Complete local HTTP endpoint parity

src/runtime.rs

@@ -165,6 +165,13 @@ fn run_command(
     idle_timeout: &mut Duration,
 ) {
     *idle_timeout = command.idle_timeout;
+    if command.cancel.load(Ordering::Relaxed) {
+        metrics.request_failed(request_started.elapsed());
+        let _ = command.events.send(GenerationEvent::Finished(
+            Err("generation cancelled".into()),
+        ));
+        return;
+    }
     if loaded
         .as_ref()
         .is_none_or(|(settings, _)| settings != &command.engine)