sliccy 6.205.0 → 6.207.0

package/README.md

@@ -93,7 +93,7 @@ SLICC is for you if:
 - **Inspect experimental features from the avatar menu.** When centrally managed flags enable the surface for the current runtime, click your avatar and choose **Experimental features…** to open its standalone dialog. The dialog may honestly be empty: `experimental-settings` controls its availability but is not itself user-toggleable. Experimental features take effect when SLICC boots, so flipping one only matters on the next load. Changes are held until you confirm: the dialog says what is waiting and offers **Reload now** to save and apply them, or **Revert** to drop them. Nothing is written until you reload, and dismissing the dialog discards — so a flag can never end up reading `on` with nothing to show for it.
 - **Steer a running turn instead of waiting for it.** In the chat composer, `Enter` sends — including from a hardware keyboard in the native iOS follower — and queues behind whatever the cone is already doing; `Shift+Enter` inserts a newline. `Ctrl+Enter` (`Cmd+Enter` on macOS) steers: the message is injected as soon as the current step finishes, so you can redirect the agent mid-turn.
 - **Boot full x86 virtual machines in the browser.** `v86 start` runs real operating systems (Alpine, FreeDOS, KolibriOS, ...) on the wasm-based [v86](https://github.com/copy/v86) emulator, entirely client-side. The agent drives the guest from the shell — type, click, screenshot, stream the screen live, save/restore state — and `-net <model>,relay=fetch` gives the guest HTTP access through SLICC's fetch proxy. Install with `ipk add -g v86`.
-- **Run native command-line programs compiled to wasm.** A package that ships Emscripten programs (for example `ipk add -g @ai-ecoverse/wasm-pkgconf`) makes each one a shell command. Each process runs in a worker of its own, with real pipes and child processes; `wasm --list` shows what is installed. No local mount or server is needed.
+- **Run native command-line programs compiled to wasm.** A package that ships Emscripten programs (for example `ipk add -g @ai-ecoverse/wasm-pkgconf`) makes each one a shell command. Each process runs in a worker of its own, with real pipes, child processes and signals; `wasm --list` shows what is installed, and `wasm -t bash` gives an interactive shell on the panel terminal. No local mount or server is needed.
 - **Delegate parallel work to scoops.** Split tasks into isolated sub-agents with their own sandboxes and context, then let the main agent coordinate the results. If a scoop hits a terminal model or provider failure, its owner gets a durable error card without spending another model call to acknowledge the outage; fatal state still bypasses mute and releases `scoop_wait`.
 - **Turn one-off wins into reusable workflows.** Package behavior as skills, build interactive sprinkles, and react to external events with webhooks and cron-driven licks.
 - **Mount your local file system.** By default, SLICC is confined to your browser. But you can ask it to mount folders from your local file system, so it can read and write from there. Mount into an empty path such as `/mnt/myproject` so you do not hide existing skills or scripts. Tear one down with `umount /mnt/myproject` (or the longer `mount unmount /mnt/myproject`). Picker mounts ask again after a page reload; for folders you always want available, map them in the launcher's mount table (`npx slicc --mount=~/Projects/foo:/mnt/foo`, or Settings → Mounts in Sliccstart.app) and they are mounted automatically on every launch, with no picker or permission prompt — see [Auto-mounted host folders](docs/mounts.md#auto-mounted-host-folders-the-mount-table).