feat(video): support Ark full-modal references (#300)

web/src/lib/generation-task-display.ts

@@ -43,6 +43,7 @@ export const operationOptions = [
     { label: "Agent 会话：拆解影视工作流", value: "agent_session" },
     { label: "文生视频", value: "text_to_video" },
     { label: "图生视频", value: "image_to_video" },
+    { label: "全模态参考", value: "reference_to_video" },
     { label: "视频续写", value: "extend" },
     { label: "视频局部修改", value: "inpaint" },
     { label: "元素替换", value: "replace_element" },

web/src/lib/model-capabilities.ts

@@ -292,7 +292,10 @@ export function defaultModelCapabilityConfig(protocol?: ModelProtocol, model = "
         video.generateAudio = { supported: true, default: true };
     }
     if (protocol === "volcengine-ark-video" || protocol === "newapi-channel-1") video.resolutions = ["480p", "720p", "1080p"];
-    if (protocol === "volcengine-ark-video") video.watermark = { supported: true, default: false };
+    if (protocol === "volcengine-ark-video") {
+        video.watermark = { supported: true, default: false };
+        video.operations.push("reference_to_video", "audio_to_video");
+    }
     if (protocol === "novita-video") {
         video.references.maxImages = 1;
         video.references.maxImageBytes = 10 * 1024 * 1024;

web/src/lib/model-selection.ts

@@ -336,7 +336,7 @@ function videoOperationLabel(operation: string) {
     if (operation === "text_to_video") return "文生视频";
     if (operation === "image_to_video") return "图生视频";
     if (operation === "audio_to_video") return "音频生视频";
-    if (operation === "reference_to_video") return "参考素材生视频";
+    if (operation === "reference_to_video") return "全模态参考";
     if (operation === "extend") return "视频续写";
     return "当前生成模式";
 }