Verify blocking sleep fix in retry logic

[Copilot]

Review comment requested verification that the blocking thread::sleep in FFmpeg retry logic no longer blocks the async runtime.

Verification Result

The issue was already addressed in commit cbef645. The retry_group method containing the blocking sleep is now executed via tokio::task::spawn_blocking:

// server/src/main.rs
"retry_stream" => {
    let group_id: String = get_arg(&payload, "groupId")?;
    let event_sink: Arc<dyn EventSink> = Arc::new(state.event_bus.clone());
    let ffmpeg_handler = state.ffmpeg_handler.clone();
    // Offloads blocking thread::sleep to Tokio's blocking thread pool
    let (pid, next_delay) = tokio::task::spawn_blocking(move || {
        ffmpeg_handler.retry_group(&group_id, event_sink)
    })
    .await
    .map_err(|e| format!("Task join error: {e}"))??;
    Ok(json!({
        "pid": pid,
        "nextDelaySecs": next_delay.map(|d| d.as_secs())
    }))
}

This ensures the async runtime remains responsive during exponential backoff delays while processing multiple concurrent streams.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.