fix(gateway): restart on retryable startup failures (#1517)

tests/gateway/test_runner_startup_failures.py

@@ -0,0 +1,89 @@
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter
+from gateway.run import GatewayRunner
+from gateway.status import read_runtime_status
+
+
+class _RetryableFailureAdapter(BasePlatformAdapter):
+    def __init__(self):
+        super().__init__(PlatformConfig(enabled=True, token="***"), Platform.TELEGRAM)
+
+    async def connect(self) -> bool:
+        self._set_fatal_error(
+            "telegram_connect_error",
+            "Telegram startup failed: temporary DNS resolution failure.",
+            retryable=True,
+        )
+        return False
+
+    async def disconnect(self) -> None:
+        self._mark_disconnected()
+
+    async def send(self, chat_id, content, reply_to=None, metadata=None):
+        raise NotImplementedError
+
+    async def get_chat_info(self, chat_id):
+        return {"id": chat_id}
+
+
+class _DisabledAdapter(BasePlatformAdapter):
+    def __init__(self):
+        super().__init__(PlatformConfig(enabled=False, token="***"), Platform.TELEGRAM)
+
+    async def connect(self) -> bool:
+        raise AssertionError("connect should not be called for disabled platforms")
+
+    async def disconnect(self) -> None:
+        self._mark_disconnected()
+
+    async def send(self, chat_id, content, reply_to=None, metadata=None):
+        raise NotImplementedError
+
+    async def get_chat_info(self, chat_id):
+        return {"id": chat_id}
+
+
+@pytest.mark.asyncio
+async def test_runner_returns_failure_for_retryable_startup_errors(monkeypatch, tmp_path):
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    config = GatewayConfig(
+        platforms={
+            Platform.TELEGRAM: PlatformConfig(enabled=True, token="***")
+        },
+        sessions_dir=tmp_path / "sessions",
+    )
+    runner = GatewayRunner(config)
+
+    monkeypatch.setattr(runner, "_create_adapter", lambda platform, platform_config: _RetryableFailureAdapter())
+
+    ok = await runner.start()
+
+    assert ok is False
+    assert runner.should_exit_cleanly is False
+    state = read_runtime_status()
+    assert state["gateway_state"] == "startup_failed"
+    assert "temporary DNS resolution failure" in state["exit_reason"]
+    assert state["platforms"]["telegram"]["state"] == "fatal"
+    assert state["platforms"]["telegram"]["error_code"] == "telegram_connect_error"
+
+
+@pytest.mark.asyncio
+async def test_runner_allows_cron_only_mode_when_no_platforms_are_enabled(monkeypatch, tmp_path):
+    monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+    config = GatewayConfig(
+        platforms={
+            Platform.TELEGRAM: PlatformConfig(enabled=False, token="***")
+        },
+        sessions_dir=tmp_path / "sessions",
+    )
+    runner = GatewayRunner(config)
+
+    ok = await runner.start()
+
+    assert ok is True
+    assert runner.should_exit_cleanly is False
+    assert runner.adapters == {}
+    state = read_runtime_status()
+    assert state["gateway_state"] == "running"

tests/gateway/test_telegram_conflict.py

@@ -100,6 +100,39 @@ async def test_polling_conflict_stops_polling_and_notifies_handler(monkeypatch):
     fatal_handler.assert_awaited_once()
 
 
+@pytest.mark.asyncio
+async def test_connect_marks_retryable_fatal_error_for_startup_network_failure(monkeypatch):
+    adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))
+
+    monkeypatch.setattr(
+        "gateway.status.acquire_scoped_lock",
+        lambda scope, identity, metadata=None: (True, None),
+    )
+    monkeypatch.setattr(
+        "gateway.status.release_scoped_lock",
+        lambda scope, identity: None,
+    )
+
+    builder = MagicMock()
+    builder.token.return_value = builder
+    app = SimpleNamespace(
+        bot=SimpleNamespace(),
+        updater=SimpleNamespace(),
+        add_handler=MagicMock(),
+        initialize=AsyncMock(side_effect=RuntimeError("Temporary failure in name resolution")),
+        start=AsyncMock(),
+    )
+    builder.build.return_value = app
+    monkeypatch.setattr("gateway.platforms.telegram.Application", SimpleNamespace(builder=MagicMock(return_value=builder)))
+
+    ok = await adapter.connect()
+
+    assert ok is False
+    assert adapter.fatal_error_code == "telegram_connect_error"
+    assert adapter.fatal_error_retryable is True
+    assert "Temporary failure in name resolution" in adapter.fatal_error_message
+
+
 @pytest.mark.asyncio
 async def test_disconnect_skips_inactive_updater_and_app(monkeypatch):
     adapter = TelegramAdapter(PlatformConfig(enabled=True, token="***"))