Compare commits
6
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7159012173 | ||
|
|
1b3d41e579 | ||
|
|
dbf272ced7 | ||
|
|
64140879d5 | ||
|
|
d3bfd76c96 | ||
|
|
47dfe760be |
Generated
+1
-1
@@ -45,7 +45,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "agent-browser-stealth"
|
||||
version = "0.27.0-fork.4"
|
||||
version = "0.27.0-fork.6"
|
||||
dependencies = [
|
||||
"aes-gcm",
|
||||
"async-trait",
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "agent-browser-stealth"
|
||||
version = "0.27.0-fork.4"
|
||||
version = "0.27.0-fork.6"
|
||||
edition = "2021"
|
||||
description = "Fast browser automation CLI for AI agents"
|
||||
license = "Apache-2.0"
|
||||
|
||||
+18
-5
@@ -822,11 +822,24 @@ fn main() {
|
||||
.collect();
|
||||
|
||||
if !ignored_flags.is_empty() && !flags.json {
|
||||
eprintln!(
|
||||
"{} {} ignored: daemon already running. Use 'agent-browser close' first to restart with new options.",
|
||||
color::warning_indicator(),
|
||||
ignored_flags.join(", ")
|
||||
);
|
||||
// Special case: --headed is irrelevant in CDP-attach mode
|
||||
// (your existing Chrome is always already visible). The
|
||||
// "agent-browser close + reopen" advice doesn't help because
|
||||
// the new daemon will attach right back to the same Chrome.
|
||||
// Don't suggest a useless workaround.
|
||||
if ignored_flags == ["--headed"] {
|
||||
eprintln!(
|
||||
"{} --headed has no effect when attached to your running Chrome (it's already visible). \
|
||||
Pass --launch to spawn a separate browser if you need to control headedness.",
|
||||
color::warning_indicator(),
|
||||
);
|
||||
} else {
|
||||
eprintln!(
|
||||
"{} {} ignored: daemon already running. Use 'agent-browser close' first to restart with new options.",
|
||||
color::warning_indicator(),
|
||||
ignored_flags.join(", ")
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1510,6 +1510,28 @@ async fn connect_auto_with_fresh_tab() -> Result<BrowserManager, String> {
|
||||
.client
|
||||
.send_command("Page.bringToFront", None, Some(&session_id))
|
||||
.await;
|
||||
|
||||
// Liveness probe: confirm the CDP session can actually round-trip
|
||||
// before returning success. Without this, a zombie CDP socket (process
|
||||
// alive, websocket dead) would let `connect_auto` and `tab_new` succeed,
|
||||
// we'd return Ok, the next user command would silently no-op, and
|
||||
// `agent-browser open URL` would exit 0 with the browser still on
|
||||
// about:blank. Failing here lets the caller surface the real error.
|
||||
if let Err(e) = mgr
|
||||
.client
|
||||
.send_command("Runtime.evaluate", Some(serde_json::json!({
|
||||
"expression": "1",
|
||||
"returnByValue": true,
|
||||
})), Some(&session_id))
|
||||
.await
|
||||
{
|
||||
return Err(format!(
|
||||
"CDP session is unresponsive after attaching ({}). \
|
||||
The browser may have lost its DevTools connection. \
|
||||
Try: agent-browser close, then re-run.",
|
||||
e
|
||||
));
|
||||
}
|
||||
Ok(mgr)
|
||||
}
|
||||
|
||||
@@ -1585,8 +1607,9 @@ async fn auto_launch(state: &mut DaemonState) -> Result<(), String> {
|
||||
To let agent-browser work with your existing Chrome (recommended):\n\
|
||||
{}\n\n\
|
||||
Or start a standalone browser with: agent-browser --launch open <url>\n\n\
|
||||
Tip: On Chrome 144+, you can enable CDP without restarting:\n\
|
||||
Open chrome://inspect/#remote-debugging and toggle it on.",
|
||||
Note: chrome://inspect/#remote-debugging only enables remote *target discovery* — \
|
||||
it does NOT expose the standard CDP HTTP API on /json/version. \
|
||||
A full restart with --remote-debugging-port=<port> is required.",
|
||||
chrome_relaunch_hint(),
|
||||
));
|
||||
}
|
||||
@@ -2113,8 +2136,9 @@ async fn handle_launch(cmd: &Value, state: &mut DaemonState) -> Result<Value, St
|
||||
To let agent-browser work with your existing Chrome (recommended):\n\
|
||||
{}\n\n\
|
||||
Or start a standalone browser with: agent-browser --launch open <url>\n\n\
|
||||
Tip: On Chrome 144+, you can enable CDP without restarting:\n\
|
||||
Open chrome://inspect/#remote-debugging and toggle it on.",
|
||||
Note: chrome://inspect/#remote-debugging only enables remote *target discovery* — \
|
||||
it does NOT expose the standard CDP HTTP API on /json/version. \
|
||||
A full restart with --remote-debugging-port=<port> is required.",
|
||||
chrome_relaunch_hint(),
|
||||
));
|
||||
}
|
||||
@@ -3105,6 +3129,15 @@ async fn handle_wait(cmd: &Value, state: &mut DaemonState) -> Result<Value, Stri
|
||||
.get("state")
|
||||
.and_then(|v| v.as_str())
|
||||
.unwrap_or("visible");
|
||||
// @-ref support: if the selector is `@e12` style, poll the ref map +
|
||||
// accessibility tree instead of `document.querySelector`. This makes
|
||||
// `wait @e8 --gone` a usable "assert modal still mounted" primitive
|
||||
// for SPA flows where the only stable identity is the AX role+name
|
||||
// captured at snapshot time.
|
||||
if selector.starts_with('@') {
|
||||
wait_for_ref(state, selector, state_str, timeout_ms).await?;
|
||||
return Ok(json!({ "waited": "ref", "ref": selector, "state": state_str }));
|
||||
}
|
||||
wait_for_selector(&mgr.client, &session_id, selector, state_str, timeout_ms).await?;
|
||||
return Ok(json!({ "waited": "selector", "selector": selector }));
|
||||
}
|
||||
@@ -3316,6 +3349,49 @@ async fn handle_reload(state: &mut DaemonState) -> Result<Value, String> {
|
||||
// Wait helpers
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
/// Poll-based wait for a ref-identified element. Resolves the @-ref by
|
||||
/// re-running the ref-identity verification each iteration. The supported
|
||||
/// states mirror selector-based waits:
|
||||
///
|
||||
/// - "visible" / "attached" — succeed when the ref resolves to a node
|
||||
/// whose AX role + name still match the snapshot entry
|
||||
/// - "detached" / "hidden" — succeed when the ref no longer matches
|
||||
/// (node removed OR re-textified to something else)
|
||||
///
|
||||
/// Times out with a "ref X did not become {state}" error.
|
||||
async fn wait_for_ref(
|
||||
state: &mut DaemonState,
|
||||
ref_selector: &str,
|
||||
desired_state: &str,
|
||||
timeout_ms: u64,
|
||||
) -> Result<(), String> {
|
||||
let want_present = !matches!(desired_state, "detached" | "hidden");
|
||||
let deadline = std::time::Instant::now() + std::time::Duration::from_millis(timeout_ms);
|
||||
loop {
|
||||
let mgr = state.browser.as_ref().ok_or("Browser not launched")?;
|
||||
let session_id = mgr.active_session_id()?.to_string();
|
||||
let resolved = super::element::resolve_element_object_id(
|
||||
&mgr.client,
|
||||
&session_id,
|
||||
&state.ref_map,
|
||||
ref_selector,
|
||||
&state.iframe_sessions,
|
||||
)
|
||||
.await;
|
||||
let present = resolved.is_ok();
|
||||
if present == want_present {
|
||||
return Ok(());
|
||||
}
|
||||
if std::time::Instant::now() >= deadline {
|
||||
return Err(format!(
|
||||
"Timeout: ref {} did not become {} within {}ms",
|
||||
ref_selector, desired_state, timeout_ms
|
||||
));
|
||||
}
|
||||
tokio::time::sleep(tokio::time::Duration::from_millis(100)).await;
|
||||
}
|
||||
}
|
||||
|
||||
async fn wait_for_selector(
|
||||
client: &super::cdp::client::CdpClient,
|
||||
session_id: &str,
|
||||
|
||||
@@ -396,9 +396,23 @@ async fn verify_ref_identity(
|
||||
"backendNodeId": backend_node_id,
|
||||
"fetchRelatives": false,
|
||||
});
|
||||
let resp: Result<GetFullAXTreeResult, String> = client
|
||||
.send_command_typed("Accessibility.getPartialAXTree", ¶ms, Some(session_id))
|
||||
.await;
|
||||
// Tight 1s timeout: this is a defensive guard, not a critical path.
|
||||
// The default 30s CDP timeout was the dominant factor in the
|
||||
// "click hangs 5+ minutes" report — three CDP calls (verify +
|
||||
// resolveNode + paint-settle) at 30s each, multiplied by parallel
|
||||
// click invocations queueing on the daemon, totalled multi-minute
|
||||
// user-visible hangs. Cap our own helper so a stuck AX query
|
||||
// doesn't make `click` worse than the no-guard version was.
|
||||
let resp: Result<GetFullAXTreeResult, String> = match tokio::time::timeout(
|
||||
std::time::Duration::from_secs(1),
|
||||
client.send_command_typed("Accessibility.getPartialAXTree", ¶ms, Some(session_id)),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(r) => r,
|
||||
// Timeout: skip identity verification rather than block the click.
|
||||
Err(_) => return Ok(()),
|
||||
};
|
||||
let Ok(tree) = resp else {
|
||||
// Node likely gone; let the box-model call fail and trigger fallback.
|
||||
return Ok(());
|
||||
|
||||
@@ -903,8 +903,15 @@ async fn wait_for_paint_settled(client: &CdpClient, session_id: &str) {
|
||||
requestAnimationFrame(() => \
|
||||
requestAnimationFrame(() => \
|
||||
queueMicrotask(() => resolve(true)))))";
|
||||
let _ = client
|
||||
.send_command_typed::<_, Value>(
|
||||
// Tight 500ms timeout. RAF normally fires at 16ms, two RAFs total ~33ms.
|
||||
// If the tab is hidden / throttled / page is doing something pathological
|
||||
// and RAF doesn't fire in 500ms, we'd rather return now than stall the
|
||||
// user's click. Without this cap, a stuck RAF inherited the default 30s
|
||||
// CDP timeout and was the main contributor to the "click hangs 5+ min"
|
||||
// user report.
|
||||
let _ = tokio::time::timeout(
|
||||
std::time::Duration::from_millis(500),
|
||||
client.send_command_typed::<_, Value>(
|
||||
"Runtime.evaluate",
|
||||
&EvaluateParams {
|
||||
expression: script.to_string(),
|
||||
@@ -912,8 +919,9 @@ async fn wait_for_paint_settled(client: &CdpClient, session_id: &str) {
|
||||
await_promise: Some(true),
|
||||
},
|
||||
Some(session_id),
|
||||
)
|
||||
.await;
|
||||
),
|
||||
)
|
||||
.await;
|
||||
}
|
||||
|
||||
async fn dispatch_click(
|
||||
|
||||
@@ -25,8 +25,14 @@ services:
|
||||
(echo "→ Linux ARM64" && cargo zigbuild --release --target aarch64-unknown-linux-gnu && cp /build/target/aarch64-unknown-linux-gnu/release/agent-browser /output/agent-browser-linux-arm64 && chmod +x /output/agent-browser-linux-arm64 && echo "✓ Linux ARM64 done") &
|
||||
PID2=$!
|
||||
|
||||
# Wait for both to complete
|
||||
wait $PID1 $PID2
|
||||
# Wait for both and check exit codes individually — without this
|
||||
# the outer script exits 0 even if one of the parallel builds
|
||||
# failed, silently leaving a stale binary in /output from the
|
||||
# previous release. Caused 0.27.0-fork.5 to ship with a stale
|
||||
# linux-x64 binary at the first publish attempt until caught
|
||||
# manually by checking the embedded version string.
|
||||
wait $PID1 || { echo "✗ Linux x64 build failed"; exit 1; }
|
||||
wait $PID2 || { echo "✗ Linux ARM64 build failed"; exit 1; }
|
||||
|
||||
echo ""
|
||||
echo "✓ Linux platforms built successfully!"
|
||||
@@ -67,8 +73,14 @@ services:
|
||||
- OUTPUT_NAME=${OUTPUT_NAME:-agent-browser-linux-x64}
|
||||
command: |
|
||||
-c '
|
||||
set -e
|
||||
cargo zigbuild --release --target $TARGET
|
||||
cp /build/target/$TARGET/release/agent-browser* /output/$OUTPUT_NAME
|
||||
# Copy the binary explicitly. The previous `agent-browser*` glob
|
||||
# matched the binary AND its `.d` dependency file, which made cp
|
||||
# treat the destination as a directory and silently failed.
|
||||
SRC="/build/target/$TARGET/release/agent-browser"
|
||||
if [ -f "$SRC.exe" ]; then SRC="$SRC.exe"; fi
|
||||
cp "$SRC" "/output/$OUTPUT_NAME"
|
||||
chmod +x /output/$OUTPUT_NAME 2>/dev/null || true
|
||||
echo "✓ Built $OUTPUT_NAME"
|
||||
'
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "agent-browser-stealth",
|
||||
"version": "0.27.0-fork.4",
|
||||
"version": "0.27.0-fork.6",
|
||||
"description": "Browser automation CLI for AI agents — stealth fork with anti-detection",
|
||||
"type": "module",
|
||||
"files": [
|
||||
|
||||
Reference in New Issue
Block a user