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

web/src/components/canvas/canvas-config-node-panel.tsx

@@ -30,6 +30,7 @@ type CanvasConfigNodePanelProps = {
 const videoOperationOptions: Array<{ label: string; value: CanvasVideoEditOperation }> = [
     { 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: "局部修改", value: "inpaint" },
     { label: "元素替换", value: "replace_element" },

web/src/components/canvas/canvas-video-segment-dialog.tsx

@@ -413,6 +413,7 @@ function videoOperationLabel(operation: CanvasVideoEditOperation) {
     const labels: Record<CanvasVideoEditOperation, string> = {
         text_to_video: "文生视频",
         image_to_video: "图生视频",
+        reference_to_video: "全模态参考",
         extend: "视频续写",
         inpaint: "局部修改",
         replace_element: "元素替换",

web/src/components/model-capability-editor.tsx

@@ -9,6 +9,7 @@ const ratioOptions = ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"];
 const operationOptions = [
     { 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: "局部修改", value: "inpaint" },
     { label: "元素替换", value: "replace_element" },

web/src/components/model-picker.tsx

@@ -294,6 +294,7 @@ function logicalCapabilitySummary(spec: NonNullable<NonNullable<AiConfig["channe
     const operationLabels: Record<string, string> = {
         text_to_video: "文生视频",
         image_to_video: "图生视频",
+        reference_to_video: "全模态参考",
         audio_to_video: "音频生视频",
         extend: "视频续写",
         inpaint: "局部修改",

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";
 }

web/src/pages/admin/logical-models/model-routing-capabilities.tsx

@@ -637,6 +637,7 @@ export function operationLabel(value: string) {
         {
             text_to_video: "文生视频",
             image_to_video: "图生视频",
+            reference_to_video: "全模态参考",
             extend: "视频续写",
             inpaint: "局部修改",
             replace_element: "元素替换",

web/src/services/api/video-provider-seedance.ts

@@ -81,8 +81,8 @@ function seedanceApiUrl(config: ResolvedAiConfig, taskId?: string) {
 }
 
 async function buildSeedanceAgentPlanPayload(config: ResolvedAiConfig, model: string, prompt: string, references: ReferenceImage[], videoReferences: ReferenceVideo[], audioReferences: ReferenceAudio[], deps: VideoProviderDeps) {
-    if (config.interfaceType !== "volcengine-ark-video" && audioReferences.length && !references.length && !videoReferences.length) {
-        throw new Error("Seedance 参考音频不能单独使用，请同时添加参考图或参考视频");
+    if (audioReferences.length && !references.length && !videoReferences.length) {
+        throw new Error(config.interfaceType === "volcengine-ark-video" ? "火山方舟全模态参考不支持纯音频或文本+音频，请同时添加参考图片或参考视频" : "Seedance 参考音频不能单独使用，请同时添加参考图或参考视频");
     }
     const content = config.interfaceType === "volcengine-ark-video"
         ? await buildVolcengineArkContent(prompt, references, videoReferences, audioReferences)

web/src/types/canvas.ts

@@ -50,7 +50,7 @@ export type CanvasGenerationBatchStatus = "queued" | "running" | "partial_failed
 export type CanvasGenerationBatchItemStatus = "waiting" | "submitting" | "queued" | "running" | "succeeded" | "failed" | "cancelled";
 export type CanvasImageGenerationType = "generation" | "edit";
 export type CanvasWorkflowKind = "free" | "script" | "story_input" | "character" | "scene" | "storyboard" | "shot" | "final" | "styleboard" | "reference_set" | "reference_video" | "action_board";
-export type CanvasVideoEditOperation = "text_to_video" | "image_to_video" | "extend" | "inpaint" | "replace_element" | "camera_motion" | "style_transfer" | "audio_to_video" | "compare_versions" | "concat";
+export type CanvasVideoEditOperation = "text_to_video" | "image_to_video" | "reference_to_video" | "extend" | "inpaint" | "replace_element" | "camera_motion" | "style_transfer" | "audio_to_video" | "compare_versions" | "concat";
 export type CanvasSkillCategory = "writing" | "storyboard" | "image" | "video" | "utility";
 export type CanvasSkillOutputMode = "text" | "json" | "image_prompt" | "workflow";
 export type StoryboardColumn =