Prefer Super+H for host window hiding
Update computer_use_remote guidance for Ubuntu/GNOME/Wayland so hide-window tasks use Super+H instead of Alt+F9. Reinforce that type results only prove keystrokes were sent and that the agent must verify the fresh screenshot before typing follow-up text or claiming success.
Alessandro committed
May 23, 2026 at 11:33 UTC
2f9037a1953c029c25d3852c018df0171bb162a9
3 files changed
+10
-3
plugins/_a0_connector/prompts/agent.system.tool.computer_use_remote.md
+1
-1
@@ -10,7 +10,7 @@ If the tool reports no CLI, disabled computer use, or `COMPUTER_USE_REARM_REQUIR
10
11
Call `start_session` before screen-driven tasks. Use `status` for state only, `capture` for screenshots without an action, and `stop_session` when the desktop task is complete. Interactive actions should use normalized global-screen coordinates from the most recent capture.
12
13
-State-changing actions automatically attach a fresh screen after they run. Treat key presses, clicks, scrolling, typing, and window-manager shortcuts as attempts, not success: inspect the latest attached screen, or one explicit `capture` if it is unclear or unchanged, before saying the requested outcome happened. This is mandatory for Ubuntu/Wayland shortcuts such as `Alt+F9`.
13
+State-changing actions automatically attach a fresh screen after they run. Treat key presses, clicks, scrolling, typing, and window-manager shortcuts as attempts, not success: inspect the latest attached screen, or one explicit `capture` if it is unclear or unchanged, before saying the requested outcome happened. For Ubuntu/GNOME/Wayland hide-window tasks, prefer `Super+H` (`{"action":"key","keys":["Super","H"]}`) for the active window; do not use `Alt+F9` as the primary hide/minimize shortcut because it often leaves the window visible. A `type` result only proves keystrokes were sent; it does not prove the window was hidden or that text landed in the intended place.
14
15
```json
16
{
plugins/_a0_connector/skills/host-computer-use/SKILL.md
+3
-1
@@ -88,7 +88,9 @@ If any tool result contains `COMPUTER_USE_REARM_REQUIRED` or `status=rearm requi
88
- If the same approach has already failed twice without visible progress, switch strategy instead of repeating it.
89
- Do not infer focus or task completion from chat logs, sidebars, tool summaries, or status text.
90
- Never claim a window was hidden, minimized, moved, text was submitted, or navigation completed until the latest screenshot visibly confirms it.
91
-- Treat Ubuntu/Wayland window-manager shortcuts such as `Alt+F9` as attempts only; verify the result from the fresh screenshot before deciding what happened.
91
+- On Ubuntu/GNOME/Wayland, use `Super+H` (`{"action":"key","keys":["Super","H"]}`) to hide the active window. Do not use `Alt+F9` as the primary hide/minimize shortcut on this environment; it often leaves the window visible.
92
+- After any hide/minimize shortcut, inspect the fresh screenshot. If the target window or focused composer is still visible, treat the attempt as failed and do not type follow-up text into the active field.
93
+- A `type` tool result only confirms keystrokes were sent. It is not evidence that the text landed in the intended application, nor evidence that a window was hidden first.
94
- For browser-navigation tasks done through this tool, only claim success if the browser content area visibly shows the destination page or result.
95
- If the attached screenshot appears unchanged after a state-changing action, use one explicit `capture` to verify before repeating the same action.
96
- Use `type(..., submit=true)` only for URL or navigation-style entry where Enter should fire immediately after typing.
tests/test_a0_connector_prompt_gating.py
+6
-1
@@ -136,9 +136,14 @@ def test_computer_use_remote_prompt_requires_visual_verification_after_actions()
136
137
assert "Treat key presses, clicks, scrolling, typing" in prompt
138
assert "attempts, not success" in prompt
139
+ assert "Super+H" in prompt
140
+ assert '["Super","H"]' in prompt
141
assert "Alt+F9" in prompt
142
+ assert "Do not use `Alt+F9` as the primary hide/minimize shortcut" in skill
143
+ assert "A `type` tool result only confirms keystrokes were sent" in skill
144
+ assert "do not type follow-up text into the active field" in skill
145
assert "visibly confirms" in skill
141
- assert "Ubuntu/Wayland" in skill
146
+ assert "Ubuntu/GNOME/Wayland" in skill
147
148
149
def test_remote_file_and_exec_tools_are_standard_tool_prompts_independent_from_context():