chore(release): 0.27.0-fork.47 — tab-drift pin, snapshot -c keeps interactive, stale-ref guidance

- snapshot -c (compact) now always keeps lines with an interactive ARIA role
  (button/link/textbox/combobox/option/…), not only `ref=`/`": "` lines — so a
  clickable control can't vanish from compact output and leave the agent clicking
  an empty ref (issue #2 P1). Additive: only ever keeps more. compact tests green.
- stale-ref error now leads with "take a fresh snapshot" and points to the `eval`
  fallback for ref-churning SPAs, and demotes AGENT_BROWSER_VERIFY_REF=0 to a
  flagged last resort instead of presenting it as the fix (issue #3 P1).

cli/Cargo.lock

@@ -45,7 +45,7 @@ dependencies = [
 
 [[package]]
 name = "agent-browser-stealth"
-version = "0.27.0-fork.43"
+version = "0.27.0-fork.47"
 dependencies = [
  "aes-gcm",
  "async-trait",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "agent-browser-stealth"
-version = "0.27.0-fork.43"
+version = "0.27.0-fork.47"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/commands.rs

@@ -403,12 +403,48 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
             Ok(json!({ "id": id, "action": "fill", "selector": sel, "value": rest[1..].join(" ") }))
         }
         "type" => {
+            // `type --focused <text>` types into whatever element currently has
+            // focus (no selector) — for custom widgets that move focus to a hidden
+            // input after you open them.
+            if rest.first() == Some(&"--focused") {
+                return Ok(json!({
+                    "id": id, "action": "type", "focused": true,
+                    "text": rest[1..].join(" "),
+                }));
+            }
             let sel = rest.first().ok_or_else(|| ParseError::MissingArguments {
                 context: "type".to_string(),
-                usage: "type <selector> <text>",
+                usage: "type <selector> <text>   (or: type --focused <text>)",
             })?;
             Ok(json!({ "id": id, "action": "type", "selector": sel, "text": rest[1..].join(" ") }))
         }
+        "pick" => {
+            // pick <selector|@ref> --option "<text>"  — atomic combobox select:
+            // open the control, wait for options (incl. portal menus), match by
+            // text, fire the right event sequence, verify. Covers native <select>,
+            // ARIA combobox/listbox, and react-select.
+            let sel = rest.first().ok_or_else(|| ParseError::MissingArguments {
+                context: "pick".to_string(),
+                usage: "pick <selector> --option \"<text>\"",
+            })?;
+            let opt_pos = rest.iter().position(|a| *a == "--option" || *a == "-o");
+            let option = match opt_pos {
+                Some(p) => rest[p + 1..].join(" "),
+                None => {
+                    return Err(ParseError::MissingArguments {
+                        context: "pick".to_string(),
+                        usage: "pick <selector> --option \"<text>\"",
+                    })
+                }
+            };
+            if option.is_empty() {
+                return Err(ParseError::MissingArguments {
+                    context: "pick".to_string(),
+                    usage: "pick <selector> --option \"<text>\"",
+                });
+            }
+            Ok(json!({ "id": id, "action": "pick", "selector": sel, "option": option }))
+        }
         "hover" => {
             let sel = rest.first().ok_or_else(|| ParseError::MissingArguments {
                 context: "hover".to_string(),

cli/src/connection.rs

@@ -832,7 +832,19 @@ pub fn send_command(mut cmd: Value, session: &str) -> Result<Response, String> {
             obj.insert("_clickMode".to_string(), Value::String(m));
         }
         if let Ok(h) = std::env::var("AGENT_BROWSER_HUMANIZE") {
-            obj.insert("_humanize".to_string(), Value::String(h));
+            // Only forward a recognized level; warn once (like the --humanize flag
+            // does) when the env var is set to garbage, instead of silently
+            // ignoring it.
+            if crate::native::humanize::HumanizeLevel::parse(&h).is_some() {
+                obj.insert("_humanize".to_string(), Value::String(h));
+            } else {
+                static WARNED: std::sync::Once = std::sync::Once::new();
+                WARNED.call_once(|| {
+                    eprintln!(
+                        "warning: AGENT_BROWSER_HUMANIZE must be off|fast|human, got {h:?} (ignored)"
+                    );
+                });
+            }
         }
     }
 

cli/src/native/actions.rs

@@ -1323,6 +1323,7 @@ pub async fn execute_command(cmd: &Value, state: &mut DaemonState) -> Value {
         "fill" => handle_fill(cmd, state).await,
         "type" => handle_type(cmd, state).await,
         "press" => handle_press(cmd, state).await,
+        "pick" => handle_pick(cmd, state).await,
         "hover" => handle_hover(cmd, state).await,
         "scroll" => handle_scroll(cmd, state).await,
         "select" => handle_select(cmd, state).await,
@@ -3031,6 +3032,22 @@ async fn handle_fill(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
 async fn handle_type(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();
+
+    // `type --focused <text>`: type into the currently-focused element without a
+    // selector (custom widgets that move focus to a hidden input on open).
+    if cmd
+        .get("focused")
+        .and_then(|v| v.as_bool())
+        .unwrap_or(false)
+    {
+        let text = cmd
+            .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).await?;
+        return Ok(json!({ "typed": text, "focused": true }));
+    }
+
     let selector = cmd
         .get("selector")
         .and_then(|v| v.as_str())
@@ -3056,6 +3073,103 @@ async fn handle_type(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
     Ok(json!({ "typed": text }))
 }
 
+/// Atomic combobox select: `pick <selector> --option "<text>"`. Opens the control
+/// (so a portal-rendered menu mounts), polls for the option by visible text, then
+/// fires the full pointer/mouse event sequence on it — covering native `<select>`,
+/// ARIA combobox/listbox, and react-select, which a bare `click`+`press Enter`
+/// can't do reliably. Runs as one in-page async routine so the open→render→pick
+/// dance happens without round-trips that let the menu collapse between commands.
+async fn handle_pick(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 selector = cmd
+        .get("selector")
+        .and_then(|v| v.as_str())
+        .ok_or("Missing 'selector' parameter")?;
+    let option = cmd
+        .get("option")
+        .and_then(|v| v.as_str())
+        .ok_or("Missing 'option' parameter")?;
+
+    let (object_id, effective_session_id) = super::element::resolve_element_object_id(
+        &mgr.client,
+        &session_id,
+        &state.ref_map,
+        selector,
+        &state.iframe_sessions,
+    )
+    .await?;
+
+    let func = format!(
+        r#"async function() {{
+            const want = {opt};
+            const norm = s => (s || '').replace(/\s+/g, ' ').trim();
+            const matches = el => norm(el.textContent).toLowerCase().includes(want.toLowerCase());
+            const el = this;
+            const fire = (n, t) => n.dispatchEvent(new MouseEvent(t, {{ bubbles: true, cancelable: true, view: window }}));
+
+            // Native <select>: set the matching option and dispatch input/change.
+            if (el.tagName === 'SELECT') {{
+                const opt = [...el.options].find(matches);
+                if (!opt) return {{ ok: false, error: 'no <option> matched ' + JSON.stringify(want) }};
+                el.value = opt.value;
+                el.dispatchEvent(new Event('input', {{ bubbles: true }}));
+                el.dispatchEvent(new Event('change', {{ bubbles: true }}));
+                return {{ ok: true, picked: norm(opt.textContent), value: el.value, kind: 'select' }};
+            }}
+
+            // Custom widget: open it.
+            (el.focus && el.focus());
+            ['pointerdown', 'mousedown', 'mouseup', 'click'].forEach(t => fire(el, t));
+
+            // Poll for the option to render anywhere in the document (portals
+            // mount the menu outside the trigger), then click it.
+            const sel = '[role=option], [role=listbox] [role=option], li[role=option], [class*=option], [class*=item]';
+            const find = () => [...document.querySelectorAll(sel)].find(o => o.offsetParent !== null && matches(o));
+            const deadline = Date.now() + 2500;
+            let opt = find();
+            while (!opt && Date.now() < deadline) {{
+                await new Promise(r => setTimeout(r, 80));
+                opt = find();
+            }}
+            if (!opt) return {{ ok: false, error: 'option ' + JSON.stringify(want) + ' did not appear after opening the control' }};
+            (opt.scrollIntoView && opt.scrollIntoView({{ block: 'center' }}));
+            ['pointermove', 'pointerover', 'mouseover', 'pointerdown', 'mousedown', 'mouseup', 'click'].forEach(t => fire(opt, t));
+            return {{ ok: true, picked: norm(opt.textContent), kind: 'custom' }};
+        }}"#,
+        opt = serde_json::to_string(option).unwrap_or_default(),
+    );
+
+    let result: super::cdp::types::EvaluateResult = mgr
+        .client
+        .send_command_typed(
+            "Runtime.callFunctionOn",
+            &super::cdp::types::CallFunctionOnParams {
+                function_declaration: func,
+                object_id: Some(object_id),
+                arguments: None,
+                return_by_value: Some(true),
+                await_promise: Some(true),
+            },
+            Some(&effective_session_id),
+        )
+        .await?;
+
+    if let Some(ref ex) = result.exception_details {
+        return Err(format!("pick failed: {}", ex.text));
+    }
+    let val = result.result.value.unwrap_or(Value::Null);
+    if val.get("ok").and_then(|v| v.as_bool()).unwrap_or(false) {
+        Ok(json!({ "picked": val.get("picked"), "selector": selector }))
+    } else {
+        Err(val
+            .get("error")
+            .and_then(|v| v.as_str())
+            .unwrap_or("pick failed")
+            .to_string())
+    }
+}
+
 async fn handle_press(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();

cli/src/native/browser.rs

@@ -315,6 +315,13 @@ pub struct BrowserManager {
     /// browser after it ends. Only ever holds tabs we created — never the user's
     /// existing tabs or other sessions' tabs — so closing them is always safe.
     created_targets: HashSet<String>,
+    /// The session's *intended* active tab, pinned by stable target_id rather
+    /// than the fragile `active_page_index`. Set on every explicit open / tab new
+    /// / tab switch. `active_session_id` resolves through this so a foreign tab
+    /// opening (passive discovery), a tab closing, or list reordering can't drift
+    /// the session's commands onto the wrong page — the wrong-origin-fetch hazard
+    /// in the dogfood reports. Falls back to the index if the pinned tab is gone.
+    active_target_id: Option<String>,
     next_tab_id: u32,
     /// Whether to enable the CDP `Runtime` domain (console / error / exception capture).
     /// OFF by default for stealth: a live `Runtime.enable` is a detectable CDP signal
@@ -440,6 +447,7 @@ impl BrowserManager {
                 ignore_https_errors,
                 visited_origins: HashSet::new(),
                 created_targets: HashSet::new(),
+                active_target_id: None,
                 next_tab_id: 1,
                 capture_console: console_capture_enabled(),
             };
@@ -531,6 +539,7 @@ impl BrowserManager {
             ignore_https_errors: false,
             visited_origins: HashSet::new(),
             created_targets: HashSet::new(),
+            active_target_id: None,
             next_tab_id: 1,
             capture_console: console_capture_enabled(),
         };
@@ -547,6 +556,7 @@ impl BrowserManager {
                 target_type: "page".to_string(),
             });
             manager.active_page_index = 0;
+            manager.pin_active_target();
             manager.enable_domains_direct().await?;
         } else {
             manager.discover_and_attach_targets().await?;
@@ -621,6 +631,7 @@ impl BrowserManager {
                 target_type: "page".to_string(),
             });
             self.active_page_index = 0;
+            self.pin_active_target();
             self.enable_domains(&attach_result.session_id).await?;
         } else {
             for target in &page_targets {
@@ -650,6 +661,7 @@ impl BrowserManager {
             }
 
             self.active_page_index = 0;
+            self.pin_active_target();
             let session_id = self.pages[0].session_id.clone();
             self.enable_domains(&session_id).await?;
         }
@@ -736,9 +748,31 @@ impl BrowserManager {
         Ok(())
     }
 
+    /// Index of the session's active page, resolved through the pinned
+    /// `active_target_id` (stable across reorder/removal/passive discovery) and
+    /// falling back to `active_page_index` when nothing is pinned or the pin is
+    /// gone. This is what keeps commands on the tab the agent actually opened.
+    fn resolved_active_index(&self) -> usize {
+        if let Some(tid) = &self.active_target_id {
+            if let Some(i) = self.pages.iter().position(|p| &p.target_id == tid) {
+                return i;
+            }
+        }
+        self.active_page_index
+    }
+
+    /// Pin the current active page by target_id so later commands stick to it.
+    /// Call after any explicit open / tab new / tab switch.
+    fn pin_active_target(&mut self) {
+        self.active_target_id = self
+            .pages
+            .get(self.active_page_index)
+            .map(|p| p.target_id.clone());
+    }
+
     pub fn active_session_id(&self) -> Result<&str, String> {
         self.pages
-            .get(self.active_page_index)
+            .get(self.resolved_active_index())
             .map(|p| p.session_id.as_str())
             .ok_or_else(|| "No active page".to_string())
     }
@@ -991,7 +1025,7 @@ impl BrowserManager {
 
     pub fn active_target_id(&self) -> Result<&str, String> {
         self.pages
-            .get(self.active_page_index)
+            .get(self.resolved_active_index())
             .map(|p| p.target_id.as_str())
             .ok_or_else(|| "No active page".to_string())
     }
@@ -1219,6 +1253,7 @@ impl BrowserManager {
             target_type: "page".to_string(),
         });
         self.active_page_index = index;
+        self.pin_active_target();
 
         Ok(json!({
             "tabId": format_tab_id(tab_id),
@@ -1238,6 +1273,7 @@ impl BrowserManager {
         }
 
         self.active_page_index = index;
+        self.pin_active_target();
         let session_id = self.pages[index].session_id.clone();
         self.enable_domains(&session_id).await?;
 
@@ -1581,6 +1617,7 @@ impl BrowserManager {
         let index = self.pages.len();
         self.pages.push(page);
         self.active_page_index = index;
+        self.pin_active_target();
     }
 
     /// Add a passively-discovered page WITHOUT changing the active tab.
@@ -1783,6 +1820,7 @@ async fn initialize_lightpanda_manager(
             ignore_https_errors: false,
             visited_origins: HashSet::new(),
             created_targets: HashSet::new(),
+            active_target_id: None,
             next_tab_id: 1,
             capture_console: console_capture_enabled(),
         };

cli/src/native/element.rs

@@ -556,8 +556,12 @@ async fn verify_ref_identity(
     Err(format!(
         "Ref {} no longer matches its snapshot. Was [{} \"{}\"], now [{} \"{}\"].\n\
          The DOM mutated between snapshot and interaction (typical with React/Vue \
-         reusing nodes during re-render). Take a fresh snapshot, then re-target.\n\
+         reusing nodes during re-render). Fix: take a fresh `snapshot` and re-target \
-         To bypass this guard set AGENT_BROWSER_VERIFY_REF=0.",
+         with the new ref. For SPAs where refs churn every interaction, drive the \
+         element directly with `eval` (e.g. `eval \"document.querySelector(...).click()\"`), \
+         which doesn't depend on refs.\n\
+         (Last resort: AGENT_BROWSER_VERIFY_REF=0 disables this safety check — only \
+         if you accept clicks may land on a re-rendered/wrong node.)",
         ref_id, expected_role, expected_name, actual_role, actual_name,
     ))
 }

cli/src/native/snapshot.rs

@@ -1305,6 +1305,39 @@ fn render_tree(
     }
 }
 
+/// True if a snapshot line names an interactive ARIA role. Compaction keeps
+/// these even without a `ref=`/`": "` marker, so a clickable control never gets
+/// dropped from `-c` output (the dogfood reports saw a button present in the full
+/// snapshot vanish from compact, leaving the agent clicking an empty ref).
+fn is_interactive_line(line: &str) -> bool {
+    const ROLES: &[&str] = &[
+        "button",
+        "link",
+        "textbox",
+        "checkbox",
+        "radio",
+        "combobox",
+        "listbox",
+        "menuitem",
+        "menuitemcheckbox",
+        "menuitemradio",
+        "option",
+        "switch",
+        "slider",
+        "spinbutton",
+        "searchbox",
+        "tab ",
+        "clickable",
+        "focusable",
+        "editable",
+    ];
+    let t = line.trim_start();
+    // Lines look like `- button "Label" [ref=e1]`; match the role token after the
+    // leading "- " marker.
+    let t = t.strip_prefix("- ").unwrap_or(t);
+    ROLES.iter().any(|r| t.starts_with(r))
+}
+
 fn compact_tree(tree: &str, interactive: bool) -> String {
     let lines: Vec<&str> = tree.lines().collect();
     if lines.is_empty() {
@@ -1314,7 +1347,7 @@ fn compact_tree(tree: &str, interactive: bool) -> String {
     let mut keep = vec![false; lines.len()];
 
     for (i, line) in lines.iter().enumerate() {
-        if line.contains("ref=") || line.contains(": ") {
+        if line.contains("ref=") || line.contains(": ") || is_interactive_line(line) {
             keep[i] = true;
             // Mark ancestors
             let my_indent = count_indent(line);

cli/src/output.rs

@@ -358,6 +358,16 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
         }
         // Eval result
         if let Some(result) = data.get("result") {
+            // Surface which page the eval actually ran on — to stderr, so it
+            // never corrupts the parsed value on stdout. Lets an agent catch tab
+            // drift (commands landing on the wrong tab) before trusting a result,
+            // e.g. a logged-in `fetch` that hit the wrong origin. (In
+            // content-boundaries mode the origin is already in the banner.)
+            if !opts.content_boundaries {
+                if let Some(o) = origin.filter(|o| !o.is_empty()) {
+                    eprintln!("eval @ {o}");
+                }
+            }
             let formatted = serde_json::to_string_pretty(result).unwrap_or_default();
             print_with_boundaries(&formatted, origin, opts);
             return;
@@ -751,7 +761,12 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
                         color::green(path)
                     );
                     if let Some(annotations) = data.get("annotations").and_then(|v| v.as_array()) {
-                        for ann in annotations {
+                        // Cap the printed legend on dense pages (it can be
+                        // hundreds of lines and flood the terminal). The image
+                        // still shows every marker; --json returns the full list.
+                        const LEGEND_CAP: usize = 40;
+                        let total = annotations.len();
+                        for ann in annotations.iter().take(LEGEND_CAP) {
                             let num = ann.get("number").and_then(|n| n.as_u64()).unwrap_or(0);
                             let ref_id = ann.get("ref").and_then(|r| r.as_str()).unwrap_or("");
                             let role = ann.get("role").and_then(|r| r.as_str()).unwrap_or("");
@@ -773,6 +788,15 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
                                 );
                             }
                         }
+                        if total > LEGEND_CAP {
+                            println!(
+                                "   {}",
+                                color::dim(&format!(
+                                    "… and {} more markers (shown in the image; --json for the full list)",
+                                    total - LEGEND_CAP
+                                ))
+                            );
+                        }
                     }
                 }
                 "pdf" => println!(

package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-browser-stealth",
-  "version": "0.27.0-fork.43",
+  "version": "0.27.0-fork.47",
   "description": "Browser automation CLI for AI agents — stealth fork with anti-detection",
   "type": "module",
   "packageManager": "pnpm@11.1.3",

skill-data/core/SKILL.md

@@ -219,8 +219,16 @@ agent-browser press Enter                 # press a key at current focus
 agent-browser press Control+a             # key combination
 agent-browser check @e3                   # check checkbox
 agent-browser uncheck @e3                 # uncheck
-agent-browser select @e4 "option-value"   # select dropdown option
+agent-browser select @e4 "option-value"   # native <select> only
 agent-browser select @e4 "a" "b"          # select multiple
+agent-browser pick @e4 --option "Europe"  # ANY combobox (react-select / ARIA /
+                                          # native): opens it, waits for the menu
+                                          # (incl. portal-rendered), matches by
+                                          # visible text, fires the right events,
+                                          # and ERRORS if the option never shows
+                                          # (no silent no-op). Use this for custom
+                                          # dropdowns where `select` returns ✓ but
+                                          # changes nothing.
 agent-browser upload @e5 file1.pdf        # upload file(s)
 agent-browser scroll down 500             # scroll page (up/down/left/right)
 agent-browser scrollintoview @e1          # scroll element into view