feat: you can summary screen shot directly

internal/application/capture_summary.go

@@ -0,0 +1,72 @@
+package application
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"github.com/mmmy/snapgo/internal/domain"
+	"github.com/mmmy/snapgo/internal/infrastructure/clipboard"
+)
+
+// VisionSummarizer describes a multimodal model capable of reading a public
+// image URL and returning a textual summary.
+type VisionSummarizer interface {
+	SummarizeImage(ctx context.Context, prompt string, imageURL string) (string, error)
+}
+
+// CaptureSummaryService wires screenshot bytes -> S3 public URL -> LLM
+// summary -> clipboard. It intentionally does not notify UI state itself:
+// the caller emits fine-grained "uploading / recognizing / done" progress.
+type CaptureSummaryService struct {
+	Provider   domain.OSSProvider
+	Summarizer VisionSummarizer
+	Clipboard  clipboard.Writer
+	Prompt     string
+	PathPrefix string
+}
+
+// UploadImage uploads the screenshot and returns the public URL visible to
+// the multimodal provider.
+func (s *CaptureSummaryService) UploadImage(ctx context.Context, pngBytes []byte) (*domain.UploadResult, error) {
+	if s.Provider == nil {
+		return nil, fmt.Errorf("s3 is not configured")
+	}
+	if len(pngBytes) == 0 {
+		return nil, fmt.Errorf("empty screenshot")
+	}
+	key := buildObjectKey(s.PathPrefix)
+	start := time.Now()
+	url, err := s.Provider.Upload(ctx, key, pngBytes, "image/png")
+	if err != nil {
+		return nil, fmt.Errorf("s3 put object: %w", err)
+	}
+	return &domain.UploadResult{
+		URL:      url,
+		Key:      key,
+		Provider: s.Provider.Name(),
+		Elapsed:  time.Since(start),
+	}, nil
+}
+
+// Summarize asks the configured model to summarize the uploaded image URL.
+func (s *CaptureSummaryService) Summarize(ctx context.Context, imageURL string) (string, error) {
+	if s.Summarizer == nil {
+		return "", fmt.Errorf("llm is not configured")
+	}
+	return s.Summarizer.SummarizeImage(ctx, s.Prompt, imageURL)
+}
+
+// CopySummary writes the final summary text to the clipboard.
+func (s *CaptureSummaryService) CopySummary(_ context.Context, summary string) error {
+	if summary == "" {
+		return fmt.Errorf("empty summary")
+	}
+	if s.Clipboard == nil {
+		return fmt.Errorf("clipboard is not configured")
+	}
+	if err := s.Clipboard.WriteText(summary); err != nil {
+		return fmt.Errorf("clipboard write failed: %w", err)
+	}
+	return nil
+}

internal/application/capture_summary_test.go

@@ -0,0 +1,86 @@
+package application
+
+import (
+	"context"
+	"testing"
+)
+
+type fakeOSSProvider struct {
+	key         string
+	data        []byte
+	contentType string
+	url         string
+}
+
+func (f *fakeOSSProvider) Upload(_ context.Context, key string, data []byte, contentType string) (string, error) {
+	f.key = key
+	f.data = append([]byte(nil), data...)
+	f.contentType = contentType
+	if f.url == "" {
+		return "https://cdn.example.com/" + key, nil
+	}
+	return f.url, nil
+}
+
+func (f *fakeOSSProvider) Name() string { return "fake" }
+
+type fakeSummarizer struct {
+	prompt string
+	url    string
+	text   string
+}
+
+func (f *fakeSummarizer) SummarizeImage(_ context.Context, prompt string, imageURL string) (string, error) {
+	f.prompt = prompt
+	f.url = imageURL
+	if f.text == "" {
+		return "summary text", nil
+	}
+	return f.text, nil
+}
+
+func TestCaptureSummaryServiceUploadsSummarizesAndCopies(t *testing.T) {
+	ctx := context.Background()
+	provider := &fakeOSSProvider{}
+	summarizer := &fakeSummarizer{}
+	clip := &fakeClipboard{}
+	svc := &CaptureSummaryService{
+		Provider:   provider,
+		Summarizer: summarizer,
+		Clipboard:  clip,
+		Prompt:     "describe screenshot",
+		PathPrefix: "snapgo/",
+	}
+
+	uploaded, err := svc.UploadImage(ctx, []byte("png"))
+	if err != nil {
+		t.Fatalf("upload image: %v", err)
+	}
+	if provider.contentType != "image/png" {
+		t.Fatalf("expected image/png content type, got %q", provider.contentType)
+	}
+	if string(provider.data) != "png" {
+		t.Fatalf("expected uploaded png bytes, got %q", string(provider.data))
+	}
+
+	summary, err := svc.Summarize(ctx, uploaded.URL)
+	if err != nil {
+		t.Fatalf("summarize: %v", err)
+	}
+	if summarizer.prompt != "describe screenshot" {
+		t.Fatalf("expected prompt forwarded, got %q", summarizer.prompt)
+	}
+	if summarizer.url != uploaded.URL {
+		t.Fatalf("expected uploaded url forwarded, got %q", summarizer.url)
+	}
+	if summary != "summary text" {
+		t.Fatalf("expected summary text, got %q", summary)
+	}
+
+	if err := svc.CopySummary(ctx, summary); err != nil {
+		t.Fatalf("copy summary: %v", err)
+	}
+	if clip.text != "summary text" {
+		t.Fatalf("expected summary copied, got %q", clip.text)
+	}
+}