domain

type Action struct {
	Kind      ActionKind
	Target    *Target
	Text      string // type: the text to type
	Label     string // press: exact accessibility label
	Scope     string // accessibility/press: frontmost, dock, menubar, app:<name>, or pid:<n>
	Combo     string // key: a combo such as "cmd+shift+t"
	Button    string // click kinds: left (default), right, middle
	Direction string // scroll: vertical (default) or horizontal
	Amount    int    // scroll: wheel clicks; negative reverses direction
}

type ActionKind string

type Image struct {
	Data     string // base64-encoded
	MimeType string
	Path     string // on-disk copy, reachable by ImageDecode for non-vision models
}

type Observation struct {
	Message  string // LLM-facing outcome description
	CursorX  int
	CursorY  int
	Width    int // frame-space dimensions
	Height   int
	Image    *Image      // set by screenshot actions
	Elements []UIElement // set by accessibility observations
}

type Region struct {
	X      int
	Y      int
	Width  int
	Height int
}

type Target struct {
	X int
	Y int
	// Region, on a screenshot action, captures only this rectangle.
	Region *Region
}

type UIElement struct {
	Role  string `json:"role"`
	Label string `json:"label"`
	State string `json:"state"`
	BBox  [4]int `json:"bbox"`
}