fix: update image models, handle upstream errors in HTTP 200

Three issues found in activity logs:

1. Image model IDs stale — FLUX and Seedream removed from OpenRouter.
   Updated to current models: Gemini 2.5/3.1 Flash Image, Gemini 3 Pro
   Image, GPT-5 Image/Mini. Default changed to gemini-2.5-flash-image.

2. openrouter/free router wraps upstream 429 errors in HTTP 200 body
   with error object. Both text and image response parsers now detect
   this pattern and surface a proper RuntimeException.

3. Image request used modalities: ["image"] but Gemini needs
   ["image", "text"]. Updated to include both.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
peptiderepo
2026-04-18 10:47:05 +07:00
parent cf3d97c0c3
commit 862d7e40e6
6 changed files with 63 additions and 45 deletions

View File

@@ -57,7 +57,7 @@ define( 'PRAUTOBLOGGER_DEFAULT_EDITOR_MODEL', 'google/gemini-2.5-flash-lite' );
// Default provider is OpenRouter (higher quality); Cloudflare is the fallback.
// Default model is FLUX.2 Pro via OpenRouter (~$0.03/image, good quality).
define( 'PRAUTOBLOGGER_DEFAULT_IMAGE_PROVIDER', 'openrouter' );
define( 'PRAUTOBLOGGER_DEFAULT_IMAGE_MODEL', 'black-forest-labs/flux-2-pro' );
define( 'PRAUTOBLOGGER_DEFAULT_IMAGE_MODEL', 'google/gemini-2.5-flash-image' );
// CEO-approved image style suffix (decision locked 2026-04-15). Users may
// override via Settings → Images → Style Suffix; this constant is the