chore(release): 1.5.15 — trusted activation for in-iframe buttons (#39)

A DOM `.click()` is isTrusted:false, which security-sensitive embedded forms
reject — Google Payments' enabled `保存` button silently no-op'd, so a
cross-origin payment/checkout/KYC form could be read, scrolled, and typed into
but never submitted. A coordinate click can't help either: getBoxModel for a
sub-frame node returns frame-local coords that don't compose the iframe offset,
so it lands wrong (verified — the same-origin probe came back isTrusted:false
via the coordinate fallback).

Fix: click on an in-iframe ref now focuses the element in its own frame session
and dispatches a real Enter (Space for checkbox-like roles) on the page session.
Chrome routes the key to the focused element across frames (same mechanism as
`type --focused`), and Enter/Space on a focused button/link/checkbox fires a
trusted click. Non-activatable roles fall back to DOM .click().

Adds e2e_iframe_button_click_is_trusted (+ fixture): an in-iframe button records
event.isTrusted into its own text; the test asserts the ref-click delivers
isTrusted:true.

cli/Cargo.lock

@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrome-use"
-version = "1.5.13"
+version = "1.5.15"
 dependencies = [
  "aes",
  "aes-gcm",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "chrome-use"
-version = "1.5.13"
+version = "1.5.15"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/commands.rs

@@ -34,11 +34,50 @@ pub enum ParseError {
 /// suggestions on an unknown command (issue #29). Not exhaustive — just the
 /// common verbs plus a few known wrong-guesses mapped to the real command.
 const KNOWN_COMMANDS: &[&str] = &[
-    "open", "navigate", "click", "fill", "type", "press", "snapshot", "screenshot", "eval", "get",
+    "open",
-    "text", "html", "frames", "find", "wait", "scroll", "hover", "select", "check", "uncheck",
+    "navigate",
-    "tab", "tabs", "close", "back", "forward", "reload", "sessions", "status", "daemon", "doctor",
+    "click",
-    "upgrade", "connect", "cookies", "mouse", "keyboard", "stream", "frame", "profiles", "title",
+    "fill",
-    "url", "is", "drag", "dialog", "upload",
+    "type",
+    "press",
+    "snapshot",
+    "screenshot",
+    "eval",
+    "get",
+    "text",
+    "html",
+    "frames",
+    "find",
+    "wait",
+    "scroll",
+    "hover",
+    "select",
+    "check",
+    "uncheck",
+    "tab",
+    "tabs",
+    "close",
+    "back",
+    "forward",
+    "reload",
+    "sessions",
+    "status",
+    "daemon",
+    "doctor",
+    "upgrade",
+    "connect",
+    "cookies",
+    "mouse",
+    "keyboard",
+    "stream",
+    "frame",
+    "profiles",
+    "title",
+    "url",
+    "is",
+    "drag",
+    "dialog",
+    "upload",
 ];
 
 /// Levenshtein distance, capped — small inputs only (command names).
@@ -547,7 +586,9 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
                 context: "type".to_string(),
                 usage: "type <selector> <text>   (or: type --focused <text>) [--key-events]",
             })?;
-            Ok(json!({ "id": id, "action": "type", "selector": sel, "text": rest[1..].join(" "), "keyEvents": key_events }))
+            Ok(
+                json!({ "id": id, "action": "type", "selector": sel, "text": rest[1..].join(" "), "keyEvents": key_events }),
+            )
         }
         "pick" => {
             // pick <selector|@ref> --option "<text>"  — atomic combobox select:
@@ -761,7 +802,8 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
                             _ => {
                                 return Err(ParseError::InvalidValue {
                                     message: format!("scroll --at: invalid coordinate `{}`", val),
-                                    usage: "scroll [direction] [amount] --at <x,y> (e.g. --at 640,400)",
+                                    usage:
+                                        "scroll [direction] [amount] --at <x,y> (e.g. --at 640,400)",
                                 })
                             }
                         }
@@ -970,17 +1012,21 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
                     "--full" | "-f" => full_page = true,
                     // `--clip x,y,w,h` captures a pixel region (issue #34).
                     "--clip" => {
-                        let raw = rest.get(i + 1).ok_or_else(|| ParseError::MissingArguments {
+                        let raw = rest
-                            context: "screenshot --clip".to_string(),
+                            .get(i + 1)
-                            usage: "screenshot --clip <x,y,w,h> [path]",
+                            .ok_or_else(|| ParseError::MissingArguments {
-                        })?;
+                                context: "screenshot --clip".to_string(),
+                                usage: "screenshot --clip <x,y,w,h> [path]",
+                            })?;
                         let nums: Vec<f64> = raw
                             .split(',')
                             .filter_map(|n| n.trim().parse::<f64>().ok())
                             .collect();
                         if nums.len() != 4 {
                             return Err(ParseError::InvalidValue {
-                                message: format!("--clip expects 'x,y,w,h' (4 numbers), got '{raw}'"),
+                                message: format!(
+                                    "--clip expects 'x,y,w,h' (4 numbers), got '{raw}'"
+                                ),
                                 usage: "screenshot --clip <x,y,w,h> [path]",
                             });
                         }
@@ -4128,7 +4174,11 @@ mod tests {
     fn test_type_key_events() {
         // --key-events sends real keystrokes (for autocomplete/combobox) and must
         // not be swallowed into the typed text.
-        let cmd = parse_command(&args("type #postal 201-0001 --key-events"), &default_flags()).unwrap();
+        let cmd = parse_command(
+            &args("type #postal 201-0001 --key-events"),
+            &default_flags(),
+        )
+        .unwrap();
         assert_eq!(cmd["action"], "type");
         assert_eq!(cmd["selector"], "#postal");
         assert_eq!(cmd["text"], "201-0001");
@@ -4426,8 +4476,11 @@ mod tests {
     #[test]
     fn test_screenshot_clip() {
         // `--clip x,y,w,h` captures a pixel region (issue #34); the path still parses.
-        let cmd = parse_command(&args("screenshot --clip 10,20,200,40 out.png"), &default_flags())
+        let cmd = parse_command(
-            .unwrap();
+            &args("screenshot --clip 10,20,200,40 out.png"),
+            &default_flags(),
+        )
+        .unwrap();
         assert_eq!(cmd["action"], "screenshot");
         assert_eq!(cmd["clip"]["x"], 10.0);
         assert_eq!(cmd["clip"]["y"], 20.0);
@@ -5005,7 +5058,10 @@ mod tests {
         assert_eq!(nearest_command("sesions").as_deref(), Some("sessions"));
         assert_eq!(nearest_command("session").as_deref(), Some("sessions"));
         assert_eq!(nearest_command("clik").as_deref(), Some("click"));
-        assert_eq!(nearest_command("screenshits").as_deref(), Some("screenshot"));
+        assert_eq!(
+            nearest_command("screenshits").as_deref(),
+            Some("screenshot")
+        );
         // Nonsense with no close match stays silent.
         assert_eq!(nearest_command("xyzzy"), None);
         // The unknown-command error embeds the suggestion.

cli/src/native/actions.rs

@@ -3244,8 +3244,14 @@ async fn handle_type(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
             .get("text")
             .and_then(|v| v.as_str())
             .ok_or("Missing 'text' parameter")?;
-        interaction::type_text_into_active_context(&mgr.client, &session_id, text, None, key_events)
+        interaction::type_text_into_active_context(
-            .await?;
+            &mgr.client,
+            &session_id,
+            text,
+            None,
+            key_events,
+        )
+        .await?;
         return Ok(json!({ "typed": text, "focused": true }));
     }
 
@@ -3493,27 +3499,40 @@ async fn handle_scroll(cmd: &Value, state: &mut DaemonState) -> Result<Value, St
         return Ok(json!({ "scrolled": true, "via": "selector" }));
     }
 
-    // No selector: dispatch a real (isTrusted) wheel at a viewport coordinate.
+    // `--at x,y` / `--frame n`: dispatch a real (isTrusted) wheel at a viewport
-    // This hits the compositor and scrolls whatever scroll container is under the
+    // coordinate. This hits the compositor and scrolls whatever scroll container
-    // pointer — including cross-origin iframes that `window.scrollBy` on the top
+    // is under the pointer — including cross-origin iframes that `window.scrollBy`
-    // document silently no-ops on (issue #36). The coordinate is, in priority:
+    // on the top document silently no-ops on (issue #36).
-    //   --at x,y  → that exact pixel
+    if cmd.get("at").is_some() || cmd.get("frame").is_some() {
-    //   --frame n → the center of frame n from `chrome-use frames`
+        let (x, y, via) = if let Some(at) = cmd.get("at").and_then(|v| v.as_array()) {
-    //   default   → the viewport center
+            let x = at.first().and_then(|v| v.as_f64()).unwrap_or(0.0);
-    let (x, y, via) = if let Some(at) = cmd.get("at").and_then(|v| v.as_array()) {
+            let y = at.get(1).and_then(|v| v.as_f64()).unwrap_or(0.0);
-        let x = at.first().and_then(|v| v.as_f64()).unwrap_or(0.0);
+            (x, y, "at")
-        let y = at.get(1).and_then(|v| v.as_f64()).unwrap_or(0.0);
+        } else {
-        (x, y, "at")
+            let n = cmd.get("frame").and_then(|v| v.as_u64()).unwrap_or(0);
-    } else if let Some(n) = cmd.get("frame").and_then(|v| v.as_u64()) {
+            let (x, y) = frame_center(mgr, &session_id, &state.iframe_sessions, n as usize).await?;
-        let (x, y) = frame_center(mgr, &session_id, &state.iframe_sessions, n as usize).await?;
+            (x, y, "frame")
-        (x, y, "frame")
+        };
-    } else {
+        dispatch_wheel(&mgr.client, &session_id, x, y, dx, dy).await?;
-        let (x, y) = viewport_center(mgr, &session_id).await?;
+        return Ok(json!({ "scrolled": true, "via": via, "at": [x, y] }));
-        (x, y, "center")
+    }
-    };
 
-    dispatch_wheel(&mgr.client, &session_id, x, y, dx, dy).await?;
+    // Default (no selector/at/frame): scroll the page with `window.scrollBy`. This
-    Ok(json!({ "scrolled": true, "via": via, "at": [x, y] }))
+    // is the reliable path for ordinary page scrolling; a coordinate wheel at the
+    // viewport centre is NOT a dependable substitute (it no-ops on some pages,
+    // e.g. headless), so the wheel stays opt-in via `--at`/`--frame` for the
+    // cross-origin-iframe case (issue #36).
+    interaction::scroll(
+        &mgr.client,
+        &session_id,
+        &state.ref_map,
+        None,
+        dx,
+        dy,
+        &state.iframe_sessions,
+    )
+    .await?;
+    Ok(json!({ "scrolled": true, "via": "page" }))
 }
 
 /// Viewport center in CSS pixels, used as the default wheel landing point for
@@ -3836,12 +3855,9 @@ async fn handle_gettext(cmd: &Value, state: &mut DaemonState) -> Result<Value, S
 async fn handle_frames(_cmd: &Value, state: &mut DaemonState) -> Result<Value, String> {
     let mgr = state.browser.as_ref().ok_or("Browser not launched")?;
     let session_id = mgr.active_session_id()?.to_string();
-    let frames = super::element::collect_all_frames_text(
+    let frames =
-        &mgr.client,
+        super::element::collect_all_frames_text(&mgr.client, &session_id, &state.iframe_sessions)
-        &session_id,
+            .await?;
-        &state.iframe_sessions,
-    )
-    .await?;
     let list: Vec<Value> = frames
         .iter()
         .enumerate()
@@ -4337,7 +4353,10 @@ async fn handle_cf_status(_cmd: &Value, state: &mut DaemonState) -> Result<Value
     let url = mgr.get_url().await.unwrap_or_default();
 
     // 1. Is the page a Cloudflare challenge right now?
-    let probe_raw = mgr.evaluate(CF_CHALLENGE_JS, None).await.unwrap_or(Value::Null);
+    let probe_raw = mgr
+        .evaluate(CF_CHALLENGE_JS, None)
+        .await
+        .unwrap_or(Value::Null);
     let probe = parse_json_string(probe_raw, "cf challenge probe").unwrap_or(Value::Null);
     let challenged = probe
         .get("challenged")

cli/src/native/browser.rs

@@ -579,7 +579,10 @@ impl BrowserManager {
         crate::connect::log_connect_mode(
             &ws_url,
             true,
-            DAEMON_SESSION.get().map(String::as_str).unwrap_or("default"),
+            DAEMON_SESSION
+                .get()
+                .map(String::as_str)
+                .unwrap_or("default"),
         );
         let manager = if engine == "lightpanda" {
             initialize_lightpanda_manager(ws_url, process).await?
@@ -681,7 +684,10 @@ impl BrowserManager {
         crate::connect::log_connect_mode(
             &ws_url,
             false,
-            DAEMON_SESSION.get().map(String::as_str).unwrap_or("default"),
+            DAEMON_SESSION
+                .get()
+                .map(String::as_str)
+                .unwrap_or("default"),
         );
         let client = Arc::new(CdpClient::connect_with_headers(&ws_url, headers).await?);
         let mut manager = Self {
@@ -1202,13 +1208,21 @@ impl BrowserManager {
     pub async fn evaluate(&self, script: &str, _args: Option<Value>) -> Result<Value, String> {
         let session_id = self.active_session_id()?.to_string();
 
-        // `replMode: true` matches the DevTools console: top-level `let`/`const`
+        // `replMode: true` lets successive `eval`s re-declare top-level
-        // can be re-declared across successive `eval`s instead of throwing
+        // `let`/`const` instead of throwing "Identifier 'x' has already been
-        // "Identifier 'x' has already been declared" (issue #38 — independent
+        // declared" (issue #38 — independent `eval` steps in a test suite collided
-        // `eval` steps in a test suite collided in the page's shared lexical
+        // in the page's shared lexical scope). BUT replMode and `awaitPromise` are
-        // scope), and top-level `await` is allowed. Completion-value and
+        // mutually exclusive in Chrome: under replMode a returned promise is NOT
-        // main-world semantics are unchanged. Built as raw params so the other
+        // awaited (it serialises to `{}`), which breaks `fetch(...).then(...)` and
-        // ~28 EvaluateParams literals don't all need a new field.
+        // every other async eval. So enable replMode ONLY for synchronous scripts
+        // that declare a top-level `let`/`const`; promise-returning scripts keep
+        // `awaitPromise` (no replMode) — exactly the pre-#38 behaviour.
+        let mentions_async = script.contains("await")
+            || script.contains(".then(")
+            || script.contains("fetch(")
+            || script.contains("Promise");
+        let declares = script.contains("let ") || script.contains("const ");
+        let repl_mode = declares && !mentions_async;
         let result: EvaluateResult = self
             .client
             .send_command_typed(
@@ -1216,8 +1230,8 @@ impl BrowserManager {
                 &json!({
                     "expression": script,
                     "returnByValue": true,
-                    "awaitPromise": true,
+                    "awaitPromise": !repl_mode,
-                    "replMode": true,
+                    "replMode": repl_mode,
                 }),
                 Some(&session_id),
             )
@@ -2815,7 +2829,9 @@ mod tests {
              its tab is gone (closed, navigated across processes, or lost after an extension \
              restart). Re-attach by re-opening your target URL before retrying."
         ));
-        assert!(is_stale_target_error("unknown sessionId cb-tab-7 for Page.navigate"));
+        assert!(is_stale_target_error(
+            "unknown sessionId cb-tab-7 for Page.navigate"
+        ));
         assert!(is_stale_target_error("no attached tab for Page.navigate"));
     }
 
@@ -2823,8 +2839,12 @@ mod tests {
     fn stale_target_error_ignores_unrelated_failures() {
         // A genuine navigation failure (bad URL, DNS, blocked) must NOT trigger
         // the open-a-fresh-tab recovery — that would mask the real error.
-        assert!(!is_stale_target_error("Navigation failed: net::ERR_NAME_NOT_RESOLVED"));
+        assert!(!is_stale_target_error(
-        assert!(!is_stale_target_error("CDP command timed out: Page.navigate"));
+            "Navigation failed: net::ERR_NAME_NOT_RESOLVED"
+        ));
+        assert!(!is_stale_target_error(
+            "CDP command timed out: Page.navigate"
+        ));
     }
 
     fn page(target_id: &str) -> PageInfo {
@@ -2931,7 +2951,10 @@ mod tests {
         let dirty = "\u{200d}\u{2061}\u{200d}\u{2063}\u{200b}\u{2062}\u{feff}GitHub";
         assert_eq!(sanitize_title(dirty), "GitHub");
         // Clean titles (incl. CJK + normal punctuation) pass through untouched.
-        assert_eq!(sanitize_title("購入手続きへ - メルカリ"), "購入手続きへ - メルカリ");
+        assert_eq!(
+            sanitize_title("購入手続きへ - メルカリ"),
+            "購入手続きへ - メルカリ"
+        );
         assert_eq!(sanitize_title("  Hello World  "), "Hello World");
         // Emoji and real content survive; only the invisibles are dropped.
         assert_eq!(sanitize_title("✓ Done\u{200b}"), "✓ Done");
@@ -2963,7 +2986,10 @@ mod tests {
         // A pinned target that IS in the live set is simply not prunable anyway.
         let mut live2 = HashSet::new();
         live2.insert("A".to_string());
-        assert_eq!(prunable_target_ids(&pages, &live2, Some("A")), vec!["B".to_string()]);
+        assert_eq!(
+            prunable_target_ids(&pages, &live2, Some("A")),
+            vec!["B".to_string()]
+        );
     }
 
     #[test]

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/element.rs

@@ -1028,7 +1028,9 @@ async fn eval_text_in_frame(client: &CdpClient, session_id: &str, frame_id: &str
         .await
         .ok()
         .and_then(|v| v.get("executionContextId").and_then(|c| c.as_i64()));
-    let Some(ctx_id) = ctx else { return String::new() };
+    let Some(ctx_id) = ctx else {
+        return String::new();
+    };
     let res = client
         .send_command(
             "Runtime.evaluate",
@@ -1099,7 +1101,10 @@ pub async fn collect_all_frames_text(
         let (kind, text) = if is_top {
             ("top", eval_text_default(client, top_session).await)
         } else {
-            ("inline", eval_text_in_frame(client, top_session, &fid).await)
+            (
+                "inline",
+                eval_text_in_frame(client, top_session, &fid).await,
+            )
         };
         out.push(FrameText {
             frame_id: fid,

cli/src/native/interaction.rs

@@ -56,16 +56,35 @@ pub async fn click(
         .await;
     }
 
-    // Over the extension relay we drive the user's real, in-use Chrome, where a
+    // An element INSIDE an iframe needs a TRUSTED activation: a DOM `.click()` is
-    // coordinate `Input.dispatchMouseEvent` is NOT reliably confined to our target
+    // `isTrusted:false`, which security-sensitive embedded forms reject — Google
-    // tab — it can be delivered to whatever tab is in the foreground, and an OOPIF
+    // Payments' enabled `保存` button silently no-ops on a synthetic click (issue
-    // element's box can't be mapped to a top-viewport point at all. This twice
+    // #39). A coordinate `Input.dispatchMouseEvent` can't help either: `getBoxModel`
-    // opened an unrelated tab on the user's busy Chrome (issues #31/#36). So on the
+    // for a sub-frame node returns frame-local coordinates that don't compose the
-    // relay, never use coordinates for a normal left click: DOM-dispatch invokes
+    // iframe's offset, so the click lands in the wrong place. The frame-agnostic
-    // the element's click in its own (frame) session, always hitting the right
+    // trusted path is keyboard activation — focus the element in its own frame, then
-    // element in the right tab. Double/right clicks still need true pointer
+    // dispatch a real Enter on the page session; Chrome routes the key to the
-    // semantics, and `coord` mode is an explicit opt-out.
+    // focused element regardless of frame (same as `type --focused`), and Enter on a
-    if mode != "coord" && button == "left" && click_count == 1 && prefer_dom_dispatch(ref_map, selector_or_ref) {
+    // 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
+        && crate::connect::relay_url().is_some()
+    {
         return dom_click(
             client,
             session_id,
@@ -266,6 +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.
@@ -319,7 +403,14 @@ pub async fn dblclick(
     if std::env::var("AGENT_BROWSER_CLICK_MODE").as_deref() != Ok("coord")
         && prefer_dom_dispatch(ref_map, selector_or_ref)
     {
-        return dom_dblclick(client, session_id, ref_map, selector_or_ref, iframe_sessions).await;
+        return dom_dblclick(
+            client,
+            session_id,
+            ref_map,
+            selector_or_ref,
+            iframe_sessions,
+        )
+        .await;
     }
     click(
         client,
@@ -387,7 +478,14 @@ pub async fn hover(
     // Coordinate `mouseMoved` drifts to the foreground tab over the relay and
     // can't reach an OOPIF — DOM-dispatch the hover there (issues #31/#36).
     if prefer_dom_dispatch(ref_map, selector_or_ref) {
-        return dom_hover(client, session_id, ref_map, selector_or_ref, iframe_sessions).await;
+        return dom_hover(
+            client,
+            session_id,
+            ref_map,
+            selector_or_ref,
+            iframe_sessions,
+        )
+        .await;
     }
     let (x, y, _w, _h, effective_session_id) = resolve_element_center(
         client,

cli/src/native/snapshot.rs

@@ -345,7 +345,16 @@ pub async fn take_snapshot(
     frame_id: Option<&str>,
     iframe_sessions: &HashMap<String, String>,
 ) -> Result<String, String> {
-    take_snapshot_at_depth(client, session_id, options, ref_map, frame_id, iframe_sessions, 0).await
+    take_snapshot_at_depth(
+        client,
+        session_id,
+        options,
+        ref_map,
+        frame_id,
+        iframe_sessions,
+        0,
+    )
+    .await
 }
 
 #[allow(clippy::too_many_arguments)]

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>

cli/src/output.rs

@@ -228,13 +228,28 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
         // because its response carries `url`/`title`, which later generic
         // renderers would otherwise swallow.
         if action == Some("cf_status") {
-            let challenged = data.get("challenged").and_then(|v| v.as_bool()).unwrap_or(false);
+            let challenged = data
-            let rec = data.get("recommendation").and_then(|v| v.as_str()).unwrap_or("?");
+                .get("challenged")
+                .and_then(|v| v.as_bool())
+                .unwrap_or(false);
+            let rec = data
+                .get("recommendation")
+                .and_then(|v| v.as_str())
+                .unwrap_or("?");
             let cl = data.get("clearance");
-            let present = cl.and_then(|c| c.get("present")).and_then(|v| v.as_bool()).unwrap_or(false);
+            let present = cl
-            let expired = cl.and_then(|c| c.get("expired")).and_then(|v| v.as_bool()).unwrap_or(false);
+                .and_then(|c| c.get("present"))
+                .and_then(|v| v.as_bool())
+                .unwrap_or(false);
+            let expired = cl
+                .and_then(|c| c.get("expired"))
+                .and_then(|v| v.as_bool())
+                .unwrap_or(false);
             let expires_in = cl.and_then(|c| c.get("expiresIn")).and_then(|v| v.as_i64());
-            let device = data.get("deviceVerified").and_then(|v| v.as_bool()).unwrap_or(false);
+            let device = data
+                .get("deviceVerified")
+                .and_then(|v| v.as_bool())
+                .unwrap_or(false);
 
             let (icon, headline) = match rec {
                 "proceed" => (color::success_indicator().to_string(), "cleared — no challenge, proceed"),
@@ -243,7 +258,10 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
                 _ => (color::cyan("•").to_string(), "unknown"),
             };
             println!("{} {}", icon, headline);
-            println!("  challenged:     {}", if challenged { "yes" } else { "no" });
+            println!(
+                "  challenged:     {}",
+                if challenged { "yes" } else { "no" }
+            );
             let cl_desc = if !present {
                 "absent".to_string()
             } else if expired {
@@ -254,7 +272,14 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
                 "present (session)".to_string()
             };
             println!("  cf_clearance:   {}", cl_desc);
-            println!("  device trusted: {}", if device { "yes (CF_VERIFIED_DEVICE)" } else { "no" });
+            println!(
+                "  device trusted: {}",
+                if device {
+                    "yes (CF_VERIFIED_DEVICE)"
+                } else {
+                    "no"
+                }
+            );
             return;
         }
 
@@ -382,7 +407,11 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
                 let count = list.len();
                 println!(
                     "{}",
-                    color::bold(&format!("{} frame{}", count, if count == 1 { "" } else { "s" }))
+                    color::bold(&format!(
+                        "{} frame{}",
+                        count,
+                        if count == 1 { "" } else { "s" }
+                    ))
                 );
                 for f in list {
                     let idx = f.get("index").and_then(|v| v.as_i64()).unwrap_or(0);

package.json

@@ -1,6 +1,6 @@
 {
   "name": "chrome-use",
-  "version": "1.5.13",
+  "version": "1.5.15",
   "description": "chrome-use — drive your real, logged-in Chrome from any AI agent, stealth by default",
   "type": "module",
   "packageManager": "pnpm@11.1.3",