From a72009099ac313466c703f6b073aed98953d80b5 Mon Sep 17 00:00:00 2001
From: damocles <damocles@hyperhive.local>
Date: Thu, 30 Jul 2026 00:02:02 +0200
Subject: [PATCH] fix list_containers reporting stale running state

handle_list_descendants derived a container's running state from
membership in nixos-container list output, but that command returns
every registered container - stopped and ghost-registered (machined
still holds the name after the process died) ones included - not just
running ones. use lifecycle::is_running (systemctl is-active on the
container's systemd unit) per container instead, same source
container_view::build_all already uses for the dashboard.

fixes hyperhive/hyperhive#2846
---
 .../src/socket_server/lifecycle_handlers.rs   | 33 +++++++------------
 1 file changed, 11 insertions(+), 22 deletions(-)

diff --git a/hive-c0re/src/socket_server/lifecycle_handlers.rs b/hive-c0re/src/socket_server/lifecycle_handlers.rs
index 29182a69..997558e0 100644
--- a/hive-c0re/src/socket_server/lifecycle_handlers.rs
+++ b/hive-c0re/src/socket_server/lifecycle_handlers.rs
@@ -160,21 +160,6 @@ pub(super) fn handle_update(coord: &Arc<Coordinator>, agent: &str, name: &str) -
 /// its running/stopped state, parents before children.
 pub(super) async fn handle_list_descendants(agent: &str) -> Response {
     tracing::debug!(%agent, "agent: list descendants");
-    // All containers known to nixos-container (running only).
-    let running_set: std::collections::HashSet<String> = match crate::lifecycle::list().await {
-        Ok(names) => names
-            .into_iter()
-            .filter_map(|c| {
-                c.strip_prefix(crate::lifecycle::AGENT_PREFIX)
-                    .map(str::to_owned)
-            })
-            .collect(),
-        Err(e) => {
-            return Response::Err {
-                message: format!("list containers failed: {e:#}"),
-            };
-        }
-    };
     // Walk the full topology and collect every descendant.
     let topo = crate::topology::read();
     let mut names: Vec<String> = topo
@@ -184,12 +169,16 @@ pub(super) async fn handle_list_descendants(agent: &str) -> Response {
         .collect();
     // Parents before children, then alpha within each tier.
     crate::auto_update::topology_sort(&mut names, &topo);
-    let containers = names
-        .into_iter()
-        .map(|name| {
-            let running = running_set.contains(&name);
-            hive_sh4re::ContainerInfo { name, running }
-        })
-        .collect();
+    // Query each container's actual systemd unit state (same source
+    // `container_view::build_all` uses for the dashboard). `nixos-container
+    // list` — what this used to key off of via a "known containers" set —
+    // reports every *registered* container, stopped and ghost-registered
+    // (machined still holds the name after a crashed/killed process) ones
+    // included, so membership there is not the same thing as "running".
+    let mut containers = Vec::with_capacity(names.len());
+    for name in names {
+        let running = crate::lifecycle::is_running(&name).await;
+        containers.push(hive_sh4re::ContainerInfo { name, running });
+    }
     Response::Containers { containers }
 }