feat: you can summary screen shot directly

internal/infrastructure/llm/openai_compatible_test.go

@@ -0,0 +1,86 @@
+package llm
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"io"
+	"net/http"
+	"testing"
+
+	"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 TestVisionClientSummarizeImageUsesChatCompletionImageURL(t *testing.T) {
+	var requestBody map[string]any
+	transport := roundTripFunc(func(r *http.Request) (*http.Response, error) {
+		if r.URL.Path != "/v1/chat/completions" {
+			t.Fatalf("expected /v1/chat/completions, got %s", r.URL.Path)
+		}
+		if got := r.Header.Get("Authorization"); got != "Bearer test-key" {
+			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(`{"choices":[{"message":{"content":"summary ok"}}]}`)),
+		}, nil
+	})
+
+	client, err := NewVisionClient(domain.LLMProviderQwen, domain.LLMProviderConfig{
+		BaseURL:     "https://example.test/v1",
+		APIKey:      "test-key",
+		Model:       "qwen-vl-plus",
+		MaxTokens:   321,
+		Temperature: 0.2,
+		TimeoutSecs: 5,
+	})
+	if err != nil {
+		t.Fatalf("new client: %v", err)
+	}
+	client.httpClient.Transport = transport
+
+	text, err := client.SummarizeImage(context.Background(), "describe", "https://cdn.example.com/a.png")
+	if err != nil {
+		t.Fatalf("summarize image: %v", err)
+	}
+	if text != "summary ok" {
+		t.Fatalf("expected response text, got %q", text)
+	}
+	if requestBody["model"] != "qwen-vl-plus" {
+		t.Fatalf("expected model forwarded, got %#v", requestBody["model"])
+	}
+	if requestBody["max_tokens"] != float64(321) {
+		t.Fatalf("expected max_tokens forwarded, got %#v", requestBody["max_tokens"])
+	}
+
+	messages := requestBody["messages"].([]any)
+	content := messages[0].(map[string]any)["content"].([]any)
+	if content[0].(map[string]any)["text"] != "describe" {
+		t.Fatalf("expected prompt content, got %#v", content[0])
+	}
+	image := content[1].(map[string]any)
+	if image["type"] != "image_url" {
+		t.Fatalf("expected image_url item, got %#v", image)
+	}
+	url := image["image_url"].(map[string]any)["url"]
+	if url != "https://cdn.example.com/a.png" {
+		t.Fatalf("expected image url forwarded, got %#v", url)
+	}
+}
+
+func TestChatCompletionsURLAcceptsFullEndpoint(t *testing.T) {
+	full := "https://example.com/v1/chat/completions"
+	if got := chatCompletionsURL(full); got != full {
+		t.Fatalf("expected full endpoint unchanged, got %q", got)
+	}
+}