feat: add ChatGPT subscription image scenes to Studio - #7
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds an explicit Generate image scene with ChatGPT action to PurplePrint Studio's AI session whenever ChatGPT subscription (Codex) is connected. It works while Claude or another provider remains selected for chat; generating an image does not change the active chat model. Each run requires confirmation because it consumes subscription limits. The Codex app-server uses the Studio-owned CLI profile, with API keys stripped, a read-only sandbox, and shell/web/apps/editor tools disabled.
The generated image is copied into app-owned project storage and previewed in chat. Studio also encodes a five-second, 24 fps MP4 and imports it into the existing video-only Media panel; the original image remains beside the clip. Known duration is recorded on the imported asset. This is a still-image scene workflow, not animation, Blender/Hyperframe, or Design Coach integration.
Type of change
Release impact
Desktop impact
Screenshots / video
No desktop screenshot is uploaded. An unsigned validation artifact from the first commit was installed on the owner's Windows PC and exercised with a synthetic, non-private scene. The provider-independent routing change was subsequently installed in a stacked PR #8 Windows candidate. With Claude local selected and Codex connected, the image-scene button enabled for a typed prompt. No second live image was generated. This PR is not a GitHub Release.
Testing
npm run test: 191 files, 2,269 passed, 4 skipped after the routing update.npm run lint,npm run i18n:check, andnpx vite build: passed. Lint reports 13 existing warnings outside the changed code.durationSec: 5video asset and one timeline clip. Studio exported a separate MP4 that decoded cleanly at 5.00 seconds and 120 frames.opus[1m]alias instead of restoring the legacy pre-test model ID.Risks / rollout