chore(release): 1.5.17 — complete multi-agent isolation (no foreign tab/pop-up adoption on click)

After strict isolation (v1.5.16) a session's tracked set is only its OWN tabs, so
in `adopt_newly_opened` (run after every click to follow a pop-up) EVERY foreign
tab looks "new" relative to the session's `before` set and got adopted — a
click-heavy flow on a busy shared Chrome pulled other agents'/the user's tabs
(github, Lark, iphone-use) into the session mid-flow.

A pop-up the agent itself opened can't be told apart from a foreign tab over the
relay (the synthesized targetInfo carries no opener/window/group), so on the relay
`adopt_newly_opened` now adopts nothing: the agent drives only tabs it explicitly
created; pop-ups (OAuth/login windows) are the user's. Launched browsers (every
tab ours) still follow pop-ups. Verified live: a fresh click-heavy relay session
stays clean (only its own tabs), and 5 concurrent agents churning tabs show zero
cross-agent drift.

cli/Cargo.lock

@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrome-use"
-version = "1.5.14"
+version = "1.5.17"
 dependencies = [
  "aes",
  "aes-gcm",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "chrome-use"
-version = "1.5.14"
+version = "1.5.17"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/native/browser.rs

@@ -235,6 +235,43 @@ fn prunable_target_ids(
         .collect()
 }
 
+/// Consecutive missing `getTargets` snapshots before an owned relay tab is
+/// pruned. >1 so a single churning/partial snapshot (other agents opening/closing
+/// tabs) or a brief cross-process-nav gap can't drop the tab the agent is driving.
+const RELAY_PRUNE_MISSES: u32 = 3;
+
+/// Debounced prune for the relay: target ids to drop, mutating per-target miss
+/// counters. A tab in `live_ids` resets to 0; an absent (non-pinned) tab
+/// increments and is pruned only at `RELAY_PRUNE_MISSES`. Counters for
+/// no-longer-tracked targets are forgotten. Pure, so the multi-agent churn
+/// tolerance is unit-testable without a live browser.
+fn debounced_prune_ids(
+    pages: &[PageInfo],
+    live_ids: &HashSet<String>,
+    pinned: Option<&str>,
+    misses: &mut HashMap<String, u32>,
+) -> Vec<String> {
+    let tracked: HashSet<&str> = pages.iter().map(|p| p.target_id.as_str()).collect();
+    misses.retain(|tid, _| tracked.contains(tid.as_str()));
+    let mut prune = Vec::new();
+    for p in pages {
+        let tid = p.target_id.as_str();
+        if live_ids.contains(tid) {
+            misses.remove(tid);
+            continue;
+        }
+        if pinned == Some(tid) {
+            continue;
+        }
+        let c = misses.entry(p.target_id.clone()).or_insert(0);
+        *c += 1;
+        if *c >= RELAY_PRUNE_MISSES {
+            prune.push(p.target_id.clone());
+        }
+    }
+    prune
+}
+
 /// Whether the resolved active page is a tab the session created (its target_id
 /// is in `created_targets`). Pure core of [`BrowserManager::active_is_session_owned`]
 /// so the relay no-hijack rule is unit-testable without a live browser.
@@ -464,6 +501,14 @@ pub struct BrowserManager {
     /// the session's commands onto the wrong page — the wrong-origin-fetch hazard
     /// in the dogfood reports. Falls back to the index if the pinned tab is gone.
     active_target_id: Option<String>,
+    /// Per-target count of CONSECUTIVE `resync_targets` snapshots in which an
+    /// owned tab was missing from `Target.getTargets`. Over the relay a single
+    /// snapshot routinely omits live tabs (multi-agent churn, a cross-process nav
+    /// briefly dropping the target), so we must not prune on one miss — that lost
+    /// the tab the agent was driving. A tab is removed only after it's been absent
+    /// for `RELAY_PRUNE_MISSES` consecutive snapshots; any snapshot that includes
+    /// it resets the counter. Keyed by stable target_id.
+    relay_target_misses: HashMap<String, u32>,
     next_tab_id: u32,
     /// Whether to enable the CDP `Runtime` domain (console / error / exception capture).
     /// OFF by default for stealth: a live `Runtime.enable` is a detectable CDP signal
@@ -600,6 +645,7 @@ impl BrowserManager {
                 visited_origins: HashSet::new(),
                 created_targets: HashSet::new(),
                 active_target_id: None,
+                relay_target_misses: HashMap::new(),
                 next_tab_id: 1,
                 capture_console: console_capture_enabled(),
             };
@@ -702,6 +748,7 @@ impl BrowserManager {
             visited_origins: HashSet::new(),
             created_targets: HashSet::new(),
             active_target_id: None,
+            relay_target_misses: HashMap::new(),
             next_tab_id: 1,
             capture_console: console_capture_enabled(),
         };
@@ -823,7 +870,19 @@ impl BrowserManager {
             self.active_page_index = 0;
             self.pin_active_target();
             self.enable_domains(&attach_result.session_id).await?;
+        } else if self.agent_group().is_some() {
+            // STRICT MULTI-AGENT ISOLATION (relay / the user's real Chrome).
+            // `page_targets` here are the USER's and OTHER agents' tabs. A tab
+            // group belongs to exactly ONE agent, so this session must NOT adopt
+            // any of them — it tracks ONLY tabs it creates (its own colored group)
+            // plus popups it opens. Adopting foreign tabs is precisely what let
+            // another concurrent agent's tab churn drop the tab we were driving and
+            // drift eval/click onto the wrong page (multi-agent failure). Open our
+            // own dedicated background tab in the session's group and pin it; the
+            // user's / other agents' tabs stay invisible to us.
+            self.tab_new(None, None).await?;
         } else {
+            // A browser WE launched: every tab is ours, so adopt them all.
             for target in &page_targets {
                 let attach_result: AttachToTargetResult = self
                     .client
@@ -849,24 +908,10 @@ impl BrowserManager {
                     target_type: target.target_type.clone(),
                 });
             }
-
-            if self.agent_group().is_some() {
-                // Relay: the adopted tabs above are the USER's, in their real
-                // Chrome. NEVER make one of them the agent's working tab — that is
-                // how commands drifted onto whatever page the user was viewing
-                // between steps (eval/click/get landed on the user's foreground
-                // tab; #35). Open our own dedicated background tab in the session's
-                // group and pin THAT as active. The user's tabs stay adopted (so
-                // `tab list` / explicit `tab switch` can reach them) but are never
-                // auto-selected — the agent only ever drives a tab it owns.
-                self.tab_new(None, None).await?;
-            } else {
-                // A browser we launched: every tab is ours, so the first is fine.
-                self.active_page_index = 0;
-                self.pin_active_target();
-                let session_id = self.pages[0].session_id.clone();
-                self.enable_domains(&session_id).await?;
-            }
+            self.active_page_index = 0;
+            self.pin_active_target();
+            let session_id = self.pages[0].session_id.clone();
+            self.enable_domains(&session_id).await?;
         }
 
         Ok(())
@@ -1515,6 +1560,18 @@ impl BrowserManager {
     /// the active tab, per #7/#8.1); the caller surfaces it so the agent knows a
     /// tab opened instead of seeing the old page (issue #24-A).
     pub async fn adopt_newly_opened(&mut self, before: &HashSet<String>) -> Option<PageInfo> {
+        // STRICT MULTI-AGENT ISOLATION: on the relay this session's `before` set is
+        // only its OWN tabs, so EVERY foreign tab (the user's, other agents') looks
+        // "new" relative to it and would be adopted here — exactly the leak where a
+        // concurrent agent's tabs (github/Lark/iphone-use) showed up in this
+        // session mid-flow. A tab the agent itself opened (a pop-up) can't be
+        // distinguished from a foreign tab over the relay (no opener/window/group
+        // in the synthesized targetInfo), so don't adopt anything: the agent drives
+        // only tabs it explicitly created, and pop-ups (e.g. an OAuth/login window)
+        // are the user's. A launched browser (every tab ours) still follows pop-ups.
+        if self.agent_group().is_some() {
+            return None;
+        }
         let result: GetTargetsResult = self
             .client
             .send_command_typed("Target.getTargets", &json!({}), None)
@@ -1557,6 +1614,11 @@ impl BrowserManager {
                 title: sanitize_title(&target.title),
                 target_type: target.target_type.clone(),
             };
+            // A tab that appeared right after THIS session's action (a click that
+            // opened a popup/new tab) is ours — record it as owned so it's tracked,
+            // protected from churn-pruning, and cleaned up on close, consistent with
+            // strict multi-agent isolation (we only ever own tabs we created/opened).
+            self.created_targets.insert(target.target_id.clone());
             self.add_background_page(page.clone());
             let _ = self.enable_domains(&attach.session_id).await;
             if opened.is_none() {
@@ -1584,13 +1646,19 @@ impl BrowserManager {
             .filter(should_track_target)
             .collect();
         let live_ids: HashSet<String> = live.iter().map(|t| t.target_id.clone()).collect();
+        let on_relay = self.agent_group().is_some();
 
         for target in &live {
             if self.update_page_target_info(target) {
                 continue;
             }
-            // A target this session hasn't tracked yet — attach and add it in the
-            // background so it's listable/adoptable without stealing the active tab.
+            // STRICT MULTI-AGENT ISOLATION: on the relay (the user's real Chrome,
+            // shared with other agents), NEVER adopt a tab this session didn't
+            // create — it belongs to the user or another agent's group. Only a
+            // browser we launched (every tab ours) adopts unknown targets.
+            if on_relay {
+                continue;
+            }
             let attach_result: AttachToTargetResult = match self
                 .client
                 .send_command_typed(
@@ -1621,12 +1689,26 @@ impl BrowserManager {
             let _ = self.enable_domains(&attach_result.session_id).await;
         }
 
-        // Drop tabs that no longer exist so `tab list` doesn't show phantom rows —
-        // but never prune the explicitly-pinned active target on a transient
-        // getTargets snapshot (issue #31; see `prunable_target_ids`).
-        let gone = prunable_target_ids(&self.pages, &live_ids, self.active_target_id.as_deref());
-        for tid in gone {
-            self.remove_page_by_target_id(&tid);
+        // Prune tabs that are gone. On a LAUNCHED browser a missing target really
+        // is closed, so prune immediately. On the RELAY a single `getTargets`
+        // snapshot routinely omits live tabs (multi-agent churn, a brief
+        // cross-process-nav gap) — dropping the tab we're driving on one bad
+        // snapshot is the failure we're fixing — so prune only after the tab has
+        // been absent for several CONSECUTIVE snapshots (debounced). The pinned
+        // active target is protected either way (issue #31).
+        let gone = if on_relay {
+            debounced_prune_ids(
+                &self.pages,
+                &live_ids,
+                self.active_target_id.as_deref(),
+                &mut self.relay_target_misses,
+            )
+        } else {
+            prunable_target_ids(&self.pages, &live_ids, self.active_target_id.as_deref())
+        };
+        for tid in &gone {
+            self.relay_target_misses.remove(tid);
+            self.remove_page_by_target_id(tid);
         }
 
         // Refresh url/title from each live tab. The relay only stamps target_info
@@ -2536,6 +2618,7 @@ async fn initialize_lightpanda_manager(
             visited_origins: HashSet::new(),
             created_targets: HashSet::new(),
             active_target_id: None,
+            relay_target_misses: HashMap::new(),
             next_tab_id: 1,
             capture_console: console_capture_enabled(),
         };
@@ -2992,6 +3075,43 @@ mod tests {
         );
     }
 
+    #[test]
+    fn debounced_prune_tolerates_transient_churn() {
+        // Multi-agent churn: a single getTargets snapshot omits our owned tab "B"
+        // (another agent opened/closed tabs). It must NOT be pruned on one miss.
+        let pages = vec![page("A"), page("B")];
+        let mut misses = HashMap::new();
+        let empty: HashSet<String> = HashSet::new();
+        // Misses 1 and 2: B absent but under threshold → not pruned.
+        assert!(debounced_prune_ids(&pages, &empty, Some("A"), &mut misses).is_empty());
+        assert!(debounced_prune_ids(&pages, &empty, Some("A"), &mut misses).is_empty());
+        // Miss 3 (== RELAY_PRUNE_MISSES): genuinely gone → pruned.
+        assert_eq!(
+            debounced_prune_ids(&pages, &empty, Some("A"), &mut misses),
+            vec!["B".to_string()]
+        );
+    }
+
+    #[test]
+    fn debounced_prune_resets_on_reappearance_and_protects_pin() {
+        let pages = vec![page("A"), page("B")];
+        let mut misses = HashMap::new();
+        let empty: HashSet<String> = HashSet::new();
+        let mut live_b: HashSet<String> = HashSet::new();
+        live_b.insert("B".to_string());
+        // Two misses for B, then it reappears → counter resets, so it survives
+        // indefinitely under intermittent churn.
+        debounced_prune_ids(&pages, &empty, Some("A"), &mut misses);
+        debounced_prune_ids(&pages, &empty, Some("A"), &mut misses);
+        assert!(debounced_prune_ids(&pages, &live_b, Some("A"), &mut misses).is_empty());
+        assert!(debounced_prune_ids(&pages, &empty, Some("A"), &mut misses).is_empty()); // back to miss 1
+                                                                                         // The pinned active "A" is never pruned no matter how many misses.
+        for _ in 0..5 {
+            let gone = debounced_prune_ids(&pages, &empty, Some("A"), &mut misses);
+            assert!(!gone.contains(&"A".to_string()));
+        }
+    }
+
     #[test]
     fn resolve_active_index_pin_survives_passive_background_tab() {
         // A foreign tab ("Z") gets appended by passive discovery after we pinned

cli/src/native/e2e_tests.rs

@@ -35,6 +35,7 @@ fn native_test_fixture_html(name: &str) -> &'static str {
         "html5_drag_probe" => include_str!("test_fixtures/html5_drag_probe.html"),
         "pointer_capture_probe" => include_str!("test_fixtures/pointer_capture_probe.html"),
         "upload_probe" => include_str!("test_fixtures/upload_probe.html"),
+        "iframe_button_probe" => include_str!("test_fixtures/iframe_button_probe.html"),
         _ => panic!("Unknown native test fixture: {}", name),
     }
 }
@@ -573,6 +574,76 @@ async fn e2e_snapshot_and_click_ref() {
     assert_success(&resp);
 }
 
+/// Clicking a button INSIDE an iframe by `@ref` must deliver a TRUSTED activation
+/// (`event.isTrusted === true`), not a synthetic DOM `.click()`. Security-sensitive
+/// embedded forms (Google Payments' `保存`) reject `isTrusted:false` clicks, so an
+/// enabled submit button silently no-op'd (issue #39). The fix routes iframe-ref
+/// clicks to a real `Input.dispatchMouseEvent` on the element's own frame session.
+/// The fixture's iframe button writes `clicked:<isTrusted>` into its own text on
+/// click, which the cross-frame snapshot reads back.
+#[tokio::test]
+#[ignore]
+async fn e2e_iframe_button_click_is_trusted() {
+    let mut state = DaemonState::new();
+
+    let resp = execute_command(
+        &json!({ "id": "1", "action": "launch", "headless": true }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+
+    let resp = execute_command(
+        &json!({ "id": "2", "action": "navigate", "url": native_test_fixture_url("iframe_button_probe") }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+
+    // Snapshot (interactive) — the button lives in the iframe and must appear with
+    // a ref; that ref carries the frame_id so the click resolves into the frame.
+    let resp = execute_command(
+        &json!({ "id": "3", "action": "snapshot", "interactive": true }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+    let snapshot = get_data(&resp)["snapshot"].as_str().unwrap_or("");
+    let ref_id = snapshot
+        .lines()
+        .find(|l| l.contains("button \"save\""))
+        .and_then(|l| l.split("ref=").nth(1))
+        .map(|r| r.trim_end_matches(']').trim())
+        .unwrap_or_else(|| panic!("iframe button not found in snapshot:\n{snapshot}"));
+
+    // Click it by ref.
+    let resp = execute_command(
+        &json!({ "id": "4", "action": "click", "selector": ref_id }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+
+    tokio::time::sleep(tokio::time::Duration::from_millis(300)).await;
+
+    // The button rewrote its own text with the click's isTrusted flag; read it
+    // back across frames.
+    let resp = execute_command(
+        &json!({ "id": "5", "action": "snapshot", "interactive": true }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+    let after = get_data(&resp)["snapshot"].as_str().unwrap_or("");
+    assert!(
+        after.contains("clicked:true"),
+        "iframe button click must be trusted (isTrusted:true); snapshot:\n{after}"
+    );
+
+    let resp = execute_command(&json!({ "id": "99", "action": "close" }), &mut state).await;
+    assert_success(&resp);
+}
+
 // ---------------------------------------------------------------------------
 // Screenshot
 // ---------------------------------------------------------------------------

cli/src/native/interaction.rs

@@ -56,19 +56,34 @@ pub async fn click(
         .await;
     }
 
-    // Over the extension relay we drive the user's real, in-use Chrome, where a
-    // coordinate `Input.dispatchMouseEvent` is NOT reliably confined to our target
-    // tab — it can be delivered to whatever tab is in the foreground, and an OOPIF
-    // element's box can't be mapped to a top-viewport point at all. This twice
-    // opened an unrelated tab on the user's busy Chrome (issues #31/#36). So on the
-    // relay, never use coordinates for a normal left click: DOM-dispatch invokes
-    // the element's click in its own (frame) session, always hitting the right
-    // element in the right tab. Double/right clicks still need true pointer
-    // semantics, and `coord` mode is an explicit opt-out.
+    // An element INSIDE an iframe needs a TRUSTED activation: a DOM `.click()` is
+    // `isTrusted:false`, which security-sensitive embedded forms reject — Google
+    // Payments' enabled `保存` button silently no-ops on a synthetic click (issue
+    // #39). A coordinate `Input.dispatchMouseEvent` can't help either: `getBoxModel`
+    // for a sub-frame node returns frame-local coordinates that don't compose the
+    // iframe's offset, so the click lands in the wrong place. The frame-agnostic
+    // trusted path is keyboard activation — focus the element in its own frame, then
+    // dispatch a real Enter on the page session; Chrome routes the key to the
+    // focused element regardless of frame (same as `type --focused`), and Enter on a
+    // focused button/link fires a trusted `click`. `coord` mode opts out.
+    let in_iframe = ref_map.ref_is_in_iframe(selector_or_ref);
+    if mode != "coord" && button == "left" && click_count == 1 && in_iframe {
+        return dom_activate(
+            client,
+            session_id,
+            ref_map,
+            selector_or_ref,
+            iframe_sessions,
+        )
+        .await;
+    }
+    // On the relay (the user's real Chrome) a TOP-document coordinate click used to
+    // drift onto the foreground tab; that root cause is fixed (#5: the agent drives
+    // its own pinned tab), but DOM-dispatch stays the conservative default here.
     if mode != "coord"
         && button == "left"
         && click_count == 1
-        && prefer_dom_dispatch(ref_map, selector_or_ref)
+        && crate::connect::relay_url().is_some()
     {
         return dom_click(
             client,
@@ -270,6 +285,71 @@ async fn dom_click(
     Ok(())
 }
 
+/// Trusted activation of an element inside an iframe (issue #39). Focuses the
+/// element in its own frame session, then dispatches a real Enter/Space on the
+/// page session — Chrome routes the key to the focused element across frames, and
+/// Enter/Space on a focused button/link/checkbox fires a `click` with
+/// `isTrusted: true`, which security-sensitive embedded forms (Google Payments
+/// `保存`) require. Non-activatable roles (a `div[onclick]`) can't be keyboard-
+/// activated, so they fall back to a DOM `.click()`.
+async fn dom_activate(
+    client: &CdpClient,
+    session_id: &str,
+    ref_map: &RefMap,
+    selector_or_ref: &str,
+    iframe_sessions: &HashMap<String, String>,
+) -> Result<(), String> {
+    let role = parse_ref(selector_or_ref)
+        .and_then(|r| ref_map.get(&r).map(|e| e.role.clone()))
+        .unwrap_or_default();
+    // Space toggles checkbox-like controls; Enter activates buttons/links/menus.
+    let key = match role.as_str() {
+        "checkbox" | "radio" | "switch" | "option" | "menuitemcheckbox" | "menuitemradio" => {
+            Some("space")
+        }
+        "button" | "link" | "menuitem" | "tab" | "treeitem" => Some("enter"),
+        _ => None,
+    };
+    let Some(key) = key else {
+        // Not keyboard-activatable — best effort via DOM .click() (untrusted).
+        return dom_click(
+            client,
+            session_id,
+            ref_map,
+            selector_or_ref,
+            iframe_sessions,
+        )
+        .await;
+    };
+
+    let (object_id, effective_session_id) = resolve_element_object_id(
+        client,
+        session_id,
+        ref_map,
+        selector_or_ref,
+        iframe_sessions,
+    )
+    .await?;
+    // Focus the element in its OWN frame session so the keystroke lands on it.
+    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?;
+    // Trusted key on the page session — routed to the focused (in-frame) element.
+    press_key(client, session_id, key).await?;
+    wait_for_paint_settled(client, &effective_session_id).await;
+    Ok(())
+}
+
 /// DOM-dispatch a double-click on the element in its own session (no coordinates)
 /// — the relay/iframe-safe counterpart to a coordinate dblclick. Fires the full
 /// click,click,dblclick sequence so handlers bound to any of them respond.

cli/src/native/test_fixtures/iframe_button_probe.html

@@ -0,0 +1,28 @@
+<!doctype html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <title>iframe button probe</title>
+  </head>
+  <body>
+    <h1>iframe button probe</h1>
+    <iframe
+      id="frame"
+      width="320"
+      height="140"
+      srcdoc="
+        <!doctype html>
+        <html>
+          <body style='margin:24px'>
+            <button id='b' style='padding:24px;font-size:22px'>save</button>
+            <script>
+              document.getElementById('b').addEventListener('click', function (e) {
+                this.textContent = 'clicked:' + e.isTrusted;
+              });
+            </script>
+          </body>
+        </html>
+      "
+    ></iframe>
+  </body>
+</html>

package.json

@@ -1,6 +1,6 @@
 {
   "name": "chrome-use",
-  "version": "1.5.14",
+  "version": "1.5.17",
   "description": "chrome-use — drive your real, logged-in Chrome from any AI agent, stealth by default",
   "type": "module",
   "packageManager": "pnpm@11.1.3",

skill-data/core/SKILL.md

@@ -131,7 +131,17 @@ Each `--session` that connects gets its **own colored Chrome tab group** (named
 after the session) and drives only its own tabs — multiple agents share the one
 real browser without cross-talk, and the user's own tabs are never grouped. CDP
 drives the page without moving the user's mouse/keyboard, so it doesn't fight
-them for control. **Anti-detection ranking: this real logged-in Chrome (extension
+them for control.
+
+**Strict multi-agent isolation.** A session over the relay tracks and drives
+**only the tabs it created** (its own group). It does **not** adopt the user's
+existing tabs, other agents' tabs, or pop-ups (e.g. an OAuth/login window — that's
+the user's), so several agents (and other tools opening tabs) can work in the same
+real Chrome concurrently without ever dropping or stealing each other's tabs —
+another agent's tab churn can't make your bound tab vanish or drift your commands
+onto the wrong page. Consequence: `tab list` shows only *your* session's tabs; to
+drive a specific page, navigate to it in your own tab instead of expecting a
+pre-existing or popped-up tab to appear in the list. **Anti-detection ranking: this real logged-in Chrome (extension
 connect) > a headed launched browser > headless (forbidden).** A genuine human
 browser has no headless/automation tells at all, so prefer it for anything
 anti-bot-sensitive.