完成 SFX V2 T5 正式生成链路

接通 Luna 英文化、ElevenLabs 单次生成、MP3 校验、OSS 与权威元数据写回
演进站内和 External v1 契约、幂等参数、详情重绘与 Agent 音效模型
新增 ElevenLabs 动态定价键及历史定价快照兼容
同步 OpenAPI、外部 Agent Skill、共享计划与决策记录

src/components/image-editor/ImageCanvasGenerationDialogModel.test.ts

@@ -376,6 +376,46 @@ describe('ImageCanvasGenerationDialogModel', () => {
     });
   });
 
+  it('restores authoritative SFX V2 prompt, duration mode, and loop on redraw', () => {
+    const draft = createAudioRedrawGenerationDialogDraft(
+      createLayer({
+        id: 'layer-sfx-v2',
+        mediaType: 'audio',
+        assetKind: 'sound-effect',
+        prompt: '不应覆盖权威用户描述',
+        generationInputs: {
+          fields: [
+            { title: '用户描述', value: '金币落地' },
+            { title: '实际英文提示词', value: 'A bright coin landing chime' },
+            { title: '时长', value: '7.42秒' },
+            { title: 'Loop', value: '开启' },
+          ],
+          references: [],
+          soundEffect: {
+            schemaVersion: 2,
+            userPrompt: '金币落地',
+            actualPrompt: 'A bright coin landing chime',
+            model: 'eleven_text_to_sound_v2',
+            durationMode: 'auto',
+            requestedDurationSeconds: null,
+            actualDurationSeconds: 7.42,
+            loop: true,
+          },
+        },
+      }),
+    );
+
+    expect(draft).toMatchObject({
+      mode: 'audio-sound-effect',
+      sourceLayerId: 'layer-sfx-v2',
+      prompt: '金币落地',
+      soundModel: 'eleven_text_to_sound_v2',
+      soundDurationMode: 'auto',
+      soundDurationSeconds: 5,
+      soundLoop: true,
+    });
+  });
+
   it('creates edit, quick-edit, and character animation panel drafts', () => {
     const sourceLayer = createLayer({
       prompt: '【系统内置】完整拼接提示词：原图提示，自动画质优化。',

src/components/image-editor/ImageCanvasGenerationDialogModel.ts

@@ -472,6 +472,7 @@ const USER_PROMPT_INPUT_TITLES = new Set(
     '快速编辑提示词',
     '重绘提示词',
     '动作描述',
+    '用户描述',
   ].map((title) => title.toLowerCase()),
 );
 
@@ -508,6 +509,14 @@ function resolveUserGenerationPromptSnapshot(sourceLayer: CanvasLayer) {
 }
 
 function resolveAudioRedrawPrompt(sourceLayer: CanvasLayer) {
+  const soundEffect = sourceLayer.generationInputs?.soundEffect;
+  if (
+    sourceLayer.assetKind === 'sound-effect' &&
+    soundEffect?.schemaVersion === 2 &&
+    soundEffect.userPrompt.trim()
+  ) {
+    return soundEffect.userPrompt;
+  }
   return resolveUserGenerationPromptSnapshot(sourceLayer);
 }
 
@@ -534,6 +543,17 @@ function resolveAudioRedrawSoundModel(
 }
 
 function resolveAudioRedrawSoundDuration(sourceLayer: CanvasLayer) {
+  const soundEffect = sourceLayer.generationInputs?.soundEffect;
+  if (soundEffect?.schemaVersion === 2) {
+    if (
+      soundEffect.durationMode === 'manual' &&
+      typeof soundEffect.requestedDurationSeconds === 'number' &&
+      Number.isFinite(soundEffect.requestedDurationSeconds)
+    ) {
+      return soundEffect.requestedDurationSeconds;
+    }
+    return DEFAULT_SOUND_EFFECT_DURATION_SECONDS;
+  }
   const fieldValue = findGenerationInputFieldValue(sourceLayer, [
     '时长',
     'duration',
@@ -582,9 +602,16 @@ export function createAudioRedrawGenerationDialogDraft(
   return {
     ...baseDraft,
     soundModel: resolveAudioRedrawSoundModel(sourceLayer),
-    soundDurationMode: 'manual',
+    soundDurationMode:
+      sourceLayer.generationInputs?.soundEffect?.schemaVersion === 2 &&
+      sourceLayer.generationInputs.soundEffect.durationMode === 'auto'
+        ? 'auto'
+        : 'manual',
     soundDurationSeconds: resolveAudioRedrawSoundDuration(sourceLayer),
-    soundLoop: false,
+    soundLoop:
+      sourceLayer.generationInputs?.soundEffect?.schemaVersion === 2
+        ? sourceLayer.generationInputs.soundEffect.loop
+        : false,
   };
 }
 

src/components/image-editor/ImageCanvasGenerationLayerModel.ts

@@ -512,7 +512,8 @@ export function createAudioResultLayer({
     objectKey: resource?.objectKey ?? generated.objectKey,
     assetObjectId: resource?.assetObjectId ?? generated.assetObjectId,
     sourceAssetId: asset?.assetId,
-    generationInputs: resource?.generationInputs ?? generationInputs,
+    generationInputs:
+      resource?.generationInputs ?? asset?.generationInputs ?? generationInputs,
     generatedAssetSnapshot: asset ?? undefined,
   };
 }

src/components/image-editor/ImageCanvasGenerationModel.test.ts

@@ -541,12 +541,18 @@ describe('ImageCanvasGenerationModel', () => {
       'Quick Edit Generator',
     );
     expect(
-      buildSoundEffectGenerationInputs('金币掉落叮当声', 'audio1.0', 7),
+      buildSoundEffectGenerationInputs(
+        '金币掉落叮当声',
+        'eleven_text_to_sound_v2',
+        7,
+        true,
+      ),
     ).toEqual({
       fields: [
-        { title: 'prompt', value: '金币掉落叮当声' },
-        { title: 'model', value: 'audio1.0' },
-        { title: '时长', value: '7秒' },
+        { title: '用户描述', value: '金币掉落叮当声' },
+        { title: 'model', value: 'eleven_text_to_sound_v2' },
+        { title: '请求时长', value: '7秒' },
+        { title: 'Loop', value: '开启' },
       ],
       references: [],
     });

src/components/image-editor/ImageCanvasGenerationModel.ts

@@ -965,9 +965,7 @@ export function calculateEditorSoundEffectPrice(
   model: string | null | undefined,
 ) {
   const normalizedModel = (model ?? DEFAULT_SOUND_EFFECT_MODEL).trim();
-  // T4 只切前端固定模型展示；新模型的动态定价键由 T5 同批接入。中间态继续以
-  // 历史 Vidu 的 5 泥点前端兜底展示，服务端价格始终是正式真相。
-  return readModelFlatPrice(normalizedModel, SOUND_EFFECT_MODEL_VIDU);
+  return readModelFlatPrice(normalizedModel, DEFAULT_SOUND_EFFECT_MODEL);
 }
 
 export function calculateEditorBackgroundMusicPrice(
@@ -1160,13 +1158,18 @@ export function buildVideoGenerationInputs(
 export function buildSoundEffectGenerationInputs(
   prompt: string,
   model: string,
-  duration: number,
+  duration: number | null,
+  loop: boolean,
 ): CanvasGenerationInputs {
   return {
     fields: [
-      ...createGenerationInputField('prompt', prompt),
+      ...createGenerationInputField('用户描述', prompt),
       ...createGenerationInputField('model', model),
-      ...createGenerationInputField('时长', `${duration}秒`),
+      ...createGenerationInputField(
+        '请求时长',
+        duration === null ? '自动' : `${duration}秒`,
+      ),
+      ...createGenerationInputField('Loop', loop ? '开启' : '关闭'),
     ],
     references: [],
   };

src/components/image-editor/ImageCanvasGenerationSubmissionModel.test.ts

@@ -1015,6 +1015,7 @@ describe('ImageCanvasGenerationSubmissionModel', () => {
         prompt: '  金币掉落叮当声  ',
         status: 'idle',
         soundDurationSeconds: 7,
+        soundDurationMode: 'manual',
       },
       layers: [],
       nextGeneratedIndex: 4,
@@ -1034,9 +1035,10 @@ describe('ImageCanvasGenerationSubmissionModel', () => {
         title: '游戏音效 4',
         generationInputs: {
           fields: [
-            { title: 'prompt', value: '金币掉落叮当声' },
+            { title: '用户描述', value: '金币掉落叮当声' },
             { title: 'model', value: 'eleven_text_to_sound_v2' },
-            { title: '时长', value: '7秒' },
+            { title: '请求时长', value: '7秒' },
+            { title: 'Loop', value: '关闭' },
           ],
           references: [],
         },
@@ -1044,6 +1046,48 @@ describe('ImageCanvasGenerationSubmissionModel', () => {
     });
   });
 
+  it('preserves frozen auto duration, loop, and manual decimal precision', () => {
+    const automatic = buildImageGenerationSubmissionPlan({
+      dialog: {
+        mode: 'audio-sound-effect',
+        prompt: '环境循环音',
+        status: 'idle',
+        soundDurationMode: 'auto',
+        soundDurationSeconds: 1.23456789,
+        soundLoop: true,
+      },
+      layers: [],
+      nextGeneratedIndex: 1,
+    });
+    expect(automatic).toMatchObject({
+      input: { duration: null, loop: true },
+      result: {
+        generationInputs: {
+          fields: expect.arrayContaining([
+            { title: '请求时长', value: '自动' },
+            { title: 'Loop', value: '开启' },
+          ]),
+        },
+      },
+    });
+
+    const manual = buildImageGenerationSubmissionPlan({
+      dialog: {
+        mode: 'audio-sound-effect',
+        prompt: '精确时长音效',
+        status: 'idle',
+        soundDurationMode: 'manual',
+        soundDurationSeconds: 1.23456789,
+        soundLoop: false,
+      },
+      layers: [],
+      nextGeneratedIndex: 2,
+    });
+    expect(manual).toMatchObject({
+      input: { duration: 1.23456789, loop: false },
+    });
+  });
+
   it('rejects an all-whitespace sound effect prompt without a fallback', () => {
     expect(() =>
       buildImageGenerationSubmissionPlan({

src/components/image-editor/ImageCanvasGenerationSubmissionModel.ts

@@ -545,9 +545,12 @@ export function buildImageGenerationSubmissionPlan({
   if (dialog.mode === 'audio-sound-effect') {
     const soundModel = EDITOR_SOUND_EFFECT_MODEL;
     const durationSeconds =
-      typeof dialog.soundDurationSeconds === 'number'
-        ? Math.min(10, Math.max(2, Math.round(dialog.soundDurationSeconds)))
-        : DEFAULT_SOUND_EFFECT_DURATION_SECONDS;
+      dialog.soundDurationMode === 'auto'
+        ? null
+        : typeof dialog.soundDurationSeconds === 'number'
+          ? dialog.soundDurationSeconds
+          : DEFAULT_SOUND_EFFECT_DURATION_SECONDS;
+    const loop = dialog.soundLoop === true;
     return {
       kind: 'audio',
       audioKind: 'sound-effect',
@@ -556,7 +559,7 @@ export function buildImageGenerationSubmissionPlan({
         prompt: normalizedPrompt,
         model: soundModel,
         duration: durationSeconds,
-        loop: false,
+        loop,
       },
       result: {
         title: resolveGenerationAssetLabel(
@@ -567,6 +570,7 @@ export function buildImageGenerationSubmissionPlan({
           normalizedPrompt,
           soundModel,
           durationSeconds,
+          loop,
         ),
       },
     };

src/components/image-editor/ImageCanvasMetadataModalView.test.tsx

@@ -260,6 +260,61 @@ describe('ImageCanvasMetadataModalView', () => {
     expect(within(dialog).queryByText('420 x 120 px')).toBeNull();
   });
 
+  it('renders SFX V2 authoritative prompts, actual duration, loop, model, and full task id', () => {
+    render(
+      <ImageCanvasMetadataModalView
+        layer={createLayer({
+          title: '金币音效',
+          src: '/generated-character-drafts/editor-audios/coin.mp3',
+          mediaType: 'audio',
+          assetKind: 'sound-effect',
+          originalWidth: 420,
+          originalHeight: 120,
+          model: 'eleven_text_to_sound_v2',
+          taskId: 'task-sfx-v2-1234-abcd',
+          generationInputs: {
+            fields: [
+              { title: '用户描述', value: '金币落地' },
+              {
+                title: '实际英文提示词',
+                value: 'A bright coin landing chime',
+              },
+              { title: '时长', value: '7.42秒' },
+              { title: 'Loop', value: '开启' },
+            ],
+            references: [],
+            soundEffect: {
+              schemaVersion: 2,
+              userPrompt: '金币落地',
+              actualPrompt: 'A bright coin landing chime',
+              model: 'eleven_text_to_sound_v2',
+              durationMode: 'auto',
+              requestedDurationSeconds: null,
+              actualDurationSeconds: 7.42,
+              loop: true,
+            },
+          },
+        })}
+        onClose={vi.fn()}
+      />,
+    );
+
+    const dialog = screen.getByRole('dialog', { name: '音频信息' });
+    for (const text of [
+      '用户描述',
+      '金币落地',
+      '实际英文提示词',
+      'A bright coin landing chime',
+      '7.42秒',
+      'Loop',
+      '开启',
+      'eleven_text_to_sound_v2',
+      'task-sfx-v2-1234-abcd',
+    ]) {
+      expect(within(dialog).getByText(text)).toBeTruthy();
+    }
+  });
+
   it('does not render a dialog when no layer is selected', () => {
     render(<ImageCanvasMetadataModalView layer={null} onClose={vi.fn()} />);
 

src/components/image-editor/ImageCanvasMetadataModalView.tsx

@@ -105,7 +105,11 @@ export function ImageCanvasMetadataModalView({
             </>
           ) : null}
           <dt>Task</dt>
-          <dd>{formatTaskIdForDisplay(layer.taskId)}</dd>
+          <dd>
+            {layer.generationInputs?.soundEffect?.schemaVersion === 2
+              ? layer.taskId || '-'
+              : formatTaskIdForDisplay(layer.taskId)}
+          </dd>
         </dl>
       ) : null}
     </UnifiedModal>

src/components/image-editor/useImageCanvasGenerationWorkflow.test.tsx

@@ -1655,12 +1655,13 @@ describe('useImageCanvasGenerationWorkflow', () => {
       height: 120,
       sourceType: 'generated',
       prompt: '金币跳出音',
-      actualPrompt: '金币跳出音',
-      model: 'audio1.0',
-      provider: 'VectorEngine',
+      actualPrompt: 'A bright coin pop sound',
+      model: 'eleven_text_to_sound_v2',
+      provider: 'elevenlabs',
       taskId: 'task-sound',
       audioKind: 'sound-effect',
-      durationSeconds: 4,
+      durationSeconds: 7.42,
+      loop: false,
     });
     render(<GenerationWorkflowHarness />);
 
@@ -1673,11 +1674,13 @@ describe('useImageCanvasGenerationWorkflow', () => {
           prompt: '金币跳出音',
           model: 'eleven_text_to_sound_v2',
           duration: 8,
+          loop: false,
           generationInputs: {
             fields: [
-              { title: 'prompt', value: '金币跳出音' },
+              { title: '用户描述', value: '金币跳出音' },
               { title: 'model', value: 'eleven_text_to_sound_v2' },
-              { title: '时长', value: '8秒' },
+              { title: '请求时长', value: '8秒' },
+              { title: 'Loop', value: '关闭' },
             ],
             references: [],
           },

src/services/image-editor/editorProjectClient.test.ts

@@ -106,6 +106,7 @@ describe('editorProjectClient', () => {
           prices: { '480p': 13, '720p': 26, '1080p': 52 },
         },
         'audio1.0': { unit: 'perGeneration', price: 15 },
+        eleven_text_to_sound_v2: { unit: 'perGeneration', price: 16 },
         'chirp-v5': { unit: 'perGeneration', price: 9 },
       },
     });
@@ -113,6 +114,7 @@ describe('editorProjectClient', () => {
     const pricing = await loadEditorGenerationPricing();
 
     expect(pricing.models['gpt-image-2']?.prices?.['1K']).toBe(29);
+    expect(pricing.models.eleven_text_to_sound_v2?.price).toBe(16);
     expect(requestJsonMock).toHaveBeenCalledWith(
       '/api/editor/generation-pricing',
       { method: 'GET' },
@@ -1797,10 +1799,7 @@ describe('editorProjectClient', () => {
         }),
       }),
       '生成游戏音效失败',
-      expect.objectContaining({
-        timeoutMs: 1_200_000,
-        retry: editorRetryOptionsExpectation,
-      }),
+      { timeoutMs: 1_200_000 },
     );
   });
 

src/services/image-editor/editorProjectClient.ts

@@ -1396,7 +1396,6 @@ export async function generateEditorSoundEffect(
     '生成游戏音效失败',
     {
       timeoutMs: 1_200_000,
-      retry: EDITOR_GENERATION_REQUEST_RETRY_OPTIONS,
     },
   );
 }