fix(gateway): fix discrepancies in gateway status

gateway/status.py

@@ -188,8 +188,8 @@ def _write_json_file(path: Path, payload: dict[str, Any]) -> None:
     path.write_text(json.dumps(payload))
 
 
-def _read_pid_record() -> Optional[dict]:
-    pid_path = _get_pid_path()
+def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
+    pid_path = pid_path or _get_pid_path()
     if not pid_path.exists():
         return None
 
@@ -212,6 +212,18 @@ def _read_pid_record() -> Optional[dict]:
     return None
 
 
+def _cleanup_invalid_pid_path(pid_path: Path, *, cleanup_stale: bool) -> None:
+    if not cleanup_stale:
+        return
+    try:
+        if pid_path == _get_pid_path():
+            remove_pid_file()
+        else:
+            pid_path.unlink(missing_ok=True)
+    except Exception:
+        pass
+
+
 def write_pid_file() -> None:
     """Write the current process PID and metadata to the gateway PID file."""
     _write_json_file(_get_pid_path(), _build_pid_record())
@@ -413,43 +425,52 @@ def release_all_scoped_locks() -> int:
     return removed
 
 
-def get_running_pid() -> Optional[int]:
+def get_running_pid(
+    pid_path: Optional[Path] = None,
+    *,
+    cleanup_stale: bool = True,
+) -> Optional[int]:
     """Return the PID of a running gateway instance, or ``None``.
 
     Checks the PID file and verifies the process is actually alive.
     Cleans up stale PID files automatically.
     """
-    record = _read_pid_record()
+    resolved_pid_path = pid_path or _get_pid_path()
+    record = _read_pid_record(resolved_pid_path)
     if not record:
-        remove_pid_file()
+        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
         return None
 
     try:
         pid = int(record["pid"])
     except (KeyError, TypeError, ValueError):
-        remove_pid_file()
+        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
         return None
 
     try:
         os.kill(pid, 0)  # signal 0 = existence check, no actual signal sent
     except (ProcessLookupError, PermissionError):
-        remove_pid_file()
+        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
         return None
 
     recorded_start = record.get("start_time")
     current_start = _get_process_start_time(pid)
     if recorded_start is not None and current_start is not None and current_start != recorded_start:
-        remove_pid_file()
+        _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
         return None
 
     if not _looks_like_gateway_process(pid):
         if not _record_looks_like_gateway(record):
-            remove_pid_file()
+            _cleanup_invalid_pid_path(resolved_pid_path, cleanup_stale=cleanup_stale)
             return None
 
     return pid
 
 
-def is_gateway_running() -> bool:
+def is_gateway_running(
+    pid_path: Optional[Path] = None,
+    *,
+    cleanup_stale: bool = True,
+) -> bool:
     """Check if the gateway daemon is currently running."""
-    return get_running_pid() is not None
+    return get_running_pid(pid_path, cleanup_stale=cleanup_stale) is not None

hermes_cli/dump.py

@@ -43,41 +43,20 @@ def _redact(value: str) -> str:
 
 def _gateway_status() -> str:
     """Return a short gateway status string."""
-    if sys.platform.startswith("linux"):
-        from hermes_constants import is_container
-        if is_container():
-            try:
-                from hermes_cli.gateway import find_gateway_pids
-                pids = find_gateway_pids()
-                if pids:
-                    return f"running (docker, pid {pids[0]})"
-                return "stopped (docker)"
-            except Exception:
-                return "stopped (docker)"
-        try:
-            from hermes_cli.gateway import get_service_name
-            svc = get_service_name()
-        except Exception:
-            svc = "hermes-gateway"
-        try:
-            r = subprocess.run(
-                ["systemctl", "--user", "is-active", svc],
-                capture_output=True, text=True, timeout=5,
-            )
-            return "running (systemd)" if r.stdout.strip() == "active" else "stopped"
-        except Exception:
-            return "unknown"
-    elif sys.platform == "darwin":
-        try:
-            from hermes_cli.gateway import get_launchd_label
-            r = subprocess.run(
-                ["launchctl", "list", get_launchd_label()],
-                capture_output=True, text=True, timeout=5,
-            )
-            return "loaded (launchd)" if r.returncode == 0 else "not loaded"
-        except Exception:
-            return "unknown"
-    return "N/A"
+    try:
+        from hermes_cli.gateway import get_gateway_runtime_snapshot
+
+        snapshot = get_gateway_runtime_snapshot()
+        if snapshot.running:
+            mode = snapshot.manager
+            if snapshot.has_process_service_mismatch:
+                mode = "manual"
+            return f"running ({mode}, pid {snapshot.gateway_pids[0]})"
+        if snapshot.service_installed and not snapshot.service_running:
+            return f"stopped ({snapshot.manager})"
+        return f"stopped ({snapshot.manager})"
+    except Exception:
+        return "unknown" if sys.platform.startswith(("linux", "darwin")) else "N/A"
 
 
 def _count_skills(hermes_home: Path) -> int:

hermes_cli/gateway.py

@@ -10,6 +10,7 @@ import shutil
 import signal
 import subprocess
 import sys
+from dataclasses import dataclass
 from pathlib import Path
 
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()
@@ -41,6 +42,23 @@ from hermes_cli.colors import Colors, color
 # Process Management (for manual gateway runs)
 # =============================================================================
 
+
+@dataclass(frozen=True)
+class GatewayRuntimeSnapshot:
+    manager: str
+    service_installed: bool = False
+    service_running: bool = False
+    gateway_pids: tuple[int, ...] = ()
+    service_scope: str | None = None
+
+    @property
+    def running(self) -> bool:
+        return self.service_running or bool(self.gateway_pids)
+
+    @property
+    def has_process_service_mismatch(self) -> bool:
+        return self.service_installed and self.running and not self.service_running
+
 def _get_service_pids() -> set:
     """Return PIDs currently managed by systemd or launchd gateway services.
 
@@ -157,20 +175,22 @@ def _request_gateway_self_restart(pid: int) -> bool:
     return True
 
 
-def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = False) -> list:
-    """Find PIDs of running gateway processes.
+def _append_unique_pid(pids: list[int], pid: int | None, exclude_pids: set[int]) -> None:
+    if pid is None or pid <= 0:
+        return
+    if pid == os.getpid() or pid in exclude_pids or pid in pids:
+        return
+    pids.append(pid)
 
-    Args:
-        exclude_pids: PIDs to exclude from the result (e.g. service-managed
-            PIDs that should not be killed during a stale-process sweep).
-        all_profiles: When ``True``, return gateway PIDs across **all**
-            profiles (the pre-7923 global behaviour).  ``hermes update``
-            needs this because a code update affects every profile.
-            When ``False`` (default), only PIDs belonging to the current
-            Hermes profile are returned.
+
+def _scan_gateway_pids(exclude_pids: set[int], all_profiles: bool = False) -> list[int]:
+    """Best-effort process-table scan for gateway PIDs.
+
+    This supplements the profile-scoped PID file so status views can still spot
+    a live gateway when the PID file is stale/missing, and ``--all`` sweeps can
+    discover gateways outside the current profile.
     """
-    _exclude = exclude_pids or set()
-    pids = [pid for pid in _get_service_pids() if pid not in _exclude]
+    pids: list[int] = []
     patterns = [
         "hermes_cli.main gateway",
         "hermes_cli.main --profile",
@@ -203,20 +223,24 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
         if is_windows():
             result = subprocess.run(
                 ["wmic", "process", "get", "ProcessId,CommandLine", "/FORMAT:LIST"],
-                capture_output=True, text=True, timeout=10
+                capture_output=True,
+                text=True,
+                timeout=10,
             )
+            if result.returncode != 0:
+                return []
             current_cmd = ""
-            for line in result.stdout.split('\n'):
+            for line in result.stdout.split("\n"):
                 line = line.strip()
                 if line.startswith("CommandLine="):
                     current_cmd = line[len("CommandLine="):]
                 elif line.startswith("ProcessId="):
                     pid_str = line[len("ProcessId="):]
-                    if any(p in current_cmd for p in patterns) and (all_profiles or _matches_current_profile(current_cmd)):
+                    if any(p in current_cmd for p in patterns) and (
+                        all_profiles or _matches_current_profile(current_cmd)
+                    ):
                         try:
-                            pid = int(pid_str)
-                            if pid != os.getpid() and pid not in pids and pid not in _exclude:
-                                pids.append(pid)
+                            _append_unique_pid(pids, int(pid_str), exclude_pids)
                         except ValueError:
                             pass
                     current_cmd = ""
@@ -227,9 +251,11 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
                 text=True,
                 timeout=10,
             )
-            for line in result.stdout.split('\n'):
+            if result.returncode != 0:
+                return []
+            for line in result.stdout.split("\n"):
                 stripped = line.strip()
-                if not stripped or 'grep' in stripped:
+                if not stripped or "grep" in stripped:
                     continue
 
                 pid = None
@@ -251,16 +277,137 @@ def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = Fals
 
                 if pid is None:
                     continue
-                if pid == os.getpid() or pid in pids or pid in _exclude:
-                    continue
-                if any(pattern in command for pattern in patterns) and (all_profiles or _matches_current_profile(command)):
-                    pids.append(pid)
+                if any(pattern in command for pattern in patterns) and (
+                    all_profiles or _matches_current_profile(command)
+                ):
+                    _append_unique_pid(pids, pid, exclude_pids)
     except (OSError, subprocess.TimeoutExpired):
-        pass
+        return []
 
     return pids
 
 
+def find_gateway_pids(exclude_pids: set | None = None, all_profiles: bool = False) -> list:
+    """Find PIDs of running gateway processes.
+
+    Args:
+        exclude_pids: PIDs to exclude from the result (e.g. service-managed
+            PIDs that should not be killed during a stale-process sweep).
+        all_profiles: When ``True``, return gateway PIDs across **all**
+            profiles (the pre-7923 global behaviour).  ``hermes update``
+            needs this because a code update affects every profile.
+            When ``False`` (default), only PIDs belonging to the current
+            Hermes profile are returned.
+    """
+    _exclude = set(exclude_pids or set())
+    pids: list[int] = []
+    if not all_profiles:
+        try:
+            from gateway.status import get_running_pid
+
+            _append_unique_pid(pids, get_running_pid(), _exclude)
+        except Exception:
+            pass
+    for pid in _get_service_pids():
+        _append_unique_pid(pids, pid, _exclude)
+    for pid in _scan_gateway_pids(_exclude, all_profiles=all_profiles):
+        _append_unique_pid(pids, pid, _exclude)
+    return pids
+
+
+def _probe_systemd_service_running(system: bool = False) -> tuple[bool, bool]:
+    selected_system = _select_systemd_scope(system)
+    unit_exists = get_systemd_unit_path(system=selected_system).exists()
+    if not unit_exists:
+        return selected_system, False
+    try:
+        result = _run_systemctl(
+            ["is-active", get_service_name()],
+            system=selected_system,
+            capture_output=True,
+            text=True,
+            timeout=10,
+        )
+    except (RuntimeError, subprocess.TimeoutExpired):
+        return selected_system, False
+    return selected_system, result.stdout.strip() == "active"
+
+
+def _probe_launchd_service_running() -> bool:
+    if not get_launchd_plist_path().exists():
+        return False
+    try:
+        result = subprocess.run(
+            ["launchctl", "list", get_launchd_label()],
+            capture_output=True,
+            text=True,
+            timeout=10,
+        )
+    except subprocess.TimeoutExpired:
+        return False
+    return result.returncode == 0
+
+
+def get_gateway_runtime_snapshot(system: bool = False) -> GatewayRuntimeSnapshot:
+    """Return a unified view of gateway liveness for the current profile."""
+    gateway_pids = tuple(find_gateway_pids())
+    if is_termux():
+        return GatewayRuntimeSnapshot(
+            manager="Termux / manual process",
+            gateway_pids=gateway_pids,
+        )
+
+    from hermes_constants import is_container
+
+    if is_linux() and is_container():
+        return GatewayRuntimeSnapshot(
+            manager="docker (foreground)",
+            gateway_pids=gateway_pids,
+        )
+
+    if supports_systemd_services():
+        selected_system, service_running = _probe_systemd_service_running(system=system)
+        scope_label = _service_scope_label(selected_system)
+        return GatewayRuntimeSnapshot(
+            manager=f"systemd ({scope_label})",
+            service_installed=get_systemd_unit_path(system=selected_system).exists(),
+            service_running=service_running,
+            gateway_pids=gateway_pids,
+            service_scope=scope_label,
+        )
+
+    if is_macos():
+        return GatewayRuntimeSnapshot(
+            manager="launchd",
+            service_installed=get_launchd_plist_path().exists(),
+            service_running=_probe_launchd_service_running(),
+            gateway_pids=gateway_pids,
+            service_scope="launchd",
+        )
+
+    return GatewayRuntimeSnapshot(
+        manager="manual process",
+        gateway_pids=gateway_pids,
+    )
+
+
+def _format_gateway_pids(pids: tuple[int, ...] | list[int], *, limit: int | None = 3) -> str:
+    rendered = [str(pid) for pid in pids[:limit] if pid > 0] if limit is not None else [str(pid) for pid in pids if pid > 0]
+    if limit is not None and len(pids) > limit:
+        rendered.append("...")
+    return ", ".join(rendered)
+
+
+def _print_gateway_process_mismatch(snapshot: GatewayRuntimeSnapshot) -> None:
+    if not snapshot.has_process_service_mismatch:
+        return
+    print()
+    print("⚠ Gateway process is running for this profile, but the service is not active")
+    print(f"  PID(s): {_format_gateway_pids(snapshot.gateway_pids, limit=None)}")
+    print("  This is usually a manual foreground/tmux/nohup run, so `hermes gateway`")
+    print("  can refuse to start another copy until this process stops.")
+
+
 def kill_gateway_processes(force: bool = False, exclude_pids: set | None = None,
                            all_profiles: bool = False) -> int:
     """Kill any running gateway processes. Returns count killed.
@@ -3376,15 +3523,18 @@ def gateway_command(args):
     elif subcmd == "status":
         deep = getattr(args, 'deep', False)
         system = getattr(args, 'system', False)
+        snapshot = get_gateway_runtime_snapshot(system=system)
         
         # Check for service first
         if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
             systemd_status(deep, system=system)
+            _print_gateway_process_mismatch(snapshot)
         elif is_macos() and get_launchd_plist_path().exists():
             launchd_status(deep)
+            _print_gateway_process_mismatch(snapshot)
         else:
             # Check for manually running processes
-            pids = find_gateway_pids()
+            pids = list(snapshot.gateway_pids)
             if pids:
                 print(f"✓ Gateway is running (PID: {', '.join(map(str, pids))})")
                 print("  (Running manually, not as a system service)")

hermes_cli/profiles.py

@@ -300,19 +300,10 @@ def _read_config_model(profile_dir: Path) -> tuple:
 
 def _check_gateway_running(profile_dir: Path) -> bool:
     """Check if a gateway is running for a given profile directory."""
-    pid_file = profile_dir / "gateway.pid"
-    if not pid_file.exists():
-        return False
     try:
-        raw = pid_file.read_text().strip()
-        if not raw:
-            return False
-        data = json.loads(raw) if raw.startswith("{") else {"pid": int(raw)}
-        pid = int(data["pid"])
-        os.kill(pid, 0)  # existence check
-        return True
-    except (json.JSONDecodeError, KeyError, ValueError, TypeError,
-            ProcessLookupError, PermissionError, OSError):
+        from gateway.status import get_running_pid
+        return get_running_pid(profile_dir / "gateway.pid", cleanup_stale=False) is not None
+    except Exception:
         return False
 
 

hermes_cli/status.py

@@ -342,73 +342,36 @@ def show_status(args):
     # =========================================================================
     print()
     print(color("◆ Gateway Service", Colors.CYAN, Colors.BOLD))
-    
-    if _is_termux():
-        try:
-            from hermes_cli.gateway import find_gateway_pids
-            gateway_pids = find_gateway_pids()
-        except Exception:
-            gateway_pids = []
-        is_running = bool(gateway_pids)
+
+    try:
+        from hermes_cli.gateway import get_gateway_runtime_snapshot, _format_gateway_pids
+
+        snapshot = get_gateway_runtime_snapshot()
+        is_running = snapshot.running
         print(f"  Status:       {check_mark(is_running)} {'running' if is_running else 'stopped'}")
-        print("  Manager:      Termux / manual process")
-        if gateway_pids:
-            rendered = ", ".join(str(pid) for pid in gateway_pids[:3])
-            if len(gateway_pids) > 3:
-                rendered += ", ..."
-            print(f"  PID(s):       {rendered}")
-        else:
+        print(f"  Manager:      {snapshot.manager}")
+        if snapshot.gateway_pids:
+            print(f"  PID(s):       {_format_gateway_pids(snapshot.gateway_pids)}")
+        if snapshot.has_process_service_mismatch:
+            print("  Service:      installed but not managing the current running gateway")
+        elif _is_termux() and not snapshot.gateway_pids:
             print("  Start with:   hermes gateway")
             print("  Note:         Android may stop background jobs when Termux is suspended")
-
-    elif sys.platform.startswith('linux'):
-        from hermes_constants import is_container
-        if is_container():
-            # Docker/Podman: no systemd — check for running gateway processes
-            try:
-                from hermes_cli.gateway import find_gateway_pids
-                gateway_pids = find_gateway_pids()
-                is_active = len(gateway_pids) > 0
-            except Exception:
-                is_active = False
-            print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
-            print("  Manager:      docker (foreground)")
+        elif snapshot.service_installed and not snapshot.service_running:
+            print("  Service:      installed but stopped")
+    except Exception:
+        if _is_termux():
+            print(f"  Status:       {color('unknown', Colors.DIM)}")
+            print("  Manager:      Termux / manual process")
+        elif sys.platform.startswith('linux'):
+            print(f"  Status:       {color('unknown', Colors.DIM)}")
+            print("  Manager:      systemd/manual")
+        elif sys.platform == 'darwin':
+            print(f"  Status:       {color('unknown', Colors.DIM)}")
+            print("  Manager:      launchd")
         else:
-            try:
-                from hermes_cli.gateway import get_service_name
-                _gw_svc = get_service_name()
-            except Exception:
-                _gw_svc = "hermes-gateway"
-            try:
-                result = subprocess.run(
-                    ["systemctl", "--user", "is-active", _gw_svc],
-                    capture_output=True,
-                    text=True,
-                    timeout=5
-                )
-                is_active = result.stdout.strip() == "active"
-            except (FileNotFoundError, subprocess.TimeoutExpired):
-                is_active = False
-            print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
-            print("  Manager:      systemd (user)")
-        
-    elif sys.platform == 'darwin':
-        from hermes_cli.gateway import get_launchd_label
-        try:
-            result = subprocess.run(
-                ["launchctl", "list", get_launchd_label()],
-                capture_output=True,
-                text=True,
-                timeout=5
-            )
-            is_loaded = result.returncode == 0
-        except subprocess.TimeoutExpired:
-            is_loaded = False
-        print(f"  Status:       {check_mark(is_loaded)} {'loaded' if is_loaded else 'not loaded'}")
-        print("  Manager:      launchd")
-    else:
-        print(f"  Status:       {color('N/A', Colors.DIM)}")
-        print("  Manager:      (not supported on this platform)")
+            print(f"  Status:       {color('N/A', Colors.DIM)}")
+            print("  Manager:      (not supported on this platform)")
     
     # =========================================================================
     # Cron Jobs

tests/gateway/test_status.py

@@ -63,6 +63,24 @@ class TestGatewayPidState:
 
         assert status.get_running_pid() == os.getpid()
 
+    def test_get_running_pid_accepts_explicit_pid_path_without_cleanup(self, tmp_path, monkeypatch):
+        other_home = tmp_path / "profile-home"
+        other_home.mkdir()
+        pid_path = other_home / "gateway.pid"
+        pid_path.write_text(json.dumps({
+            "pid": os.getpid(),
+            "kind": "hermes-gateway",
+            "argv": ["python", "-m", "hermes_cli.main", "gateway"],
+            "start_time": 123,
+        }))
+
+        monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
+        monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
+        monkeypatch.setattr(status, "_read_process_cmdline", lambda pid: None)
+
+        assert status.get_running_pid(pid_path, cleanup_stale=False) == os.getpid()
+        assert pid_path.exists()
+
 
 class TestGatewayRuntimeStatus:
     def test_write_runtime_status_overwrites_stale_pid_on_restart(self, tmp_path, monkeypatch):

tests/hermes_cli/test_gateway.py

@@ -179,6 +179,21 @@ def test_install_linux_gateway_from_setup_system_choice_as_root_installs(monkeyp
     assert calls == [(True, True, "alice")]
 
 
+def test_find_gateway_pids_falls_back_to_pid_file_when_process_scan_fails(monkeypatch):
+    monkeypatch.setattr(gateway, "_get_service_pids", lambda: set())
+    monkeypatch.setattr(gateway, "is_windows", lambda: False)
+    monkeypatch.setattr("gateway.status.get_running_pid", lambda: 321)
+
+    def fake_run(cmd, **kwargs):
+        if cmd[:4] == ["ps", "-A", "eww", "-o"]:
+            return SimpleNamespace(returncode=1, stdout="", stderr="ps failed")
+        raise AssertionError(f"Unexpected command: {cmd}")
+
+    monkeypatch.setattr(gateway.subprocess, "run", fake_run)
+
+    assert gateway.find_gateway_pids() == [321]
+
+
 # ---------------------------------------------------------------------------
 # _wait_for_gateway_exit
 # ---------------------------------------------------------------------------

tests/hermes_cli/test_gateway_service.py

@@ -450,7 +450,6 @@ class TestGatewayServiceDetection:
 
         assert gateway_cli._is_service_running() is False
 
-
 class TestGatewaySystemServiceRouting:
     def test_systemd_restart_self_requests_graceful_restart_and_waits(self, monkeypatch, capsys):
         calls = []
@@ -554,6 +553,38 @@ class TestGatewaySystemServiceRouting:
 
         assert calls == [(False, False)]
 
+    def test_gateway_status_reports_manual_process_when_service_is_stopped(self, monkeypatch, capsys):
+        user_unit = SimpleNamespace(exists=lambda: True)
+        system_unit = SimpleNamespace(exists=lambda: False)
+
+        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
+        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_systemd_unit_path",
+            lambda system=False: system_unit if system else user_unit,
+        )
+        monkeypatch.setattr(gateway_cli, "systemd_status", lambda deep=False, system=False: print("service stopped"))
+        monkeypatch.setattr(
+            gateway_cli,
+            "get_gateway_runtime_snapshot",
+            lambda system=False: gateway_cli.GatewayRuntimeSnapshot(
+                manager="systemd (user)",
+                service_installed=True,
+                service_running=False,
+                gateway_pids=(4321,),
+                service_scope="user",
+            ),
+        )
+
+        gateway_cli.gateway_command(SimpleNamespace(gateway_command="status", deep=False, system=False))
+
+        out = capsys.readouterr().out
+        assert "service stopped" in out
+        assert "Gateway process is running for this profile" in out
+        assert "PID(s): 4321" in out
+
     def test_gateway_status_on_termux_shows_manual_guidance(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: False)
         monkeypatch.setattr(gateway_cli, "is_termux", lambda: True)

tests/hermes_cli/test_profiles.py

@@ -799,35 +799,30 @@ class TestEdgeCases:
         assert default.skill_count == 0
 
     def test_gateway_running_check_with_pid_file(self, profile_env):
-        """Verify _check_gateway_running reads pid file and probes os.kill."""
+        """Verify _check_gateway_running uses the shared gateway PID validator."""
         from hermes_cli.profiles import _check_gateway_running
         tmp_path = profile_env
         default_home = tmp_path / ".hermes"
 
-        # No pid file -> not running
-        assert _check_gateway_running(default_home) is False
-
-        # Write a PID file with a JSON payload
-        pid_file = default_home / "gateway.pid"
-        pid_file.write_text(json.dumps({"pid": 99999}))
-
-        # os.kill(99999, 0) should raise ProcessLookupError -> not running
-        assert _check_gateway_running(default_home) is False
-
-        # Mock os.kill to simulate a running process
-        with patch("os.kill", return_value=None):
+        with patch("gateway.status.get_running_pid", return_value=99999) as mock_get_running_pid:
             assert _check_gateway_running(default_home) is True
+        mock_get_running_pid.assert_called_once_with(
+            default_home / "gateway.pid",
+            cleanup_stale=False,
+        )
 
     def test_gateway_running_check_plain_pid(self, profile_env):
-        """Pid file containing just a number (legacy format)."""
+        """Shared PID validator returning None means the profile is not running."""
         from hermes_cli.profiles import _check_gateway_running
         tmp_path = profile_env
         default_home = tmp_path / ".hermes"
-        pid_file = default_home / "gateway.pid"
-        pid_file.write_text("99999")
 
-        with patch("os.kill", return_value=None):
-            assert _check_gateway_running(default_home) is True
+        with patch("gateway.status.get_running_pid", return_value=None) as mock_get_running_pid:
+            assert _check_gateway_running(default_home) is False
+        mock_get_running_pid.assert_called_once_with(
+            default_home / "gateway.pid",
+            cleanup_stale=False,
+        )
 
     def test_profile_name_boundary_single_char(self):
         """Single alphanumeric character is valid."""