# 2026-09-18 — AppleScript launcher (`scripts/launch-ori.applescript`)

## State

Written, compile-checked, handlers tested in isolation. **Not yet run end to end** — that needs Docker Desktop + a real `sbx run`, which creates the sandbox and starts Claude inside it. First real run to do by the user: `osascript scripts/launch-ori.applescript`.

## Things to confirm on the first real run

- Behaviour of `sbx run -d --name ori` when the sandbox is already **running** (unknown: no-op or error?). The script only notifies on error there and relies on the health check, so either way the app should open; tighten if the notification is noisy.
- Time for the kit to start the server after `sbx run -d` returns; budget is 90 s (`healthTimeoutSeconds`), adjust if the template pull makes the first launch slower.
- `display notification` from a compiled app may need notification permission the first time.

## Traps

- `do shell script` PATH: fine from a terminal (inherits the shell), minimal from Finder — hence the explicit `export PATH`.
- `sbx inspect`/`sbx ports` on a missing sandbox print `ERROR:` but their exit code was masked in my probe; `sbx ls -q` (names only) is the reliable existence test.
- Handlers can be tested without running `on run`: `osacompile -o /tmp/x.scpt …` then `load script` + call `s's waitForServer(...)`.

## Update (same day) — double-clickable app

`scripts/Launch Ori.app` built with `osacompile -o "scripts/Launch Ori.app" scripts/launch-ori.applescript`; gitignored (`scripts/*.app/`), rebuild after editing the `.applescript`. `path to me` then resolves to the `.app` bundle inside `scripts/`, so the repo root still derives correctly. The app has no quarantine attribute (built locally), so Gatekeeper does not block it. Still not run end to end.

## Update — README

`scripts/README.md` (EN) and `scripts/README.fr.md` (FR) document the launcher; keep them in sync with the `property` defaults at the top of the script if those change.