From a9ce8a945f08a22e476447589fcb168236cad6ce Mon Sep 17 00:00:00 2001
From: damocles <damocles@hyperhive.local>
Date: Wed, 3 Jun 2026 18:23:18 +0200
Subject: [PATCH] fix(#1160): restart agent on failed rebuild if it was running

---
 hive-c0re/src/lifecycle.rs | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/hive-c0re/src/lifecycle.rs b/hive-c0re/src/lifecycle.rs
index 4441d0f4..cd4c0555 100644
--- a/hive-c0re/src/lifecycle.rs
+++ b/hive-c0re/src/lifecycle.rs
@@ -467,7 +467,26 @@ pub async fn rebuild_no_meta(
             priv_run("stop", name).await?;
         }
         on_step("nixos-container update");
-        priv_run("update", name).await?;
+        let update_result = priv_run("update", name).await;
+        if let Err(ref update_err) = update_result {
+            // The update failed (e.g. nix build error). If the agent was
+            // running before we stopped it, try to bring it back up on the
+            // previous successful configuration so it doesn't stay dead.
+            // The start failure is logged but not promoted to an error —
+            // we always propagate the original update error (below).
+            if was_running {
+                tracing::warn!(
+                    %name,
+                    error = %update_err,
+                    "nixos-container update failed; attempting restart on old config"
+                );
+                on_step("nixos-container start (recovery)");
+                if let Err(e) = priv_run("start", name).await {
+                    tracing::warn!(%name, error = %e, "recovery start after failed update also failed");
+                }
+            }
+        }
+        update_result?;
         if was_running {
             // Cold-start fallback on activation errors.
             // See `docs/coordinator.md::Cold-start fallback`.