Trey t 2ab8af64d4 feat: add variation spawner and content repurposing
Variation spawner: select an image asset → spawn N variations that keep the
same emotional pattern/visual style but explore different hook angles. Runs
a focused ad-creative-designer agent with the original as a Gemini reference
image. New assets link back via parentAssetId.

Content repurposing: resize an image to all other platform dimensions using
Sharp (cover crop). Captions are re-toned for the target platform via Claude
CLI. No external APIs needed — fully local.

- Add parentAssetId self-relation to Asset model
- lib/repurpose.ts: Sharp resize, platform format mapping, caption re-toning
- lib/variations.ts: asset DNA extraction, variation prompt builder, mini-pipeline
- API routes: /api/assets/[id]/repurpose (GET formats, POST resize)
- API routes: /api/assets/[id]/variations (GET existing, POST spawn)
- Repurpose modal: checkbox list of target formats
- Variation modal: count picker, async launch
- Asset card: Repurpose + Variations buttons on image assets
- Asset lineage: "Derived from" shown on child assets

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-23 22:46:42 -05:00
2026-03-23 11:55:42 -05:00

This is a Next.js project bootstrapped with create-next-app.

Getting Started

First, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.

Learn More

To learn more about Next.js, take a look at the following resources:

You can check out the Next.js GitHub repository - your feedback and contributions are welcome!

Deploy on Vercel

The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.

Check out our Next.js deployment documentation for more details.

S
Description
No description provided
Readme 212 MiB
Languages
TypeScript 92.4%
JavaScript 5.9%
CSS 1.2%
Dockerfile 0.3%
Shell 0.2%