- Node.js >= 20.0.0
-- pnpm >= 9.0.0
-- An OpenAI-compatible API key
+9 built-in tools (write_draft, audit_chapter, revise_chapter, scan_market, create_book, get_book_status, read_truth_files, list_books, write_full_pipeline), with the LLM deciding call order via tool-use.
+
+## Quick Start
 
 ### Install
 
@@ -84,17 +205,33 @@ npm i -g @actalk/inkos
 ### Configure
 
 ```bash
-inkos init              # Initialize project, generates .env template
-# Edit .env with your API key (any OpenAI-compatible endpoint)
+inkos init              # Initialize project, generates inkos.json + .env template
 ```
 
-### Create Your First Book
+Edit `.env`:
 
 ```bash
-inkos book create       # Create a new book (interactive)
-inkos write next        # Write next chapter (full agent pipeline)
-inkos review            # Review the latest draft
-inkos status            # Check project status
+# Required
+INKOS_LLM_PROVIDER=openai                        # openai / anthropic
+INKOS_LLM_BASE_URL=https://api.openai.com/v1     # API endpoint (proxy-friendly)
+INKOS_LLM_API_KEY=sk-xxx                          # API Key
+INKOS_LLM_MODEL=gpt-5.4                            # Model name
+
+# Optional
+# INKOS_LLM_TEMPERATURE=0.7                       # Temperature
+# INKOS_LLM_MAX_TOKENS=8192                        # Max output tokens
+# INKOS_LLM_THINKING_BUDGET=0                      # Anthropic extended thinking budget
+```
+
+### Usage
+
+```bash
+inkos book create --title "Devouring Emperor" --genre xuanhuan  # Create a book
+inkos write next my-book          # Write next chapter (full pipeline)
+inkos status                      # Check status
+inkos review list my-book         # Review drafts
+inkos export my-book              # Export full book
+inkos up                          # Daemon mode
 ```
 
 <p align="center">
@@ -105,35 +242,56 @@ inkos status            # Check project status
 
 | Command | Description |
 |---------|-------------|
-| `inkos init` | Initialize a new InkOS project |
-| `inkos book create` | Create a new book (interactive) |
-| `inkos write next` | Run the agent pipeline to produce the next chapter |
-| `inkos write rewrite <n>` | Rewrite chapter N (restores state snapshot) |
-| `inkos review` | Review and approve/reject the latest draft |
-| `inkos review approve-all <id>` | Batch approve all pending chapters |
-| `inkos status` | Show project and book status |
+| `inkos init` | Initialize a new project |
+| `inkos book create` | Create a new book (generates worldbuilding + outline + book rules) |
+| `inkos book list` | List all books |
+| `inkos genre list/show/copy/create` | View, copy, or create genres |
+| `inkos write next <id>` | Full pipeline: write next chapter |
+| `inkos write rewrite <id> <n>` | Rewrite chapter N (restores state snapshot) |
+| `inkos draft <id>` | Write draft only (no audit or revision) |
+| `inkos audit <id> [n]` | Audit a specific chapter |
+| `inkos revise <id> [n]` | Revise a specific chapter |
+| `inkos agent <instruction>` | Natural language agent mode |
+| `inkos review list/approve/reject` | Review drafts |
+| `inkos review approve-all <id>` | Batch approve |
+| `inkos status` | Project status |
 | `inkos export <id>` | Export book to txt/md |
-| `inkos radar` | Run the Radar agent to scan platform trends |
-| `inkos config` | View or update project configuration |
+| `inkos radar scan` | Scan platform trends |
+| `inkos config set/show` | View/update config |
 | `inkos doctor` | Diagnose setup issues |
-| `inkos up` | Start daemon mode |
-| `inkos down` | Stop the daemon |
+| `inkos up / down` | Start/stop daemon |
+
+All commands support `--json` for structured output. `draft`/`write next`/`book create` support `--context` for writing guidance.
 
 ## Key Features
 
-### State Snapshots
+### State Snapshots + Chapter Rewrite
 
-Every chapter automatically creates a state snapshot. Use `inkos write rewrite <n>` to roll back and regenerate any chapter — world state, resource ledger, and plot hooks all restore to the pre-chapter state.
+Every chapter automatically creates a state snapshot. Use `inkos write rewrite <id> <n>` to roll back and regenerate any chapter — world state, resource ledger, and plot hooks all restore to the pre-chapter state.
 
 ### Write Lock
 
 File-based locking prevents concurrent writes to the same book.
 
+### Pre-Write Checklist + Post-Write Settlement
+
+The Writer agent outputs a pre-write checklist before writing (context scope, current resources, pending hooks, conflict overview, risk scan), and a settlement table after writing (resource changes, hook changes). The Auditor cross-validates the settlement table against prose content.
+
+### Pluggable Radar
+
+Radar data sources are pluggable via the `RadarSource` interface. Built-in sources for Tomato Novel and Qidian. Custom data sources or skipping radar entirely are both supported.
+
 ### Daemon Mode
 
-`inkos up` starts an autonomous loop that writes chapters on a schedule. The pipeline runs fully unattended for non-critical issues, but pauses for human review when the auditor flags problems it cannot auto-fix.
+`inkos up` starts an autonomous background loop that writes chapters on a schedule. The pipeline runs fully unattended for non-critical issues, but pauses for human review when the auditor flags problems it cannot auto-fix.
+
+### Notifications
+
+Telegram, Feishu, and WeCom. In daemon mode, get notified on your phone when a chapter is done or an audit fails.
 
-Notifications via Telegram, Feishu, or WeCom.
+### External Agent Integration
+
+Atomic commands + `--json` output make InkOS callable by OpenClaw and other AI agents. OpenClaw executes `inkos draft`/`audit`/`revise` via `exec`, reads JSON results, and decides next steps.
 
 ## Architecture
 
@@ -142,37 +300,40 @@ inkos/
 ├── packages/
 │   ├── core/              # Agent runtime, pipeline, state management
 │   │   ├── agents/        # architect, writer, continuity, reviser, radar
-│   │   ├── pipeline/      # runner (write→audit→revise), scheduler (daemon)
+│   │   ├── pipeline/      # runner (atomic ops + full pipeline), agent (tool-use), scheduler
 │   │   ├── state/         # File-based state manager
-│   │   ├── llm/           # OpenAI-compatible provider (streaming)
+│   │   ├── llm/           # OpenAI + Anthropic dual SDK (streaming)
 │   │   ├── notify/        # Telegram, Feishu, WeCom
-│   │   ├── models/        # Zod schemas
-│   │   └── prompts/       # Agent prompt templates
-│   └── cli/               # Commander.js CLI
-│       └── commands/      # init, book, write, review, status, export, etc.
-├── templates/             # Project scaffolding templates
-└── (future) studio/       # Web UI for review and editing
+│   │   └── models/        # Zod schema validation
+│   └── cli/               # Commander.js CLI (15 commands)
+│       └── commands/      # init, book, write, draft, audit, revise, agent, review, status, export...
+└── (planned) studio/      # Web UI for review and editing
 ```
 
 TypeScript monorepo managed with pnpm workspaces.
 
-## Status
-
-**Early alpha.** The core pipeline works, but expect breaking changes.
-
-What works:
-- Full agent pipeline (architect -> writer -> continuity auditor -> reviser)
-- File-based state management with canonical truth files
-- CLI for project init, book creation, writing, review, export
-- State snapshots and chapter rewrite
-- Notification dispatch (Telegram, Feishu, WeCom)
-- Daemon mode with scheduler
-
-What's planned:
-- `packages/studio` — web UI for review, editing, and book management
-- Plugin system for custom agents
-- Multi-LLM routing (different models for different agents)
-- Export to platform-specific formats
+## Roadmap
+
+- [x] Full pipeline (radar → architect → writer → auditor → reviser)
+- [x] Canonical truth files + continuity audit
+- [x] Built-in writing rule system
+- [x] Full CLI (15 commands)
+- [x] State snapshots + chapter rewrite
+- [x] Daemon mode
+- [x] Notifications (Telegram / Feishu / WeCom)
+- [x] Atomic commands + JSON output (draft / audit / revise)
+- [x] Natural language agent mode (tool-use orchestration)
+- [x] Pluggable radar (RadarSource interface)
+- [x] External agent integration (OpenClaw, etc.)
+- [x] Genre customization + per-book rules (genre CLI + book_rules.md)
+- [x] 19-dimension continuity audit
+- [x] De-AI-ification rules
+- [x] Multi-LLM provider (OpenAI + Anthropic + compatible endpoints)
+- [ ] AI detection review (AIGC detection + auto-rewrite to reduce detection rate)
+- [ ] `packages/studio` Web UI for review and editing
+- [ ] Multi-model routing (different models for different agents)
+- [ ] Custom agent plugin system
+- [ ] Platform-specific export (Qidian, Tomato, etc.)
 
 ## Contributing
 
@@ -180,9 +341,9 @@ Contributions welcome. Open an issue or PR.
 
 ```bash
 pnpm install
-pnpm dev          # watch mode for all packages
-pnpm test         # run tests
-pnpm typecheck    # type-check without emitting
+pnpm dev          # Watch mode for all packages
+pnpm test         # Run tests
+pnpm typecheck    # Type-check without emitting
 ```
 
 ## License