Remove load from SKILL.toml fallback #10007
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 28253fa7a3
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| let interface_path = skill_dir.join(SKILLS_JSON_FILENAME); | ||
| if !interface_path.exists() { | ||
| return None; |
There was a problem hiding this comment.
Because load_skill_interface now returns None whenever SKILL.json is missing, any skill that still publishes interface metadata only in SKILL.toml (the legacy format still referenced in the protocol docs) will silently lose display_name, icons, and default_prompt, so clients/UI regress to bare SKILL.md metadata. If TOML-based skills are still in circulation, this change is a backward‑compat break unless you migrate them or keep a fallback reader.
Useful? React with 👍 / 👎.
No description provided.