docs: add Obsidian disclosure section, bump version to 0.3.1

Adds required disclosures (account, payment, network use) to README and
README-cn.md per Obsidian developer policies.

Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>

README-cn.md

@@ -64,6 +64,33 @@
 | Ollama | 本地模型（Llama、Mistral、Qwen 等） |
 | 自定义 | 任意 OpenAI 兼容或 Anthropic 兼容端点 |
 
+## 披露说明
+
+### 需要账号
+
+使用远程 LLM 服务提供商（OpenAI、Anthropic、DeepSeek、通义千问、Kimi、智谱、Z.ai、MiniMax、OpenRouter）需要在该提供商处注册账号并获取有效的 API Key。本地服务提供商（Ollama、LM Studio）及自定义自托管端点无需账号。
+
+### 可能需要付费
+
+远程 LLM 服务提供商按 API 用量收费，费用由您直接向所选提供商支付——本插件本身不设订阅费或应用内购买。本地服务提供商（Ollama、LM Studio）免费使用。
+
+### 网络请求
+
+当您发送消息时，插件会将您的消息文本及相关笔记库内容发送至您所配置的 LLM 服务提供商。在您提供 API Key 并发送消息之前，插件不会向任何服务发送任何数据。根据您选择的服务提供商，可能会访问以下远程服务：
+
+| 服务提供商 | 接口地址 |
+|---|---|
+| OpenAI | `https://api.openai.com` |
+| Anthropic | `https://api.anthropic.com` |
+| DeepSeek | `https://api.deepseek.com` |
+| 通义千问（阿里云） | `https://dashscope.aliyuncs.com` |
+| Kimi（月之暗面） | `https://api.moonshot.cn` |
+| 智谱 / Z.ai | `https://open.bigmodel.cn`、`https://open.z.ai` |
+| MiniMax | `https://api.minimax.chat` |
+| OpenRouter | `https://openrouter.ai` |
+
+Ollama 和 LM Studio 仅与 `localhost` 通信，数据不会离开您的设备。
+
 ## 开发
 
 ```bash

README.md

@@ -64,6 +64,33 @@ An agentic AI assistant plugin for [Obsidian](https://obsidian.md) that can read
 | Ollama | Local models — Llama, Mistral, Qwen, etc. |
 | Custom | Any OpenAI-compatible or Anthropic-compatible endpoint |
 
+## Disclosures
+
+### Account required
+
+Using a remote LLM provider (OpenAI, Anthropic, DeepSeek, Qwen, Kimi, Zhipu, Z.ai, MiniMax, OpenRouter) requires an account with that provider and a valid API key. Local providers (Ollama, LM Studio) and custom self-hosted endpoints require no account.
+
+### Payment may be required
+
+Remote LLM providers charge for API usage. You are billed directly by the provider you choose — this plugin has no subscription or in-app purchase of its own. Local providers (Ollama, LM Studio) are free.
+
+### Network use
+
+When you send a message, the plugin transmits your message text and relevant vault context to the LLM provider you have configured. No data is sent to any service by default — the plugin is inert until you supply an API key and send a message. The following remote services may be contacted, depending on your provider selection:
+
+| Provider | Endpoint |
+|---|---|
+| OpenAI | `https://api.openai.com` |
+| Anthropic | `https://api.anthropic.com` |
+| DeepSeek | `https://api.deepseek.com` |
+| Qwen (Alibaba Cloud) | `https://dashscope.aliyuncs.com` |
+| Kimi (Moonshot AI) | `https://api.moonshot.cn` |
+| Zhipu / Z.ai | `https://open.bigmodel.cn`, `https://open.z.ai` |
+| MiniMax | `https://api.minimax.chat` |
+| OpenRouter | `https://openrouter.ai` |
+
+Ollama and LM Studio communicate only with `localhost` — no data leaves your machine.
+
 ## Development
 
 ```bash

manifest.json

@@ -1,10 +1,10 @@
 {
   "id": "smart-note-agent",
   "name": "Smart Note Agent",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "minAppVersion": "1.5.0",
   "description": "Agentic AI assistant for reading and editing vault notes.",
   "author": "Bin Hong",
   "authorUrl": "https://github.com/binhong87",
-  "isDesktopOnly": false
+  "isDesktopOnly": true
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "smart-note-agent",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "main": "index.js",
   "directories": {
     "doc": "docs"