feat: add AI email extraction with Cloudflare Workers AI

Add AI-powered email content extraction feature using Cloudflare Workers AI to automatically identify and extract important information from emails including verification codes, authentication links, service links, and subscription links.

Features:
- AI extraction with priority-based logic (auth_code > auth_link > service_link > subscription_link > other_link)
- Admin allowlist configuration with wildcard support (*@example.com)
- Frontend display in both email list (compact) and detail view (full mode)
- Bilingual documentation (Chinese/English)
- Database migration: add metadata field to raw_mails (v0.0.3 -> v0.0.4)

Technical highlights:
- Proper regex escaping for wildcard pattern matching
- Content truncation to avoid AI token limits
- Error handling that won't affect email receiving
- JSON schema validation for AI responses
- Type-safe TypeScript implementation
- Vue I18n support with special character escaping

References:
- Inspired by Alle Project: https://github.com/bestruirui/Alle
- Uses Cloudflare Workers AI JSON Mode

🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>

db/2025-12-06-metadata.sql

@@ -0,0 +1,4 @@
+-- Add metadata column to raw_mails table for storing AI extraction results and other metadata
+-- This column stores JSON data with flexible schema for various analysis results
+
+ALTER TABLE raw_mails ADD COLUMN metadata TEXT;

db/schema.sql

@@ -4,6 +4,7 @@ CREATE TABLE IF NOT EXISTS raw_mails (
     source TEXT,
     address TEXT,
     raw TEXT,
+    metadata TEXT,
     created_at DATETIME DEFAULT CURRENT_TIMESTAMP
 );
 

frontend/package.json

@@ -29,12 +29,12 @@
     "axios": "^1.13.2",
     "jszip": "^3.10.1",
     "mail-parser-wasm": "^0.2.1",
-    "naive-ui": "^2.43.1",
+    "naive-ui": "^2.43.2",
-    "postal-mime": "^2.6.0",
+    "postal-mime": "^2.6.1",
     "vooks": "^0.2.12",
-    "vue": "^3.5.24",
+    "vue": "^3.5.25",
     "vue-clipboard3": "^2.0.0",
-    "vue-i18n": "^11.1.12",
+    "vue-i18n": "^11.2.2",
     "vue-router": "^4.6.3"
   },
   "devDependencies": {
@@ -44,12 +44,12 @@
     "unplugin-auto-import": "^19.3.0",
     "unplugin-vue-components": "^28.8.0",
     "vite": "^6.4.1",
-    "vite-plugin-pwa": "^1.1.0",
+    "vite-plugin-pwa": "^1.2.0",
     "vite-plugin-top-level-await": "^1.6.0",
     "vite-plugin-wasm": "^3.5.0",
-    "workbox-build": "^7.3.0",
+    "workbox-build": "^7.4.0",
-    "workbox-window": "^7.3.0",
+    "workbox-window": "^7.4.0",
-    "wrangler": "^4.47.0"
+    "wrangler": "^4.53.0"
   },
   "packageManager": "pnpm@10.10.0+sha512.d615db246fe70f25dcfea6d8d73dee782ce23e2245e3c4f6f888249fb568149318637dca73c2c5c8ef2a4ca0d5657fb9567188bfab47f566d1ee6ce987815c39"
 }

frontend/src/components/AiExtractInfo.vue

@@ -0,0 +1,145 @@
+<script setup>
+import { computed } from 'vue';
+import { useI18n } from 'vue-i18n';
+import { ContentCopyOutlined, LinkRound, CodeRound } from '@vicons/material';
+import { useMessage } from 'naive-ui';
+
+const message = useMessage();
+
+const { t } = useI18n({
+  messages: {
+    en: {
+      authCode: 'Verification Code',
+      authLink: 'Authentication Link',
+      serviceLink: 'Service Link',
+      subscriptionLink: 'Subscription Link',
+      otherLink: 'Other Link',
+      copySuccess: 'Copied successfully',
+      copyFailed: 'Copy failed',
+      open: 'Open',
+    },
+    zh: {
+      authCode: '验证码',
+      authLink: '认证链接',
+      serviceLink: '服务链接',
+      subscriptionLink: '订阅链接',
+      otherLink: '其他链接',
+      copySuccess: '复制成功',
+      copyFailed: '复制失败',
+      open: '打开',
+    }
+  }
+});
+
+const props = defineProps({
+  metadata: {
+    type: String,
+    default: null
+  },
+  compact: {
+    type: Boolean,
+    default: false
+  }
+});
+
+const aiExtract = computed(() => {
+  if (!props.metadata) return null;
+  try {
+    const data = JSON.parse(props.metadata);
+    return data.ai_extract || null;
+  } catch (e) {
+    return null;
+  }
+});
+
+const typeLabel = computed(() => {
+  if (!aiExtract.value) return '';
+  const typeMap = {
+    auth_code: t('authCode'),
+    auth_link: t('authLink'),
+    service_link: t('serviceLink'),
+    subscription_link: t('subscriptionLink'),
+    other_link: t('otherLink'),
+  };
+  return typeMap[aiExtract.value.type] || '';
+});
+
+const typeIcon = computed(() => {
+  if (!aiExtract.value) return null;
+  const iconMap = {
+    auth_code: CodeRound,
+    auth_link: LinkRound,
+    service_link: LinkRound,
+    subscription_link: LinkRound,
+    other_link: LinkRound,
+  };
+  return iconMap[aiExtract.value.type] || null;
+});
+
+const isLink = computed(() => {
+  return aiExtract.value && aiExtract.value.type !== 'auth_code';
+});
+
+const displayText = computed(() => {
+  if (!aiExtract.value) return '';
+  return aiExtract.value.result_text || aiExtract.value.result;
+});
+
+const copyToClipboard = async () => {
+  try {
+    await navigator.clipboard.writeText(aiExtract.value.result);
+    message.success(t('copySuccess'));
+  } catch (e) {
+    message.error(t('copyFailed'));
+  }
+};
+
+const openLink = () => {
+  if (isLink.value && aiExtract.value.result) {
+    window.open(aiExtract.value.result, '_blank');
+  }
+};
+</script>
+
+<template>
+  <div v-if="aiExtract && aiExtract.result" class="ai-extract-info">
+    <n-alert v-if="!compact" type="success" closable>
+      <template #icon>
+        <n-icon :component="typeIcon" />
+      </template>
+      <template #header>
+        {{ typeLabel }}
+      </template>
+      <n-space align="center">
+        <n-text v-if="aiExtract.type === 'auth_code'" strong style="font-size: 18px; font-family: monospace;">
+          {{ aiExtract.result }}
+        </n-text>
+        <n-ellipsis v-else style="max-width: 400px;">
+          {{ displayText }}
+        </n-ellipsis>
+        <n-button size="small" @click="copyToClipboard" tertiary>
+          <template #icon>
+            <n-icon :component="ContentCopyOutlined" />
+          </template>
+        </n-button>
+        <n-button v-if="isLink" size="small" @click="openLink" tertiary type="primary">
+          {{ t('open') }}
+        </n-button>
+      </n-space>
+    </n-alert>
+    <n-tag v-else type="success" @click="copyToClipboard" style="cursor: pointer;" size="small">
+      <template #icon>
+        <n-icon :component="typeIcon" />
+      </template>
+      <n-ellipsis style="max-width: 150px;">
+        {{ typeLabel }}: {{ displayText }}
+      </n-ellipsis>
+    </n-tag>
+  </div>
+</template>
+
+<style scoped>
+.ai-extract-info {
+  margin-bottom: 10px;
+}
+</style>

frontend/src/components/MailBox.vue

@@ -8,6 +8,7 @@ import { useIsMobile } from '../utils/composables'
 import { processItem } from '../utils/email-parser'
 import { utcToLocalDate } from '../utils';
 import MailContentRenderer from "./MailContentRenderer.vue";
+import AiExtractInfo from "./AiExtractInfo.vue";
 
 const message = useMessage()
 const isMobile = useIsMobile()
@@ -439,6 +440,7 @@ onBeforeUnmount(() => {
                         TO: {{ row.address }}
                       </n-ellipsis>
                     </n-tag>
+                    <AiExtractInfo :metadata="row.metadata" compact />
                   </template>
                 </n-thing>
               </n-list-item>
@@ -513,6 +515,7 @@ onBeforeUnmount(() => {
                 <n-tag v-if="showEMailTo" type="info">
                   TO: {{ row.address }}
                 </n-tag>
+                <AiExtractInfo :metadata="row.metadata" compact />
               </template>
             </n-thing>
           </n-list-item>

frontend/src/components/MailContentRenderer.vue

@@ -3,6 +3,7 @@ import { ref } from "vue";
 import { useI18n } from 'vue-i18n'
 import { CloudDownloadRound, ReplyFilled, ForwardFilled, FullscreenRound } from '@vicons/material'
 import ShadowHtmlComponent from "./ShadowHtmlComponent.vue";
+import AiExtractInfo from "./AiExtractInfo.vue";
 import { getDownloadEmlUrl } from '../utils/email-parser';
 import { utcToLocalDate } from '../utils';
 import { useGlobalState } from '../store';
@@ -179,6 +180,9 @@ const handleSaveToS3 = async (filename, blob) => {
       </n-button>
     </n-space>
 
+    <!-- AI 提取信息 -->
+    <AiExtractInfo :metadata="mail.metadata" />
+
     <!-- 邮件内容 -->
     <div class="mail-content">
       <pre v-if="showTextMail" class="mail-text">{{ mail.text }}</pre>

frontend/src/views/Admin.vue

@@ -26,6 +26,7 @@ import Webhook from './admin/Webhook.vue';
 import MailWebhook from './admin/MailWebhook.vue';
 import WorkerConfig from './admin/WorkerConfig.vue';
 import IpBlacklistSettings from './admin/IpBlacklistSettings.vue';
+import AiExtractSettings from './admin/AiExtractSettings.vue';
 
 const {
   adminAuth, showAdminAuth, adminTab, loading,
@@ -74,6 +75,7 @@ const { t } = useI18n({
       database: 'Database',
       workerconfig: 'Worker Config',
       ipBlacklistSettings: 'IP Blacklist',
+      aiExtractSettings: 'AI Extract Settings',
       appearance: 'Appearance',
       about: 'About',
       ok: 'OK',
@@ -103,6 +105,7 @@ const { t } = useI18n({
       database: '数据库',
       workerconfig: 'Worker 配置',
       ipBlacklistSettings: 'IP 黑名单',
+      aiExtractSettings: 'AI 提取设置',
       appearance: '外观',
       about: '关于',
       ok: '确定',
@@ -166,6 +169,9 @@ onMounted(async () => {
           <n-tab-pane name="ipBlacklistSettings" :tab="t('ipBlacklistSettings')">
             <IpBlacklistSettings />
           </n-tab-pane>
+          <n-tab-pane name="aiExtractSettings" :tab="t('aiExtractSettings')">
+            <AiExtractSettings />
+          </n-tab-pane>
           <n-tab-pane name="webhook" :tab="t('webhookSettings')">
             <Webhook />
           </n-tab-pane>

frontend/src/views/admin/AiExtractSettings.vue

@@ -0,0 +1,125 @@
+<script setup lang="ts">
+import { onMounted, ref } from 'vue'
+import { useI18n } from 'vue-i18n'
+import { useMessage } from 'naive-ui'
+// @ts-ignore
+import { api } from '../../api'
+
+const message = useMessage()
+
+const { t } = useI18n({
+    messages: {
+        en: {
+            title: 'AI Email Extraction Settings',
+            successTip: 'Success',
+            save: 'Save',
+            enableAllowList: 'Enable Address Allowlist',
+            enableAllowListTip: 'When enabled, AI extraction will only process emails sent to addresses in the allowlist',
+            allowList: 'Address Allowlist (Enter address and press Enter, wildcards supported)',
+            allowListTip: "Wildcard * matches any characters, e.g. *{'@'}example.com matches all addresses under example.com domain",
+            manualInputPrompt: 'Type and press Enter to add',
+            disabledTip: 'When disabled, AI extraction will process all email addresses',
+        },
+        zh: {
+            title: 'AI 邮件提取设置',
+            successTip: '成功',
+            save: '保存',
+            enableAllowList: '启用地址白名单',
+            enableAllowListTip: '启用后，AI 提取功能仅对白名单中的邮箱地址生效',
+            allowList: '地址白名单 (请输入地址并回车，支持通配符)',
+            allowListTip: "通配符 * 可匹配任意字符，如 *{'@'}example.com 可匹配 example.com 域名下的所有地址",
+            manualInputPrompt: '输入后按回车键添加',
+            disabledTip: '未启用时，所有邮箱地址都可使用 AI 提取功能',
+        }
+    }
+});
+
+type AiExtractSettings = {
+    enableAllowList: boolean
+    allowList: string[]
+}
+
+const settings = ref<AiExtractSettings>({
+    enableAllowList: false,
+    allowList: []
+})
+
+const fetchData = async () => {
+    try {
+        const res = await api.fetch(`/admin/ai_extract/settings`) as AiExtractSettings
+        Object.assign(settings.value, res)
+    } catch (error) {
+        message.error((error as Error).message || "error");
+    }
+}
+
+const saveSettings = async () => {
+    try {
+        await api.fetch(`/admin/ai_extract/settings`, {
+            method: 'POST',
+            body: JSON.stringify(settings.value),
+        })
+        message.success(t('successTip'))
+    } catch (error) {
+        message.error((error as Error).message || "error");
+    }
+}
+
+onMounted(async () => {
+    await fetchData();
+})
+</script>
+
+<template>
+    <div class="center">
+        <n-card :title="t('title')" :bordered="false" embedded style="max-width: 800px; overflow: auto;">
+            <n-flex justify="end">
+                <n-button @click="saveSettings" type="primary">
+                    {{ t('save') }}
+                </n-button>
+            </n-flex>
+
+            <n-form-item-row :label="t('enableAllowList')">
+                <n-switch v-model:value="settings.enableAllowList" :round="false" />
+            </n-form-item-row>
+
+            <n-alert v-if="!settings.enableAllowList" type="info" style="margin-bottom: 16px;">
+                {{ t('disabledTip') }}
+            </n-alert>
+
+            <div v-if="settings.enableAllowList">
+                <n-alert type="warning" style="margin-bottom: 16px;">
+                    {{ t('enableAllowListTip') }}
+                </n-alert>
+
+                <n-form-item-row :label="t('allowList')">
+                    <n-select v-model:value="settings.allowList" filterable multiple tag
+                        :placeholder="t('allowListTip')">
+                        <template #empty>
+                            <n-text depth="3">
+                                {{ t('manualInputPrompt') }}
+                            </n-text>
+                        </template>
+                    </n-select>
+                </n-form-item-row>
+
+                <n-text depth="3" style="font-size: 12px;">
+                    {{ t('allowListTip') }}
+                </n-text>
+            </div>
+        </n-card>
+    </div>
+</template>
+
+<style scoped>
+.center {
+    display: flex;
+    text-align: left;
+    place-items: center;
+    justify-content: center;
+}
+
+.n-button {
+    margin-top: 10px;
+}
+</style>

pages/package.json

@@ -11,7 +11,7 @@
   "author": "",
   "license": "ISC",
   "devDependencies": {
-    "wrangler": "^4.47.0"
+    "wrangler": "^4.53.0"
   },
   "packageManager": "pnpm@10.10.0+sha512.d615db246fe70f25dcfea6d8d73dee782ce23e2245e3c4f6f888249fb568149318637dca73c2c5c8ef2a4ca0d5657fb9567188bfab47f566d1ee6ce987815c39"
 }

vitepress-docs/docs/.vitepress/en.ts

@@ -142,6 +142,7 @@ function sidebarGuide(): DefaultTheme.SidebarItem[] {
             text: 'Additional Features',
             collapsed: false,
             items: [
+                { text: 'AI Email Recognition', link: 'feature/ai-extract' },
                 { text: 'Configure SMTP IMAP Proxy', link: 'feature/config-smtp-proxy' },
                 { text: 'Send Email API', link: 'feature/send-mail-api' },
                 { text: 'View Email API', link: 'feature/mail-api' },

vitepress-docs/docs/.vitepress/zh.ts

@@ -142,6 +142,7 @@ function sidebarGuide(): DefaultTheme.SidebarItem[] {
             text: '附加功能',
             collapsed: false,
             items: [
+                { text: 'AI 邮件识别', link: 'feature/ai-extract' },
                 { text: '配置 SMTP IMAP 代理服务', link: 'feature/config-smtp-proxy' },
                 { text: '发送邮件 API', link: 'feature/send-mail-api' },
                 { text: '查看邮件 API', link: 'feature/mail-api' },

vitepress-docs/docs/en/guide/feature/ai-extract.md

@@ -0,0 +1,70 @@
+# AI Email Recognition
+
+> [!NOTE]
+> This feature is supported from version v1.1.0
+>
+> This feature is inspired by the [Alle project](https://github.com/bestruirui/Alle/blob/62e74629ded0c7966c12d4e1c54f0bcc2e54f12c/src/lib/email/extract.ts#L54)
+
+## Features
+
+The AI email recognition feature uses Cloudflare Workers AI to automatically analyze incoming email content and intelligently extract important information, including:
+
+- **Verification Code** (auth_code) - OTP, security code, confirmation code, etc.
+- **Authentication Link** (auth_link) - Login, verify, activate, password reset links
+- **Service Link** (service_link) - GitHub, GitLab, deployment notifications and other service-related links
+- **Subscription Link** (subscription_link) - Unsubscribe, manage subscription links
+- **Other Link** (other_link) - Other valuable links
+
+Extraction results are automatically saved to the `metadata` field in the database, and the frontend can directly display extracted verification codes or links.
+
+## Configuration Variables
+
+| Variable Name              | Type      | Description                                                                                                                      | Example                          |
+| -------------------------- | --------- | -------------------------------------------------------------------------------------------------------------------------------- | -------------------------------- |
+| `ENABLE_AI_EMAIL_EXTRACT`  | Text/JSON | Whether to enable AI email recognition feature                                                                                   | `true`                           |
+| `AI_EXTRACT_MODEL`         | Text      | AI model name, choose from [models supporting JSON mode](https://developers.cloudflare.com/workers-ai/features/json-mode/#supported-models) | `@cf/meta/llama-3.1-8b-instruct` |
+
+## Workers AI Binding
+
+Configure Workers AI binding in `wrangler.toml`:
+
+```toml
+[ai]
+binding = "AI"
+```
+
+Or add in Cloudflare Dashboard Worker settings:
+- **Variable name**: `AI`
+- **Type**: Workers AI
+
+## Address Allowlist (Optional)
+
+To control costs and resource usage, you can configure an address allowlist in the Admin console's **AI Extract Settings** page:
+
+### Configuration
+
+- **Allowlist Disabled**: AI extraction will process all email addresses
+- **Allowlist Enabled**: AI extraction will only process addresses in the allowlist
+
+### Allowlist Format
+
+One address per line, supporting wildcard `*` to match any characters:
+
+- **Exact Match**: `user@example.com` - Only matches this specific email
+- **Domain Wildcard**: `*@example.com` - Matches all emails under example.com domain
+- **User Wildcard**: `admin*@example.com` - Matches emails starting with admin
+- **Wildcard Anywhere**: `*test*@example.com` - Matches emails containing test
+- **Multiple Wildcards**: `admin*@*.com` - Matches emails starting with admin under any .com domain
+
+### Configuration Example
+
+```text
+user@example.com
+*@mydomain.com
+admin*@company.com
+```
+
+This configuration will only perform AI extraction for:
+- `user@example.com` (exact match)
+- All emails under `@mydomain.com` (e.g., `test@mydomain.com`, `admin@mydomain.com`)
+- All emails starting with `admin` under `@company.com` (e.g., `admin@company.com`, `admin123@company.com`)

vitepress-docs/docs/en/guide/worker-vars.md

@@ -6,7 +6,7 @@
 ## Required Variables
 
 | Variable Name              | Type        | Description                                                            | Example                              |
-| -------------------------- | ----------- | ------------------------------------------------------------ | ------------------------------------ |
+| -------------------------- | ----------- | ---------------------------------------------------------------------- | ------------------------------------ |
 | `DOMAINS`                  | JSON        | All domains for temporary email, supports multiple domains             | `["awsl.uk", "dreamhunter2333.xyz"]` |
 | `JWT_SECRET`               | Text/Secret | Secret key for generating JWT, used for login and authentication       | `xxx`                                |
 | `ADMIN_PASSWORDS`          | JSON        | Admin console passwords, console access disabled if not configured     | `["123", "456"]`                     |
@@ -16,14 +16,14 @@
 ## Console Related Variables
 
 | Variable Name                  | Type      | Description                                             | Example          |
-| ------------------------------ | --------- | -------------------------------------------------- | ---------------- |
+| ------------------------------ | --------- | ------------------------------------------------------- | ---------------- |
 | `PASSWORDS`                    | JSON      | Website private passwords, required after configuration | `["123", "456"]` |
 | `DISABLE_ADMIN_PASSWORD_CHECK` | Text/JSON | Warning: Admin console without password or user check   | `false`          |
 
 ## Email Related Variables
 
 | Variable Name                         | Type      | Description                                                                                                                                                                                                       | Example                                   |
-| ------------------------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------- |
+| ------------------------------------- | --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------- |
 | `PREFIX`                              | Text      | Default prefix for new `email address` names, can be left unconfigured if no prefix needed                                                                                                                        | `tmp`                                     |
 | `MIN_ADDRESS_LEN`                     | Number    | Minimum length of `email address` name                                                                                                                                                                            | `1`                                       |
 | `MAX_ADDRESS_LEN`                     | Number    | Maximum length of `email address` name                                                                                                                                                                            | `30`                                      |
@@ -40,7 +40,7 @@
 ## Email Reception Related Variables
 
 | Variable Name                   | Type      | Description                                                                                                            | Example                    |
-| ------------------------------- | --------- | -------------------------------------------------------------------------------------- | -------------------------- |
+| ------------------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------- | -------------------------- |
 | `BLACK_LIST`                    | Text      | Blacklist for filtering senders, comma separated                                                                       | `gov.cn,edu.cn`            |
 | `ENABLE_CHECK_JUNK_MAIL`        | Text/JSON | Whether to enable junk mail checking, used with the following two lists                                                | `false`                    |
 | `JUNK_MAIL_CHECK_LIST`          | JSON      | Junk mail check configuration, marked as junk if any item `exists` and `fails`                                         | `["spf", "dkim", "dmarc"]` |
@@ -59,7 +59,7 @@
 ## Webhook Related Variables
 
 | Variable Name    | Type      | Description                                       | Example            |
-| ---------------- | --------- | -------------------------------------------- | ------------------ |
+| ---------------- | --------- | ------------------------------------------------- | ------------------ |
 | `ENABLE_WEBHOOK` | Text/JSON | Whether to enable webhook                         | `true`             |
 | `FRONTEND_URL`   | Text      | Frontend URL, used for sending webhook email URLs | `https://xxxx.xxx` |
 
@@ -73,7 +73,7 @@
 ## User Related Variables
 
 | Variable Name                         | Type      | Description                                                                                          | Example   |
-| ------------------------------------- | --------- | ---------------------------------------------------------------------------------------------- | ------- |
+| ------------------------------------- | --------- | ---------------------------------------------------------------------------------------------------- | --------- |
 | `USER_DEFAULT_ROLE`                   | Text      | Default role for new users, only effective when email verification is enabled                        | `vip`     |
 | `ADMIN_USER_ROLE`                     | Text      | Admin role configuration, if user role equals ADMIN_USER_ROLE, user can access admin console         | `admin`   |
 | `USER_ROLES`                          | JSON      | -                                                                                                    | See below |
@@ -92,7 +92,7 @@
 ## Web Related Variables
 
 | Variable Name              | Type        | Description                                                              | Example               |
-| -------------------------- | ----------- | -------------------------------------------------------- | --------------------- |
+| -------------------------- | ----------- | ------------------------------------------------------------------------ | --------------------- |
 | `DEFAULT_LANG`             | Text        | Worker error message default language, zh/en                             | `zh`                  |
 | `TITLE`                    | Text        | Custom frontend page website title, supports html                        | `Custom Title`        |
 | `ANNOUNCEMENT`             | Text        | Custom frontend page announcement, supports html                         | `Custom Announcement` |
@@ -106,7 +106,7 @@
 ## Telegram Bot Related Variables
 
 | Variable Name    | Type   | Description                                                                 | Example |
-| ---------------- | ------ | ---------------------------------------------------------------------------------------- | ------- |
+| ---------------- | ------ | --------------------------------------------------------------------------- | ------- |
 | `TG_MAX_ADDRESS` | Number | Maximum number of mailboxes that can be bound to telegram bot               | `5`     |
 | `TG_BOT_INFO`    | Text   | Optional, telegram BOT_INFO, predefined BOT_INFO can reduce webhook latency | `{}`    |
 
@@ -120,7 +120,7 @@
 ## Other Variables
 
 | Variable Name           | Type      | Description                                                                                                                                                                                                                                                   | Example   |
-| ----------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| ----------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- |
 | `ENABLE_ANOTHER_WORKER` | Text/JSON | Whether to enable other workers to process emails                                                                                                                                                                                                             | `false`   |
 | `ANOTHER_WORKER_LIST`   | JSON      | - Configuration for other workers to process emails, multiple workers can be configured <br/> - Filter by keywords, call the bound worker's method (default method name is rpcEmail)<br/> - keywords are required, otherwise the worker will not be triggered | See below |
 

vitepress-docs/docs/zh/guide/feature/ai-extract.md

@@ -0,0 +1,70 @@
+# AI 邮件识别
+
+> [!NOTE]
+> 此功能从 v1.1.0 版本开始支持
+>
+> 本功能参考自 [Alle 项目](https://github.com/bestruirui/Alle/blob/62e74629ded0c7966c12d4e1c54f0bcc2e54f12c/src/lib/email/extract.ts#L54)
+
+## 功能说明
+
+AI 邮件识别功能使用 Cloudflare Workers AI 自动分析收到的邮件内容，智能提取重要信息，包括：
+
+- **验证码** (auth_code) - OTP、安全码、确认码等
+- **认证链接** (auth_link) - 登录、验证、激活、重置密码链接
+- **服务链接** (service_link) - GitHub、GitLab、部署通知等服务相关链接
+- **订阅管理链接** (subscription_link) - 退订、管理订阅等链接
+- **其他链接** (other_link) - 其他有价值的链接
+
+提取结果会自动保存到数据库的 `metadata` 字段中，前端可以直接展示提取的验证码或链接。
+
+## 配置变量
+
+| 变量名                    | 类型      | 说明                                                                                                                           | 示例                             |
+| ------------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------ | -------------------------------- |
+| `ENABLE_AI_EMAIL_EXTRACT` | 文本/JSON | 是否启用 AI 邮件识别功能                                                                                                       | `true`                           |
+| `AI_EXTRACT_MODEL`        | 文本      | AI 模型名称，从[支持 JSON 模式的模型](https://developers.cloudflare.com/workers-ai/features/json-mode/#supported-models)中选择 | `@cf/meta/llama-3.1-8b-instruct` |
+
+## Workers AI 绑定
+
+需要在 `wrangler.toml` 中配置 Workers AI 绑定：
+
+```toml
+[ai]
+binding = "AI"
+```
+
+或在 Cloudflare Dashboard 的 Worker 设置中添加：
+- **Variable name**: `AI`
+- **Type**: Workers AI
+
+## 地址白名单（可选）
+
+为了控制成本和资源使用，可以在 Admin 控制台的 **AI 提取设置** 页面配置地址白名单：
+
+### 配置说明
+
+- **未启用白名单**：所有邮箱地址都可使用 AI 提取功能
+- **启用白名单**：仅白名单中的邮箱地址会进行 AI 提取
+
+### 白名单格式
+
+每行一个地址，支持通配符 `*` 匹配任意字符：
+
+- **精确匹配**：`user@example.com` - 仅匹配该邮箱
+- **域名通配符**：`*@example.com` - 匹配 example.com 域名下的所有邮箱
+- **用户通配符**：`admin*@example.com` - 匹配 admin 开头的邮箱
+- **任意位置通配符**：`*test*@example.com` - 匹配包含 test 的邮箱
+- **多个通配符**：`admin*@*.com` - 匹配所有 .com 域名下 admin 开头的邮箱
+
+### 配置示例
+
+```text
+user@example.com
+*@mydomain.com
+admin*@company.com
+```
+
+此配置将只对以下邮箱进行 AI 提取：
+- `user@example.com`（精确匹配）
+- 所有 `@mydomain.com` 的邮箱（如 `test@mydomain.com`、`admin@mydomain.com`）
+- 所有 `admin` 开头的 `@company.com` 邮箱（如 `admin@company.com`、`admin123@company.com`）

vitepress-docs/package.json

@@ -6,7 +6,7 @@
   "devDependencies": {
     "@types/node": "^24.10.1",
     "vitepress": "^1.6.4",
-    "wrangler": "^4.47.0"
+    "wrangler": "^4.53.0"
   },
   "scripts": {
     "dev": "vitepress dev docs",

worker/package.json

@@ -11,26 +11,26 @@
     "build": "wrangler deploy --dry-run --outdir dist --minify"
   },
   "devDependencies": {
-    "@cloudflare/workers-types": "^4.20251111.0",
+    "@cloudflare/workers-types": "^4.20251205.0",
     "@eslint/js": "9.18.0",
     "@simplewebauthn/types": "10.0.0",
     "@types/node": "^22.19.1",
     "eslint": "9.18.0",
     "globals": "^15.15.0",
-    "typescript-eslint": "^8.46.4",
+    "typescript-eslint": "^8.48.1",
-    "wrangler": "^4.47.0"
+    "wrangler": "^4.53.0"
   },
   "dependencies": {
     "@aws-sdk/client-s3": "3.888.0",
     "@aws-sdk/s3-request-presigner": "3.888.0",
     "@simplewebauthn/server": "10.0.1",
-    "hono": "^4.10.5",
+    "hono": "^4.10.7",
     "jsonpath-plus": "^10.3.0",
     "mimetext": "^3.0.27",
-    "postal-mime": "^2.6.0",
+    "postal-mime": "^2.6.1",
     "resend": "^4.8.0",
     "telegraf": "4.16.3",
-    "worker-mailer": "^1.2.0"
+    "worker-mailer": "^1.2.1"
   },
   "pnpm": {
     "patchedDependencies": {

worker/src/admin_api/ai_extract_settings.ts

@@ -0,0 +1,27 @@
+import { Context } from "hono";
+import { CONSTANTS } from "../constants";
+import { getJsonSetting, saveSetting } from "../utils";
+
+export type AiExtractSettings = {
+    enableAllowList: boolean;
+    allowList: string[];
+}
+
+async function getAiExtractSettings(c: Context<HonoCustomType>): Promise<Response> {
+    const settings = await getJsonSetting<AiExtractSettings>(c, CONSTANTS.AI_EXTRACT_SETTINGS_KEY) || {
+        enableAllowList: false,
+        allowList: []
+    };
+    return c.json(settings);
+}
+
+async function saveAiExtractSettings(c: Context<HonoCustomType>): Promise<Response> {
+    const settings = await c.req.json<AiExtractSettings>();
+    await saveSetting(c, CONSTANTS.AI_EXTRACT_SETTINGS_KEY, JSON.stringify(settings));
+    return c.json({ success: true })
+}
+
+export default {
+    getAiExtractSettings,
+    saveAiExtractSettings,
+}

worker/src/admin_api/db_api.ts

@@ -9,6 +9,7 @@ CREATE TABLE IF NOT EXISTS raw_mails (
     source TEXT,
     address TEXT,
     raw TEXT,
+    metadata TEXT,
     created_at DATETIME DEFAULT CURRENT_TIMESTAMP
 );
 
@@ -142,8 +143,11 @@ export default {
             const query = `ALTER TABLE address ADD password TEXT;`
             await c.env.DB.exec(query);
         }
+        if (version == "v0.0.3") {
+            // migration from v0.0.3 to v0.0.4
+            await c.env.DB.exec(`ALTER TABLE raw_mails ADD COLUMN metadata TEXT;`);
+        }
         if (version != CONSTANTS.DB_VERSION) {
-            // TODO: Perform migration logic here
             // remove all \r and \n characters from the query string
             // split by ; and join with a ;\n
             const query = DB_INIT_QUERIES.replace(/[\r\n]/g, "")

worker/src/admin_api/index.ts

@@ -15,6 +15,7 @@ import admin_mail_api from './admin_mail_api'
 import { sendMailbyAdmin } from './send_mail'
 import db_api from './db_api'
 import ip_blacklist_settings from './ip_blacklist_settings'
+import ai_extract_settings from './ai_extract_settings'
 import { EmailRuleSettings } from '../models'
 
 export const api = new Hono<HonoCustomType>()
@@ -377,3 +378,7 @@ api.post('admin/db_migration', db_api.migrate);
 // IP blacklist settings
 api.get("/admin/ip_blacklist/settings", ip_blacklist_settings.getIpBlacklistSettings);
 api.post("/admin/ip_blacklist/settings", ip_blacklist_settings.saveIpBlacklistSettings);
+
+// AI extract settings
+api.get("/admin/ai_extract/settings", ai_extract_settings.getAiExtractSettings);
+api.post("/admin/ai_extract/settings", ai_extract_settings.saveAiExtractSettings);

worker/src/constants.ts

@@ -3,7 +3,7 @@ export const CONSTANTS = {
 
     // DB Version
     DB_VERSION_KEY: 'db_version',
-    DB_VERSION: "v0.0.3",
+    DB_VERSION: "v0.0.4",
 
     // DB settings
     ADDRESS_BLOCK_LIST_KEY: 'address_block_list',
@@ -16,6 +16,7 @@ export const CONSTANTS = {
     EMAIL_RULE_SETTINGS_KEY: 'email_rule_settings',
     ROLE_ADDRESS_CONFIG_KEY: 'role_address_config',
     IP_BLACKLIST_SETTINGS_KEY: 'ip_blacklist_settings',
+    AI_EXTRACT_SETTINGS_KEY: 'ai_extract_settings',
 
     // KV
     TG_KV_PREFIX: "temp-mail-telegram",

worker/src/email/ai_extract.ts

@@ -0,0 +1,235 @@
+/**
+ * AI Email Extraction Module
+ *
+ * This module provides email content analysis using Cloudflare Workers AI.
+ * It extracts important information like verification codes, authentication links,
+ * service links, and subscription management links from email content.
+ */
+
+import { commonParseMail } from "../common";
+import { getBooleanValue, getJsonSetting } from "../utils";
+import { CONSTANTS } from "../constants";
+import { Context } from "hono";
+import type { AiExtractSettings } from "../admin_api/ai_extract_settings";
+
+// AI Prompt for email analysis
+const PROMPT = `
+You are an expert email analyzer. Your task is to first UNDERSTAND the email content, then EXTRACT the most relevant information based on priority.
+
+# Step 1: UNDERSTAND the Email
+Read the entire email carefully and determine its:
+- Overall purpose (verification, marketing, notification, etc.)
+- Key context and situation
+- What the sender wants the recipient to do
+- Any security-sensitive content
+
+# Step 2: EXTRACT Based on Priority
+After understanding, extract the most important item according to this priority order:
+
+**Priority 1: auth_code (Authentication Code)**
+- Numeric or alphanumeric codes used for login verification
+- Keywords: verification code, OTP, security code, confirmation code, auth code, 验证码, 校验码
+- Extract ONLY the code itself (remove spaces, hyphens, etc.)
+- Example: "123456" from "Your verification code is 123-456"
+
+**Priority 2: auth_link (Authentication Link)**
+- Links used for login, email verification, account activation, or password reset
+- Keywords: verify, confirm, activate, login, signin, signup, reset, 验证, 激活, 登录
+- Must be a real, complete URL (http:// or https://)
+- Never fabricate or infer links that don't exist in the content
+- Example: "https://example.com/verify?token=abc123"
+
+**Priority 3: service_link (Service Link)**
+- Links related to specific services or actions
+- Keywords: commit, pull request, issue, repository, deployment, GitHub, GitLab, code review
+- Real URLs for technical or service-related notifications
+- Example: GitHub commit link, deployment notification link
+
+**Priority 4: subscription_link (Subscription Management Link)**
+- Links for managing email subscriptions, typically unsubscribe
+- Keywords: unsubscribe, opt-out, manage preferences, 退订, 取消订阅
+- Usually found at the bottom of marketing emails
+- Real URLs for subscription control
+
+**Priority 5: other_link (Other Valuable Link)**
+- Any other link that might be useful or important
+- Only extract if no higher-priority items exist
+- Must be a real, complete URL from the content
+
+**Priority 6: none**
+- No relevant codes, links, or valuable content found
+- Email appears to be plain text or irrelevant
+
+# Special Case: Markdown Link Format
+If the extracted content is in markdown link format [text](url):
+
+- Extract the text inside the brackets as result_text
+- When brackets are empty, analyze the email context and language
+- Generate a concise, meaningful description (2-5 words) for result_text
+- Match the email's language (Chinese → Chinese description, English → English)
+
+# Critical Rules
+1. **Understand First**: Always analyze the email's purpose before extracting
+2. **Single Selection**: Choose ONLY ONE type based on the highest priority match
+3. **Real Data Only**: Never invent, guess, or fabricate content
+4. **Complete URLs**: Links must be full, valid URLs as they appear in the email
+5. **Clean Extraction**: Return only the raw extracted content, no extra text
+
+# Output Format (JSON only)
+{
+  "type": "auth_code|auth_link|service_link|subscription_link|other_link|none",
+  "result": "the extracted code/link OR empty string",
+  "result_text": "the display text from markdown-format links."
+}
+
+IMPORTANT: Return ONLY the JSON, no explanations or additional text.
+`;
+
+/**
+ * Extract important information from email content using Cloudflare Workers AI
+ *
+ * @param content - The email content to analyze (plain text or HTML)
+ * @param env - Cloudflare Workers environment bindings
+ * @returns Promise<ExtractResult> - The extracted information
+ */
+async function extractWithCloudflareAI(
+    content: string,
+    env: Bindings
+): Promise<ExtractResult> {
+    // Get the AI model name from environment variable or use default
+    const modelName = env.AI_EXTRACT_MODEL || '@cf/meta/llama-3.1-8b-instruct';
+
+    const result = await env.AI.run(modelName as keyof AiModels, {
+        messages: [
+            { role: 'system', content: PROMPT },
+            { role: 'user', content },
+        ],
+        response_format: {
+            type: 'json_schema',
+            json_schema: {
+                type: 'object',
+                properties: {
+                    type: {
+                        type: 'string',
+                        enum: ['auth_code', 'auth_link', 'service_link', 'subscription_link', 'other_link', 'none']
+                    },
+                    result: { type: 'string' },
+                    result_text: { type: 'string' },
+                },
+                required: ['type', 'result', 'result_text'],
+            },
+        },
+        stream: false,
+    });
+
+    // @ts-expect-error result.response
+    const response = result.response;
+
+    if (typeof response === 'string') {
+        return JSON.parse(response) as ExtractResult;
+    }
+
+    if (response && typeof response === 'object') {
+        return response as ExtractResult;
+    }
+
+    throw new Error('Unexpected response format from Cloudflare AI');
+}
+
+/**
+ * Main extraction function
+ * Checks if AI extraction is enabled, processes the email content, and saves to database
+ *
+ * @param parsedEmailContext - The parsed email context
+ * @param env - Cloudflare Workers environment bindings
+ * @param message_id - The email message ID
+ * @param address - The recipient email address
+ * @returns Promise<void>
+ */
+export async function extractEmailInfo(
+    parsedEmailContext: ParsedEmailContext,
+    env: Bindings,
+    message_id: string | null,
+    address: string
+): Promise<void> {
+    try {
+        // Check if AI extraction is enabled via environment variable
+        if (!getBooleanValue(env.ENABLE_AI_EMAIL_EXTRACT)) {
+            return;
+        }
+
+        // Ensure AI binding is available
+        if (!env.AI) {
+            console.error('AI binding not available');
+            return;
+        }
+
+        // Check allowlist if enabled
+        const aiSettings = await getJsonSetting<AiExtractSettings>(
+            { env: env } as Context<HonoCustomType>,
+            CONSTANTS.AI_EXTRACT_SETTINGS_KEY
+        );
+
+        if (aiSettings?.enableAllowList && aiSettings.allowList?.length > 0) {
+            const isAllowed = aiSettings.allowList.some(pattern => {
+                // Support wildcard matching
+                if (pattern.includes('*')) {
+                    // Escape special regex characters except *
+                    const escapedPattern = pattern
+                        .replace(/[.+?^${}()|[\]\\]/g, '\\$&')
+                        .replace(/\*/g, '.*');
+                    const regex = new RegExp('^' + escapedPattern + '$');
+                    return regex.test(address);
+                }
+                // Exact match
+                return address === pattern;
+            });
+
+            if (!isAllowed) {
+                console.log(`AI extraction skipped for ${address}: not in allowlist`);
+                return;
+            }
+        }
+
+        // Parse email to get content
+        const parsedEmail = await commonParseMail(parsedEmailContext);
+        const emailContent = parsedEmail?.text || parsedEmail?.html || "";
+
+        if (!emailContent) {
+            return;
+        }
+
+        // Truncate content if too long (max 4000 characters to avoid token limits)
+        const truncatedContent = emailContent.length > 4000
+            ? emailContent.substring(0, 4000) + '...[truncated]'
+            : emailContent;
+
+        const result = await extractWithCloudflareAI(truncatedContent, env);
+
+        // If extraction found something useful, save it to database
+        if (result.type !== 'none' && result.result) {
+            const metadata = JSON.stringify({
+                ai_extract: result,
+                extracted_at: new Date().toISOString()
+            });
+
+            // Update the raw_mails record with metadata
+            await env.DB.prepare(
+                `UPDATE raw_mails SET metadata = ? WHERE message_id = ?`
+            ).bind(metadata, message_id).run();
+
+            console.log(`AI extraction completed for ${message_id}: ${result.type}`);
+        }
+    } catch (e) {
+        console.error('AI email extraction error:', e);
+    }
+}
+
+/**
+ * Type definition for extraction result
+ */
+export type ExtractResult = {
+    type: 'auth_code' | 'auth_link' | 'service_link' | 'subscription_link' | 'other_link' | 'none';
+    result: string;
+    result_text: string;
+};

worker/src/email/index.ts

@@ -7,6 +7,7 @@ import { isBlocked } from "./black_list";
 import { triggerWebhook, triggerAnotherWorker, commonParseMail } from "../common";
 import { check_if_junk_mail } from "./check_junk";
 import { remove_attachment_if_need } from "./check_attachment";
+import { extractEmailInfo } from "./ai_extract";
 import { EmailRuleSettings } from "../models";
 import { CONSTANTS } from "../constants";
 
@@ -155,6 +156,9 @@ async function email(message: ForwardableEmailMessage, env: Bindings, ctx: Execu
 
     // auto reply email
     await auto_reply(message, env);
+
+    // AI email content extraction
+    await extractEmailInfo(parsedEmailContext, env, message_id, message.to);
 }
 
 export { email }

worker/src/types.d.ts

@@ -11,6 +11,7 @@ type Bindings = {
     RATE_LIMITER: any
     SEND_MAIL: any
     ASSETS: Fetcher
+    AI: Ai
 
     // config
     DEFAULT_LANG: string | undefined
@@ -86,6 +87,10 @@ type Bindings = {
 
     // webhook config
     FRONTEND_URL: string | undefined
+
+    // AI extraction config
+    ENABLE_AI_EMAIL_EXTRACT: string | boolean | undefined
+    AI_EXTRACT_MODEL: string | undefined
 }
 
 type JwtPayload = {

worker/wrangler.toml.template

@@ -107,6 +107,10 @@ ENABLE_AUTO_REPLY = false
 # REMOVE_EXCEED_SIZE_ATTACHMENT = true
 # remove all attachment, mail maybe mising some information due to parsing
 # REMOVE_ALL_ATTACHMENT = true
+# AI email extraction, automatically extract verification codes, auth links, etc.
+# ENABLE_AI_EMAIL_EXTRACT = true
+# AI model name, choose from https://developers.cloudflare.com/workers-ai/models/#text-generation
+# AI_EXTRACT_MODEL = "@cf/meta/llama-3.1-8b-instruct"
 # Calling other woker to process email
 # ENABLE_ANOTHER_WORKER = false
 # ANOTHER_WORKER_LIST = """
@@ -127,6 +131,10 @@ binding = "DB"
 database_name = "xxx"
 database_id = "xxx"
 
+# Workers AI binding (required for AI email extraction)
+# [ai]
+# binding = "AI"
+
 # kv config for send email verification code
 # [[kv_namespaces]]
 # binding = "KV"