Files
chrome-use/cli/src/native/interaction.rs
T
leeguooooo 9bd6587278 feat(stealth): in-bbox landing jitter + eased wheel/drag (humanize v4)
Completes the humanize suite:
- Clicks land on a jittered point inside the element's box (Fast/Human) instead
  of its exact centre. `resolve_element_center` now also returns the element
  width/height (box_model_dims); the CSS-selector path reports zero size → land
  on centre (no jitter, no regression). Jitter is clamped to the inner box so the
  click never misses.
- Wheel scrolls split into eased, jittered segments (humanize::scroll_segments,
  unit-tested) instead of one instant jump.
- Drag follows the curved trajectory at Fast/Human (linear 10-step at Off).

Off is unchanged throughout. 9/9 unit tests; verified headless — jittered click
still lands (→ iana.org), segmented scroll moves the page.
2026-06-11 19:52:33 +09:00

1402 lines
44 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
use std::collections::HashMap;
use serde_json::Value;
use super::cdp::client::CdpClient;
use super::cdp::types::*;
use super::element::{resolve_element_center, resolve_element_object_id, RefMap};
use super::humanize;
pub async fn click(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
button: &str,
click_count: i32,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
// AGENT_BROWSER_CLICK_MODE: "" (default) = coordinate click with a DOM
// fallback; "coord" = strict coordinate only (no fallback); "dom" = always
// dispatch through the DOM.
let mode = std::env::var("AGENT_BROWSER_CLICK_MODE").unwrap_or_default();
// (A) Scroll the target into view first so the computed coordinates land
// inside the viewport. Without this, an element below the fold (or revealed
// after scroll/popup) yields off-viewport coordinates and the click lands on
// whatever currently occupies that point. Best-effort: ignore failures.
scroll_into_view_if_needed(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await;
if mode == "dom" {
return dom_click(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await;
}
let resolved = resolve_element_center(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await;
match resolved {
Ok((cx, cy, w, h, effective_session_id)) => {
// Land on a jittered point inside the element rather than its exact
// centre (Fast/Human). Zero size or Off → exact centre.
let (tx, ty) = humanize::landing_point(
(cx - w / 2.0, cy - h / 2.0, w, h),
humanize::active_level(),
humanize::next_seed(),
);
dispatch_click(client, &effective_session_id, tx, ty, button, click_count).await
}
Err(e) => {
// (B) The coordinate path failed — typically a persistent overlay
// failing the occlusion guard, or coordinates that won't resolve.
// Fall back to a DOM-dispatched `.click()` on the intended element,
// which targets the element directly instead of a screen point.
// Skipped for strict "coord" mode and for non-left / multi-clicks
// (a DOM `.click()` can't express right/middle/double semantics).
if mode == "coord" || button != "left" || click_count != 1 {
return Err(e);
}
eprintln!(
"[click] coordinate click failed ({e}); falling back to DOM dispatch \
(set AGENT_BROWSER_CLICK_MODE=coord to disable)"
);
dom_click(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await
.map_err(|dom_err| format!("{e}\n(DOM-dispatch fallback also failed: {dom_err})"))
}
}
}
/// Best-effort scroll-into-view before a coordinate click. Uses Chrome's
/// `scrollIntoViewIfNeeded` (only scrolls when not already fully visible),
/// falling back to centered `scrollIntoView`. Resolution failures are ignored —
/// the subsequent resolve will surface a real "not found" error.
async fn scroll_into_view_if_needed(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) {
let Ok((object_id, effective_session_id)) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await
else {
return;
};
let js = "function() { try { \
if (typeof this.scrollIntoViewIfNeeded === 'function') { this.scrollIntoViewIfNeeded(true); } \
else { this.scrollIntoView({ block: 'center', inline: 'center' }); } \
} catch (e) {} }";
let _ = client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: js.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await;
// Let the scroll settle so the following getBoxModel sees final coordinates.
wait_for_paint_settled(client, &effective_session_id).await;
}
/// Dispatch a click through the DOM (`element.click()`) instead of via screen
/// coordinates. Targets the intended element directly, so it works when a
/// floating layer occludes the click point or the element sits in a portal that
/// confuses `elementFromPoint`. Used as the fallback for `click` and when
/// `AGENT_BROWSER_CLICK_MODE=dom`.
async fn dom_click(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: "function() { this.click(); }".to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
wait_for_paint_settled(client, &effective_session_id).await;
Ok(())
}
pub async fn dblclick(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
click(
client,
session_id,
ref_map,
selector_or_ref,
"left",
2,
iframe_sessions,
)
.await
}
pub async fn hover(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (x, y, _w, _h, effective_session_id) = resolve_element_center(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Input.dispatchMouseEvent",
&DispatchMouseEventParams {
event_type: "mouseMoved".to_string(),
x,
y,
button: None,
buttons: None,
click_count: None,
delta_x: None,
delta_y: None,
modifiers: None,
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn fill(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
value: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
// Focus the element
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: "function() { this.focus(); }".to_string(),
object_id: Some(object_id.clone()),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
// Select all + delete to clear
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: r#"function() {
this.select && this.select();
this.value = '';
this.dispatchEvent(new Event('input', { bubbles: true }));
}"#
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
// Insert text (keyboard input dispatched at page level, use parent session_id)
client
.send_command_typed::<_, Value>(
"Input.insertText",
&InsertTextParams {
text: value.to_string(),
},
Some(session_id),
)
.await?;
Ok(())
}
#[allow(clippy::too_many_arguments)]
pub async fn type_text(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
text: &str,
clear: bool,
delay_ms: Option<u64>,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
// Focus
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: "function() { this.focus(); }".to_string(),
object_id: Some(object_id.clone()),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
if clear {
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: r#"function() {
this.select && this.select();
this.value = '';
this.dispatchEvent(new Event('input', { bubbles: true }));
}"#
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
}
type_text_into_active_context(client, session_id, text, delay_ms).await
}
pub async fn type_text_into_active_context(
client: &CdpClient,
session_id: &str,
text: &str,
delay_ms: Option<u64>,
) -> Result<(), String> {
// Per-character timing: an explicit `delay_ms` wins (caller asked for a
// fixed cadence); otherwise fall back to humanize — variable, human-like
// inter-keystroke gaps at Fast/Human, all-zero (instant) at Off.
let chars: Vec<char> = text.chars().collect();
let cadence: Vec<std::time::Duration> = match delay_ms {
Some(d) => vec![std::time::Duration::from_millis(d); chars.len()],
None => {
humanize::keystroke_delays(chars.len(), humanize::active_level(), humanize::next_seed())
}
};
for (i, ch) in chars.into_iter().enumerate() {
if matches!(ch, '\n' | '\r' | '\t') {
let (key, code, key_code) = char_to_key_info(ch);
let text_str = key_text(&key);
client
.send_command_typed::<_, Value>(
"Input.dispatchKeyEvent",
&DispatchKeyEventParams {
event_type: "keyDown".to_string(),
key: Some(key.clone()),
code: Some(code.clone()),
text: text_str.clone(),
unmodified_text: text_str,
windows_virtual_key_code: Some(key_code),
native_virtual_key_code: Some(key_code),
modifiers: None,
},
Some(session_id),
)
.await?;
client
.send_command_typed::<_, Value>(
"Input.dispatchKeyEvent",
&DispatchKeyEventParams {
event_type: "keyUp".to_string(),
key: Some(key),
code: Some(code),
text: None,
unmodified_text: None,
windows_virtual_key_code: Some(key_code),
native_virtual_key_code: Some(key_code),
modifiers: None,
},
Some(session_id),
)
.await?;
} else {
// VS Code/Electron webviews reject repeated dispatchKeyEvent calls
// carrying printable `text`. Insert printable characters directly
// and reserve key events for controls like Enter and Tab.
client
.send_command_typed::<_, Value>(
"Input.insertText",
&InsertTextParams {
text: ch.to_string(),
},
Some(session_id),
)
.await?;
}
let gap = cadence[i];
if !gap.is_zero() {
tokio::time::sleep(gap).await;
}
}
Ok(())
}
pub async fn press_key(client: &CdpClient, session_id: &str, key: &str) -> Result<(), String> {
press_key_with_modifiers(client, session_id, key, None).await
}
/// Dispatch a keyDown+keyUp sequence for `key` with an optional CDP modifier bitmask.
///
/// Modifier values follow the CDP `Input.dispatchKeyEvent` spec:
/// 1 = Alt, 2 = Control, 4 = Meta (Cmd), 8 = Shift.
///
/// Callers that need a platform-appropriate modifier (e.g. Cmd on macOS,
/// Ctrl elsewhere) must choose the value themselves -- see `cfg!(target_os)`.
pub async fn press_key_with_modifiers(
client: &CdpClient,
session_id: &str,
key: &str,
modifiers: Option<i32>,
) -> Result<(), String> {
let (key_name, code, key_code) = named_key_info(key);
// Suppress text insertion when Control (2) or Meta (4) modifiers are active,
// since these are command chords (e.g. Ctrl+A = select-all), not text input.
let has_command_modifier = modifiers.is_some_and(|m| m & (2 | 4) != 0);
let text = if has_command_modifier {
None
} else {
key_text(&key_name)
};
client
.send_command_typed::<_, Value>(
"Input.dispatchKeyEvent",
&DispatchKeyEventParams {
event_type: "keyDown".to_string(),
key: Some(key_name.clone()),
code: Some(code.clone()),
text: text.clone(),
unmodified_text: text.clone(),
windows_virtual_key_code: Some(key_code),
native_virtual_key_code: Some(key_code),
modifiers,
},
Some(session_id),
)
.await?;
client
.send_command_typed::<_, Value>(
"Input.dispatchKeyEvent",
&DispatchKeyEventParams {
event_type: "keyUp".to_string(),
key: Some(key_name),
code: Some(code),
text: None,
unmodified_text: None,
windows_virtual_key_code: Some(key_code),
native_virtual_key_code: Some(key_code),
modifiers,
},
Some(session_id),
)
.await?;
Ok(())
}
pub async fn scroll(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: Option<&str>,
delta_x: f64,
delta_y: f64,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
if let Some(sel) = selector_or_ref {
let (object_id, effective_session_id) =
resolve_element_object_id(client, session_id, ref_map, sel, iframe_sessions).await?;
let js = "function(dx, dy) { this.scrollBy(dx, dy); }".to_string();
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: js,
object_id: Some(object_id),
arguments: Some(vec![
CallArgument {
value: Some(serde_json::json!(delta_x)),
object_id: None,
},
CallArgument {
value: Some(serde_json::json!(delta_y)),
object_id: None,
},
]),
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
} else {
let js = format!("window.scrollBy({}, {})", delta_x, delta_y);
client
.send_command_typed::<_, Value>(
"Runtime.evaluate",
&EvaluateParams {
expression: js,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(session_id),
)
.await?;
}
Ok(())
}
pub async fn select_option(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
values: &[String],
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
let js = r#"function(vals) {
const options = Array.from(this.options);
for (const opt of options) {
opt.selected = vals.includes(opt.value) || vals.includes(opt.textContent.trim());
}
this.dispatchEvent(new Event('change', { bubbles: true }));
}"#
.to_string();
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: js,
object_id: Some(object_id),
arguments: Some(vec![CallArgument {
value: Some(serde_json::json!(values)),
object_id: None,
}]),
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn check(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let is_checked = super::element::is_element_checked(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
if !is_checked {
click(
client,
session_id,
ref_map,
selector_or_ref,
"left",
1,
iframe_sessions,
)
.await?;
// Verify the click changed the state (Playwright parity: _setChecked re-checks).
// If the coordinate-based click missed (e.g. hidden input, overlay), retry
// with a JS .click() on the element and its associated input.
if !super::element::is_element_checked(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?
{
js_click_checkbox(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
}
}
Ok(())
}
pub async fn uncheck(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let is_checked = super::element::is_element_checked(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
if is_checked {
click(
client,
session_id,
ref_map,
selector_or_ref,
"left",
1,
iframe_sessions,
)
.await?;
// Same verify-and-retry as check().
if super::element::is_element_checked(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?
{
js_click_checkbox(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
}
}
Ok(())
}
/// Fallback for when the coordinate-based CDP click did not toggle the
/// checkbox/radio state. This mirrors how Playwright dispatches clicks
/// through the DOM rather than via raw Input.dispatchMouseEvent coordinates.
///
/// Uses the same follow-label resolution as `is_element_checked`:
/// 1. If the element is a native input → `.click()` it directly.
/// 2. If the element is inside a `<label>` → `.click()` the label's `.control`.
/// 3. If the element has a nested `<input>` → `.click()` that input.
/// 4. Otherwise → `.click()` the element itself (handles ARIA role controls).
async fn js_click_checkbox(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
let js = r#"function() {
var el = this;
var tag = el.tagName && el.tagName.toUpperCase();
// 1. Native input — click it directly
if (tag === 'INPUT' && (el.type === 'checkbox' || el.type === 'radio')) {
el.click();
return;
}
// 2. Follow label → control association
var label = tag === 'LABEL' ? el : (el.closest && el.closest('label'));
if (label && label.tagName && label.tagName.toUpperCase() === 'LABEL' && label.control) {
label.control.click();
return;
}
// 3. Nested native input
var input = el.querySelector && el.querySelector('input[type="checkbox"], input[type="radio"]');
if (input) {
input.click();
return;
}
// 4. ARIA role control — click the element itself
el.click();
}"#;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: js.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn focus(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: "function() { this.focus(); }".to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn clear(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: r#"function() {
this.focus();
this.value = '';
this.dispatchEvent(new Event('input', { bubbles: true }));
this.dispatchEvent(new Event('change', { bubbles: true }));
}"#
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn select_all(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: r#"function() {
this.focus();
if (typeof this.select === 'function') {
this.select();
} else {
const range = document.createRange();
range.selectNodeContents(this);
const sel = window.getSelection();
sel.removeAllRanges();
sel.addRange(range);
}
}"#
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn scroll_into_view(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration:
"function() { this.scrollIntoView({ block: 'center', inline: 'center' }); }"
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn dispatch_event(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
event_type: &str,
event_init: Option<&Value>,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
let init_json = event_init
.map(|v| serde_json::to_string(v).unwrap_or("{}".to_string()))
.unwrap_or_else(|| "{ bubbles: true }".to_string());
let js = format!(
"function() {{ this.dispatchEvent(new Event({}, {})); }}",
serde_json::to_string(event_type).unwrap_or_default(),
init_json
);
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: js,
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn highlight(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (object_id, effective_session_id) = resolve_element_object_id(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command_typed::<_, Value>(
"Runtime.callFunctionOn",
&CallFunctionOnParams {
function_declaration: r#"function() {
this.style.outline = '2px solid red';
this.style.outlineOffset = '2px';
const el = this;
setTimeout(() => {
el.style.outline = '';
el.style.outlineOffset = '';
}, 3000);
}"#
.to_string(),
object_id: Some(object_id),
arguments: None,
return_by_value: Some(true),
await_promise: Some(false),
},
Some(&effective_session_id),
)
.await?;
Ok(())
}
pub async fn tap_touch(
client: &CdpClient,
session_id: &str,
ref_map: &RefMap,
selector_or_ref: &str,
iframe_sessions: &HashMap<String, String>,
) -> Result<(), String> {
let (x, y, _w, _h, effective_session_id) = resolve_element_center(
client,
session_id,
ref_map,
selector_or_ref,
iframe_sessions,
)
.await?;
client
.send_command(
"Input.dispatchTouchEvent",
Some(serde_json::json!({
"type": "touchStart",
"touchPoints": [{ "x": x, "y": y }],
})),
Some(&effective_session_id),
)
.await?;
client
.send_command(
"Input.dispatchTouchEvent",
Some(serde_json::json!({
"type": "touchEnd",
"touchPoints": [],
})),
Some(&effective_session_id),
)
.await?;
Ok(())
}
/// After a click is dispatched, give the page two animation frames + a
/// microtask boundary to let React/Vue/Svelte commit any state update
/// scheduled by the click handler. Without this wait, follow-up commands
/// (e.g. `inserttext` against the textbox the click was supposed to mount)
/// race the renderer and can land on stale or wrong elements.
///
/// The wait is bounded to ~33ms in the common case (two RAFs at 60fps) and
/// returns immediately on any error — never an exception path.
///
/// Set `AGENT_BROWSER_CLICK_WAIT_STABLE=0` to disable for perf-sensitive
/// scripts that don't drive SPA UIs.
async fn wait_for_paint_settled(client: &CdpClient, session_id: &str) {
if std::env::var("AGENT_BROWSER_CLICK_WAIT_STABLE").as_deref() == Ok("0") {
return;
}
let script = "new Promise(resolve => \
requestAnimationFrame(() => \
requestAnimationFrame(() => \
queueMicrotask(() => resolve(true)))))";
// Tight 500ms timeout. RAF normally fires at 16ms, two RAFs total ~33ms.
// If the tab is hidden / throttled / page is doing something pathological
// and RAF doesn't fire in 500ms, we'd rather return now than stall the
// user's click. Without this cap, a stuck RAF inherited the default 30s
// CDP timeout and was the main contributor to the "click hangs 5+ min"
// user report.
let _ = tokio::time::timeout(
std::time::Duration::from_millis(500),
client.send_command_typed::<_, Value>(
"Runtime.evaluate",
&EvaluateParams {
expression: script.to_string(),
return_by_value: Some(true),
await_promise: Some(true),
},
Some(session_id),
),
)
.await;
}
async fn dispatch_click(
client: &CdpClient,
session_id: &str,
x: f64,
y: f64,
button: &str,
click_count: i32,
) -> Result<(), String> {
// Move toward the target along a human-like path. At HumanizeLevel::Off this
// is a single zero-delay step to (x, y) — identical to the old teleport — so
// the default behaviour is unchanged. At Fast/Human it's a curved,
// decelerating trajectory starting from where the cursor last landed, which
// removes the "instant jump to exact centre, no prior movement" tell that
// behavioural anti-bot systems flag.
let level = humanize::active_level();
let start = humanize::last_cursor();
let seed = humanize::next_seed();
for step in humanize::move_path(start, (x, y), level, seed) {
client
.send_command_typed::<_, Value>(
"Input.dispatchMouseEvent",
&DispatchMouseEventParams {
event_type: "mouseMoved".to_string(),
x: step.x,
y: step.y,
button: None,
buttons: None,
click_count: None,
delta_x: None,
delta_y: None,
modifiers: None,
},
Some(session_id),
)
.await?;
if !step.delay.is_zero() {
tokio::time::sleep(step.delay).await;
}
}
humanize::set_last_cursor((x, y));
let button_value = match button {
"right" => 2,
"middle" => 4,
_ => 1,
};
// Press
client
.send_command_typed::<_, Value>(
"Input.dispatchMouseEvent",
&DispatchMouseEventParams {
event_type: "mousePressed".to_string(),
x,
y,
button: Some(button.to_string()),
buttons: Some(button_value),
click_count: Some(click_count),
delta_x: None,
delta_y: None,
modifiers: None,
},
Some(session_id),
)
.await?;
// Hold briefly before releasing — a real click isn't instantaneous. Zero at
// HumanizeLevel::Off.
let dwell = humanize::press_dwell(level, seed);
if !dwell.is_zero() {
tokio::time::sleep(dwell).await;
}
// Release
client
.send_command_typed::<_, Value>(
"Input.dispatchMouseEvent",
&DispatchMouseEventParams {
event_type: "mouseReleased".to_string(),
x,
y,
button: Some(button.to_string()),
buttons: Some(0),
click_count: Some(click_count),
delta_x: None,
delta_y: None,
modifiers: None,
},
Some(session_id),
)
.await?;
wait_for_paint_settled(client, session_id).await;
Ok(())
}
fn char_to_key_info(ch: char) -> (String, String, i32) {
match ch {
'\n' | '\r' => ("Enter".to_string(), "Enter".to_string(), 13),
'\t' => ("Tab".to_string(), "Tab".to_string(), 9),
' ' => (" ".to_string(), "Space".to_string(), 32),
_ => {
let key = ch.to_string();
if ch.is_ascii_alphabetic() {
// For letters the Windows VK code equals the uppercase ASCII value.
let upper = ch.to_ascii_uppercase();
let code = format!("Key{}", upper);
let key_code = upper as i32;
(key, code, key_code)
} else if ch.is_ascii_digit() {
let code = format!("Digit{}", ch);
let key_code = ch as i32;
(key, code, key_code)
} else {
let (code, key_code) = punctuation_key_info(ch);
(key, code.to_string(), key_code)
}
}
}
}
/// Return the DOM `KeyboardEvent.code` value and Windows virtual-key code for
/// a punctuation / symbol character assuming a US keyboard layout.
///
/// The Windows virtual-key codes (VK_OEM_*) differ from ASCII values for
/// punctuation. Using the raw ASCII code would misidentify characters e.g.
/// '.' (ASCII 46) collides with VK_DELETE (0x2E = 46), causing the period to
/// be swallowed.
fn punctuation_key_info(ch: char) -> (&'static str, i32) {
match ch {
// VK_OEM_1 (0xBA = 186) — ";:" key on US layout
';' | ':' => ("Semicolon", 186),
// VK_OEM_PLUS (0xBB = 187) — "=+" key
'=' | '+' => ("Equal", 187),
// VK_OEM_COMMA (0xBC = 188) — ",<" key
',' | '<' => ("Comma", 188),
// VK_OEM_MINUS (0xBD = 189) — "-_" key
'-' | '_' => ("Minus", 189),
// VK_OEM_PERIOD (0xBE = 190) — ".>" key
'.' | '>' => ("Period", 190),
// VK_OEM_2 (0xBF = 191) — "/?" key
'/' | '?' => ("Slash", 191),
// VK_OEM_3 (0xC0 = 192) — "`~" key
'`' | '~' => ("Backquote", 192),
// VK_OEM_4 (0xDB = 219) — "[{" key
'[' | '{' => ("BracketLeft", 219),
// VK_OEM_5 (0xDC = 220) — "\\|" key
'\\' | '|' => ("Backslash", 220),
// VK_OEM_6 (0xDD = 221) — "]}" key
']' | '}' => ("BracketRight", 221),
// VK_OEM_7 (0xDE = 222) — "'\""" key
'\'' | '"' => ("Quote", 222),
_ => ("", 0),
}
}
/// Return the `text` value that CDP `Input.dispatchKeyEvent` needs on the
/// `keyDown` event so that Chrome performs the default action for the key.
/// For example Enter needs `"\r"` to actually submit a form, and Tab needs
/// `"\t"` to move focus. Non-printable / navigation keys return `None`.
fn key_text(key_name: &str) -> Option<String> {
match key_name {
"Enter" => Some("\r".to_string()),
"Tab" => Some("\t".to_string()),
" " => Some(" ".to_string()),
_ => {
// Single printable characters carry themselves as text.
if key_name.len() == 1 {
Some(key_name.to_string())
} else {
None
}
}
}
}
fn named_key_info(key: &str) -> (String, String, i32) {
match key.to_lowercase().as_str() {
"enter" | "return" => ("Enter".to_string(), "Enter".to_string(), 13),
"tab" => ("Tab".to_string(), "Tab".to_string(), 9),
"escape" | "esc" => ("Escape".to_string(), "Escape".to_string(), 27),
"backspace" => ("Backspace".to_string(), "Backspace".to_string(), 8),
"delete" => ("Delete".to_string(), "Delete".to_string(), 46),
"arrowup" | "up" => ("ArrowUp".to_string(), "ArrowUp".to_string(), 38),
"arrowdown" | "down" => ("ArrowDown".to_string(), "ArrowDown".to_string(), 40),
"arrowleft" | "left" => ("ArrowLeft".to_string(), "ArrowLeft".to_string(), 37),
"arrowright" | "right" => ("ArrowRight".to_string(), "ArrowRight".to_string(), 39),
"home" => ("Home".to_string(), "Home".to_string(), 36),
"end" => ("End".to_string(), "End".to_string(), 35),
"pageup" => ("PageUp".to_string(), "PageUp".to_string(), 33),
"pagedown" => ("PageDown".to_string(), "PageDown".to_string(), 34),
"space" | " " => (" ".to_string(), "Space".to_string(), 32),
_ => {
if key.len() == 1 {
let ch = key.chars().next().unwrap();
char_to_key_info(ch)
} else {
(key.to_string(), key.to_string(), 0)
}
}
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Verify that `char_to_key_info` returns the correct (key, code,
/// windowsVirtualKeyCode) triple for every character in Playwright's
/// USKeyboardLayout. The expected values below are taken verbatim from
/// playwright-core/lib/server/usKeyboardLayout.js so that any drift from
/// Playwright's behaviour is caught immediately.
#[test]
fn test_char_to_key_info_matches_playwright_layout() {
// (character, expected_code, expected_vk_code)
let cases: &[(char, &str, i32)] = &[
// Letters VK code must equal the uppercase ASCII value.
('a', "KeyA", 65),
('z', "KeyZ", 90),
('A', "KeyA", 65),
// Digits
('0', "Digit0", 48),
('9', "Digit9", 57),
// Punctuation these are the values from Playwright's layout.
// The bug that prompted this test sent '.' as VK 46 (= VK_DELETE).
('.', "Period", 190),
(',', "Comma", 188),
('/', "Slash", 191),
(';', "Semicolon", 186),
('\'', "Quote", 222),
('[', "BracketLeft", 219),
(']', "BracketRight", 221),
('\\', "Backslash", 220),
('`', "Backquote", 192),
('-', "Minus", 189),
('=', "Equal", 187),
// Shifted variants produced by the same physical keys.
('>', "Period", 190),
('<', "Comma", 188),
('?', "Slash", 191),
(':', "Semicolon", 186),
('"', "Quote", 222),
('{', "BracketLeft", 219),
('}', "BracketRight", 221),
('|', "Backslash", 220),
('~', "Backquote", 192),
('_', "Minus", 189),
('+', "Equal", 187),
// Whitespace / control
(' ', "Space", 32),
('\n', "Enter", 13),
('\t', "Tab", 9),
];
for &(ch, expected_code, expected_vk) in cases {
let (key, code, vk) = char_to_key_info(ch);
assert_eq!(
code, expected_code,
"char {:?}: expected code {:?}, got {:?}",
ch, expected_code, code
);
assert_eq!(
vk, expected_vk,
"char {:?}: expected VK {}, got {} (ASCII would be {})",
ch, expected_vk, vk, ch as i32
);
// key should be the character itself (except control chars).
if !ch.is_control() {
assert_eq!(key, ch.to_string(), "char {:?}: key mismatch", ch);
}
}
}
/// Regression test: period must NEVER map to VK 46 (VK_DELETE).
#[test]
fn test_period_is_not_vk_delete() {
let (_, _, vk) = char_to_key_info('.');
assert_ne!(
vk, 46,
"Period must not use VK code 46 (VK_DELETE); expected 190 (VK_OEM_PERIOD)"
);
assert_eq!(vk, 190);
}
/// Characters outside the US keyboard layout should return (key, "", 0)
/// so that `type_text` falls back to `Input.insertText`.
#[test]
fn test_unmapped_chars_return_zero_keycode() {
for ch in ['@', '#', '$', '%', '^', '&', '*', '(', ')', '€', '£', '你'] {
let (key, code, vk) = char_to_key_info(ch);
assert_eq!(
code, "",
"char {:?}: unmapped char should have empty code, got {:?}",
ch, code
);
assert_eq!(
vk, 0,
"char {:?}: unmapped char should have VK 0, got {}",
ch, vk
);
assert_eq!(key, ch.to_string());
}
}
#[test]
fn test_key_text_returns_correct_text_for_special_keys() {
assert_eq!(key_text("Enter"), Some("\r".to_string()));
assert_eq!(key_text("Tab"), Some("\t".to_string()));
assert_eq!(key_text(" "), Some(" ".to_string()));
// Single printable characters carry themselves.
assert_eq!(key_text("a"), Some("a".to_string()));
assert_eq!(key_text("Z"), Some("Z".to_string()));
// Non-printable named keys return None.
assert_eq!(key_text("Escape"), None);
assert_eq!(key_text("ArrowUp"), None);
assert_eq!(key_text("Backspace"), None);
assert_eq!(key_text("Delete"), None);
}
}