diff --git a/decisions/2026-10-05-pm-agent-issue-to-pr.md b/decisions/2026-10-05-pm-agent-issue-to-pr.md
index 18a673d..f07d9e0 100644
--- a/decisions/2026-10-05-pm-agent-issue-to-pr.md
+++ b/decisions/2026-10-05-pm-agent-issue-to-pr.md
@@ -90,6 +90,12 @@ All offline, in the pinned toolbox (`./infra/devcontainer/dev.sh run`), never on
      kustomization, because the kustomization's comment named it by filename. Correctly
      refused: the distance between a filename in a comment and a line under `resources:` is
      one careless edit. The comment now points at it in prose.
+- **A self-review of the trigger found and fixed one real defect** before any of this ran:
+  `last_activity()` compared RFC 3339 timestamp STRINGS to find the newest comment, which is
+  only correct while every offset Gitea returns is identical — and the failure mode is the
+  worst available one, the PM answering its own last comment in a loop. It now takes the last
+  element of the comments list, which is the order the endpoint returns, so there is nothing
+  about timezones to be right about.
 - **`check-jsonschema --schemafile schemas/servicedefinition.schema.json catalog/gitea.yaml`
   → ok.**
 - **The golden reproduces:** `python3 catalog/render.py --all catalog -o apps --wave-layout
diff --git a/infra/agent/pm-dispatch.py b/infra/agent/pm-dispatch.py
index 5ef7e77..df16e6d 100755
--- a/infra/agent/pm-dispatch.py
+++ b/infra/agent/pm-dispatch.py
@@ -599,19 +599,22 @@ def render_thread(cfg: Config, issue: dict, comments, pr: dict, status: dict,
 
 
 def last_activity(issue: dict, comments) -> tuple:
-    """Who wrote the newest thing in this thread, and when.
+    """Who wrote the newest thing in this thread, and when. THE TRIGGER DEPENDS ON THIS.
 
     Deliberately NOT `issue.updated_at`: that moves when a label is added or the title is
     edited, which would re-trigger the PM for a change nobody asked it about.
+
+    And deliberately NOT a comparison of the timestamp STRINGS. Gitea returns RFC 3339 with
+    a timezone offset, and lexicographic order over such strings is only correct while every
+    offset is identical — true today, silently wrong after a server timezone change, and the
+    failure would be the PM answering its own last comment in a loop. The comments endpoint
+    returns them in creation order, so the last element IS the newest; that is one less thing
+    to be right about.
     """
-    actor = (issue.get("user") or {}).get("login")
-    when = issue.get("created_at") or ""
-    for c in comments:
-        ts = c.get("created_at") or ""
-        if ts >= when:
-            when = ts
-            actor = (c.get("user") or {}).get("login")
-    return actor, when
+    if comments:
+        newest = comments[-1]
+        return (newest.get("user") or {}).get("login"), newest.get("created_at") or ""
+    return (issue.get("user") or {}).get("login"), issue.get("created_at") or ""
 
 
 # --------------------------------------------------------------------------- job