docs: fix README stale references (DuckDuckGo, command counts, tool counts)

- Remove DuckDuckGo mention from English README (replaced by native search)
- Update CLI command count 18→20 (added import, analytics)
- Update agent tool count 9→12 (added web_fetch, import_style, import_canon)

README.en.md

@@ -82,7 +82,7 @@ Real testing showed `rewrite` mode introduces 6x more AI markers than the origin
 ### Other v0.4 Changes
 
 - Audit dimensions expanded from 26 to 32 (+4 spinoff dims + sensitive word check + reader expectation management)
-- Auditor web search: era-research genres can call DuckDuckGo to verify real events/people/geography
+- Auditor web search: era-research genres can verify real events/people/geography online (native search)
 - Scheduler rewrite: AI-paced (15min cycles), parallel book processing, immediate retry, daily cap
 - New `spot-fix` revise mode (targeted repair)
 - `additionalAuditDimensions` in `book_rules.md` now supports name-string matching
@@ -298,7 +298,7 @@ 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"
 ```
 
-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.
+12 built-in tools (write_draft, audit_chapter, revise_chapter, scan_market, create_book, get_book_status, read_truth_files, list_books, write_full_pipeline, web_fetch, import_style, import_canon), with the LLM deciding call order via tool-use.
 
 ## Quick Start
 
@@ -434,7 +434,7 @@ inkos/
 │   │   ├── llm/           # OpenAI + Anthropic dual SDK (streaming)
 │   │   ├── notify/        # Telegram, Feishu, WeCom, Webhook
 │   │   └── models/        # Zod schema validation
-│   └── cli/               # Commander.js CLI (18 commands)
+│   └── cli/               # Commander.js CLI (20 commands)
 │       └── commands/      # init, book, write, draft, audit, revise, agent, review, detect, style...
 └── (planned) studio/      # Web UI for review and editing
 ```
@@ -446,7 +446,7 @@ TypeScript monorepo managed with pnpm workspaces.
 - [x] Full pipeline (radar → architect → writer → auditor → reviser)
 - [x] Canonical truth files + continuity audit
 - [x] Built-in writing rule system
-- [x] Full CLI (18 commands)
+- [x] Full CLI (20 commands)
 - [x] State snapshots + chapter rewrite
 - [x] Daemon mode
 - [x] Notifications (Telegram / Feishu / WeCom)

README.md

@@ -91,7 +91,7 @@ inkos style import 参考小说.txt 吞天魔帝 --name 某作者  # 导入文
 ### 其他 v0.4 变更
 
 - 审计维度从 26 扩展到 32（+4 番外维度 + dim 27 敏感词 + dim 32 读者期待管理）
-- 审计员联网搜索：年代考据题材可调用 DuckDuckGo 核实真实事件/人物/地理
+- 审计员联网搜索：年代考据题材可联网核实真实事件/人物/地理（原生搜索能力）
 - 调度器重写：AI 节奏（默认 15 分钟一轮）、并行书处理、立即重试、每日上限
 - 修订者新增 `spot-fix` 模式（定点修复）
 - `book_rules.md` 的 `additionalAuditDimensions` 支持中文名称匹配
@@ -308,7 +308,7 @@ inkos agent "写下一章，重点写师徒矛盾"
 inkos agent "先扫描市场趋势，然后根据结果创建一本新书"
 ```
 
-内置 9 个工具（write_draft、audit_chapter、revise_chapter、scan_market、create_book、get_book_status、read_truth_files、list_books、write_full_pipeline），LLM 通过 tool-use 决定调用顺序。
+内置 12 个工具（write_draft、audit_chapter、revise_chapter、scan_market、create_book、get_book_status、read_truth_files、list_books、write_full_pipeline、web_fetch、import_style、import_canon），LLM 通过 tool-use 决定调用顺序。
 
 ## 快速开始
 
@@ -462,7 +462,7 @@ inkos/
 │   │   ├── llm/           # OpenAI + Anthropic 双 SDK 接口 (流式)
 │   │   ├── notify/        # Telegram, 飞书, 企业微信, Webhook
 │   │   └── models/        # Zod schema 校验
-│   └── cli/               # Commander.js 命令行 (18 条命令)
+│   └── cli/               # Commander.js 命令行 (20 条命令)
 │       └── commands/      # init, book, write, draft, audit, revise, agent, review, detect, style...
 └── (规划中) studio/        # 网页审阅编辑界面
 ```
@@ -474,7 +474,7 @@ TypeScript 单仓库，pnpm workspaces 管理。
 - [x] 完整管线（雷达 → 建筑师 → 写手 → 审计 → 修订）
 - [x] 长期记忆 + 连续性审计
 - [x] 内置创作规则体系
-- [x] CLI 全套命令（18 条）
+- [x] CLI 全套命令（20 条）
 - [x] 状态快照 + 章节重写
 - [x] 守护进程模式
 - [x] 通知推送（Telegram / 飞书 / 企微）