From dccf1fb6e0eacca33a3c46f44bccde35f9fa2880 Mon Sep 17 00:00:00 2001
From: LeonSGP43 <cine.dreamer.one@gmail.com>
Date: Tue, 5 May 2026 10:18:06 +0800
Subject: [PATCH] fix(gateway): cap adapter disconnect during stop

---
 gateway/run.py                                | 28 ++++++++++++++++++-
 hermes_cli/gateway.py                         | 10 ++++++-
 tests/gateway/test_safe_adapter_disconnect.py | 20 +++++++++++++
 tests/hermes_cli/test_gateway_service.py      | 23 +++++++++++++++
 4 files changed, 79 insertions(+), 2 deletions(-)

diff --git a/gateway/run.py b/gateway/run.py
index 13d57c46d0..457dc60d75 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -61,6 +61,7 @@ from hermes_cli.config import cfg_get
 _AGENT_CACHE_MAX_SIZE = 128
 _AGENT_CACHE_IDLE_TTL_SECS = 3600.0  # evict agents idle for >1h
 _PLATFORM_CONNECT_TIMEOUT_SECS_DEFAULT = 30.0
+_ADAPTER_DISCONNECT_TIMEOUT_SECS_DEFAULT = 5.0
 _TELEGRAM_COMMAND_MENTION_RE = re.compile(r"(?<![\w:/])/([A-Za-z0-9][A-Za-z0-9_-]*)")
 
 
@@ -1494,8 +1495,18 @@ class GatewayRunner:
         Must tolerate partial-init state and never raise, since callers
         use it inside error-handling blocks.
         """
+        timeout = self._adapter_disconnect_timeout_secs()
         try:
-            await adapter.disconnect()
+            if timeout <= 0:
+                await adapter.disconnect()
+            else:
+                await asyncio.wait_for(adapter.disconnect(), timeout=timeout)
+        except asyncio.TimeoutError:
+            logger.warning(
+                "Timed out after %.1fs while disconnecting %s adapter; continuing shutdown",
+                timeout,
+                platform.value if platform is not None else "adapter",
+            )
         except Exception as e:
             logger.debug(
                 "Defensive %s disconnect after failed connect raised: %s",
@@ -1503,6 +1514,21 @@ class GatewayRunner:
                 e,
             )
 
+    def _adapter_disconnect_timeout_secs(self) -> float:
+        """Return the per-adapter disconnect timeout used during shutdown."""
+        raw = os.getenv("HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT", "").strip()
+        if raw:
+            try:
+                timeout = float(raw)
+            except ValueError:
+                logger.warning(
+                    "Ignoring invalid HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT=%r",
+                    raw,
+                )
+            else:
+                return max(0.0, timeout)
+        return _ADAPTER_DISCONNECT_TIMEOUT_SECS_DEFAULT
+
     def _platform_connect_timeout_secs(self) -> float:
         """Return the per-platform connect timeout used during startup/retry."""
         raw = os.getenv("HERMES_GATEWAY_PLATFORM_CONNECT_TIMEOUT", "").strip()
diff --git a/hermes_cli/gateway.py b/hermes_cli/gateway.py
index ecd7fa2e0c..adee8cd44b 100644
--- a/hermes_cli/gateway.py
+++ b/hermes_cli/gateway.py
@@ -2387,7 +2387,15 @@ def systemd_stop(system: bool = False):
             write_planned_stop_marker(pid)
     except Exception:
         pass
-    _run_systemctl(["stop", get_service_name()], system=system, check=True, timeout=90)
+    try:
+        _run_systemctl(["stop", get_service_name()], system=system, check=True, timeout=90)
+    except subprocess.TimeoutExpired:
+        label = _service_scope_label(system)
+        print(
+            f"Gateway {label} service is still stopping after 90s; "
+            "check `hermes gateway status` or logs for final shutdown state."
+        )
+        return
     print(f"✓ {_service_scope_label(system).capitalize()} service stopped")
 
 
diff --git a/tests/gateway/test_safe_adapter_disconnect.py b/tests/gateway/test_safe_adapter_disconnect.py
index ec11f2663a..9a17aa0476 100644
--- a/tests/gateway/test_safe_adapter_disconnect.py
+++ b/tests/gateway/test_safe_adapter_disconnect.py
@@ -10,6 +10,8 @@ The fix: gateway/run.py wraps each adapter connect() with a safety-net
 call to _safe_adapter_disconnect() in the failure branches.
 """
 
+import asyncio
+import logging
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
@@ -57,3 +59,21 @@ async def test_safe_disconnect_handles_none_platform(bare_runner):
     await bare_runner._safe_adapter_disconnect(adapter, None)
 
     adapter.disconnect.assert_awaited_once()
+
+
+@pytest.mark.asyncio
+async def test_safe_disconnect_times_out_and_continues(bare_runner, monkeypatch, caplog):
+    """A wedged adapter disconnect must not block gateway shutdown."""
+    monkeypatch.setenv("HERMES_GATEWAY_ADAPTER_DISCONNECT_TIMEOUT", "0.001")
+    adapter = MagicMock()
+
+    async def hang():
+        await asyncio.sleep(60)
+
+    adapter.disconnect = AsyncMock(side_effect=hang)
+
+    with caplog.at_level(logging.WARNING, logger="gateway.run"):
+        await bare_runner._safe_adapter_disconnect(adapter, Platform.FEISHU)
+
+    adapter.disconnect.assert_awaited_once()
+    assert "Timed out after 0.0s while disconnecting feishu adapter" in caplog.text
diff --git a/tests/hermes_cli/test_gateway_service.py b/tests/hermes_cli/test_gateway_service.py
index 15968f798e..3b68476fbd 100644
--- a/tests/hermes_cli/test_gateway_service.py
+++ b/tests/hermes_cli/test_gateway_service.py
@@ -140,6 +140,29 @@ class TestSystemdServiceRefresh:
         assert markers == [321]
         assert calls == [["stop", gateway_cli.get_service_name()]]
 
+    def test_systemd_stop_timeout_prints_status_guidance(self, monkeypatch, capsys):
+        markers = []
+
+        monkeypatch.setattr(gateway_cli, "_select_systemd_scope", lambda system=False: False)
+        monkeypatch.setattr(gateway_cli, "_require_service_installed", lambda action, system=False: None)
+        monkeypatch.setattr(status, "get_running_pid", lambda cleanup_stale=True: 321)
+        monkeypatch.setattr(
+            status,
+            "write_planned_stop_marker",
+            lambda pid: markers.append(pid) or True,
+        )
+
+        def fake_run_systemctl(args, **kwargs):
+            raise subprocess.TimeoutExpired(args, kwargs.get("timeout"))
+
+        monkeypatch.setattr(gateway_cli, "_run_systemctl", fake_run_systemctl)
+
+        gateway_cli.systemd_stop()
+
+        assert markers == [321]
+        output = capsys.readouterr().out
+        assert "still stopping after 90s" in output
+        assert "hermes gateway status" in output
 
     def test_run_gateway_refreshes_outdated_unit_on_boot(self, tmp_path, monkeypatch):
         """run_gateway() should refresh the systemd unit on boot so that