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 |
|
zhayujie
|
d36d5aee3f
|
feat: rename repository name from chatgpt-on-wechat to CowAgent
- Update GitHub URLs in README.md (badges, release links, clone address, wiki, issues, contributors)
- Add project rename notice with SEO keywords and git remote update command
- Update docs/docs.json GitHub links
- Update all docs (zh/en/ja) across guide, intro, models, releases, skills
- Update run.sh and scripts/run.ps1 clone URLs and directory names
- Docker image name (zhayujie/chatgpt-on-wechat) kept unchanged for compatibility
|
2026-04-12 17:09:07 +08:00 |
|