Remove vision tools (except take_screenshot) and macax tools

Vision tools removed:
- extract_text (OCR from image files)
- extract_text_with_boxes (OCR with bounding boxes)
- vision_find_text (find text in app windows)
- vision_click_text (find and click on text)
- vision_click_near_text (click near text labels)

macax tools removed:
- macax_list_apps
- macax_get_frontmost_app
- macax_activate_app
- macax_press_key
- macax_type_text

The LLM can now read images directly via read_image tool.
take_screenshot is retained for capturing application windows.

Files deleted:
- crates/g3-core/src/tools/vision.rs
- crates/g3-core/src/tools/macax.rs
- docs/macax-tools.md

Updated tool counts: 12 core + 15 webdriver = 27 total
This commit is contained in:
Dhanji R. Prasanna
2026-01-03 17:38:25 +11:00
parent 29e263ac49
commit 386176899e
19 changed files with 15 additions and 1408 deletions

View File

@@ -20,7 +20,6 @@ pub struct ToolContext<'a, W: UiWriter> {
pub computer_controller: Option<&'a Box<dyn g3_computer_control::ComputerController>>,
pub webdriver_session: &'a Arc<RwLock<Option<Arc<tokio::sync::Mutex<WebDriverSession>>>>>,
pub webdriver_process: &'a Arc<RwLock<Option<tokio::process::Child>>>,
pub macax_controller: &'a Arc<RwLock<Option<g3_computer_control::MacAxController>>>,
pub background_process_manager: &'a Arc<BackgroundProcessManager>,
pub todo_content: &'a Arc<RwLock<String>>,
pub pending_images: &'a mut Vec<g3_providers::ImageContent>,