Skip to content

Fix execute hang in remote mode #89

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
andrii-i wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

Fix execute hang in remote mode #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4cfd4c7
Fix execute hang caused by missing timeout in kernel message select
andrii-i May 26, 2026
d89ef4f
optimize logic
andrii-i May 26, 2026
5e6736a
run cargo fmt
andrii-i May 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
89 changes: 51 additions & 38 deletions src/execution/remote/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ pub mod websocket;
pub mod ydoc;
pub mod ydoc_notebook_ops;

use crate::execution::types::{ExecutionConfig, ExecutionError, ExecutionResult};
use crate::execution::types::{ExecutionConfig, ExecutionResult};
use crate::execution::ExecutionBackend;
use anyhow::{Context, Result};
use client::{JupyterClient, SessionInfo};
Expand Down Expand Up @@ -227,25 +227,7 @@ impl ExecutionBackend for RemoteExecutor {
}

if idle_received {
let has_error = outputs
.iter()
.any(|o| matches!(o, nbformat::v4::Output::Error(_)));
let error_info = outputs.iter().find_map(|o| {
if let nbformat::v4::Output::Error(err) = o {
Some(ExecutionError {
ename: err.ename.clone(),
evalue: err.evalue.clone(),
traceback: err.traceback.clone(),
})
} else {
None
}
});
return if has_error {
Ok(ExecutionResult::error(outputs, ec, error_info.unwrap()))
} else {
Ok(ExecutionResult::success(outputs, ec))
};
return Ok(ExecutionResult::from_outputs(outputs, ec));
}
}

Expand All @@ -259,37 +241,68 @@ impl ExecutionBackend for RemoteExecutor {
} else {
tokio::select! {
kernel_msg = ws.recv_message() => {
if let Some(msg) = kernel_msg? {
let is_ours = msg.parent_header.as_ref()
.map(|h| h.msg_id == msg_id).unwrap_or(false);
if is_ours {
match &msg.content {
JupyterMessageContent::ExecuteInput(input) => {
expected_ec = Some(input.execution_count.0 as i64);
}
JupyterMessageContent::Status(status) => {
if matches!(status.execution_state,
jupyter_protocol::ExecutionState::Idle) {
idle_received = true;
match kernel_msg? {
Some(msg) => {
let is_ours = msg.parent_header.as_ref()
.map(|h| h.msg_id == msg_id).unwrap_or(false);
if is_ours {
match &msg.content {
JupyterMessageContent::ExecuteInput(input) => {
expected_ec = Some(input.execution_count.0 as i64);
}
JupyterMessageContent::Status(status) => {
if matches!(status.execution_state,
jupyter_protocol::ExecutionState::Idle) {
idle_received = true;
}
}
_ => {}
}
_ => {}
}
}
None => break,
}
}
ydoc_result = ydoc.recv_update() => {
ydoc_result.context("Y.js update error")?;
}
_ = tokio::time::sleep_until(deadline) => {
break;
}
}
}
}

let ec = ydoc
.read_cell_outputs(cell_idx)
.ok()
.and_then(|c| c.execution_count);
Ok(ExecutionResult::success(outputs, ec))
// Fallback: loop exited via timeout or WS close.
// Collect any outputs we haven't seen yet.
let ec = if let Ok(cell_data) = ydoc.read_cell_outputs(cell_idx) {
for (idx, url_path) in &cell_data.externalized_urls {
if fetched_urls.insert(url_path.clone()) {
seen_indices.insert(*idx);
if let Some(output) =
Self::fetch_output(&http, &self.server_url, &self.token, url_path).await
{
if let Some(cb) = &on_output {
cb(&output);
}
outputs.push(output);
}
}
}
for (idx, output) in &cell_data.inline_outputs {
if seen_indices.insert(*idx) {
if let Some(cb) = &on_output {
cb(output);
}
outputs.push(output.clone());
}
}
cell_data.execution_count
} else {
None
};

Ok(ExecutionResult::from_outputs(outputs, ec))
}

async fn stop(&mut self) -> Result<()> {
Expand Down
19 changes: 19 additions & 0 deletions src/execution/types.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,25 @@ impl ExecutionResult {
error: Some(error),
}
}

/// Build a result by inspecting outputs for errors in a single pass.
pub fn from_outputs(outputs: Vec<nbformat::v4::Output>, execution_count: Option<i64>) -> Self {
let error_info = outputs.iter().find_map(|o| {
if let nbformat::v4::Output::Error(err) = o {
Some(ExecutionError {
ename: err.ename.clone(),
evalue: err.evalue.clone(),
traceback: err.traceback.clone(),
})
} else {
None
}
});
match error_info {
Some(err) => Self::error(outputs, execution_count, err),
None => Self::success(outputs, execution_count),
}
}
}

/// Output from a single execution message
Expand Down
Loading