From 32af7e06394fd87e0726f19a6280adb5195355c8 Mon Sep 17 00:00:00 2001
From: atlas <atlas@hyperhive.local>
Date: Fri, 6 Nov 2026 03:07:50 +0100
Subject: [PATCH] lifecycle: leak the stop-failed warning kind once per agent

Closes #6096
---
 hive-c0re/src/lifecycle/mod.rs   | 21 +++++++++++++++------
 hive-c0re/src/lifecycle/tests.rs | 24 ++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 6 deletions(-)

diff --git a/hive-c0re/src/lifecycle/mod.rs b/hive-c0re/src/lifecycle/mod.rs
index 2b1a442f..609cf2c0 100644
--- a/hive-c0re/src/lifecycle/mod.rs
+++ b/hive-c0re/src/lifecycle/mod.rs
@@ -325,11 +325,20 @@ fn stop_failed_guards()
     REG.get_or_init(|| std::sync::Mutex::new(std::collections::HashMap::new()))
 }
 
-/// Leak a per-agent warning `kind`. Agent names are a small, bounded set —
-/// leaking one short string per distinct agent that ever hits a stop
-/// failure is cheap.
-fn static_stop_kind(name: &str) -> &'static str {
-    Box::leak(format!("agent_stop_failed_{name}").into_boxed_str())
+/// The per-agent warning `kind`, leaked on the first call for a name and
+/// returned unchanged afterwards, whether or not the warning was cleared in
+/// between. The leak is one short string per distinct agent name.
+fn stop_kind(name: &str) -> &'static str {
+    static KINDS: std::sync::OnceLock<
+        std::sync::Mutex<std::collections::HashMap<String, &'static str>>,
+    > = std::sync::OnceLock::new();
+    let mut kinds = KINDS
+        .get_or_init(|| std::sync::Mutex::new(std::collections::HashMap::new()))
+        .lock()
+        .unwrap_or_else(std::sync::PoisonError::into_inner);
+    kinds
+        .entry(name.to_owned())
+        .or_insert_with(|| Box::leak(format!("agent_stop_failed_{name}").into_boxed_str()))
 }
 
 /// Stop `name`'s container. See `hive-priv`'s `stop_and_release` for why
@@ -356,7 +365,7 @@ pub async fn kill(name: &str) -> Result<()> {
             guards.insert(
                 name.to_owned(),
                 crate::warnings::set_warning(
-                    static_stop_kind(name),
+                    stop_kind(name),
                     "crit",
                     format!("{name}: stop failed — {e}"),
                 ),
diff --git a/hive-c0re/src/lifecycle/tests.rs b/hive-c0re/src/lifecycle/tests.rs
index 7f7b5680..2e635925 100644
--- a/hive-c0re/src/lifecycle/tests.rs
+++ b/hive-c0re/src/lifecycle/tests.rs
@@ -422,3 +422,27 @@ fn a_build_without_a_log_row_has_an_empty_build_id() {
     assert_eq!(field(&logged[0].1, "build_id"), Some(""));
     assert_eq!(field(&logged[0].1, "agent"), Some("alice"));
 }
+
+#[test]
+fn stop_kind_is_leaked_once_per_agent() {
+    let first = stop_kind("stopkind-a");
+    assert_eq!(first, "agent_stop_failed_stopkind-a");
+    assert!(std::ptr::eq(first, stop_kind("stopkind-a")));
+    assert!(!std::ptr::eq(first, stop_kind("stopkind-b")));
+}
+
+#[test]
+fn stop_kind_survives_a_clean_stop_between_failures() {
+    let failed = |guards: &mut std::collections::HashMap<_, _>| {
+        let kind = stop_kind("stopkind-c");
+        guards.insert(
+            "stopkind-c".to_owned(),
+            crate::warnings::set_warning(kind, "crit", "stop failed"),
+        );
+        kind
+    };
+    let mut guards = std::collections::HashMap::new();
+    let first = failed(&mut guards);
+    guards.remove("stopkind-c");
+    assert!(std::ptr::eq(first, failed(&mut guards)));
+}