mirror of
https://github.com/stablyai/orca.git
synced 2026-09-22 08:02:28 +00:00
Brennan Benson
66dfdc456f
* feat(computer-use): support macOS middle click and gate the AX click path `--mouse-button middle` already validated end-to-end through the CLI, the zod schema, and the provider validator, and both the Windows and Linux providers honored it. Only the macOS provider rejected it outright with "middle-click is not yet supported", so the flag was a dead end on the one platform that has no fallback. Two changes: - Add `.middle` to the macOS button mapping. macOS has no dedicated middle event family, so it rides `otherMouseDown`/`otherMouseUp` with the button number carried by `mouseButton: .center`; that constructor argument is honored for exactly the `otherMouse*` types, so no extra field write is needed. - Validate the requested button before the accessibility fast path, and skip that path for buttons it cannot express. Previously the raw string was read unvalidated, and `performClickAction` only special-cased `right`, so `click --mouse-button middle --element-index N` (no modifiers, count 1) fell through to `AXPress` — a left click — and reported success with `path: "accessibility"`. Any unrecognized button string did the same. This matches guards the Windows and Linux providers already had. The button enum moves into `OrcaComputerUseMacOSCore` so it is unit-testable; `main.swift` keeps only the CoreGraphics mapping. Also documents `--mouse-button` in the computer-use skill guide, which never mentioned the flag, so agents on Windows and Linux had no way to discover it. * test(computer-use): cover macOS middle click in the real-desktop e2e suite * test(computer-use): prove macOS middle-click delivery
65 lines
2.2 KiB
Swift
65 lines
2.2 KiB
Swift
public struct ActionArgumentValidationError: Error, Equatable {
|
|
public let message: String
|
|
|
|
public init(_ message: String) {
|
|
self.message = message
|
|
}
|
|
}
|
|
|
|
public enum MouseButtonSelection: String, Equatable, Sendable, CaseIterable {
|
|
case left
|
|
case right
|
|
case middle
|
|
|
|
/// Why: AXPress/AXShowMenu only model primary and secondary intent, so a middle
|
|
/// click has no accessibility equivalent and must reach the app as real events.
|
|
public var hasAccessibilityAction: Bool {
|
|
self != .middle
|
|
}
|
|
}
|
|
|
|
public enum ActionArgumentValidation {
|
|
public static func positiveInteger(
|
|
_ value: Double?,
|
|
defaultValue: Int,
|
|
name: String
|
|
) -> Result<Int, ActionArgumentValidationError> {
|
|
guard let value else { return .success(defaultValue) }
|
|
guard value.isFinite, value > 0, let parsed = boundedInteger(value, as: Int.self) else {
|
|
return .failure(ActionArgumentValidationError("\(name) must be a positive integer"))
|
|
}
|
|
return .success(parsed)
|
|
}
|
|
|
|
public static func positiveNumber(
|
|
_ value: Double?,
|
|
defaultValue: Double,
|
|
name: String
|
|
) -> Result<Double, ActionArgumentValidationError> {
|
|
guard let value else { return .success(defaultValue) }
|
|
guard value.isFinite, value > 0 else {
|
|
return .failure(ActionArgumentValidationError("\(name) must be a positive number"))
|
|
}
|
|
return .success(value)
|
|
}
|
|
|
|
public static func mouseButton(
|
|
_ value: String?
|
|
) -> Result<MouseButtonSelection, ActionArgumentValidationError> {
|
|
guard let value else { return .success(.left) }
|
|
guard let button = MouseButtonSelection(rawValue: value) else {
|
|
return .failure(ActionArgumentValidationError("unsupported mouse button '\(value)'"))
|
|
}
|
|
return .success(button)
|
|
}
|
|
|
|
public static func scrollDirection(_ value: String) -> Result<String, ActionArgumentValidationError> {
|
|
switch value {
|
|
case "up", "down", "left", "right":
|
|
return .success(value)
|
|
default:
|
|
return .failure(ActionArgumentValidationError("unsupported scroll direction: \(value)"))
|
|
}
|
|
}
|
|
}
|