diff options
| author | Danilo M. <danix@danix.xyz> | 2026-08-25 18:42:40 +0200 |
|---|---|---|
| committer | Danilo M. <danix@danix.xyz> | 2026-08-25 18:42:40 +0200 |
| commit | 6ae195baa09bc217d51f3fb0a38312dfdcc85fdb (patch) | |
| tree | f6e0f19af4bb0931fe23cd7cf65381e3e87930d2 /README.md | |
| parent | 767636465e43eb9662cde31037392d4b9c05a735 (diff) | |
| download | llamachat-6ae195baa09bc217d51f3fb0a38312dfdcc85fdb.tar.gz llamachat-6ae195baa09bc217d51f3fb0a38312dfdcc85fdb.zip | |
fix: honor skills_enabled on restore, and final-review polish
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 5 |
1 files changed, 5 insertions, 0 deletions
@@ -495,6 +495,11 @@ the whole session in chat mode and drop after the reply in one-shot mode. `max_searches` caps the total tool rounds per turn here too, so skills load and searches share the same per-turn budget. +Skill text is injected verbatim into the system prompt. Skills are +user-authored files in a directory you control, trusted the same way the +prompts in `prompts/` are, but treat a skill downloaded from elsewhere like +any other untrusted instructions. + ### External providers llamachat can talk to OpenAI-compatible cloud providers alongside the local |