feat: add screenshot OCR extraction

app.go

@@ -3,10 +3,12 @@
 package main
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"fmt"
 	"image"
+	"image/png"
 	"log/slog"
 	"os"
 	"path/filepath"
@@ -23,6 +25,7 @@ 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 +502,48 @@ 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
@@ -519,7 +564,8 @@ func (a *App) captureSelectedPNG(result CaptureResult, pc *pendingCapture) ([]by
 		return nil, err
 	}
 	if len(result.Annotations) > 0 {
-		cropped, err = application.ApplyAnnotations(cropped, result.Annotations, pc.Display.Scale)
+		scaleX, scaleY := annotationScalesForCapture(cropped, rect, pc.Display.Scale)
+		cropped, err = application.ApplyAnnotationsWithScale(cropped, result.Annotations, scaleX, scaleY)
 		if err != nil {
 			return nil, err
 		}
@@ -527,6 +573,33 @@ func (a *App) captureSelectedPNG(result CaptureResult, pc *pendingCapture) ([]by
 	return cropped, nil
 }
 
+func annotationScalesForCapture(pngBytes []byte, rect RegionRect, fallback float64) (float64, float64) {
+	if fallback <= 0 {
+		fallback = 1
+	}
+	scaleX := fallback
+	scaleY := fallback
+
+	cfg, err := png.DecodeConfig(bytes.NewReader(pngBytes))
+	if err != nil {
+		return scaleX, scaleY
+	}
+	if rect.W > 0 && cfg.Width > 0 {
+		scaleX = saneAnnotationScale(float64(cfg.Width)/float64(rect.W), fallback)
+	}
+	if rect.H > 0 && cfg.Height > 0 {
+		scaleY = saneAnnotationScale(float64(cfg.Height)/float64(rect.H), fallback)
+	}
+	return scaleX, scaleY
+}
+
+func saneAnnotationScale(scale, fallback float64) float64 {
+	if scale >= 0.25 && scale <= 8 {
+		return scale
+	}
+	return fallback
+}
+
 func (a *App) chooseSaveDirectory() (string, error) {
 	return wruntime.OpenDirectoryDialog(a.ctx, wruntime.OpenDialogOptions{
 		Title:                "Save screenshot to folder",
@@ -876,6 +949,35 @@ 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 +1035,33 @@ 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 {
@@ -77,6 +79,25 @@ interface OverlayPayload {
 }
 const overlayPayload = ref<OverlayPayload | null>(null)
 
+interface OverlayAnnotation {
+  tool: string
+  color: string
+  points: Array<{ x: number; y: number }>
+  text?: string
+  strokeWidth?: number
+  fontSize?: number
+}
+
+interface OverlayResult {
+  rect: {
+    x: number
+    y: number
+    w: number
+    h: number
+  }
+  annotations: OverlayAnnotation[]
+}
+
 const capturing = ref(false)
 
 const toast = ref<{ kind: 'success' | 'error'; text: string } | null>(null)
@@ -121,19 +142,7 @@ async function retryHotkey() {
   }
 }
 
-async function onOverlayConfirm(rect: {
-  rect: {
-    x: number
-    y: number
-    w: number
-    h: number
-  }
-  annotations: Array<{
-    tool: string
-    color: string
-    points: Array<{ x: number; y: number }>
-  }>
-}) {
+async function onOverlayConfirm(rect: OverlayResult) {
   // Optimistically swap back so the window does not visually lag the
   // Go-side hide. If upload fails, the toast surfaces the reason.
   mode.value = 'settings'
@@ -145,19 +154,7 @@ async function onOverlayConfirm(rect: {
   }
 }
 
-async function onOverlayCopy(rect: {
-  rect: {
-    x: number
-    y: number
-    w: number
-    h: number
-  }
-  annotations: Array<{
-    tool: string
-    color: string
-    points: Array<{ x: number; y: number }>
-  }>
-}) {
+async function onOverlayCopy(rect: OverlayResult) {
   mode.value = 'settings'
   overlayPayload.value = null
   try {
@@ -167,19 +164,7 @@ async function onOverlayCopy(rect: {
   }
 }
 
-async function onOverlaySave(rect: {
-  rect: {
-    x: number
-    y: number
-    w: number
-    h: number
-  }
-  annotations: Array<{
-    tool: string
-    color: string
-    points: Array<{ x: number; y: number }>
-  }>
-}) {
+async function onOverlaySave(rect: OverlayResult) {
   mode.value = 'settings'
   overlayPayload.value = null
   try {
@@ -189,19 +174,7 @@ async function onOverlaySave(rect: {
   }
 }
 
-async function onOverlaySaveRemote(rect: {
-  rect: {
-    x: number
-    y: number
-    w: number
-    h: number
-  }
-  annotations: Array<{
-    tool: string
-    color: string
-    points: Array<{ x: number; y: number }>
-  }>
-}) {
+async function onOverlaySaveRemote(rect: OverlayResult) {
   mode.value = 'settings'
   overlayPayload.value = null
   try {
@@ -211,19 +184,7 @@ async function onOverlaySaveRemote(rect: {
   }
 }
 
-async function onOverlaySummarize(rect: {
-  rect: {
-    x: number
-    y: number
-    w: number
-    h: number
-  }
-  annotations: Array<{
-    tool: string
-    color: string
-    points: Array<{ x: number; y: number }>
-  }>
-}) {
+async function onOverlaySummarize(rect: OverlayResult) {
   mode.value = 'settings'
   overlayPayload.value = null
   try {
@@ -233,6 +194,16 @@ async function onOverlaySummarize(rect: {
   }
 }
 
+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
@@ -264,6 +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}`
     )
   })
@@ -303,6 +276,7 @@ onUnmounted(() => {
     @save="onOverlaySave"
     @save-remote="onOverlaySaveRemote"
     @summarize="onOverlaySummarize"
+    @ocr="onOverlayOCR"
     @cancel="onOverlayCancel"
   />
 

frontend/src/views/CaptureOverlay.vue

@@ -33,6 +33,8 @@ interface Annotation {
   color: string
   points: Point[]
   text?: string
+  strokeWidth?: number
+  fontSize?: number
 }
 
 const emit = defineEmits<{
@@ -56,6 +58,10 @@ const emit = defineEmits<{
     e: 'summarize',
     payload: { rect: Rect; annotations: Annotation[] }
   ): void
+  (
+    e: 'ocr',
+    payload: { rect: Rect; annotations: Annotation[] }
+  ): void
   (e: 'cancel'): void
 }>()
 
@@ -64,28 +70,45 @@ const annotations = ref<Annotation[]>([])
 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 activeStrokeWidth = ref(3)
+const activeFontSize = ref(20)
+const textDraft = ref<{
+  point: Point
+  value: string
+  color: string
+  fontSize: number
+  index: number | null
+} | null>(null)
 const textInputRef = ref<HTMLInputElement | null>(null)
+const selectedTextIndex = ref<number | null>(null)
 
 type ResizeHandle = 'n' | 's' | 'e' | 'w' | 'nw' | 'ne' | 'sw' | 'se'
-type DragMode = 'idle' | 'creating' | 'moving' | 'resizing' | 'annotating'
+type DragMode =
+  | 'idle'
+  | 'creating'
+  | 'moving'
+  | 'resizing'
+  | 'annotating'
+  | 'moving-text'
 const dragMode = ref<DragMode>('idle')
 const resizeHandle = ref<ResizeHandle | null>(null)
 const dragAnchor = ref({ x: 0, y: 0 })
 const startRect = ref<Rect | null>(null)
+const textDragStartPoint = ref<Point | null>(null)
+const textDragOriginalPoint = ref<Point | null>(null)
+
+const DEFAULT_TEXT_FONT_SIZE = 20
+const STROKE_WIDTHS = [2, 4, 6]
+const FONT_SIZES = [16, 20, 28, 36]
 
 const colors = [
   '#ef4444',
-  '#f97316',
   '#facc15',
   '#22c55e',
-  '#06b6d4',
   '#3b82f6',
-  '#8b5cf6',
-  '#ec4899',
-  '#ffffff',
   '#111827',
+  '#9ca3af',
+  '#ffffff',
 ]
 
 const maskPath = computed(() => {
@@ -118,10 +141,32 @@ const sizeLabel = computed(() => {
   return `${Math.round(rect.value.w)} × ${Math.round(rect.value.h)}`
 })
 
-const MARK_TOOLBAR_W = 222
-const ACTION_TOOLBAR_W = 216
+const MARK_TOOLBAR_W = 178
+const ACTION_TOOLBAR_W = 252
 const TOOLBAR_GROUP_GAP = 8
 
+const toolOrder: Tool[] = ['pen', 'rect', 'ellipse', 'text']
+
+const toolSettingsPos = computed(() => {
+  if (!leftToolbarPos.value || !rect.value || !activeTool.value) return null
+  const menuW = activeTool.value === 'text' ? 462 : 398
+  const menuH = 58
+  const buttonIndex = toolOrder.indexOf(activeTool.value)
+  const buttonCenter = 4 + buttonIndex * 34 + 14
+  let x = leftToolbarPos.value.x
+  let y = leftToolbarPos.value.y + 44
+  if (y + menuH > props.height) {
+    y = leftToolbarPos.value.y - menuH - 8
+  }
+  x = clamp(x, 8, Math.max(8, props.width - menuW - 8))
+  return {
+    x,
+    y,
+    w: menuW,
+    arrowX: clamp(leftToolbarPos.value.x + buttonCenter - x, 18, menuW - 18),
+  }
+})
+
 const rightToolbarPos = computed(() => {
   if (!rect.value) return null
   return placeToolbar(rect.value, ACTION_TOOLBAR_W, 40, 'right')
@@ -207,6 +252,89 @@ function insideRect(p: Point, r: Rect | null) {
   return p.x >= r.x && p.x <= r.x + r.w && p.y >= r.y && p.y <= r.y + r.h
 }
 
+let measureCanvas: HTMLCanvasElement | null = null
+
+function textFont(fontSize = DEFAULT_TEXT_FONT_SIZE) {
+  return `600 ${fontSize}px -apple-system, BlinkMacSystemFont, "SF Pro Text", sans-serif`
+}
+
+function textSize(annotation: Pick<Annotation, 'text' | 'fontSize'>) {
+  const fontSize = annotation.fontSize || DEFAULT_TEXT_FONT_SIZE
+  const lines = (annotation.text || ' ').split('\n')
+  if (typeof document === 'undefined') {
+    return {
+      w: Math.max(1, ...lines.map((line) => line.length * fontSize)),
+      h: Math.max(fontSize * 1.2, lines.length * fontSize * 1.2),
+    }
+  }
+  measureCanvas ||= document.createElement('canvas')
+  const ctx = measureCanvas.getContext('2d')
+  if (!ctx) {
+    return {
+      w: Math.max(1, ...lines.map((line) => line.length * fontSize)),
+      h: Math.max(fontSize * 1.2, lines.length * fontSize * 1.2),
+    }
+  }
+  ctx.font = textFont(fontSize)
+  return {
+    w: Math.ceil(Math.max(1, ...lines.map((line) => ctx.measureText(line || ' ').width))),
+    h: Math.ceil(Math.max(fontSize * 1.2, lines.length * fontSize * 1.2)),
+  }
+}
+
+function textEditorSize(draft: { value: string; fontSize: number }) {
+  const size = textSize({
+    text: draft.value || ' ',
+    fontSize: draft.fontSize,
+  })
+  return {
+    width: Math.max(180, Math.min(420, size.w + 28)),
+    height: Math.max(30, Math.ceil(draft.fontSize * 1.6)),
+    lineHeight: Math.ceil(draft.fontSize * 1.25),
+  }
+}
+
+function textRenderBox(annotation: Annotation) {
+  const point = annotation.points[0] || { x: 0, y: 0 }
+  const size = textSize(annotation)
+  return {
+    x: point.x - 4,
+    y: point.y - 3,
+    w: size.w + 8,
+    h: size.h + 6,
+  }
+}
+
+function textAnnotationIndexAtPoint(p: Point) {
+  if (!rect.value) return null
+  for (let i = annotations.value.length - 1; i >= 0; i--) {
+    const annotation = annotations.value[i]
+    if (annotation.tool !== 'text' || annotation.points.length === 0) continue
+    const point = annotation.points[0]
+    const size = textSize(annotation)
+    const x = rect.value.x + point.x
+    const y = rect.value.y + point.y
+    if (
+      p.x >= x - 6 &&
+      p.x <= x + size.w + 6 &&
+      p.y >= y - 6 &&
+      p.y <= y + size.h + 6
+    ) {
+      return i
+    }
+  }
+  return null
+}
+
+function clampTextLocalPoint(point: Point, annotation: Pick<Annotation, 'text' | 'fontSize'>) {
+  if (!rect.value) return point
+  const size = textSize(annotation)
+  return {
+    x: clamp(point.x, 0, Math.max(0, rect.value.w - size.w)),
+    y: clamp(point.y, 0, Math.max(0, rect.value.h - size.h)),
+  }
+}
+
 function hitHandle(p: Point): ResizeHandle | null {
   if (!rect.value) return null
   const tolerance = 9
@@ -231,7 +359,8 @@ function hitHandle(p: Point): ResizeHandle | null {
 function onMouseDown(e: MouseEvent) {
   if (e.button !== 0) return
   commitTextDraft()
-  paletteOpen.value = false
+  textDragStartPoint.value = null
+  textDragOriginalPoint.value = null
   const p = pointFromEvent(e)
   const handle = hitHandle(p)
   if (handle && rect.value) {
@@ -250,15 +379,34 @@ function onMouseDown(e: MouseEvent) {
   dragAnchor.value = p
   rect.value = { x: p.x, y: p.y, w: 0, h: 0 }
   annotations.value = []
+  selectedTextIndex.value = null
   draftAnnotation.value = null
 }
 
 function onSelectionMouseDown(e: MouseEvent) {
   if (e.button !== 0 || !rect.value) return
   e.stopPropagation()
-  paletteOpen.value = false
+  commitTextDraft()
+  const p = pointFromEvent(e)
+  const hitTextIndex = textAnnotationIndexAtPoint(p)
+  if (hitTextIndex !== null) {
+    selectedTextIndex.value = hitTextIndex
+    const annotation = annotations.value[hitTextIndex]
+    activeTool.value = 'text'
+    activeColor.value = annotation.color
+    activeFontSize.value = annotation.fontSize || DEFAULT_TEXT_FONT_SIZE
+    if (e.detail >= 2) {
+      beginTextAnnotation(annotation.points[0], hitTextIndex)
+      return
+    }
+    dragMode.value = 'moving-text'
+    textDragStartPoint.value = localPoint(p)
+    textDragOriginalPoint.value = { ...annotation.points[0] }
+    return
+  }
+  selectedTextIndex.value = null
   if (activeTool.value === 'text') {
-    beginTextAnnotation(localPoint(pointFromEvent(e)))
+    beginTextAnnotation(localPoint(p))
     return
   }
   if (e.detail >= 2) {
@@ -266,7 +414,6 @@ function onSelectionMouseDown(e: MouseEvent) {
     onCopy()
     return
   }
-  const p = pointFromEvent(e)
   const handle = hitHandle(p)
   if (handle) {
     dragMode.value = 'resizing'
@@ -280,6 +427,7 @@ function onSelectionMouseDown(e: MouseEvent) {
   draftAnnotation.value = {
     tool: activeTool.value,
     color: activeColor.value,
+    strokeWidth: activeStrokeWidth.value,
     points: [local],
   }
 }
@@ -297,6 +445,21 @@ function onMouseMove(e: MouseEvent) {
     }
   } else if (dragMode.value === 'resizing') {
     resizeSelection(p)
+  } else if (
+    dragMode.value === 'moving-text' &&
+    selectedTextIndex.value !== null &&
+    textDragStartPoint.value &&
+    textDragOriginalPoint.value
+  ) {
+    const annotation = annotations.value[selectedTextIndex.value]
+    if (annotation?.tool === 'text') {
+      const local = localPoint(p)
+      const next = {
+        x: textDragOriginalPoint.value.x + local.x - textDragStartPoint.value.x,
+        y: textDragOriginalPoint.value.y + local.y - textDragStartPoint.value.y,
+      }
+      annotation.points[0] = clampTextLocalPoint(next, annotation)
+    }
   } else if (dragMode.value === 'annotating' && draftAnnotation.value) {
     if (activeTool.value === 'pen') {
       draftAnnotation.value.points.push(localPoint(p))
@@ -324,6 +487,8 @@ function onMouseUp() {
   dragMode.value = 'idle'
   resizeHandle.value = null
   startRect.value = null
+  textDragStartPoint.value = null
+  textDragOriginalPoint.value = null
 }
 
 function resizeSelection(p: Point) {
@@ -356,7 +521,38 @@ function selectTool(tool: Tool) {
 
 function chooseColor(color: string) {
   activeColor.value = color
-  paletteOpen.value = false
+  if (textDraft.value) {
+    textDraft.value.color = color
+  } else if (
+    activeTool.value === 'text' &&
+    selectedTextIndex.value !== null &&
+    annotations.value[selectedTextIndex.value]?.tool === 'text'
+  ) {
+    annotations.value[selectedTextIndex.value].color = color
+  }
+}
+
+function chooseStrokeWidth(width: number) {
+  activeStrokeWidth.value = width
+}
+
+function chooseFontSize(size: number) {
+  activeFontSize.value = size
+  if (textDraft.value) {
+    textDraft.value.fontSize = size
+    textDraft.value.point = clampTextLocalPoint(textDraft.value.point, {
+      text: textDraft.value.value,
+      fontSize: size,
+    })
+  } else if (
+    activeTool.value === 'text' &&
+    selectedTextIndex.value !== null &&
+    annotations.value[selectedTextIndex.value]?.tool === 'text'
+  ) {
+    const annotation = annotations.value[selectedTextIndex.value]
+    annotation.fontSize = size
+    annotation.points[0] = clampTextLocalPoint(annotation.points[0], annotation)
+  }
 }
 
 function onConfirm() {
@@ -379,7 +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 = {
@@ -391,6 +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() {
@@ -415,8 +616,16 @@ function onKeydown(e: KeyboardEvent) {
 }
 
 function undoAnnotation() {
+  if (!textDraft.value && annotations.value.length === 0) return
   cancelTextDraft()
+  if (annotations.value.length === 0) return
   annotations.value.pop()
+  if (
+    selectedTextIndex.value !== null &&
+    selectedTextIndex.value >= annotations.value.length
+  ) {
+    selectedTextIndex.value = null
+  }
 }
 
 function removeSinglePointAnnotation() {
@@ -426,11 +635,24 @@ function removeSinglePointAnnotation() {
   }
 }
 
-function beginTextAnnotation(point: Point) {
+function beginTextAnnotation(point: Point, index: number | null = null) {
   commitTextDraft()
   dragMode.value = 'idle'
   draftAnnotation.value = null
-  textDraft.value = { point, value: '' }
+  const existing = index !== null ? annotations.value[index] : null
+  const color = existing?.color || activeColor.value
+  const fontSize = existing?.fontSize || activeFontSize.value
+  if (existing) {
+    activeColor.value = color
+    activeFontSize.value = fontSize
+  }
+  textDraft.value = {
+    point: clampTextLocalPoint(point, existing || { text: '', fontSize }),
+    value: existing?.text || '',
+    color,
+    fontSize,
+    index,
+  }
   void nextTick(() => {
     textInputRef.value?.focus()
     textInputRef.value?.select()
@@ -440,13 +662,31 @@ function beginTextAnnotation(point: Point) {
 function commitTextDraft() {
   if (!textDraft.value) return
   const text = textDraft.value.value.trim()
+  const draft = textDraft.value
+  if (draft.index !== null) {
+    const target = annotations.value[draft.index]
+    if (target?.tool === 'text') {
       if (text !== '') {
+        target.points = [clampTextLocalPoint(draft.point, { text, fontSize: draft.fontSize })]
+        target.text = text
+        target.color = draft.color
+        target.fontSize = draft.fontSize
+        selectedTextIndex.value = draft.index
+      } else {
+        annotations.value.splice(draft.index, 1)
+        selectedTextIndex.value = null
+      }
+    }
+  } else if (text !== '') {
+    const point = clampTextLocalPoint(draft.point, { text, fontSize: draft.fontSize })
     annotations.value.push({
       tool: 'text',
-      color: activeColor.value,
-      points: [textDraft.value.point],
+      color: draft.color,
+      points: [point],
       text,
+      fontSize: draft.fontSize,
     })
+    selectedTextIndex.value = annotations.value.length - 1
   }
   textDraft.value = null
 }
@@ -506,7 +746,7 @@ onUnmounted(() => {
           v-if="annotation.tool === 'pen'"
           :points="annotation.points.map((p) => `${p.x},${p.y}`).join(' ')"
           :stroke="annotation.color"
-          stroke-width="3"
+          :stroke-width="annotation.strokeWidth || 3"
           stroke-linecap="round"
           stroke-linejoin="round"
           fill="none"
@@ -518,7 +758,7 @@ onUnmounted(() => {
           :width="Math.abs(annotation.points[1].x - annotation.points[0].x)"
           :height="Math.abs(annotation.points[1].y - annotation.points[0].y)"
           :stroke="annotation.color"
-          stroke-width="3"
+          :stroke-width="annotation.strokeWidth || 3"
           fill="none"
         />
         <ellipse
@@ -528,20 +768,30 @@ onUnmounted(() => {
           :rx="Math.abs(annotation.points[1].x - annotation.points[0].x) / 2"
           :ry="Math.abs(annotation.points[1].y - annotation.points[0].y) / 2"
           :stroke="annotation.color"
-          stroke-width="3"
+          :stroke-width="annotation.strokeWidth || 3"
           fill="none"
         />
+        <template v-else-if="annotation.tool === 'text' && annotation.points.length >= 1">
+          <rect
+            v-if="selectedTextIndex === index && index < annotations.length"
+            class="text-selection-box"
+            :x="textRenderBox(annotation).x"
+            :y="textRenderBox(annotation).y"
+            :width="textRenderBox(annotation).w"
+            :height="textRenderBox(annotation).h"
+          />
           <text
-          v-else-if="annotation.tool === 'text' && annotation.points.length >= 1"
+            class="annotation-text"
             :x="annotation.points[0].x"
             :y="annotation.points[0].y"
             :fill="annotation.color"
-          font-size="20"
+            :font-size="annotation.fontSize || DEFAULT_TEXT_FONT_SIZE"
             font-weight="600"
             dominant-baseline="hanging"
           >
             {{ annotation.text }}
           </text>
+        </template>
       </g>
     </svg>
 
@@ -565,7 +815,11 @@ onUnmounted(() => {
       :style="{
         left: rect.x + textDraft.point.x + 'px',
         top: rect.y + textDraft.point.y + 'px',
-        color: activeColor,
+        color: textDraft.color,
+        fontSize: textDraft.fontSize + 'px',
+        width: textEditorSize(textDraft).width + 'px',
+        height: textEditorSize(textDraft).height + 'px',
+        lineHeight: textEditorSize(textDraft).lineHeight + 'px',
       }"
       spellcheck="false"
       @mousedown.stop
@@ -649,15 +903,57 @@ onUnmounted(() => {
           <path d="M9 19h6" />
         </svg>
       </button>
-      <div class="color-wrap">
       <button
-          class="icon-btn color-btn"
-          title="选择标记颜色"
-          @click="paletteOpen = !paletteOpen"
+        class="icon-btn"
+        :class="{ muted: annotations.length === 0 }"
+        :aria-disabled="annotations.length === 0"
+        title="撤销上一处标记"
+        @click="undoAnnotation"
       >
-          <span :style="{ background: activeColor }" />
+        <svg viewBox="0 0 24 24" aria-hidden="true">
+          <path d="M9 7H4v5" />
+          <path d="M4 7c3-3 8-4 12-1 4 3 4 9 0 12-2 1-4 2-7 1" />
+        </svg>
       </button>
-        <div v-if="paletteOpen" class="palette">
+    </div>
+
+    <div
+      v-if="toolSettingsPos && rect && rect.w >= 4 && rect.h >= 4"
+      class="tool-settings-menu"
+      :style="{
+        left: toolSettingsPos.x + 'px',
+        top: toolSettingsPos.y + 'px',
+        width: toolSettingsPos.w + 'px',
+        '--arrow-x': toolSettingsPos.arrowX + 'px',
+      }"
+      @mousedown.stop
+    >
+      <div v-if="activeTool !== 'text'" class="setting-group stroke-group">
+        <button
+          v-for="widthValue in STROKE_WIDTHS"
+          :key="widthValue"
+          class="stroke-choice"
+          :class="{ active: activeStrokeWidth === widthValue }"
+          :title="`${widthValue}px`"
+          @click="chooseStrokeWidth(widthValue)"
+        >
+          <span :style="{ width: widthValue * 4 + 'px', height: widthValue * 4 + 'px' }" />
+        </button>
+      </div>
+      <div v-else class="setting-group font-group">
+        <button
+          v-for="size in FONT_SIZES"
+          :key="size"
+          class="font-choice"
+          :class="{ active: activeFontSize === size }"
+          :title="`${size}px`"
+          @click="chooseFontSize(size)"
+        >
+          {{ size }}
+        </button>
+      </div>
+      <div class="settings-divider" />
+      <div class="setting-group color-group">
         <button
           v-for="color in colors"
           :key="color"
@@ -669,18 +965,6 @@ onUnmounted(() => {
         />
       </div>
     </div>
-      <button
-        class="icon-btn"
-        :disabled="annotations.length === 0"
-        title="撤销上一处标记"
-        @click="undoAnnotation"
-      >
-        <svg viewBox="0 0 24 24" aria-hidden="true">
-          <path d="M9 7H4v5" />
-          <path d="M4 7c3-3 8-4 12-1 4 3 4 9 0 12-2 1-4 2-7 1" />
-        </svg>
-      </button>
-    </div>
 
     <div
       v-if="rightToolbarPos && rect && rect.w >= 4 && rect.h >= 4"
@@ -716,6 +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"
@@ -761,6 +1060,17 @@ onUnmounted(() => {
   pointer-events: none;
 }
 
+.annotation-text {
+  font-family: -apple-system, BlinkMacSystemFont, "SF Pro Text", sans-serif;
+}
+
+.text-selection-box {
+  fill: transparent;
+  stroke: #3b82f6;
+  stroke-width: 1.5;
+  stroke-dasharray: 4 3;
+}
+
 .selection-hit-area {
   position: absolute;
   cursor: crosshair;
@@ -769,10 +1079,10 @@ onUnmounted(() => {
 .text-editor {
   position: absolute;
   z-index: 6;
+  box-sizing: border-box;
   min-width: 120px;
-  max-width: 320px;
-  height: 28px;
-  padding: 2px 6px;
+  max-width: 420px;
+  padding: 0 10px;
   border: 1px solid currentColor;
   border-radius: 4px;
   outline: none;
@@ -835,15 +1145,17 @@ onUnmounted(() => {
 }
 
 .mark-toolbar {
-  width: 222px;
+  width: 178px;
 }
 .action-toolbar {
-  width: 216px;
+  width: 252px;
 }
 
 .icon-btn,
 .action-btn,
-.swatch {
+.swatch,
+.stroke-choice,
+.font-choice {
   font-family: inherit;
 }
 
@@ -936,14 +1248,14 @@ onUnmounted(() => {
   background: transparent;
   cursor: pointer;
 }
-.icon-btn:hover:not(:disabled),
+.icon-btn:hover:not(.muted),
 .icon-btn.active {
   color: #fff;
   background: rgba(255, 255, 255, 0.12);
 }
-.icon-btn:disabled {
+.icon-btn.muted {
   opacity: 0.35;
-  cursor: not-allowed;
+  cursor: default;
 }
 .icon-btn svg {
   width: 18px;
@@ -955,36 +1267,88 @@ onUnmounted(() => {
   stroke-linejoin: round;
 }
 
-.color-wrap {
-  position: relative;
+.tool-settings-menu {
+  position: absolute;
+  z-index: 5;
+  box-sizing: border-box;
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  min-height: 42px;
+  padding: 8px 14px;
+  color: #1f2937;
+  background: rgba(255, 255, 255, 0.96);
+  border-radius: 8px;
+  box-shadow: 0 12px 30px rgba(0, 0, 0, 0.26);
+  cursor: default;
 }
-.color-btn span {
+.tool-settings-menu::before {
+  content: '';
+  position: absolute;
+  left: var(--arrow-x);
+  top: -8px;
+  transform: translateX(-50%) rotate(45deg);
   width: 16px;
   height: 16px;
-  border: 1px solid rgba(255, 255, 255, 0.7);
-  box-shadow: inset 0 0 0 1px rgba(0, 0, 0, 0.18);
+  background: rgba(255, 255, 255, 0.96);
+  border-radius: 3px;
 }
-.palette {
-  position: absolute;
-  left: 0;
-  bottom: 36px;
+.setting-group {
+  position: relative;
+  z-index: 1;
+  display: flex;
+  align-items: center;
+  gap: 10px;
+}
+.stroke-choice,
+.font-choice {
   display: grid;
-  grid-template-columns: repeat(5, 22px);
-  gap: 6px;
-  padding: 8px;
-  background: rgba(28, 28, 32, 0.96);
-  border-radius: 8px;
-  box-shadow: 0 8px 26px rgba(0, 0, 0, 0.45);
+  place-items: center;
+  width: 32px;
+  height: 32px;
+  padding: 0;
+  border: 0;
+  border-radius: 6px;
+  color: #1f2937;
+  background: transparent;
+  cursor: pointer;
+}
+.stroke-choice:hover,
+.stroke-choice.active,
+.font-choice:hover,
+.font-choice.active {
+  color: #2563eb;
+  background: #eaf1ff;
+}
+.stroke-choice span {
+  display: block;
+  border-radius: 999px;
+  background: currentColor;
+}
+.font-choice {
+  min-width: 40px;
+  width: auto;
+  padding: 0 8px;
+  font-size: 14px;
+  font-weight: 700;
+}
+.settings-divider {
+  position: relative;
+  z-index: 1;
+  width: 1px;
+  height: 26px;
+  background: #d1d5db;
 }
 .swatch {
   width: 22px;
   height: 22px;
-  border: 1px solid rgba(255, 255, 255, 0.55);
+  padding: 0;
+  border: 1px solid rgba(17, 24, 39, 0.18);
   border-radius: 4px;
   cursor: pointer;
 }
 .swatch.selected {
-  outline: 2px solid #fff;
+  outline: 2px solid #2563eb;
   outline-offset: 2px;
 }
 

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

@@ -19,6 +19,8 @@ export namespace application {
 	    color: string;
 	    points: Point[];
 	    text?: string;
+	    strokeWidth?: number;
+	    fontSize?: number;
 	
 	    static createFrom(source: any = {}) {
 	        return new Annotation(source);
@@ -30,6 +32,8 @@ export namespace application {
 	        this.color = source["color"];
 	        this.points = this.convertValues(source["points"], Point);
 	        this.text = source["text"];
+	        this.strokeWidth = source["strokeWidth"];
+	        this.fontSize = source["fontSize"];
 	    }
 
 		convertValues(a: any, classs: any, asMap: boolean = false): any {
@@ -55,6 +59,66 @@ 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;
@@ -175,6 +239,7 @@ export namespace domain {
 	    s3: S3Config;
 	    ssh: SSHConfig;
 	    llm: LLMConfig;
+	    ocr: OCRConfig;
 
 	    static createFrom(source: any = {}) {
 	        return new AppConfig(source);
@@ -187,6 +252,7 @@ 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 {
@@ -211,6 +277,8 @@ export namespace domain {
 
 
 
+
+
 }
 
 export namespace main {
@@ -281,4 +349,3 @@ export namespace main {
 	}
 
 }
-

internal/application/annotation.go

@@ -26,6 +26,8 @@ type Annotation struct {
 	Color       string  `json:"color"`
 	Points      []Point `json:"points"`
 	Text        string  `json:"text,omitempty"`
+	StrokeWidth float64 `json:"strokeWidth,omitempty"`
+	FontSize    float64 `json:"fontSize,omitempty"`
 }
 
 type Point struct {
@@ -35,12 +37,22 @@ type Point struct {
 
 // ApplyAnnotations decodes a PNG, draws all annotations, and re-encodes it.
 func ApplyAnnotations(pngBytes []byte, annotations []Annotation, scale float64) ([]byte, error) {
+	return ApplyAnnotationsWithScale(pngBytes, annotations, scale, scale)
+}
+
+// ApplyAnnotationsWithScale decodes a PNG, draws all annotations using the
+// actual device-pixel scale of the captured image, and re-encodes it.
+func ApplyAnnotationsWithScale(pngBytes []byte, annotations []Annotation, scaleX, scaleY float64) ([]byte, error) {
 	if len(annotations) == 0 {
 		return pngBytes, nil
 	}
-	if scale <= 0 {
-		scale = 1
+	if scaleX <= 0 {
+		scaleX = 1
 	}
+	if scaleY <= 0 {
+		scaleY = scaleX
+	}
+	strokeScale := math.Max(scaleX, scaleY)
 
 	src, err := png.Decode(bytes.NewReader(pngBytes))
 	if err != nil {
@@ -55,16 +67,20 @@ func ApplyAnnotations(pngBytes []byte, annotations []Annotation, scale float64)
 		if err != nil {
 			c = color.RGBA{R: 59, G: 130, B: 246, A: 255}
 		}
-		width := int(math.Max(2, math.Round(3*scale)))
+		strokeWidth := ann.StrokeWidth
+		if strokeWidth <= 0 {
+			strokeWidth = 3
+		}
+		width := int(math.Max(1, math.Round(strokeWidth*strokeScale)))
 		switch ann.Tool {
 		case "pen":
-			drawPolyline(dst, ann.Points, scale, width, c)
+			drawPolyline(dst, ann.Points, scaleX, scaleY, width, c)
 		case "rect":
-			drawRectOutline(dst, ann.Points, scale, width, c)
+			drawRectOutline(dst, ann.Points, scaleX, scaleY, width, c)
 		case "ellipse":
-			drawEllipseOutline(dst, ann.Points, scale, width, c)
+			drawEllipseOutline(dst, ann.Points, scaleX, scaleY, width, c)
 		case "text":
-			drawTextAnnotation(dst, ann, scale, c)
+			drawTextAnnotation(dst, ann, scaleX, scaleY, c)
 		}
 	}
 
@@ -92,22 +108,22 @@ func parseHexColor(hex string) (color.RGBA, error) {
 	}, nil
 }
 
-func drawPolyline(img *image.RGBA, points []Point, scale float64, width int, c color.RGBA) {
+func drawPolyline(img *image.RGBA, points []Point, scaleX, scaleY float64, width int, c color.RGBA) {
 	if len(points) == 1 {
-		drawDot(img, scalePoint(points[0], scale), width, c)
+		drawDot(img, scalePoint(points[0], scaleX, scaleY), width, c)
 		return
 	}
 	for i := 1; i < len(points); i++ {
-		drawLine(img, scalePoint(points[i-1], scale), scalePoint(points[i], scale), width, c)
+		drawLine(img, scalePoint(points[i-1], scaleX, scaleY), scalePoint(points[i], scaleX, scaleY), width, c)
 	}
 }
 
-func drawRectOutline(img *image.RGBA, points []Point, scale float64, width int, c color.RGBA) {
+func drawRectOutline(img *image.RGBA, points []Point, scaleX, scaleY float64, width int, c color.RGBA) {
 	if len(points) < 2 {
 		return
 	}
-	a := scalePoint(points[0], scale)
-	b := scalePoint(points[len(points)-1], scale)
+	a := scalePoint(points[0], scaleX, scaleY)
+	b := scalePoint(points[len(points)-1], scaleX, scaleY)
 	x1, x2 := ordered(a.X, b.X)
 	y1, y2 := ordered(a.Y, b.Y)
 	drawLine(img, Point{X: x1, Y: y1}, Point{X: x2, Y: y1}, width, c)
@@ -116,12 +132,12 @@ func drawRectOutline(img *image.RGBA, points []Point, scale float64, width int,
 	drawLine(img, Point{X: x1, Y: y2}, Point{X: x1, Y: y1}, width, c)
 }
 
-func drawEllipseOutline(img *image.RGBA, points []Point, scale float64, width int, c color.RGBA) {
+func drawEllipseOutline(img *image.RGBA, points []Point, scaleX, scaleY float64, width int, c color.RGBA) {
 	if len(points) < 2 {
 		return
 	}
-	a := scalePoint(points[0], scale)
-	b := scalePoint(points[len(points)-1], scale)
+	a := scalePoint(points[0], scaleX, scaleY)
+	b := scalePoint(points[len(points)-1], scaleX, scaleY)
 	x1, x2 := ordered(a.X, b.X)
 	y1, y2 := ordered(a.Y, b.Y)
 	rx := (x2 - x1) / 2
@@ -180,8 +196,8 @@ func drawDot(img *image.RGBA, p Point, width int, c color.RGBA) {
 	}
 }
 
-func scalePoint(p Point, scale float64) Point {
-	return Point{X: p.X * scale, Y: p.Y * scale}
+func scalePoint(p Point, scaleX, scaleY float64) Point {
+	return Point{X: p.X * scaleX, Y: p.Y * scaleY}
 }
 
 func ordered(a, b float64) (float64, float64) {
@@ -191,7 +207,7 @@ func ordered(a, b float64) (float64, float64) {
 	return b, a
 }
 
-func drawTextAnnotation(img *image.RGBA, ann Annotation, scale float64, c color.RGBA) {
+func drawTextAnnotation(img *image.RGBA, ann Annotation, scaleX, scaleY float64, c color.RGBA) {
 	if len(ann.Points) == 0 {
 		return
 	}
@@ -199,16 +215,20 @@ func drawTextAnnotation(img *image.RGBA, ann Annotation, scale float64, c color.
 	if text == "" {
 		return
 	}
-	face := annotationFontFace(20 * scale)
+	fontSize := ann.FontSize
+	if fontSize <= 0 {
+		fontSize = 20
+	}
+	face := annotationFontFace(fontSize * scaleY)
 	if face == nil {
 		face = basicfont.Face7x13
 	}
 
-	origin := scalePoint(ann.Points[0], scale)
+	origin := scalePoint(ann.Points[0], scaleX, scaleY)
 	metrics := face.Metrics()
 	lineHeight := metrics.Height
 	if lineHeight <= 0 {
-		lineHeight = fixed.I(int(math.Ceil(24 * scale)))
+		lineHeight = fixed.I(int(math.Ceil(fontSize * 1.2 * scaleY)))
 	}
 	d := &xfont.Drawer{
 		Dst:  img,

internal/application/annotation_test.go

@@ -93,3 +93,81 @@ func TestApplyAnnotationsDrawsTextIntoPNG(t *testing.T) {
 		t.Fatalf("expected red text pixels near annotation point")
 	}
 }
+
+func TestApplyAnnotationsWithScaleDrawsTextAtDevicePosition(t *testing.T) {
+	src := image.NewRGBA(image.Rect(0, 0, 220, 120))
+	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 := ApplyAnnotationsWithScale(buf.Bytes(), []Annotation{
+		{
+			Tool:     "text",
+			Color:    "#ef4444",
+			Points:   []Point{{X: 50, Y: 20}},
+			Text:     "T",
+			FontSize: 20,
+		},
+	}, 2, 2)
+	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)
+	}
+	minX := 999
+	found := false
+	for y := 0; y < img.Bounds().Dy(); y++ {
+		for x := 0; x < img.Bounds().Dx(); x++ {
+			got := color.RGBAModel.Convert(img.At(x, y)).(color.RGBA)
+			if got.R > 180 && got.G < 180 && got.B < 180 {
+				found = true
+				if x < minX {
+					minX = x
+				}
+			}
+		}
+	}
+	if !found {
+		t.Fatalf("expected red text pixels")
+	}
+	if minX < 90 {
+		t.Fatalf("expected text to be drawn near scaled x=100, min red x=%d", minX)
+	}
+}
+
+func TestApplyAnnotationsUsesStrokeWidth(t *testing.T) {
+	src := image.NewRGBA(image.Rect(0, 0, 80, 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:        "rect",
+			Color:       "#ef4444",
+			Points:      []Point{{X: 20, Y: 20}, {X: 60, Y: 60}},
+			StrokeWidth: 8,
+		},
+	}, 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)
+	}
+	got := color.RGBAModel.Convert(img.At(20, 24)).(color.RGBA)
+	if got.R < 180 || got.G > 180 || got.B > 180 {
+		t.Fatalf("expected thick rectangle stroke to cover y=24, got %#v", got)
+	}
+}

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;
@@ -81,6 +82,50 @@ static id nativeOverlayKeyMonitor = nil;
 }
 @end
 
+@interface SnipToolSettingsView : NSView
+@property CGFloat arrowX;
+@end
+
+@implementation SnipToolSettingsView
+- (BOOL)isFlipped { return YES; }
+- (void)drawRect:(NSRect)dirtyRect {
+    [[NSColor clearColor] setFill];
+    NSRectFill(dirtyRect);
+
+    CGFloat arrowHalf = 8;
+    CGFloat arrowH = 9;
+    CGFloat radius = 8;
+    NSRect body = NSMakeRect(0, arrowH, self.bounds.size.width, self.bounds.size.height - arrowH);
+    CGFloat arrowX = MAX(18, MIN(_arrowX, self.bounds.size.width - 18));
+
+    NSBezierPath *path = [NSBezierPath bezierPath];
+    [path moveToPoint:NSMakePoint(NSMinX(body) + radius, NSMinY(body))];
+    [path lineToPoint:NSMakePoint(arrowX - arrowHalf, NSMinY(body))];
+    [path lineToPoint:NSMakePoint(arrowX, 0)];
+    [path lineToPoint:NSMakePoint(arrowX + arrowHalf, NSMinY(body))];
+    [path lineToPoint:NSMakePoint(NSMaxX(body) - radius, NSMinY(body))];
+    [path curveToPoint:NSMakePoint(NSMaxX(body), NSMinY(body) + radius)
+         controlPoint1:NSMakePoint(NSMaxX(body) - radius / 2, NSMinY(body))
+         controlPoint2:NSMakePoint(NSMaxX(body), NSMinY(body) + radius / 2)];
+    [path lineToPoint:NSMakePoint(NSMaxX(body), NSMaxY(body) - radius)];
+    [path curveToPoint:NSMakePoint(NSMaxX(body) - radius, NSMaxY(body))
+         controlPoint1:NSMakePoint(NSMaxX(body), NSMaxY(body) - radius / 2)
+         controlPoint2:NSMakePoint(NSMaxX(body) - radius / 2, NSMaxY(body))];
+    [path lineToPoint:NSMakePoint(NSMinX(body) + radius, NSMaxY(body))];
+    [path curveToPoint:NSMakePoint(NSMinX(body), NSMaxY(body) - radius)
+         controlPoint1:NSMakePoint(NSMinX(body) + radius / 2, NSMaxY(body))
+         controlPoint2:NSMakePoint(NSMinX(body), NSMaxY(body) - radius / 2)];
+    [path lineToPoint:NSMakePoint(NSMinX(body), NSMinY(body) + radius)];
+    [path curveToPoint:NSMakePoint(NSMinX(body) + radius, NSMinY(body))
+         controlPoint1:NSMakePoint(NSMinX(body), NSMinY(body) + radius / 2)
+         controlPoint2:NSMakePoint(NSMinX(body) + radius / 2, NSMinY(body))];
+    [path closePath];
+
+    [[NSColor colorWithCalibratedWhite:1 alpha:0.96] setFill];
+    [path fill];
+}
+@end
+
 @interface SnipNativeOverlayView : NSView
 @property BOOL hasSelection;
 @property BOOL creating;
@@ -94,6 +139,8 @@ static id nativeOverlayKeyMonitor = nil;
 @property NSString *resizeHandle;
 @property NSString *activeTool;
 @property(strong) NSColor *activeColor;
+@property CGFloat activeStrokeWidth;
+@property CGFloat activeFontSize;
 @property(strong) NSMutableArray<NSDictionary *> *annotations;
 @property(strong) NSMutableDictionary *draftAnnotation;
 @property(strong) NSButton *cancelButton;
@@ -103,18 +150,28 @@ 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) SnipToolSettingsView *toolSettingsView;
+@property(strong) NSView *settingsDivider;
+@property(strong) NSMutableArray<NSButton *> *strokeSettingButtons;
+@property(strong) NSMutableArray<NSButton *> *fontSettingButtons;
+@property(strong) NSMutableArray<NSButton *> *colorSettingButtons;
 @property(strong) NSView *actionToolbarBg;
 @property(strong) NSTextField *textEditor;
 @property NSPoint textEditorLocalPoint;
+@property NSInteger textEditorAnnotationIndex;
+@property(strong) NSColor *textEditorColor;
+@property NSInteger selectedTextAnnotationIndex;
+@property BOOL draggingTextAnnotation;
+@property NSPoint textDragStartLocalPoint;
+@property NSPoint textDragOriginalLocalPoint;
 @property(strong) NSTextField *sizeLabel;
 @property(strong) NSTextField *hintLabel;
 - (void)syncControls;
@@ -124,9 +181,17 @@ static id nativeOverlayKeyMonitor = nil;
 - (void)copySelection;
 - (void)saveSelection;
 - (void)saveRemoteSelection;
+- (void)ocrSelection;
 - (void)summarizeSelection;
 - (void)cancelSelection;
 - (void)beginTextAnnotationAtPoint:(NSPoint)localPoint;
+- (void)beginEditingTextAnnotationAtIndex:(NSInteger)index;
+- (NSInteger)textAnnotationIndexAtPoint:(NSPoint)p;
+- (NSRect)textAnnotationRectForItem:(NSDictionary *)item;
+- (NSPoint)clampedTextLocalPoint:(NSPoint)localPoint text:(NSString *)text fontSize:(CGFloat)fontSize;
+- (void)selectStrokeWidth:(NSButton *)sender;
+- (void)selectFontSize:(NSButton *)sender;
+- (void)selectToolColor:(NSButton *)sender;
 - (BOOL)isEditingText;
 - (void)commitTextEditor;
 - (void)cancelTextEditor;
@@ -144,15 +209,20 @@ static id nativeOverlayKeyMonitor = nil;
 
         _activeTool = nil;
         _activeColor = [NSColor colorWithCalibratedRed:239.0/255.0 green:68.0/255.0 blue:68.0/255.0 alpha:1.0];
+        _activeStrokeWidth = 3.0;
+        _activeFontSize = 20.0;
         _annotations = [NSMutableArray array];
+        _textEditorAnnotationIndex = -1;
+        _selectedTextAnnotationIndex = -1;
 
-        // 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.
@@ -161,15 +231,19 @@ 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];
+        _toolSettingsView = [[SnipToolSettingsView alloc] initWithFrame:NSZeroRect];
+        _settingsDivider = [[NSView alloc] initWithFrame:NSZeroRect];
+        _strokeSettingButtons = [NSMutableArray array];
+        _fontSettingButtons = [NSMutableArray array];
+        _colorSettingButtons = [NSMutableArray array];
         // Dark rounded background container behind the action icon buttons,
         // mirroring the look of `.action-toolbar` in the Vue overlay.
         _actionToolbarBg = [[NSView alloc] initWithFrame:NSZeroRect];
@@ -183,10 +257,10 @@ 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, _textButton, _colorButton, _undoButton, _paletteView, _sizeLabel, _hintLabel]) {
+        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _ocrButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _textButton, _undoButton, _toolSettingsView, _sizeLabel, _hintLabel]) {
             [self addSubview:view];
         }
-        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _textButton, _colorButton, _undoButton, _paletteView, _actionToolbarBg]) {
+        for (NSView *view in @[_cancelButton, _clipboardButton, _saveButton, _saveRemoteButton, _ocrButton, _summaryButton, _uploadButton, _penButton, _rectButton, _ellipseButton, _textButton, _undoButton, _toolSettingsView, _actionToolbarBg]) {
             [view setHidden:YES];
         }
         [_sizeLabel setHidden:YES];
@@ -249,8 +323,8 @@ static id nativeOverlayKeyMonitor = nil;
 }
 
 - (void)styleControls {
-    // Cancel / Copy / Save / Save-remote / Upload — square icon buttons
-    // rendered from the user-supplied SVG assets. All five default to white
+    // Cancel / Copy / Save / Save-remote / OCR / Summary / Upload — square icon buttons
+    // 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.
@@ -260,6 +334,7 @@ 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>"];
@@ -268,10 +343,11 @@ 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];
@@ -281,12 +357,14 @@ 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;
 
@@ -294,11 +372,62 @@ static id nativeOverlayKeyMonitor = nil;
     [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];
-    [[_paletteView layer] setCornerRadius:8];
-    [[_paletteView layer] setBackgroundColor:[[NSColor colorWithCalibratedWhite:0.11 alpha:0.96] CGColor]];
+
+    [_toolSettingsView setWantsLayer:NO];
+    [_settingsDivider setWantsLayer:YES];
+    [[_settingsDivider layer] setBackgroundColor:[[NSColor colorWithCalibratedWhite:0.82 alpha:1] CGColor]];
+    [_toolSettingsView addSubview:_settingsDivider];
+
+    for (NSNumber *width in @[@2, @4, @6]) {
+        NSButton *button = [NSButton buttonWithTitle:@"●" target:self action:@selector(selectStrokeWidth:)];
+        [button setTag:[width integerValue]];
+        [button setBordered:NO];
+        [button setWantsLayer:YES];
+        [[button layer] setCornerRadius:6];
+        NSMutableAttributedString *title = [[NSMutableAttributedString alloc] initWithString:@"●"];
+        [title addAttribute:NSFontAttributeName value:[NSFont systemFontOfSize:8 + [width doubleValue] * 2 weight:NSFontWeightBold] range:NSMakeRange(0, title.length)];
+        [button setAttributedTitle:title];
+        [_strokeSettingButtons addObject:button];
+        [_toolSettingsView addSubview:button];
+    }
+
+    for (NSNumber *size in @[@16, @20, @28, @36]) {
+        NSButton *button = [NSButton buttonWithTitle:[NSString stringWithFormat:@"%ld", (long)[size integerValue]] target:self action:@selector(selectFontSize:)];
+        [button setTag:[size integerValue]];
+        [button setBordered:NO];
+        [button setWantsLayer:YES];
+        [[button layer] setCornerRadius:6];
+        NSMutableAttributedString *title = [[NSMutableAttributedString alloc] initWithString:[button title]];
+        [title addAttribute:NSForegroundColorAttributeName value:[NSColor colorWithCalibratedWhite:0.12 alpha:1] range:NSMakeRange(0, title.length)];
+        [title addAttribute:NSFontAttributeName value:[NSFont systemFontOfSize:13 weight:NSFontWeightBold] range:NSMakeRange(0, title.length)];
+        [button setAttributedTitle:title];
+        [_fontSettingButtons addObject:button];
+        [_toolSettingsView addSubview:button];
+    }
+
+    NSArray *colors = @[
+        [NSColor colorWithCalibratedRed:239.0/255.0 green:68.0/255.0 blue:68.0/255.0 alpha:1.0],
+        [NSColor colorWithCalibratedRed:250.0/255.0 green:204.0/255.0 blue:21.0/255.0 alpha:1.0],
+        [NSColor colorWithCalibratedRed:34.0/255.0 green:197.0/255.0 blue:94.0/255.0 alpha:1.0],
+        [NSColor colorWithCalibratedRed:59.0/255.0 green:130.0/255.0 blue:246.0/255.0 alpha:1.0],
+        [NSColor colorWithCalibratedWhite:0.0 alpha:1.0],
+        [NSColor colorWithCalibratedRed:156.0/255.0 green:163.0/255.0 blue:175.0/255.0 alpha:1.0],
+        [NSColor whiteColor]
+    ];
+    for (NSUInteger i = 0; i < colors.count; i++) {
+        NSButton *button = [NSButton buttonWithTitle:@"" target:self action:@selector(selectToolColor:)];
+        [button setTag:(NSInteger)i];
+        [button setBordered:NO];
+        [button setWantsLayer:YES];
+        [[button layer] setCornerRadius:4];
+        [[button layer] setBorderWidth:1];
+        [[button layer] setBorderColor:[[NSColor colorWithCalibratedWhite:0.12 alpha:0.22] CGColor]];
+        [[button layer] setBackgroundColor:[colors[i] CGColor]];
+        [_colorSettingButtons addObject:button];
+        [_toolSettingsView addSubview:button];
+    }
+    objc_setAssociatedObject(_toolSettingsView, "snapgoColors", colors, OBJC_ASSOCIATION_RETAIN_NONATOMIC);
 }
 
 - (void)drawRect:(NSRect)dirtyRect {
@@ -364,12 +493,107 @@ static id nativeOverlayKeyMonitor = nil;
     }
 }
 
+- (CGFloat)fontSizeForTextItem:(NSDictionary *)item {
+    NSNumber *fontSize = item[@"fontSize"];
+    if (fontSize != nil && [fontSize doubleValue] > 0) {
+        return [fontSize doubleValue];
+    }
+    return 20.0;
+}
+
+- (CGFloat)strokeWidthForItem:(NSDictionary *)item {
+    NSNumber *strokeWidth = item[@"strokeWidth"];
+    if (strokeWidth != nil && [strokeWidth doubleValue] > 0) {
+        return [strokeWidth doubleValue];
+    }
+    return 3.0;
+}
+
+- (NSDictionary *)textAttributesWithFontSize:(CGFloat)fontSize color:(NSColor *)color {
+    return @{
+        NSFontAttributeName: [NSFont systemFontOfSize:fontSize weight:NSFontWeightSemibold],
+        NSForegroundColorAttributeName: color ?: [NSColor whiteColor]
+    };
+}
+
+- (NSSize)textSizeForString:(NSString *)text fontSize:(CGFloat)fontSize {
+    NSString *measured = text.length > 0 ? text : @" ";
+    NSDictionary *attrs = [self textAttributesWithFontSize:fontSize color:[NSColor whiteColor]];
+    NSRect bounds = [measured boundingRectWithSize:NSMakeSize(CGFLOAT_MAX, CGFLOAT_MAX)
+                                           options:NSStringDrawingUsesLineFragmentOrigin | NSStringDrawingUsesFontLeading
+                                        attributes:attrs];
+    return NSMakeSize(ceil(MAX(1.0, bounds.size.width)), ceil(MAX(fontSize * 1.2, bounds.size.height)));
+}
+
+- (NSSize)textEditorSizeForString:(NSString *)text fontSize:(CGFloat)fontSize {
+    NSSize textSize = [self textSizeForString:text fontSize:fontSize];
+    return NSMakeSize(MAX(180, MIN(420, textSize.width + 28)), MAX(30, ceil(fontSize * 1.6)));
+}
+
+- (NSRect)textEditorFrameForLocalPoint:(NSPoint)localPoint text:(NSString *)text fontSize:(CGFloat)fontSize {
+    NSSize editorSize = [self textEditorSizeForString:text fontSize:fontSize];
+    NSPoint clampedLocal = [self clampedTextLocalPoint:localPoint text:text fontSize:fontSize];
+    NSRect frame = NSMakeRect(_selection.origin.x + clampedLocal.x, _selection.origin.y + clampedLocal.y, editorSize.width, editorSize.height);
+    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));
+    return frame;
+}
+
+- (void)resizeTextEditorForCurrentFont {
+    if (_textEditor == nil) {
+        return;
+    }
+    NSString *text = [_textEditor stringValue] ?: @"";
+    NSRect frame = [self textEditorFrameForLocalPoint:_textEditorLocalPoint text:text fontSize:_activeFontSize];
+    [_textEditor setFrame:frame];
+    _textEditorLocalPoint = [self localPoint:frame.origin];
+}
+
+- (NSRect)textAnnotationRectForItem:(NSDictionary *)item {
+    if (![item[@"tool"] isEqualToString:@"text"]) {
+        return NSZeroRect;
+    }
+    NSArray *points = item[@"points"];
+    NSString *text = item[@"text"];
+    if (points.count == 0 || text.length == 0) {
+        return NSZeroRect;
+    }
+    NSPoint p = [points[0] pointValue];
+    CGFloat fontSize = [self fontSizeForTextItem:item];
+    NSSize size = [self textSizeForString:text fontSize:fontSize];
+    return NSMakeRect(_selection.origin.x + p.x, _selection.origin.y + p.y, size.width, size.height);
+}
+
+- (NSPoint)clampedTextLocalPoint:(NSPoint)localPoint text:(NSString *)text fontSize:(CGFloat)fontSize {
+    NSSize size = [self textSizeForString:text fontSize:fontSize];
+    CGFloat maxX = MAX(0, _selection.size.width - size.width);
+    CGFloat maxY = MAX(0, _selection.size.height - size.height);
+    return NSMakePoint(MAX(0, MIN(localPoint.x, maxX)), MAX(0, MIN(localPoint.y, maxY)));
+}
+
+- (NSInteger)textAnnotationIndexAtPoint:(NSPoint)p {
+    for (NSInteger i = (NSInteger)_annotations.count - 1; i >= 0; i--) {
+        NSDictionary *item = _annotations[(NSUInteger)i];
+        if (![item[@"tool"] isEqualToString:@"text"]) {
+            continue;
+        }
+        NSRect hitRect = NSInsetRect([self textAnnotationRectForItem:item], -6, -6);
+        if (!NSIsEmptyRect(hitRect) && NSPointInRect(p, hitRect)) {
+            return i;
+        }
+    }
+    return -1;
+}
+
 - (void)drawAnnotations {
     NSMutableArray *items = [NSMutableArray arrayWithArray:_annotations];
     if (_draftAnnotation != nil) {
         [items addObject:_draftAnnotation];
     }
-    for (NSDictionary *item in items) {
+    for (NSUInteger index = 0; index < items.count; index++) {
+        NSDictionary *item = items[index];
         NSString *tool = item[@"tool"];
         NSColor *color = item[@"nsColor"];
         NSArray *points = item[@"points"];
@@ -382,16 +606,24 @@ static id nativeOverlayKeyMonitor = nil;
                 continue;
             }
             NSPoint p = [points[0] pointValue];
-            NSDictionary *attrs = @{
-                NSFontAttributeName: [NSFont systemFontOfSize:20 weight:NSFontWeightSemibold],
-                NSForegroundColorAttributeName: color ?: [NSColor whiteColor]
-            };
+            CGFloat fontSize = [self fontSizeForTextItem:item];
+            NSDictionary *attrs = [self textAttributesWithFontSize:fontSize color:color];
             [text drawAtPoint:NSMakePoint(_selection.origin.x + p.x, _selection.origin.y + p.y) withAttributes:attrs];
+            if ((NSInteger)index == _selectedTextAnnotationIndex && index < _annotations.count) {
+                NSRect rect = NSInsetRect([self textAnnotationRectForItem:item], -4, -3);
+                NSBezierPath *selectionPath = [NSBezierPath bezierPathWithRoundedRect:rect xRadius:4 yRadius:4];
+                [selectionPath setLineWidth:1.5];
+                CGFloat dash[] = {4.0, 3.0};
+                [selectionPath setLineDash:dash count:2 phase:0];
+                [[NSColor colorWithCalibratedRed:59.0/255.0 green:130.0/255.0 blue:246.0/255.0 alpha:0.95] setStroke];
+                [selectionPath stroke];
+            }
             continue;
         }
         [color setStroke];
+        CGFloat strokeWidth = [self strokeWidthForItem:item];
         NSBezierPath *path = [NSBezierPath bezierPath];
-        [path setLineWidth:3];
+        [path setLineWidth:strokeWidth];
         [path setLineCapStyle:NSLineCapStyleRound];
         [path setLineJoinStyle:NSLineJoinStyleRound];
         if ([tool isEqualToString:@"pen"]) {
@@ -412,11 +644,11 @@ static id nativeOverlayKeyMonitor = nil;
                 fabs(b.y - a.y));
             if ([tool isEqualToString:@"rect"]) {
                 NSBezierPath *rectPath = [NSBezierPath bezierPathWithRect:r];
-                [rectPath setLineWidth:3];
+                [rectPath setLineWidth:strokeWidth];
                 [rectPath stroke];
             } else if ([tool isEqualToString:@"ellipse"]) {
                 NSBezierPath *ellipsePath = [NSBezierPath bezierPathWithOvalInRect:r];
-                [ellipsePath setLineWidth:3];
+                [ellipsePath setLineWidth:strokeWidth];
                 [ellipsePath stroke];
             }
         }
@@ -501,6 +733,7 @@ static id nativeOverlayKeyMonitor = nil;
     if (_textEditor != nil) {
         [self commitTextEditor];
     }
+    _draggingTextAnnotation = NO;
     NSString *handle = [self resizeHandleAtPoint:p];
     if (handle != nil) {
         _resizing = YES;
@@ -512,6 +745,34 @@ static id nativeOverlayKeyMonitor = nil;
         [self syncControls];
         return;
     }
+    NSInteger textIndex = _hasSelection ? [self textAnnotationIndexAtPoint:p] : -1;
+    if (textIndex >= 0) {
+        _selectedTextAnnotationIndex = textIndex;
+        NSDictionary *item = _annotations[(NSUInteger)textIndex];
+        _activeTool = @"text";
+        _activeColor = item[@"nsColor"] ?: _activeColor;
+        _activeFontSize = [self fontSizeForTextItem:item];
+        _creating = NO;
+        _moving = NO;
+        _resizing = NO;
+        _annotating = NO;
+        if ([event clickCount] >= 2) {
+            [self beginEditingTextAnnotationAtIndex:textIndex];
+            [self syncControls];
+            [self setNeedsDisplay:YES];
+            return;
+        }
+        NSArray *points = item[@"points"];
+        if (points.count > 0) {
+            _draggingTextAnnotation = YES;
+            _textDragStartLocalPoint = [self localPoint:p];
+            _textDragOriginalLocalPoint = [points[0] pointValue];
+        }
+        [self syncControls];
+        [self setNeedsDisplay:YES];
+        return;
+    }
+    _selectedTextAnnotationIndex = -1;
     if (_hasSelection && NSPointInRect(p, _selection) && [_activeTool isEqualToString:@"text"]) {
         _creating = NO;
         _moving = NO;
@@ -535,6 +796,7 @@ static id nativeOverlayKeyMonitor = nil;
             @"tool": _activeTool,
             @"color": [self hexForColor:_activeColor],
             @"nsColor": _activeColor,
+            @"strokeWidth": @(_activeStrokeWidth),
             @"points": [NSMutableArray arrayWithObject:[NSValue valueWithPoint:local]]
         } mutableCopy];
     } else if (_hasSelection && NSPointInRect(p, _selection)) {
@@ -553,6 +815,7 @@ static id nativeOverlayKeyMonitor = nil;
         _selection = NSMakeRect(p.x, p.y, 0, 0);
         [_annotations removeAllObjects];
         _draftAnnotation = nil;
+        _selectedTextAnnotationIndex = -1;
     }
     [self syncControls];
 }
@@ -583,6 +846,17 @@ static id nativeOverlayKeyMonitor = nil;
         top = MAX(0, MIN(top, self.bounds.size.height));
         bottom = MAX(0, MIN(bottom, self.bounds.size.height));
         _selection = NSMakeRect(MIN(left, right), MIN(top, bottom), fabs(right - left), fabs(bottom - top));
+    } else if (_draggingTextAnnotation && _selectedTextAnnotationIndex >= 0 && _selectedTextAnnotationIndex < (NSInteger)_annotations.count) {
+        NSMutableDictionary *item = (NSMutableDictionary *)_annotations[(NSUInteger)_selectedTextAnnotationIndex];
+        NSMutableArray *points = (NSMutableArray *)item[@"points"];
+        if (points.count > 0) {
+            NSPoint local = [self localPoint:p];
+            NSPoint delta = NSMakePoint(local.x - _textDragStartLocalPoint.x, local.y - _textDragStartLocalPoint.y);
+            NSPoint next = NSMakePoint(_textDragOriginalLocalPoint.x + delta.x, _textDragOriginalLocalPoint.y + delta.y);
+            NSString *text = item[@"text"] ?: @"";
+            CGFloat fontSize = [self fontSizeForTextItem:item];
+            points[0] = [NSValue valueWithPoint:[self clampedTextLocalPoint:next text:text fontSize:fontSize]];
+        }
     } else if (_annotating && _draftAnnotation != nil) {
         NSMutableArray *points = _draftAnnotation[@"points"];
         NSPoint local = [self localPoint:p];
@@ -604,6 +878,7 @@ static id nativeOverlayKeyMonitor = nil;
     _creating = NO;
     _moving = NO;
     _resizing = NO;
+    _draggingTextAnnotation = NO;
     if (_annotating && _draftAnnotation != nil) {
         [_annotations addObject:_draftAnnotation];
         _draftAnnotation = nil;
@@ -646,6 +921,7 @@ 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];
@@ -653,8 +929,8 @@ static id nativeOverlayKeyMonitor = nil;
     [_rectButton setHidden:!visible];
     [_ellipseButton setHidden:!visible];
     [_textButton setHidden:!visible];
-    [_colorButton setHidden:!visible];
     [_undoButton setHidden:!visible];
+    [_toolSettingsView setHidden:!visible || _activeTool == nil];
     [_sizeLabel setHidden:!visible];
     [_hintLabel setHidden:_hasSelection];
 
@@ -665,12 +941,12 @@ 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,
-    // with 4px outer padding. Total = 6*28 + 5*8 + 2*4 = 216px wide.
+    // Action toolbar layout — 7 icon buttons, each 28x28, separated by 8px,
+    // 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;
@@ -688,23 +964,62 @@ 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)];
-    [_uploadButton     setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 5, btnY, actionBtnSize, actionBtnSize)];
+    [_ocrButton        setFrame:NSMakeRect(baseX + (actionBtnSize + actionGap) * 4, 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 = 202;
+    CGFloat markW = 178;
     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)];
-    [_textButton setFrame:NSMakeRect(markX + 100, 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)];
+    [_rectButton setFrame:NSMakeRect(markX + 38, y + 4, 28, 28)];
+    [_ellipseButton setFrame:NSMakeRect(markX + 72, y + 4, 28, 28)];
+    [_textButton setFrame:NSMakeRect(markX + 106, y + 4, 28, 28)];
+    [_undoButton setFrame:NSMakeRect(markX + 144, y + 4, 28, 28)];
+    [_undoButton setEnabled:YES];
+    [[_undoButton layer] setOpacity:_annotations.count > 0 ? 1.0 : 0.35];
+
+    if (_activeTool != nil) {
+        BOOL isText = [_activeTool isEqualToString:@"text"];
+        CGFloat settingsW = isText ? 462 : 398;
+        CGFloat settingsH = 58;
+        CGFloat settingsX = MAX(8, MIN(markX, self.bounds.size.width - settingsW - 8));
+        CGFloat settingsY = y + toolbarH + 4;
+        if (settingsY + settingsH > self.bounds.size.height) {
+            settingsY = y - settingsH - 8;
+        }
+        CGFloat activeCenter = markX + 18;
+        if ([_activeTool isEqualToString:@"rect"]) activeCenter = markX + 52;
+        if ([_activeTool isEqualToString:@"ellipse"]) activeCenter = markX + 86;
+        if ([_activeTool isEqualToString:@"text"]) activeCenter = markX + 120;
+        [_toolSettingsView setFrame:NSMakeRect(settingsX, settingsY, settingsW, settingsH)];
+        [_toolSettingsView setArrowX:MAX(18, MIN(activeCenter - settingsX, settingsW - 18))];
+        [_toolSettingsView setNeedsDisplay:YES];
+
+        CGFloat contentY = 18;
+        CGFloat xCursor = 14;
+        for (NSButton *button in _strokeSettingButtons) {
+            [button setHidden:isText];
+            [button setFrame:NSMakeRect(xCursor, contentY, 32, 32)];
+            xCursor += 42;
+        }
+        xCursor = 14;
+        for (NSButton *button in _fontSettingButtons) {
+            [button setHidden:!isText];
+            [button setFrame:NSMakeRect(xCursor, contentY, 40, 32)];
+            xCursor += 48;
+        }
+        CGFloat groupW = isText ? (4 * 40 + 3 * 8) : (3 * 32 + 2 * 10);
+        CGFloat dividerX = 14 + groupW + 12;
+        [_settingsDivider setFrame:NSMakeRect(dividerX, contentY + 3, 1, 26)];
+        CGFloat colorX = dividerX + 18;
+        for (NSButton *button in _colorSettingButtons) {
+            [button setFrame:NSMakeRect(colorX, contentY + 5, 22, 22)];
+            colorX += 34;
+        }
+    }
     [self updateToolButtonStates];
 }
 
@@ -717,46 +1032,125 @@ static id nativeOverlayKeyMonitor = nil;
             : [NSColor clearColor];
         [[button layer] setBackgroundColor:[bg CGColor]];
     }
+    [self updateToolSettingsStates];
 }
 
-- (void)toggleTool:(NSString *)tool {
-    _activeTool = [_activeTool isEqualToString:tool] ? nil : tool;
-    [self syncControls];
-}
-- (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];
-        [self setNeedsDisplay:YES];
+- (void)updateToolSettingsStates {
+    NSColor *activeBg = [NSColor colorWithCalibratedRed:234.0/255.0 green:241.0/255.0 blue:1.0 alpha:1.0];
+    NSColor *clear = [NSColor clearColor];
+    NSColor *activeFg = [NSColor colorWithCalibratedRed:37.0/255.0 green:99.0/255.0 blue:235.0/255.0 alpha:1.0];
+    NSColor *normalFg = [NSColor colorWithCalibratedWhite:0.12 alpha:1.0];
+
+    for (NSButton *button in _strokeSettingButtons) {
+        BOOL active = fabs((CGFloat)button.tag - _activeStrokeWidth) < 0.1;
+        [[button layer] setBackgroundColor:[(active ? activeBg : clear) CGColor]];
+        NSMutableAttributedString *title = [[button attributedTitle] mutableCopy];
+        if (title.length > 0) {
+            [title addAttribute:NSForegroundColorAttributeName value:(active ? activeFg : normalFg) range:NSMakeRange(0, title.length)];
+            [button setAttributedTitle:title];
+        }
+    }
+    for (NSButton *button in _fontSettingButtons) {
+        BOOL active = fabs((CGFloat)button.tag - _activeFontSize) < 0.1;
+        [[button layer] setBackgroundColor:[(active ? activeBg : clear) CGColor]];
+        NSMutableAttributedString *title = [[button attributedTitle] mutableCopy];
+        if (title.length > 0) {
+            [title addAttribute:NSForegroundColorAttributeName value:(active ? activeFg : normalFg) range:NSMakeRange(0, title.length)];
+            [button setAttributedTitle:title];
+        }
+    }
+
+    NSString *activeHex = [self hexForColor:_activeColor];
+    NSArray *colors = objc_getAssociatedObject(_toolSettingsView, "snapgoColors");
+    for (NSUInteger i = 0; i < _colorSettingButtons.count; i++) {
+        NSButton *button = _colorSettingButtons[i];
+        NSString *hex = i < colors.count ? [self hexForColor:colors[i]] : @"";
+        BOOL active = [hex isEqualToString:activeHex];
+        [[button layer] setBorderWidth:active ? 2 : 1];
+        [[button layer] setBorderColor:[(active ? activeFg : [NSColor colorWithCalibratedWhite:0.12 alpha:0.22]) CGColor]];
     }
 }
 
-- (void)beginTextAnnotationAtPoint:(NSPoint)localPoint {
+- (void)selectTool:(NSString *)tool {
+    _activeTool = tool;
+    [self syncControls];
+}
+- (void)selectPen { [self selectTool:@"pen"]; }
+- (void)selectRect { [self selectTool:@"rect"]; }
+- (void)selectEllipse { [self selectTool:@"ellipse"]; }
+- (void)selectText { [self selectTool:@"text"]; }
+- (void)undoAnnotation {
+    if (_annotations.count == 0 && _textEditor == nil) {
+        return;
+    }
     [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));
+    if (_annotations.count == 0) {
+        [self syncControls];
+        [self setNeedsDisplay:YES];
+        return;
+    }
+    [_annotations removeLastObject];
+    if (_selectedTextAnnotationIndex >= (NSInteger)_annotations.count) {
+        _selectedTextAnnotationIndex = -1;
+    }
+    [self syncControls];
+    [self setNeedsDisplay:YES];
+}
+
+- (void)beginTextAnnotationAtPoint:(NSPoint)localPoint {
+    [self beginTextEditorAtLocalPoint:localPoint text:@"" color:_activeColor annotationIndex:-1];
+}
+
+- (void)beginEditingTextAnnotationAtIndex:(NSInteger)index {
+    if (index < 0 || index >= (NSInteger)_annotations.count) {
+        return;
+    }
+    NSDictionary *item = _annotations[(NSUInteger)index];
+    if (![item[@"tool"] isEqualToString:@"text"]) {
+        return;
+    }
+    NSArray *points = item[@"points"];
+    if (points.count == 0) {
+        return;
+    }
+    NSColor *color = item[@"nsColor"] ?: _activeColor;
+    _activeColor = color;
+    _activeFontSize = [self fontSizeForTextItem:item];
+    [self beginTextEditorAtLocalPoint:[points[0] pointValue]
+                                 text:item[@"text"] ?: @""
+                                color:color
+                      annotationIndex:index];
+}
+
+- (void)beginTextEditorAtLocalPoint:(NSPoint)localPoint text:(NSString *)text color:(NSColor *)color annotationIndex:(NSInteger)index {
+    [self cancelTextEditor];
+    CGFloat fontSize = _activeFontSize;
+    if (index >= 0 && index < (NSInteger)_annotations.count) {
+        fontSize = [self fontSizeForTextItem:_annotations[(NSUInteger)index]];
+        _activeFontSize = fontSize;
+    }
+    NSPoint clampedLocal = [self clampedTextLocalPoint:localPoint text:text fontSize:fontSize];
+    _textEditorLocalPoint = clampedLocal;
+    _textEditorAnnotationIndex = index;
+    _textEditorColor = color ?: _activeColor;
+
+    NSRect frame = [self textEditorFrameForLocalPoint:clampedLocal text:text fontSize:fontSize];
+    _textEditorLocalPoint = [self localPoint:frame.origin];
 
     _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 setTextColor:_textEditorColor];
+    [_textEditor setFont:[NSFont systemFontOfSize:fontSize weight:NSFontWeightSemibold]];
+    [_textEditor setStringValue:text ?: @""];
     [_textEditor setFocusRingType:NSFocusRingTypeNone];
     [_textEditor setTarget:self];
     [_textEditor setAction:@selector(commitTextEditorFromSender:)];
     [self addSubview:_textEditor];
     [[self window] makeFirstResponder:_textEditor];
+    [_textEditor selectText:nil];
 }
 
 - (BOOL)isEditingText {
@@ -772,17 +1166,35 @@ static id nativeOverlayKeyMonitor = nil;
         return;
     }
     NSString *text = [[_textEditor stringValue] stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceAndNewlineCharacterSet]];
+    NSColor *textColor = _textEditorColor ?: _activeColor;
+    if (_textEditorAnnotationIndex >= 0 && _textEditorAnnotationIndex < (NSInteger)_annotations.count) {
         if (text.length > 0) {
+            NSMutableDictionary *item = (NSMutableDictionary *)_annotations[(NSUInteger)_textEditorAnnotationIndex];
+            item[@"color"] = [self hexForColor:textColor];
+            item[@"nsColor"] = textColor;
+            item[@"points"] = [NSMutableArray arrayWithObject:[NSValue valueWithPoint:_textEditorLocalPoint]];
+            item[@"text"] = text;
+            item[@"fontSize"] = @(_activeFontSize);
+            _selectedTextAnnotationIndex = _textEditorAnnotationIndex;
+        } else {
+            [_annotations removeObjectAtIndex:(NSUInteger)_textEditorAnnotationIndex];
+            _selectedTextAnnotationIndex = -1;
+        }
+    } else if (text.length > 0) {
         [_annotations addObject:[@{
             @"tool": @"text",
-            @"color": [self hexForColor:_activeColor],
-            @"nsColor": _activeColor,
+            @"color": [self hexForColor:textColor],
+            @"nsColor": textColor,
             @"points": [NSMutableArray arrayWithObject:[NSValue valueWithPoint:_textEditorLocalPoint]],
-            @"text": text
+            @"text": text,
+            @"fontSize": @(_activeFontSize)
         } mutableCopy]];
+        _selectedTextAnnotationIndex = (NSInteger)_annotations.count - 1;
     }
     [_textEditor removeFromSuperview];
     _textEditor = nil;
+    _textEditorAnnotationIndex = -1;
+    _textEditorColor = nil;
     [[self window] makeFirstResponder:self];
     [self syncControls];
     [self setNeedsDisplay:YES];
@@ -794,44 +1206,50 @@ static id nativeOverlayKeyMonitor = nil;
     }
     [_textEditor removeFromSuperview];
     _textEditor = nil;
+    _textEditorAnnotationIndex = -1;
+    _textEditorColor = nil;
     [[self window] makeFirstResponder:self];
     [self setNeedsDisplay:YES];
 }
 
-- (void)togglePalette {
-    [_paletteView setHidden:![_paletteView isHidden]];
-    if (![_paletteView isHidden] && _paletteView.subviews.count == 0) {
-        NSArray *colors = @[
-            [NSColor colorWithCalibratedRed:239.0/255.0 green:68.0/255.0 blue:68.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:249.0/255.0 green:115.0/255.0 blue:22.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:250.0/255.0 green:204.0/255.0 blue:21.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:34.0/255.0 green:197.0/255.0 blue:94.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:59.0/255.0 green:130.0/255.0 blue:246.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:139.0/255.0 green:92.0/255.0 blue:246.0/255.0 alpha:1.0],
-            [NSColor colorWithCalibratedRed:236.0/255.0 green:72.0/255.0 blue:153.0/255.0 alpha:1.0],
-            [NSColor whiteColor],
-            [NSColor colorWithCalibratedWhite:0.07 alpha:1.0]
-        ];
-        for (NSUInteger i = 0; i < colors.count; i++) {
-            NSButton *button = [NSButton buttonWithTitle:@"" target:self action:@selector(selectPaletteColor:)];
-            [button setBordered:NO];
-            [button setWantsLayer:YES];
-            [[button layer] setCornerRadius:4];
-            [[button layer] setBackgroundColor:[colors[i] CGColor]];
-            [button setTag:(NSInteger)i];
-            [button setFrame:NSMakeRect(8 + (i % 5) * 28, 38 - (i / 5) * 28, 22, 22)];
-            [_paletteView addSubview:button];
-        }
-        objc_setAssociatedObject(_paletteView, "snapgoColors", colors, OBJC_ASSOCIATION_RETAIN_NONATOMIC);
-    }
+- (void)selectStrokeWidth:(NSButton *)sender {
+    _activeStrokeWidth = MAX(1.0, (CGFloat)sender.tag);
+    [self updateToolSettingsStates];
 }
 
-- (void)selectPaletteColor:(NSButton *)sender {
-    NSArray *colors = objc_getAssociatedObject(_paletteView, "snapgoColors");
+- (void)selectFontSize:(NSButton *)sender {
+    _activeFontSize = MAX(8.0, (CGFloat)sender.tag);
+    if (_textEditor != nil) {
+        [_textEditor setFont:[NSFont systemFontOfSize:_activeFontSize weight:NSFontWeightSemibold]];
+        [self resizeTextEditorForCurrentFont];
+    } else if ([_activeTool isEqualToString:@"text"] && _selectedTextAnnotationIndex >= 0 && _selectedTextAnnotationIndex < (NSInteger)_annotations.count) {
+        NSMutableDictionary *item = (NSMutableDictionary *)_annotations[(NSUInteger)_selectedTextAnnotationIndex];
+        item[@"fontSize"] = @(_activeFontSize);
+        NSMutableArray *points = (NSMutableArray *)item[@"points"];
+        if (points.count > 0) {
+            NSString *text = item[@"text"] ?: @"";
+            NSPoint p = [points[0] pointValue];
+            points[0] = [NSValue valueWithPoint:[self clampedTextLocalPoint:p text:text fontSize:_activeFontSize]];
+        }
+        [self setNeedsDisplay:YES];
+    }
+    [self syncControls];
+}
+
+- (void)selectToolColor:(NSButton *)sender {
+    NSArray *colors = objc_getAssociatedObject(_toolSettingsView, "snapgoColors");
     if (sender.tag >= 0 && sender.tag < (NSInteger)colors.count) {
         _activeColor = colors[(NSUInteger)sender.tag];
-        [_paletteView setHidden:YES];
-        [self syncControls];
+        if (_textEditor != nil) {
+            _textEditorColor = _activeColor;
+            [_textEditor setTextColor:_activeColor];
+        } else if ([_activeTool isEqualToString:@"text"] && _selectedTextAnnotationIndex >= 0 && _selectedTextAnnotationIndex < (NSInteger)_annotations.count) {
+            NSMutableDictionary *item = (NSMutableDictionary *)_annotations[(NSUInteger)_selectedTextAnnotationIndex];
+            item[@"color"] = [self hexForColor:_activeColor];
+            item[@"nsColor"] = _activeColor;
+            [self setNeedsDisplay:YES];
+        }
+        [self updateToolSettingsStates];
     }
 }
 
@@ -848,6 +1266,9 @@ static id nativeOverlayKeyMonitor = nil;
         NSString *text = item[@"text"];
         if (text.length > 0) {
             entry[@"text"] = text;
+            entry[@"fontSize"] = item[@"fontSize"] ?: @20.0;
+        } else {
+            entry[@"strokeWidth"] = item[@"strokeWidth"] ?: @3.0;
         }
         [payload addObject:entry];
     }
@@ -872,8 +1293,8 @@ static id nativeOverlayKeyMonitor = nil;
         return;
     }
     NSRect r = [self globalRectForSelection:_selection];
-    [self closeOverlayWindow];
     NSString *json = [self annotationsJSON];
+    [self closeOverlayWindow];
     nativeOverlayConfirm((int)llround(r.origin.x), (int)llround(r.origin.y), (int)llround(r.size.width), (int)llround(r.size.height), [json UTF8String]);
 }
 
@@ -882,8 +1303,8 @@ static id nativeOverlayKeyMonitor = nil;
         return;
     }
     NSRect r = [self globalRectForSelection:_selection];
-    [self closeOverlayWindow];
     NSString *json = [self annotationsJSON];
+    [self closeOverlayWindow];
     nativeOverlayCopy((int)llround(r.origin.x), (int)llround(r.origin.y), (int)llround(r.size.width), (int)llround(r.size.height), [json UTF8String]);
 }
 
@@ -925,11 +1346,23 @@ static id nativeOverlayKeyMonitor = nil;
         return;
     }
     NSRect r = [self globalRectForSelection:_selection];
-    [self closeOverlayWindow];
     NSString *json = [self annotationsJSON];
+    [self closeOverlayWindow];
     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];
+    NSString *json = [self annotationsJSON];
+    [self closeOverlayWindow];
+    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 {
@@ -937,8 +1370,8 @@ static id nativeOverlayKeyMonitor = nil;
         return;
     }
     NSRect r = [self globalRectForSelection:_selection];
-    [self closeOverlayWindow];
     NSString *json = [self annotationsJSON];
+    [self closeOverlayWindow];
     nativeOverlaySummarize((int)llround(r.origin.x), (int)llround(r.origin.y), (int)llround(r.size.width), (int)llround(r.size.height), [json UTF8String]);
 }
 @end