codenomad-automation

# CodeNomad Automation Use this workflow when changing CodeNomad itself: 1. Call `codenomad.inspect` before editing. It identifies the visible local CodeNomad window, verifies that this OpenCode session is the active pane, and returns accessibility refs plus runtime diagnostics. 2. Use only refs from the latest inspection with `codenomad.act`. Inspect again after navigation, reload, tab changes, or failed actions. 3. Make the smallest source change and run the relevant typecheck, native test, or build. Automation does not own OpenCode: the shared `opencode2` daemon and this session remain alive if CodeNomad closes. 4. After updated artifacts are ready, call `codenomad.act` with `action: "restart"`. The call gracefully relaunches the host pinned by the latest inspection, waits for the same artifact identity to reconnect to the OpenCode session, and returns a fresh inspection. It never switches to another worktree's build. 5. Call `codenomad.screenshot` for final visual evidence and report the checks that ran. If no target is found, make the session visible in a local CodeNomad window. Current builds initialize automation at normal startup; there is no Developer Mode toggle or additional activation restart. An older running build must first be replaced with the rebuilt artifact. Do not use the removed Advanced Settings launcher or install a build-specific global OpenCode plugin shim. For Electron, rebuild before relaunching. For Windows Tauri, stop and launch the rebuilt executable manually only when the Windows linker cannot replace the running binary; the OpenCode daemon and session still persist across that gap.