转换器: 图片内容块跨协议互转保留(base64/url)

- 支持 OpenAI image_url ↔ Anthropic image.source(base64/url) 双向转换
- messages→chat / responses→chat 不再丢弃图片块, 保留图文原始顺序
- chat→messages 的 data URL 拆成 base64 source(media_type+data)
- chat→responses 的 image_url 转 input_image
- responses↔messages 经 chat 中转, 六方向全覆盖
- 新增多图/顺序回归测试

Co-Authored-By: Claude <noreply@anthropic.com>

server/internal/proxy/convert/convert_test.go

@@ -306,3 +306,246 @@ func TestStreamMessagesToResponses(t *testing.T) {
 		t.Fatalf("missing response.completed: %s", out)
 	}
 }
+
+// ---------------------------------------------------------------------------
+// 图片内容块转换（messages image / chat image_url / responses input_image 互转不丢图）
+
+const testB64 = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII="
+
+// userContentBlocks 断言 Chat 用户消息 content 为块数组并返回。
+func userContentBlocks(t *testing.T, out []byte) []any {
+	t.Helper()
+	var m map[string]any
+	if err := json.Unmarshal(out, &m); err != nil {
+		t.Fatalf("unmarshal: %v\n%s", err, out)
+	}
+	msgs := m["messages"].([]any)
+	if len(msgs) != 1 {
+		t.Fatalf("messages len = %d: %s", len(msgs), out)
+	}
+	content, ok := msgs[0].(map[string]any)["content"].([]any)
+	if !ok {
+		t.Fatalf("content not array: %s", out)
+	}
+	return content
+}
+
+// blockURL 取 image_url 块的 url。
+func blockURL(t *testing.T, b any) string {
+	t.Helper()
+	bm := b.(map[string]any)
+	if bm["type"] != "image_url" {
+		t.Fatalf("block type = %v", bm["type"])
+	}
+	iu := bm["image_url"].(map[string]any)
+	url, _ := iu["url"].(string)
+	return url
+}
+
+func TestMessagesToChatReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "gpt-4o-mini",
+		"messages": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "text", "text": "describe"},
+			map[string]any{"type": "image", "source": map[string]any{"type": "base64", "media_type": "image/png", "data": testB64}},
+			map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": "https://example.com/a.png"}},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoMessages, ProtoChat)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	blocks := userContentBlocks(t, out)
+	if len(blocks) != 3 {
+		t.Fatalf("blocks len = %d: %s", len(blocks), out)
+	}
+	if got := blockURL(t, blocks[1]); got != "data:image/png;base64,"+testB64 {
+		t.Fatalf("base64 image url = %q", got)
+	}
+	if got := blockURL(t, blocks[2]); got != "https://example.com/a.png" {
+		t.Fatalf("url image = %q", got)
+	}
+}
+
+// 多图 + 图/文交错顺序：转换后块数量与顺序保持不变（文档推荐的 Image 1:/Image 2: 标签模式）。
+func TestMessagesToChatReqMultiImage(t *testing.T) {
+	img := func(url string) any {
+		return map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": url}}
+	}
+	in := mustJSON(t, map[string]any{
+		"model": "gpt-4o-mini",
+		"messages": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "text", "text": "Image 1:"},
+			img("https://example.com/1.png"),
+			map[string]any{"type": "text", "text": "Image 2:"},
+			img("https://example.com/2.png"),
+			map[string]any{"type": "text", "text": "How are these images different?"},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoMessages, ProtoChat)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	blocks := userContentBlocks(t, out)
+	if len(blocks) != 5 {
+		t.Fatalf("blocks len = %d: %s", len(blocks), out)
+	}
+	types := []string{}
+	for _, b := range blocks {
+		types = append(types, b.(map[string]any)["type"].(string))
+	}
+	want := []string{"text", "image_url", "text", "image_url", "text"}
+	for i := range want {
+		if types[i] != want[i] {
+			t.Fatalf("block[%d] type = %s, want %s: %v", i, types[i], want[i], types)
+		}
+	}
+	// 第二张图仍是第二张
+	if got := blockURL(t, blocks[3]); got != "https://example.com/2.png" {
+		t.Fatalf("image2 url = %q", got)
+	}
+}
+
+func TestChatToMessagesReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "claude-sonnet-5",
+		"messages": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "text", "text": "describe"},
+			map[string]any{"type": "image_url", "image_url": map[string]any{"url": "data:image/jpeg;base64," + testB64}},
+			map[string]any{"type": "image_url", "image_url": map[string]any{"url": "https://example.com/b.png"}},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoChat, ProtoMessages)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	var m map[string]any
+	_ = json.Unmarshal(out, &m)
+	msgs := m["messages"].([]any)
+	content := msgs[0].(map[string]any)["content"].([]any)
+	if len(content) != 3 {
+		t.Fatalf("content len = %d: %s", len(content), out)
+	}
+	src1 := content[1].(map[string]any)["source"].(map[string]any)
+	if src1["type"] != "base64" || src1["media_type"] != "image/jpeg" || src1["data"] != testB64 {
+		t.Fatalf("base64 source = %v", src1)
+	}
+	src2 := content[2].(map[string]any)["source"].(map[string]any)
+	if src2["type"] != "url" || src2["url"] != "https://example.com/b.png" {
+		t.Fatalf("url source = %v", src2)
+	}
+}
+
+func TestResponsesToChatReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "claude-sonnet-5",
+		"input": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "input_text", "text": "describe"},
+			map[string]any{"type": "input_image", "image_url": "data:image/png;base64," + testB64},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoResponses, ProtoChat)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	blocks := userContentBlocks(t, out)
+	if len(blocks) != 2 {
+		t.Fatalf("blocks len = %d: %s", len(blocks), out)
+	}
+	if got := blockURL(t, blocks[1]); got != "data:image/png;base64,"+testB64 {
+		t.Fatalf("image url = %q", got)
+	}
+}
+
+func TestChatToResponsesReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "gpt-4o",
+		"messages": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "text", "text": "describe"},
+			map[string]any{"type": "image_url", "image_url": map[string]any{"url": "https://example.com/c.png"}},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoChat, ProtoResponses)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	var m map[string]any
+	_ = json.Unmarshal(out, &m)
+	var input []map[string]any
+	// 单条 user 消息项
+	switch v := m["input"].(type) {
+	case map[string]any:
+		input = []map[string]any{v}
+	case []any:
+		for _, it := range v {
+			input = append(input, it.(map[string]any))
+		}
+	}
+	content := input[0]["content"].([]any)
+	if len(content) != 2 {
+		t.Fatalf("content len = %d: %s", len(content), out)
+	}
+	img := content[1].(map[string]any)
+	if img["type"] != "input_image" {
+		t.Fatalf("block type = %v", img["type"])
+	}
+	if img["image_url"] != "https://example.com/c.png" {
+		t.Fatalf("image_url = %v", img["image_url"])
+	}
+}
+
+// 链式转换：responses→messages、messages→responses（经 chat 中转）也不丢图。
+func TestResponsesToMessagesReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "claude-sonnet-5",
+		"input": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "input_text", "text": "describe"},
+			map[string]any{"type": "input_image", "image_url": "data:image/png;base64," + testB64},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoResponses, ProtoMessages)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	var m map[string]any
+	_ = json.Unmarshal(out, &m)
+	msgs := m["messages"].([]any)
+	content := msgs[0].(map[string]any)["content"].([]any)
+	if len(content) != 2 {
+		t.Fatalf("content len = %d: %s", len(content), out)
+	}
+	src := content[1].(map[string]any)["source"].(map[string]any)
+	if src["type"] != "base64" || src["data"] != testB64 {
+		t.Fatalf("source = %v", src)
+	}
+}
+
+func TestMessagesToResponsesReqImage(t *testing.T) {
+	in := mustJSON(t, map[string]any{
+		"model": "gpt-4o",
+		"messages": []any{map[string]any{"role": "user", "content": []any{
+			map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": "https://example.com/d.png"}},
+			map[string]any{"type": "text", "text": "describe"},
+		}}},
+	})
+	out, err := ConvertRequest([]byte(in), ProtoMessages, ProtoResponses)
+	if err != nil {
+		t.Fatalf("convert: %v", err)
+	}
+	var m map[string]any
+	_ = json.Unmarshal(out, &m)
+	var content []any
+	switch v := m["input"].(type) {
+	case map[string]any:
+		content = v["content"].([]any)
+	case []any:
+		content = v[0].(map[string]any)["content"].([]any)
+	}
+	if len(content) != 2 {
+		t.Fatalf("content len = %d: %s", len(content), out)
+	}
+	img := content[0].(map[string]any)
+	if img["type"] != "input_image" || img["image_url"] != "https://example.com/d.png" {
+		t.Fatalf("input_image = %v", img)
+	}
+}

server/internal/proxy/convert/json_chat.go

@@ -137,9 +137,11 @@ func chatMsgToAnthropic(m chatMsg) any {
 					var url string
 					if iu, ok := b["image_url"].(map[string]any); ok {
 						url, _ = iu["url"].(string)
+					} else if s, ok := b["image_url"].(string); ok {
+						url = s
 					}
 					if url != "" {
-						blocks = append(blocks, map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": url}})
+						blocks = append(blocks, anthropicImageBlock(url))
 					}
 				}
 			}
@@ -229,12 +231,18 @@ func anthropicMsgToChat(role string, content json.RawMessage) []any {
 	if json.Unmarshal(content, &blocks) == nil && blocks != nil {
 		var out []any
 		var textParts []string
+		var contentBlocks []any // text / image_url 块，保留原始顺序
 		var toolCalls []any
 		for _, b := range blocks {
 			switch b["type"] {
 			case "text":
 				if t, _ := b["text"].(string); t != "" {
 					textParts = append(textParts, t)
+					contentBlocks = append(contentBlocks, map[string]any{"type": "text", "text": t})
+				}
+			case "image":
+				if cb := chatImageBlock(b); cb != nil {
+					contentBlocks = append(contentBlocks, cb)
 				}
 			case "tool_use":
 				id, _ := b["id"].(string)
@@ -254,9 +262,19 @@ func anthropicMsgToChat(role string, content json.RawMessage) []any {
 				out = append(out, map[string]any{"role": "tool", "tool_call_id": callID, "content": res})
 			}
 		}
-		if len(textParts) > 0 || len(toolCalls) > 0 {
+		hasImage := false
+		for _, cb := range contentBlocks {
+			if m, _ := cb.(map[string]any); m["type"] == "image_url" {
+				hasImage = true
+				break
+			}
+		}
+		if hasImage || len(textParts) > 0 || len(toolCalls) > 0 {
 			msg := map[string]any{"role": role}
-			if len(textParts) > 0 {
+			switch {
+			case hasImage:
+				msg["content"] = contentBlocks
+			case len(textParts) > 0:
 				msg["content"] = strings.Join(textParts, "")
 			}
 			if len(toolCalls) > 0 {
@@ -416,6 +434,58 @@ func intOrNil(p *int, def int) any {
 	return *p
 }
 
+// splitDataURL 解析 data:media_type;base64,data 形式的 URL；非该形式返回 ok=false。
+func splitDataURL(url string) (media, data string, ok bool) {
+	if !strings.HasPrefix(url, "data:") {
+		return "", "", false
+	}
+	i := strings.Index(url, ";base64,")
+	if i < 0 {
+		return "", "", false
+	}
+	return url[len("data:"):i], url[i+len(";base64,"):], true
+}
+
+// chatImageBlock 把 Anthropic image 块转 OpenAI image_url 块。
+// 仅支持 base64 与 url source；其他类型（如 Files API 的 file_id）不支持，跳过。
+func chatImageBlock(b map[string]any) any {
+	src, ok := b["source"].(map[string]any)
+	if !ok {
+		return nil
+	}
+	switch src["type"] {
+	case "base64":
+		media, _ := src["media_type"].(string)
+		data, _ := src["data"].(string)
+		if data == "" {
+			return nil
+		}
+		if media == "" {
+			media = "image/png"
+		}
+		return map[string]any{"type": "image_url", "image_url": map[string]any{"url": "data:" + media + ";base64," + data}}
+	case "url":
+		url, _ := src["url"].(string)
+		if url == "" {
+			return nil
+		}
+		return map[string]any{"type": "image_url", "image_url": map[string]any{"url": url}}
+	}
+	return nil
+}
+
+// anthropicImageBlock 把 OpenAI image_url 的 url 转 Anthropic image 块。
+// data URL → base64 source；http(s) URL → url source。
+func anthropicImageBlock(url string) any {
+	if media, data, ok := splitDataURL(url); ok {
+		if media == "" {
+			media = "image/png"
+		}
+		return map[string]any{"type": "image", "source": map[string]any{"type": "base64", "media_type": media, "data": data}}
+	}
+	return map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": url}}
+}
+
 func rawOrObject(raw json.RawMessage) any {
 	if len(raw) == 0 || string(raw) == "null" {
 		return map[string]any{}

server/internal/proxy/convert/json_responses.go

@@ -101,20 +101,82 @@ func responsesInputToChat(raw json.RawMessage) []any {
 				out = append(out, map[string]any{"role": role, "content": content})
 			} else if blocks, ok := item["content"].([]any); ok {
 				var text []string
+				var contentBlocks []any
 				for _, b := range blocks {
-					if bm, ok := b.(map[string]any); ok {
+					bm, ok := b.(map[string]any)
+					if !ok {
+						continue
+					}
+					switch bm["type"] {
+					case "input_text", "text":
 						if t, _ := bm["text"].(string); t != "" {
 							text = append(text, t)
+							contentBlocks = append(contentBlocks, map[string]any{"type": "text", "text": t})
+						}
+					case "input_image":
+						var url string
+						if s, ok := bm["image_url"].(string); ok {
+							url = s
+						} else if m, ok := bm["image_url"].(map[string]any); ok {
+							url, _ = m["url"].(string)
+						}
+						if url != "" {
+							contentBlocks = append(contentBlocks, map[string]any{"type": "image_url", "image_url": map[string]any{"url": url}})
 						}
 					}
 				}
+				hasImage := false
+				for _, cb := range contentBlocks {
+					if m, _ := cb.(map[string]any); m["type"] == "image_url" {
+						hasImage = true
+						break
+					}
+				}
+				if hasImage {
+					out = append(out, map[string]any{"role": role, "content": contentBlocks})
+				} else {
 					out = append(out, map[string]any{"role": role, "content": strings.Join(text, "")})
 				}
 			}
 		}
+	}
 	return out
 }
 
+// chatContentToResponsesBlocks 把 Chat 用户消息 content 转 Responses input 块数组（input_text / input_image）。
+func chatContentToResponsesBlocks(content json.RawMessage) []any {
+	// 纯字符串 → 单个 input_text
+	var s string
+	if json.Unmarshal(content, &s) == nil && s != "" {
+		return []any{map[string]any{"type": "input_text", "text": s}}
+	}
+	// 数组 → 按块转换（text / image_url）
+	var arr []map[string]any
+	if json.Unmarshal(content, &arr) == nil && arr != nil {
+		var out []any
+		for _, b := range arr {
+			switch b["type"] {
+			case "text", "input_text":
+				if t, _ := b["text"].(string); t != "" {
+					out = append(out, map[string]any{"type": "input_text", "text": t})
+				}
+			case "image_url":
+				var url string
+				if iu, ok := b["image_url"].(map[string]any); ok {
+					url, _ = iu["url"].(string)
+				} else if s, ok := b["image_url"].(string); ok {
+					url = s
+				}
+				if url != "" {
+					out = append(out, map[string]any{"type": "input_image", "image_url": url})
+				}
+			}
+		}
+		return out
+	}
+	return nil
+}
+
 // ---------------------------------------------------------------------------
 // 请求：Chat → Responses
 
@@ -170,10 +232,8 @@ func chatToResponsesReq(body []byte) ([]byte, error) {
 				}})
 			}
 		default:
-			if s := str(m.Content); s != "" {
+			if blocks := chatContentToResponsesBlocks(m.Content); len(blocks) > 0 {
-				input = append(input, map[string]any{"type": "message", "role": "user", "content": []any{
+				input = append(input, map[string]any{"type": "message", "role": "user", "content": blocks})
-					map[string]any{"type": "input_text", "text": s},
-				}})
 			}
 		}
 	}