feat: add screenshot OCR extraction

app.go

@@ -25,6 +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"
@@ -501,6 +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
@@ -906,6 +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
@@ -963,6 +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