mirror of
https://github.com/getcompanion-ai/co-mono.git
synced 2026-04-20 15:01:24 +00:00
feat(coding-agent): support disable-model-invocation frontmatter for skills
When set to true, the skill is hidden from the system prompt, preventing agentic invocation. Users can still invoke explicitly via /skill:name. Also fixes pre-existing test bug where source expectation was wrong. Fixes #927
This commit is contained in:
parent
3235926eed
commit
951fb953ed
8 changed files with 99 additions and 3 deletions
|
|
@ -11,6 +11,7 @@
|
|||
|
||||
### Added
|
||||
|
||||
- `disable-model-invocation` frontmatter field for skills to prevent agentic invocation while still allowing explicit `/skill:name` commands ([#927](https://github.com/badlogic/pi-mono/issues/927))
|
||||
- Exposed `copyToClipboard` utility for extensions ([#926](https://github.com/badlogic/pi-mono/issues/926) by [@mitsuhiko](https://github.com/mitsuhiko))
|
||||
- Skill invocation messages are now collapsible in chat output, showing collapsed by default with skill name and expand hint ([#894](https://github.com/badlogic/pi-mono/issues/894))
|
||||
- Header values in `models.json` now support environment variables and shell commands, matching `apiKey` resolution ([#909](https://github.com/badlogic/pi-mono/issues/909))
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue