Commit Graph

6 Commits

Author SHA1 Message Date
root 222e5a0219 refactor(ui): focus the product on image generation only
Drop the disabled video/3D model tabs from the composer and home model
picker, reword storyboard/campaign copy away from motion/video toward
static campaign frames, ease the home prompt editor font sizing, and
update the deterministic fallback message to describe image generation
and editing instead of "video not yet supported".

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 10:56:14 +08:00
root 3c5006e2f3 feat(composer): carry reference image names and submit on Enter
Propagate an optional imageName through the agent content pipeline
(frontend types → API → domain → prompt building) so reference images
render with their name instead of a bare "image" label.

Also switch PromptComposer to submit on plain Enter (Shift+Enter for
newline, IME-safe) and add a submitDisabled guard wired from the canvas
and home composers.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 08:41:15 +08:00
root f23c847e13 fix(agent-threads): hide prompt reference directives in thread titles
Add a shared visiblePromptText helper and strip reference tokens,
image-generator directives, and model-selection lines from agent thread
summaries and the assistant panel header, so titles show the user's
actual prompt instead of internal directives. Covered by a server test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 01:55:08 +08:00
root 07aa33d30e feat(image): preserve transparency for alpha images end to end
Skip WebP re-encoding for PNG/AVIF/BMP uploads and any bitmap that
actually contains alpha, tag transparency-capable canvas uploads with
the transparent-image tone, and detect alpha in merged layers so the
composed node keeps a transparent tone.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-08 01:54:32 +08:00
root 2f5291a0f9 feat(image): pass reference images to GPT image model for edits
Server: forward canvas/reference images to the image model so extract,
continue, and edit requests stay faithful to the source product.
- Add ImageRequestOptions.Images and route requests with inputs to the
  /v1/images/edits endpoint, via multipart upload (default) or JSON
  image_url payload, selectable through Agent.Image.InputImageTransport.
- Extract reference URLs from prompt directives, inline @image tokens,
  and chat message image/mask contents; fold them into the idempotency
  key and prepend a reference-fidelity instruction to the prompt.

Frontend:
- Shrink CanvasToast to a compact top pill.
- Paste an internal transparent clipboard node instead of re-uploading
  when it matches the clipboard image.
- Keep agent-project polling alive on stream error while streaming.
2026-07-08 01:19:20 +08:00
root 44406b72db Initial commit: img-infinite-canvas AI design workbench MVP
Moteva-style AI design workbench replica. Home prompt creates a project;
the project page provides an infinite canvas with node drag, zoom/pan,
a design chat panel, history replay, image asset upload, and project
save/regenerate.

- Backend: go-zero, DDD layering, sqlc/pgx, optional PostgreSQL; memory
  or Redis cache; asynq job queue; MinIO/S3/R2/OSS object storage;
  sky-valley/pi agent runtime adapter.
- Frontend: Next.js App Router + Vite artifact build, TypeScript, i18n,
  shadcn/ui components, auth (OTP/Turnstile/Google/WeChat).
- Deploy: Docker Compose and k3s manifests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-07 23:15:37 +08:00