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>
Replaces Cloudflare Workers AI (FLUX.1 schnell) as the default image
provider with OpenRouter, which offers FLUX.2 Pro, Seedream 3.0,
Gemini Flash Image, and GPT Image 1 at comparable or better pricing.
- New provider class (3-file split: provider, pricing, support) reuses
the existing OpenRouter API key and Cloudflare AI Gateway
- Admin settings: new Image Provider dropdown (openrouter/cloudflare),
model picker shows all available image models from both providers
- Image pipeline auto-selects the configured provider at construction
- Cost logging now uses actual model name instead of hardcoded flux-1-schnell
- Default model changed to black-forest-labs/flux-2-pro ($0.03/image)
- Unit tests for pricing resolution and provider response parsing
Cost impact: FLUX.2 Pro at $0.03/image vs schnell at $0.0007/image —
~43x more expensive per image, but dramatically better quality. At 2
images/article × 1 article/day = ~$1.80/month. Seedream 3.0 ($0.003)
available as a budget alternative.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Apply the same interactive model picker UI to the image model field.
Since Cloudflare models don't come from OpenRouter's registry, the
two FLUX models are embedded as static data in the page config and
the JS popup renders cost-per-image instead of token pricing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract schedule, publishing, analytics, and images field definitions
into PRAutoBlogger_Settings_Fields_Extended. Core class retains sections
and API/Models/Content/Sources fields, merging extended fields via
get_fields(). Both files well under 300-line limit.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
