feat: add screenshot OCR extraction

app.go

@@ -23,6 +23,7 @@ import (
 	"github.com/mmmy/snapgo/internal/infrastructure/display"
 	"github.com/mmmy/snapgo/internal/infrastructure/hotkey"
 	llmpkg "github.com/mmmy/snapgo/internal/infrastructure/llm"
+	ocrpkg "github.com/mmmy/snapgo/internal/infrastructure/ocr"
 	"github.com/mmmy/snapgo/internal/infrastructure/oss"
 	"github.com/mmmy/snapgo/internal/infrastructure/screencapture"
 	sshpkg "github.com/mmmy/snapgo/internal/infrastructure/ssh"
@@ -499,6 +500,48 @@ func (a *App) finishSummary(svc *application.CaptureSummaryService, summary stri
 	return nil
 }
 
+func (a *App) runOCRPipeline(pngBytes []byte) error {
+	a.mu.RLock()
+	cfg := a.cfg
+	a.mu.RUnlock()
+
+	if !cfg.IsOCRConfigured() {
+		err := fmt.Errorf("请先在文字提取配置页填写 OCR Provider 的 AccessKey ID 和 AccessKey Secret")
+		a.emitOperationStatus("ocr", "需要配置 OCR", err.Error(), "error")
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+
+	providerID, ocrCfg, _ := cfg.ActiveOCRProvider()
+	recognizer, err := ocrpkg.NewClient(providerID, ocrCfg)
+	if err != nil {
+		a.emitOperationStatus("ocr", "OCR 配置错误", err.Error(), "error")
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+
+	svc := &application.CaptureOCRService{
+		Recognizer: recognizer,
+		Clipboard:  a.clip,
+	}
+
+	a.emitOperationStatus("ocr", "识别中", "正在提取截图文字", "running")
+	text, err := svc.Recognize(a.ctx, pngBytes)
+	if err != nil {
+		a.emitOperationStatus("ocr", "识别失败", err.Error(), "error")
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+	if err := svc.CopyText(a.ctx, text); err != nil {
+		a.emitOperationStatus("ocr", "复制失败", err.Error(), "error")
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+	a.emitOperationStatus("ocr", "提取完成", "文字已复制到剪贴板", "success")
+	wruntime.EventsEmit(a.ctx, "upload:success", "ocr text copied to clipboard")
+	return nil
+}
+
 func (a *App) consumePendingCapture() (*pendingCapture, error) {
 	a.pendingMu.Lock()
 	pc := a.pending
@@ -876,6 +919,35 @@ func (a *App) SummarizeRegion(result CaptureResult) error {
 	return a.runSummaryPipeline(cropped)
 }
 
+// ExtractTextRegion sends the selected screenshot to the configured OCR
+// provider and copies the extracted text to the clipboard.
+func (a *App) ExtractTextRegion(result CaptureResult) error {
+	pc, err := a.consumePendingCapture()
+	if err != nil {
+		slog.Warn("ExtractTextRegion: no pending capture", "err", err)
+		return err
+	}
+	defer func() {
+		a.capturing.Store(false)
+		a.dismissOverlay()
+	}()
+
+	a.dismissOverlay()
+	flushFrame()
+
+	slog.Info("ExtractTextRegion: capturing region",
+		"x", result.Rect.X, "y", result.Rect.Y,
+		"w", result.Rect.W, "h", result.Rect.H,
+		"annotations", len(result.Annotations))
+	cropped, err := a.captureSelectedPNG(result, pc)
+	if err != nil {
+		slog.Error("ExtractTextRegion: capture failed", "err", err)
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+	return a.runOCRPipeline(cropped)
+}
+
 // SaveNativeRegionToRemote is the macOS-native overlay equivalent of
 // SaveRegionToRemote. The AppKit panel is already closed by the time this
 // runs (see saveRemoteSelection in native_overlay_darwin.go), so we only
@@ -933,6 +1005,33 @@ func (a *App) SummarizeNativeRegion(result CaptureResult) error {
 	return a.runSummaryPipeline(cropped)
 }
 
+// ExtractTextNativeRegion is the macOS-native overlay equivalent of
+// ExtractTextRegion. The AppKit panel is already closed before this runs.
+func (a *App) ExtractTextNativeRegion(result CaptureResult) error {
+	pc, err := a.consumePendingCapture()
+	if err != nil {
+		slog.Warn("ExtractTextNativeRegion: no pending capture", "err", err)
+		return err
+	}
+	defer func() {
+		a.capturing.Store(false)
+		hideDockIcon()
+	}()
+
+	flushFrame()
+	slog.Info("ExtractTextNativeRegion: capturing region",
+		"x", result.Rect.X, "y", result.Rect.Y,
+		"w", result.Rect.W, "h", result.Rect.H,
+		"annotations", len(result.Annotations))
+	cropped, err := a.captureSelectedPNG(result, pc)
+	if err != nil {
+		slog.Error("ExtractTextNativeRegion: capture failed", "err", err)
+		wruntime.EventsEmit(a.ctx, "upload:failure", err.Error())
+		return err
+	}
+	return a.runOCRPipeline(cropped)
+}
+
 func parseNativeAnnotations(raw string) []application.Annotation {
 	if raw == "" {
 		return nil

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 {
@@ -233,6 +235,28 @@ async function onOverlaySummarize(rect: {
   }
 }
 
+async function onOverlayOCR(rect: {
+  rect: {
+    x: number
+    y: number
+    w: number
+    h: number
+  }
+  annotations: Array<{
+    tool: string
+    color: string
+    points: Array<{ x: number; y: number }>
+  }>
+}) {
+  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
@@ -264,6 +288,8 @@ onMounted(() => {
       'success',
       url === 'summary copied to clipboard'
         ? 'Summary copied to clipboard'
+        : url === 'ocr text copied to clipboard'
+          ? 'OCR text copied to clipboard'
         : `Copied: ${url}`
     )
   })
@@ -303,6 +329,7 @@ onUnmounted(() => {
     @save="onOverlaySave"
     @save-remote="onOverlaySaveRemote"
     @summarize="onOverlaySummarize"
+    @ocr="onOverlayOCR"
     @cancel="onOverlayCancel"
   />
 

frontend/src/views/CaptureOverlay.vue

@@ -1,5 +1,5 @@
 <script setup lang="ts">
-import { computed, onMounted, onUnmounted, ref } from 'vue'
+import { computed, nextTick, onMounted, onUnmounted, ref } from 'vue'
 // Inline SVG markup imported as raw strings via Vite's `?raw` suffix.
 // Rationale: rendering through v-html lets the icon inherit `currentColor`
 // from the toolbar button, so styling stays in CSS without bundling extra
@@ -23,7 +23,7 @@ interface Rect {
   h: number
 }
 
-type Tool = 'pen' | 'rect' | 'ellipse'
+type Tool = 'pen' | 'rect' | 'ellipse' | 'text'
 interface Point {
   x: number
   y: number
@@ -32,6 +32,7 @@ interface Annotation {
   tool: Tool
   color: string
   points: Point[]
+  text?: string
 }
 
 const emit = defineEmits<{
@@ -55,6 +56,10 @@ const emit = defineEmits<{
     e: 'summarize',
     payload: { rect: Rect; annotations: Annotation[] }
   ): void
+  (
+    e: 'ocr',
+    payload: { rect: Rect; annotations: Annotation[] }
+  ): void
   (e: 'cancel'): void
 }>()
 
@@ -64,6 +69,8 @@ const draftAnnotation = ref<Annotation | null>(null)
 const activeTool = ref<Tool>('pen')
 const activeColor = ref('#ef4444')
 const paletteOpen = ref(false)
+const textDraft = ref<{ point: Point; value: string } | null>(null)
+const textInputRef = ref<HTMLInputElement | null>(null)
 
 type ResizeHandle = 'n' | 's' | 'e' | 'w' | 'nw' | 'ne' | 'sw' | 'se'
 type DragMode = 'idle' | 'creating' | 'moving' | 'resizing' | 'annotating'
@@ -115,8 +122,8 @@ const sizeLabel = computed(() => {
   return `${Math.round(rect.value.w)} × ${Math.round(rect.value.h)}`
 })
 
-const MARK_TOOLBAR_W = 190
+const MARK_TOOLBAR_W = 222
-const ACTION_TOOLBAR_W = 216
+const ACTION_TOOLBAR_W = 252
 const TOOLBAR_GROUP_GAP = 8
 
 const rightToolbarPos = computed(() => {
@@ -227,6 +234,7 @@ function hitHandle(p: Point): ResizeHandle | null {
 
 function onMouseDown(e: MouseEvent) {
   if (e.button !== 0) return
+  commitTextDraft()
   paletteOpen.value = false
   const p = pointFromEvent(e)
   const handle = hitHandle(p)
@@ -253,6 +261,10 @@ function onSelectionMouseDown(e: MouseEvent) {
   if (e.button !== 0 || !rect.value) return
   e.stopPropagation()
   paletteOpen.value = false
+  if (activeTool.value === 'text') {
+    beginTextAnnotation(localPoint(pointFromEvent(e)))
+    return
+  }
   if (e.detail >= 2) {
     removeSinglePointAnnotation()
     onCopy()
@@ -371,8 +383,13 @@ 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 = {
     rect: { ...rect.value },
     annotations: annotations.value,
@@ -382,6 +399,7 @@ 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() {
@@ -389,6 +407,13 @@ function onCancel() {
 }
 
 function onKeydown(e: KeyboardEvent) {
+  if (textDraft.value) {
+    if (e.key === 'Escape') {
+      e.preventDefault()
+      cancelTextDraft()
+    }
+    return
+  }
   if (e.key === 'Escape') {
     e.preventDefault()
     onCancel()
@@ -399,6 +424,7 @@ function onKeydown(e: KeyboardEvent) {
 }
 
 function undoAnnotation() {
+  cancelTextDraft()
   annotations.value.pop()
 }
 
@@ -409,6 +435,45 @@ function removeSinglePointAnnotation() {
   }
 }
 
+function beginTextAnnotation(point: Point) {
+  commitTextDraft()
+  dragMode.value = 'idle'
+  draftAnnotation.value = null
+  textDraft.value = { point, value: '' }
+  void nextTick(() => {
+    textInputRef.value?.focus()
+    textInputRef.value?.select()
+  })
+}
+
+function commitTextDraft() {
+  if (!textDraft.value) return
+  const text = textDraft.value.value.trim()
+  if (text !== '') {
+    annotations.value.push({
+      tool: 'text',
+      color: activeColor.value,
+      points: [textDraft.value.point],
+      text,
+    })
+  }
+  textDraft.value = null
+}
+
+function cancelTextDraft() {
+  textDraft.value = null
+}
+
+function onTextDraftKeydown(e: KeyboardEvent) {
+  if (e.key === 'Enter') {
+    e.preventDefault()
+    commitTextDraft()
+  } else if (e.key === 'Escape') {
+    e.preventDefault()
+    cancelTextDraft()
+  }
+}
+
 onMounted(() => {
   window.addEventListener('keydown', onKeydown)
 })
@@ -475,6 +540,17 @@ onUnmounted(() => {
           stroke-width="3"
           fill="none"
         />
+        <text
+          v-else-if="annotation.tool === 'text' && annotation.points.length >= 1"
+          :x="annotation.points[0].x"
+          :y="annotation.points[0].y"
+          :fill="annotation.color"
+          font-size="20"
+          font-weight="600"
+          dominant-baseline="hanging"
+        >
+          {{ annotation.text }}
+        </text>
       </g>
     </svg>
 
@@ -490,6 +566,22 @@ onUnmounted(() => {
       @mousedown="onSelectionMouseDown"
     />
 
+    <input
+      v-if="rect && textDraft"
+      ref="textInputRef"
+      v-model="textDraft.value"
+      class="text-editor"
+      :style="{
+        left: rect.x + textDraft.point.x + 'px',
+        top: rect.y + textDraft.point.y + 'px',
+        color: activeColor,
+      }"
+      spellcheck="false"
+      @mousedown.stop
+      @keydown.stop="onTextDraftKeydown"
+      @blur="commitTextDraft"
+    />
+
     <div
       v-for="handle in handles"
       :key="handle.name"
@@ -554,6 +646,18 @@ onUnmounted(() => {
           <circle cx="12" cy="12" r="7" />
         </svg>
       </button>
+      <button
+        class="icon-btn"
+        :class="{ active: activeTool === 'text' }"
+        title="文字标记"
+        @click="selectTool('text')"
+      >
+        <svg viewBox="0 0 24 24" aria-hidden="true">
+          <path d="M5 5h14" />
+          <path d="M12 5v14" />
+          <path d="M9 19h6" />
+        </svg>
+      </button>
       <div class="color-wrap">
         <button
           class="icon-btn color-btn"
@@ -621,6 +725,21 @@ 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"
@@ -671,6 +790,21 @@ onUnmounted(() => {
   cursor: crosshair;
 }
 
+.text-editor {
+  position: absolute;
+  z-index: 6;
+  min-width: 120px;
+  max-width: 320px;
+  height: 28px;
+  padding: 2px 6px;
+  border: 1px solid currentColor;
+  border-radius: 4px;
+  outline: none;
+  background: rgba(15, 23, 42, 0.72);
+  box-shadow: 0 4px 18px rgba(0, 0, 0, 0.35);
+  font: 600 20px/1.2 -apple-system, BlinkMacSystemFont, "SF Pro Text", sans-serif;
+}
+
 .resize-handle {
   position: absolute;
   width: 10px;
@@ -725,10 +859,10 @@ onUnmounted(() => {
 }
 
 .mark-toolbar {
-  width: 190px;
+  width: 222px;
 }
 .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

@@ -18,6 +18,7 @@ export namespace application {
 	    tool: string;
 	    color: string;
 	    points: Point[];
+	    text?: string;
 
 	    static createFrom(source: any = {}) {
 	        return new Annotation(source);
@@ -28,6 +29,7 @@ export namespace application {
 	        this.tool = source["tool"];
 	        this.color = source["color"];
 	        this.points = this.convertValues(source["points"], Point);
+	        this.text = source["text"];
 	    }
 
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
@@ -53,6 +55,66 @@ 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;
@@ -173,6 +235,7 @@ export namespace domain {
 	    s3: S3Config;
 	    ssh: SSHConfig;
 	    llm: LLMConfig;
+	    ocr: OCRConfig;
 
 	    static createFrom(source: any = {}) {
 	        return new AppConfig(source);
@@ -185,6 +248,7 @@ 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 {
@@ -209,6 +273,8 @@ export namespace domain {
 
 
 
+
+
 }
 
 export namespace main {

go.mod

@@ -12,6 +12,7 @@ require (
 	golang.design/x/clipboard v0.7.0
 	golang.design/x/hotkey v0.4.1
 	golang.org/x/crypto v0.33.0
+	golang.org/x/image v0.12.0
 )
 
 require (
@@ -52,7 +53,6 @@ require (
 	github.com/wailsapp/go-webview2 v1.0.22 // indirect
 	github.com/wailsapp/mimetype v1.4.1 // indirect
 	golang.org/x/exp v0.0.0-20190731235908-ec7cb31e5a56 // indirect
-	golang.org/x/image v0.12.0 // indirect
 	golang.org/x/mobile v0.0.0-20230301163155-e0f57694e12c // indirect
 	golang.org/x/net v0.35.0 // indirect
 	golang.org/x/sys v0.30.0 // indirect

internal/application/annotation.go

@@ -8,8 +8,15 @@ import (
 	"image/draw"
 	"image/png"
 	"math"
+	"os"
 	"strconv"
 	"strings"
+	"sync"
+
+	xfont "golang.org/x/image/font"
+	"golang.org/x/image/font/basicfont"
+	"golang.org/x/image/font/opentype"
+	"golang.org/x/image/math/fixed"
 )
 
 // Annotation describes a user-drawn mark relative to the selected screenshot.
@@ -18,6 +25,7 @@ type Annotation struct {
 	Tool   string  `json:"tool"`
 	Color  string  `json:"color"`
 	Points []Point `json:"points"`
+	Text   string  `json:"text,omitempty"`
 }
 
 type Point struct {
@@ -55,6 +63,8 @@ func ApplyAnnotations(pngBytes []byte, annotations []Annotation, scale float64)
 			drawRectOutline(dst, ann.Points, scale, width, c)
 		case "ellipse":
 			drawEllipseOutline(dst, ann.Points, scale, width, c)
+		case "text":
+			drawTextAnnotation(dst, ann, scale, c)
 		}
 	}
 
@@ -180,3 +190,90 @@ func ordered(a, b float64) (float64, float64) {
 	}
 	return b, a
 }
+
+func drawTextAnnotation(img *image.RGBA, ann Annotation, scale float64, c color.RGBA) {
+	if len(ann.Points) == 0 {
+		return
+	}
+	text := strings.TrimSpace(ann.Text)
+	if text == "" {
+		return
+	}
+	face := annotationFontFace(20 * scale)
+	if face == nil {
+		face = basicfont.Face7x13
+	}
+
+	origin := scalePoint(ann.Points[0], scale)
+	metrics := face.Metrics()
+	lineHeight := metrics.Height
+	if lineHeight <= 0 {
+		lineHeight = fixed.I(int(math.Ceil(24 * scale)))
+	}
+	d := &xfont.Drawer{
+		Dst:  img,
+		Src:  image.NewUniform(c),
+		Face: face,
+	}
+	baselineY := fixed.I(int(math.Round(origin.Y))) + metrics.Ascent
+	x := fixed.I(int(math.Round(origin.X)))
+	for _, line := range strings.Split(text, "\n") {
+		line = strings.TrimRight(line, "\r")
+		if line != "" {
+			d.Dot = fixed.Point26_6{X: x, Y: baselineY}
+			d.DrawString(line)
+		}
+		baselineY += lineHeight
+	}
+}
+
+var (
+	annotationFontOnce sync.Once
+	annotationFont     *opentype.Font
+)
+
+func annotationFontFace(size float64) xfont.Face {
+	if size <= 0 {
+		size = 20
+	}
+	annotationFontOnce.Do(func() {
+		annotationFont = loadAnnotationFont()
+	})
+	if annotationFont == nil {
+		return basicfont.Face7x13
+	}
+	face, err := opentype.NewFace(annotationFont, &opentype.FaceOptions{
+		Size:    size,
+		DPI:     72,
+		Hinting: xfont.HintingFull,
+	})
+	if err != nil {
+		return basicfont.Face7x13
+	}
+	return face
+}
+
+func loadAnnotationFont() *opentype.Font {
+	paths := []string{
+		"/System/Library/Fonts/Supplemental/Arial Unicode.ttf",
+		"/Library/Fonts/Arial Unicode.ttf",
+		"/System/Library/Fonts/Hiragino Sans GB.ttc",
+		"/System/Library/Fonts/PingFang.ttc",
+		"/System/Library/Fonts/Helvetica.ttc",
+	}
+	for _, path := range paths {
+		data, err := os.ReadFile(path)
+		if err != nil {
+			continue
+		}
+		if collection, err := opentype.ParseCollection(data); err == nil && collection.NumFonts() > 0 {
+			if font, err := collection.Font(0); err == nil {
+				return font
+			}
+		}
+		if font, err := opentype.Parse(data); err == nil {
+			return font
+		}
+	}
+	return nil
+}

internal/application/annotation_test.go

@@ -51,3 +51,45 @@ func TestApplyAnnotationsNoAnnotationsReturnsOriginalBytes(t *testing.T) {
 		t.Fatalf("expected original bytes")
 	}
 }
+
+func TestApplyAnnotationsDrawsTextIntoPNG(t *testing.T) {
+	src := image.NewRGBA(image.Rect(0, 0, 120, 80))
+	draw.Draw(src, src.Bounds(), &image.Uniform{C: color.White}, image.Point{}, draw.Src)
+
+	var buf bytes.Buffer
+	if err := png.Encode(&buf, src); err != nil {
+		t.Fatalf("encode source: %v", err)
+	}
+
+	out, err := ApplyAnnotations(buf.Bytes(), []Annotation{
+		{
+			Tool:  "text",
+			Color: "#ef4444",
+			Points: []Point{
+				{X: 10, Y: 10},
+			},
+			Text: "T",
+		},
+	}, 1)
+	if err != nil {
+		t.Fatalf("apply annotations: %v", err)
+	}
+
+	img, err := png.Decode(bytes.NewReader(out))
+	if err != nil {
+		t.Fatalf("decode output: %v", err)
+	}
+	found := false
+	for y := 8; y < 40 && !found; y++ {
+		for x := 8; x < 40; x++ {
+			got := color.RGBAModel.Convert(img.At(x, y)).(color.RGBA)
+			if got.R > 180 && got.G < 180 && got.B < 180 {
+				found = true
+				break
+			}
+		}
+	}
+	if !found {
+		t.Fatalf("expected red text pixels near annotation point")
+	}
+}

internal/application/capture_ocr.go

@@ -0,0 +1,57 @@
+package application
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"github.com/mmmy/snapgo/internal/infrastructure/clipboard"
+)
+
+// OCRRecognizer describes a provider capable of extracting text from a PNG
+// screenshot.
+type OCRRecognizer interface {
+	RecognizeText(ctx context.Context, pngBytes []byte) (string, error)
+}
+
+// CaptureOCRService wires screenshot bytes -> OCR provider -> clipboard. It
+// leaves progress reporting to the caller so native and web overlays can share
+// the same status HUD.
+type CaptureOCRService struct {
+	Recognizer OCRRecognizer
+	Clipboard  clipboard.Writer
+}
+
+// Recognize asks the configured OCR provider to extract text from the PNG.
+func (s *CaptureOCRService) Recognize(ctx context.Context, pngBytes []byte) (string, error) {
+	if s.Recognizer == nil {
+		return "", fmt.Errorf("ocr is not configured")
+	}
+	if len(pngBytes) == 0 {
+		return "", fmt.Errorf("empty screenshot")
+	}
+	text, err := s.Recognizer.RecognizeText(ctx, pngBytes)
+	if err != nil {
+		return "", err
+	}
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return "", fmt.Errorf("ocr result is empty")
+	}
+	return text, nil
+}
+
+// CopyText writes the extracted text to the clipboard.
+func (s *CaptureOCRService) CopyText(_ context.Context, text string) error {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return fmt.Errorf("empty ocr text")
+	}
+	if s.Clipboard == nil {
+		return fmt.Errorf("clipboard is not configured")
+	}
+	if err := s.Clipboard.WriteText(text); err != nil {
+		return fmt.Errorf("clipboard write failed: %w", err)
+	}
+	return nil
+}

internal/application/capture_ocr_test.go

@@ -0,0 +1,50 @@
+package application
+
+import (
+	"context"
+	"testing"
+)
+
+type fakeOCRRecognizer struct {
+	image []byte
+	text  string
+}
+
+func (f *fakeOCRRecognizer) RecognizeText(_ context.Context, pngBytes []byte) (string, error) {
+	f.image = append([]byte(nil), pngBytes...)
+	if f.text == "" {
+		return "extracted text", nil
+	}
+	return f.text, nil
+}
+
+func TestCaptureOCRServiceRecognizesAndCopies(t *testing.T) {
+	ctx := context.Background()
+	recognizer := &fakeOCRRecognizer{}
+	clip := &fakeClipboard{}
+	svc := &CaptureOCRService{Recognizer: recognizer, Clipboard: clip}
+
+	text, err := svc.Recognize(ctx, []byte("png"))
+	if err != nil {
+		t.Fatalf("recognize: %v", err)
+	}
+	if string(recognizer.image) != "png" {
+		t.Fatalf("expected screenshot bytes forwarded, got %q", string(recognizer.image))
+	}
+	if text != "extracted text" {
+		t.Fatalf("expected extracted text, got %q", text)
+	}
+	if err := svc.CopyText(ctx, text); err != nil {
+		t.Fatalf("copy text: %v", err)
+	}
+	if clip.text != "extracted text" {
+		t.Fatalf("expected ocr text copied, got %q", clip.text)
+	}
+}
+
+func TestCaptureOCRServiceRejectsEmptyResult(t *testing.T) {
+	svc := &CaptureOCRService{Recognizer: &fakeOCRRecognizer{text: " \n "}}
+	if _, err := svc.Recognize(context.Background(), []byte("png")); err == nil {
+		t.Fatalf("expected empty OCR result to fail")
+	}
+}

internal/domain/config.go

@@ -107,6 +107,29 @@ type LLMConfig struct {
 	Providers      map[string]LLMProviderConfig `json:"providers"`
 }
 
+// OCRProviderConfig stores one cloud OCR endpoint that accepts a screenshot
+// image and returns extracted text. Aliyun and Volcengine both authenticate
+// with an AccessKey pair, but their signing schemes use slightly different
+// endpoint metadata; keeping Region/Service/Action/Version configurable lets
+// the presets track official API changes without a schema rewrite.
+type OCRProviderConfig struct {
+	Label           string `json:"label"`
+	Endpoint        string `json:"endpoint"`
+	AccessKeyID     string `json:"accessKeyId"`
+	AccessKeySecret string `json:"accessKeySecret"`
+	Region          string `json:"region"`
+	Service         string `json:"service"`
+	Action          string `json:"action"`
+	Version         string `json:"version"`
+	TimeoutSecs     int    `json:"timeoutSecs"`
+}
+
+// OCRConfig controls screenshot text extraction.
+type OCRConfig struct {
+	ActiveProvider string                       `json:"activeProvider"`
+	Providers      map[string]OCRProviderConfig `json:"providers"`
+}
+
 // SSH authentication method identifiers stored in SSHConfig.AuthMethod.
 const (
 	// SSHAuthBuiltin is the legacy combined method (password → agent → key
@@ -129,6 +152,12 @@ const (
 	LLMProviderOpenAI = "openai"
 )
 
+// Built-in OCR provider identifiers.
+const (
+	OCRProviderAliyun     = "aliyun"
+	OCRProviderVolcengine = "volcengine"
+)
+
 // Theme preference identifiers stored in AppConfig.Theme.
 const (
 	ThemeAuto  = "auto"
@@ -172,6 +201,9 @@ type AppConfig struct {
 
 	// LLM holds provider settings for the "copy summary" screenshot action.
 	LLM LLMConfig `json:"llm"`
+
+	// OCR holds provider settings for the "extract text" screenshot action.
+	OCR OCRConfig `json:"ocr"`
 }
 
 // DefaultAppConfig returns sane zero-value defaults used on first launch.
@@ -190,6 +222,7 @@ func DefaultAppConfig() AppConfig {
 			StrictHostKey:      false,
 		},
 		LLM: DefaultLLMConfig(),
+		OCR: DefaultOCRConfig(),
 	}
 	cfg.Normalize()
 	return cfg
@@ -234,6 +267,33 @@ func DefaultLLMConfig() LLMConfig {
 	}
 }
 
+// DefaultOCRConfig returns the built-in OCR provider presets. Users only need
+// to fill AccessKey credentials for the common regions/actions, while advanced
+// accounts can still override endpoint metadata from the settings UI.
+func DefaultOCRConfig() OCRConfig {
+	return OCRConfig{
+		ActiveProvider: OCRProviderAliyun,
+		Providers: map[string]OCRProviderConfig{
+			OCRProviderAliyun: {
+				Label:       "阿里云文字识别",
+				Endpoint:    "https://ocr-api.cn-hangzhou.aliyuncs.com",
+				Action:      "RecognizeGeneral",
+				Version:     "2021-07-07",
+				TimeoutSecs: 30,
+			},
+			OCRProviderVolcengine: {
+				Label:       "火山引擎文字识别",
+				Endpoint:    "https://visual.volcengineapi.com",
+				Region:      "cn-north-1",
+				Service:     "cv",
+				Action:      "OCRNormal",
+				Version:     "2020-08-26",
+				TimeoutSecs: 30,
+			},
+		},
+	}
+}
+
 // Normalize fills defaults into configs written by older app versions while
 // preserving any user-provided provider fields.
 func (c *AppConfig) Normalize() {
@@ -295,6 +355,43 @@ func (c *AppConfig) Normalize() {
 		}
 		c.LLM.Providers[id] = current
 	}
+
+	defaultOCR := DefaultOCRConfig()
+	if c.OCR.ActiveProvider == "" {
+		c.OCR.ActiveProvider = defaultOCR.ActiveProvider
+	}
+	if c.OCR.Providers == nil {
+		c.OCR.Providers = map[string]OCRProviderConfig{}
+	}
+	for id, def := range defaultOCR.Providers {
+		current, ok := c.OCR.Providers[id]
+		if !ok {
+			c.OCR.Providers[id] = def
+			continue
+		}
+		if current.Label == "" {
+			current.Label = def.Label
+		}
+		if current.Endpoint == "" {
+			current.Endpoint = def.Endpoint
+		}
+		if current.Region == "" {
+			current.Region = def.Region
+		}
+		if current.Service == "" {
+			current.Service = def.Service
+		}
+		if current.Action == "" {
+			current.Action = def.Action
+		}
+		if current.Version == "" {
+			current.Version = def.Version
+		}
+		if current.TimeoutSecs == 0 {
+			current.TimeoutSecs = def.TimeoutSecs
+		}
+		c.OCR.Providers[id] = current
+	}
 }
 
 // IsS3Configured reports whether the user has filled the mandatory S3 fields.
@@ -329,3 +426,32 @@ func (c AppConfig) IsLLMConfigured() bool {
 	_, provider, ok := c.ActiveLLMProvider()
 	return ok && provider.BaseURL != "" && provider.APIKey != "" && provider.Model != ""
 }
+
+// ActiveOCRProvider returns the selected OCR provider config plus a boolean
+// indicating whether the selection exists.
+func (c AppConfig) ActiveOCRProvider() (string, OCRProviderConfig, bool) {
+	id := c.OCR.ActiveProvider
+	if id == "" {
+		id = OCRProviderAliyun
+	}
+	provider, ok := c.OCR.Providers[id]
+	return id, provider, ok
+}
+
+// IsOCRConfigured reports whether the selected OCR provider has the fields
+// required to sign and send a request.
+func (c AppConfig) IsOCRConfigured() bool {
+	id, provider, ok := c.ActiveOCRProvider()
+	if !ok ||
+		provider.Endpoint == "" ||
+		provider.AccessKeyID == "" ||
+		provider.AccessKeySecret == "" ||
+		provider.Action == "" ||
+		provider.Version == "" {
+		return false
+	}
+	if id == OCRProviderVolcengine && (provider.Region == "" || provider.Service == "") {
+		return false
+	}
+	return true
+}

internal/infrastructure/ocr/client.go

@@ -0,0 +1,568 @@
+// Package ocr contains cloud OCR adapters.
+package ocr
+
+import (
+	"bytes"
+	"context"
+	"crypto/hmac"
+	"crypto/rand"
+	"crypto/sha256"
+	"encoding/base64"
+	"encoding/hex"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/mmmy/snapgo/internal/application"
+	"github.com/mmmy/snapgo/internal/domain"
+)
+
+// Client calls one configured OCR provider.
+type Client struct {
+	providerID string
+	cfg        domain.OCRProviderConfig
+	httpClient *http.Client
+	now        func() time.Time
+	nonce      func() string
+}
+
+var _ application.OCRRecognizer = (*Client)(nil)
+
+// NewClient validates cfg and returns a reusable OCR client.
+func NewClient(providerID string, cfg domain.OCRProviderConfig) (*Client, error) {
+	if strings.TrimSpace(cfg.Endpoint) == "" {
+		return nil, fmt.Errorf("ocr endpoint is required")
+	}
+	if strings.TrimSpace(cfg.AccessKeyID) == "" {
+		return nil, fmt.Errorf("ocr access key id is required")
+	}
+	if strings.TrimSpace(cfg.AccessKeySecret) == "" {
+		return nil, fmt.Errorf("ocr access key secret is required")
+	}
+	if strings.TrimSpace(cfg.Action) == "" {
+		return nil, fmt.Errorf("ocr action is required")
+	}
+	if strings.TrimSpace(cfg.Version) == "" {
+		return nil, fmt.Errorf("ocr version is required")
+	}
+	switch providerID {
+	case domain.OCRProviderAliyun:
+	case domain.OCRProviderVolcengine:
+		if strings.TrimSpace(cfg.Region) == "" {
+			return nil, fmt.Errorf("volcengine ocr region is required")
+		}
+		if strings.TrimSpace(cfg.Service) == "" {
+			return nil, fmt.Errorf("volcengine ocr service is required")
+		}
+	default:
+		return nil, fmt.Errorf("unsupported ocr provider %q", providerID)
+	}
+	timeout := cfg.TimeoutSecs
+	if timeout <= 0 {
+		timeout = 30
+	}
+	return &Client{
+		providerID: providerID,
+		cfg:        cfg,
+		httpClient: &http.Client{Timeout: time.Duration(timeout) * time.Second},
+		now:        time.Now,
+		nonce:      randomNonce,
+	}, nil
+}
+
+// RecognizeText extracts visible text from a PNG screenshot.
+func (c *Client) RecognizeText(ctx context.Context, pngBytes []byte) (string, error) {
+	if len(pngBytes) == 0 {
+		return "", fmt.Errorf("empty screenshot")
+	}
+	switch c.providerID {
+	case domain.OCRProviderAliyun:
+		return c.recognizeAliyun(ctx, pngBytes)
+	case domain.OCRProviderVolcengine:
+		return c.recognizeVolcengine(ctx, pngBytes)
+	default:
+		return "", fmt.Errorf("unsupported ocr provider %q", c.providerID)
+	}
+}
+
+func (c *Client) recognizeAliyun(ctx context.Context, pngBytes []byte) (string, error) {
+	endpoint, err := parseEndpoint(c.cfg.Endpoint)
+	if err != nil {
+		return "", err
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, endpoint.String(), bytes.NewReader(pngBytes))
+	if err != nil {
+		return "", fmt.Errorf("build aliyun ocr request: %w", err)
+	}
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Content-Type", "application/octet-stream")
+	c.signAliyun(req, pngBytes)
+	return c.doOCRRequest(req, "aliyun ocr")
+}
+
+func (c *Client) recognizeVolcengine(ctx context.Context, pngBytes []byte) (string, error) {
+	endpoint, err := parseEndpoint(c.cfg.Endpoint)
+	if err != nil {
+		return "", err
+	}
+	query := endpoint.Query()
+	query.Set("Action", c.cfg.Action)
+	query.Set("Version", c.cfg.Version)
+	endpoint.RawQuery = query.Encode()
+
+	body := map[string]string{
+		"image_base64": base64.StdEncoding.EncodeToString(pngBytes),
+	}
+	payload, err := json.Marshal(body)
+	if err != nil {
+		return "", fmt.Errorf("marshal volcengine ocr request: %w", err)
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, endpoint.String(), bytes.NewReader(payload))
+	if err != nil {
+		return "", fmt.Errorf("build volcengine ocr request: %w", err)
+	}
+	req.Header.Set("Accept", "application/json")
+	req.Header.Set("Content-Type", "application/json")
+	c.signVolcengine(req, payload)
+	return c.doOCRRequest(req, "volcengine ocr")
+}
+
+func (c *Client) doOCRRequest(req *http.Request, label string) (string, error) {
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return "", fmt.Errorf("%s request: %w", label, err)
+	}
+	defer resp.Body.Close()
+	data, _ := io.ReadAll(io.LimitReader(resp.Body, 8<<20))
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return "", fmt.Errorf("%s status %d: %s", label, resp.StatusCode, compactBody(data))
+	}
+	text, err := parseOCRText(data)
+	if err != nil {
+		return "", fmt.Errorf("%s response: %w", label, err)
+	}
+	return text, nil
+}
+
+func (c *Client) signAliyun(req *http.Request, payload []byte) {
+	now := c.now().UTC()
+	payloadHash := sha256Hex(payload)
+	nonce := c.nonce()
+
+	req.Header.Set("x-acs-action", c.cfg.Action)
+	req.Header.Set("x-acs-version", c.cfg.Version)
+	req.Header.Set("x-acs-date", now.Format("2006-01-02T15:04:05Z"))
+	req.Header.Set("x-acs-signature-nonce", nonce)
+	req.Header.Set("x-acs-content-sha256", payloadHash)
+
+	signedHeaders := []string{
+		"content-type",
+		"host",
+		"x-acs-action",
+		"x-acs-content-sha256",
+		"x-acs-date",
+		"x-acs-signature-nonce",
+		"x-acs-version",
+	}
+	canonicalHeaders := canonicalHeaders(req, signedHeaders)
+	canonicalRequest := strings.Join([]string{
+		req.Method,
+		canonicalURI(req.URL),
+		canonicalQuery(req.URL),
+		canonicalHeaders,
+		strings.Join(signedHeaders, ";"),
+		payloadHash,
+	}, "\n")
+	stringToSign := "ACS3-HMAC-SHA256\n" + sha256Hex([]byte(canonicalRequest))
+	signature := hmacSHA256Hex([]byte(c.cfg.AccessKeySecret), []byte(stringToSign))
+	req.Header.Set(
+		"Authorization",
+		fmt.Sprintf("ACS3-HMAC-SHA256 Credential=%s,SignedHeaders=%s,Signature=%s",
+			c.cfg.AccessKeyID,
+			strings.Join(signedHeaders, ";"),
+			signature,
+		),
+	)
+}
+
+func (c *Client) signVolcengine(req *http.Request, payload []byte) {
+	now := c.now().UTC()
+	xDate := now.Format("20060102T150405Z")
+	shortDate := now.Format("20060102")
+	payloadHash := sha256Hex(payload)
+
+	req.Header.Set("X-Date", xDate)
+	req.Header.Set("X-Content-Sha256", payloadHash)
+
+	signedHeaders := []string{
+		"content-type",
+		"host",
+		"x-content-sha256",
+		"x-date",
+	}
+	canonicalHeaders := canonicalHeaders(req, signedHeaders)
+	canonicalRequest := strings.Join([]string{
+		req.Method,
+		canonicalURI(req.URL),
+		canonicalQuery(req.URL),
+		canonicalHeaders,
+		strings.Join(signedHeaders, ";"),
+		payloadHash,
+	}, "\n")
+	scope := strings.Join([]string{shortDate, c.cfg.Region, c.cfg.Service, "request"}, "/")
+	stringToSign := strings.Join([]string{
+		"HMAC-SHA256",
+		xDate,
+		scope,
+		sha256Hex([]byte(canonicalRequest)),
+	}, "\n")
+	signingKey := volcengineSigningKey(c.cfg.AccessKeySecret, shortDate, c.cfg.Region, c.cfg.Service)
+	signature := hmacSHA256Hex(signingKey, []byte(stringToSign))
+	req.Header.Set(
+		"Authorization",
+		fmt.Sprintf("HMAC-SHA256 Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+			c.cfg.AccessKeyID,
+			scope,
+			strings.Join(signedHeaders, ";"),
+			signature,
+		),
+	)
+}
+
+func parseEndpoint(raw string) (*url.URL, error) {
+	endpoint := strings.TrimSpace(raw)
+	if endpoint == "" {
+		return nil, fmt.Errorf("ocr endpoint is required")
+	}
+	if !strings.Contains(endpoint, "://") {
+		endpoint = "https://" + endpoint
+	}
+	parsed, err := url.Parse(endpoint)
+	if err != nil {
+		return nil, fmt.Errorf("parse ocr endpoint: %w", err)
+	}
+	if parsed.Scheme == "" || parsed.Host == "" {
+		return nil, fmt.Errorf("invalid ocr endpoint %q", raw)
+	}
+	if parsed.Path == "" {
+		parsed.Path = "/"
+	}
+	return parsed, nil
+}
+
+func parseOCRText(data []byte) (string, error) {
+	var root any
+	if err := json.Unmarshal(data, &root); err != nil {
+		return "", fmt.Errorf("decode json: %w", err)
+	}
+	if msg := responseError(root); msg != "" {
+		return "", errors.New(msg)
+	}
+	parts := collectOCRParts(root, "")
+	if len(parts) == 0 {
+		return "", fmt.Errorf("no text found")
+	}
+	return strings.Join(dedupeNonEmpty(parts), "\n"), nil
+}
+
+func responseError(v any) string {
+	obj, ok := v.(map[string]any)
+	if !ok {
+		return ""
+	}
+	if meta, ok := obj["ResponseMetadata"].(map[string]any); ok {
+		if errObj, ok := meta["Error"].(map[string]any); ok {
+			if msg := stringValue(errObj["Message"]); msg != "" {
+				return msg
+			}
+			if code := stringValue(errObj["Code"]); code != "" {
+				return code
+			}
+		}
+	}
+	if errObj, ok := obj["Error"].(map[string]any); ok {
+		if msg := stringValue(errObj["Message"]); msg != "" {
+			return msg
+		}
+		if msg := stringValue(errObj["message"]); msg != "" {
+			return msg
+		}
+	}
+	if code, ok := numericCode(obj["code"]); ok && code != 0 && code != 10000 {
+		if msg := stringValue(obj["message"]); msg != "" {
+			return msg
+		}
+		if msg := stringValue(obj["msg"]); msg != "" {
+			return msg
+		}
+		return fmt.Sprintf("provider code %.0f", code)
+	}
+	if code := stringValue(obj["Code"]); code != "" && !isSuccessCode(code) {
+		if msg := stringValue(obj["Message"]); msg != "" {
+			return msg
+		}
+		return code
+	}
+	return ""
+}
+
+func collectOCRParts(v any, parentKey string) []string {
+	switch value := v.(type) {
+	case string:
+		text := strings.TrimSpace(value)
+		if text == "" {
+			return nil
+		}
+		if looksLikeJSON(text) {
+			var nested any
+			if err := json.Unmarshal([]byte(text), &nested); err == nil {
+				return collectOCRParts(nested, parentKey)
+			}
+		}
+		if isTextKey(parentKey) || isContainerTextKey(parentKey) {
+			return []string{text}
+		}
+		return nil
+	case []any:
+		parts := make([]string, 0, len(value))
+		for _, item := range value {
+			parts = append(parts, collectOCRParts(item, parentKey)...)
+		}
+		return parts
+	case map[string]any:
+		parts := make([]string, 0)
+		for _, key := range priorityOCRKeys() {
+			if child, ok := value[key]; ok {
+				parts = append(parts, collectOCRParts(child, key)...)
+			}
+		}
+		keys := make([]string, 0, len(value))
+		for key := range value {
+			keys = append(keys, key)
+		}
+		sort.Strings(keys)
+		for _, key := range keys {
+			if isPriorityOCRKey(key) || isMetadataKey(key) {
+				continue
+			}
+			parts = append(parts, collectOCRParts(value[key], key)...)
+		}
+		return parts
+	default:
+		return nil
+	}
+}
+
+func priorityOCRKeys() []string {
+	return []string{
+		"Data",
+		"data",
+		"Result",
+		"result",
+		"content",
+		"Content",
+		"text",
+		"Text",
+		"DetectedText",
+		"detected_text",
+		"line_text",
+		"LineText",
+		"line_texts",
+		"LineTexts",
+		"word",
+		"Word",
+		"words",
+		"Words",
+		"words_result",
+		"WordsResult",
+		"prism_wordsInfo",
+		"prism_words_info",
+		"ocr_infos",
+		"OCRInfos",
+		"items",
+		"Items",
+		"blocks",
+		"Blocks",
+		"regions",
+		"Regions",
+	}
+}
+
+func isPriorityOCRKey(key string) bool {
+	for _, item := range priorityOCRKeys() {
+		if item == key {
+			return true
+		}
+	}
+	return false
+}
+
+func isTextKey(key string) bool {
+	switch normalizeKey(key) {
+	case "content", "text", "detectedtext", "linetext", "word", "words", "value":
+		return true
+	default:
+		return false
+	}
+}
+
+func isContainerTextKey(key string) bool {
+	switch normalizeKey(key) {
+	case "data", "result", "linetexts", "texts":
+		return true
+	default:
+		return false
+	}
+}
+
+func isMetadataKey(key string) bool {
+	switch normalizeKey(key) {
+	case "requestid", "request", "code", "status", "statuscode", "success",
+		"error", "errors", "message", "msg", "cost", "angle", "probability",
+		"confidence", "height", "width", "left", "top", "right", "bottom",
+		"x", "y", "responsemetadata":
+		return true
+	default:
+		return false
+	}
+}
+
+func normalizeKey(key string) string {
+	key = strings.ToLower(key)
+	key = strings.ReplaceAll(key, "_", "")
+	key = strings.ReplaceAll(key, "-", "")
+	return key
+}
+
+func dedupeNonEmpty(parts []string) []string {
+	seen := map[string]struct{}{}
+	out := make([]string, 0, len(parts))
+	for _, part := range parts {
+		for _, line := range strings.Split(part, "\n") {
+			line = strings.TrimSpace(line)
+			if line == "" {
+				continue
+			}
+			if _, ok := seen[line]; ok {
+				continue
+			}
+			seen[line] = struct{}{}
+			out = append(out, line)
+		}
+	}
+	return out
+}
+
+func looksLikeJSON(text string) bool {
+	return strings.HasPrefix(text, "{") || strings.HasPrefix(text, "[")
+}
+
+func stringValue(v any) string {
+	if s, ok := v.(string); ok {
+		return strings.TrimSpace(s)
+	}
+	return ""
+}
+
+func numericCode(v any) (float64, bool) {
+	switch n := v.(type) {
+	case float64:
+		return n, true
+	case int:
+		return float64(n), true
+	case json.Number:
+		f, err := n.Float64()
+		return f, err == nil
+	default:
+		return 0, false
+	}
+}
+
+func isSuccessCode(code string) bool {
+	switch strings.ToLower(strings.TrimSpace(code)) {
+	case "", "ok", "success", "200", "10000":
+		return true
+	default:
+		return false
+	}
+}
+
+func canonicalURI(u *url.URL) string {
+	if u == nil || u.EscapedPath() == "" {
+		return "/"
+	}
+	return u.EscapedPath()
+}
+
+func canonicalQuery(u *url.URL) string {
+	if u == nil || u.RawQuery == "" {
+		return ""
+	}
+	values, _ := url.ParseQuery(u.RawQuery)
+	return values.Encode()
+}
+
+func canonicalHeaders(req *http.Request, signedHeaders []string) string {
+	lines := make([]string, 0, len(signedHeaders))
+	for _, key := range signedHeaders {
+		var value string
+		if key == "host" {
+			value = req.URL.Host
+		} else {
+			value = req.Header.Get(key)
+		}
+		lines = append(lines, key+":"+normalizeHeaderValue(value)+"\n")
+	}
+	return strings.Join(lines, "")
+}
+
+func normalizeHeaderValue(value string) string {
+	return strings.Join(strings.Fields(strings.TrimSpace(value)), " ")
+}
+
+func volcengineSigningKey(secret, date, region, service string) []byte {
+	kDate := hmacSHA256([]byte(secret), []byte(date))
+	kRegion := hmacSHA256(kDate, []byte(region))
+	kService := hmacSHA256(kRegion, []byte(service))
+	return hmacSHA256(kService, []byte("request"))
+}
+
+func hmacSHA256(key, data []byte) []byte {
+	mac := hmac.New(sha256.New, key)
+	mac.Write(data)
+	return mac.Sum(nil)
+}
+
+func hmacSHA256Hex(key, data []byte) string {
+	return hex.EncodeToString(hmacSHA256(key, data))
+}
+
+func sha256Hex(data []byte) string {
+	sum := sha256.Sum256(data)
+	return hex.EncodeToString(sum[:])
+}
+
+func randomNonce() string {
+	buf := make([]byte, 16)
+	if _, err := rand.Read(buf); err != nil {
+		return fmt.Sprintf("%d", time.Now().UnixNano())
+	}
+	return hex.EncodeToString(buf)
+}
+
+func compactBody(data []byte) string {
+	text := strings.TrimSpace(string(data))
+	if text == "" {
+		return "<empty body>"
+	}
+	if len(text) > 800 {
+		return text[:800] + "..."
+	}
+	return text
+}

internal/infrastructure/ocr/client_test.go

@@ -0,0 +1,150 @@
+package ocr
+
+import (
+	"bytes"
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"io"
+	"net/http"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/mmmy/snapgo/internal/domain"
+)
+
+type roundTripFunc func(*http.Request) (*http.Response, error)
+
+func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
+	return f(req)
+}
+
+func TestAliyunRecognizeTextSignsRawPNGRequest(t *testing.T) {
+	var requestBody []byte
+	transport := roundTripFunc(func(r *http.Request) (*http.Response, error) {
+		if r.URL.Host != "ocr-api.cn-hangzhou.aliyuncs.com" {
+			t.Fatalf("unexpected host %s", r.URL.Host)
+		}
+		if got := r.Header.Get("x-acs-action"); got != "RecognizeGeneral" {
+			t.Fatalf("unexpected action %q", got)
+		}
+		if got := r.Header.Get("x-acs-version"); got != "2021-07-07" {
+			t.Fatalf("unexpected version %q", got)
+		}
+		if got := r.Header.Get("x-acs-date"); got != "2026-07-08T01:02:03Z" {
+			t.Fatalf("unexpected date %q", got)
+		}
+		if got := r.Header.Get("Authorization"); !strings.Contains(got, "ACS3-HMAC-SHA256 Credential=ak") {
+			t.Fatalf("unexpected auth header %q", got)
+		}
+		var err error
+		requestBody, err = io.ReadAll(r.Body)
+		if err != nil {
+			t.Fatalf("read body: %v", err)
+		}
+		return &http.Response{
+			StatusCode: http.StatusOK,
+			Header:     http.Header{"Content-Type": []string{"application/json"}},
+			Body: io.NopCloser(bytes.NewBufferString(
+				`{"Data":"{\"content\":\"第一行\\n第二行\"}"}`,
+			)),
+		}, nil
+	})
+
+	client, err := NewClient(domain.OCRProviderAliyun, domain.OCRProviderConfig{
+		Endpoint:        "https://ocr-api.cn-hangzhou.aliyuncs.com",
+		AccessKeyID:     "ak",
+		AccessKeySecret: "sk",
+		Action:          "RecognizeGeneral",
+		Version:         "2021-07-07",
+	})
+	if err != nil {
+		t.Fatalf("new client: %v", err)
+	}
+	client.httpClient.Transport = transport
+	client.now = func() time.Time { return time.Date(2026, 7, 8, 1, 2, 3, 0, time.UTC) }
+	client.nonce = func() string { return "nonce" }
+
+	text, err := client.RecognizeText(context.Background(), []byte("png"))
+	if err != nil {
+		t.Fatalf("recognize text: %v", err)
+	}
+	if string(requestBody) != "png" {
+		t.Fatalf("expected raw png body, got %q", string(requestBody))
+	}
+	if text != "第一行\n第二行" {
+		t.Fatalf("unexpected OCR text %q", text)
+	}
+}
+
+func TestVolcengineRecognizeTextSignsBase64JSONRequest(t *testing.T) {
+	var requestBody map[string]string
+	transport := roundTripFunc(func(r *http.Request) (*http.Response, error) {
+		if got := r.URL.Query().Get("Action"); got != "OCRNormal" {
+			t.Fatalf("unexpected action %q", got)
+		}
+		if got := r.URL.Query().Get("Version"); got != "2020-08-26" {
+			t.Fatalf("unexpected version %q", got)
+		}
+		if got := r.Header.Get("X-Date"); got != "20260708T010203Z" {
+			t.Fatalf("unexpected x-date %q", got)
+		}
+		if got := r.Header.Get("Authorization"); !strings.Contains(got, "HMAC-SHA256 Credential=ak/20260708/cn-north-1/cv/request") {
+			t.Fatalf("unexpected auth header %q", got)
+		}
+		if err := json.NewDecoder(r.Body).Decode(&requestBody); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		return &http.Response{
+			StatusCode: http.StatusOK,
+			Header:     http.Header{"Content-Type": []string{"application/json"}},
+			Body: io.NopCloser(bytes.NewBufferString(
+				`{"ResponseMetadata":{"RequestId":"r"},"Result":{"LineTexts":["你好","世界"]}}`,
+			)),
+		}, nil
+	})
+
+	client, err := NewClient(domain.OCRProviderVolcengine, domain.OCRProviderConfig{
+		Endpoint:        "https://visual.volcengineapi.com",
+		AccessKeyID:     "ak",
+		AccessKeySecret: "sk",
+		Region:          "cn-north-1",
+		Service:         "cv",
+		Action:          "OCRNormal",
+		Version:         "2020-08-26",
+	})
+	if err != nil {
+		t.Fatalf("new client: %v", err)
+	}
+	client.httpClient.Transport = transport
+	client.now = func() time.Time { return time.Date(2026, 7, 8, 1, 2, 3, 0, time.UTC) }
+
+	text, err := client.RecognizeText(context.Background(), []byte("png"))
+	if err != nil {
+		t.Fatalf("recognize text: %v", err)
+	}
+	if requestBody["image_base64"] != base64.StdEncoding.EncodeToString([]byte("png")) {
+		t.Fatalf("expected base64 image body, got %#v", requestBody)
+	}
+	if text != "你好\n世界" {
+		t.Fatalf("unexpected OCR text %q", text)
+	}
+}
+
+func TestParseOCRTextSupportsWordsResult(t *testing.T) {
+	text, err := parseOCRText([]byte(`{"data":{"words_result":[{"words":"foo"},{"words":"bar"}]}}`))
+	if err != nil {
+		t.Fatalf("parse ocr text: %v", err)
+	}
+	if text != "foo\nbar" {
+		t.Fatalf("unexpected OCR text %q", text)
+	}
+}
+
+func TestParseOCRTextReturnsProviderError(t *testing.T) {
+	_, err := parseOCRText([]byte(`{"ResponseMetadata":{"Error":{"Code":"BadRequest","Message":"bad image"}}}`))
+	if err == nil || !strings.Contains(err.Error(), "bad image") {
+		t.Fatalf("expected provider error, got %v", err)
+	}
+}

native_overlay_callbacks_darwin.go

@@ -86,6 +86,18 @@ func nativeOverlaySummarize(x, y, w, h C.int, annotationsJSON *C.char) {
 	}()
 }
 
+//export nativeOverlayOCR
+func nativeOverlayOCR(x, y, w, h C.int, annotationsJSON *C.char) {
+	app := consumeNativeOverlayApp()
+	if app == nil {
+		return
+	}
+	result := nativeCaptureResult(x, y, w, h, annotationsJSON)
+	go func() {
+		_ = app.ExtractTextNativeRegion(result)
+	}()
+}
+
 //export nativeOverlayCancel
 func nativeOverlayCancel() {
 	app := consumeNativeOverlayApp()

native_overlay_darwin.go

@@ -16,6 +16,7 @@ extern void nativeOverlayCopy(int x, int y, int w, int h, const char *annotation
 extern void nativeOverlaySave(int x, int y, int w, int h, const char *annotationsJSON, const char *dir);
 extern void nativeOverlaySaveRemote(int x, int y, int w, int h, const char *annotationsJSON);
 extern void nativeOverlaySummarize(int x, int y, int w, int h, const char *annotationsJSON);
+extern void nativeOverlayOCR(int x, int y, int w, int h, const char *annotationsJSON);
 extern void nativeOverlayCancel(void);
 
 static NSWindow *nativeOverlayWindow = nil;
@@ -103,25 +104,35 @@ static id nativeOverlayKeyMonitor = nil;
 @property(strong) NSButton *clipboardButton;
 @property(strong) NSButton *saveButton;
 @property(strong) NSButton *saveRemoteButton;
+@property(strong) NSButton *ocrButton;
 @property(strong) NSButton *summaryButton;
 @property(strong) NSButton *uploadButton;
 @property(strong) NSButton *penButton;
 @property(strong) NSButton *rectButton;
 @property(strong) NSButton *ellipseButton;
+@property(strong) NSButton *textButton;
 @property(strong) NSButton *colorButton;
 @property(strong) NSButton *undoButton;
 @property(strong) NSView *paletteView;
 @property(strong) NSView *actionToolbarBg;
+@property(strong) NSTextField *textEditor;
+@property NSPoint textEditorLocalPoint;
 @property(strong) NSTextField *sizeLabel;
 @property(strong) NSTextField *hintLabel;
 - (void)syncControls;
 - (void)styleControls;
+- (void)selectText;
 - (void)confirmSelection;
 - (void)copySelection;
 - (void)saveSelection;
 - (void)saveRemoteSelection;
+- (void)ocrSelection;
 - (void)summarizeSelection;
 - (void)cancelSelection;
+- (void)beginTextAnnotationAtPoint:(NSPoint)localPoint;
+- (BOOL)isEditingText;
+- (void)commitTextEditor;
+- (void)cancelTextEditor;
 @end
 
 @implementation SnipNativeOverlayView
@@ -138,13 +149,14 @@ static id nativeOverlayKeyMonitor = nil;
         _activeColor = [NSColor colorWithCalibratedRed:239.0/255.0 green:68.0/255.0 blue:68.0/255.0 alpha:1.0];
         _annotations = [NSMutableArray array];
 
-        // Use SnipHoverButton for the 5 action buttons so we get hover-color
+        // Use SnipHoverButton for the action buttons so we get hover-color
         // animation. Annotation buttons stay as plain NSButton because they
         // already have explicit on/off "active" styling.
         _cancelButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(cancelSelection)];
         _clipboardButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(copySelection)];
         _saveButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(saveSelection)];
         _saveRemoteButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(saveRemoteSelection)];
+        _ocrButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(ocrSelection)];
         _summaryButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(summarizeSelection)];
         _uploadButton = [SnipHoverButton buttonWithTitle:@"" target:self action:@selector(confirmSelection)];
         // Tooltip strings shown on hover for each action button.
@@ -153,11 +165,13 @@ static id nativeOverlayKeyMonitor = nil;
         [_clipboardButton setToolTip:@"复制图片"];
         [_saveButton setToolTip:@"保存本地"];
         [_saveRemoteButton setToolTip:@"保存远端"];
+        [_ocrButton setToolTip:@"提取文字"];
         [_summaryButton setToolTip:@"复制总结"];
         [_uploadButton setToolTip:@"上传云端"];
         _penButton = [NSButton buttonWithTitle:@"" target:self action:@selector(selectPen)];
         _rectButton = [NSButton buttonWithTitle:@"" target:self action:@selector(selectRect)];
         _ellipseButton = [NSButton buttonWithTitle:@"" target:self action:@selector(selectEllipse)];
+        _textButton = [NSButton buttonWithTitle:@"" target:self action:@selector(selectText)];
         _colorButton = [NSButton buttonWithTitle:@"" target:self action:@selector(togglePalette)];
         _undoButton = [NSButton buttonWithTitle:@"" target:self action:@selector(undoAnnotation)];
         _paletteView = [[NSView alloc] initWithFrame:NSZeroRect];
@@ -174,10 +188,10 @@ static id nativeOverlayKeyMonitor = nil;
         // Add the action toolbar background BEFORE the buttons so it sits
         // behind them in the view hierarchy (AppKit z-order = subview order).
         [self addSubview:_actionToolbarBg];
-        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _colorButton, _undoButton, _paletteView, _sizeLabel, _hintLabel]) {
+        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _ocrButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _textButton, _colorButton, _undoButton, _paletteView, _sizeLabel, _hintLabel]) {
             [self addSubview:view];
         }
-        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _colorButton, _undoButton, _paletteView, _actionToolbarBg]) {
+        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _ocrButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _textButton, _colorButton, _undoButton, _paletteView, _actionToolbarBg]) {
             [view setHidden:YES];
         }
         [_sizeLabel setHidden:YES];
@@ -240,8 +254,8 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (void)styleControls {
-    // Cancel / Copy / Save / Save-remote / Upload — square icon buttons
+    // Cancel / Copy / Save / Save-remote / OCR / Summary / Upload — square icon buttons
-    // rendered from the user-supplied SVG assets. All five default to white
+    // rendered from the user-supplied SVG assets. All actions default to white
     // and animate to a per-action accent color on hover (cancel = red,
     // others = blue). The base "white default" replaces the previous blue
     // upload tint so the toolbar reads as a uniform icon row.
@@ -251,6 +265,7 @@ static id nativeOverlayKeyMonitor = nil;
     // save-remote.svg — provided by the user; its content is the same arrow
     // icon as the previous upload, so we reuse it verbatim here.
     NSImage *saveRemoteIcon = [self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M481.749333 353.792c16.682667-16.64 43.690667-16.64 60.373334 0l120.917333 120.832 3.541333 4.010667a42.666667 42.666667 0 0 1-63.872 56.32L554.666667 486.954667V896a42.666667 42.666667 0 0 1-85.333334 0v-409.173333l-48.170666 48.128a42.666667 42.666667 0 0 1-60.330667 0l-3.541333-4.010667a42.666667 42.666667 0 0 1 3.541333-56.32zM512 85.333333c122.538667 0 227.84 73.813333 273.92 179.370667A213.333333 213.333333 0 0 1 725.333333 682.666667a42.666667 42.666667 0 0 1-4.992-85.034667L725.333333 597.333333a128 128 0 0 0 36.394667-250.794666l-38.144-11.264-15.914667-36.437334a213.376 213.376 0 0 0-407.296 58.026667l-7.381333 58.368-57.173333 13.824A85.418667 85.418667 0 0 0 256 597.333333h42.666667a42.666667 42.666667 0 0 1 0 85.333334H256a170.666667 170.666667 0 0 1-40.277333-336.554667A298.709333 298.709333 0 0 1 512 85.333333z' fill='white'/></svg>"];
+    NSImage *ocrIcon = [self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M192 160h192v64H256v128h-64V160zM640 160h192v192h-64V224H640v-64zM256 672v128h128v64H192V672h64zM832 672v192H640v-64h128V672h64zM469.333333 288h85.333334l170.666666 448h-78.933333l-39.253333-106.666667H416.853333L377.6 736H298.666667l170.666666-448zM439.466667 565.333333h144.896L512 368.981333 439.466667 565.333333z' fill='white'/></svg>"];
     NSImage *summaryIcon = [self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M256 128h448l192 192v576H256V128z m64 64v640h512V352H672V192H320z m416 45.248V288h50.752L736 237.248zM384 448h384v64H384v-64z m0 128h384v64H384v-64z m0 128h256v64H384v-64zM192 256v704h512v64H128V256h64z' fill='white'/></svg>"];
     // upload.svg — newly replaced "send/cloud" icon supplied by the user.
     NSImage *uploadIcon = [self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M550.528 544.128L640 539.776V678.4l178.005333-178.005333L640 322.389333v129.024l-72.618667 10.922667c-155.52 23.424-251.733333 73.557333-312.874666 164.437333 84.906667-50.602667 178.261333-76.928 296.021333-82.645333zM554.666667 629.376c-27.392 1.322667-53.034667 3.968-77.141334 7.808l-8.192 1.365333c-136.704 23.637333-224.810667 87.168-310.954666 176.128-26.154667 27.008-51.882667 59.648-51.882667 59.648-14.848 18.176-24.021333 14.037333-20.352-9.173333 0 0 4.394667-31.402667 11.690667-65.792C144.938667 577.066667 250.581333 423.68 554.666667 377.941333V209.066667a38.4 38.4 0 0 1 65.536-27.136l291.328 291.285333a38.4 38.4 0 0 1 0 54.314667l-291.328 291.285333A38.4 38.4 0 0 1 554.666667 791.637333v-162.261333z' fill='white'/></svg>"];
@@ -259,10 +274,11 @@ static id nativeOverlayKeyMonitor = nil;
     [self styleIconButton:_clipboardButton image:copyIcon];
     [self styleIconButton:_saveButton image:saveIcon];
     [self styleIconButton:_saveRemoteButton image:saveRemoteIcon];
+    [self styleIconButton:_ocrButton image:ocrIcon];
     [self styleIconButton:_summaryButton image:summaryIcon];
     [self styleIconButton:_uploadButton image:uploadIcon];
 
-    // Configure hover colors for the 5 action buttons. White is the shared
+    // Configure hover colors for the action buttons. White is the shared
     // base; cancel turns red on hover and the rest turn blue, providing a
     // glance-able cue for destructive vs. constructive actions.
     NSColor *baseWhite = [NSColor whiteColor];
@@ -272,18 +288,21 @@ static id nativeOverlayKeyMonitor = nil;
     SnipHoverButton *clipboardHB  = (SnipHoverButton *)_clipboardButton;
     SnipHoverButton *saveHB       = (SnipHoverButton *)_saveButton;
     SnipHoverButton *saveRemoteHB = (SnipHoverButton *)_saveRemoteButton;
+    SnipHoverButton *ocrHB        = (SnipHoverButton *)_ocrButton;
     SnipHoverButton *summaryHB    = (SnipHoverButton *)_summaryButton;
     SnipHoverButton *uploadHB     = (SnipHoverButton *)_uploadButton;
     cancelHB.baseColor = baseWhite;     cancelHB.hoverColor = hoverRed;
     clipboardHB.baseColor = baseWhite;  clipboardHB.hoverColor = hoverBlue;
     saveHB.baseColor = baseWhite;       saveHB.hoverColor = hoverBlue;
     saveRemoteHB.baseColor = baseWhite; saveRemoteHB.hoverColor = hoverBlue;
+    ocrHB.baseColor = baseWhite;        ocrHB.hoverColor = hoverBlue;
     summaryHB.baseColor = baseWhite;    summaryHB.hoverColor = hoverBlue;
     uploadHB.baseColor = baseWhite;     uploadHB.hoverColor = hoverBlue;
 
     [self styleIconButton:_penButton image:[self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M742.72 752.064c-29.696 28.576-42.976 48.96-42.976 77.12 0 98.4 143.776 142.464 229.728 65.536l-21.344-23.84c-66.976 59.936-176.384 26.4-176.384-41.696 0-16.832 9.28-31.104 33.184-54.08l13.44-12.736c61.024-58.016 75.328-102.72 29.312-179.84-43.84-73.44-96.8-88.288-162.784-50.56-47.232 27.04-68.64 47.456-208.32 190.4-70.624 72.288-153.92 77.088-217.344 26.784-59.712-47.328-79.872-127.36-42.176-188.64 24.512-39.84 62.656-72.896 136.64-124.48 5.952-4.192 27.04-18.816 31.104-21.664 12.16-8.448 21.536-15.104 30.4-21.536 107.552-78.272 140.8-139.136 86.048-219.904-76.992-113.472-202.304-90.016-367.744 61.472l21.6 23.616c153.088-140.224 256.896-159.616 319.68-67.104 41.632 61.408 16.896 106.688-78.4 176.032-8.64 6.304-17.92 12.832-29.888 21.184l-31.136 21.632c-77.504 54.08-117.984 89.184-145.536 133.984-46.784 76.032-22.176 173.664 49.536 230.496 76.224 60.416 177.952 54.56 260.096-29.504 136.16-139.36 158.08-160.224 201.312-184.96 50.656-28.96 84.416-19.52 119.424 39.168 36.896 61.824 27.52 91.392-23.808 140.16 0.096-0.064-10.976 10.368-13.632 12.96z' fill='white'/></svg>"]];
     [self styleIconButton:_rectButton image:[self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M96 96h832v832H96V96z m32 32v768h768V128H128z' fill='white'/></svg>"]];
     [self styleIconButton:_ellipseButton image:[self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M512 928c229.76 0 416-186.24 416-416S741.76 96 512 96 96 282.24 96 512s186.24 416 416 416z m0-32C299.936 896 128 724.064 128 512S299.936 128 512 128s384 171.936 384 384-171.936 384-384 384z' fill='white'/></svg>"]];
+    [self styleIconButton:_textButton image:[self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><path d='M224 160h576v96H560v608h-96V256H224V160zM384 864h256v64H384v-64z' fill='white'/></svg>"]];
     [self styleIconButton:_colorButton image:nil];
     [self styleIconButton:_undoButton image:[self iconFromSVG:@"<svg viewBox='0 0 1024 1024' xmlns='http://www.w3.org/2000/svg'><g transform='translate(1024 0) scale(-1 1)'><path d='M838.976 288l-169.344-162.56a16 16 0 1 1 22.144-23.04l213.632 204.992-213.312 215.84a16 16 0 0 1-22.784-22.464L847.936 320H454.56c-164.192 0-297.28 128.96-297.28 288s133.088 288 297.28 288H704v32h-242.784C266.88 928 128 784.736 128 608S266.88 288 461.248 288h377.728z' fill='white'/></g></svg>"]];
     [_paletteView setWantsLayer:YES];
@@ -366,6 +385,19 @@ static id nativeOverlayKeyMonitor = nil;
         if (points.count == 0) {
             continue;
         }
+        if ([tool isEqualToString:@"text"]) {
+            NSString *text = item[@"text"];
+            if (text.length == 0) {
+                continue;
+            }
+            NSPoint p = [points[0] pointValue];
+            NSDictionary *attrs = @{
+                NSFontAttributeName: [NSFont systemFontOfSize:20 weight:NSFontWeightSemibold],
+                NSForegroundColorAttributeName: color ?: [NSColor whiteColor]
+            };
+            [text drawAtPoint:NSMakePoint(_selection.origin.x + p.x, _selection.origin.y + p.y) withAttributes:attrs];
+            continue;
+        }
         [color setStroke];
         NSBezierPath *path = [NSBezierPath bezierPath];
         [path setLineWidth:3];
@@ -475,9 +507,8 @@ static id nativeOverlayKeyMonitor = nil;
 
 - (void)mouseDown:(NSEvent *)event {
     NSPoint p = [self convertPoint:[event locationInWindow] fromView:nil];
-    if ([event clickCount] == 2 && _hasSelection && NSPointInRect(p, _selection)) {
+    if (_textEditor != nil) {
-        [self copySelection];
+        [self commitTextEditor];
-        return;
     }
     NSString *handle = [self resizeHandleAtPoint:p];
     if (handle != nil) {
@@ -487,7 +518,23 @@ static id nativeOverlayKeyMonitor = nil;
         _annotating = NO;
         _resizeHandle = handle;
         _resizeStart = _selection;
-    } else if (_hasSelection && NSPointInRect(p, _selection) && _activeTool != nil) {
+        [self syncControls];
+        return;
+    }
+    if (_hasSelection && NSPointInRect(p, _selection) && [_activeTool isEqualToString:@"text"]) {
+        _creating = NO;
+        _moving = NO;
+        _resizing = NO;
+        _annotating = NO;
+        [self beginTextAnnotationAtPoint:[self localPoint:p]];
+        [self syncControls];
+        return;
+    }
+    if ([event clickCount] == 2 && _hasSelection && NSPointInRect(p, _selection)) {
+        [self copySelection];
+        return;
+    }
+    if (_hasSelection && NSPointInRect(p, _selection) && _activeTool != nil) {
         _annotating = YES;
         _creating = NO;
         _moving = NO;
@@ -579,6 +626,16 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (void)keyDown:(NSEvent *)event {
+    if ([self isEditingText]) {
+        if ([event keyCode] == 53 || [[event charactersIgnoringModifiers] isEqualToString:@"\033"]) {
+            [self cancelTextEditor];
+            return;
+        }
+        if ([event keyCode] == 36 || [[event charactersIgnoringModifiers] isEqualToString:@"\r"]) {
+            [self commitTextEditor];
+            return;
+        }
+    }
     if ([event keyCode] == 53 || [[event charactersIgnoringModifiers] isEqualToString:@"\033"]) {
         [self cancelSelection];
     } else if (([event keyCode] == 36 || [[event charactersIgnoringModifiers] isEqualToString:@"\r"]) && _hasSelection) {
@@ -598,12 +655,14 @@ static id nativeOverlayKeyMonitor = nil;
     [_clipboardButton setHidden:!visible];
     [_saveButton setHidden:!visible];
     [_saveRemoteButton setHidden:!visible];
+    [_ocrButton setHidden:!visible];
     [_summaryButton setHidden:!visible];
     [_uploadButton setHidden:!visible];
     [_actionToolbarBg setHidden:!visible];
     [_penButton setHidden:!visible];
     [_rectButton setHidden:!visible];
     [_ellipseButton setHidden:!visible];
+    [_textButton setHidden:!visible];
     [_colorButton setHidden:!visible];
     [_undoButton setHidden:!visible];
     [_sizeLabel setHidden:!visible];
@@ -616,12 +675,12 @@ static id nativeOverlayKeyMonitor = nil;
     [_sizeLabel setStringValue:[NSString stringWithFormat:@"%.0f × %.0f", _selection.size.width, _selection.size.height]];
     [_sizeLabel setFrame:NSMakeRect(_selection.origin.x, MAX(0, _selection.origin.y - 26), 110, 22)];
 
-    // Action toolbar layout — 6 icon buttons, each 28x28, separated by 8px,
+    // Action toolbar layout — 7 icon buttons, each 28x28, separated by 8px,
-    // with 4px outer padding. Total = 6*28 + 5*8 + 2*4 = 216px wide.
+    // with 4px outer padding. Total = 7*28 + 6*8 + 2*4 = 252px wide.
     CGFloat actionBtnSize = 28;
     CGFloat actionGap = 8;
     CGFloat actionPad = 4;
-    NSInteger actionCount = 6;
+    NSInteger actionCount = 7;
     CGFloat toolbarW = actionPad * 2 + actionBtnSize * actionCount + actionGap * (actionCount - 1);
     CGFloat toolbarH = 40;
     CGFloat x = _selection.origin.x + _selection.size.width - toolbarW;
@@ -639,19 +698,21 @@ static id nativeOverlayKeyMonitor = nil;
     [_clipboardButton  setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 1, btnY, actionBtnSize, actionBtnSize)];
     [_saveButton       setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 2, btnY, actionBtnSize, actionBtnSize)];
     [_saveRemoteButton setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 3, btnY, actionBtnSize, actionBtnSize)];
-    [_summaryButton    setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 4, btnY, actionBtnSize, actionBtnSize)];
+    [_ocrButton        setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 4, btnY, actionBtnSize, actionBtnSize)];
-    [_uploadButton     setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 5, btnY, actionBtnSize, actionBtnSize)];
+    [_summaryButton    setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 5, btnY, actionBtnSize, actionBtnSize)];
+    [_uploadButton     setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 6, btnY, actionBtnSize, actionBtnSize)];
 
     // Mark toolbar sits to the LEFT of the action toolbar (same row) with an
     // 8px gap between the two groups, so they never overlap on tiny selections.
-    CGFloat markW = 170;
+    CGFloat markW = 202;
     CGFloat markGap = 8;
     CGFloat markX = MAX(0, x - markGap - markW);
     [_penButton setFrame:NSMakeRect(markX + 4, y + 4, 28, 28)];
     [_rectButton setFrame:NSMakeRect(markX + 36, y + 4, 28, 28)];
     [_ellipseButton setFrame:NSMakeRect(markX + 68, y + 4, 28, 28)];
-    [_colorButton setFrame:NSMakeRect(markX + 104, y + 7, 22, 22)];
+    [_textButton setFrame:NSMakeRect(markX + 100, y + 4, 28, 28)];
-    [_undoButton setFrame:NSMakeRect(markX + 134, y + 4, 28, 28)];
+    [_colorButton setFrame:NSMakeRect(markX + 136, y + 7, 22, 22)];
+    [_undoButton setFrame:NSMakeRect(markX + 166, y + 4, 28, 28)];
     [[_colorButton layer] setBackgroundColor:[_activeColor CGColor]];
     [_undoButton setEnabled:_annotations.count > 0];
     [_paletteView setFrame:NSMakeRect(markX, MAX(0, y - 78), 150, 70)];
@@ -659,7 +720,7 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (void)updateToolButtonStates {
-    NSDictionary *buttons = @{@"pen": _penButton, @"rect": _rectButton, @"ellipse": _ellipseButton};
+    NSDictionary *buttons = @{@"pen": _penButton, @"rect": _rectButton, @"ellipse": _ellipseButton, @"text": _textButton};
     for (NSString *tool in buttons) {
         NSButton *button = buttons[tool];
         NSColor *bg = [tool isEqualToString:_activeTool]
@@ -676,7 +737,9 @@ static id nativeOverlayKeyMonitor = nil;
 - (void)selectPen { [self toggleTool:@"pen"]; }
 - (void)selectRect { [self toggleTool:@"rect"]; }
 - (void)selectEllipse { [self toggleTool:@"ellipse"]; }
+- (void)selectText { [self toggleTool:@"text"]; }
 - (void)undoAnnotation {
+    [self cancelTextEditor];
     if (_annotations.count > 0) {
         [_annotations removeLastObject];
         [self syncControls];
@@ -684,6 +747,68 @@ static id nativeOverlayKeyMonitor = nil;
     }
 }
 
+- (void)beginTextAnnotationAtPoint:(NSPoint)localPoint {
+    [self cancelTextEditor];
+    _textEditorLocalPoint = localPoint;
+    NSRect frame = NSMakeRect(_selection.origin.x + localPoint.x, _selection.origin.y + localPoint.y, 180, 30);
+    CGFloat maxX = self.bounds.size.width - frame.size.width - 8;
+    CGFloat maxY = self.bounds.size.height - frame.size.height - 8;
+    frame.origin.x = MAX(8, MIN(frame.origin.x, maxX));
+    frame.origin.y = MAX(8, MIN(frame.origin.y, maxY));
+
+    _textEditor = [[NSTextField alloc] initWithFrame:frame];
+    [_textEditor setBezeled:YES];
+    [_textEditor setBordered:YES];
+    [_textEditor setDrawsBackground:YES];
+    [_textEditor setBackgroundColor:[NSColor colorWithCalibratedWhite:0.08 alpha:0.78]];
+    [_textEditor setTextColor:_activeColor];
+    [_textEditor setFont:[NSFont systemFontOfSize:20 weight:NSFontWeightSemibold]];
+    [_textEditor setFocusRingType:NSFocusRingTypeNone];
+    [_textEditor setTarget:self];
+    [_textEditor setAction:@selector(commitTextEditorFromSender:)];
+    [self addSubview:_textEditor];
+    [[self window] makeFirstResponder:_textEditor];
+}
+
+- (BOOL)isEditingText {
+    return _textEditor != nil;
+}
+
+- (void)commitTextEditorFromSender:(id)sender {
+    [self commitTextEditor];
+}
+
+- (void)commitTextEditor {
+    if (_textEditor == nil) {
+        return;
+    }
+    NSString *text = [[_textEditor stringValue] stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];
+    if (text.length > 0) {
+        [_annotations addObject:[@{
+            @"tool": @"text",
+            @"color": [self hexForColor:_activeColor],
+            @"nsColor": _activeColor,
+            @"points": [NSMutableArray arrayWithObject:[NSValue valueWithPoint:_textEditorLocalPoint]],
+            @"text": text
+        } mutableCopy]];
+    }
+    [_textEditor removeFromSuperview];
+    _textEditor = nil;
+    [[self window] makeFirstResponder:self];
+    [self syncControls];
+    [self setNeedsDisplay:YES];
+}
+
+- (void)cancelTextEditor {
+    if (_textEditor == nil) {
+        return;
+    }
+    [_textEditor removeFromSuperview];
+    _textEditor = nil;
+    [[self window] makeFirstResponder:self];
+    [self setNeedsDisplay:YES];
+}
+
 - (void)togglePalette {
     [_paletteView setHidden:![_paletteView isHidden]];
     if (![_paletteView isHidden] && _paletteView.subviews.count == 0) {
@@ -722,6 +847,7 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (NSString *)annotationsJSON {
+    [self commitTextEditor];
     NSMutableArray *payload = [NSMutableArray array];
     for (NSDictionary *item in _annotations) {
         NSMutableArray *points = [NSMutableArray array];
@@ -729,7 +855,12 @@ static id nativeOverlayKeyMonitor = nil;
             NSPoint p = [value pointValue];
             [points addObject:@{@"x": @(p.x), @"y": @(p.y)}];
         }
-        [payload addObject:@{@"tool": item[@"tool"], @"color": item[@"color"], @"points": points}];
+        NSMutableDictionary *entry = [@{@"tool": item[@"tool"], @"color": item[@"color"], @"points": points} mutableCopy];
+        NSString *text = item[@"text"];
+        if (text.length > 0) {
+            entry[@"text"] = text;
+        }
+        [payload addObject:entry];
     }
     NSData *data = [NSJSONSerialization dataWithJSONObject:payload options:0 error:nil];
     if (data == nil) {
@@ -792,6 +923,7 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (void)cancelSelection {
+    [self cancelTextEditor];
     [self closeOverlayWindow];
     nativeOverlayCancel();
 }
@@ -809,6 +941,18 @@ static id nativeOverlayKeyMonitor = nil;
     nativeOverlaySaveRemote((int)llround(r.origin.x), (int)llround(r.origin.y), (int)llround(r.size.width), (int)llround(r.size.height), [json UTF8String]);
 }
 
+// `ocrSelection` sends the screenshot to the configured OCR provider and
+// copies the extracted text.
+- (void)ocrSelection {
+    if (!_hasSelection) {
+        return;
+    }
+    NSRect r = [self globalRectForSelection:_selection];
+    [self closeOverlayWindow];
+    NSString *json = [self annotationsJSON];
+    nativeOverlayOCR((int)llround(r.origin.x), (int)llround(r.origin.y), (int)llround(r.size.width), (int)llround(r.size.height), [json UTF8String]);
+}
+
 // `summarizeSelection` uploads the screenshot to S3, sends it to the
 // configured multimodal model, and copies the generated summary.
 - (void)summarizeSelection {
@@ -880,10 +1024,18 @@ static void snipShowNativeOverlay(int width, int height) {
 
         nativeOverlayKeyMonitor = [NSEvent addLocalMonitorForEventsMatchingMask:NSEventMaskKeyDown handler:^NSEvent *(NSEvent *event) {
             if ([event keyCode] == 53) {
+                if ([view isEditingText]) {
+                    [view cancelTextEditor];
+                    return nil;
+                }
                 [view cancelSelection];
                 return nil;
             }
             if ([event keyCode] == 36 && [view hasSelection]) {
+                if ([view isEditingText]) {
+                    [view commitTextEditor];
+                    return nil;
+                }
                 [view confirmSelection];
                 return nil;
             }