oimwiodev/chrome-use
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

annotated screenshots (#503)

Browse Source 
* screenshot annotation

* fixes

* fix CI checks

* fixes

* fixes

* fixes

* fixes

* fixes
This commit is contained in:
Chris Tate
2026-02-18 22:20:01 -06:00
committed by GitHub
parent 06a32f4191
commit e2e259f1e2
12 changed files with 445 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cli/src/output.rs
+41 -5
View File
@@ -363,11 +363,37 @@ pub fn print_response(resp: &Response, json_mode: bool, action: Option<&str>) {
// Path-based operations (screenshot/pdf/trace/har/download/state/video)
if let Some(path) = data.get("path").and_then(|v| v.as_str()) {
match action.unwrap_or("") {
"screenshot" => println!(
"{} Screenshot saved to {}",
color::success_indicator(),
color::green(path)
),
"screenshot" => {
println!(
"{} Screenshot saved to {}",
color::success_indicator(),
color::green(path)
);
if let Some(annotations) = data.get("annotations").and_then(|v| v.as_array()) {
for ann in annotations {
let num = ann.get("number").and_then(|n| n.as_u64()).unwrap_or(0);
let ref_id = ann.get("ref").and_then(|r| r.as_str()).unwrap_or("");
let role = ann.get("role").and_then(|r| r.as_str()).unwrap_or("");
let name = ann.get("name").and_then(|n| n.as_str()).unwrap_or("");
if name.is_empty() {
println!(
" {} @{} {}",
color::dim(&format!("[{}]", num)),
ref_id,
role,
);
} else {
println!(
" {} @{} {} {:?}",
color::dim(&format!("[{}]", num)),
ref_id,
role,
name,
);
}
}
}
}
"pdf" => println!(
"{} PDF saved to {}",
color::success_indicator(),
@@ -965,6 +991,10 @@ saves to a temporary directory with a generated filename.
Options:
--full, -f Capture full page (not just viewport)
--annotate Overlay numbered labels on interactive elements.
Each label [N] corresponds to ref @eN from snapshot.
Prints a legend mapping labels to element roles/names.
With --json, annotations are included in the response.
Global Options:
--json Output as JSON
@@ -974,6 +1004,9 @@ Examples:
agent-browser screenshot
agent-browser screenshot ./screenshot.png
agent-browser screenshot --full ./full-page.png
agent-browser screenshot --annotate # Labeled screenshot + legend
agent-browser screenshot --annotate ./page.png # Save annotated screenshot
agent-browser screenshot --annotate --json # JSON output with annotations
"##
}
"pdf" => {
@@ -1932,6 +1965,7 @@ Options:
--device <name> iOS device name (e.g., "iPhone 15 Pro")
--json JSON output
--full, -f Full page screenshot
--annotate Annotated screenshot with numbered labels and legend
--headed Show browser window (not headless)
--cdp <port> Connect via CDP (Chrome DevTools Protocol)
--auto-connect Auto-discover and connect to running Chrome
@@ -1970,6 +2004,7 @@ Environment:
AGENT_BROWSER_HEADED Show browser window (not headless)
AGENT_BROWSER_JSON JSON output
AGENT_BROWSER_FULL Full page screenshot
AGENT_BROWSER_ANNOTATE Annotated screenshot with numbered labels and legend
AGENT_BROWSER_DEBUG Debug output
AGENT_BROWSER_IGNORE_HTTPS_ERRORS Ignore HTTPS certificate errors
AGENT_BROWSER_PROVIDER Browser provider (ios, browserbase, kernel, browseruse)
@@ -1994,6 +2029,7 @@ Examples:
agent-browser find role button click --name Submit
agent-browser get text @e1
agent-browser screenshot --full
agent-browser screenshot --annotate # Labeled screenshot for vision models
agent-browser wait --load networkidle # Wait for slow pages to load
agent-browser --cdp 9222 snapshot # Connect via CDP port
agent-browser --auto-connect snapshot # Auto-discover running Chrome