147 lines
5.9 KiB
Plaintext
147 lines
5.9 KiB
Plaintext
name: click
|
|
|
|
description:
|
|
Click against a target pid. **Prefer `element_index` over pixel coordinates** — element_index works on backgrounded / hidden windows, surfaces a stable handle, and tells you what you're clicking via the cached AT-SPI element's role + label. Reach for `x, y` only when the target is a canvas / custom-drawn surface that doesn't appear in the AT-SPI tree.
|
|
|
|
Provide either (window_id + x/y) or (pid + element_index). Routes via XSendEvent (no focus steal). element_index cache is scoped per (pid, window_id) and is replaced by the next get_window_state of the same window — re-snapshot every turn before clicking.
|
|
|
|
After a zoom call, pass from_zoom=true to auto-translate zoom-image coords back to full-window space.
|
|
|
|
button: "left" (default), "right", or "middle". Defaults to left so the field is fully back-compat. X11: routes through XSendEvent ButtonPress/Release with the matching button code. Native Wayland: only left-button is supported via the virtual-pointer protocol — right/middle return an error rather than silently degrading to left. `modifier` holds ctrl/shift/alt/super for the click on X11. Native Wayland refuses modified pointer clicks until its input protocol can carry keyboard modifier state.
|
|
|
|
input_schema:
|
|
{
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"button": {
|
|
"description": "Mouse button. Default: \"left\" (legacy back-compat). X11: routed via ButtonPress/Release with the matching evdev code. Native Wayland: only left-button is supported via the virtual-pointer protocol; right/middle return an error.",
|
|
"enum": [
|
|
"left",
|
|
"right",
|
|
"middle"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"count": {
|
|
"type": "integer"
|
|
},
|
|
"cursor_id": {
|
|
"description": "Optional multi-cursor instance id. Default: 'default'.",
|
|
"type": "string"
|
|
},
|
|
"delivery_mode": {
|
|
"default": "background",
|
|
"description": "Input delivery mode. 'background' (default) never activates or raises the target window. On X11 it injects via XTEST / the XInput2 master pointer (no focus steal). On Wayland it goes through libei + xdg-desktop-portal, which injects to the compositor's input focus — Wayland's security model has no per-window background targeting, so a specific non-focused window cannot be aimed at; when no libei backend is available the tool returns a structured background_unavailable error. 'foreground' is the explicit escalation: activate the target (X11 _NET_ACTIVE_WINDOW; Wayland compositor activate), inject, then restore the prior active window — a brief focus swap unless the target was already active. Matches the macOS / Windows delivery_mode surface.",
|
|
"enum": [
|
|
"background",
|
|
"foreground"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"element_index": {
|
|
"description": "Element index from get_window_state. Requires the matching `snapshot_id` alongside it. Prefer `element_token`, which carries both values.",
|
|
"type": "integer"
|
|
},
|
|
"element_token": {
|
|
"description": "Opaque per-snapshot element handle from `structuredContent.elements[].element_token`. If element_index, snapshot_id, or window_id are also supplied they must agree. Returns an explicit stale error once a newer snapshot supersedes it.",
|
|
"type": "string"
|
|
},
|
|
"from_zoom": {
|
|
"description": "Set true after a zoom call to auto-translate zoom-image pixel coordinates back to full-window space.",
|
|
"type": "boolean"
|
|
},
|
|
"modifier": {
|
|
"description": "Modifier keys held during the action: cmd, shift, option/alt, ctrl.",
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"type": "array"
|
|
},
|
|
"pid": {
|
|
"type": "integer"
|
|
},
|
|
"scope": {
|
|
"default": "window",
|
|
"enum": [
|
|
"window",
|
|
"desktop"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"session": {
|
|
"description": "For multi-call work, prefer a short public session label and repeat it on every call that accepts it. Omit it to use the authenticated transport's implicit lifecycle session.",
|
|
"type": "string"
|
|
},
|
|
"snapshot_id": {
|
|
"description": "Snapshot handle from get_window_state. Required when targeting by element_index; stale snapshots fail closed.",
|
|
"pattern": "^s[0-9a-f]{8}$",
|
|
"type": "string"
|
|
},
|
|
"target": {
|
|
"anyOf": [
|
|
{
|
|
"description": "Exact capture/input target selected independently for each action.\n\n`display_id=\"primary\"` is the portable desktop target in this release.\nPlatforms that cannot address another display reject it explicitly rather\nthan silently changing coordinate spaces.",
|
|
"oneOf": [
|
|
{
|
|
"additionalProperties": true,
|
|
"properties": {
|
|
"kind": {
|
|
"const": "window",
|
|
"type": "string"
|
|
},
|
|
"pid": {
|
|
"format": "uint32",
|
|
"minimum": 0,
|
|
"type": "integer"
|
|
},
|
|
"window_id": {
|
|
"format": "uint64",
|
|
"minimum": 0,
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"kind",
|
|
"pid",
|
|
"window_id"
|
|
],
|
|
"type": "object"
|
|
},
|
|
{
|
|
"additionalProperties": true,
|
|
"properties": {
|
|
"display_id": {
|
|
"type": "string"
|
|
},
|
|
"kind": {
|
|
"const": "desktop",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"kind",
|
|
"display_id"
|
|
],
|
|
"type": "object"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
]
|
|
},
|
|
"window_id": {
|
|
"type": "integer"
|
|
},
|
|
"x": {
|
|
"type": "number"
|
|
},
|
|
"y": {
|
|
"type": "number"
|
|
}
|
|
},
|
|
"required": [],
|
|
"type": "object"
|
|
}
|