Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
70ab38d35f | ||
|
|
6830df50ea | ||
|
|
cd47ec43d0 | ||
|
|
2cd361817d | ||
|
|
42f47c49aa | ||
|
|
e29800df72 | ||
|
|
e7e849ea39 | ||
|
|
ebb02c65c8 | ||
|
|
4317db636f | ||
|
|
c99838a034 | ||
|
|
dc2aa4cade | ||
|
|
7085f3bf36 | ||
|
|
29815ff5f3 | ||
|
|
2a338d4c29 | ||
|
|
6fcf52db60 | ||
|
|
af8823b27b | ||
|
|
c85e3faa82 | ||
|
|
b25958946c | ||
|
|
d4ff49caa8 | ||
|
|
4e949fffbf | ||
|
|
af46490812 |
@@ -152,9 +152,16 @@ jobs:
|
||||
# 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)"
|
||||
# NOTE: the job runs under `bash -e`. grep returning 1 (no match) and
|
||||
# the `[ -n "$body" ]` test returning 1 (empty section) must NOT abort
|
||||
# the script — otherwise a release whose commit range lacks a whole
|
||||
# category (e.g. only `feat`, no `fix`) dies before writing the closing
|
||||
# heredoc delimiter and the whole release step fails. `|| true` +
|
||||
# `return 0` keep section() always-succeeding.
|
||||
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"; }
|
||||
local body; body="$(printf '%s\n' "$LOG" | grep -E "$2" | sed 's/^/- /' || true)"
|
||||
[ -n "$body" ] && printf '\n### %s\n%s\n' "$1" "$body"
|
||||
return 0
|
||||
}
|
||||
{
|
||||
echo "notes<<__NOTES_EOF__"
|
||||
|
||||
Generated
+1
-1
@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
|
||||
|
||||
[[package]]
|
||||
name = "chrome-use"
|
||||
version = "1.5.1"
|
||||
version = "1.5.11"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"aes-gcm",
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "chrome-use"
|
||||
version = "1.5.1"
|
||||
version = "1.5.11"
|
||||
edition = "2021"
|
||||
description = "Fast browser automation CLI for AI agents"
|
||||
license = "Apache-2.0"
|
||||
|
||||
+243
-29
@@ -30,12 +30,65 @@ pub enum ParseError {
|
||||
InvalidSessionName { name: String },
|
||||
}
|
||||
|
||||
/// Top-level commands an agent is likely to mistype, used for "did you mean"
|
||||
/// 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",
|
||||
"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).
|
||||
fn edit_distance(a: &str, b: &str) -> usize {
|
||||
let a: Vec<char> = a.chars().collect();
|
||||
let b: Vec<char> = b.chars().collect();
|
||||
let mut prev: Vec<usize> = (0..=b.len()).collect();
|
||||
let mut curr = vec![0usize; b.len() + 1];
|
||||
for (i, &ca) in a.iter().enumerate() {
|
||||
curr[0] = i + 1;
|
||||
for (j, &cb) in b.iter().enumerate() {
|
||||
let cost = if ca == cb { 0 } else { 1 };
|
||||
curr[j + 1] = (prev[j + 1] + 1).min(curr[j] + 1).min(prev[j] + cost);
|
||||
}
|
||||
std::mem::swap(&mut prev, &mut curr);
|
||||
}
|
||||
prev[b.len()]
|
||||
}
|
||||
|
||||
/// Closest known command within a small edit distance, or a prefix/substring
|
||||
/// match — `None` if nothing is close enough to suggest confidently.
|
||||
fn nearest_command(input: &str) -> Option<String> {
|
||||
let lower = input.to_lowercase();
|
||||
// Exact prefix/substring hits first (e.g. "session" -> "sessions").
|
||||
if let Some(c) = KNOWN_COMMANDS
|
||||
.iter()
|
||||
.find(|c| c.starts_with(&lower) || lower.starts_with(**c))
|
||||
{
|
||||
return Some(c.to_string());
|
||||
}
|
||||
// Tolerance scales with length: short words get distance 1, longer get 2.
|
||||
let max_dist = if lower.len() <= 4 { 1 } else { 2 };
|
||||
KNOWN_COMMANDS
|
||||
.iter()
|
||||
.map(|c| (*c, edit_distance(&lower, c)))
|
||||
.filter(|(_, d)| *d <= max_dist)
|
||||
.min_by_key(|(_, d)| *d)
|
||||
.map(|(c, _)| c.to_string())
|
||||
}
|
||||
|
||||
impl ParseError {
|
||||
pub fn format(&self) -> String {
|
||||
match self {
|
||||
ParseError::UnknownCommand { command } => {
|
||||
format!("Unknown command: {}", command)
|
||||
}
|
||||
ParseError::UnknownCommand { command } => match nearest_command(command) {
|
||||
Some(suggestion) => format!(
|
||||
"Unknown command: {}\nDid you mean: chrome-use {}?",
|
||||
command, suggestion
|
||||
),
|
||||
None => format!("Unknown command: {}", command),
|
||||
},
|
||||
ParseError::UnknownSubcommand {
|
||||
subcommand,
|
||||
valid_options,
|
||||
@@ -676,10 +729,56 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
|
||||
} else {
|
||||
return Err(ParseError::MissingArguments {
|
||||
context: "scroll --selector".to_string(),
|
||||
usage: "scroll [direction] [amount] [--selector <sel>]",
|
||||
usage: "scroll [direction] [amount] [--selector <sel>] [--at <x,y>] [--frame <n>]",
|
||||
});
|
||||
}
|
||||
}
|
||||
"--at" => {
|
||||
// `--at x,y`: dispatch the wheel at this viewport pixel, so it
|
||||
// scrolls whatever element/iframe is under the pointer — including
|
||||
// cross-origin iframes that `window.scrollBy` can't reach (#36).
|
||||
let val = rest.get(i + 1).ok_or(ParseError::MissingArguments {
|
||||
context: "scroll --at".to_string(),
|
||||
usage: "scroll [direction] [amount] --at <x,y>",
|
||||
})?;
|
||||
let mut parts = val.split(',');
|
||||
match (
|
||||
parts.next().and_then(|s| s.trim().parse::<f64>().ok()),
|
||||
parts.next().and_then(|s| s.trim().parse::<f64>().ok()),
|
||||
) {
|
||||
(Some(x), Some(y)) => {
|
||||
obj.insert("at".to_string(), json!([x, y]));
|
||||
}
|
||||
_ => {
|
||||
return Err(ParseError::InvalidValue {
|
||||
message: format!("scroll --at: invalid coordinate `{}`", val),
|
||||
usage: "scroll [direction] [amount] --at <x,y> (e.g. --at 640,400)",
|
||||
})
|
||||
}
|
||||
}
|
||||
i += 1;
|
||||
}
|
||||
"--frame" => {
|
||||
// `--frame n`: scroll the n-th frame from `chrome-use frames` by
|
||||
// dispatching the wheel at that frame's center — reaches content in
|
||||
// a cross-origin iframe without needing a selector into it (#36).
|
||||
let val = rest.get(i + 1).ok_or(ParseError::MissingArguments {
|
||||
context: "scroll --frame".to_string(),
|
||||
usage: "scroll [direction] [amount] --frame <n>",
|
||||
})?;
|
||||
match val.trim().parse::<usize>() {
|
||||
Ok(n) => {
|
||||
obj.insert("frame".to_string(), json!(n));
|
||||
}
|
||||
Err(_) => {
|
||||
return Err(ParseError::InvalidValue {
|
||||
message: format!("scroll --frame: invalid index `{}`", val),
|
||||
usage: "scroll [direction] [amount] --frame <n> (index from `chrome-use frames`)",
|
||||
})
|
||||
}
|
||||
}
|
||||
i += 1;
|
||||
}
|
||||
arg if arg.starts_with('-') => {}
|
||||
_ => {
|
||||
match positional_index {
|
||||
@@ -854,17 +953,37 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
|
||||
// selector: @ref or CSS selector
|
||||
// path: file path (contains / or . or ends with known extension)
|
||||
let mut full_page = false;
|
||||
let positional: Vec<&str> = rest
|
||||
.iter()
|
||||
.filter(|arg| match **arg {
|
||||
"--full" | "-f" => {
|
||||
full_page = true;
|
||||
false
|
||||
let mut clip: Option<Value> = None;
|
||||
let mut positional: Vec<&str> = Vec::new();
|
||||
let mut i = 0;
|
||||
while i < rest.len() {
|
||||
match rest[i] {
|
||||
"--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 {
|
||||
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}'"),
|
||||
usage: "screenshot --clip <x,y,w,h> [path]",
|
||||
});
|
||||
}
|
||||
clip = Some(json!({
|
||||
"x": nums[0], "y": nums[1], "width": nums[2], "height": nums[3]
|
||||
}));
|
||||
i += 1;
|
||||
}
|
||||
_ => true,
|
||||
})
|
||||
.copied()
|
||||
.collect();
|
||||
other => positional.push(other),
|
||||
}
|
||||
i += 1;
|
||||
}
|
||||
let (selector, path) = match (positional.first(), positional.get(1)) {
|
||||
(Some(first), Some(second)) => {
|
||||
// Two args: first is selector, second is path
|
||||
@@ -895,6 +1014,9 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
|
||||
"path": path, "selector": selector,
|
||||
"fullPage": full_page, "annotate": flags.annotate
|
||||
});
|
||||
if let Some(c) = clip {
|
||||
cmd["clip"] = c;
|
||||
}
|
||||
if let Some(ref fmt) = flags.screenshot_format {
|
||||
cmd["format"] = json!(fmt);
|
||||
}
|
||||
@@ -1025,6 +1147,14 @@ fn parse_command_inner(args: &[String], flags: &Flags) -> Result<Value, ParseErr
|
||||
Ok(json!({ "id": id, "action": "stealth_status" }))
|
||||
}
|
||||
|
||||
// `cf-status` — Cloudflare challenge/clearance preflight: is the page
|
||||
// currently a CF challenge, and is there a still-valid cf_clearance (the
|
||||
// HttpOnly persistence cookie)? Lets an agent SKIP re-solving when already
|
||||
// cleared, and know when it must solve. Persistence optimization.
|
||||
"cf-status" | "cf" | "cloudflare-status" | "clearance" => {
|
||||
Ok(json!({ "id": id, "action": "cf_status" }))
|
||||
}
|
||||
|
||||
// === Close ===
|
||||
"close" | "quit" | "exit" => {
|
||||
// `close <tab>` closes only that tab (and the output says "Tab
|
||||
@@ -2402,6 +2532,15 @@ fn parse_get(rest: &[&str], id: &str) -> Result<Value, ParseError> {
|
||||
if all_frames {
|
||||
return Ok(json!({ "id": id, "action": "gettext", "allFrames": true }));
|
||||
}
|
||||
// `get text --pierce` reads through CLOSED shadow DOM / child docs
|
||||
// via the CDP DOM tree — content eval/innerText can't reach, e.g. an
|
||||
// extension's injected panel in a closed shadow root (issue #30).
|
||||
let pierce = rest[1..]
|
||||
.iter()
|
||||
.any(|a| matches!(*a, "--pierce" | "--shadow" | "--deep"));
|
||||
if pierce {
|
||||
return Ok(json!({ "id": id, "action": "gettext", "pierce": true }));
|
||||
}
|
||||
// `get text --main` returns the main-content region (readability),
|
||||
// skipping header/nav/footer/sidebar boilerplate (issue #27).
|
||||
let main = rest[1..]
|
||||
@@ -2410,16 +2549,16 @@ fn parse_get(rest: &[&str], id: &str) -> Result<Value, ParseError> {
|
||||
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 }))
|
||||
// `get text` with no selector reads the WHOLE PAGE and now defaults
|
||||
// to cross-frame aggregation, so an agent gets a page's iframed
|
||||
// content (listing descriptions etc.) without having to know about
|
||||
// `--all-frames` (#27). On a single-frame page this is identical to
|
||||
// the old body read; multi-frame pages get the child frames too —
|
||||
// a strict superset. An explicit selector stays element-scoped.
|
||||
match rest.iter().skip(1).find(|a| !a.starts_with("--")).copied() {
|
||||
Some(sel) => Ok(json!({ "id": id, "action": "gettext", "selector": sel })),
|
||||
None => Ok(json!({ "id": id, "action": "gettext", "allFrames": true })),
|
||||
}
|
||||
}
|
||||
Some("html") => {
|
||||
let sel = rest.get(1).ok_or_else(|| ParseError::MissingArguments {
|
||||
@@ -4257,6 +4396,21 @@ mod tests {
|
||||
assert_eq!(cmd["fullPage"], true);
|
||||
}
|
||||
|
||||
#[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())
|
||||
.unwrap();
|
||||
assert_eq!(cmd["action"], "screenshot");
|
||||
assert_eq!(cmd["clip"]["x"], 10.0);
|
||||
assert_eq!(cmd["clip"]["y"], 20.0);
|
||||
assert_eq!(cmd["clip"]["width"], 200.0);
|
||||
assert_eq!(cmd["clip"]["height"], 40.0);
|
||||
assert_eq!(cmd["path"], "out.png");
|
||||
// Bad clip is a clear error, not silent.
|
||||
assert!(parse_command(&args("screenshot --clip 1,2,3"), &default_flags()).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_screenshot_with_ref() {
|
||||
let cmd = parse_command(&args("screenshot @e1"), &default_flags()).unwrap();
|
||||
@@ -4777,15 +4931,21 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_text_defaults_to_body() {
|
||||
// `get text` with no selector now returns the whole page (body) instead
|
||||
// of erroring (issue #24-D).
|
||||
fn test_get_text_defaults_to_all_frames() {
|
||||
// `get text` with no selector now reads the whole page across ALL frames
|
||||
// by default (#27), so iframed content isn't silently missed. (Was: a
|
||||
// top-frame `body` read, #24-D.)
|
||||
let cmd = parse_command(&args("get text"), &default_flags()).unwrap();
|
||||
assert_eq!(cmd["action"], "gettext");
|
||||
assert_eq!(cmd["selector"], "body");
|
||||
// An explicit selector still wins.
|
||||
assert_eq!(cmd["allFrames"], true);
|
||||
assert!(cmd.get("selector").is_none());
|
||||
// An explicit selector still wins and stays element-scoped.
|
||||
let cmd2 = parse_command(&args("get text h1"), &default_flags()).unwrap();
|
||||
assert_eq!(cmd2["selector"], "h1");
|
||||
assert!(cmd2.get("allFrames").is_none());
|
||||
// `text` top-level shortcut behaves the same.
|
||||
let cmd3 = parse_command(&args("text"), &default_flags()).unwrap();
|
||||
assert_eq!(cmd3["allFrames"], true);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -4813,6 +4973,21 @@ mod tests {
|
||||
assert_eq!(cmd["action"], "frames");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_nearest_command_suggestions() {
|
||||
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"));
|
||||
// Nonsense with no close match stays silent.
|
||||
assert_eq!(nearest_command("xyzzy"), None);
|
||||
// The unknown-command error embeds the suggestion.
|
||||
let err = ParseError::UnknownCommand {
|
||||
command: "sesions".to_string(),
|
||||
};
|
||||
assert!(err.format().contains("Did you mean: chrome-use sessions?"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_text_main() {
|
||||
for variant in ["get text --main", "get text --readable", "text -m"] {
|
||||
@@ -4823,6 +4998,16 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_get_text_pierce() {
|
||||
for variant in ["get text --pierce", "get text --shadow", "text --deep"] {
|
||||
let cmd = parse_command(&args(variant), &default_flags()).unwrap();
|
||||
assert_eq!(cmd["action"], "gettext", "{variant}");
|
||||
assert_eq!(cmd["pierce"], 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();
|
||||
@@ -5729,6 +5914,35 @@ mod tests {
|
||||
assert_eq!(cmd["selector"], ".sidebar");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_scroll_at_coordinate() {
|
||||
// `--at x,y` carries a [x, y] array for a wheel dispatched at that pixel
|
||||
// (issue #36: cross-origin iframe scroll).
|
||||
let cmd = parse_command(&args("scroll down 700 --at 640,400"), &default_flags()).unwrap();
|
||||
assert_eq!(cmd["action"], "scroll");
|
||||
assert_eq!(cmd["direction"], "down");
|
||||
assert_eq!(cmd["amount"], 700);
|
||||
assert_eq!(cmd["at"], json!([640.0, 400.0]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_scroll_at_rejects_garbage() {
|
||||
assert!(parse_command(&args("scroll --at nope"), &default_flags()).is_err());
|
||||
assert!(parse_command(&args("scroll --at 1"), &default_flags()).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_scroll_frame_index() {
|
||||
let cmd = parse_command(&args("scroll down 700 --frame 2"), &default_flags()).unwrap();
|
||||
assert_eq!(cmd["action"], "scroll");
|
||||
assert_eq!(cmd["frame"], 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_scroll_frame_rejects_non_integer() {
|
||||
assert!(parse_command(&args("scroll --frame two"), &default_flags()).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_scroll_selector_before_positional() {
|
||||
let cmd =
|
||||
|
||||
@@ -449,6 +449,47 @@ pub fn relay_url() -> Option<String> {
|
||||
}
|
||||
}
|
||||
|
||||
/// Append a one-line record of how a CDP connection was established, to
|
||||
/// `~/.chrome-use/connect-mode.log`. This is the smoking-gun detector for the
|
||||
/// "Allow remote debugging?" consent modal: that modal ONLY appears on a raw
|
||||
/// remote-debugging attach / a browser we launched with a debug port — NEVER on
|
||||
/// the extension relay. When the modal reappears, this log says which session
|
||||
/// took which path and when, so we can tell a code regression (`raw-port` /
|
||||
/// `launched` while the relay was up) from Chrome's own extension-debugger
|
||||
/// consent UX. Low volume (one line per connection); best-effort, never fails a
|
||||
/// connection.
|
||||
pub fn log_connect_mode(ws_url: &str, launched: bool, session: &str) {
|
||||
let relay = relay_url();
|
||||
let relay_up = relay.is_some();
|
||||
let mode = if launched {
|
||||
"launched(debug-port)"
|
||||
} else if relay.as_deref() == Some(ws_url) {
|
||||
"relay"
|
||||
} else if ws_url.contains("127.0.0.1") || ws_url.contains("localhost") {
|
||||
"raw-port-attach"
|
||||
} else {
|
||||
"remote-ws"
|
||||
};
|
||||
// A raw-port attach or a self-launch while the relay was available is the
|
||||
// exact thing that pops the consent modal — flag it loudly in the line.
|
||||
let suspect = (mode == "raw-port-attach" || launched) && relay_up;
|
||||
let line = format!(
|
||||
"session={session} mode={mode} relay_up={relay_up}{} ws={ws_url}\n",
|
||||
if suspect { " CONSENT-MODAL-RISK" } else { "" }
|
||||
);
|
||||
if let Some(home) = dirs::home_dir() {
|
||||
let path = home.join(".chrome-use").join("connect-mode.log");
|
||||
use std::io::Write;
|
||||
if let Ok(mut f) = std::fs::OpenOptions::new()
|
||||
.create(true)
|
||||
.append(true)
|
||||
.open(&path)
|
||||
{
|
||||
let _ = f.write_all(line.as_bytes());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Sidecar recording the connected extension's version, written by the host when
|
||||
/// it receives the extension's `hello` (sibling of `relay-cdp-url`). Lets
|
||||
/// `doctor` surface which extension build is live without a CDP round-trip.
|
||||
|
||||
@@ -893,6 +893,14 @@ fn main() {
|
||||
return;
|
||||
}
|
||||
|
||||
// `sessions` is a natural top-level guess for "list my sessions" (the skill
|
||||
// advertises sessions as a feature) — route it to the daemon inventory the
|
||||
// same way `daemon status` does (issue #29).
|
||||
if clean.first().map(|s| s.as_str()) == Some("sessions") {
|
||||
run_daemon(&["sessions".to_string(), "status".to_string()], flags.json);
|
||||
return;
|
||||
}
|
||||
|
||||
// Handle close --all: close all active sessions
|
||||
if matches!(
|
||||
clean.first().map(|s| s.as_str()),
|
||||
@@ -1361,6 +1369,20 @@ fn main() {
|
||||
&& flags.provider.is_none()
|
||||
&& (flags.force_launch || !flags.auto_connect)
|
||||
{
|
||||
// Launching a debug-port Chrome pops Chrome's "Allow remote debugging?"
|
||||
// consent modal (Chrome 136+). When the ab-connect relay is already up,
|
||||
// this is almost always unintended — the relay drives the user's real
|
||||
// Chrome with NO modal. Warn so the modal is self-explained and the
|
||||
// caller (often a stray --launch / --no-auto-connect) is fixable (#32).
|
||||
if !flags.json && connect::relay_url().is_some() {
|
||||
eprintln!(
|
||||
"{} launching a new Chrome with a debug port — this pops Chrome's \
|
||||
\"Allow remote debugging?\" modal.\n The ab-connect relay is up; \
|
||||
drop --launch/--new (and don't pass --no-auto-connect) to drive your \
|
||||
real Chrome with no modal.",
|
||||
color::warning_indicator()
|
||||
);
|
||||
}
|
||||
let mut launch_cmd = json!({
|
||||
"id": gen_id(),
|
||||
"action": "launch",
|
||||
|
||||
+320
-12
@@ -1341,6 +1341,7 @@ pub async fn execute_command(cmd: &Value, state: &mut DaemonState) -> Value {
|
||||
"forward" => handle_forward(state).await,
|
||||
"reload" => handle_reload(state).await,
|
||||
"cookies_get" => handle_cookies_get(cmd, state).await,
|
||||
"cf_status" => handle_cf_status(cmd, state).await,
|
||||
"cookies_set" => handle_cookies_set(cmd, state).await,
|
||||
"cookies_clear" => handle_cookies_clear(state).await,
|
||||
"storage_get" => handle_storage_get(cmd, state).await,
|
||||
@@ -2999,6 +3000,14 @@ async fn handle_screenshot(cmd: &Value, state: &mut DaemonState) -> Result<Value
|
||||
.get("screenshotDir")
|
||||
.and_then(|v| v.as_str())
|
||||
.map(String::from),
|
||||
clip: cmd.get("clip").and_then(|c| {
|
||||
Some((
|
||||
c.get("x")?.as_f64()?,
|
||||
c.get("y")?.as_f64()?,
|
||||
c.get("width")?.as_f64()?,
|
||||
c.get("height")?.as_f64()?,
|
||||
))
|
||||
}),
|
||||
};
|
||||
|
||||
if annotate {
|
||||
@@ -3458,17 +3467,169 @@ async fn handle_scroll(cmd: &Value, state: &mut DaemonState) -> Result<Value, St
|
||||
}
|
||||
}
|
||||
|
||||
interaction::scroll(
|
||||
&mgr.client,
|
||||
&session_id,
|
||||
&state.ref_map,
|
||||
selector,
|
||||
dx,
|
||||
dy,
|
||||
&state.iframe_sessions,
|
||||
)
|
||||
.await?;
|
||||
Ok(json!({ "scrolled": true }))
|
||||
// An explicit `--selector` keeps the precise element-scroll path (scrollBy on
|
||||
// the resolved node, same-origin only).
|
||||
if let Some(sel) = selector {
|
||||
interaction::scroll(
|
||||
&mgr.client,
|
||||
&session_id,
|
||||
&state.ref_map,
|
||||
Some(sel),
|
||||
dx,
|
||||
dy,
|
||||
&state.iframe_sessions,
|
||||
)
|
||||
.await?;
|
||||
return Ok(json!({ "scrolled": true, "via": "selector" }));
|
||||
}
|
||||
|
||||
// No selector: dispatch a real (isTrusted) wheel at a viewport coordinate.
|
||||
// This hits the compositor and scrolls whatever scroll container is under the
|
||||
// pointer — including cross-origin iframes that `window.scrollBy` on the top
|
||||
// document silently no-ops on (issue #36). The coordinate is, in priority:
|
||||
// --at x,y → that exact pixel
|
||||
// --frame n → the center of frame n from `chrome-use frames`
|
||||
// default → the viewport center
|
||||
let (x, y, via) = if let Some(at) = cmd.get("at").and_then(|v| v.as_array()) {
|
||||
let x = at.first().and_then(|v| v.as_f64()).unwrap_or(0.0);
|
||||
let y = at.get(1).and_then(|v| v.as_f64()).unwrap_or(0.0);
|
||||
(x, y, "at")
|
||||
} 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?;
|
||||
(x, y, "frame")
|
||||
} else {
|
||||
let (x, y) = viewport_center(mgr, &session_id).await?;
|
||||
(x, y, "center")
|
||||
};
|
||||
|
||||
dispatch_wheel(&mgr.client, &session_id, x, y, dx, dy).await?;
|
||||
Ok(json!({ "scrolled": true, "via": via, "at": [x, y] }))
|
||||
}
|
||||
|
||||
/// Viewport center in CSS pixels, used as the default wheel landing point for
|
||||
/// `scroll` (issue #36). Falls back to a sane 640×400 center if the page can't
|
||||
/// be evaluated (e.g. a restricted document).
|
||||
async fn viewport_center(mgr: &BrowserManager, session_id: &str) -> Result<(f64, f64), String> {
|
||||
let dims = mgr
|
||||
.client
|
||||
.send_command_typed::<_, Value>(
|
||||
"Runtime.evaluate",
|
||||
&super::cdp::types::EvaluateParams {
|
||||
expression: "[window.innerWidth, window.innerHeight]".to_string(),
|
||||
return_by_value: Some(true),
|
||||
await_promise: Some(false),
|
||||
},
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.ok();
|
||||
let arr = dims
|
||||
.as_ref()
|
||||
.and_then(|v| v.get("result"))
|
||||
.and_then(|v| v.get("value"))
|
||||
.and_then(|v| v.as_array());
|
||||
let w = arr
|
||||
.and_then(|a| a.first())
|
||||
.and_then(|v| v.as_f64())
|
||||
.filter(|w| *w > 0.0)
|
||||
.unwrap_or(1280.0);
|
||||
let h = arr
|
||||
.and_then(|a| a.get(1))
|
||||
.and_then(|v| v.as_f64())
|
||||
.filter(|h| *h > 0.0)
|
||||
.unwrap_or(800.0);
|
||||
Ok((w / 2.0, h / 2.0))
|
||||
}
|
||||
|
||||
/// Center of the `n`-th frame (as listed by `chrome-use frames`) in top-viewport
|
||||
/// CSS pixels, so `scroll --frame n` lands its wheel inside a cross-origin iframe
|
||||
/// without needing a selector into it (issue #36). Resolves the frame's owning
|
||||
/// `<iframe>` element box via `DOM.getFrameOwner` + `DOM.getBoxModel` — exact for
|
||||
/// a frame nested directly under the top document; for a deeper nesting the box is
|
||||
/// relative to the intermediate frame, so prefer `--at x,y` from a screenshot.
|
||||
async fn frame_center(
|
||||
mgr: &BrowserManager,
|
||||
session_id: &str,
|
||||
iframe_sessions: &HashMap<String, String>,
|
||||
n: usize,
|
||||
) -> Result<(f64, f64), String> {
|
||||
let frames =
|
||||
super::element::collect_all_frames_text(&mgr.client, session_id, iframe_sessions).await?;
|
||||
let frame = frames.get(n).ok_or_else(|| {
|
||||
format!(
|
||||
"frame index {} out of range (run `chrome-use frames`: {} frame(s))",
|
||||
n,
|
||||
frames.len()
|
||||
)
|
||||
})?;
|
||||
if n == 0 {
|
||||
// Frame 0 is the top document — there's no owner element; scroll its center.
|
||||
return viewport_center(mgr, session_id).await;
|
||||
}
|
||||
let owner = mgr
|
||||
.client
|
||||
.send_command_typed::<_, Value>(
|
||||
"DOM.getFrameOwner",
|
||||
&json!({ "frameId": frame.frame_id }),
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("can't locate frame {}'s owner element: {}", n, e))?;
|
||||
let backend_node_id = owner
|
||||
.get("backendNodeId")
|
||||
.and_then(|v| v.as_i64())
|
||||
.ok_or_else(|| format!("frame {} has no owner <iframe> element", n))?;
|
||||
let box_model = mgr
|
||||
.client
|
||||
.send_command_typed::<_, Value>(
|
||||
"DOM.getBoxModel",
|
||||
&json!({ "backendNodeId": backend_node_id }),
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("can't measure frame {}'s box: {}", n, e))?;
|
||||
let content = box_model
|
||||
.get("model")
|
||||
.and_then(|m| m.get("content"))
|
||||
.and_then(|c| c.as_array())
|
||||
.ok_or_else(|| format!("frame {} box model has no content quad", n))?;
|
||||
let coord = |i: usize| content.get(i).and_then(|v| v.as_f64()).unwrap_or(0.0);
|
||||
// content quad is [x1,y1, x2,y2, x3,y3, x4,y4]; opposite corners are 0 and 2.
|
||||
let cx = (coord(0) + coord(4)) / 2.0;
|
||||
let cy = (coord(1) + coord(5)) / 2.0;
|
||||
Ok((cx, cy))
|
||||
}
|
||||
|
||||
/// Dispatch a trusted mouse wheel at `(x, y)`, humanized like `handle_wheel`.
|
||||
async fn dispatch_wheel(
|
||||
client: &super::cdp::client::CdpClient,
|
||||
session_id: &str,
|
||||
x: f64,
|
||||
y: f64,
|
||||
delta_x: f64,
|
||||
delta_y: f64,
|
||||
) -> Result<(), String> {
|
||||
let level = humanize::active_level();
|
||||
let seed = humanize::next_seed();
|
||||
for (dx, dy, delay) in humanize::scroll_segments(delta_x, delta_y, level, seed) {
|
||||
client
|
||||
.send_command(
|
||||
"Input.dispatchMouseEvent",
|
||||
Some(json!({
|
||||
"type": "mouseWheel",
|
||||
"x": x,
|
||||
"y": y,
|
||||
"deltaX": dx,
|
||||
"deltaY": dy,
|
||||
})),
|
||||
Some(session_id),
|
||||
)
|
||||
.await?;
|
||||
if !delay.is_zero() {
|
||||
tokio::time::sleep(delay).await;
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn handle_select(cmd: &Value, state: &mut DaemonState) -> Result<Value, String> {
|
||||
@@ -3628,6 +3789,15 @@ async fn handle_gettext(cmd: &Value, state: &mut DaemonState) -> Result<Value, S
|
||||
}));
|
||||
}
|
||||
|
||||
// `get text --pierce` reads text through CLOSED shadow roots and child
|
||||
// documents via the CDP DOM tree — content `innerText`/`eval` can't see,
|
||||
// e.g. an extension's injected panel in a closed shadow DOM (#30).
|
||||
if cmd.get("pierce").and_then(|v| v.as_bool()) == Some(true) {
|
||||
let text = super::element::get_pierced_text(&mgr.client, &session_id).await?;
|
||||
let url = mgr.get_url().await.unwrap_or_default();
|
||||
return Ok(json!({ "text": text, "origin": url, "pierce": 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) {
|
||||
@@ -4113,6 +4283,108 @@ async fn handle_cookies_clear(state: &DaemonState) -> Result<Value, String> {
|
||||
Ok(json!({ "cleared": true }))
|
||||
}
|
||||
|
||||
// Detect whether the active page is *currently* a Cloudflare challenge
|
||||
// (the full-page "Just a moment…" / "正在进行安全验证" interstitial), so an agent
|
||||
// knows whether it must solve or can proceed. Runs in the top frame main world.
|
||||
const CF_CHALLENGE_JS: &str = r#"(function(){
|
||||
var t = document.title || '';
|
||||
var challenged =
|
||||
/just a moment|attention required|checking (your|if)|verify you are human|正在进行安全验证|安全验证|请稍候|请完成|人机验证/i.test(t) ||
|
||||
!!document.querySelector('#challenge-form, #challenge-running, #cf-challenge-running, [id^="cf-chl"], script[src*="/cdn-cgi/challenge-platform/"]');
|
||||
var turnstile = !!document.querySelector('.cf-turnstile, [data-sitekey]');
|
||||
return JSON.stringify({ title: t, challenged: challenged, turnstile: turnstile, readyState: document.readyState });
|
||||
})()"#;
|
||||
|
||||
/// Recommendation for a Cloudflare-gated page, from the current challenge state
|
||||
/// and whether a still-valid `cf_clearance` exists. Pure so it's unit-testable.
|
||||
/// - not challenged → "proceed" (the page is cleared/loaded)
|
||||
/// - challenged, valid cookie → "reissue" (clearance present but page still
|
||||
/// blocks → it's stale or the IP/UA no longer matches what it was issued for)
|
||||
/// - challenged, no cookie → "solve"
|
||||
fn cf_recommendation(challenged: bool, clearance_valid: bool) -> &'static str {
|
||||
if !challenged {
|
||||
"proceed"
|
||||
} else if clearance_valid {
|
||||
"reissue"
|
||||
} else {
|
||||
"solve"
|
||||
}
|
||||
}
|
||||
|
||||
/// `cf_clearance` validity for a cookie's expiry (epoch seconds; <=0 = session
|
||||
/// cookie, treated as non-expiring). Returns (present, expired). Pure.
|
||||
fn clearance_state(expires: Option<f64>, now: f64) -> (bool, bool) {
|
||||
match expires {
|
||||
None => (false, false),
|
||||
Some(e) if e <= 0.0 => (true, false), // session cookie: no expiry
|
||||
Some(e) => (true, e < now),
|
||||
}
|
||||
}
|
||||
|
||||
async fn handle_cf_status(_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 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 = parse_json_string(probe_raw, "cf challenge probe").unwrap_or(Value::Null);
|
||||
let challenged = probe
|
||||
.get("challenged")
|
||||
.and_then(|v| v.as_bool())
|
||||
.unwrap_or(false);
|
||||
let turnstile = probe
|
||||
.get("turnstile")
|
||||
.and_then(|v| v.as_bool())
|
||||
.unwrap_or(false);
|
||||
let title = probe
|
||||
.get("title")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("")
|
||||
.to_string();
|
||||
|
||||
// 2. Persistence artifacts: cf_clearance (HttpOnly → must read via CDP, not
|
||||
// document.cookie) + CF_VERIFIED_DEVICE. Scope to the current URL.
|
||||
let urls = if url.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(vec![url.clone()])
|
||||
};
|
||||
let cookies = super::cookies::get_cookies(&mgr.client, &session_id, urls)
|
||||
.await
|
||||
.unwrap_or_default();
|
||||
let clearance = cookies.iter().find(|c| c.name == "cf_clearance");
|
||||
let now = std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.map(|d| d.as_secs_f64())
|
||||
.unwrap_or(0.0);
|
||||
let (present, expired) = clearance_state(clearance.map(|c| c.expires), now);
|
||||
let expires_in = clearance
|
||||
.filter(|_| present && !expired)
|
||||
.map(|c| (c.expires - now).max(0.0) as i64);
|
||||
let device_verified = cookies
|
||||
.iter()
|
||||
.any(|c| c.name.starts_with("CF_VERIFIED_DEVICE"));
|
||||
|
||||
let clearance_valid = present && !expired;
|
||||
let recommendation = cf_recommendation(challenged, clearance_valid);
|
||||
|
||||
Ok(json!({
|
||||
"url": url,
|
||||
"title": title,
|
||||
"challenged": challenged,
|
||||
"turnstile": turnstile,
|
||||
"clearance": {
|
||||
"present": present,
|
||||
"expired": expired,
|
||||
"expiresIn": expires_in,
|
||||
"httpOnly": clearance.map(|c| c.http_only).unwrap_or(false),
|
||||
},
|
||||
"deviceVerified": device_verified,
|
||||
"recommendation": recommendation,
|
||||
}))
|
||||
}
|
||||
|
||||
async fn handle_storage_get(cmd: &Value, state: &DaemonState) -> Result<Value, String> {
|
||||
let mgr = state.browser.as_ref().ok_or("Browser not launched")?;
|
||||
let session_id = mgr.active_session_id()?.to_string();
|
||||
@@ -4561,7 +4833,22 @@ async fn handle_tab_switch(cmd: &Value, state: &mut DaemonState) -> Result<Value
|
||||
state.ref_map.clear();
|
||||
state.iframe_sessions.clear();
|
||||
state.active_frame_id = None;
|
||||
let result = mgr.tab_switch_by_id(tab_id).await?;
|
||||
let mut result = mgr.tab_switch_by_id(tab_id).await?;
|
||||
|
||||
// Liveness probe: confirm the new session actually answers before we report
|
||||
// success, so `tab <id>` doesn't print a misleading ✓ for a session that's
|
||||
// stale and will fail on the very next command (issue #29.3). On the churned
|
||||
// -tabId case the ext-0.4.9 targetId recovery (#24) self-heals within ~6s, so
|
||||
// we surface a warning rather than a hard error to avoid a false failure
|
||||
// during that window.
|
||||
if mgr.evaluate("1", None).await.is_err() {
|
||||
if let Some(obj) = result.as_object_mut() {
|
||||
obj.insert(
|
||||
"warning".to_string(),
|
||||
json!("switched tab is not responding yet (session re-attaching); retry the next command"),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// `--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
|
||||
@@ -7319,6 +7606,7 @@ async fn handle_diff_screenshot(cmd: &Value, state: &DaemonState) -> Result<Valu
|
||||
quality: None,
|
||||
annotate: false,
|
||||
output_dir: None,
|
||||
clip: None,
|
||||
};
|
||||
|
||||
let result = screenshot::take_screenshot(
|
||||
@@ -9045,6 +9333,26 @@ mod tests {
|
||||
use crate::test_utils::EnvGuard;
|
||||
use std::fs;
|
||||
|
||||
#[test]
|
||||
fn test_cf_recommendation() {
|
||||
assert_eq!(cf_recommendation(false, false), "proceed");
|
||||
assert_eq!(cf_recommendation(false, true), "proceed");
|
||||
assert_eq!(cf_recommendation(true, false), "solve");
|
||||
assert_eq!(cf_recommendation(true, true), "reissue");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_clearance_state() {
|
||||
// no cookie
|
||||
assert_eq!(clearance_state(None, 1000.0), (false, false));
|
||||
// session cookie (expires <= 0) → present, never expired
|
||||
assert_eq!(clearance_state(Some(-1.0), 1000.0), (true, false));
|
||||
// valid: expiry in the future
|
||||
assert_eq!(clearance_state(Some(2000.0), 1000.0), (true, false));
|
||||
// expired: expiry in the past
|
||||
assert_eq!(clearance_state(Some(500.0), 1000.0), (true, true));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_url_glob_to_regex() {
|
||||
assert_eq!(url_glob_to_regex("**/dashboard"), "^.*/dashboard$");
|
||||
|
||||
+373
-38
@@ -121,7 +121,7 @@ fn normalize_url_for_match(url: &str) -> String {
|
||||
fn update_page_target_info_in_pages(pages: &mut [PageInfo], target: &TargetInfo) -> bool {
|
||||
if let Some(page) = pages.iter_mut().find(|p| p.target_id == target.target_id) {
|
||||
page.url = target.url.clone();
|
||||
page.title = target.title.clone();
|
||||
page.title = sanitize_title(&target.title);
|
||||
page.target_type = target.target_type.clone();
|
||||
return true;
|
||||
}
|
||||
@@ -166,6 +166,75 @@ fn resolve_active_index(
|
||||
active_page_index
|
||||
}
|
||||
|
||||
/// Strip zero-width / invisible / bidi-format Unicode from a page title before
|
||||
/// we store it. Some sites prepend runs of ZWJ / word-joiner / invisible-times /
|
||||
/// BOM to `document.title` (badging, watermarking, anti-scrape); left in, they
|
||||
/// pollute `tab list`, break text matching, and wreck column alignment (#33).
|
||||
fn sanitize_title(s: &str) -> String {
|
||||
s.chars()
|
||||
.filter(|&c| {
|
||||
!matches!(c as u32,
|
||||
0x00AD // soft hyphen
|
||||
| 0x200B..=0x200F // ZWSP, ZWNJ, ZWJ, LRM, RLM
|
||||
| 0x2028 | 0x2029 // line / paragraph separators
|
||||
| 0x202A..=0x202E // bidi embedding/override
|
||||
| 0x2060..=0x2064 // word joiner, invisible operators
|
||||
| 0x2066..=0x2069 // bidi isolates
|
||||
| 0x180E // Mongolian vowel separator
|
||||
| 0xFEFF // BOM / ZW no-break space
|
||||
)
|
||||
})
|
||||
.collect::<String>()
|
||||
.trim()
|
||||
.to_string()
|
||||
}
|
||||
|
||||
/// Best-effort MIME type from a filename extension, for the relay file-upload
|
||||
/// fallback (the page-constructed `File` needs a sensible `type`). Covers the
|
||||
/// common upload kinds; anything unknown falls back to a generic binary type.
|
||||
fn mime_for_path(name: &str) -> &'static str {
|
||||
let ext = name.rsplit('.').next().unwrap_or("").to_lowercase();
|
||||
match ext.as_str() {
|
||||
"png" => "image/png",
|
||||
"jpg" | "jpeg" => "image/jpeg",
|
||||
"gif" => "image/gif",
|
||||
"webp" => "image/webp",
|
||||
"svg" => "image/svg+xml",
|
||||
"bmp" => "image/bmp",
|
||||
"pdf" => "application/pdf",
|
||||
"txt" => "text/plain",
|
||||
"csv" => "text/csv",
|
||||
"json" => "application/json",
|
||||
"mp4" => "video/mp4",
|
||||
"webm" => "video/webm",
|
||||
"mov" => "video/quicktime",
|
||||
"mp3" => "audio/mpeg",
|
||||
"zip" => "application/zip",
|
||||
_ => "application/octet-stream",
|
||||
}
|
||||
}
|
||||
|
||||
/// Target ids to prune after a `Target.getTargets` resync: tracked pages whose
|
||||
/// target is no longer in the live set — EXCEPT the explicitly-pinned active
|
||||
/// target, which is protected. The relay against a busy real Chrome occasionally
|
||||
/// returns a different window's tabs for a single `getTargets` call ("tab list
|
||||
/// hops windows", issue #31); pruning on that transient snapshot would drop the
|
||||
/// agent's adopted tab and drift subsequent eval/click onto a foreign tab. A
|
||||
/// genuine close still arrives as `Target.targetDestroyed` (handled in the event
|
||||
/// drain), which removes the pin properly — so protecting it here only guards
|
||||
/// against flaky snapshots, not real closures.
|
||||
fn prunable_target_ids(
|
||||
pages: &[PageInfo],
|
||||
live_ids: &HashSet<String>,
|
||||
pinned: Option<&str>,
|
||||
) -> Vec<String> {
|
||||
pages
|
||||
.iter()
|
||||
.map(|p| p.target_id.clone())
|
||||
.filter(|tid| !live_ids.contains(tid) && pinned != Some(tid.as_str()))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Whether the resolved active page is a tab the session created (its target_id
|
||||
/// is in `created_targets`). Pure core of [`BrowserManager::active_is_session_owned`]
|
||||
/// so the relay no-hijack rule is unit-testable without a live browser.
|
||||
@@ -185,6 +254,21 @@ fn active_index_is_owned(
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
/// Whether a CDP error means the bound relay target is gone — the tab was
|
||||
/// closed, navigated across processes (renderer swap), or lost after an
|
||||
/// extension/service-worker restart, and the relay could not re-attach. The
|
||||
/// ab-connect relay surfaces these as `stale sessionId … its tab is gone`,
|
||||
/// `unknown sessionId …`, or `no attached tab …`. `navigate` keys its
|
||||
/// auto-reattach recovery off this (issue #35) so a dead session rebinds to a
|
||||
/// fresh tab instead of erroring on every command until the user runs `tab new`.
|
||||
fn is_stale_target_error(error: &str) -> bool {
|
||||
let lower = error.to_lowercase();
|
||||
lower.contains("its tab is gone")
|
||||
|| lower.contains("stale sessionid")
|
||||
|| lower.contains("unknown sessionid")
|
||||
|| lower.contains("no attached tab")
|
||||
}
|
||||
|
||||
/// Converts common error messages into AI-friendly, actionable descriptions.
|
||||
pub fn to_ai_friendly_error(error: &str) -> String {
|
||||
let lower = error.to_lowercase();
|
||||
@@ -490,6 +574,13 @@ impl BrowserManager {
|
||||
}
|
||||
};
|
||||
|
||||
// A launched browser carries a debug port → it's the other path that can
|
||||
// pop Chrome's consent modal; record it for #31 diagnosis.
|
||||
crate::connect::log_connect_mode(
|
||||
&ws_url,
|
||||
true,
|
||||
DAEMON_SESSION.get().map(String::as_str).unwrap_or("default"),
|
||||
);
|
||||
let manager = if engine == "lightpanda" {
|
||||
initialize_lightpanda_manager(ws_url, process).await?
|
||||
} else {
|
||||
@@ -585,6 +676,13 @@ impl BrowserManager {
|
||||
headers: Option<Vec<(String, String)>>,
|
||||
) -> Result<Self, String> {
|
||||
let ws_url = resolve_cdp_url(url).await?;
|
||||
// Record the transport so a reappearing "Allow remote debugging?" modal
|
||||
// can be traced to a raw-port attach vs the consent-free relay (#31).
|
||||
crate::connect::log_connect_mode(
|
||||
&ws_url,
|
||||
false,
|
||||
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 {
|
||||
client,
|
||||
@@ -713,7 +811,7 @@ impl BrowserManager {
|
||||
target_id: target.target_id.clone(),
|
||||
session_id: attach_result.session_id.clone(),
|
||||
url: target.url.clone(),
|
||||
title: target.title.clone(),
|
||||
title: sanitize_title(&target.title),
|
||||
target_type: target.target_type.clone(),
|
||||
});
|
||||
}
|
||||
@@ -832,6 +930,24 @@ impl BrowserManager {
|
||||
)
|
||||
}
|
||||
|
||||
/// Drop the page bound to `session_id` from the tracked list — used when the
|
||||
/// relay reports its tab is gone (issue #35) so the stale entry can't keep
|
||||
/// resolving as active. Forgets ownership, unpins it if it was pinned, and
|
||||
/// keeps `active_page_index` in range.
|
||||
fn drop_page_by_session(&mut self, session_id: &str) {
|
||||
let Some(pos) = self.pages.iter().position(|p| p.session_id == session_id) else {
|
||||
return;
|
||||
};
|
||||
let target_id = self.pages[pos].target_id.clone();
|
||||
self.pages.remove(pos);
|
||||
self.created_targets.remove(&target_id);
|
||||
if self.active_target_id.as_deref() == Some(target_id.as_str()) {
|
||||
self.active_target_id = None;
|
||||
}
|
||||
self.active_page_index =
|
||||
active_page_index_after_removal(self.active_page_index, pos, self.pages.len());
|
||||
}
|
||||
|
||||
/// 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) {
|
||||
@@ -861,10 +977,10 @@ impl BrowserManager {
|
||||
if self.agent_group().is_some() && !self.active_is_session_owned() {
|
||||
self.tab_new(None, None).await?;
|
||||
}
|
||||
let session_id = self.active_session_id()?.to_string();
|
||||
let mut session_id = self.active_session_id()?.to_string();
|
||||
let mut lifecycle_rx = self.client.subscribe();
|
||||
|
||||
let nav_result: PageNavigateResult = self
|
||||
let nav_result: PageNavigateResult = match self
|
||||
.client
|
||||
.send_command_typed(
|
||||
"Page.navigate",
|
||||
@@ -874,7 +990,38 @@ impl BrowserManager {
|
||||
},
|
||||
Some(&session_id),
|
||||
)
|
||||
.await?;
|
||||
.await
|
||||
{
|
||||
Ok(r) => r,
|
||||
// Auto-reattach when the bound tab is gone (issue #35). On the shared
|
||||
// real browser the human can close/swap the agent's tab, and a
|
||||
// cross-process nav can destroy the target without a re-attachable
|
||||
// tabId — both leave the cached `cb-tab-<id>` session stale, so every
|
||||
// command (including `open`) failed on it and only `tab new`
|
||||
// recovered. The relay error literally says "re-open your target URL
|
||||
// to re-attach"; fulfil that here: drop the dead page, open a fresh
|
||||
// owned tab in this session's group, and navigate THAT. Gated on the
|
||||
// relay (`agent_group`) and on the explicit navigation intent — read
|
||||
// commands deliberately still fail loudly rather than silently
|
||||
// recover onto a blank tab and return wrong data (issue #8.1).
|
||||
Err(e) if self.agent_group().is_some() && is_stale_target_error(&e) => {
|
||||
self.drop_page_by_session(&session_id);
|
||||
self.tab_new(None, None).await?;
|
||||
session_id = self.active_session_id()?.to_string();
|
||||
lifecycle_rx = self.client.subscribe();
|
||||
self.client
|
||||
.send_command_typed(
|
||||
"Page.navigate",
|
||||
&PageNavigateParams {
|
||||
url: url.to_string(),
|
||||
referrer: None,
|
||||
},
|
||||
Some(&session_id),
|
||||
)
|
||||
.await?
|
||||
}
|
||||
Err(e) => return Err(e),
|
||||
};
|
||||
|
||||
if let Some(ref error_text) = nav_result.error_text {
|
||||
return Err(format!("Navigation failed: {}", error_text));
|
||||
@@ -939,7 +1086,7 @@ impl BrowserManager {
|
||||
self.active_page_index = self.resolved_active_index();
|
||||
if let Some(page) = self.pages.get_mut(self.active_page_index) {
|
||||
page.url = page_url.clone();
|
||||
page.title = title.clone();
|
||||
page.title = sanitize_title(&title);
|
||||
}
|
||||
self.pin_active_target();
|
||||
|
||||
@@ -1001,7 +1148,7 @@ impl BrowserManager {
|
||||
|
||||
pub async fn get_title(&self) -> Result<String, String> {
|
||||
let result = self.evaluate_simple("document.title").await?;
|
||||
Ok(result.as_str().unwrap_or("").to_string())
|
||||
Ok(sanitize_title(result.as_str().unwrap_or("")))
|
||||
}
|
||||
|
||||
pub async fn get_content(&self) -> Result<String, String> {
|
||||
@@ -1344,7 +1491,7 @@ impl BrowserManager {
|
||||
target_id: target.target_id.clone(),
|
||||
session_id: attach.session_id.clone(),
|
||||
url: target.url.clone(),
|
||||
title: target.title.clone(),
|
||||
title: sanitize_title(&target.title),
|
||||
target_type: target.target_type.clone(),
|
||||
};
|
||||
self.add_background_page(page.clone());
|
||||
@@ -1405,19 +1552,16 @@ impl BrowserManager {
|
||||
target_id: target.target_id.clone(),
|
||||
session_id: attach_result.session_id.clone(),
|
||||
url: target.url.clone(),
|
||||
title: target.title.clone(),
|
||||
title: sanitize_title(&target.title),
|
||||
target_type: target.target_type.clone(),
|
||||
});
|
||||
let _ = self.enable_domains(&attach_result.session_id).await;
|
||||
}
|
||||
|
||||
// Drop tabs that no longer exist so `tab list` doesn't show phantom rows.
|
||||
let gone: Vec<String> = self
|
||||
.pages
|
||||
.iter()
|
||||
.map(|p| p.target_id.clone())
|
||||
.filter(|tid| !live_ids.contains(tid))
|
||||
.collect();
|
||||
// Drop tabs that no longer exist so `tab list` doesn't show phantom rows —
|
||||
// but never prune the explicitly-pinned active target on a transient
|
||||
// getTargets snapshot (issue #31; see `prunable_target_ids`).
|
||||
let gone = prunable_target_ids(&self.pages, &live_ids, self.active_target_id.as_deref());
|
||||
for tid in gone {
|
||||
self.remove_page_by_target_id(&tid);
|
||||
}
|
||||
@@ -1451,7 +1595,7 @@ impl BrowserManager {
|
||||
}
|
||||
}
|
||||
if let Some(t) = ti.get("title").and_then(|v| v.as_str()) {
|
||||
page.title = t.to_string();
|
||||
page.title = sanitize_title(t);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1639,7 +1783,7 @@ impl BrowserManager {
|
||||
|
||||
if let Some(page) = self.pages.get_mut(index) {
|
||||
page.url = url.clone();
|
||||
page.title = title.clone();
|
||||
page.title = sanitize_title(&title);
|
||||
}
|
||||
|
||||
let page = &self.pages[index];
|
||||
@@ -1894,7 +2038,8 @@ impl BrowserManager {
|
||||
.and_then(|v| v.as_i64())
|
||||
.ok_or("Could not get backendNodeId for file input")?;
|
||||
|
||||
self.client
|
||||
let set_files = self
|
||||
.client
|
||||
.send_command(
|
||||
"DOM.setFileInputFiles",
|
||||
Some(json!({
|
||||
@@ -1903,26 +2048,153 @@ impl BrowserManager {
|
||||
})),
|
||||
Some(&effective_session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| {
|
||||
// Chrome's chrome.debugger API (the extension-relay transport)
|
||||
// forbids DOM.setFileInputFiles for security, surfacing as an
|
||||
// opaque `-32000 "Not allowed"`. Translate it into an actionable
|
||||
// message rather than leaking the raw CDP error (issue #13).
|
||||
if e.contains("Not allowed") || e.contains("-32000") {
|
||||
"file upload isn't supported over the extension relay — \
|
||||
Chrome's chrome.debugger API forbids DOM.setFileInputFiles. \
|
||||
Use a direct-CDP session instead: \
|
||||
`chrome-use --session up --launch open <url>` (carry your \
|
||||
login over with `cookies export` | `cookies set --curl`), \
|
||||
then run `upload` in that session. \
|
||||
See https://github.com/leeguooooo/chrome-use/issues/13"
|
||||
.to_string()
|
||||
} else {
|
||||
e
|
||||
}
|
||||
})?;
|
||||
.await;
|
||||
|
||||
if let Err(e) = set_files {
|
||||
// Chrome's chrome.debugger API (the extension-relay transport) forbids
|
||||
// DOM.setFileInputFiles for security, surfacing as an opaque
|
||||
// `-32000 "Not allowed"`. Fall back to constructing the File entirely
|
||||
// IN THE PAGE and assigning it to the input — the standard
|
||||
// Playwright/Cypress trick, which needs no privileged CDP and so works
|
||||
// over the relay (issue #13).
|
||||
if e.contains("Not allowed") || e.contains("-32000") {
|
||||
return self
|
||||
.upload_files_via_page(object_id, files, &effective_session_id)
|
||||
.await;
|
||||
}
|
||||
return Err(e);
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Relay-safe file upload: read each file locally, hand its bytes to the page
|
||||
/// as base64, and rebuild a `File` there — then either assign it to a file
|
||||
/// `<input>` (Chrome allows `input.files = dataTransfer.files`) or, for a
|
||||
/// dropzone/composer, dispatch synthetic `paste`/`drop` events carrying the
|
||||
/// `DataTransfer`. No `DOM.setFileInputFiles`, so chrome.debugger permits it.
|
||||
async fn upload_files_via_page(
|
||||
&self,
|
||||
object_id: String,
|
||||
files: &[String],
|
||||
session_id: &str,
|
||||
) -> Result<(), String> {
|
||||
use base64::Engine;
|
||||
// The relay tunnels every CDP message through Chrome native messaging,
|
||||
// which caps a single message at ~1 MiB. A whole image's base64 blows
|
||||
// past that ("CDP response channel closed"), so we STREAM the bytes into
|
||||
// a page-side buffer in sub-limit chunks, then assemble the File from it.
|
||||
const CHUNK: usize = 96 * 1024; // base64 chars per message; safe under 1 MiB
|
||||
|
||||
// Reset the staging buffer.
|
||||
self.client
|
||||
.send_command(
|
||||
"Runtime.evaluate",
|
||||
Some(json!({ "expression": "window.__cuUpload = [];", "returnByValue": true })),
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("relay upload (reset) failed: {}", e))?;
|
||||
|
||||
for path in files {
|
||||
let bytes = std::fs::read(path).map_err(|e| format!("cannot read {}: {}", path, e))?;
|
||||
let name = std::path::Path::new(path)
|
||||
.file_name()
|
||||
.and_then(|n| n.to_str())
|
||||
.unwrap_or("upload.bin")
|
||||
.to_string();
|
||||
let mime = mime_for_path(&name);
|
||||
let b64 = base64::engine::general_purpose::STANDARD.encode(&bytes);
|
||||
|
||||
// Push the file's metadata with an empty buffer.
|
||||
let init = format!(
|
||||
"window.__cuUpload.push({{ name: {}, type: {}, b64: '' }});",
|
||||
serde_json::to_string(&name).unwrap_or_default(),
|
||||
serde_json::to_string(mime).unwrap_or_default(),
|
||||
);
|
||||
self.client
|
||||
.send_command(
|
||||
"Runtime.evaluate",
|
||||
Some(json!({ "expression": init, "returnByValue": true })),
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("relay upload (init) failed: {}", e))?;
|
||||
|
||||
// Stream the base64 in chunks. base64's alphabet (A–Za–z0–9+/=) needs
|
||||
// no escaping inside a single-quoted JS string, so concatenation is safe.
|
||||
let idx = "window.__cuUpload[window.__cuUpload.length-1].b64";
|
||||
let mut start = 0;
|
||||
while start < b64.len() {
|
||||
let end = (start + CHUNK).min(b64.len());
|
||||
let chunk = &b64[start..end];
|
||||
let expr = format!("{idx} += '{chunk}';");
|
||||
self.client
|
||||
.send_command(
|
||||
"Runtime.evaluate",
|
||||
Some(json!({ "expression": expr, "returnByValue": true })),
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("relay upload (chunk) failed: {}", e))?;
|
||||
start = end;
|
||||
}
|
||||
}
|
||||
|
||||
// Assemble the Files from the buffer and attach to the element, then clean up.
|
||||
let func = r#"function() {
|
||||
const filesData = window.__cuUpload || [];
|
||||
const dt = new DataTransfer();
|
||||
for (const f of filesData) {
|
||||
const bin = atob(f.b64);
|
||||
const arr = new Uint8Array(bin.length);
|
||||
for (let i = 0; i < bin.length; i++) arr[i] = bin.charCodeAt(i);
|
||||
dt.items.add(new File([arr], f.name, { type: f.type }));
|
||||
}
|
||||
try { delete window.__cuUpload; } catch (e) { window.__cuUpload = undefined; }
|
||||
const el = this;
|
||||
if (el.tagName === 'INPUT' && el.type === 'file') {
|
||||
el.files = dt.files;
|
||||
el.dispatchEvent(new Event('input', { bubbles: true }));
|
||||
el.dispatchEvent(new Event('change', { bubbles: true }));
|
||||
return 'input:' + dt.files.length;
|
||||
}
|
||||
// Dropzone / rich composer: replay paste then drop with the files.
|
||||
try { el.dispatchEvent(new ClipboardEvent('paste', { bubbles: true, clipboardData: dt })); } catch (e) {}
|
||||
try {
|
||||
const ev = new DragEvent('drop', { bubbles: true, cancelable: true });
|
||||
Object.defineProperty(ev, 'dataTransfer', { value: dt });
|
||||
el.dispatchEvent(ev);
|
||||
} catch (e) {}
|
||||
return 'event:' + dt.files.length;
|
||||
}"#;
|
||||
|
||||
let result: EvaluateResult = self
|
||||
.client
|
||||
.send_command_typed(
|
||||
"Runtime.callFunctionOn",
|
||||
&CallFunctionOnParams {
|
||||
function_declaration: func.to_string(),
|
||||
object_id: Some(object_id),
|
||||
arguments: None,
|
||||
return_by_value: Some(true),
|
||||
await_promise: Some(false),
|
||||
},
|
||||
Some(session_id),
|
||||
)
|
||||
.await
|
||||
.map_err(|e| format!("relay file-injection failed: {}", e))?;
|
||||
|
||||
if let Some(ref details) = result.exception_details {
|
||||
return Err(format!(
|
||||
"relay file-injection threw: {}",
|
||||
details
|
||||
.exception
|
||||
.as_ref()
|
||||
.and_then(|ex| ex.description.as_deref())
|
||||
.unwrap_or(&details.text)
|
||||
));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -2485,6 +2757,27 @@ mod tests {
|
||||
assert_eq!(active_page_index_after_removal(0, 0, 0), 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn stale_target_error_matches_relay_signatures() {
|
||||
// The exact relay error `open` must recover from (issue #35), as wrapped
|
||||
// by send_command's `CDP error (Page.navigate): …` prefix.
|
||||
assert!(is_stale_target_error(
|
||||
"CDP error (Page.navigate): stale sessionId cb-tab-1655244623 for Page.navigate: \
|
||||
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("no attached tab for Page.navigate"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
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("CDP command timed out: Page.navigate"));
|
||||
}
|
||||
|
||||
fn page(target_id: &str) -> PageInfo {
|
||||
PageInfo {
|
||||
tab_id: 1,
|
||||
@@ -2582,6 +2875,48 @@ mod tests {
|
||||
assert!(!active_index_is_owned(&[], None, 0, &created));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_sanitize_title() {
|
||||
// The exact pollution from #33: ZWJ / word-joiner / invisible-times / BOM
|
||||
// prepended to "GitHub".
|
||||
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(" Hello World "), "Hello World");
|
||||
// Emoji and real content survive; only the invisibles are dropped.
|
||||
assert_eq!(sanitize_title("✓ Done\u{200b}"), "✓ Done");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_mime_for_path() {
|
||||
assert_eq!(mime_for_path("a.png"), "image/png");
|
||||
assert_eq!(mime_for_path("PHOTO.JPG"), "image/jpeg");
|
||||
assert_eq!(mime_for_path("clip.webp"), "image/webp");
|
||||
assert_eq!(mime_for_path("doc.pdf"), "application/pdf");
|
||||
assert_eq!(mime_for_path("noext"), "application/octet-stream");
|
||||
assert_eq!(mime_for_path("weird.xyz"), "application/octet-stream");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_protects_pinned_target_on_transient_snapshot() {
|
||||
// The relay returned a getTargets snapshot missing the pinned tab "A"
|
||||
// (it hopped to another window). "B" is also absent. Without protection
|
||||
// both would be pruned and the next command would drift; with the pin
|
||||
// protected, only the genuinely-unpinned "B" is dropped (issue #31).
|
||||
let pages = vec![page("A"), page("B")];
|
||||
let live: HashSet<String> = HashSet::new(); // snapshot returned neither
|
||||
let gone = prunable_target_ids(&pages, &live, Some("A"));
|
||||
assert_eq!(gone, vec!["B".to_string()]);
|
||||
// With no pin, both are prunable (unchanged behavior).
|
||||
let gone_unpinned = prunable_target_ids(&pages, &live, None);
|
||||
assert_eq!(gone_unpinned.len(), 2);
|
||||
// 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()]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn resolve_active_index_pin_survives_passive_background_tab() {
|
||||
// A foreign tab ("Z") gets appended by passive discovery after we pinned
|
||||
|
||||
@@ -1169,6 +1169,69 @@ pub async fn get_main_content_text(client: &CdpClient, session_id: &str) -> Resu
|
||||
.to_string())
|
||||
}
|
||||
|
||||
// Text nodes whose parent is one of these carry no visible content.
|
||||
fn is_noise_tag(name: &str) -> bool {
|
||||
matches!(name, "SCRIPT" | "STYLE" | "NOSCRIPT" | "TEMPLATE" | "HEAD")
|
||||
}
|
||||
|
||||
// Walk a CDP DOM.Node tree, collecting text-node values. Unlike `innerText`
|
||||
// (JS, blocked by CLOSED shadow roots), the CDP DOM tree from
|
||||
// `DOM.getDocument(pierce:true)` includes closed shadow roots and child
|
||||
// documents — so this reaches text JS can't. `parent_noise` carries whether an
|
||||
// ancestor was <script>/<style>/etc so their text is skipped.
|
||||
fn collect_dom_text(node: &Value, parent_noise: bool, out: &mut String) {
|
||||
let node_type = node.get("nodeType").and_then(|v| v.as_i64()).unwrap_or(0);
|
||||
let node_name = node.get("nodeName").and_then(|v| v.as_str()).unwrap_or("");
|
||||
if node_type == 3 {
|
||||
if !parent_noise {
|
||||
if let Some(t) = node.get("nodeValue").and_then(|v| v.as_str()) {
|
||||
let t = t.trim();
|
||||
if !t.is_empty() {
|
||||
if !out.is_empty() {
|
||||
out.push(' ');
|
||||
}
|
||||
out.push_str(t);
|
||||
}
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
let noise = parent_noise || is_noise_tag(node_name);
|
||||
if let Some(children) = node.get("children").and_then(|v| v.as_array()) {
|
||||
for child in children {
|
||||
collect_dom_text(child, noise, out);
|
||||
}
|
||||
}
|
||||
if let Some(shadow) = node.get("shadowRoots").and_then(|v| v.as_array()) {
|
||||
for sr in shadow {
|
||||
collect_dom_text(sr, noise, out);
|
||||
}
|
||||
}
|
||||
if let Some(doc) = node.get("contentDocument") {
|
||||
collect_dom_text(doc, noise, out);
|
||||
}
|
||||
}
|
||||
|
||||
/// Extract text from the page via the CDP DOM tree with `pierce:true`, which
|
||||
/// reaches into CLOSED shadow roots and child documents that `innerText`/`eval`
|
||||
/// cannot. Lets an agent read content rendered into a closed shadow DOM (e.g. an
|
||||
/// extension's injected debug panel) without any extra Chrome permission — it
|
||||
/// rides the per-tab debugger session that's already attached (#30).
|
||||
pub async fn get_pierced_text(client: &CdpClient, session_id: &str) -> Result<String, String> {
|
||||
let doc = client
|
||||
.send_command(
|
||||
"DOM.getDocument",
|
||||
Some(serde_json::json!({ "depth": -1, "pierce": true })),
|
||||
Some(session_id),
|
||||
)
|
||||
.await?;
|
||||
let mut out = String::new();
|
||||
if let Some(root) = doc.get("root") {
|
||||
collect_dom_text(root, false, &mut out);
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
pub async fn get_element_attribute(
|
||||
client: &CdpClient,
|
||||
session_id: &str,
|
||||
@@ -1642,6 +1705,31 @@ mod tests {
|
||||
assert_eq!(parse_ref("@e123"), Some("e123".to_string()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_collect_dom_text_pierces_closed_shadow_and_skips_noise() {
|
||||
// A CDP DOM.Node tree: a host element whose CLOSED shadow root holds the
|
||||
// text, plus a <script> whose text must be skipped.
|
||||
let tree = serde_json::json!({
|
||||
"nodeType": 1, "nodeName": "BODY",
|
||||
"children": [
|
||||
{ "nodeType": 1, "nodeName": "SCRIPT",
|
||||
"children": [ { "nodeType": 3, "nodeName": "#text", "nodeValue": "var secret=1;" } ] },
|
||||
{ "nodeType": 1, "nodeName": "DIV",
|
||||
"shadowRoots": [
|
||||
{ "nodeType": 11, "nodeName": "#document-fragment",
|
||||
"children": [
|
||||
{ "nodeType": 1, "nodeName": "SPAN",
|
||||
"children": [ { "nodeType": 3, "nodeName": "#text", "nodeValue": "DECRYPTED 42" } ] }
|
||||
] }
|
||||
] }
|
||||
]
|
||||
});
|
||||
let mut out = String::new();
|
||||
collect_dom_text(&tree, false, &mut out);
|
||||
assert_eq!(out, "DECRYPTED 42");
|
||||
assert!(!out.contains("secret"), "script text must be skipped");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_parse_ref_equals_prefix() {
|
||||
assert_eq!(parse_ref("ref=e1"), Some("e1".to_string()));
|
||||
|
||||
@@ -45,6 +45,31 @@ pub async fn click(
|
||||
.await;
|
||||
}
|
||||
|
||||
// Over the extension relay we drive the user's real, in-use Chrome, where a
|
||||
// coordinate `Input.dispatchMouseEvent` is NOT reliably confined to our target
|
||||
// tab — it can be delivered to whatever tab is in the foreground, and an OOPIF
|
||||
// element's box can't be mapped to a top-viewport point at all. This twice
|
||||
// opened an unrelated tab on the user's busy Chrome (issues #31/#36). So on the
|
||||
// relay, never use coordinates for a normal left click: DOM-dispatch invokes
|
||||
// the element's click in its own (frame) session, always hitting the right
|
||||
// element in the right tab. Double/right clicks still need true pointer
|
||||
// semantics, and `coord` mode is an explicit opt-out.
|
||||
if mode != "coord" && button == "left" && click_count == 1 {
|
||||
let in_iframe = parse_ref(selector_or_ref)
|
||||
.and_then(|r| ref_map.get(&r).map(|e| e.frame_id.is_some()))
|
||||
.unwrap_or(false);
|
||||
if in_iframe || crate::connect::relay_url().is_some() {
|
||||
return dom_click(
|
||||
client,
|
||||
session_id,
|
||||
ref_map,
|
||||
selector_or_ref,
|
||||
iframe_sessions,
|
||||
)
|
||||
.await;
|
||||
}
|
||||
}
|
||||
|
||||
let resolved = resolve_element_center(
|
||||
client,
|
||||
session_id,
|
||||
|
||||
@@ -60,6 +60,9 @@ pub struct ScreenshotOptions {
|
||||
pub quality: Option<i32>,
|
||||
pub annotate: bool,
|
||||
pub output_dir: Option<String>,
|
||||
/// Explicit pixel region (x, y, width, height) — `--clip` (issue #34). Takes
|
||||
/// precedence over selector/full_page.
|
||||
pub clip: Option<(f64, f64, f64, f64)>,
|
||||
}
|
||||
|
||||
impl Default for ScreenshotOptions {
|
||||
@@ -72,6 +75,7 @@ impl Default for ScreenshotOptions {
|
||||
quality: None,
|
||||
annotate: false,
|
||||
output_dir: None,
|
||||
clip: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -187,7 +191,16 @@ async fn capture_screenshot_base64(
|
||||
capture_beyond_viewport: if options.full_page { Some(true) } else { None },
|
||||
};
|
||||
|
||||
if options.full_page {
|
||||
if let Some((x, y, width, height)) = options.clip {
|
||||
// Explicit pixel region wins over selector/full_page (issue #34).
|
||||
params.clip = Some(Viewport {
|
||||
x,
|
||||
y,
|
||||
width,
|
||||
height,
|
||||
scale: 1.0,
|
||||
});
|
||||
} else if options.full_page {
|
||||
let metrics: Value = client
|
||||
.send_command_no_params("Page.getLayoutMetrics", Some(session_id))
|
||||
.await?;
|
||||
|
||||
+76
-18
@@ -224,6 +224,40 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
|
||||
return;
|
||||
}
|
||||
|
||||
// Cloudflare challenge/clearance preflight (`cf-status`). Checked early
|
||||
// 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 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 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 (icon, headline) = match rec {
|
||||
"proceed" => (color::success_indicator().to_string(), "cleared — no challenge, proceed"),
|
||||
"solve" => (color::warning_indicator().to_string(), "Cloudflare challenge active, no valid clearance — solve it"),
|
||||
"reissue" => (color::warning_indicator().to_string(), "challenge active but a clearance cookie exists — stale (IP/UA changed?), re-solve"),
|
||||
_ => (color::cyan("•").to_string(), "unknown"),
|
||||
};
|
||||
println!("{} {}", icon, headline);
|
||||
println!(" challenged: {}", if challenged { "yes" } else { "no" });
|
||||
let cl_desc = if !present {
|
||||
"absent".to_string()
|
||||
} else if expired {
|
||||
"present but EXPIRED".to_string()
|
||||
} else if let Some(s) = expires_in {
|
||||
format!("valid, expires in {}m {}s", s / 60, s % 60)
|
||||
} else {
|
||||
"present (session)".to_string()
|
||||
};
|
||||
println!(" cf_clearance: {}", cl_desc);
|
||||
println!(" device trusted: {}", if device { "yes (CF_VERIFIED_DEVICE)" } else { "no" });
|
||||
return;
|
||||
}
|
||||
|
||||
// Dialog status response
|
||||
if action == Some("dialog") {
|
||||
if let Some(has_dialog) = data.get("hasDialog").and_then(|v| v.as_bool()) {
|
||||
@@ -597,19 +631,21 @@ pub fn print_response_with_opts(resp: &Response, action: Option<&str>, opts: &Ou
|
||||
// Tab switch
|
||||
if action == Some("tab_switch") {
|
||||
if let Some(tab_id) = data.get("tabId").and_then(|v| v.as_str()) {
|
||||
if let Some(url) = data.get("url").and_then(|v| v.as_str()) {
|
||||
println!(
|
||||
"{} Switched to tab [{}] ({})",
|
||||
color::success_indicator(),
|
||||
tab_id,
|
||||
url
|
||||
);
|
||||
let warning = data.get("warning").and_then(|v| v.as_str());
|
||||
// A non-responding session isn't a real success — show a warning
|
||||
// indicator instead of the green ✓ (issue #29.3).
|
||||
let indicator = if warning.is_some() {
|
||||
color::warning_indicator()
|
||||
} else {
|
||||
println!(
|
||||
"{} Switched to tab [{}]",
|
||||
color::success_indicator(),
|
||||
tab_id
|
||||
);
|
||||
color::success_indicator()
|
||||
};
|
||||
if let Some(url) = data.get("url").and_then(|v| v.as_str()) {
|
||||
println!("{} Switched to tab [{}] ({})", indicator, tab_id, url);
|
||||
} else {
|
||||
println!("{} Switched to tab [{}]", indicator, tab_id);
|
||||
}
|
||||
if let Some(w) = warning {
|
||||
eprintln!("{}", color::dim(w));
|
||||
}
|
||||
return;
|
||||
}
|
||||
@@ -1699,12 +1735,23 @@ Usage: chrome-use scroll [direction] [amount] [options]
|
||||
|
||||
Scrolls the page or a specific element in the specified direction.
|
||||
|
||||
Without --selector, scroll dispatches a real (isTrusted) mouse wheel at a
|
||||
viewport coordinate, so it scrolls whatever container is under the pointer —
|
||||
including cross-origin iframes (Google Payments, Stripe, embedded checkout/KYC)
|
||||
that plain page scroll can't reach.
|
||||
|
||||
Arguments:
|
||||
direction up, down, left, right (default: down)
|
||||
amount Pixels to scroll (default: 300)
|
||||
|
||||
Options:
|
||||
-s, --selector <sel> CSS selector for a scrollable container
|
||||
-s, --selector <sel> CSS selector for a scrollable container (same-origin)
|
||||
--at <x,y> Dispatch the wheel at this viewport pixel (read it from a
|
||||
screenshot) — precise way into a cross-origin iframe
|
||||
--frame <n> Scroll the n-th frame from `chrome-use frames` (wheel at
|
||||
that frame's center)
|
||||
|
||||
Without --selector/--at/--frame the wheel lands at the viewport center.
|
||||
|
||||
Global Options:
|
||||
--json Output as JSON
|
||||
@@ -1716,6 +1763,8 @@ Examples:
|
||||
chrome-use scroll up 200
|
||||
chrome-use scroll left 100
|
||||
chrome-use scroll down 500 --selector "div.scroll-container"
|
||||
chrome-use scroll down 700 --at 640,400 # wheel at a pixel over an iframe
|
||||
chrome-use scroll down 700 --frame 2 # scroll frame 2 from `frames`
|
||||
"##
|
||||
}
|
||||
"scrollintoview" | "scrollinto" => {
|
||||
@@ -1796,6 +1845,8 @@ Pass --hide-scrollbars false when launching to keep native scrollbars visible.
|
||||
|
||||
Options:
|
||||
--full, -f Capture full page (not just viewport)
|
||||
[selector] Capture just an element (CSS or @ref), e.g. `screenshot ".header" h.png`
|
||||
--clip <x,y,w,h> Capture a pixel region, e.g. `screenshot --clip 0,0,200,40 corner.png`
|
||||
--annotate Overlay numbered labels on interactive elements.
|
||||
Each label [N] corresponds to ref @eN from snapshot.
|
||||
Prints a legend mapping labels to element roles/names.
|
||||
@@ -1816,6 +1867,8 @@ Examples:
|
||||
chrome-use screenshot
|
||||
chrome-use screenshot ./screenshot.png
|
||||
chrome-use screenshot --full ./full-page.png
|
||||
chrome-use screenshot ".header .indicator" corner.png # just one element
|
||||
chrome-use screenshot --clip 1600,0,200,40 corner.png # a pixel region
|
||||
chrome-use screenshot --annotate # Labeled screenshot + legend
|
||||
chrome-use screenshot --annotate ./page.png # Save annotated screenshot
|
||||
chrome-use screenshot --annotate --json # JSON output with annotations
|
||||
@@ -1957,9 +2010,9 @@ Usage: chrome-use get <subcommand> [args]
|
||||
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 [selector] Element text; no selector = WHOLE PAGE, all frames
|
||||
text --main Main-content text only (skip nav/header/sidebar)
|
||||
text --pierce Read through CLOSED shadow DOM (injected panels)
|
||||
html <selector> Get inner HTML of element
|
||||
value <selector> Get value of input element
|
||||
attr <selector> <name> Get attribute value
|
||||
@@ -1975,8 +2028,8 @@ Global Options:
|
||||
--session <name> Use specific session
|
||||
|
||||
Examples:
|
||||
chrome-use get text @e1
|
||||
chrome-use get text --all-frames # read iframed content (listing pages)
|
||||
chrome-use get text # whole page across ALL frames (default)
|
||||
chrome-use get text @e1 # one element
|
||||
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"
|
||||
@@ -3188,11 +3241,15 @@ 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)
|
||||
text (no selector = whole page, all frames), text --main, frames (list)
|
||||
|
||||
Check State: chrome-use is <what> <selector>
|
||||
visible, enabled, checked
|
||||
|
||||
Anti-bot: chrome-use stealth | cf-status
|
||||
stealth stealth self-check (webdriver/UA/plugins + overrides)
|
||||
cf-status Cloudflare challenge + cf_clearance preflight (skip re-solving)
|
||||
|
||||
Find Elements: chrome-use find <locator> <value> <action> [text]
|
||||
role, text, label, placeholder, alt, title, testid, first, last, nth
|
||||
|
||||
@@ -3287,6 +3344,7 @@ Confirmation:
|
||||
Sessions:
|
||||
session Show current session name
|
||||
session list List active sessions
|
||||
sessions List running session daemons (alias of daemon status)
|
||||
daemon status List running session daemons (+ relay state)
|
||||
daemon restart Kill all session daemons; keeps the extension relay
|
||||
up. Clears stale/cross-leaked state after an upgrade.
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "chrome-use",
|
||||
"version": "1.5.1",
|
||||
"version": "1.5.11",
|
||||
"description": "chrome-use — drive your real, logged-in Chrome from any AI agent, stealth by default",
|
||||
"type": "module",
|
||||
"packageManager": "pnpm@11.1.3",
|
||||
|
||||
+45
-14
@@ -127,6 +127,19 @@ cadence, and scroll/drag ease. Default `off`; a per-navigation detector
|
||||
auto-escalates pages guarded by Akamai/PerimeterX/DataDome to `human`. Leave it
|
||||
on auto; force `human` only when you already know the target scores behaviour.
|
||||
|
||||
**Cloudflare clearance — solve once, reuse.** Passing a Cloudflare challenge
|
||||
mints a `cf_clearance` cookie (HttpOnly — invisible to `eval`/`document.cookie`;
|
||||
read it via `chrome-use cookies`). It's bound to your **IP + User-Agent**: reuse
|
||||
the same exit IP and UA and you skip the challenge until it expires. Driving the
|
||||
user's real Chrome (relay) persists it natively; for isolated sessions,
|
||||
`--session-name <name>` save/restores it. Before spending effort solving, run
|
||||
`chrome-use cf-status` (aliases `cf`, `clearance`): it reports whether the page
|
||||
is *currently* a Cloudflare challenge and whether a still-valid `cf_clearance`
|
||||
exists, with a recommendation — `proceed` (already cleared, don't re-solve),
|
||||
`solve` (challenge up, no clearance), or `reissue` (clearance present but page
|
||||
still blocks → IP/UA drifted, re-solve). Use it as a preflight to avoid
|
||||
re-solving what you already cleared.
|
||||
|
||||
## Two ways to drive a page — and when to drop to `eval`
|
||||
|
||||
You have a **real Chrome with the user's DOM**. Two layers, mix them freely:
|
||||
@@ -207,9 +220,10 @@ assigned fresh on every snapshot.
|
||||
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 # WHOLE PAGE — all frames by default (see below)
|
||||
chrome-use get text @e1 # visible text of one element (or a CSS selector)
|
||||
chrome-use get text --main # main content only — skip nav/header/sidebar
|
||||
chrome-use get text --pierce # read through CLOSED shadow DOM (injected panels)
|
||||
chrome-use frames # list every frame + where the text lives
|
||||
chrome-use get html @e1 # innerHTML
|
||||
chrome-use get attr @e1 href # any attribute
|
||||
@@ -219,13 +233,26 @@ 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.
|
||||
**Whole-page text is cross-frame by default.** `chrome-use get text` with no
|
||||
selector aggregates visible text across **every** frame — top document plus
|
||||
same-process child frames plus cross-origin iframes — so you never silently miss
|
||||
content that lives in an iframe (Yahoo Auctions / Rakuten / Mercari shop
|
||||
descriptions, embedded checkout/spec frames). Each child frame is delimited with
|
||||
a `----- frame [kind] url -----` marker. You do **not** need to remember a flag —
|
||||
the default already reads all frames. (`--all-frames` is still accepted as an
|
||||
explicit alias.)
|
||||
|
||||
So: when text looks missing or wrong, you don't have to guess — just
|
||||
`chrome-use get text` reads everything. To **see** the structure (which frame
|
||||
holds what), run `chrome-use frames`. To **cut boilerplate** (global nav/header/
|
||||
footer, "related items" sidebars), use `chrome-use get text --main`. If content
|
||||
is lazy-loaded, `scroll` it into view first, then read.
|
||||
|
||||
**Closed shadow DOM.** Some injected UI (browser-extension debug panels, web
|
||||
components) renders into a *closed* shadow root that `eval`/`innerText` cannot
|
||||
read. `chrome-use get text --pierce` reads through closed shadow roots and child
|
||||
documents via the CDP DOM tree — use it when content is clearly on screen (you
|
||||
see it in a screenshot) but `get text`/`eval` come back empty.
|
||||
|
||||
## Interacting
|
||||
|
||||
@@ -254,12 +281,16 @@ chrome-use pick @e4 --option "Europe" # ANY combobox (react-select / ARIA /
|
||||
# (no silent no-op). Use this for custom
|
||||
# dropdowns where `select` returns ✓ but
|
||||
# changes nothing.
|
||||
chrome-use upload @e5 file1.pdf # upload file(s) — NOTE: needs a --launch/direct-CDP
|
||||
# session. Over the extension relay it CANNOT work
|
||||
# (Chrome's chrome.debugger forbids it); chrome-use
|
||||
# errors with a hint. Carry your login into a launched
|
||||
# session via `cookies export` | `cookies set --curl`.
|
||||
chrome-use upload @e5 file1.pdf # upload file(s) — works over the extension relay too:
|
||||
# chrome.debugger forbids setFileInputFiles, so the
|
||||
# file's bytes are streamed into the page and rebuilt as
|
||||
# a File there (chunked under native-messaging's 1 MiB cap).
|
||||
# Works on file <input>s and drop/paste composers (e.g. X).
|
||||
chrome-use scroll down 500 # scroll page (up/down/left/right)
|
||||
chrome-use scroll down 700 --at 640,400 # wheel at a pixel — scrolls a cross-origin
|
||||
# iframe (Payments/Stripe/checkout/KYC) that
|
||||
# plain page scroll can't reach
|
||||
chrome-use scroll down 700 --frame 2 # scroll frame 2 from `chrome-use frames`
|
||||
chrome-use scrollintoview @e1 # scroll element into view
|
||||
chrome-use drag @e1 @e2 # drag and drop
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user