Fix PaintPlus OpenAI edit quality: edits silently fell back to dall-e-2

inpaint()/img2img()/outpaint() called /v1/images/edits without a model
field, so OpenAI defaulted every cloud edit to dall-e-2 regardless of
configuration — while txt2img used dall-e-3. Add a separate
OPENAI_EDIT_MODEL (default gpt-image-1, the only current model that
supports masked edits at ChatGPT-comparable quality), thread it through
the provider and both compose files, and handle gpt-image-1's
b64_json-only response shape alongside the url shape dall-e-2/3 return.

paintplus/backend/app/config.py

@@ -27,7 +27,8 @@ class Settings(BaseSettings):
 
     # Provider API Keys
     openai_api_key: str = ""
-    openai_model: str = "dall-e-3"
+    openai_model: str = "dall-e-3"          # text-to-image (generations endpoint)
+    openai_edit_model: str = "gpt-image-1"  # inpaint/img2img/outpaint (edits endpoint — dall-e-3 isn't supported there)
     stability_api_key: str = ""
     replicate_api_key: str = ""