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/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}})
 						}
 					}
 				}
-				out = append(out, map[string]any{"role": role, "content": strings.Join(text, "")})
+				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 != "" {
-				input = append(input, map[string]any{"type": "message", "role": "user", "content": []any{
-					map[string]any{"type": "input_text", "text": s},
-				}})
+			if blocks := chatContentToResponsesBlocks(m.Content); len(blocks) > 0 {
+				input = append(input, map[string]any{"type": "message", "role": "user", "content": blocks})
 			}
 		}
 	}