fix(update): the legacy start_watchdog matches the monitor exactly too; a restart is reported only when the monitor runs (Issue #72, review round 4)

With MAM_DELEGATION_PY=0 the legacy helper still found the monitor with an
unanchored pgrep -f, so a process that only named the monitor path was
reported as the restarted monitor and none was started. lib.sh _monitor_pids
is the shell twin of daemon.find_running; update.sh and post_update.sh check
the PID start_watchdog printed with mam_monitor_started before saying
"monitor: restarted".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_issue72_update.py

@@ -146,9 +146,12 @@ class Box:
         _until(lambda: _lock_held(self.mam / "monitor.lock"))
 
     def monitor_pids(self):
-        r = subprocess.run(["pgrep", "-f", "bash %s --subscribe" % (self.ws / MONITOR_REL)],
-                           capture_output=True, text=True)
-        return r.stdout.split()
+        return _exact_monitor_pids(self.ws / MONITOR_REL)
+
+    def decoy(self):
+        """A process that only names this workspace's monitor in an argument."""
+        return self.helper("/bin/bash", "-c", "sleep 120 & wait $!",
+                           "bash %s --subscribe" % (self.ws / MONITOR_REL))
 
     def monitor_starts(self):
         p = self.mam / "stub-monitor.log"
@@ -164,6 +167,20 @@ def _until(cond, timeout=15.0):
     raise AssertionError("condition not met within %ss" % timeout)
 
 
+def _exact_monitor_pids(script) -> list:
+    """`bash <script> --subscribe ...` processes, judged here independently of
+    the code under test (a `pgrep -f` would also count a decoy)."""
+    out = subprocess.run(["ps", "-A", "-ww", "-o", "pid=", "-o", "args="], capture_output=True, text=True).stdout
+    want = "%s --subscribe" % script
+    pids = []
+    for line in out.splitlines():
+        pid, _, args = line.strip().partition(" ")
+        argv0, _, rest = args.partition(" ")
+        if os.path.basename(argv0) == "bash" and (rest == want or rest.startswith(want + " ")):
+            pids.append(pid)
+    return pids
+
+
 def _lock_held(path: Path) -> bool:
     if not path.exists():
         return False
@@ -603,11 +620,13 @@ def test_a_monitor_lock_held_by_an_unknown_process_refuses(box):
     assert_refused_unchanged(box, before, res, "monitor.lock is held by a monitor the skills did not start")
 
 
-def test_only_this_workspaces_exact_monitor_command_line_is_its_monitor(tmp_path):
-    """The update signals what `lib_py.update monitor` returns: `bash <this
-    workspace's reconcile.sh> --subscribe ...` only - not another workspace's
-    daemon the path matched as a regex (ws.a, wsXa), nor a process that names
-    the path in an argument. A path with a space is still found."""
+@pytest.mark.parametrize("finder", ["python", "shell"])
+def test_only_this_workspaces_exact_monitor_command_line_is_its_monitor(tmp_path, finder):
+    """The update signals what `lib_py.update monitor` returns, and the legacy
+    start_watchdog (MAM_DELEGATION_PY=0) reuses what lib.sh _monitor_pids finds:
+    `bash <this workspace's reconcile.sh> --subscribe ...` only - not another
+    workspace's daemon the path matched as a regex (ws.a, wsXa), nor a process
+    that names the path in an argument. A path with a space is still found."""
     root = Path(os.path.realpath(tmp_path))
     procs = []
 
@@ -620,6 +639,12 @@ def test_only_this_workspaces_exact_monitor_command_line_is_its_monitor(tmp_path
         return str(procs[-1].pid)
 
     def monitor(ws):
+        if finder == "shell":
+            res = subprocess.run(["bash", "-c", 'source "$1" && _monitor_pids "$2"', "_",
+                                  str(REPO_ROOT / ".agents" / "skills" / "lib.sh"), str(ws / MONITOR_REL)],
+                                 env=dict(_clean_env(), WORKSPACE_ROOT=str(root)), capture_output=True, text=True)
+            assert res.returncode == 0, res.stderr
+            return res.stdout.split()
         res = subprocess.run([sys.executable, "-m", "lib_py.update", "monitor", "--workspace", str(ws)],
                              cwd=str(REPO_ROOT / ".agents" / "skills"), capture_output=True, text=True)
         assert res.returncode == 0, res.stderr
@@ -643,6 +668,34 @@ def test_only_this_workspaces_exact_monitor_command_line_is_its_monitor(tmp_path
             p.wait()
 
 
+@pytest.mark.parametrize("case", ["installed", "killed", "rolled-back"])
+@pytest.mark.parametrize("mode", ["0", "1"])
+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
+    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)
+    first = set(box.monitor_pids())
+    decoy = box.decoy()
+    _until(lambda: str(decoy.pid) in subprocess.run(["ps", "-A", "-ww", "-o", "pid=", "-o", "args="],
+                                                     capture_output=True, text=True).stdout)
+    if case == "killed":
+        env["MAM_UPDATE_MONITOR_STOP_S"] = "1"
+    if case == "rolled-back":
+        box.installer("exit 7\n")
+    res = box.update(env=env)
+    assert res.returncode == (0 if case == "installed" else 1), res.stdout + res.stderr
+    assert {"installed": "monitor: restarted", "killed": "it was killed and is started again",
+            "rolled-back": "rolled back"}[case] in res.stdout + res.stderr
+    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
+    assert decoy.poll() is None, "the decoy was not signalled"
+
+
 # --- rollback (decisions 3, 10; U4) --------------------------------------------------
 
 FAILING_INSTALL = """