15 Commits

Author SHA1 Message Date
roboomp ea887b00a9 fix(computer): corrected Wayland foreground delivery
Reported compositor-limited per-window input before reaching the AT-SPI focus path and stopped advertising foreground delivery on Wayland.

Removed the obsolete AT-SPI window-raise helper and updated public recovery guidance.

Fixes #7702
2026-08-05 10:57:25 +00:00
can1357 ebd5e3f86f chore: update stale docs 2026-08-03 16:39:23 +02:00
can1357 7c3b24ddf2 feat: implemented cross-platform window discovery and targeting capabilities
- Added window discovery, targeting, and frame validation for macOS, Windows, and Linux platforms.
- Updated computer tool and protocol definitions to support listing and targeting specific application windows.
- Refactored native computer tool exposure to function-only representation across models.
- Updated documentation and test suites to reflect window-scoped computer control capabilities.
2026-08-02 17:35:29 +02:00
can1357 d1dc436d1e Merge PR #6596: fix(coding-agent): preserve Claude computer coordinates (@wolfiesch)
# Conflicts:
#	docs/computer-use.md
#	packages/coding-agent/src/tools/computer.ts
#	packages/coding-agent/test/tools/computer.test.ts
2026-07-26 15:44:51 +02:00
Wolfgang Schoenberger 153e1b1f5c docs(computer): describe coordinate-safe capture sizing 2026-07-26 02:55:20 -07:00
Wolfgang Schoenberger fc68288477 fix(coding-agent): scope computer capture limits 2026-07-26 02:53:01 -07:00
Wolfgang Schoenberger 25dc887fb2 fix(coding-agent): preserve computer coordinates across providers 2026-07-26 02:53:00 -07:00
usr-bin-roygbiv 6b7e2ccc40 docs(computer-use): document routing diagnostics 2026-07-25 00:42:23 +00:00
usr-bin-roygbiv c12c282aa5 fix(computer): gate native Responses transport 2026-07-25 00:42:23 +00:00
can1357 11eb003fc8 fix: screenshot latency, somehow calling screencapture is faster ??? 2026-07-24 06:39:49 +02:00
usr-bin-roygbiv 68ac163e2c fix(computer): harden native desktop execution 2026-07-24 01:40:05 +00:00
can1357 681d7daf65 feat(computer): unified native addon, /computer toggle, function tool
- Replaced the separate GUI-linked pi_natives.desktop.linux-x64 addon with
  a pure-Rust X11 backend (x11rb RustConnection capture via RandR/GetImage,
  XTest input with keysym mapping) compiled into the core addon on every
  published target; Linux arm64 and musl are now supported and headless
  hosts load the addon unaffected.
- Removed the native-desktop-linux cargo feature, desktop_unsupported.rs,
  lazy desktop loader, second napi build, desktop packaging/CI steps, GUI
  build dependencies, and the now-unreferenced vendored libspa crate;
  reverted setup-system-deps to main.
- Preserved the desktop input hardening semantics on the unified backend:
  XTest layouts reject negative origins and coordinates beyond 0..=32767,
  batch coordinates stay bound to the frame last returned to JS with
  intermediate screenshots deferred, coordinate input requires a
  previously returned frame, and failed chord releases still release
  every held key.
- Enforced a 60s worker-side execute deadline (DESKTOP_DEADLINE_EXCEEDED):
  no input is emitted after expiry and wait-heavy batches are rejected
  upfront.
- Added int32 fail-closed validation for coordinates, drag points, and
  scroll deltas at the JS ingress and gateway schema.
- Exposed computer to models without native OpenAI computer-use support as
  a regular function tool with a typed GA action schema across OpenAI,
  Azure, and Codex Responses providers, including named forced choice.
- Added the /computer slash command (on/off/status/toggle) for
  session-only enablement via runtime tool registration in SessionTools.
- Updated docs, changelogs, and contract tests accordingly.
2026-07-24 01:40:05 +00:00
usr-bin-roygbiv 57f8acdd18 fix(native): harden desktop input and compatibility 2026-07-24 01:40:05 +00:00
usr-bin-roygbiv 87f37bcb1f fix(native): support Ubuntu 22 desktop builds 2026-07-24 01:40:05 +00:00
usr-bin-roygbiv b9504f65e7 feat: add native Codex computer use 2026-07-24 01:40:04 +00:00