chore(release): 0.27.0-fork.38 — silent operation (no foreground tab stealing)

Driving the user's real Chrome should not yank their view around. Now the agent
operates entirely in the background:
- New tabs are created with `background: true` (CreateTargetParams) so opening
  one never foregrounds it (the ab-connect extension already used active:false;
  this covers the raw-CDP path too).
- Dropped the two AUTO `Page.bringToFront` calls (auto-connect fresh tab, and the
  internal active-page switch). The explicit `bringToFront` command is untouched —
  surfacing a tab stays opt-in.
- enable_domains now sets `Emulation.setFocusEmulationEnabled(true)` so a
  backgrounded agent tab still renders (screenshots work), isn't render-throttled,
  and reports document.hasFocus()/visibilityState='visible' — which also removes
  the "tab is hidden the whole session" bot tell.

Verified headless: hasFocus=true/visible while backgrounded; click + screenshot
still work. Default behaviour, no flag.

cli/Cargo.lock

@@ -45,7 +45,7 @@ dependencies = [
 
 [[package]]
 name = "agent-browser-stealth"
-version = "0.27.0-fork.36"
+version = "0.27.0-fork.38"
 dependencies = [
  "aes-gcm",
  "async-trait",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "agent-browser-stealth"
-version = "0.27.0-fork.36"
+version = "0.27.0-fork.38"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/native/actions.rs

@@ -1511,12 +1511,11 @@ pub async fn execute_command(cmd: &Value, state: &mut DaemonState) -> Value {
 /// subsequent navigations don't hijack the user's existing tabs.
 async fn connect_auto_with_fresh_tab() -> Result<BrowserManager, String> {
     let mut mgr = BrowserManager::connect_auto().await?;
+    // tab_new creates the tab in the background (CreateTargetParams.background),
+    // so attaching to the user's Chrome never steals their foreground tab. We
+    // deliberately do NOT bring it to front — silent operation.
     mgr.tab_new(None, None).await?;
     let session_id = mgr.active_session_id()?.to_string();
-    let _ = mgr
-        .client
-        .send_command("Page.bringToFront", None, Some(&session_id))
-        .await;
 
     // Liveness probe: confirm the CDP session can actually round-trip
     // before returning success. Without this, a zombie CDP socket (process
@@ -5513,19 +5512,29 @@ 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 }))
 }
@@ -6522,7 +6531,7 @@ 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,
@@ -6530,7 +6539,7 @@ 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,
@@ -6555,12 +6564,26 @@ 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",
@@ -6568,7 +6591,9 @@ 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

cli/src/native/browser.rs

@@ -581,6 +581,7 @@ impl BrowserManager {
                     &CreateTargetParams {
                         url: "about:blank".to_string(),
                         agent_group,
+                        background: None,
                     },
                     None,
                 )
@@ -687,6 +688,20 @@ impl BrowserManager {
                 Some(session_id),
             )
             .await;
+        // Silent operation: agent tabs are driven in the background (we never
+        // force them to the foreground), so emulate focus. Without this a
+        // backgrounded tab is render-throttled and reports `document.hidden` /
+        // `!document.hasFocus()` — which both breaks timing-sensitive pages and
+        // is itself a bot signal (a real user looks at the page). Best-effort;
+        // ignored on engines without Emulation support.
+        let _ = self
+            .client
+            .send_command(
+                "Emulation.setFocusEmulationEnabled",
+                Some(json!({ "enabled": true })),
+                Some(session_id),
+            )
+            .await;
         Ok(())
     }
 
@@ -973,6 +988,7 @@ impl BrowserManager {
                 &CreateTargetParams {
                     url: "about:blank".to_string(),
                     agent_group,
+                    background: None,
                 },
                 None,
             )
@@ -1137,6 +1153,7 @@ impl BrowserManager {
                 &CreateTargetParams {
                     url: target_url.to_string(),
                     agent_group,
+                    background: Some(true),
                 },
                 None,
             )
@@ -1192,11 +1209,10 @@ impl BrowserManager {
         let session_id = self.pages[index].session_id.clone();
         self.enable_domains(&session_id).await?;
 
-        // Bring tab to front
-        let _ = self
-            .client
-            .send_command("Page.bringToFront", None, Some(&session_id))
-            .await;
+        // Silent: switching the agent's *internal* active page must not yank the
+        // user's foreground tab. The page is driven in the background (focus is
+        // emulated in enable_domains); the explicit `bringToFront` command is the
+        // only way a tab is deliberately surfaced.
 
         let url = self.get_url().await.unwrap_or_default();
         let title = self.get_title().await.unwrap_or_default();

cli/src/native/cdp/types.rs

@@ -153,6 +153,12 @@ pub struct CreateTargetParams {
     /// endpoint never receives an unknown parameter.
     #[serde(skip_serializing_if = "Option::is_none")]
     pub agent_group: Option<String>,
+    /// Create the tab in the background so opening it never steals the user's
+    /// foreground tab (silent operation). Standard CDP param; the ab-connect
+    /// extension creates its tabs `active: false` regardless, so this only
+    /// affects the raw-CDP (no extension) path.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub background: Option<bool>,
 }
 
 #[derive(Debug, Deserialize)]

cli/src/native/element.rs

@@ -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,

cli/src/native/humanize.rs

@@ -277,6 +277,41 @@ pub fn move_path(
     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 {
@@ -435,6 +470,23 @@ mod tests {
         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();

cli/src/native/interaction.rs

@@ -55,8 +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
@@ -191,7 +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,
@@ -999,7 +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,

cli/src/native/state.rs

@@ -121,6 +121,7 @@ async fn collect_storage_via_temp_target(
                 url: "about:blank".to_string(),
                 // Transient internal target (storage collection) — never grouped.
                 agent_group: None,
+                background: None,
             },
             None,
         )

package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-browser-stealth",
-  "version": "0.27.0-fork.36",
+  "version": "0.27.0-fork.38",
   "description": "Browser automation CLI for AI agents — stealth fork with anti-detection",
   "type": "module",
   "packageManager": "pnpm@11.1.3",