Compare commits
6
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1c2e594003 | ||
|
|
9bd6587278 | ||
|
|
df53b1a70e | ||
|
|
a6f0193779 | ||
|
|
bab58991fe | ||
|
|
c5d4c8908d |
Generated
+1
-1
@@ -45,7 +45,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "agent-browser-stealth"
|
||||
version = "0.27.0-fork.35"
|
||||
version = "0.27.0-fork.37"
|
||||
dependencies = [
|
||||
"aes-gcm",
|
||||
"async-trait",
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "agent-browser-stealth"
|
||||
version = "0.27.0-fork.35"
|
||||
version = "0.27.0-fork.37"
|
||||
edition = "2021"
|
||||
description = "Fast browser automation CLI for AI agents"
|
||||
license = "Apache-2.0"
|
||||
|
||||
@@ -248,6 +248,7 @@ fn extract_config_path(args: &[String]) -> Option<Option<String>> {
|
||||
"--screenshot-format",
|
||||
"--idle-timeout",
|
||||
"--model",
|
||||
"--humanize",
|
||||
];
|
||||
let mut i = 0;
|
||||
while i < args.len() {
|
||||
@@ -796,6 +797,21 @@ pub fn parse_flags(args: &[String]) -> Flags {
|
||||
i += 1;
|
||||
}
|
||||
}
|
||||
"--humanize" => {
|
||||
// Human-like input motion level (off|fast|human). Surface it as
|
||||
// AGENT_BROWSER_HUMANIZE so the daemon — spawned as a child that
|
||||
// inherits this process's env — picks it up and it overrides the
|
||||
// adaptive detector. Applies when the session's daemon launches.
|
||||
if let Some(s) = args.get(i + 1) {
|
||||
match crate::native::humanize::HumanizeLevel::parse(s) {
|
||||
Some(_) => std::env::set_var("AGENT_BROWSER_HUMANIZE", s),
|
||||
None => eprintln!(
|
||||
"warning: --humanize must be off|fast|human, got {s:?} (ignored)"
|
||||
),
|
||||
}
|
||||
i += 1;
|
||||
}
|
||||
}
|
||||
"--screenshot-dir" => {
|
||||
if let Some(s) = args.get(i + 1) {
|
||||
flags.screenshot_dir = Some(s.clone());
|
||||
@@ -922,6 +938,7 @@ pub fn clean_args(args: &[String]) -> Vec<String> {
|
||||
"--screenshot-format",
|
||||
"--idle-timeout",
|
||||
"--model",
|
||||
"--humanize",
|
||||
];
|
||||
|
||||
let mut i = 0;
|
||||
|
||||
+92
-23
@@ -23,6 +23,7 @@ use super::cdp::types::{
|
||||
use super::cookies;
|
||||
use super::diff;
|
||||
use super::element::RefMap;
|
||||
use super::humanize;
|
||||
use super::inspect_server::InspectServer;
|
||||
use super::interaction;
|
||||
use super::network::{self, DomainFilter, EventTracker};
|
||||
@@ -2512,7 +2513,49 @@ async fn handle_navigate(cmd: &Value, state: &mut DaemonState) -> Result<Value,
|
||||
state.ref_map.clear();
|
||||
state.iframe_sessions.clear();
|
||||
state.active_frame_id = None;
|
||||
mgr.navigate(url, wait_until).await
|
||||
let result = mgr.navigate(url, wait_until).await?;
|
||||
// Adaptive humanize: sample the freshly loaded page for known behavioural
|
||||
// anti-bot vendors and escalate this session to Human if any are present.
|
||||
detect_and_set_humanize(mgr).await;
|
||||
Ok(result)
|
||||
}
|
||||
|
||||
/// After navigation, probe the page for known anti-bot vendor fingerprints
|
||||
/// (cookies / script URLs / `window` globals) and set this session's humanize
|
||||
/// level accordingly — `Human` when a vendor is detected, else the `Off`
|
||||
/// baseline. Best-effort: any failure leaves the level unchanged. Skipped when
|
||||
/// `AGENT_BROWSER_HUMANIZE` is set, since the override always wins and the probe
|
||||
/// would be wasted work.
|
||||
async fn detect_and_set_humanize(mgr: &BrowserManager) {
|
||||
if std::env::var("AGENT_BROWSER_HUMANIZE").is_ok() {
|
||||
return;
|
||||
}
|
||||
let js = r#"(() => { try {
|
||||
const cookies = document.cookie.split(';').map(c => c.trim().split('=')[0]).filter(Boolean);
|
||||
const scripts = Array.from(document.scripts, s => s.src || '').filter(Boolean);
|
||||
const re = /_px|bmak|_abck|datadome|reese84|kpsdk|incap_ses|visid_incap|akam/i;
|
||||
const globals = Object.getOwnPropertyNames(window).filter(k => re.test(k));
|
||||
return { cookies, scripts, globals };
|
||||
} catch (e) { return {}; } })()"#;
|
||||
let Ok(val) = mgr.evaluate(js, None).await else {
|
||||
return;
|
||||
};
|
||||
let to_strings = |v: Option<&Value>| -> Vec<String> {
|
||||
v.and_then(|v| v.as_array())
|
||||
.map(|a| {
|
||||
a.iter()
|
||||
.filter_map(|x| x.as_str().map(String::from))
|
||||
.collect()
|
||||
})
|
||||
.unwrap_or_default()
|
||||
};
|
||||
let signals = humanize::DetectSignals {
|
||||
cookie_names: to_strings(val.get("cookies")),
|
||||
script_urls: to_strings(val.get("scripts")),
|
||||
window_globals: to_strings(val.get("globals")),
|
||||
};
|
||||
let level = humanize::detect_level(&signals, humanize::HumanizeLevel::Off);
|
||||
humanize::set_detected_level(level);
|
||||
}
|
||||
|
||||
async fn handle_url(state: &DaemonState) -> Result<Value, String> {
|
||||
@@ -5470,19 +5513,29 @@ async fn handle_wheel(cmd: &Value, state: &DaemonState) -> Result<Value, String>
|
||||
let delta_x = cmd.get("deltaX").and_then(|v| v.as_f64()).unwrap_or(0.0);
|
||||
let delta_y = cmd.get("deltaY").and_then(|v| v.as_f64()).unwrap_or(0.0);
|
||||
|
||||
mgr.client
|
||||
.send_command(
|
||||
"Input.dispatchMouseEvent",
|
||||
Some(json!({
|
||||
"type": "mouseWheel",
|
||||
"x": x,
|
||||
"y": y,
|
||||
"deltaX": delta_x,
|
||||
"deltaY": delta_y,
|
||||
})),
|
||||
Some(&session_id),
|
||||
)
|
||||
.await?;
|
||||
// Humanize: at Off this is one instant wheel event (unchanged); at
|
||||
// Fast/Human the scroll is split into eased, slightly-jittered segments so
|
||||
// it ramps and settles like a real wheel/trackpad flick.
|
||||
let level = humanize::active_level();
|
||||
let seed = humanize::next_seed();
|
||||
for (dx, dy, delay) in humanize::scroll_segments(delta_x, delta_y, level, seed) {
|
||||
mgr.client
|
||||
.send_command(
|
||||
"Input.dispatchMouseEvent",
|
||||
Some(json!({
|
||||
"type": "mouseWheel",
|
||||
"x": x,
|
||||
"y": y,
|
||||
"deltaX": dx,
|
||||
"deltaY": dy,
|
||||
})),
|
||||
Some(&session_id),
|
||||
)
|
||||
.await?;
|
||||
if !delay.is_zero() {
|
||||
tokio::time::sleep(delay).await;
|
||||
}
|
||||
}
|
||||
|
||||
Ok(json!({ "scrolled": true, "deltaX": delta_x, "deltaY": delta_y }))
|
||||
}
|
||||
@@ -6479,7 +6532,7 @@ async fn handle_drag(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
|
||||
.and_then(|v| v.as_str())
|
||||
.ok_or("Missing 'target' parameter")?;
|
||||
|
||||
let (sx, sy, source_session_id) = super::element::resolve_element_center(
|
||||
let (sx, sy, _, _, source_session_id) = super::element::resolve_element_center(
|
||||
&mgr.client,
|
||||
&session_id,
|
||||
&state.ref_map,
|
||||
@@ -6487,7 +6540,7 @@ async fn handle_drag(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
|
||||
&state.iframe_sessions,
|
||||
)
|
||||
.await?;
|
||||
let (tx, ty, target_session_id) = super::element::resolve_element_center(
|
||||
let (tx, ty, _, _, target_session_id) = super::element::resolve_element_center(
|
||||
&mgr.client,
|
||||
&session_id,
|
||||
&state.ref_map,
|
||||
@@ -6512,12 +6565,26 @@ async fn handle_drag(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
|
||||
)
|
||||
.await?;
|
||||
|
||||
// Move in steps to target, keeping the left button held (buttons: 1) so
|
||||
// that the browser sees a drag rather than a plain pointer move.
|
||||
let steps = 10;
|
||||
for i in 1..=steps {
|
||||
let cx = sx + (tx - sx) * (i as f64) / (steps as f64);
|
||||
let cy = sy + (ty - sy) * (i as f64) / (steps as f64);
|
||||
// Move to the target with the left button held (buttons: 1) so the browser
|
||||
// sees a drag. At Off this is the original linear 10-step path; at
|
||||
// Fast/Human it follows humanize's curved, decelerating trajectory.
|
||||
let level = humanize::active_level();
|
||||
let drag_path: Vec<(f64, f64, std::time::Duration)> =
|
||||
if matches!(level, humanize::HumanizeLevel::Off) {
|
||||
(1..=10)
|
||||
.map(|i| {
|
||||
let cx = sx + (tx - sx) * (i as f64) / 10.0;
|
||||
let cy = sy + (ty - sy) * (i as f64) / 10.0;
|
||||
(cx, cy, std::time::Duration::from_millis(10))
|
||||
})
|
||||
.collect()
|
||||
} else {
|
||||
humanize::move_path((sx, sy), (tx, ty), level, humanize::next_seed())
|
||||
.into_iter()
|
||||
.map(|s| (s.x, s.y, s.delay))
|
||||
.collect()
|
||||
};
|
||||
for (cx, cy, delay) in drag_path {
|
||||
mgr.client
|
||||
.send_command(
|
||||
"Input.dispatchMouseEvent",
|
||||
@@ -6525,7 +6592,9 @@ async fn handle_drag(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
|
||||
Some(&target_session_id),
|
||||
)
|
||||
.await?;
|
||||
tokio::time::sleep(tokio::time::Duration::from_millis(10)).await;
|
||||
if !delay.is_zero() {
|
||||
tokio::time::sleep(delay).await;
|
||||
}
|
||||
}
|
||||
|
||||
// Mouse up at target
|
||||
|
||||
@@ -200,13 +200,17 @@ async fn relocate_stale_ref(
|
||||
}
|
||||
}
|
||||
|
||||
/// Resolve a `@ref` or CSS selector to a click point. Returns
|
||||
/// `(centre_x, centre_y, width, height, session_id)`. Width/height come from the
|
||||
/// element's box model and feed humanize's in-bounds landing jitter; the CSS
|
||||
/// selector path returns zero size (→ land on centre, no jitter).
|
||||
pub async fn resolve_element_center(
|
||||
client: &CdpClient,
|
||||
session_id: &str,
|
||||
ref_map: &RefMap,
|
||||
selector_or_ref: &str,
|
||||
iframe_sessions: &HashMap<String, String>,
|
||||
) -> Result<(f64, f64, String), String> {
|
||||
) -> Result<(f64, f64, f64, f64, String), String> {
|
||||
if let Some(ref_id) = parse_ref(selector_or_ref) {
|
||||
let entry = ref_map
|
||||
.get(&ref_id)
|
||||
@@ -263,7 +267,7 @@ pub async fn resolve_element_center(
|
||||
.await;
|
||||
|
||||
if let Ok(r) = result {
|
||||
let (x, y) = box_model_center(&r.model);
|
||||
let (x, y, w, h) = box_model_dims(&r.model);
|
||||
// Occlusion check: a transient overlay (X.com's "click
|
||||
// outside to close" mask, modal backdrop, sticky banner,
|
||||
// etc.) can land on top of our target between snapshot
|
||||
@@ -279,7 +283,7 @@ pub async fn resolve_element_center(
|
||||
verify_click_target(client, effective_session_id, active_id, &ref_id, x, y)
|
||||
.await?;
|
||||
}
|
||||
return Ok((x, y, effective_session_id.to_string()));
|
||||
return Ok((x, y, w, h, effective_session_id.to_string()));
|
||||
}
|
||||
// backend_node_id is stale; re-query the accessibility tree below
|
||||
}
|
||||
@@ -316,13 +320,14 @@ pub async fn resolve_element_center(
|
||||
Some(effective_session_id),
|
||||
)
|
||||
.await?;
|
||||
let (x, y) = box_model_center(&result.model);
|
||||
return Ok((x, y, effective_session_id.to_string()));
|
||||
let (x, y, w, h) = box_model_dims(&result.model);
|
||||
return Ok((x, y, w, h, effective_session_id.to_string()));
|
||||
}
|
||||
|
||||
// CSS selector
|
||||
let (x, y) = resolve_by_selector(client, session_id, selector_or_ref).await?;
|
||||
Ok((x, y, session_id.to_string()))
|
||||
// No box model on the CSS-selector fast path → zero size → land on centre.
|
||||
Ok((x, y, 0.0, 0.0, session_id.to_string()))
|
||||
}
|
||||
|
||||
pub async fn resolve_element_object_id(
|
||||
@@ -872,6 +877,35 @@ fn box_model_center(model: &BoxModel) -> (f64, f64) {
|
||||
}
|
||||
}
|
||||
|
||||
/// Centre plus width/height of the content box, derived from the quad's
|
||||
/// bounding extent. Width/height feed humanize's in-bounds landing jitter; a
|
||||
/// degenerate quad yields zero size, which the jitter treats as "land on
|
||||
/// centre" (no jitter).
|
||||
fn box_model_dims(model: &BoxModel) -> (f64, f64, f64, f64) {
|
||||
let (cx, cy) = box_model_center(model);
|
||||
if model.content.len() >= 8 {
|
||||
let xs = [
|
||||
model.content[0],
|
||||
model.content[2],
|
||||
model.content[4],
|
||||
model.content[6],
|
||||
];
|
||||
let ys = [
|
||||
model.content[1],
|
||||
model.content[3],
|
||||
model.content[5],
|
||||
model.content[7],
|
||||
];
|
||||
let w = xs.iter().cloned().fold(f64::MIN, f64::max)
|
||||
- xs.iter().cloned().fold(f64::MAX, f64::min);
|
||||
let h = ys.iter().cloned().fold(f64::MIN, f64::max)
|
||||
- ys.iter().cloned().fold(f64::MAX, f64::min);
|
||||
(cx, cy, w.max(0.0), h.max(0.0))
|
||||
} else {
|
||||
(cx, cy, 0.0, 0.0)
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn get_element_text(
|
||||
client: &CdpClient,
|
||||
session_id: &str,
|
||||
|
||||
@@ -0,0 +1,517 @@
|
||||
//! Human-like input behaviour for stealth.
|
||||
//!
|
||||
//! When agent-browser drives a real Chrome over CDP, the input events it
|
||||
//! dispatches are already `isTrusted` — but a click that teleports the cursor
|
||||
//! straight to an element's exact centre, with no approach path and zero delay
|
||||
//! between move/press/release, is a behavioural tell that advanced anti-bot
|
||||
//! vendors (Akamai, PerimeterX, DataDome) look for.
|
||||
//!
|
||||
//! This module produces **human-like motion plans** — curved, eased cursor
|
||||
//! trajectories and variable keystroke timing — as *pure data*. It performs no
|
||||
//! I/O and knows nothing about CDP: callers turn the returned steps into
|
||||
//! `Input.dispatchMouseEvent` / `dispatchKeyEvent` calls. Keeping the maths pure
|
||||
//! makes the easing/jitter/detection logic unit-testable and deterministic
|
||||
//! (every randomised value comes from a caller-supplied seed).
|
||||
//!
|
||||
//! Design (see brainstorm 2026-06-11):
|
||||
//! - Three levels: [`HumanizeLevel::Off`] (instant, today's behaviour),
|
||||
//! `Fast` (a few cheap eased steps), `Human` (full curved trajectory + jitter).
|
||||
//! - Baseline is `Off`; the daemon escalates a session to `Human` when
|
||||
//! [`detect_level`] spots a known anti-bot vendor on the page. `--humanize` /
|
||||
//! `AGENT_BROWSER_HUMANIZE` force a fixed level.
|
||||
//! - Humanization only changes *how* the cursor reaches a target, never *which*
|
||||
//! element is hit: the landing jitter stays inside the caller-provided bounds.
|
||||
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::sync::{Mutex, OnceLock};
|
||||
use std::time::Duration;
|
||||
|
||||
// ---- daemon-wide runtime state -------------------------------------------
|
||||
//
|
||||
// The pure motion maths above are stateless. The daemon drives one active page
|
||||
// at a time, so we keep the *current* humanize level and last cursor position
|
||||
// in process-global slots rather than threading them through every call site.
|
||||
// (The adaptive detector flips the level per navigation; `dispatch_click` reads
|
||||
// the level + cursor here, so no signature in the click/type call graph has to
|
||||
// change.)
|
||||
|
||||
/// `AGENT_BROWSER_HUMANIZE` forces a fixed level, overriding the adaptive
|
||||
/// detector. Parsed once.
|
||||
fn env_override() -> Option<HumanizeLevel> {
|
||||
static OVERRIDE: OnceLock<Option<HumanizeLevel>> = OnceLock::new();
|
||||
*OVERRIDE.get_or_init(|| {
|
||||
std::env::var("AGENT_BROWSER_HUMANIZE")
|
||||
.ok()
|
||||
.and_then(|s| HumanizeLevel::parse(&s))
|
||||
})
|
||||
}
|
||||
|
||||
fn session_level() -> &'static Mutex<HumanizeLevel> {
|
||||
static LEVEL: OnceLock<Mutex<HumanizeLevel>> = OnceLock::new();
|
||||
LEVEL.get_or_init(|| Mutex::new(HumanizeLevel::Off))
|
||||
}
|
||||
|
||||
fn last_cursor_slot() -> &'static Mutex<(f64, f64)> {
|
||||
static CURSOR: OnceLock<Mutex<(f64, f64)>> = OnceLock::new();
|
||||
CURSOR.get_or_init(|| Mutex::new((0.0, 0.0)))
|
||||
}
|
||||
|
||||
/// The level that should apply right now: the env override if set, else the
|
||||
/// level the detector last chose for the active page.
|
||||
pub fn active_level() -> HumanizeLevel {
|
||||
env_override().unwrap_or_else(|| *session_level().lock().unwrap())
|
||||
}
|
||||
|
||||
/// Set by the adaptive detector after navigation. Ignored while an env override
|
||||
/// is in force (so `--humanize` always wins).
|
||||
pub fn set_detected_level(level: HumanizeLevel) {
|
||||
*session_level().lock().unwrap() = level;
|
||||
}
|
||||
|
||||
/// Where the virtual cursor currently sits, so the next move starts from there
|
||||
/// instead of teleporting.
|
||||
pub fn last_cursor() -> (f64, f64) {
|
||||
*last_cursor_slot().lock().unwrap()
|
||||
}
|
||||
|
||||
/// Record the cursor landing point after a move/click.
|
||||
pub fn set_last_cursor(p: (f64, f64)) {
|
||||
*last_cursor_slot().lock().unwrap() = p;
|
||||
}
|
||||
|
||||
/// A fresh seed per action so repeated clicks on the same point still vary,
|
||||
/// without touching the wall clock or a global RNG (both would break replay).
|
||||
pub fn next_seed() -> u64 {
|
||||
static COUNTER: AtomicU64 = AtomicU64::new(0x1234_5678);
|
||||
COUNTER
|
||||
.fetch_add(0x9E37_79B9_7F4A_7C15, Ordering::Relaxed)
|
||||
.rotate_left(17)
|
||||
}
|
||||
|
||||
/// How human-like input motion should be.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq, Default)]
|
||||
pub enum HumanizeLevel {
|
||||
/// Instant: a single move to the exact point, no delays. Original behaviour.
|
||||
#[default]
|
||||
Off,
|
||||
/// A few eased steps with small delays — cheap cover for ordinary sites.
|
||||
Fast,
|
||||
/// Full curved, decelerating trajectory with landing jitter and press
|
||||
/// dwell — for pages guarded by behavioural anti-bot systems.
|
||||
Human,
|
||||
}
|
||||
|
||||
impl HumanizeLevel {
|
||||
/// Parse a user-supplied level (`--humanize` / `AGENT_BROWSER_HUMANIZE`).
|
||||
pub fn parse(s: &str) -> Option<Self> {
|
||||
match s.trim().to_ascii_lowercase().as_str() {
|
||||
"off" | "none" | "instant" | "0" => Some(Self::Off),
|
||||
"fast" | "light" | "low" => Some(Self::Fast),
|
||||
"human" | "full" | "high" | "max" => Some(Self::Human),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn is_off(self) -> bool {
|
||||
matches!(self, Self::Off)
|
||||
}
|
||||
}
|
||||
|
||||
/// One step of a humanized cursor move: dispatch `mouseMoved` to (`x`, `y`),
|
||||
/// then sleep for `delay` before the next step. The final step's point is where
|
||||
/// the press/release should land.
|
||||
#[derive(Clone, Copy, Debug, PartialEq)]
|
||||
pub struct MoveStep {
|
||||
pub x: f64,
|
||||
pub y: f64,
|
||||
pub delay: Duration,
|
||||
}
|
||||
|
||||
/// Tiny deterministic PRNG (xorshift64*). Seeded by the caller so trajectories
|
||||
/// are reproducible in tests; we avoid pulling in the `rand` crate and never
|
||||
/// call a wall-clock/global RNG (which would also break workflow replay).
|
||||
struct Rng(u64);
|
||||
|
||||
impl Rng {
|
||||
fn new(seed: u64) -> Self {
|
||||
// Avoid the zero state, which xorshift cannot escape.
|
||||
Rng(seed ^ 0x9E37_79B9_7F4A_7C15)
|
||||
}
|
||||
|
||||
fn next_u64(&mut self) -> u64 {
|
||||
let mut x = self.0;
|
||||
x ^= x >> 12;
|
||||
x ^= x << 25;
|
||||
x ^= x >> 27;
|
||||
self.0 = x;
|
||||
x.wrapping_mul(0x2545_F491_4F6C_DD1D)
|
||||
}
|
||||
|
||||
/// Uniform in [0, 1).
|
||||
fn unit(&mut self) -> f64 {
|
||||
// Top 53 bits → f64 mantissa.
|
||||
(self.next_u64() >> 11) as f64 / (1u64 << 53) as f64
|
||||
}
|
||||
|
||||
/// Uniform in [-1, 1).
|
||||
fn signed(&mut self) -> f64 {
|
||||
self.unit() * 2.0 - 1.0
|
||||
}
|
||||
}
|
||||
|
||||
/// Smootherstep ease (zero velocity at both ends) — used to bias the per-step
|
||||
/// timing so the cursor accelerates away from the start and decelerates into
|
||||
/// the target, the way a hand does.
|
||||
fn ease(t: f64) -> f64 {
|
||||
let t = t.clamp(0.0, 1.0);
|
||||
t * t * t * (t * (t * 6.0 - 15.0) + 10.0)
|
||||
}
|
||||
|
||||
/// Cubic Bézier point at parameter `t`.
|
||||
fn bezier(p0: (f64, f64), p1: (f64, f64), p2: (f64, f64), p3: (f64, f64), t: f64) -> (f64, f64) {
|
||||
let u = 1.0 - t;
|
||||
let (a, b, c, d) = (u * u * u, 3.0 * u * u * t, 3.0 * u * t * t, t * t * t);
|
||||
(
|
||||
a * p0.0 + b * p1.0 + c * p2.0 + d * p3.0,
|
||||
a * p0.1 + b * p1.1 + c * p2.1 + d * p3.1,
|
||||
)
|
||||
}
|
||||
|
||||
/// Pick a landing point inside `bbox` (`x`, `y`, `width`, `height`). `Off`
|
||||
/// returns the exact centre; `Fast`/`Human` jitter around the centre but stay
|
||||
/// well inside the element so the click still lands on it.
|
||||
pub fn landing_point(bbox: (f64, f64, f64, f64), level: HumanizeLevel, seed: u64) -> (f64, f64) {
|
||||
let (bx, by, bw, bh) = bbox;
|
||||
let cx = bx + bw / 2.0;
|
||||
let cy = by + bh / 2.0;
|
||||
if level.is_off() || bw <= 1.0 || bh <= 1.0 {
|
||||
return (cx, cy);
|
||||
}
|
||||
// Keep within the inner 60% so jitter never lands on a neighbouring element
|
||||
// or the element's padding/edge.
|
||||
let spread = match level {
|
||||
HumanizeLevel::Human => 0.30,
|
||||
_ => 0.15,
|
||||
};
|
||||
let mut rng = Rng::new(seed);
|
||||
(
|
||||
cx + rng.signed() * bw * spread,
|
||||
cy + rng.signed() * bh * spread,
|
||||
)
|
||||
}
|
||||
|
||||
/// Build the cursor path from `from` to `to`. The last [`MoveStep`] is the
|
||||
/// landing point. `Off` yields a single zero-delay step at `to` (today's
|
||||
/// teleport), so callers can use one code path for every level.
|
||||
pub fn move_path(
|
||||
from: (f64, f64),
|
||||
to: (f64, f64),
|
||||
level: HumanizeLevel,
|
||||
seed: u64,
|
||||
) -> Vec<MoveStep> {
|
||||
if level.is_off() {
|
||||
return vec![MoveStep {
|
||||
x: to.0,
|
||||
y: to.1,
|
||||
delay: Duration::ZERO,
|
||||
}];
|
||||
}
|
||||
|
||||
let dist = (to.0 - from.0).hypot(to.1 - from.1);
|
||||
if dist < 1.0 {
|
||||
return vec![MoveStep {
|
||||
x: to.0,
|
||||
y: to.1,
|
||||
delay: Duration::ZERO,
|
||||
}];
|
||||
}
|
||||
|
||||
let (steps, total_ms, arc) = match level {
|
||||
HumanizeLevel::Fast => {
|
||||
let s = ((dist / 120.0).round() as usize).clamp(3, 6);
|
||||
(s, (dist * 0.35).clamp(40.0, 130.0), 0.06)
|
||||
}
|
||||
// Off handled above.
|
||||
_ => {
|
||||
let s = ((dist / 45.0).round() as usize).clamp(8, 24);
|
||||
(s, (dist * 0.9).clamp(140.0, 650.0), 0.16)
|
||||
}
|
||||
};
|
||||
|
||||
let mut rng = Rng::new(seed);
|
||||
|
||||
// Two control points along the line, pushed perpendicular to it to bow the
|
||||
// path into a gentle, slightly asymmetric arc.
|
||||
let (dx, dy) = (to.0 - from.0, to.1 - from.1);
|
||||
let (nx, ny) = (-dy / dist, dx / dist); // unit normal
|
||||
let bow = dist * arc * rng.signed();
|
||||
let ctrl = |frac: f64, jitter: f64, rng: &mut Rng| {
|
||||
let base = (from.0 + dx * frac, from.1 + dy * frac);
|
||||
let off = bow * (1.0 + jitter * rng.signed());
|
||||
(base.0 + nx * off, base.1 + ny * off)
|
||||
};
|
||||
let p1 = ctrl(0.33, 0.4, &mut rng);
|
||||
let p2 = ctrl(0.66, 0.4, &mut rng);
|
||||
|
||||
let mut out = Vec::with_capacity(steps);
|
||||
let mut prev_ease = 0.0;
|
||||
for i in 1..=steps {
|
||||
let t = i as f64 / steps as f64;
|
||||
// Ease maps wall-time progress so most points cluster near the ends
|
||||
// (slow start, slow finish, fast middle).
|
||||
let te = ease(t);
|
||||
let (x, y) = bezier(from, p1, p2, to, te);
|
||||
let frac = te - prev_ease;
|
||||
prev_ease = te;
|
||||
out.push(MoveStep {
|
||||
x,
|
||||
y,
|
||||
delay: Duration::from_micros((total_ms * frac * 1000.0).max(0.0) as u64),
|
||||
});
|
||||
}
|
||||
// Guarantee the final point is exactly the target.
|
||||
if let Some(last) = out.last_mut() {
|
||||
last.x = to.0;
|
||||
last.y = to.1;
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
/// Split a wheel scroll of (`total_dx`, `total_dy`) into eased segments. `Off`
|
||||
/// returns a single instant segment (today's one-shot scroll); `Fast`/`Human`
|
||||
/// break it into several accelerate-then-decelerate chunks with small,
|
||||
/// jittered inter-segment delays, the way a trackpad/wheel flick actually
|
||||
/// lands. The segment deltas always sum to the requested total.
|
||||
pub fn scroll_segments(
|
||||
total_dx: f64,
|
||||
total_dy: f64,
|
||||
level: HumanizeLevel,
|
||||
seed: u64,
|
||||
) -> Vec<(f64, f64, Duration)> {
|
||||
if level.is_off() {
|
||||
return vec![(total_dx, total_dy, Duration::ZERO)];
|
||||
}
|
||||
let (segs, base_ms) = match level {
|
||||
HumanizeLevel::Fast => (4usize, 18.0),
|
||||
_ => (9usize, 28.0),
|
||||
};
|
||||
let mut rng = Rng::new(seed);
|
||||
let mut out = Vec::with_capacity(segs);
|
||||
let mut prev = 0.0;
|
||||
for i in 1..=segs {
|
||||
let f = ease(i as f64 / segs as f64);
|
||||
let frac = f - prev;
|
||||
prev = f;
|
||||
let jitter = 1.0 + 0.3 * rng.signed();
|
||||
out.push((
|
||||
total_dx * frac,
|
||||
total_dy * frac,
|
||||
Duration::from_millis((base_ms * jitter).max(4.0) as u64),
|
||||
));
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
/// Dwell between `mousePressed` and `mouseReleased` (a real click isn't
|
||||
/// instantaneous). Zero for `Off`.
|
||||
pub fn press_dwell(level: HumanizeLevel, seed: u64) -> Duration {
|
||||
match level {
|
||||
HumanizeLevel::Off => Duration::ZERO,
|
||||
HumanizeLevel::Fast => Duration::from_millis(20 + (seed % 30)),
|
||||
HumanizeLevel::Human => Duration::from_millis(50 + (seed % 90)),
|
||||
}
|
||||
}
|
||||
|
||||
/// Per-character delays for typing `len` characters. `Off` is all-zero (use a
|
||||
/// single `Input.insertText`); `Fast`/`Human` produce variable inter-keystroke
|
||||
/// gaps with the occasional longer "think" pause, like a real typist.
|
||||
pub fn keystroke_delays(len: usize, level: HumanizeLevel, seed: u64) -> Vec<Duration> {
|
||||
if level.is_off() || len == 0 {
|
||||
return vec![Duration::ZERO; len];
|
||||
}
|
||||
let (mean, jitter, pause_chance, pause_extra) = match level {
|
||||
HumanizeLevel::Fast => (25.0, 15.0, 0.0, 0.0),
|
||||
_ => (95.0, 55.0, 0.06, 220.0),
|
||||
};
|
||||
let mut rng = Rng::new(seed);
|
||||
(0..len)
|
||||
.map(|_| {
|
||||
let mut ms = (mean + rng.signed() * jitter).max(8.0);
|
||||
if pause_chance > 0.0 && rng.unit() < pause_chance {
|
||||
ms += rng.unit() * pause_extra;
|
||||
}
|
||||
Duration::from_millis(ms as u64)
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Page signals sampled after navigation, used to decide whether to escalate a
|
||||
/// session to [`HumanizeLevel::Human`]. All strings are matched case-insensitively.
|
||||
#[derive(Debug, Default, Clone)]
|
||||
pub struct DetectSignals {
|
||||
/// Cookie names present on the document (e.g. `_abck`, `datadome`).
|
||||
pub cookie_names: Vec<String>,
|
||||
/// `src` of loaded scripts.
|
||||
pub script_urls: Vec<String>,
|
||||
/// Names of suspicious globals on `window` (e.g. `_px`, `bmak`).
|
||||
pub window_globals: Vec<String>,
|
||||
}
|
||||
|
||||
/// Known behavioural anti-bot fingerprints: (substring, vendor). Matched against
|
||||
/// cookie names, script URLs, and window globals.
|
||||
const VENDOR_MARKERS: &[(&str, &str)] = &[
|
||||
("_abck", "akamai"),
|
||||
("bm_sz", "akamai"),
|
||||
("ak_bmsc", "akamai"),
|
||||
("bmak", "akamai"),
|
||||
("_px", "perimeterx"),
|
||||
("perimeterx", "perimeterx"),
|
||||
("px-cloud", "perimeterx"),
|
||||
("datadome", "datadome"),
|
||||
("kpsdk", "kasada"),
|
||||
("incap_ses", "imperva"),
|
||||
("visid_incap", "imperva"),
|
||||
("reese84", "imperva"),
|
||||
("__cf_bm", "cloudflare-bot-mgmt"),
|
||||
];
|
||||
|
||||
/// Decide the level for a page. Returns `Human` if any known anti-bot vendor is
|
||||
/// present, otherwise `baseline`. Misses just stay at baseline and false hits
|
||||
/// only cost a little latency, so matching is deliberately liberal.
|
||||
pub fn detect_level(signals: &DetectSignals, baseline: HumanizeLevel) -> HumanizeLevel {
|
||||
let hay: Vec<String> = signals
|
||||
.cookie_names
|
||||
.iter()
|
||||
.chain(signals.script_urls.iter())
|
||||
.chain(signals.window_globals.iter())
|
||||
.map(|s| s.to_ascii_lowercase())
|
||||
.collect();
|
||||
let matched = VENDOR_MARKERS
|
||||
.iter()
|
||||
.any(|(marker, _)| hay.iter().any(|h| h.contains(marker)));
|
||||
if matched {
|
||||
HumanizeLevel::Human
|
||||
} else {
|
||||
baseline
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn parse_accepts_known_levels_and_rejects_junk() {
|
||||
assert_eq!(HumanizeLevel::parse("off"), Some(HumanizeLevel::Off));
|
||||
assert_eq!(HumanizeLevel::parse(" FAST "), Some(HumanizeLevel::Fast));
|
||||
assert_eq!(HumanizeLevel::parse("Human"), Some(HumanizeLevel::Human));
|
||||
assert_eq!(HumanizeLevel::parse("max"), Some(HumanizeLevel::Human));
|
||||
assert_eq!(HumanizeLevel::parse("wat"), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn off_level_teleports_in_one_step() {
|
||||
let path = move_path((0.0, 0.0), (100.0, 50.0), HumanizeLevel::Off, 1);
|
||||
assert_eq!(path.len(), 1);
|
||||
assert_eq!((path[0].x, path[0].y), (100.0, 50.0));
|
||||
assert_eq!(path[0].delay, Duration::ZERO);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn humanized_path_is_multi_step_and_lands_exactly_on_target() {
|
||||
let to = (640.0, 480.0);
|
||||
let path = move_path((10.0, 10.0), to, HumanizeLevel::Human, 42);
|
||||
assert!(path.len() >= 8, "human path should have many steps");
|
||||
let last = path.last().unwrap();
|
||||
assert_eq!((last.x, last.y), to, "final point must equal the target");
|
||||
// Path must actually leave the straight line at some point (it's a curve).
|
||||
let straight = path.iter().all(|s| {
|
||||
let t = (s.x - 10.0) / (to.0 - 10.0);
|
||||
(s.y - (10.0 + t * (to.1 - 10.0))).abs() < 0.5
|
||||
});
|
||||
assert!(!straight, "human path should bow off the straight line");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fast_path_is_shorter_than_human() {
|
||||
let fast = move_path((0.0, 0.0), (500.0, 500.0), HumanizeLevel::Fast, 7);
|
||||
let human = move_path((0.0, 0.0), (500.0, 500.0), HumanizeLevel::Human, 7);
|
||||
assert!(fast.len() < human.len());
|
||||
assert!((3..=6).contains(&fast.len()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn move_path_is_deterministic_for_a_seed() {
|
||||
let a = move_path((1.0, 2.0), (300.0, 400.0), HumanizeLevel::Human, 99);
|
||||
let b = move_path((1.0, 2.0), (300.0, 400.0), HumanizeLevel::Human, 99);
|
||||
assert_eq!(a, b);
|
||||
let c = move_path((1.0, 2.0), (300.0, 400.0), HumanizeLevel::Human, 100);
|
||||
assert_ne!(a, c, "different seeds should differ");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn landing_point_stays_inside_bounds_and_centres_when_off() {
|
||||
let bbox = (100.0, 100.0, 40.0, 20.0);
|
||||
assert_eq!(landing_point(bbox, HumanizeLevel::Off, 1), (120.0, 110.0));
|
||||
for seed in 0..200 {
|
||||
let (x, y) = landing_point(bbox, HumanizeLevel::Human, seed);
|
||||
assert!(x > 100.0 && x < 140.0, "x {x} escaped bbox");
|
||||
assert!(y > 100.0 && y < 120.0, "y {y} escaped bbox");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn keystroke_delays_zero_when_off_and_positive_otherwise() {
|
||||
assert!(keystroke_delays(5, HumanizeLevel::Off, 1)
|
||||
.iter()
|
||||
.all(|d| *d == Duration::ZERO));
|
||||
let human = keystroke_delays(20, HumanizeLevel::Human, 3);
|
||||
assert_eq!(human.len(), 20);
|
||||
assert!(human.iter().all(|d| *d >= Duration::from_millis(8)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn scroll_segments_sum_to_total_and_single_when_off() {
|
||||
let off = scroll_segments(0.0, 600.0, HumanizeLevel::Off, 1);
|
||||
assert_eq!(off.len(), 1);
|
||||
assert_eq!((off[0].0, off[0].1), (0.0, 600.0));
|
||||
assert_eq!(off[0].2, Duration::ZERO);
|
||||
|
||||
let human = scroll_segments(0.0, 600.0, HumanizeLevel::Human, 5);
|
||||
assert!(human.len() >= 5);
|
||||
let total_dy: f64 = human.iter().map(|s| s.1).sum();
|
||||
assert!(
|
||||
(total_dy - 600.0).abs() < 1e-6,
|
||||
"segments must sum to total"
|
||||
);
|
||||
assert!(human.iter().all(|s| s.2 >= Duration::from_millis(4)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn detect_escalates_on_known_vendor_else_baseline() {
|
||||
let mut s = DetectSignals::default();
|
||||
assert_eq!(detect_level(&s, HumanizeLevel::Off), HumanizeLevel::Off);
|
||||
|
||||
s.cookie_names = vec!["sessionid".into(), "_abck".into()];
|
||||
assert_eq!(detect_level(&s, HumanizeLevel::Off), HumanizeLevel::Human);
|
||||
|
||||
let s2 = DetectSignals {
|
||||
script_urls: vec!["https://cdn.example.com/DataDome-tags.js".into()],
|
||||
..Default::default()
|
||||
};
|
||||
assert_eq!(detect_level(&s2, HumanizeLevel::Off), HumanizeLevel::Human);
|
||||
|
||||
let s3 = DetectSignals {
|
||||
window_globals: vec!["_pxAppId".into()],
|
||||
..Default::default()
|
||||
};
|
||||
assert_eq!(detect_level(&s3, HumanizeLevel::Fast), HumanizeLevel::Human);
|
||||
|
||||
// Unknown signals keep the baseline.
|
||||
let s4 = DetectSignals {
|
||||
cookie_names: vec!["cart".into(), "theme".into()],
|
||||
..Default::default()
|
||||
};
|
||||
assert_eq!(detect_level(&s4, HumanizeLevel::Fast), HumanizeLevel::Fast);
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ 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,
|
||||
@@ -54,8 +55,15 @@ pub async fn click(
|
||||
.await;
|
||||
|
||||
match resolved {
|
||||
Ok((x, y, effective_session_id)) => {
|
||||
dispatch_click(client, &effective_session_id, x, y, button, click_count).await
|
||||
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
|
||||
@@ -190,7 +198,7 @@ pub async fn hover(
|
||||
selector_or_ref: &str,
|
||||
iframe_sessions: &HashMap<String, String>,
|
||||
) -> Result<(), String> {
|
||||
let (x, y, effective_session_id) = resolve_element_center(
|
||||
let (x, y, _w, _h, effective_session_id) = resolve_element_center(
|
||||
client,
|
||||
session_id,
|
||||
ref_map,
|
||||
@@ -349,9 +357,18 @@ pub async fn type_text_into_active_context(
|
||||
text: &str,
|
||||
delay_ms: Option<u64>,
|
||||
) -> Result<(), String> {
|
||||
let delay = delay_ms.unwrap_or(0);
|
||||
// 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 ch in text.chars() {
|
||||
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);
|
||||
@@ -403,8 +420,9 @@ pub async fn type_text_into_active_context(
|
||||
.await?;
|
||||
}
|
||||
|
||||
if delay > 0 {
|
||||
tokio::time::sleep(tokio::time::Duration::from_millis(delay)).await;
|
||||
let gap = cadence[i];
|
||||
if !gap.is_zero() {
|
||||
tokio::time::sleep(gap).await;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -988,7 +1006,7 @@ pub async fn tap_touch(
|
||||
selector_or_ref: &str,
|
||||
iframe_sessions: &HashMap<String, String>,
|
||||
) -> Result<(), String> {
|
||||
let (x, y, effective_session_id) = resolve_element_center(
|
||||
let (x, y, _w, _h, effective_session_id) = resolve_element_center(
|
||||
client,
|
||||
session_id,
|
||||
ref_map,
|
||||
@@ -1070,24 +1088,38 @@ async fn dispatch_click(
|
||||
button: &str,
|
||||
click_count: i32,
|
||||
) -> Result<(), String> {
|
||||
// Move
|
||||
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(session_id),
|
||||
)
|
||||
.await?;
|
||||
// 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,
|
||||
@@ -1114,6 +1146,13 @@ async fn dispatch_click(
|
||||
)
|
||||
.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>(
|
||||
|
||||
@@ -17,6 +17,8 @@ pub mod diff;
|
||||
#[allow(dead_code)]
|
||||
pub mod element;
|
||||
#[allow(dead_code)]
|
||||
pub mod humanize;
|
||||
#[allow(dead_code)]
|
||||
pub mod inspect_server;
|
||||
#[allow(dead_code)]
|
||||
pub mod interaction;
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "agent-browser-stealth",
|
||||
"version": "0.27.0-fork.35",
|
||||
"version": "0.27.0-fork.37",
|
||||
"description": "Browser automation CLI for AI agents — stealth fork with anti-detection",
|
||||
"type": "module",
|
||||
"packageManager": "pnpm@11.1.3",
|
||||
|
||||
Reference in New Issue
Block a user