seahi/baoyu-skills
1
0
Fork 0
mirror of https://github.com/JimLiu/baoyu-skills.git synced 2026-08-08 09:53:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(baoyu-imagine): add OpenAI-compatible image API dialect support

Browse Source 
Add --imageApiDialect flag, OPENAI_IMAGE_API_DIALECT env var, and
default_image_api_dialect config for gateways that expect aspect-ratio
size plus metadata.resolution instead of pixel size.
This commit is contained in:
Jim Liu 宝玉
2026-04-12 02:14:18 -05:00
parent 58ba4579ef
commit 11d80eeaa9
18 changed files with 298 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/baoyu-imagine/references/config/first-time-setup.md
+3
View File
@@ -175,6 +175,7 @@ default_provider: [selected provider or null]
default_quality: [selected quality]
default_aspect_ratio: null
default_image_size: null
default_image_api_dialect: null
default_model:
google: [selected google model or null]
openai: null
@@ -187,6 +188,8 @@ default_model:
---
```
If the user selects `OpenAI` but says their endpoint is only OpenAI-compatible and fronts another image model family, save `default_image_api_dialect: ratio-metadata` when they explicitly confirm the gateway expects aspect-ratio `size` plus metadata-based resolution. Otherwise leave it `null` / `openai-native`.
## Flow 2: EXTEND.md Exists, Model Null
When EXTEND.md exists but `default_model.[current_provider]` is null, ask ONLY the model question for the current provider.