From b429bf9381d22edd4a5d35eb720cd2704eae63b5 Mon Sep 17 00:00:00 2001
From: Re-bin <xubinrencs@gmail.com>
Date: Thu, 12 Feb 2026 01:20:57 +0000
Subject: [PATCH] fix: improve long-running stability for various channels

---
 nanobot/channels/dingtalk.py | 11 +++++++++--
 nanobot/channels/feishu.py   | 13 ++++++++-----
 nanobot/channels/qq.py       | 15 +++++++++------
 nanobot/channels/telegram.py | 11 +++++++++--
 4 files changed, 35 insertions(+), 15 deletions(-)

diff --git a/nanobot/channels/dingtalk.py b/nanobot/channels/dingtalk.py
index 72d3afd..4a8cdd9 100644
--- a/nanobot/channels/dingtalk.py
+++ b/nanobot/channels/dingtalk.py
@@ -137,8 +137,15 @@ class DingTalkChannel(BaseChannel):
 
             logger.info("DingTalk bot started with Stream Mode")
 
-            # client.start() is an async infinite loop handling the websocket connection
-            await self._client.start()
+            # Reconnect loop: restart stream if SDK exits or crashes
+            while self._running:
+                try:
+                    await self._client.start()
+                except Exception as e:
+                    logger.warning(f"DingTalk stream error: {e}")
+                if self._running:
+                    logger.info("Reconnecting DingTalk stream in 5 seconds...")
+                    await asyncio.sleep(5)
 
         except Exception as e:
             logger.exception(f"Failed to start DingTalk channel: {e}")
diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py
index 1c176a2..23d1415 100644
--- a/nanobot/channels/feishu.py
+++ b/nanobot/channels/feishu.py
@@ -98,12 +98,15 @@ class FeishuChannel(BaseChannel):
             log_level=lark.LogLevel.INFO
         )
         
-        # Start WebSocket client in a separate thread
+        # Start WebSocket client in a separate thread with reconnect loop
         def run_ws():
-            try:
-                self._ws_client.start()
-            except Exception as e:
-                logger.error(f"Feishu WebSocket error: {e}")
+            while self._running:
+                try:
+                    self._ws_client.start()
+                except Exception as e:
+                    logger.warning(f"Feishu WebSocket error: {e}")
+                if self._running:
+                    import time; time.sleep(5)
         
         self._ws_thread = threading.Thread(target=run_ws, daemon=True)
         self._ws_thread.start()
diff --git a/nanobot/channels/qq.py b/nanobot/channels/qq.py
index 5964d30..0e8fe66 100644
--- a/nanobot/channels/qq.py
+++ b/nanobot/channels/qq.py
@@ -75,12 +75,15 @@ class QQChannel(BaseChannel):
         logger.info("QQ bot started (C2C private message)")
 
     async def _run_bot(self) -> None:
-        """Run the bot connection."""
-        try:
-            await self._client.start(appid=self.config.app_id, secret=self.config.secret)
-        except Exception as e:
-            logger.error(f"QQ auth failed, check AppID/Secret at q.qq.com: {e}")
-            self._running = False
+        """Run the bot connection with auto-reconnect."""
+        while self._running:
+            try:
+                await self._client.start(appid=self.config.app_id, secret=self.config.secret)
+            except Exception as e:
+                logger.warning(f"QQ bot error: {e}")
+            if self._running:
+                logger.info("Reconnecting QQ bot in 5 seconds...")
+                await asyncio.sleep(5)
 
     async def stop(self) -> None:
         """Stop the QQ bot."""
diff --git a/nanobot/channels/telegram.py b/nanobot/channels/telegram.py
index ff46c86..1abd600 100644
--- a/nanobot/channels/telegram.py
+++ b/nanobot/channels/telegram.py
@@ -9,6 +9,7 @@ from typing import TYPE_CHECKING
 from loguru import logger
 from telegram import BotCommand, Update
 from telegram.ext import Application, CommandHandler, MessageHandler, filters, ContextTypes
+from telegram.request import HTTPXRequest
 
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
@@ -121,11 +122,13 @@ class TelegramChannel(BaseChannel):
         
         self._running = True
         
-        # Build the application
-        builder = Application.builder().token(self.config.token)
+        # Build the application with larger connection pool to avoid pool-timeout on long runs
+        req = HTTPXRequest(connection_pool_size=16, pool_timeout=5.0, connect_timeout=30.0, read_timeout=30.0)
+        builder = Application.builder().token(self.config.token).request(req).get_updates_request(req)
         if self.config.proxy:
             builder = builder.proxy(self.config.proxy).get_updates_proxy(self.config.proxy)
         self._app = builder.build()
+        self._app.add_error_handler(self._on_error)
         
         # Add command handlers
         self._app.add_handler(CommandHandler("start", self._on_start))
@@ -386,6 +389,10 @@ class TelegramChannel(BaseChannel):
         except Exception as e:
             logger.debug(f"Typing indicator stopped for {chat_id}: {e}")
     
+    async def _on_error(self, update: object, context: ContextTypes.DEFAULT_TYPE) -> None:
+        """Log polling / handler errors instead of silently swallowing them."""
+        logger.error(f"Telegram error: {context.error}")
+
     def _get_extension(self, media_type: str, mime_type: str | None) -> str:
         """Get file extension based on media type."""
         if mime_type: