fix(interaction): honor scroll cancellation and visible bounds

This commit is contained in:
drakezhang
2026-09-10 00:05:48 +08:00
parent 29355e041d
commit 61c97c9cb5
13 changed files with 955 additions and 189 deletions
+6 -1
View File
@@ -59,7 +59,12 @@ bsk click|hover|focus|blur|fill|select|press ... --session <id>
bsk observe --session <id> # after navigation or a meaningful DOM change
```
`bsk scroll-to <ref-or-selector>` scrolls an element and its frame owners into the visible viewport.
`bsk scroll-to <ref-or-selector> --session <id>` scrolls an element and its frame owners into view.
Use a fresh element ref for iframe/shadow-root targets; CSS selectors search the main document.
The result is the visible border-box portion's bounds in top-level viewport CSS pixels after
ancestor clipping. Partial visibility is enough; hidden or fully clipped targets fail with
`element_not_visible`. The result does not guarantee that other elements do not cover the target.
For a specific tab or deadline: `bsk scroll-to @e3 --session <id> --tab-id 42 --timeout 5s`.
`bsk focus <ref>` explicitly focuses a target; `bsk blur <ref>` removes focus and reports whether
it was focused. Use these for UI states triggered by focus changes.
+4 -21
View File
@@ -7,9 +7,10 @@ use bsk_protocol::Method;
use bsk_protocol::tools::{ScrollToParams, ScrollToResult};
use clap::Args;
use crate::cli::dialogs::print_dialog_summaries;
use crate::cli::ensure_daemon::ensure_daemon;
use crate::cli::error::{CliError, Format};
use crate::cli::interaction::looks_like_ref;
use crate::cli::interaction::split_target;
use crate::cli::navigate::parse_timeout_ms;
#[derive(Debug, Clone, Args)]
@@ -34,8 +35,8 @@ pub struct ScrollToArgs {
}
pub fn dispatch(args: ScrollToArgs, format: Format) -> Result<(), CliError> {
let info = ensure_daemon().context("ensure daemon is running")?;
let (ref_, selector) = split_target(args.target, args.ref_, args.selector)?;
let info = ensure_daemon().context("ensure daemon is running")?;
let params = ScrollToParams {
session_id: args.session,
ref_,
@@ -63,30 +64,12 @@ pub fn dispatch(args: ScrollToArgs, format: Format) -> Result<(), CliError> {
"scroll-to ok tab={} target={target} bounds=({}, {}, {}, {})",
reply.tab_id, reply.x, reply.y, reply.width, reply.height
);
print_dialog_summaries(&reply.dialogs);
}
}
Ok(())
}
fn split_target(
positional: Option<String>,
explicit_ref: Option<String>,
explicit_selector: Option<String>,
) -> Result<(Option<String>, Option<String>), CliError> {
match (positional, explicit_ref, explicit_selector) {
(None, None, None) => Err(CliError::Local(anyhow::anyhow!(
"missing target: pass <ref-or-selector>, --ref @eN, or --selector <css>"
))),
(None, Some(r), None) => Ok((Some(r), None)),
(None, None, Some(s)) => Ok((None, Some(s))),
(Some(target), None, None) if looks_like_ref(&target) => Ok((Some(target), None)),
(Some(target), None, None) => Ok((None, Some(target))),
_ => Err(CliError::Local(anyhow::anyhow!(
"pass exactly one of: <target>, --ref, or --selector"
))),
}
}
fn format_used_target(used_ref: Option<&str>, used_selector: Option<&str>) -> String {
used_ref
.map(|r| format!("@{r}"))
+32
View File
@@ -264,6 +264,38 @@ fn parses_scroll_to_target() {
assert_eq!(args.target.as_deref(), Some("@e2"));
}
#[test]
fn parses_scroll_to_explicit_target_tab_and_timeout() {
for flag in ["--ref", "--selector"] {
let cli = parse(&[
"bsk",
"scroll-to",
flag,
"e3",
"--session",
"s1",
"--tab-id",
"42",
"--timeout",
"5s",
]);
let Command::ScrollTo(args) = cli.command else {
panic!("expected scroll-to command");
};
assert_eq!(args.tab_id, Some(42));
assert_eq!(args.timeout, 5_000);
assert_eq!(
if flag == "--ref" {
args.ref_
} else {
args.selector
}
.as_deref(),
Some("e3")
);
}
}
#[test]
fn parses_focus_target() {
let cli = parse(&["bsk", "focus", "@e2", "--session", "s1"]);
+23 -13
View File
@@ -293,6 +293,15 @@ async fn session_user_interrupt_event_cancels_inflight_with_user_aborted() {
/// catch a tool dispatched arbitrarily later.
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle() {
assert_idle_interrupt_rejects(Method::ToolClick).await;
}
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn user_interrupt_rejects_scroll_to_before_forwarding() {
assert_idle_interrupt_rejects(Method::ToolScrollTo).await;
}
async fn assert_idle_interrupt_rejects(method: Method) {
let (handle, sock) = spawn_daemon().await;
let mut ws = connect_ext(handle.ws_addr()).await;
let _ = handshake_as_ext(&mut ws).await;
@@ -301,10 +310,11 @@ async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle()
// Fake extension: answer tool.session_start, observe other
// requests but never reply. We expect the daemon to reject the
// tool call BEFORE it ever forwards a tool.click frame.
// tool call BEFORE it ever forwards a browser-input frame.
let ws_sink_for_responder = Arc::clone(&ws_sink);
let observed_click_count = Arc::new(std::sync::atomic::AtomicUsize::new(0));
let observed_click_count_clone = Arc::clone(&observed_click_count);
let observed_call_count = Arc::new(std::sync::atomic::AtomicUsize::new(0));
let observed_call_count_clone = Arc::clone(&observed_call_count);
let forwarded_method = method.clone();
let responder = tokio::spawn(async move {
let mut ws_stream = ws_stream;
while let Some(Ok(msg)) = ws_stream.next().await {
@@ -329,8 +339,8 @@ async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle()
g.send(Message::Text(serde_json::to_string(&reply).unwrap()))
.await
.unwrap();
} else if req.method == Method::ToolClick {
observed_click_count_clone.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
} else if req.method == forwarded_method {
observed_call_count_clone.fetch_add(1, std::sync::atomic::Ordering::SeqCst);
// Deliberately do NOT reply — daemon should reject before
// ever forwarding to us.
let _ = req;
@@ -377,12 +387,12 @@ async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle()
let state = handle.state();
wait_for_session_interrupt_pending(&state, &start.session_id).await;
// The CLI now issues a tool.click (mutating). The daemon must
// The CLI now issues a browser-input (mutating). The daemon must
// reject it WITHOUT forwarding to the extension.
let click_outcome = ipc
let outcome = ipc
.call::<_, serde_json::Value>(
"click-after-interrupt",
Method::ToolClick,
"input-after-interrupt",
method,
Some(json!({
"session_id": start.session_id,
"ref": "fake-ref-1",
@@ -391,7 +401,7 @@ async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle()
)
.await
.unwrap();
let err = click_outcome.expect_err("tool.click must be rejected");
let err = outcome.expect_err("browser-input must be rejected");
assert_eq!(
err.code,
ErrorCode::UserAborted,
@@ -399,11 +409,11 @@ async fn user_interrupt_rejects_next_mutating_tool_call_when_session_was_idle()
err
);
// Crucially: the extension never saw a tool.click frame.
// Crucially: the extension never saw a browser-input frame.
assert_eq!(
observed_click_count.load(std::sync::atomic::Ordering::SeqCst),
observed_call_count.load(std::sync::atomic::Ordering::SeqCst),
0,
"tool.click must NOT have been forwarded to the extension"
"browser-input must NOT have been forwarded to the extension"
);
responder.abort();