feat(design): multi-provider support — GPT Image 1.5 + Gemini#946
Open
lubos-buracinsky wants to merge 2 commits intogarrytan:mainfrom
Open
feat(design): multi-provider support — GPT Image 1.5 + Gemini#946lubos-buracinsky wants to merge 2 commits intogarrytan:mainfrom
lubos-buracinsky wants to merge 2 commits intogarrytan:mainfrom
Conversation
- Upgrade OpenAI from gpt-4o Responses API to GPT Image 1.5 (gpt-image-1) via Images API. Better text rendering, dedicated image model. - Add Gemini provider (Nano Banana 2 / Gemini 3.1 Flash Image) as alternative. Faster, cheaper, good quality. - Auto-detect provider from available API keys. - New config: ~/.gstack/design.json with provider selection. - Backwards compatible: existing ~/.gstack/openai.json still works. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove response_format (not supported by gpt-image-1) - Use output_format: "png" (GPT Image always returns base64) - Parse both b64_json and b64 response fields - Add GOOGLE_AI_API_KEY as fallback for Gemini provider detection Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
gpt-4oResponses API to GPT Image 1.5 (gpt-image-1) via Images API. Better text rendering for UI mockups.~/.gstack/design.jsonwith explicit provider selection.~/.gstack/openai.jsonstill works.Why
The current
$D generateusesgpt-4owith theimage_generationtool, which routes to DALL-E 3 under the hood. GPT Image 1.5 is a newer, dedicated image model with significantly better text rendering (ELO 1264 on text benchmarks). For UI mockups with text, buttons, and layout, this is a meaningful quality upgrade.Gemini support opens the door for users who already have a Google API key (common in the ecosystem) but not an OpenAI key.
Changes
design/src/auth.ts— multi-provider config resolution (design.json > env vars > legacy openai.json)design/src/generate.ts— provider routing: OpenAI Images API + Gemini generateContent APITest plan
bun build --compile design/src/cli.ts)~/.gstack/openai.jsonstill worksGEMINI_API_KEYenv var auto-detects Gemini provider🤖 Generated with Claude Code