Add image-to-text Describe on the bench via exclusive llama.cpp caption jobs.

server/utils/jobs.ts

@@ -36,9 +36,11 @@ export interface Job {
   upscale?: boolean
   yueGp?: boolean
   yue2?: boolean
+  caption?: boolean
+  resultText?: string
   musicActivity?: { checkedAt: number; running: boolean }
   id: string
-  kind?: 'video' | 'edit' | 'music'
+  kind?: 'video' | 'edit' | 'music' | 'caption'
   promptId?: string
   clientId: string
   status: JobStatus
@@ -222,6 +224,7 @@ export function jobSnapshot(job: Job) {
     clipId: job.clipId,
     stillId: job.stillId,
     trackId: job.trackId,
+    resultText: job.resultText,
     hideThumbnail: job.hideThumbnail,
     error: job.error,
     folderLocked: job.library?.folderLocked,