chore(release): 1.5.1 — frame-aware text extraction (get text --all-frames/--main, frames; #27) + ab-connect 0.4.9 targetId recovery (#24)

On listing/marketplace pages (Yahoo Auctions, Rakuten, Mercari shops) the
seller's description lives in a child frame or under a related-items sidebar,
so 'get text body' returned only header/nav boilerplate.

- get text --all-frames: aggregate visible text across every reachable frame.
  Same-process child frames are read via Page.createIsolatedWorld; OOPIFs via
  their auto-attached debugger session (iframe_sessions). Each non-top frame is
  labelled with a '----- frame [kind] url -----' separator.
- get text --main: readability-lite — prefer the densest <main>/<article>
  region over the whole body, dropping global header/nav/footer chrome.
- frames: enumerate frames (kind + url + per-frame text length) so an agent can
  see where a page's text actually lives and pick the right read.

Verified live: inline srcdoc frame text aggregated through --all-frames; Yahoo
Auctions <main> (2881 chars) extracted via --main, stripping the Yahoo header.

.github/workflows/release-binaries.yml

@@ -147,16 +147,24 @@ jobs:
           git fetch --tags --force --quiet origin 2>/dev/null || true
           TAG="${{ github.event.inputs.tag || github.ref_name }}"
           PREV="$(git describe --tags --abbrev=0 "${TAG}^" 2>/dev/null || true)"
+          RANGE="${TAG}"
+          [ -n "$PREV" ] && RANGE="${PREV}..${TAG}"
+          # Group commit subjects by conventional-commit type so the notes are
+          # scannable ("what's new / what's fixed") instead of a flat dev log.
+          LOG="$(git log "$RANGE" --no-merges --pretty='%s' | grep -v '^chore(release)' || true)"
+          section() { # $1=header  $2=grep-pattern
+            local body; body="$(printf '%s\n' "$LOG" | grep -E "$2" | sed 's/^/- /')"
+            [ -n "$body" ] && { printf '\n### %s\n%s\n' "$1" "$body"; }
+          }
           {
             echo "notes<<__NOTES_EOF__"
             echo "## What changed"
-            echo ""
+            section "✨ Features" '^feat'
+            section "🐛 Fixes" '^fix'
+            section "🔧 Other" '^(perf|refactor|docs|build|ci|test|style|revert)'
             if [ -n "$PREV" ]; then
-              git log "${PREV}..${TAG}" --no-merges --pretty='- %s' | grep -v '^- chore(release)' || true
               echo ""
               echo "**Full changelog**: https://github.com/${{ github.repository }}/compare/${PREV}...${TAG}"
-            else
-              git log "${TAG}" --no-merges --pretty='- %s' | grep -v '^- chore(release)' || true
             fi
             echo "__NOTES_EOF__"
           } >> "$GITHUB_OUTPUT"

cli/Cargo.lock

@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrome-use"
-version = "1.4.1"
+version = "1.5.1"
 dependencies = [
  "aes",
  "aes-gcm",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "chrome-use"
-version = "1.4.1"
+version = "1.5.1"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/commands.rs

@@ -424,6 +424,9 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
         // === Core Actions ===
         "click" => {
             let new_tab = rest.contains(&"--new-tab");
+            // `--follow`: if the click opens a new tab, switch the active tab to
+            // it (default reports the opened tab but stays put) (issue #24-A).
+            let follow = rest.contains(&"--follow");
             // Coordinate click as a first-class form (issue #8.4): when the only
             // handle is a pixel position, no element/selector is needed.
             //   click <x> <y>          e.g. click 449 320
@@ -432,23 +435,27 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
             let coord_args: Vec<&str> = rest
                 .iter()
                 .copied()
-                .filter(|a| *a != "--new-tab" && *a != "--coords")
+                .filter(|a| !a.starts_with("--"))
                 .collect();
             if let Some((x, y)) = parse_coords(&coord_args) {
                 return Ok(json!({ "id": id, "action": "click", "x": x, "y": y }));
             }
             let sel = rest
                 .iter()
-                .find(|arg| **arg != "--new-tab")
+                .find(|arg| !arg.starts_with("--"))
                 .ok_or_else(|| ParseError::MissingArguments {
                     context: "click".to_string(),
-                    usage: "click <selector> | click <x> <y> | click --coords <x>,<y> [--new-tab]",
+                    usage:
+                        "click <selector> | click <x> <y> | click --coords <x>,<y> [--new-tab] [--follow]",
                 })?;
+            let mut cmd = json!({ "id": id, "action": "click", "selector": sel });
             if new_tab {
-                Ok(json!({ "id": id, "action": "click", "selector": sel, "newTab": true }))
+                cmd["newTab"] = json!(true);
-            } else {
-                Ok(json!({ "id": id, "action": "click", "selector": sel }))
             }
+            if follow {
+                cmd["follow"] = json!(true);
+            }
+            Ok(cmd)
         }
         "dblclick" => {
             let sel = rest.first().ok_or_else(|| ParseError::MissingArguments {
@@ -583,11 +590,27 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
 
         // === Keyboard ===
         "press" | "key" => {
-            let key = rest.first().ok_or_else(|| ParseError::MissingArguments {
+            let key = rest.iter().find(|a| !a.starts_with("--")).ok_or_else(|| {
-                context: "press".to_string(),
+                ParseError::MissingArguments {
-                usage: "press <key>",
+                    context: "press".to_string(),
+                    usage: "press <key> [--hold <ms>]",
+                }
             })?;
-            Ok(json!({ "id": id, "action": "press", "key": key }))
+            let mut c = json!({ "id": id, "action": "press", "key": key });
+            // `--hold <ms>`: hold the key down for <ms> then release, timed inside
+            // the daemon (one round-trip, no shell-sleep jitter) — for games and
+            // hold-to-charge where keydown+sleep+keyup over 3 round-trips is too
+            // imprecise.
+            if let Some(i) = rest.iter().position(|a| *a == "--hold") {
+                let ms = rest.get(i + 1).and_then(|s| s.parse::<u64>().ok()).ok_or(
+                    ParseError::MissingArguments {
+                        context: "press --hold".to_string(),
+                        usage: "press <key> --hold <ms>",
+                    },
+                )?;
+                c["hold"] = json!(ms);
+            }
+            Ok(c)
         }
         "keydown" => {
             let key = rest.first().ok_or_else(|| ParseError::MissingArguments {
@@ -1003,7 +1026,22 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
         }
 
         // === Close ===
-        "close" | "quit" | "exit" => Ok(json!({ "id": id, "action": "close" })),
+        "close" | "quit" | "exit" => {
+            // `close <tab>` closes only that tab (and the output says "Tab
+            // closed"); bare `close` closes the browser/session. `close --all` is
+            // intercepted earlier in the dispatcher. Previously `close t12` still
+            // ran a browser close and alarmingly printed "Browser closed" (#26).
+            if let Some(tab_ref) = rest.iter().find(|a| !a.starts_with("--")) {
+                Ok(json!({ "id": id, "action": "tab_close", "tabId": tab_ref }))
+            } else {
+                Ok(json!({ "id": id, "action": "close" }))
+            }
+        }
+
+        // The active tab's stable handle — `targetId` survives cross-process
+        // navigation and is reusable across sessions, so an agent can hold it
+        // instead of re-deriving "which tab is live" from `tabs` each step (#26).
+        "current" => Ok(json!({ "id": id, "action": "current" })),
 
         // === Inspect ===
         "inspect" => Ok(json!({ "id": id, "action": "inspect" })),
@@ -1258,6 +1296,11 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
         // === Get ===
         "get" => parse_get(&rest, &id),
 
+        // List every frame the session can reach (top + same-process child
+        // frames + out-of-process iframes), with a text-length per frame so you
+        // can see where a listing's description actually lives (issue #27).
+        "frames" => Ok(json!({ "id": id, "action": "frames" })),
+
         // Top-level shortcuts for `get <x>` status reads — users naturally type
         // `chrome-use url` / `cdp-url` / `title` without the `get` prefix
         // (and expect `cdp-url`/`cdp_url` to work interchangeably).
@@ -1559,11 +1602,16 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
                     }
                     Ok(cmd)
                 }
-                Some(tab_ref) => Ok(json!({
+                Some(tab_ref) => {
-                    "id": id,
+                    // `tab <ref> --activate` (alias `--front`) switches to the tab
-                    "action": "tab_switch",
+                    // AND raises it to the foreground — for handing a specific tab
-                    "tabId": tab_ref,
+                    // to the human (SMS code, captcha) (issue #24-C).
-                })),
+                    let mut cmd = json!({ "id": id, "action": "tab_switch", "tabId": tab_ref });
+                    if rest.iter().any(|a| *a == "--activate" || *a == "--front") {
+                        cmd["activate"] = json!(true);
+                    }
+                    Ok(cmd)
+                }
                 None => {
                     let mut cmd = json!({ "id": id, "action": "tab_list" });
                     if full {
@@ -2345,10 +2393,32 @@ fn parse_get(rest: &[&str], id: &str) -> Result<Value, ParseError> {
 
     match rest.first().copied() {
         Some("text") => {
-            let sel = rest.get(1).ok_or_else(|| ParseError::MissingArguments {
+            // `get text --all-frames` aggregates visible text across every
-                context: "get text".to_string(),
+            // frame, including out-of-process iframes invisible to the top
-                usage: "get text <selector>",
+            // document (issue #27). The selector is ignored in this mode.
-            })?;
+            let all_frames = rest[1..]
+                .iter()
+                .any(|a| matches!(*a, "--all-frames" | "--frames" | "-a"));
+            if all_frames {
+                return Ok(json!({ "id": id, "action": "gettext", "allFrames": true }));
+            }
+            // `get text --main` returns the main-content region (readability),
+            // skipping header/nav/footer/sidebar boilerplate (issue #27).
+            let main = rest[1..]
+                .iter()
+                .any(|a| matches!(*a, "--main" | "--readable" | "-m"));
+            if main {
+                return Ok(json!({ "id": id, "action": "gettext", "main": true }));
+            }
+            // `get text` with no selector returns the whole page's text (body) —
+            // a common convenience; previously it errored without a selector
+            // (issue #24-D).
+            let sel = rest
+                .iter()
+                .skip(1)
+                .find(|a| !a.starts_with("--"))
+                .copied()
+                .unwrap_or("body");
             Ok(json!({ "id": id, "action": "gettext", "selector": sel }))
         }
         Some("html") => {
@@ -3581,6 +3651,22 @@ mod tests {
         assert_eq!(cmd["url"], "https://example.com");
     }
 
+    #[test]
+    fn test_press_plain_and_hold() {
+        let cmd = parse_command(&args("press d"), &default_flags()).unwrap();
+        assert_eq!(cmd["action"], "press");
+        assert_eq!(cmd["key"], "d");
+        assert!(cmd.get("hold").is_none());
+
+        let held = parse_command(&args("press d --hold 800"), &default_flags()).unwrap();
+        assert_eq!(held["key"], "d");
+        assert_eq!(held["hold"], 800);
+
+        // Missing/invalid duration is an error, not a silent no-hold.
+        assert!(parse_command(&args("press d --hold"), &default_flags()).is_err());
+        assert!(parse_command(&args("press d --hold abc"), &default_flags()).is_err());
+    }
+
     #[test]
     fn test_navigate_reuse_tab_flag() {
         let cmd = parse_command(
@@ -3747,6 +3833,21 @@ mod tests {
         assert!(cmd.get("x").is_none());
     }
 
+    #[test]
+    fn test_click_follow_flag() {
+        // `--follow` sets the flag; the selector is still found even with the flag
+        // before it (issue #24-A).
+        let cmd = parse_command(&args("click @e5 --follow"), &default_flags()).unwrap();
+        assert_eq!(cmd["selector"], "@e5");
+        assert_eq!(cmd["follow"], true);
+        let cmd2 = parse_command(&args("click --follow @e5"), &default_flags()).unwrap();
+        assert_eq!(cmd2["selector"], "@e5");
+        assert_eq!(cmd2["follow"], true);
+        // Absent by default.
+        let plain = parse_command(&args("click @e5"), &default_flags()).unwrap();
+        assert!(plain.get("follow").is_none());
+    }
+
     #[test]
     fn test_tabs_alias_lists() {
         assert_eq!(
@@ -3955,6 +4056,28 @@ mod tests {
         assert_eq!(cmd["tabId"], "docs");
     }
 
+    #[test]
+    fn test_close_tab_vs_browser() {
+        // `close <tab>` closes that tab (says "Tab closed"); bare `close` closes
+        // the browser (#26).
+        let tab = parse_command(&args("close t12"), &default_flags()).unwrap();
+        assert_eq!(tab["action"], "tab_close");
+        assert_eq!(tab["tabId"], "t12");
+        let browser = parse_command(&args("close"), &default_flags()).unwrap();
+        assert_eq!(browser["action"], "close");
+        // `quit`/`exit` aliases still browser-close.
+        assert_eq!(
+            parse_command(&args("quit"), &default_flags()).unwrap()["action"],
+            "close"
+        );
+    }
+
+    #[test]
+    fn test_current_command() {
+        let cmd = parse_command(&args("current"), &default_flags()).unwrap();
+        assert_eq!(cmd["action"], "current");
+    }
+
     #[test]
     fn test_tab_sends_string_tab_id() {
         let cmd = parse_command(&args("tab t2"), &default_flags()).unwrap();
@@ -4654,12 +4777,65 @@ mod tests {
     }
 
     #[test]
-    fn test_get_text_missing_selector() {
+    fn test_get_text_defaults_to_body() {
-        let result = parse_command(&args("get text"), &default_flags());
+        // `get text` with no selector now returns the whole page (body) instead
-        assert!(result.is_err());
+        // of erroring (issue #24-D).
-        let err = result.unwrap_err();
+        let cmd = parse_command(&args("get text"), &default_flags()).unwrap();
-        assert!(matches!(err, ParseError::MissingArguments { .. }));
+        assert_eq!(cmd["action"], "gettext");
-        assert!(err.format().contains("get text"));
+        assert_eq!(cmd["selector"], "body");
+        // An explicit selector still wins.
+        let cmd2 = parse_command(&args("get text h1"), &default_flags()).unwrap();
+        assert_eq!(cmd2["selector"], "h1");
+    }
+
+    #[test]
+    fn test_get_text_all_frames() {
+        // `--all-frames` switches to whole-page, cross-frame aggregation and
+        // drops the selector (issue #27).
+        for variant in ["get text --all-frames", "get text --frames", "text -a"] {
+            let cmd = parse_command(&args(variant), &default_flags()).unwrap();
+            assert_eq!(cmd["action"], "gettext", "{variant}");
+            assert_eq!(cmd["allFrames"], true, "{variant}");
+            assert!(cmd.get("selector").is_none(), "{variant}");
+        }
+        // A flag mixed with a selector still triggers all-frames.
+        let cmd = parse_command(&args("get text body --all-frames"), &default_flags()).unwrap();
+        assert_eq!(cmd["allFrames"], true);
+        // Without the flag, a leading flag-like token is skipped for the selector.
+        let cmd = parse_command(&args("get text main"), &default_flags()).unwrap();
+        assert_eq!(cmd["selector"], "main");
+        assert!(cmd.get("allFrames").is_none());
+    }
+
+    #[test]
+    fn test_frames_command() {
+        let cmd = parse_command(&args("frames"), &default_flags()).unwrap();
+        assert_eq!(cmd["action"], "frames");
+    }
+
+    #[test]
+    fn test_get_text_main() {
+        for variant in ["get text --main", "get text --readable", "text -m"] {
+            let cmd = parse_command(&args(variant), &default_flags()).unwrap();
+            assert_eq!(cmd["action"], "gettext", "{variant}");
+            assert_eq!(cmd["main"], true, "{variant}");
+            assert!(cmd.get("selector").is_none(), "{variant}");
+        }
+    }
+
+    #[test]
+    fn test_tab_activate_flag() {
+        let plain = parse_command(&args("tab t3"), &default_flags()).unwrap();
+        assert_eq!(plain["action"], "tab_switch");
+        assert!(plain.get("activate").is_none());
+
+        let act = parse_command(&args("tab t3 --activate"), &default_flags()).unwrap();
+        assert_eq!(act["action"], "tab_switch");
+        assert_eq!(act["tabId"], "t3");
+        assert_eq!(act["activate"], true);
+        // `--front` alias.
+        let front = parse_command(&args("tab t3 --front"), &default_flags()).unwrap();
+        assert_eq!(front["activate"], true);
     }
 
     // === Protocol alignment tests ===

cli/src/native/actions.rs

@@ -1332,6 +1332,7 @@ pub async fn execute_command(cmd: &Value, state: &mut DaemonState) -> Value {
         "uncheck" => handle_uncheck(cmd, state).await,
         "wait" => handle_wait(cmd, state).await,
         "gettext" => handle_gettext(cmd, state).await,
+        "frames" => handle_frames(cmd, state).await,
         "getattribute" => handle_getattribute(cmd, state).await,
         "isvisible" => handle_isvisible(cmd, state).await,
         "isenabled" => handle_isenabled(cmd, state).await,
@@ -1395,6 +1396,7 @@ pub async fn execute_command(cmd: &Value, state: &mut DaemonState) -> Value {
         "count" => handle_count(cmd, state).await,
         "styles" => handle_styles(cmd, state).await,
         "bringtofront" => handle_bringtofront(state).await,
+        "current" => handle_current(state).await,
         "timezone" => handle_timezone(cmd, state).await,
         "locale" => handle_locale(cmd, state).await,
         "geolocation" => handle_geolocation(cmd, state).await,
@@ -3116,6 +3118,15 @@ async fn handle_click(cmd: &Value, state: &mut DaemonState) -> Result<Value, Str
 
     let button = cmd.get("button").and_then(|v| v.as_str()).unwrap_or("left");
     let click_count = cmd.get("clickCount").and_then(|v| v.as_i64()).unwrap_or(1) as i32;
+    let follow = cmd.get("follow").and_then(|v| v.as_bool()).unwrap_or(false);
+
+    // Snapshot tracked targets so we can tell if this click opened a NEW tab
+    // (target=_blank link / window.open). On the relay the new tab is discovered
+    // passively and doesn't steal focus (#7/#8.1), so without surfacing it the
+    // post-click snapshot shows the OLD page and looks like the click failed
+    // (issue #24-A).
+    let before: std::collections::HashSet<String> =
+        mgr.pages_list().into_iter().map(|p| p.target_id).collect();
 
     interaction::click(
         &mgr.client,
@@ -3128,7 +3139,26 @@ async fn handle_click(cmd: &Value, state: &mut DaemonState) -> Result<Value, Str
     )
     .await?;
 
-    Ok(json!({ "clicked": selector }))
+    // Give a just-opened tab a moment to register, then look for it.
+    let mgr = state.browser.as_mut().ok_or("Browser not launched")?;
+    tokio::time::sleep(std::time::Duration::from_millis(150)).await;
+    let opened = mgr.adopt_newly_opened(&before).await;
+
+    let mut out = json!({ "clicked": selector });
+    if let Some(page) = opened {
+        let tab_id = super::browser::format_tab_id(page.tab_id);
+        out["openedTab"] = json!({ "tabId": tab_id, "url": page.url, "title": page.title });
+        // `--follow`: switch the active tab to the newly-opened one (default is
+        // to report it but stay put, so multi-tab flows aren't hijacked).
+        if follow {
+            state.ref_map.clear();
+            state.iframe_sessions.clear();
+            state.active_frame_id = None;
+            let _ = mgr.tab_switch_by_id(page.tab_id).await;
+            out["followed"] = json!(true);
+        }
+    }
+    Ok(out)
 }
 
 async fn handle_dblclick(cmd: &Value, state: &mut DaemonState) -> Result<Value, String> {
@@ -3334,6 +3364,16 @@ async fn handle_press(cmd: &Value, state: &mut DaemonState) -> Result<Value, Str
     // Parse modifier+key chords like "Control+a", "Shift+Enter", "Control+Shift+a"
     let (actual_key, modifiers) = parse_key_chord(key);
 
+    // `--hold <ms>`: keyDown, wait, keyUp — all inside the daemon so the hold
+    // duration is precise (no shell-sleep / round-trip jitter). For games
+    // (hold-to-move/charge) and any press-and-hold interaction.
+    if let Some(ms) = cmd.get("hold").and_then(|v| v.as_u64()) {
+        interaction::dispatch_single_key(&mgr.client, &session_id, &actual_key, "keyDown").await?;
+        tokio::time::sleep(std::time::Duration::from_millis(ms)).await;
+        interaction::dispatch_single_key(&mgr.client, &session_id, &actual_key, "keyUp").await?;
+        return Ok(json!({ "pressed": key, "heldMs": ms }));
+    }
+
     interaction::press_key_with_modifiers(&mgr.client, &session_id, &actual_key, modifiers).await?;
     Ok(json!({ "pressed": key }))
 }
@@ -3555,6 +3595,47 @@ async fn handle_wait(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
 async fn handle_gettext(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();
+
+    // `get text --all-frames` aggregates visible text across every frame the
+    // session can reach — including out-of-process iframes that never show up
+    // in the top document (#27: Yahoo/Rakuten/Mercari listing descriptions).
+    if cmd.get("allFrames").and_then(|v| v.as_bool()) == Some(true) {
+        let frames = super::element::collect_all_frames_text(
+            &mgr.client,
+            &session_id,
+            &state.iframe_sessions,
+        )
+        .await?;
+        let mut combined = String::new();
+        let mut frame_count = 0usize;
+        for f in &frames {
+            let t = f.text.trim();
+            if t.is_empty() {
+                continue;
+            }
+            frame_count += 1;
+            if f.kind != "top" {
+                combined.push_str(&format!("\n\n----- frame [{}] {} -----\n", f.kind, f.url));
+            }
+            combined.push_str(t);
+        }
+        let url = mgr.get_url().await.unwrap_or_default();
+        return Ok(json!({
+            "text": combined,
+            "origin": url,
+            "frames": frame_count,
+            "allFrames": true,
+        }));
+    }
+
+    // `get text --main` returns the page's main-content region (readability-lite),
+    // skipping global header/nav/footer/sidebar boilerplate (#27).
+    if cmd.get("main").and_then(|v| v.as_bool()) == Some(true) {
+        let text = super::element::get_main_content_text(&mgr.client, &session_id).await?;
+        let url = mgr.get_url().await.unwrap_or_default();
+        return Ok(json!({ "text": text, "origin": url, "main": true }));
+    }
+
     let selector = cmd
         .get("selector")
         .and_then(|v| v.as_str())
@@ -3572,6 +3653,32 @@ async fn handle_gettext(cmd: &Value, state: &mut DaemonState) -> Result<Value, S
     Ok(json!({ "text": text, "origin": url }))
 }
 
+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(
+        &mgr.client,
+        &session_id,
+        &state.iframe_sessions,
+    )
+    .await?;
+    let list: Vec<Value> = frames
+        .iter()
+        .enumerate()
+        .map(|(i, f)| {
+            json!({
+                "index": i,
+                "kind": f.kind,
+                "url": f.url,
+                "frameId": f.frame_id,
+                "textLen": f.text.trim().chars().count(),
+            })
+        })
+        .collect();
+    let url = mgr.get_url().await.unwrap_or_default();
+    Ok(json!({ "frames": list, "count": list.len(), "origin": url }))
+}
+
 async fn handle_getattribute(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();
@@ -4456,6 +4563,17 @@ async fn handle_tab_switch(cmd: &Value, state: &mut DaemonState) -> Result<Value
     state.active_frame_id = None;
     let result = mgr.tab_switch_by_id(tab_id).await?;
 
+    // `--activate`: raise this tab to the foreground (the switch made it active;
+    // bring_to_front acts on the active tab) — for handing a specific tab to the
+    // human (issue #24-C). Best-effort; don't fail the switch if it can't.
+    if cmd
+        .get("activate")
+        .and_then(|v| v.as_bool())
+        .unwrap_or(false)
+    {
+        let _ = mgr.bring_to_front().await;
+    }
+
     if let Some(ref server) = state.stream_server {
         if let Ok(dims) = mgr
             .evaluate(
@@ -5284,6 +5402,18 @@ async fn handle_bringtofront(state: &DaemonState) -> Result<Value, String> {
     Ok(json!({ "broughtToFront": true }))
 }
 
+async fn handle_current(state: &mut DaemonState) -> Result<Value, String> {
+    let mgr = state.browser.as_mut().ok_or("Browser not launched")?;
+    // Refresh so `current` reflects the live URL/title even after a cross-process
+    // nav (the relay's cached target_info can lag) (#26).
+    mgr.resync_targets().await.ok();
+    let mut info = mgr.active_page_info().ok_or("No active tab")?;
+    if let Some(obj) = info.as_object_mut() {
+        obj.insert("current".to_string(), json!(true));
+    }
+    Ok(info)
+}
+
 async fn handle_timezone(cmd: &Value, state: &DaemonState) -> Result<Value, String> {
     let mgr = state.browser.as_ref().ok_or("Browser not launched")?;
     let timezone = cmd

cli/src/native/browser.rs

@@ -1263,6 +1263,22 @@ impl BrowserManager {
             .collect()
     }
 
+    /// The active tab's stable handle + current location, for `chrome-use
+    /// current` (#26). `targetId` survives cross-process navigation, so it's the
+    /// handle an agent should hold across a multi-step flow.
+    pub fn active_page_info(&self) -> Option<Value> {
+        let i = self.resolved_active_index();
+        self.pages.get(i).map(|p| {
+            json!({
+                "tabId": format_tab_id(p.tab_id),
+                "targetId": p.target_id,
+                "label": p.label,
+                "url": p.url,
+                "title": p.title,
+            })
+        })
+    }
+
     /// Stable `tab_id` for a page identified by its CDP `targetId`, if tracked.
     /// Lets callers adopt a tab by the cross-session-stable target id.
     pub fn tab_id_for_target(&self, target_id: &str) -> Option<u32> {
@@ -1279,6 +1295,67 @@ impl BrowserManager {
     /// the active tab is preserved, and re-pinned if it was pruned. Powers a live
     /// `tab list` and adopt-by-targetId so a fresh session can reach a stranded,
     /// still-filled tab without reloading it (issue #21).
+    /// Detect targets that appeared since the `before` set (e.g. a click that
+    /// opened a new tab via a `target=_blank` link or `window.open`), attach +
+    /// track each in the background, and return the first newly-opened page.
+    ///
+    /// Lighter than [`resync_targets`] — one `getTargets` and work only on the
+    /// new targets, no whole-tab url/title refresh — so it's cheap enough to run
+    /// after every click. The new tab is added in the background (never steals
+    /// 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> {
+        let result: GetTargetsResult = self
+            .client
+            .send_command_typed("Target.getTargets", &json!({}), None)
+            .await
+            .ok()?;
+        let live: Vec<TargetInfo> = result
+            .target_infos
+            .into_iter()
+            .filter(should_track_target)
+            .collect();
+        let mut opened: Option<PageInfo> = None;
+        for target in &live {
+            if before.contains(&target.target_id)
+                || self.pages.iter().any(|p| p.target_id == target.target_id)
+            {
+                continue;
+            }
+            let attach: AttachToTargetResult = match self
+                .client
+                .send_command_typed(
+                    "Target.attachToTarget",
+                    &AttachToTargetParams {
+                        target_id: target.target_id.clone(),
+                        flatten: true,
+                    },
+                    None,
+                )
+                .await
+            {
+                Ok(r) => r,
+                Err(_) => continue,
+            };
+            let tab_id = self.assign_tab_id();
+            let page = PageInfo {
+                tab_id,
+                label: None,
+                target_id: target.target_id.clone(),
+                session_id: attach.session_id.clone(),
+                url: target.url.clone(),
+                title: target.title.clone(),
+                target_type: target.target_type.clone(),
+            };
+            self.add_background_page(page.clone());
+            let _ = self.enable_domains(&attach.session_id).await;
+            if opened.is_none() {
+                opened = Some(page);
+            }
+        }
+        opened
+    }
+
     pub async fn resync_targets(&mut self) -> Result<(), String> {
         self.client
             .send_command_typed::<_, Value>(

cli/src/native/element.rs

@@ -796,16 +796,43 @@ pub(super) fn extract_ax_string(value: &Option<AXValue>) -> String {
 /// Build a JS expression that finds a DOM element by CSS selector or XPath.
 fn build_find_element_js(selector: &str) -> String {
     if let Some(xpath) = selector.strip_prefix("xpath=") {
-        format!(
+        return format!(
             "document.evaluate({}, document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue",
             serde_json::to_string(xpath).unwrap_or_default()
-        )
+        );
-    } else {
-        format!(
-            "document.querySelector({})",
-            serde_json::to_string(selector).unwrap_or_default()
-        )
     }
+    // Bare string (or explicit `text=`): try CSS first, then fall back to
+    // matching an interactive element by its VISIBLE TEXT. snapshot exposes
+    // buttons/links by their name, so `click "購入手続きへ"` should resolve by
+    // that label — previously it was fed straight to `querySelector` as CSS and
+    // failed as an invalid selector even though the button was right there
+    // (issue #24-B). CSS still wins when it matches, so existing selectors are
+    // unaffected; nested/non-ASCII labels now resolve too.
+    let text_only = selector.strip_prefix("text=");
+    let force_text = text_only.is_some();
+    let sel_json = serde_json::to_string(selector).unwrap_or_default();
+    let want_json = serde_json::to_string(text_only.unwrap_or(selector)).unwrap_or_default();
+    format!(
+        r#"(() => {{
+  const sel = {sel};
+  const css = {force_text} ? null : (() => {{ try {{ return document.querySelector(sel); }} catch (_e) {{ return null; }} }})();
+  if (css) return css;
+  const norm = s => (s == null ? '' : String(s)).replace(/\s+/g, ' ').trim();
+  const w = norm({want}); if (!w) return null;
+  const wl = w.toLowerCase();
+  const interactive = Array.from(document.querySelectorAll(
+    'button,a,[role=button],[role=link],[role=menuitem],[role=tab],[role=option],input[type=submit],input[type=button],input[type=reset],summary,label,[onclick]'));
+  const textOf = e => norm(e.innerText || e.textContent) || norm(e.value) ||
+    norm(e.getAttribute && e.getAttribute('aria-label')) || norm(e.getAttribute && e.getAttribute('title'));
+  let hit = interactive.find(e => textOf(e) === w) || interactive.find(e => textOf(e).toLowerCase().includes(wl));
+  if (hit) return hit;
+  const leaves = Array.from(document.querySelectorAll('*')).filter(e => !e.children.length);
+  return leaves.find(e => norm(e.textContent) === w) || leaves.find(e => norm(e.textContent).toLowerCase().includes(wl)) || null;
+}})()"#,
+        sel = sel_json,
+        want = want_json,
+        force_text = force_text
+    )
 }
 
 /// Build a JS expression that counts matching DOM elements by CSS selector or XPath.
@@ -948,6 +975,200 @@ pub async fn get_element_text(
         .unwrap_or_default())
 }
 
+/// Text content collected from a single frame of the page.
+#[derive(Debug, Clone)]
+pub struct FrameText {
+    pub frame_id: String,
+    pub url: String,
+    /// "top" | "inline" (same-process child frame) | "oopif" (out-of-process).
+    pub kind: &'static str,
+    pub text: String,
+}
+
+// The expression we run in every frame to read its visible text. innerText
+// honors CSS visibility (skips display:none), textContent is the fallback.
+const FRAME_INNERTEXT_JS: &str = "(function(){try{var b=document.body||document.documentElement;return b?(b.innerText||b.textContent||''):'';}catch(e){return '';}})()";
+
+async fn eval_text_default(client: &CdpClient, session_id: &str) -> String {
+    let res = client
+        .send_command(
+            "Runtime.evaluate",
+            Some(serde_json::json!({
+                "expression": FRAME_INNERTEXT_JS,
+                "returnByValue": true,
+            })),
+            Some(session_id),
+        )
+        .await;
+    res.ok()
+        .and_then(|v| v.get("result").and_then(|r| r.get("value")).cloned())
+        .and_then(|v| v.as_str().map(|s| s.to_string()))
+        .unwrap_or_default()
+}
+
+// Same-process child frames share the top renderer but live in their own
+// execution context. Page.createIsolatedWorld hands us a context id bound to
+// that frame so Runtime.evaluate reads the child document, not the parent.
+async fn eval_text_in_frame(client: &CdpClient, session_id: &str, frame_id: &str) -> String {
+    let ctx = client
+        .send_command(
+            "Page.createIsolatedWorld",
+            Some(serde_json::json!({ "frameId": frame_id, "worldName": "chrome_use_text" })),
+            Some(session_id),
+        )
+        .await
+        .ok()
+        .and_then(|v| v.get("executionContextId").and_then(|c| c.as_i64()));
+    let Some(ctx_id) = ctx else { return String::new() };
+    let res = client
+        .send_command(
+            "Runtime.evaluate",
+            Some(serde_json::json!({
+                "expression": FRAME_INNERTEXT_JS,
+                "returnByValue": true,
+                "contextId": ctx_id,
+            })),
+            Some(session_id),
+        )
+        .await;
+    res.ok()
+        .and_then(|v| v.get("result").and_then(|r| r.get("value")).cloned())
+        .and_then(|v| v.as_str().map(|s| s.to_string()))
+        .unwrap_or_default()
+}
+
+fn flatten_frame_tree(node: &Value, is_top: bool, out: &mut Vec<(String, String, bool)>) {
+    if let Some(frame) = node.get("frame") {
+        if let Some(id) = frame.get("id").and_then(|v| v.as_str()) {
+            let url = frame
+                .get("url")
+                .and_then(|v| v.as_str())
+                .unwrap_or("")
+                .to_string();
+            out.push((id.to_string(), url, is_top));
+        }
+    }
+    if let Some(children) = node.get("childFrames").and_then(|v| v.as_array()) {
+        for child in children {
+            flatten_frame_tree(child, false, out);
+        }
+    }
+}
+
+/// Collect visible text from every frame reachable in the active session,
+/// including out-of-process iframes (which never appear in the top frame's
+/// `Page.getFrameTree` and so are invisible to `document.body.innerText`).
+///
+/// Same-process child frames are read through `Page.createIsolatedWorld`;
+/// OOPIFs are read through their own auto-attached debugger session
+/// (`iframe_sessions`, keyed by frameId == targetId). This is the engine
+/// behind `get text --all-frames` and `chrome-use frames` — the fix for
+/// listing/marketplace pages whose description lives in a child frame (#27).
+pub async fn collect_all_frames_text(
+    client: &CdpClient,
+    top_session: &str,
+    iframe_sessions: &HashMap<String, String>,
+) -> Result<Vec<FrameText>, String> {
+    let mut out: Vec<FrameText> = Vec::new();
+    let mut seen: std::collections::HashSet<String> = std::collections::HashSet::new();
+
+    // 1. Top session: the top frame plus its same-process descendants. OOPIF
+    //    frames that happen to surface here are skipped — they're read via
+    //    their dedicated session in step 2 (cross-process isolated worlds fail).
+    let tree = client
+        .send_command_no_params("Page.getFrameTree", Some(top_session))
+        .await?;
+    let mut frames: Vec<(String, String, bool)> = Vec::new();
+    flatten_frame_tree(&tree["frameTree"], true, &mut frames);
+    for (fid, url, is_top) in frames {
+        if iframe_sessions.contains_key(&fid) {
+            continue;
+        }
+        if !seen.insert(fid.clone()) {
+            continue;
+        }
+        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)
+        };
+        out.push(FrameText {
+            frame_id: fid,
+            url,
+            kind,
+            text,
+        });
+    }
+
+    // 2. Each out-of-process iframe, read through its own session.
+    for (fid, sid) in iframe_sessions {
+        if !seen.insert(fid.clone()) {
+            continue;
+        }
+        let url = client
+            .send_command_no_params("Page.getFrameTree", Some(sid))
+            .await
+            .ok()
+            .and_then(|t| {
+                t.get("frameTree")
+                    .and_then(|ft| ft.get("frame"))
+                    .and_then(|f| f.get("url"))
+                    .and_then(|v| v.as_str())
+                    .map(|s| s.to_string())
+            })
+            .unwrap_or_default();
+        let text = eval_text_default(client, sid).await;
+        out.push(FrameText {
+            frame_id: fid.clone(),
+            url,
+            kind: "oopif",
+            text,
+        });
+    }
+
+    Ok(out)
+}
+
+// Readability-lite: prefer the page's semantic main-content region over the
+// whole body so global header/nav/footer chrome (and, on many listing pages,
+// the "related items" sidebar) doesn't drown out the actual content. Runs on
+// the live, rendered tree (innerText needs layout — a detached clone returns
+// empty), so we pick the densest <main>/<article> region rather than cloning
+// and stripping. Falls back to <body> when no substantial main region exists.
+const MAIN_CONTENT_JS: &str = r#"(function(){
+  function txt(el){try{return (el.innerText||'').trim();}catch(e){return '';}}
+  var sels=['main','[role=main]','article','#main','#contents','#l-content'];
+  var best=null,bestLen=0;
+  for(var i=0;i<sels.length;i++){
+    var els=document.querySelectorAll(sels[i]);
+    for(var j=0;j<els.length;j++){var l=txt(els[j]).length;if(l>bestLen){bestLen=l;best=els[j];}}
+  }
+  if(best&&bestLen>200)return txt(best);
+  return txt(document.body);
+})()"#;
+
+/// Extract the page's main-content text (readability-lite), preferring a
+/// semantic `<main>`/`<article>` region over the full body. Used by
+/// `get text --main` to avoid header/nav/sidebar boilerplate (#27).
+pub async fn get_main_content_text(client: &CdpClient, session_id: &str) -> Result<String, String> {
+    let res = client
+        .send_command(
+            "Runtime.evaluate",
+            Some(serde_json::json!({
+                "expression": MAIN_CONTENT_JS,
+                "returnByValue": true,
+            })),
+            Some(session_id),
+        )
+        .await?;
+    Ok(res
+        .get("result")
+        .and_then(|r| r.get("value"))
+        .and_then(|v| v.as_str())
+        .unwrap_or_default()
+        .to_string())
+}
+
 pub async fn get_element_attribute(
     client: &CdpClient,
     session_id: &str,
@@ -1452,10 +1673,30 @@ mod tests {
     #[test]
     fn test_build_selector_js_css() {
         let js = build_selector_js("#submit-btn");
-        assert!(js.contains("document.querySelector(\"#submit-btn\")"));
+        // CSS is now tried via a `sel` variable, with a visible-text fallback
+        // appended (issue #24-B). It must still use querySelector (not xpath).
+        assert!(js.contains("const sel = \"#submit-btn\""));
+        assert!(js.contains("document.querySelector(sel)"));
         assert!(!js.contains("document.evaluate"));
     }
 
+    #[test]
+    fn test_build_find_element_js_text_fallback() {
+        // A bare label gets a text-matching fallback so `click "購入手続きへ"`
+        // resolves by visible text, not just CSS (issue #24-B).
+        let js = build_find_element_js("購入手続きへ");
+        assert!(js.contains("購入手続きへ"));
+        assert!(js.contains("interactive")); // the text-match branch
+        assert!(js.contains("textOf"));
+        // `text=` forces the text path (skips CSS).
+        let forced = build_find_element_js("text=Buy now");
+        assert!(forced.contains("true ? null")); // force_text => css skipped
+                                                 // xpath is unchanged.
+        let xp = build_find_element_js("xpath=//button");
+        assert!(xp.contains("document.evaluate"));
+        assert!(!xp.contains("interactive"));
+    }
+
     #[test]
     fn test_build_selector_js_xpath() {
         let js = build_selector_js("xpath=//button[@id='ok']");

cli/src/native/interaction.rs

@@ -306,32 +306,50 @@ pub async fn fill(
     )
     .await?;
 
-    // Focus the element
+    // Emulate a real edit so framework-controlled inputs (React/Vue) and
-    client
+    // site-side listeners actually see the change (issue #25): the old path set
-        .send_command_typed::<_, Value>(
+    // `this.value` directly and used Input.insertText, which left React's
-            "Runtime.callFunctionOn",
+    // internal value-tracker out of sync and never fired change/blur — so
-            &CallFunctionOnParams {
+    // dependent logic (e.g. Mercari's postal-code → 都道府県 autocomplete) never
-                function_declaration: "function() { this.focus(); }".to_string(),
+    // ran even though the value was visible. Set the value through the element's
-                object_id: Some(object_id.clone()),
+    // PROTOTYPE setter (which React's _valueTracker hooks), then dispatch
-                arguments: None,
+    // input → change → blur/focusout. `type <sel> <text>` remains for sites that
-                return_by_value: Some(true),
+    // need per-keystroke events.
-                await_promise: Some(false),
+    let fill_js = format!(
-            },
+        r#"function() {{
-            Some(&effective_session_id),
+            const el = this;
-        )
+            const v = {val};
-        .await?;
+            try {{ el.focus(); }} catch (e) {{}}
+            const tag = el.tagName;
+            const fire = (type, ctor) => el.dispatchEvent(new (ctor || Event)(type, {{ bubbles: true }}));
+            if (tag === 'SELECT') {{
+                el.value = v; fire('input'); fire('change'); return true;
+            }}
+            if (el.isContentEditable) {{
+                el.textContent = v; fire('input', window.InputEvent || Event); fire('change');
+                try {{ el.blur(); }} catch (e) {{}} fire('focusout'); return true;
+            }}
+            const proto = tag === 'TEXTAREA' ? window.HTMLTextAreaElement.prototype
+                                             : window.HTMLInputElement.prototype;
+            const desc = Object.getOwnPropertyDescriptor(proto, 'value');
+            const set = desc && desc.set ? (x) => desc.set.call(el, x) : (x) => {{ el.value = x; }};
+            set('');                                   // reset the framework tracker
+            fire('input', window.InputEvent || Event);
+            set(v);                                    // native setter → React/Vue registers
+            fire('input', window.InputEvent || Event);
+            fire('change');
+            try {{ el.blur(); }} catch (e) {{}}
+            fire('focusout');                          // blur-triggered lookups/validation
+            return true;
+        }}"#,
+        val = serde_json::to_string(value).unwrap_or_default()
+    );
 
-    // Select all + delete to clear
     client
         .send_command_typed::<_, Value>(
             "Runtime.callFunctionOn",
             &CallFunctionOnParams {
-                function_declaration: r#"function() {
+                function_declaration: fill_js,
-                    this.select && this.select();
-                    this.value = '';
-                    this.dispatchEvent(new Event('input', { bubbles: true }));
-                }"#
-                .to_string(),
                 object_id: Some(object_id),
                 arguments: None,
                 return_by_value: Some(true),
@@ -341,17 +359,6 @@ pub async fn fill(
         )
         .await?;
 
-    // Insert text (keyboard input dispatched at page level, use parent session_id)
-    client
-        .send_command_typed::<_, Value>(
-            "Input.insertText",
-            &InsertTextParams {
-                text: value.to_string(),
-            },
-            Some(session_id),
-        )
-        .await?;
-
     Ok(())
 }
 

cli/src/output.rs

@@ -186,6 +186,44 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
     }
 
     if let Some(data) = &resp.data {
+        // A click that opened a new tab: surface it so the agent doesn't read the
+        // unchanged old page as a failed click (issue #24-A).
+        if let Some(opened) = data.get("openedTab") {
+            let tid = opened.get("tabId").and_then(|v| v.as_str()).unwrap_or("?");
+            let url = opened.get("url").and_then(|v| v.as_str()).unwrap_or("");
+            let followed = data
+                .get("followed")
+                .and_then(|v| v.as_bool())
+                .unwrap_or(false);
+            let verb = if followed {
+                "switched to new tab"
+            } else {
+                "opened new tab"
+            };
+            eprintln!(
+                "{} {} [{}] {}",
+                color::cyan("→"),
+                verb,
+                tid,
+                color::dim(url)
+            );
+        }
+
+        // `current`: the active tab's stable handle (#26).
+        if data
+            .get("current")
+            .and_then(|v| v.as_bool())
+            .unwrap_or(false)
+        {
+            let tid = data.get("tabId").and_then(|v| v.as_str()).unwrap_or("?");
+            let title = data.get("title").and_then(|v| v.as_str()).unwrap_or("");
+            let url = data.get("url").and_then(|v| v.as_str()).unwrap_or("");
+            let target = data.get("targetId").and_then(|v| v.as_str()).unwrap_or("");
+            println!("{} [{}] {} - {}", color::cyan("→"), tid, title, url);
+            println!("      {}", color::dim(&format!("target: {}", target)));
+            return;
+        }
+
         // Dialog status response
         if action == Some("dialog") {
             if let Some(has_dialog) = data.get("hasDialog").and_then(|v| v.as_bool()) {
@@ -304,6 +342,34 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
             }
             return;
         }
+        // Frame list (`chrome-use frames`)
+        if action == Some("frames") {
+            if let Some(list) = data.get("frames").and_then(|v| v.as_array()) {
+                let count = list.len();
+                println!(
+                    "{}",
+                    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);
+                    let kind = f.get("kind").and_then(|v| v.as_str()).unwrap_or("?");
+                    let url = f.get("url").and_then(|v| v.as_str()).unwrap_or("");
+                    let len = f.get("textLen").and_then(|v| v.as_i64()).unwrap_or(0);
+                    println!(
+                        "  [{}] {:<6} {} chars  {}",
+                        idx,
+                        kind,
+                        len,
+                        color::dim(if url.is_empty() { "(about:blank)" } else { url })
+                    );
+                }
+                eprintln!(
+                    "{}",
+                    color::dim("read everything with: chrome-use get text --all-frames")
+                );
+            }
+            return;
+        }
         // Title
         if let Some(title) = data.get("title").and_then(|v| v.as_str()) {
             println!("{}", title);
@@ -1892,6 +1958,8 @@ Retrieves various types of information from elements or the page.
 
 Subcommands:
   text <selector>            Get text content of element
+  text --all-frames          Aggregate text across ALL frames (incl. iframes)
+  text --main                Main-content text only (skip nav/header/sidebar)
   html <selector>            Get inner HTML of element
   value <selector>           Get value of input element
   attr <selector> <name>     Get attribute value
@@ -1908,6 +1976,9 @@ Global Options:
 
 Examples:
   chrome-use get text @e1
+  chrome-use get text --all-frames     # read iframed content (listing pages)
+  chrome-use get text --main           # main content, no nav/sidebar boilerplate
+  chrome-use frames                    # list frames + where the text lives
   chrome-use get html "#content"
   chrome-use get value "#email-input"
   chrome-use get attr "#link" href
@@ -2778,6 +2849,20 @@ Notes:
   - Streaming is always enabled. Set AGENT_BROWSER_STREAM_PORT to bind to a
     specific port instead of the default OS-assigned port.
 
+The WS is BIDIRECTIONAL — the high-throughput way to drive a live/real-time page
+(games, canvas apps) instead of one screenshot + one CLI call per action:
+  - Server -> client (JSON text frames):
+      {"type":"frame","data":"<base64 jpeg>"}   live screencast (~60fps)
+      plus status / tabs messages.
+  - Client -> server (send JSON text):
+      {"type":"input_keyboard","eventType":"keyDown|keyUp","key":" ","code":"Space",
+       "windowsVirtualKeyCode":32}
+      {"type":"input_mouse","eventType":"mousePressed|mouseReleased|mouseMoved",
+       "x":640,"y":360,"button":"left","clickCount":1}
+      {"type":"input_touch","eventType":"touchStart|touchEnd","touchPoints":[...]}
+  Connect once and run a tight local loop: read frames, send timed input — no
+  per-action process spawn, no round-trip. Works over the extension relay too.
+
 Global Options:
   --json               Output as JSON
   --session <name>     Use specific session
@@ -3070,7 +3155,9 @@ Core Commands:
   dblclick <sel>             Double-click element
   type <sel> <text>          Type into element
   fill <sel> <text>          Clear and fill
-  press <key>                Press key (Enter, Tab, Control+a)
+  press <key> [--hold <ms>]  Press key (Enter, Tab, Control+a). --hold keeps it
+                             down <ms> then releases — precise (in-daemon), for
+                             games/charge: `press d --hold 800`
   keydown <key>              Hold a key down (no auto-release) — for games/shortcuts
   keyup <key>                Release a held key. Pair with keydown to hold-to-move:
                              `keydown d` … `keyup d`
@@ -3101,6 +3188,7 @@ Navigation:
 
 Get Info:  chrome-use get <what> [selector]
   text, html, value, attr <name>, title, url, count, box, styles, cdp-url
+  text --all-frames (cross-frame), text --main (no boilerplate), frames (list)
 
 Check State:  chrome-use is <what> <selector>
   visible, enabled, checked

extensions/ab-connect/background.js

@@ -30,6 +30,16 @@ const tabs = new Map()
 const sessionToTab = new Map()
 /** child (OOPIF/worker) sessionId -> tabId */
 const childSessionToTab = new Map()
+/** sessionId -> CDP targetId, kept ACROSS detach so a dead `cb-tab-<oldTabId>`
+ * session can be recovered by its stable targetId when the cross-process nav
+ * gave the tab a new Chrome tabId (issue #24). Capped to bound memory. */
+const sessionTargets = new Map()
+function rememberSessionTarget(sessionId, targetId) {
+  if (!sessionId || !targetId) return
+  sessionTargets.delete(sessionId)
+  sessionTargets.set(sessionId, targetId)
+  if (sessionTargets.size > 256) sessionTargets.delete(sessionTargets.keys().next().value)
+}
 /** tab-group name -> chrome tabGroups id (best-effort cache) */
 const groupIdByName = new Map()
 
@@ -172,17 +182,49 @@ function tabIdFromSession(sessionId) {
 // (closed / restricted). (issues #20.1, #23)
 async function recoverSessionTab(sessionId) {
   const tabId = tabIdFromSession(sessionId)
-  if (tabId == null) return null
+  // 1) Fast path: the encoded Chrome tabId still exists — re-attach it (covers
-  for (let i = 0; i < 3; i++) {
+  //    the common renderer-process swap where the tabId is preserved, #23).
-    const tab = await chrome.tabs.get(tabId).catch(() => null)
+  if (tabId != null) {
-    if (!eligible(tab)) return null
+    for (let i = 0; i < 3; i++) {
-    try {
+      const tab = await chrome.tabs.get(tabId).catch(() => null)
-      await attachTab(tabId)
+      if (!eligible(tab)) break // tabId is gone — fall through to targetId recovery
-      if (tabs.has(tabId)) return tabId
+      try {
-    } catch {
+        await attachTab(tabId)
-      // mid-swap: the tab exists but isn't attachable yet — back off and retry.
+        if (tabs.has(tabId)) return tabId
+      } catch {
+        // mid-swap: tab exists but isn't attachable yet — back off and retry.
+      }
+      await new Promise((r) => setTimeout(r, 120 + i * 150))
+    }
+  }
+  // 2) The Chrome tabId is gone, but the CDP targetId is STABLE across the nav.
+  //    Some cross-process hops (Mercari's signin token exchange) give the tab a
+  //    NEW tabId while keeping the same target, so `cb-tab-<oldTabId>` can't be
+  //    recovered by tabId. Find the tab now hosting our remembered targetId via
+  //    chrome.debugger.getTargets(), attach it, and ALIAS the dead session to it
+  //    so the daemon's session id keeps resolving. Longer window: this hop can
+  //    take several seconds to settle (issue #24).
+  const targetId = sessionTargets.get(sessionId)
+  if (targetId) {
+    for (let i = 0; i < 6; i++) {
+      const targets = await chrome.debugger.getTargets().catch(() => null)
+      const t = targets && targets.find((x) => x.id === targetId && x.tabId != null)
+      if (t && t.tabId != null) {
+        const tab = await chrome.tabs.get(t.tabId).catch(() => null)
+        if (eligible(tab)) {
+          try {
+            await attachTab(t.tabId)
+            if (tabs.has(t.tabId)) {
+              sessionToTab.set(sessionId, t.tabId) // alias dead session -> live tab
+              return t.tabId
+            }
+          } catch {
+            // not attachable yet — keep waiting for the swap to settle.
+          }
+        }
+      }
+      await new Promise((r) => setTimeout(r, 300 + i * 300))
     }
-    await new Promise((r) => setTimeout(r, 120 + i * 150))
   }
   return null
 }
@@ -343,6 +385,7 @@ async function attachTab(tabId) {
   const entry = { sessionId, targetId }
   tabs.set(tabId, entry)
   sessionToTab.set(sessionId, tabId)
+  rememberSessionTarget(sessionId, targetId)
   setBadge(tabId, port ? 'on' : 'connecting')
   postToHost({
     method: 'forwardCDPEvent',

extensions/ab-connect/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "chrome-use",
-  "version": "0.4.8",
+  "version": "0.4.9",
   "description": "Let chrome-use drive your logged-in Chrome \u2014 install once, no token, no per-use confirmation.",
   "key": "MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA6vQIyscGIPYPZdSpPwPL0+0gxUROyRgCpmvCSDoc8XUm4qm97VbKnD9Ijc1lV22lNWZtE78gaRjt6BeSfuMgnBymnhLKjN1gU6AI5QUU0mrJyeHdWKvrKQR5FmsM2A7Xr1ykE2SiiS8zNUS3Y/6O5l+Nva7wrVy6E4a2dkBVQkOsu+DV+nEZvhIyuDY5D5SPXqNwUTWTaglwj5mjvHz36xSwCWlPmrtJ+ED0AUyrb2z4GIOmvk4kqtBVrh/UD058klLo4CkYOnIybB5aV6WYuwarfPY4bF/dLggPem+ewLNTUNBuwrxj/A4nUv0LJTuRO8rR7f8WR9qnRCY0Ic5saQIDAQAB",
   "icons": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "chrome-use",
-  "version": "1.4.1",
+  "version": "1.5.1",
   "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

@@ -208,6 +208,9 @@ For unstructured reading (no refs needed):
 
 ```bash
 chrome-use get text @e1                # visible text of an element
+chrome-use get text --all-frames       # whole page, aggregated across ALL frames
+chrome-use get text --main             # main content only — skip nav/header/sidebar
+chrome-use frames                      # list every frame + where the text lives
 chrome-use get html @e1                # innerHTML
 chrome-use get attr @e1 href           # any attribute
 chrome-use get value @e1               # input value
@@ -216,6 +219,14 @@ chrome-use get url                     # current URL
 chrome-use get count ".item"           # count matching elements
 ```
 
+On listing/marketplace pages (Yahoo Auctions, Rakuten, Mercari shops) the seller's
+description often lives in a **child frame** or is buried under a "related items"
+sidebar, so a plain `get text body` returns only header/nav boilerplate. When the
+text you expect is missing: run `chrome-use frames` to see where it is, then
+`get text --all-frames` (reads every reachable frame incl. cross-origin iframes)
+or `get text --main` (drops the global chrome). If the content is lazy-loaded,
+`scroll` it into view first.
+
 ## Interacting
 
 ```bash
@@ -309,12 +320,43 @@ detects this and prints a one-line hint. Drive them the screenshot way:
 chrome-use screenshot /tmp/s.png       # SEE the state (your only read path —
                                           # eval/get text return nothing useful)
 chrome-use click 640 360               # interact by viewport coordinate
-chrome-use keydown d; sleep 0.6; chrome-use keyup d   # hold-to-move
+chrome-use press d --hold 800          # hold-to-move, precise (timed in-daemon —
+                                          # NOT keydown+shell-sleep+keyup, which
+                                          # adds ~250ms jitter per round-trip)
 chrome-use press Space                 # discrete actions (jump/attack/confirm)
 ```
 
-Each command is a ~250ms round-trip, so this is fine for turn-based / canvas
+**Don't drive frame-by-frame with one CLI call per action** — that's the slowest,
-*apps* but too slow to play a real-time 60fps action game frame-by-frame.
+lowest-fidelity way (each call is a process spawn + round-trip). Script a *timed
+sequence in a single round-trip* with `batch` (it sends each step to the running
+daemon; `press --hold` and `wait` block in-daemon, so timing is precise):
+
+```bash
+chrome-use batch "press d --hold 900" "press j" "press j" "wait 200" "press d --hold 500"
+```
+
+Also try reading real state instead of pixels: `eval` runs in the page's main
+world, so for a framework/engine game you can often reach its globals (e.g. a
+Phaser/PIXI/Three instance, a store, `window.__GAME__`) and read positions/score
+directly — far better than guessing from a screenshot.
+
+**For genuinely real-time driving, drop the CLI entirely and use the WebSocket.**
+`chrome-use stream enable` opens a bidirectional WS (`stream status` prints the
+`ws://127.0.0.1:<port>`). Connect once and you get a live ~60fps screencast AND
+can send input on the same socket — no per-action process spawn, no round-trip,
+works over the extension relay:
+
+```js
+// node (global WebSocket): live frames + locally-timed input
+const ws = new WebSocket("ws://127.0.0.1:PORT")
+ws.onmessage = e => { const m = JSON.parse(e.data); if (m.type==="frame") {/* base64 jpeg */} }
+const k = (eventType,key,code,vk) => ws.send(JSON.stringify({type:"input_keyboard",eventType,key,code,windowsVirtualKeyCode:vk}))
+k("keyDown"," ","Space",32); setTimeout(()=>k("keyUp"," ","Space",32), 80)   // a jump
+// also: {type:"input_mouse",eventType:"mousePressed",x,y,button:"left",clickCount:1}
+```
+
+This is the difference between watching a slideshow and playing the game. Reserve
+screenshots for one-off checks; use the WS for any sustained real-time control.
 
 ## Waiting (read this)