Replace retired OpenAI image models with gpt-image-2 (DALL-E shut down 2026-05-12)

- openai_image: enum narrowed to ["gpt-image-2"]; DALL-E code path, sizes
  (1024x1792/1792x1024) and qualities (standard/hd) removed; estimate_cost
  updated to real GPT Image 2 pricing ($0.006/$0.053/$0.211 at 1024x1024)
- image_gen (deprecated but callable): default dall-e-3 -> gpt-image-2; drop
  response_format="b64_json", which GPT image models reject; update pricing
- docs/skills sweep: scrub retired-model references from README (en/zh),
  .env.example, docs/PROVIDERS.md (incl. pricing table + deprecation note),
  docs/ARCHITECTURE.md, AGENT_GUIDE.md, skills/creative/*, 14 pipeline
  director skills, and tests/qa/QA_PLAN.md

Source: https://developers.openai.com/api/docs/deprecations

proofread by fable 5 + codex
This commit is contained in:
Remotely Human
2026-07-02 11:36:31 +08:00
parent 07739952a8
commit fabc0e7088
26 changed files with 69 additions and 85 deletions

View File

@@ -48,7 +48,7 @@ OpenMontage/
│ ├── audio/ # TTS (ElevenLabs, OpenAI, Piper), music gen, mixing, enhancement
│ ├── avatar/ # Talking head animation, lip sync
│ ├── enhancement/ # Upscale, bg removal, face enhance/restore, color grading
│ ├── graphics/ # Image gen (FLUX, DALL-E, Recraft, local diffusion), stock, diagrams, code snippets, math animation
│ ├── graphics/ # Image gen (FLUX, GPT Image, Recraft, local diffusion), stock, diagrams, code snippets, math animation
│ ├── publishers/ # (Reserved)
│ ├── subtitle/ # SRT/VTT generation from timestamps
│ └── video/ # 13 video gen providers, composition, stitching, trimming
@@ -383,7 +383,7 @@ All config is validated via Pydantic models in `lib/config_model.py`.
| Variable | Used By | Purpose |
|----------|---------|---------|
| `ELEVENLABS_API_KEY` | elevenlabs_tts, music_gen | TTS, music, sound effects |
| `OPENAI_API_KEY` | openai_tts, openai_image | TTS fallback, DALL-E 3 |
| `OPENAI_API_KEY` | openai_tts, openai_image | TTS fallback, GPT Image 2 |
| `XAI_API_KEY` | grok_image, grok_video | Grok image editing/generation, Grok video generation |
| `FAL_KEY` | flux_image, kling_video, veo_video, minimax_video, recraft_image | fal.ai hosted models (FLUX, Veo, Kling, MiniMax, Recraft) |
| `HEYGEN_API_KEY` | heygen_video | Multi-provider video generation |