From fcbfa325459fbef0ce8515d0f6ad1ae0ac480970 Mon Sep 17 00:00:00 2001
From: Jeena <hello@jeena.net>
Date: Thu, 29 Oct 2026 18:56:03 +0900
Subject: [PATCH] container: Stop gracefully on podman stop

Containers used `sleep infinity` as PID 1, which never reacts to
SIGTERM: the kernel does not apply default signal dispositions to PID 1,
and sleep has no SIGTERM handler, so every `podman stop` silently
ignored the signal, waited out the full 10-second grace period, and fell
back to SIGKILL.

PID 1 now traps TERM and INT itself and exits on request, so one-off
manual stops of a still-running agent container end immediately instead
of after the kill timeout.

The PID 1 command is baked in at create time, so containers predating
this change are detected and recreated automatically on the next run.
---
 CHANGELOG.md       | 22 ++++++++++++++++++++++
 agent-container.py | 32 +++++++++++++++++++++++++++++++-
 2 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 52b3aaa..38c6e6e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,27 @@
 # Release notes
 
+## 1.0.1 — 2026-10-29
+
+`podman stop` now stops a running agent container immediately instead of
+after a 10-second SIGTERM timeout followed by SIGKILL.
+
+### Why
+
+Containers used `sleep infinity` as PID 1. The kernel does not apply
+default signal dispositions to PID 1, and `sleep` has no SIGTERM handler,
+so the stop signal was silently ignored and every stop fell through to
+SIGKILL. PID 1 now traps TERM (and INT) itself and exits on request:
+
+```sh
+trap "exit 0" TERM INT; sleep infinity & wait
+```
+
+### Upgrading
+
+The PID 1 command is baked in when a container is created, so existing
+containers are detected on the next run and recreated automatically.
+Nothing in the container home is touched.
+
 ## 1.0.0 — 2026-10-29
 
 Containers now run with rootless Podman instead of Docker.
diff --git a/agent-container.py b/agent-container.py
index 1029344..c430f88 100755
--- a/agent-container.py
+++ b/agent-container.py
@@ -179,6 +179,12 @@ class AgentContainer:
             )
             self.remove_container()
 
+        if self.container_exists() and not self._container_cmd_matches():
+            logger.info(
+                "Recreating container: it predates the SIGTERM-aware PID 1"
+            )
+            self.remove_container()
+
         if not self.container_exists():
             self.create_container()
 
@@ -513,7 +519,11 @@ class AgentContainer:
                 self.IMAGE,
                 "sh",
                 "-c",
-                "sleep infinity",
+                # PID 1 ignores signals with default dispositions, so a bare
+                # `sleep infinity` never reacts to SIGTERM and every
+                # `podman stop` times out into SIGKILL. Trapping TERM (and
+                # INT) makes stop requests end the container immediately.
+                'trap "exit 0" TERM INT; sleep infinity & wait',
             ]
         )
 
@@ -555,6 +565,26 @@ class AgentContainer:
         ).stdout
         return "AGENT_CONTAINER=1" in env
 
+    def _container_cmd_matches(self) -> bool:
+        """Whether the container runs the current PID 1 command.
+
+        The PID 1 entrypoint is baked in at create time and can only change
+        by recreating the container. Comparing against Config.Cmd catches
+        containers created before the SIGTERM-aware fix."""
+        cmd = subprocess.run(
+            [
+                self.RUNTIME,
+                "container",
+                "inspect",
+                "-f",
+                "{{json .Config.Cmd}}",
+                self.container_name,
+            ],
+            capture_output=True,
+            text=True,
+        ).stdout.strip()
+        return "TERM INT" in cmd
+
     def start_container(self) -> bool:
         subprocess.run(
             [self.RUNTIME, "start", self.container_name],