feat: add screenshot OCR extraction

frontend/src/App.vue

@@ -23,6 +23,7 @@ import {
   SaveRegionImage,
   SaveRegionToRemote,
   SummarizeRegion,
+  ExtractTextRegion,
   CancelRegion,
   GetConfig,
 } from '../wailsjs/go/main/App'
@@ -58,7 +59,7 @@ async function loadThemePreference() {
 // `SettingsTab` is hoisted to the App shell so the sidebar (which lives
 // here) and the inner SettingsView (which renders the matching card) can
 // share a single source of truth without an event bus.
-type SettingsTab = 'general' | 's3' | 'ssh' | 'llm'
+type SettingsTab = 'general' | 's3' | 'ssh' | 'llm' | 'ocr'
 const activeTab = ref<SettingsTab>('general')
 
 // Sidebar entries are declarative so adding a destination type later is
@@ -68,6 +69,7 @@ const sidebarItems: Array<{ id: SettingsTab; label: string }> = [
   { id: 's3', label: '对象存储' },
   { id: 'ssh', label: '远程主机' },
   { id: 'llm', label: '智能识图' },
+  { id: 'ocr', label: '文字提取' },
 ]
 
 interface OverlayPayload {
@@ -192,6 +194,16 @@ async function onOverlaySummarize(rect: OverlayResult) {
   }
 }
 
+async function onOverlayOCR(rect: OverlayResult) {
+  mode.value = 'settings'
+  overlayPayload.value = null
+  try {
+    await ExtractTextRegion(rect as any)
+  } catch {
+    /* Surfaced via upload:failure */
+  }
+}
+
 async function onOverlayCancel() {
   mode.value = 'settings'
   overlayPayload.value = null
@@ -223,6 +235,8 @@ onMounted(() => {
       'success',
       url === 'summary copied to clipboard'
         ? 'Summary copied to clipboard'
+        : url === 'ocr text copied to clipboard'
+          ? 'OCR text copied to clipboard'
         : `Copied: ${url}`
     )
   })
@@ -262,6 +276,7 @@ onUnmounted(() => {
     @save="onOverlaySave"
     @save-remote="onOverlaySaveRemote"
     @summarize="onOverlaySummarize"
+    @ocr="onOverlayOCR"
     @cancel="onOverlayCancel"
   />
 

frontend/src/views/CaptureOverlay.vue

@@ -58,6 +58,10 @@ const emit = defineEmits<{
     e: 'summarize',
     payload: { rect: Rect; annotations: Annotation[] }
   ): void
+  (
+    e: 'ocr',
+    payload: { rect: Rect; annotations: Annotation[] }
+  ): void
   (e: 'cancel'): void
 }>()
 
@@ -138,7 +142,7 @@ const sizeLabel = computed(() => {
 })
 
 const MARK_TOOLBAR_W = 178
-const ACTION_TOOLBAR_W = 216
+const ACTION_TOOLBAR_W = 252
 const TOOLBAR_GROUP_GAP = 8
 
 const toolOrder: Tool[] = ['pen', 'rect', 'ellipse', 'text']
@@ -571,7 +575,11 @@ function onSummarize() {
   emitAction('summarize')
 }
 
-function emitAction(action: 'confirm' | 'copy' | 'save' | 'save-remote' | 'summarize') {
+function onOCR() {
+  emitAction('ocr')
+}
+
+function emitAction(action: 'confirm' | 'copy' | 'save' | 'save-remote' | 'summarize' | 'ocr') {
   if (!rect.value) return
   commitTextDraft()
   const payload = {
@@ -583,6 +591,7 @@ function emitAction(action: 'confirm' | 'copy' | 'save' | 'save-remote' | 'summa
   if (action === 'save') emit('save', payload)
   if (action === 'save-remote') emit('save-remote', payload)
   if (action === 'summarize') emit('summarize', payload)
+  if (action === 'ocr') emit('ocr', payload)
 }
 
 function onCancel() {
@@ -991,6 +1000,21 @@ onUnmounted(() => {
         @click="onSaveRemote"
         v-html="saveRemoteIcon"
       />
+      <button
+        class="action-btn"
+        data-tip="提取文字"
+        aria-label="提取文字"
+        @click="onOCR"
+      >
+        <svg viewBox="0 0 24 24" aria-hidden="true">
+          <path d="M5 8V5h3" />
+          <path d="M16 5h3v3" />
+          <path d="M19 16v3h-3" />
+          <path d="M8 19H5v-3" />
+          <path d="M9 15l3-7 3 7" />
+          <path d="M10 13h4" />
+        </svg>
+      </button>
       <button
         class="action-btn"
         data-tip="复制总结"
@@ -1124,7 +1148,7 @@ onUnmounted(() => {
   width: 178px;
 }
 .action-toolbar {
-  width: 216px;
+  width: 252px;
 }
 
 .icon-btn,

frontend/src/views/SettingsView.vue

@@ -9,6 +9,7 @@
  *   • "s3"      — S3-compatible object-storage credentials.
  *   • "ssh"     — SSH/SCP destination for the "save remote" button.
  *   • "llm"     — multimodal screenshot summary provider settings.
+ *   • "ocr"     — cloud OCR provider settings for text extraction.
  *
  * State flow: load() pulls config from Go on mount, save() pushes back.
  */
@@ -23,7 +24,7 @@ import {
 
 // Tab discriminator shared with the App shell. Kept as a string union so
 // the parent can pass the value without importing a type from this view.
-type TabId = 'general' | 's3' | 'ssh' | 'llm'
+type TabId = 'general' | 's3' | 'ssh' | 'llm' | 'ocr'
 type ThemeMode = 'auto' | 'light' | 'dark'
 
 const props = defineProps<{
@@ -74,12 +75,30 @@ interface LLMConfig {
   providers: Record<string, LLMProviderConfig>
 }
 
+interface OCRProviderConfig {
+  label: string
+  endpoint: string
+  accessKeyId: string
+  accessKeySecret: string
+  region: string
+  service: string
+  action: string
+  version: string
+  timeoutSecs: number
+}
+
+interface OCRConfig {
+  activeProvider: string
+  providers: Record<string, OCRProviderConfig>
+}
+
 interface AppConfig {
   hotkey: string
   theme: ThemeMode
   s3: S3Config
   ssh: SSHConfig
   llm: LLMConfig
+  ocr: OCRConfig
 }
 
 const llmProviderOptions = [
@@ -88,6 +107,11 @@ const llmProviderOptions = [
   { id: 'openai', label: 'ChatGPT / OpenAI-compatible' },
 ]
 
+const ocrProviderOptions = [
+  { id: 'aliyun', label: '阿里云文字识别' },
+  { id: 'volcengine', label: '火山引擎文字识别' },
+]
+
 const themeOptions: Array<{ id: ThemeMode; label: string }> = [
   { id: 'light', label: '浅色' },
   { id: 'dark', label: '深色' },
@@ -165,6 +189,33 @@ function defaultConfig(): AppConfig {
         },
       },
     },
+    ocr: {
+      activeProvider: 'aliyun',
+      providers: {
+        aliyun: {
+          label: '阿里云文字识别',
+          endpoint: 'https://ocr-api.cn-hangzhou.aliyuncs.com',
+          accessKeyId: '',
+          accessKeySecret: '',
+          region: '',
+          service: '',
+          action: 'RecognizeGeneral',
+          version: '2021-07-07',
+          timeoutSecs: 30,
+        },
+        volcengine: {
+          label: '火山引擎文字识别',
+          endpoint: 'https://visual.volcengineapi.com',
+          accessKeyId: '',
+          accessKeySecret: '',
+          region: 'cn-north-1',
+          service: 'cv',
+          action: 'OCRNormal',
+          version: '2020-08-26',
+          timeoutSecs: 30,
+        },
+      },
+    },
   }
 }
 
@@ -198,6 +249,15 @@ const activeLLMProvider = computed(() => {
   return config.value.llm.providers[id]
 })
 
+const activeOCRProvider = computed(() => {
+  const id = config.value.ocr.activeProvider || 'aliyun'
+  if (!config.value.ocr.providers[id]) {
+    config.value.ocr.activeProvider = 'aliyun'
+    return config.value.ocr.providers.aliyun
+  }
+  return config.value.ocr.providers[id]
+})
+
 function normalizeTheme(theme: unknown): ThemeMode {
   return theme === 'light' || theme === 'dark' || theme === 'auto'
     ? theme
@@ -225,6 +285,11 @@ async function load() {
       ...defaultConfig().llm.providers,
       ...((cfg as any).llm?.providers ?? {}),
     }
+    merged.ocr = { ...merged.ocr, ...(cfg as any).ocr }
+    merged.ocr.providers = {
+      ...defaultConfig().ocr.providers,
+      ...((cfg as any).ocr?.providers ?? {}),
+    }
     merged.theme = normalizeTheme((cfg as any).theme)
     config.value = merged
     emit('theme-change', config.value.theme)
@@ -586,6 +651,103 @@ onMounted(load)
       </div>
     </section>
 
+    <!-- OCR tab — cloud OCR provider settings for screenshot text extraction. -->
+    <section v-if="props.tab === 'ocr'" class="card">
+      <h2>文字提取</h2>
+      <div class="grid">
+        <label class="field full">
+          <span>Provider</span>
+          <select v-model="config.ocr.activeProvider">
+            <option
+              v-for="provider in ocrProviderOptions"
+              :key="provider.id"
+              :value="provider.id"
+            >
+              {{ provider.label }}
+            </option>
+          </select>
+        </label>
+        <label class="field full">
+          <span>Endpoint *</span>
+          <input
+            v-model="activeOCRProvider.endpoint"
+            placeholder="https://ocr-api.cn-hangzhou.aliyuncs.com"
+            spellcheck="false"
+          />
+        </label>
+        <label class="field">
+          <span>AccessKey ID *</span>
+          <input v-model="activeOCRProvider.accessKeyId" spellcheck="false" />
+        </label>
+        <label class="field">
+          <span>AccessKey Secret *</span>
+          <input v-model="activeOCRProvider.accessKeySecret" type="password" />
+        </label>
+        <label
+          v-if="config.ocr.activeProvider === 'volcengine'"
+          class="field"
+        >
+          <span>Region *</span>
+          <input
+            v-model="activeOCRProvider.region"
+            placeholder="cn-north-1"
+            spellcheck="false"
+          />
+        </label>
+        <label
+          v-if="config.ocr.activeProvider === 'volcengine'"
+          class="field"
+        >
+          <span>Service *</span>
+          <input
+            v-model="activeOCRProvider.service"
+            placeholder="cv"
+            spellcheck="false"
+          />
+        </label>
+        <label class="field">
+          <span>Action *</span>
+          <input
+            v-model="activeOCRProvider.action"
+            placeholder="RecognizeGeneral / OCRNormal"
+            spellcheck="false"
+          />
+        </label>
+        <label class="field">
+          <span>Version *</span>
+          <input
+            v-model="activeOCRProvider.version"
+            placeholder="2021-07-07 / 2020-08-26"
+            spellcheck="false"
+          />
+        </label>
+        <label class="field">
+          <span>Timeout (sec)</span>
+          <input
+            v-model.number="activeOCRProvider.timeoutSecs"
+            type="number"
+            min="5"
+            max="120"
+            placeholder="30"
+          />
+        </label>
+      </div>
+      <p v-if="config.ocr.activeProvider === 'aliyun'" class="hint">
+        阿里云默认使用 OCR API 的 <code>RecognizeGeneral</code>，请求体为截图
+        PNG 原始数据，并使用 ACS3-HMAC-SHA256 签名。
+      </p>
+      <p v-else class="hint">
+        火山引擎默认使用视觉智能的 <code>OCRNormal</code>，截图以
+        <code>image_base64</code> 发送，并使用 Region/Service 参与签名。
+      </p>
+
+      <div class="actions">
+        <button class="btn primary" :disabled="saving" @click="save">
+          {{ saving ? 'Saving…' : 'Save' }}
+        </button>
+      </div>
+    </section>
+
     <transition name="fade">
       <div
         v-if="message"

frontend/wailsjs/go/main/App.d.ts

@@ -17,6 +17,10 @@ export function CopyNativeRegionImage(arg1:main.CaptureResult):Promise<void>;
 
 export function CopyRegionImage(arg1:main.CaptureResult):Promise<void>;
 
+export function ExtractTextNativeRegion(arg1:main.CaptureResult):Promise<void>;
+
+export function ExtractTextRegion(arg1:main.CaptureResult):Promise<void>;
+
 export function GetConfig():Promise<domain.AppConfig>;
 
 export function QuitApp():Promise<void>;

frontend/wailsjs/go/main/App.js

@@ -30,6 +30,14 @@ export function CopyRegionImage(arg1) {
   return window['go']['main']['App']['CopyRegionImage'](arg1);
 }
 
+export function ExtractTextNativeRegion(arg1) {
+  return window['go']['main']['App']['ExtractTextNativeRegion'](arg1);
+}
+
+export function ExtractTextRegion(arg1) {
+  return window['go']['main']['App']['ExtractTextRegion'](arg1);
+}
+
 export function GetConfig() {
   return window['go']['main']['App']['GetConfig']();
 }

frontend/wailsjs/go/models.ts

@@ -1,13 +1,13 @@
 export namespace application {
-	
+
 	export class Point {
 	    x: number;
 	    y: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new Point(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.x = source["x"];
@@ -25,7 +25,7 @@ export namespace application {
 	    static createFrom(source: any = {}) {
 	        return new Annotation(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.tool = source["tool"];
@@ -35,7 +35,7 @@ export namespace application {
 	        this.strokeWidth = source["strokeWidth"];
 	        this.fontSize = source["fontSize"];
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -58,7 +58,67 @@ export namespace application {
 }
 
 export namespace domain {
-	
+
+	export class OCRProviderConfig {
+	    label: string;
+	    endpoint: string;
+	    accessKeyId: string;
+	    accessKeySecret: string;
+	    region: string;
+	    service: string;
+	    action: string;
+	    version: string;
+	    timeoutSecs: number;
+
+	    static createFrom(source: any = {}) {
+	        return new OCRProviderConfig(source);
+	    }
+
+	    constructor(source: any = {}) {
+	        if ('string' === typeof source) source = JSON.parse(source);
+	        this.label = source["label"];
+	        this.endpoint = source["endpoint"];
+	        this.accessKeyId = source["accessKeyId"];
+	        this.accessKeySecret = source["accessKeySecret"];
+	        this.region = source["region"];
+	        this.service = source["service"];
+	        this.action = source["action"];
+	        this.version = source["version"];
+	        this.timeoutSecs = source["timeoutSecs"];
+	    }
+	}
+	export class OCRConfig {
+	    activeProvider: string;
+	    providers: Record<string, OCRProviderConfig>;
+
+	    static createFrom(source: any = {}) {
+	        return new OCRConfig(source);
+	    }
+
+	    constructor(source: any = {}) {
+	        if ('string' === typeof source) source = JSON.parse(source);
+	        this.activeProvider = source["activeProvider"];
+	        this.providers = this.convertValues(source["providers"], OCRProviderConfig, true);
+	    }
+
+		convertValues(a: any, classs: any, asMap: boolean = false): any {
+		    if (!a) {
+		        return a;
+		    }
+		    if (a.slice && a.map) {
+		        return (a as any[]).map(elem => this.convertValues(elem, classs));
+		    } else if ("object" === typeof a) {
+		        if (asMap) {
+		            for (const key of Object.keys(a)) {
+		                a[key] = new classs(a[key]);
+		            }
+		            return a;
+		        }
+		        return new classs(a);
+		    }
+		    return a;
+		}
+	}
 	export class LLMProviderConfig {
 	    label: string;
 	    baseUrl: string;
@@ -68,11 +128,11 @@ export namespace domain {
 	    temperature: number;
 	    timeoutSecs: number;
 	    maxInlineBytes: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new LLMProviderConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.label = source["label"];
@@ -89,18 +149,18 @@ export namespace domain {
 	    activeProvider: string;
 	    prompt: string;
 	    providers: Record<string, LLMProviderConfig>;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new LLMConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.activeProvider = source["activeProvider"];
 	        this.prompt = source["prompt"];
 	        this.providers = this.convertValues(source["providers"], LLMProviderConfig, true);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -129,11 +189,11 @@ export namespace domain {
 	    strictHostKey: boolean;
 	    knownHostsPath: string;
 	    connectTimeoutSecs: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new SSHConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.host = source["host"];
@@ -156,11 +216,11 @@ export namespace domain {
 	    pathPrefix: string;
 	    publicUrlBase: string;
 	    usePathStyle: boolean;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new S3Config(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.endpoint = source["endpoint"];
@@ -179,11 +239,12 @@ export namespace domain {
 	    s3: S3Config;
 	    ssh: SSHConfig;
 	    llm: LLMConfig;
-	
+	    ocr: OCRConfig;
+
 	    static createFrom(source: any = {}) {
 	        return new AppConfig(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.hotkey = source["hotkey"];
@@ -191,8 +252,9 @@ export namespace domain {
 	        this.s3 = this.convertValues(source["s3"], S3Config);
 	        this.ssh = this.convertValues(source["ssh"], SSHConfig);
 	        this.llm = this.convertValues(source["llm"], LLMConfig);
+	        this.ocr = this.convertValues(source["ocr"], OCRConfig);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -211,22 +273,24 @@ export namespace domain {
 		    return a;
 		}
 	}
-	
-	
-	
+
+
+
+
+
 
 }
 
 export namespace main {
-	
+
 	export class CaptureActionResult {
 	    completed: boolean;
 	    path?: string;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new CaptureActionResult(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.completed = source["completed"];
@@ -238,11 +302,11 @@ export namespace main {
 	    y: number;
 	    w: number;
 	    h: number;
-	
+
 	    static createFrom(source: any = {}) {
 	        return new RegionRect(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.x = source["x"];
@@ -254,17 +318,17 @@ export namespace main {
 	export class CaptureResult {
 	    rect: RegionRect;
 	    annotations: application.Annotation[];
-	
+
 	    static createFrom(source: any = {}) {
 	        return new CaptureResult(source);
 	    }
-	
+
 	    constructor(source: any = {}) {
 	        if ('string' === typeof source) source = JSON.parse(source);
 	        this.rect = this.convertValues(source["rect"], RegionRect);
 	        this.annotations = this.convertValues(source["annotations"], application.Annotation);
 	    }
-	
+
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
 		    if (!a) {
 		        return a;
@@ -285,4 +349,3 @@ export namespace main {
 	}
 
 }
-