.agents/skills/lib.sh

@@ -2297,10 +2297,16 @@ _start_watchdog_legacy() {
   elif [ -z "$pid" ]; then
     # Start the wildcard monitor subscriber daemon with --idle-timeout 0 (never idle out)
     # and ensure it runs with $workdir as cwd to anchor relative log paths.
-    local orig_pwd="$PWD"
+    # Issue #72 (decision 2): job control (`set -m`) starts it in its own
+    # process group, out of the caller's, as the python body's new session
+    # does; macOS has no setsid(1). The caller's option is restored.
+    local orig_pwd="$PWD" had_m=0
+    case $- in *m*) had_m=1 ;; esac
     cd "$workdir" || return 1
+    set -m
     nohup bash "$monitor_script" --subscribe --idle-timeout 0 </dev/null >> "$log_file" 2>&1 &
     pid=$!
+    [ "$had_m" = 1 ] || set +m
     cd "$orig_pwd" || return 1
   fi
   

tests/test_issue72_update.py

@@ -181,6 +181,18 @@ def _exact_monitor_pids(script) -> list:
     return pids
 
 
+def _descendants(pid) -> list:
+    kids = subprocess.run(["pgrep", "-P", str(pid)], capture_output=True, text=True).stdout.split()
+    return [d for k in kids for d in [k] + _descendants(k)]
+
+
+def _processes_naming(path) -> list:
+    """Live processes whose command line names PATH (read only, to report leftovers)."""
+    out = subprocess.run(["ps", "-A", "-ww", "-o", "pid=", "-o", "args="], capture_output=True, text=True).stdout
+    return [line.strip() for line in out.splitlines()
+            if str(path) in line and line.split(None, 1)[0] != str(os.getpid())]
+
+
 def _lock_held(path: Path) -> bool:
     if not path.exists():
         return False
@@ -206,12 +218,26 @@ def box(template, tmp_path):
     try:
         yield b
     finally:
+        # Only what this test started: its helpers' process groups, and the
+        # monitors whose exact command line is this test's own workspace
+        # (detached, so in a group of their own), with their children. No
+        # pattern kill: the host runs other workspaces' monitors.
         for p in b.helpers:
             try:
                 os.killpg(p.pid, signal.SIGKILL)
             except OSError:
                 pass
-        subprocess.run(["pkill", "-KILL", "-f", str(ws)], capture_output=True)
+            p.wait()
+        for pid in _exact_monitor_pids(ws / MONITOR_REL):
+            for q in [pid] + _descendants(pid):
+                try:
+                    os.kill(int(q), signal.SIGKILL)
+                except OSError:
+                    pass
+        try:
+            _until(lambda: not _processes_naming(ws), timeout=10)
+        except AssertionError:
+            raise AssertionError("processes of this test outlived it: %s" % _processes_naming(ws))
 
 
 # --- helpers ---------------------------------------------------------------------
@@ -673,8 +699,9 @@ def test_only_this_workspaces_exact_monitor_command_line_is_its_monitor(tmp_path
 def test_every_restart_starts_a_real_monitor_in_both_delegation_modes(box, mode, case):
     """MAM_DELEGATION_PY=0 keeps the legacy start_watchdog, the switch the
     delegate skill documents. Its restart, after an install, after a stop
-    timeout or after a rollback, must start this workspace's monitor again and
+    timeout or after a rollback, must start this workspace's monitor again, out
-    not report a process that only names the monitor path in an argument."""
+    of the caller's process group (decision 2), and not report a process that
+    only names the monitor path in an argument."""
     env = {"MAM_DELEGATION_PY": mode}
     box.stub_monitor()
     box.start_monitor(env=dict(env, STUB_MONITOR_IGNORE_TERM="1") if case == "killed" else env)
@@ -693,6 +720,8 @@ def test_every_restart_starts_a_real_monitor_in_both_delegation_modes(box, mode,
     assert "PID %s)" % decoy.pid not in res.stdout, "the decoy is reported as the monitor"
     _until(lambda: bool(box.monitor_pids()))
     assert not (set(box.monitor_pids()) & first) and box.monitor_starts() == 2
+    # box.update runs update.sh in this test's process group: the caller's.
+    assert all(os.getpgid(int(p)) != os.getpgrp() for p in box.monitor_pids()), "left in the caller's group"
     assert decoy.poll() is None, "the decoy was not signalled"