GAnet 0.5.0 ships macOS sidecars, so the SOP no longer stops on non-Windows
desktops. The flow itself is unchanged; the edits are the platform facts GA
needs to follow it on a Mac:
- default component location moves to ~/.genericagent/components/GAnet on
every platform; a checkout under the GA root's temp/ is wiped by the temp
rewind mechanism
- launcher is ganet.cmd on Windows and ganet.sh on macOS; the bound Python
shim is ga_python.cmd / ga_python.sh
- sidecar data lives in %LOCALAPPDATA%\GenericAgent\GAnet or
~/Library/Application Support/GenericAgent/GAnet; login autostart is the
HKCU Run entry or a LaunchAgent; both are removed by remove_environment()
- release entries for macOS use platform "darwin", and verify_release checks
Mach-O as well as PE
- on macOS, setup and upgrades request the screen-recording permission at the
end and report it in screen_access; it is advisory and never blocks
- macOS needs no sudo; git/python placeholders without Xcode CLT must not be
invoked
Allow GenericAgent to start with empty mykey, watch subscription
portal writes via list_llms, and app-rerun so sidebar LLM select
refreshes without a manual click. Also harden mykey reimport and
note the fastest tmwebdriver autofill login path.
On macOS the screenshot path lacked a counterpart to win32's
ClientToScreen. Detecting a target inside a cropped GrabScreen(bbox)
image and feeding the in-image (px,py) straight to Click silently
mis-clicks because the crop-origin offset is dropped.
- add CropToScreen(bbox, x, y): in-crop coords -> absolute physical
coords (pure crop-origin add, no scaling)
- GrabScreen docstring: warn about the crop-origin trap and not to
hand-roll screencapture -R (it takes logical points)
- Click 0%-pixel-change warning now names the common causes
- ljqCtrl_sop.md: add macOS subsection mirroring the win32 trap note
Annotate config block to guide new GA instances: enumerate candidate
mykey.py variable names and experimentally probe which config works;
only print var/field names, model, apibase host/path, status codes and
error types (never full dict or apikey/token); include a config format
example. Also flag that apibase/endpoint may differ per provider/proxy
at the two request-building sites.
- macljqCtrl.py: macOS implementation of mouse/keyboard/screenshot/window
enumeration mirroring ljqCtrl API, plus AX accessibility control tree
(AXElements/AXFind/AXPress) as the macOS equivalent of UIA
- computer_use.md: add section 3 documenting the macOS platform branch
- .gitignore: whitelist memory/macljqCtrl.py
- Anchor file becomes temp/.active_project.<host pid>: dies with the GA process,
so closing GA auto-deactivates; re-activation requires user confirmation per SOP
- Multiple GA instances each keep their own active project, no cross-talk
- Startup sweep removes only legacy unsuffixed anchors and own-pid leftovers
(pid reuse); anchors of other pids are never touched — deliberately no
liveness probe, because os.kill(pid, 0) on Windows terminates the process
Activate a project with a file anchor (temp/.active_project); every turn
the agent_before hook appends an L1 context (rules + memory file pointer
+ wrap-up discipline) to the latest user message, while the full project
memory (L2) stays on disk for the model to read on demand.
Zero core changes: plugin + SOP + gitignore whitelist only.
ljq