Merge pull request #1339 from NousResearch/hermes/hermes-048e6599

Merging Telegram gateway conflict hardening: same-host token lock, clean shutdown on getUpdates conflict, persisted runtime health, and clearer gateway status diagnostics.

tests/gateway/test_runner_fatal_adapter.py

@@ -0,0 +1,46 @@
+import pytest
+
+from gateway.config import GatewayConfig, Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter
+from gateway.run import GatewayRunner
+
+
+class _FatalAdapter(BasePlatformAdapter):
+    def __init__(self):
+        super().__init__(PlatformConfig(enabled=True, token="token"), Platform.TELEGRAM)
+
+    async def connect(self) -> bool:
+        self._set_fatal_error(
+            "telegram_token_lock",
+            "Another local Hermes gateway is already using this Telegram bot token.",
+            retryable=False,
+        )
+        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}
+
+
+@pytest.mark.asyncio
+async def test_runner_requests_clean_exit_for_nonretryable_startup_conflict(monkeypatch, tmp_path):
+    config = GatewayConfig(
+        platforms={
+            Platform.TELEGRAM: PlatformConfig(enabled=True, token="token")
+        },
+        sessions_dir=tmp_path / "sessions",
+    )
+    runner = GatewayRunner(config)
+
+    monkeypatch.setattr(runner, "_create_adapter", lambda platform, platform_config: _FatalAdapter())
+
+    ok = await runner.start()
+
+    assert ok is True
+    assert runner.should_exit_cleanly is True
+    assert "already using this Telegram bot token" in runner.exit_reason

tests/gateway/test_status.py

@@ -25,3 +25,77 @@ class TestGatewayPidState:
 
         assert status.get_running_pid() is None
         assert not pid_path.exists()
+
+
+class TestGatewayRuntimeStatus:
+    def test_write_runtime_status_records_platform_failure(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_HOME", str(tmp_path))
+
+        status.write_runtime_status(
+            gateway_state="startup_failed",
+            exit_reason="telegram conflict",
+            platform="telegram",
+            platform_state="fatal",
+            error_code="telegram_polling_conflict",
+            error_message="another poller is active",
+        )
+
+        payload = status.read_runtime_status()
+        assert payload["gateway_state"] == "startup_failed"
+        assert payload["exit_reason"] == "telegram conflict"
+        assert payload["platforms"]["telegram"]["state"] == "fatal"
+        assert payload["platforms"]["telegram"]["error_code"] == "telegram_polling_conflict"
+        assert payload["platforms"]["telegram"]["error_message"] == "another poller is active"
+
+
+class TestScopedLocks:
+    def test_acquire_scoped_lock_rejects_live_other_process(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
+        lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
+        lock_path.parent.mkdir(parents=True, exist_ok=True)
+        lock_path.write_text(json.dumps({
+            "pid": 99999,
+            "start_time": 123,
+            "kind": "hermes-gateway",
+        }))
+
+        monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
+        monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
+
+        acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
+
+        assert acquired is False
+        assert existing["pid"] == 99999
+
+    def test_acquire_scoped_lock_replaces_stale_record(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
+        lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
+        lock_path.parent.mkdir(parents=True, exist_ok=True)
+        lock_path.write_text(json.dumps({
+            "pid": 99999,
+            "start_time": 123,
+            "kind": "hermes-gateway",
+        }))
+
+        def fake_kill(pid, sig):
+            raise ProcessLookupError
+
+        monkeypatch.setattr(status.os, "kill", fake_kill)
+
+        acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
+
+        assert acquired is True
+        payload = json.loads(lock_path.read_text())
+        assert payload["pid"] == os.getpid()
+        assert payload["metadata"]["platform"] == "telegram"
+
+    def test_release_scoped_lock_only_removes_current_owner(self, tmp_path, monkeypatch):
+        monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
+
+        acquired, _ = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
+        assert acquired is True
+        lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
+        assert lock_path.exists()
+
+        status.release_scoped_lock("telegram-bot-token", "secret")
+        assert not lock_path.exists()

tests/gateway/test_telegram_conflict.py

@@ -0,0 +1,100 @@
+import asyncio
+import sys
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from gateway.config import PlatformConfig
+
+
+def _ensure_telegram_mock():
+    if "telegram" in sys.modules and hasattr(sys.modules["telegram"], "__file__"):
+        return
+
+    telegram_mod = MagicMock()
+    telegram_mod.ext.ContextTypes.DEFAULT_TYPE = type(None)
+    telegram_mod.constants.ParseMode.MARKDOWN_V2 = "MarkdownV2"
+    telegram_mod.constants.ChatType.GROUP = "group"
+    telegram_mod.constants.ChatType.SUPERGROUP = "supergroup"
+    telegram_mod.constants.ChatType.CHANNEL = "channel"
+    telegram_mod.constants.ChatType.PRIVATE = "private"
+
+    for name in ("telegram", "telegram.ext", "telegram.constants"):
+        sys.modules.setdefault(name, telegram_mod)
+
+
+_ensure_telegram_mock()
+
+from gateway.platforms.telegram import TelegramAdapter  # noqa: E402
+
+
+@pytest.mark.asyncio
+async def test_connect_rejects_same_host_token_lock(monkeypatch):
+    adapter = TelegramAdapter(PlatformConfig(enabled=True, token="secret-token"))
+
+    monkeypatch.setattr(
+        "gateway.status.acquire_scoped_lock",
+        lambda scope, identity, metadata=None: (False, {"pid": 4242}),
+    )
+
+    ok = await adapter.connect()
+
+    assert ok is False
+    assert adapter.fatal_error_code == "telegram_token_lock"
+    assert adapter.has_fatal_error is True
+    assert "already using this Telegram bot token" in adapter.fatal_error_message
+
+
+@pytest.mark.asyncio
+async def test_polling_conflict_stops_polling_and_notifies_handler(monkeypatch):
+    adapter = TelegramAdapter(PlatformConfig(enabled=True, token="secret-token"))
+    fatal_handler = AsyncMock()
+    adapter.set_fatal_error_handler(fatal_handler)
+
+    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,
+    )
+
+    captured = {}
+
+    async def fake_start_polling(**kwargs):
+        captured["error_callback"] = kwargs["error_callback"]
+
+    updater = SimpleNamespace(
+        start_polling=AsyncMock(side_effect=fake_start_polling),
+        stop=AsyncMock(),
+    )
+    bot = SimpleNamespace(set_my_commands=AsyncMock())
+    app = SimpleNamespace(
+        bot=bot,
+        updater=updater,
+        add_handler=MagicMock(),
+        initialize=AsyncMock(),
+        start=AsyncMock(),
+    )
+    builder = MagicMock()
+    builder.token.return_value = builder
+    builder.build.return_value = app
+    monkeypatch.setattr("gateway.platforms.telegram.Application", SimpleNamespace(builder=MagicMock(return_value=builder)))
+
+    ok = await adapter.connect()
+
+    assert ok is True
+    assert callable(captured["error_callback"])
+
+    conflict = type("Conflict", (Exception,), {})
+    captured["error_callback"](conflict("Conflict: terminated by other getUpdates request; make sure that only one bot instance is running"))
+
+    await asyncio.sleep(0)
+    await asyncio.sleep(0)
+
+    assert adapter.fatal_error_code == "telegram_polling_conflict"
+    assert adapter.has_fatal_error is True
+    updater.stop.assert_awaited()
+    fatal_handler.assert_awaited_once()

tests/hermes_cli/test_gateway_runtime_health.py

@@ -0,0 +1,22 @@
+from hermes_cli.gateway import _runtime_health_lines
+
+
+def test_runtime_health_lines_include_fatal_platform_and_startup_reason(monkeypatch):
+    monkeypatch.setattr(
+        "gateway.status.read_runtime_status",
+        lambda: {
+            "gateway_state": "startup_failed",
+            "exit_reason": "telegram conflict",
+            "platforms": {
+                "telegram": {
+                    "state": "fatal",
+                    "error_message": "another poller is active",
+                }
+            },
+        },
+    )
+
+    lines = _runtime_health_lines()
+
+    assert "⚠ telegram: another poller is active" in lines
+    assert "⚠ Last startup issue: telegram conflict" in lines