aboutsummaryrefslogtreecommitdiffstats
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md7
1 files changed, 5 insertions, 2 deletions
diff --git a/README.md b/README.md
index 349c21d..3e05f00 100644
--- a/README.md
+++ b/README.md
@@ -46,7 +46,8 @@ persistent process and toggles like a scratchpad from a Hyprland keybind.
loaded into the model's context on demand. The model can call a
`load_skill` tool when a task matches one; you can type `/skill-name` or
mention a skill's name. Loaded skills show as removable chips, stay for
- the whole session in chat mode, and drop after the reply in one-shot mode.
+ the whole session in chat mode, and in one-shot mode stay in memory until
+ New or the chip is clicked (never written to history).
- **Tray icon** for show/hide/quit, hosted by waybar's tray module.
Not in this version: RAG or embedding search over history, multi-user
@@ -491,7 +492,9 @@ A skill is loaded into the model's context on demand, three ways:
- You mention a skill's name anywhere in the message.
Loaded skills show as removable chips above the input. They stay loaded for
-the whole session in chat mode and drop after the reply in one-shot mode.
+the whole session in chat mode. One-shot mode keeps them in memory (never in
+history) until New is pressed or the chip is clicked, so a skill loaded in a
+scratch window stays active for the rest of it.
`max_searches` caps the total tool rounds per turn here too, so skills load
and searches share the same per-turn budget.