Skip to content

The agent that grows with you

fix(process): a supervisor a broken-pipe write dropped is still restarted by its waiter

kshitijk4poor9cb4e058cd85
diff --git a/hermes_cli/process_identity.py b/hermes_cli/process_identity.py
index 987ddbaa433..36ac575dddb 100644
--- a/hermes_cli/process_identity.py
+++ b/hermes_cli/process_identity.py
@@ -870,8 +870,10 @@ def _watch_supervisor(proc) -> None:
global _supervisor
proc.wait()
with _supervisor_lock:
- if _supervisor is not proc:
- return # released, or already replaced after a broken pipe: only reaped
+ if _supervisor is not None and _supervisor is not proc:
+ return # already replaced: only reaped
+ # Still current, or dropped by a caller whose write hit its broken pipe: restart below if
+ # groups are still registered (a deliberate release leaves the set empty).
_supervisor = None
_prune_dead_supervised_pgids()
if not _supervised_pgids:
diff --git a/tests/hermes_cli/test_process_identity_supervisor.py b/tests/hermes_cli/test_process_identity_supervisor.py
index b9e6b7929fe..07eef1c08f4 100644
--- a/tests/hermes_cli/test_process_identity_supervisor.py
+++ b/tests/hermes_cli/test_process_identity_supervisor.py
@@ -890,3 +890,24 @@ def test_a_supervisor_killed_on_its_own_is_restarted_with_every_group_replayed(m
finally:
_kill(child.pid)
child.wait(timeout=10)
+
+
+def test_a_supervisor_dropped_on_a_broken_pipe_is_still_restarted_by_its_waiter(monkeypatch):
+ """A caller can hit the dead supervisor's pipe before its waiter wakes (the waiter holds the
+ Popen's waitpid lock, so poll() still says "running"); that caller drops it. The waiter must still
+ restart coverage, or the registered groups wait for the next registration change."""
+ monkeypatch.setattr(process_identity, "_SUPERVISOR_RESTART_MIN_UPTIME_S", 0.0)
+ child = subprocess.Popen(_VICTIM, start_new_session=True)
+ try:
+ process_identity.own_process_groups([child.pid])
+ first = process_identity._supervisor
+ with process_identity._supervisor_lock: # the broken-pipe caller, before the waiter runs
+ first.kill()
+ process_identity._supervisor = None
+ wait_until(lambda: process_identity._supervisor not in (None, first), timeout=10,
+ what="a replacement started for the supervisor a broken pipe dropped")
+ process_identity._supervisor.stdin.close()
+ wait_until(lambda: child.poll() is not None, timeout=15, what="the replayed group killed")
+ finally:
+ _kill(child.pid)
+ child.wait(timeout=10)