From a8198267718633d2acfbc14854eee7ee127e7d27 Mon Sep 17 00:00:00 2001 From: Yo_DDV <116607353+Yo-DDV@users.noreply.github.com> Date: Mon, 29 Jun 2026 14:55:51 +0200 Subject: [PATCH] fix: align computer use version parity --- Cargo.lock | 2 +- computer-use-linux/Cargo.toml | 2 +- computer-use-linux/src/server.rs | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 601791a3..c2a69fb1 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -482,7 +482,7 @@ dependencies = [ [[package]] name = "codex-computer-use-linux" -version = "0.2.9-linux-alpha1" +version = "0.2.10-linux-alpha1" dependencies = [ "anyhow", "atspi", diff --git a/computer-use-linux/Cargo.toml b/computer-use-linux/Cargo.toml index bd346555..307a56d7 100644 --- a/computer-use-linux/Cargo.toml +++ b/computer-use-linux/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "codex-computer-use-linux" -version = "0.2.9-linux-alpha1" +version = "0.2.10-linux-alpha1" edition = "2021" [[bin]] diff --git a/computer-use-linux/src/server.rs b/computer-use-linux/src/server.rs index 78a0ed9f..fd4e2fad 100644 --- a/computer-use-linux/src/server.rs +++ b/computer-use-linux/src/server.rs @@ -1110,7 +1110,7 @@ impl ComputerUseLinux { // The rmcp tool_handler macro only accepts a string literal here, so this // can't be env!("CARGO_PKG_VERSION"); the MCP safety check (CI) fails the // build if it drifts from the Cargo version. - version = "0.2.9-linux-alpha1", + version = "0.2.10-linux-alpha1", instructions = "Begin every turn that uses Computer Use by calling get_app_state. If diagnostics report disabled GNOME accessibility, call setup_accessibility before asking the user to retry. Use list_windows/focused_window before targeted keyboard input. If diagnostics report windowing.can_list_windows=false on GNOME, call setup_window_targeting to install the optional GNOME Shell extension backend, then ask the user to log out and back in if the setup report says a shell reload is required. This Linux backend can capture size-bounded screenshots through GNOME Shell or XDG Desktop Portal, read AT-SPI trees with action/value metadata, invoke native AT-SPI actions, set AT-SPI values or editable text, list/focus compositor windows through registered Linux window backends when the session permits it, attach best-effort terminal tty/process metadata to terminal windows, send coordinate or element-targeted click/scroll/drag input through the Wayland remote desktop portal when available, and send layout-safe literal type_text through KDE clipboard integration on Plasma Wayland or through portal keysyms on other Wayland sessions before falling back to ydotool. Screenshot results include width/height for the returned image plus coordinate_width/coordinate_height and scale for desktop coordinate conversion; request more detail with max_width, max_height, max_bytes, format=jpeg, quality, or a smaller target/crop instead of relying on unbounded screenshots. Tools with readOnlyHint=false may mutate local desktop or application state; hosts should require approval for actions that can submit, delete, send, purchase, or overwrite data. For element-targeted actions, prefer element_index from the latest get_app_state result; click, perform_action, and set_value can also use semantic role/name/text/states selectors when the target is unique. type_text and press_key accept optional window_id, pid, app_id, wm_class, title, tty, terminal_pid, terminal_command, or terminal_cwd selectors and refuse targeted input if focus cannot be verified." )] impl ServerHandler for ComputerUseLinux {}