mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-06-03 10:47:08 +08:00

Files

zhayujie 68ce2e5232 feat(skill): multi-provider image generation with auto-fallback

- Add Gemini, Seedream (Volcengine Ark), Qwen (DashScope), MiniMax
  providers to image-generation skill with universal sequential
  fallback: OpenAI → Gemini → Seedream → Qwen → MiniMax → LinkAI
- Each provider filters unsupported size tiers to valid values
  (e.g. Seedream 1K→2K, Qwen 3K→2K, Gemini 3K→2K)
- Pinned model only tries its native provider; auto-routing uses
  each provider's default model
- Support skill-namespaced config (config.skill.image-generation.model
  → SKILL_IMAGE_GENERATION_MODEL env var)
- Add image lightbox (click-to-enlarge) in web console
- Add  docs for built-in skills (skill-creator, knowledge-wiki,
  image-generation) under docs/skills/

2026-04-23 12:39:39 +08:00

static

feat(skill): multi-provider image generation with auto-fallback

2026-04-23 12:39:39 +08:00

chat.html

fix(web): smart auto-scroll for chat #2775

2026-04-20 21:43:21 +08:00

README.md

docs: add web channel and agent plugin docs

2025-05-23 11:56:41 +08:00

web_channel.py

feat(skill): support gpt-image-2 in image generation skill