refactor(WS): 使用连接池上下文管理器简化连接管理

重构 WS 类中的连接获取和释放逻辑，使用 connection 上下文管理器确保连接正确释放。
同时改进消息处理循环中的异常处理和连接管理。

refactor(ws_pool): 增强连接池的健壮性和管理能力

1. 添加连接上下文管理器支持
2. 改进连接获取和释放逻辑，增加连接计数和锁保护
3. 优化连接健康检查和清理机制
4. 增强错误处理和日志记录

fix(bot_status): 增加系统信息获取和渲染的错误处理

1. 为系统信息获取添加超时和错误处理
2. 为Redis数据获取添加异常捕获
3. 为图片渲染添加异常处理
4. 改进日志记录和用户反馈

plugins/bot_status.py

@@ -6,6 +6,7 @@ Bot 状态查询插件
 import os
 import psutil
 import time
+import asyncio
 from datetime import datetime, timedelta
 
 from core.bot import Bot
@@ -32,15 +33,23 @@ def _get_system_info():
     """
     同步函数：使用 psutil 获取系统信息，避免阻塞事件循环。
     """
-    # interval=1 会阻塞1秒，必须在线程池中运行
-    cpu_percent = psutil.cpu_percent(interval=1)
-    mem_info = psutil.virtual_memory()
-    bot_mem_mb = PROCESS.memory_info().rss / (1024 * 1024)
-    return {
-        "cpu_percent": f"{cpu_percent:.1f}",
-        "mem_percent": f"{mem_info.percent:.1f}",
-        "bot_mem_mb": f"{bot_mem_mb:.2f}",
-    }
+    try:
+        # interval=1 会阻塞1秒，必须在线程池中运行
+        cpu_percent = psutil.cpu_percent(interval=1)
+        mem_info = psutil.virtual_memory()
+        bot_mem_mb = PROCESS.memory_info().rss / (1024 * 1024)
+        return {
+            "cpu_percent": f"{cpu_percent:.1f}",
+            "mem_percent": f"{mem_info.percent:.1f}",
+            "bot_mem_mb": f"{bot_mem_mb:.2f}",
+        }
+    except Exception as e:
+        logger.error(f"获取系统信息失败: {e}")
+        return {
+            "cpu_percent": "N/A",
+            "mem_percent": "N/A",
+            "bot_mem_mb": "N/A",
+        }
 
 @matcher.command("status", "状态")
 async def handle_status(bot: Bot, event: MessageEvent, args: list[str]):
@@ -93,26 +102,51 @@ async def handle_status(bot: Bot, event: MessageEvent, args: list[str]):
         }
 
         # 3. 获取统计数据
-        msgs_recv = await redis_manager.get("neobot:stats:messages_received") or 0
-        msgs_sent = await redis_manager.get("neobot:stats:messages_sent") or 0
-        command_stats_raw = await redis_manager.redis.hgetall("neobot:command_stats")
-        
-        total_commands = sum(int(v) for v in command_stats_raw.values())
-        
-        stats_data = {
-            "messages_received": int(msgs_recv),
-            "messages_sent": int(msgs_sent),
-            "total_commands": total_commands,
-        }
+        try:
+            msgs_recv = await redis_manager.get("neobot:stats:messages_received") or 0
+            msgs_sent = await redis_manager.get("neobot:stats:messages_sent") or 0
+            command_stats_raw = await redis_manager.redis.hgetall("neobot:command_stats")
+            
+            total_commands = sum(int(v) for v in command_stats_raw.values())
+            
+            stats_data = {
+                "messages_received": int(msgs_recv),
+                "messages_sent": int(msgs_sent),
+                "total_commands": total_commands,
+            }
 
-        command_stats_data = sorted(
-            [{"name": k, "count": int(v)} for k, v in command_stats_raw.items()],
-            key=lambda x: x["count"],
-            reverse=True
-        )
+            command_stats_data = sorted(
+                [{"name": k, "count": int(v)} for k, v in command_stats_raw.items()],
+                key=lambda x: x["count"],
+                reverse=True
+            )
+        except Exception as e:
+            logger.error(f"获取Redis统计数据失败: {e}")
+            stats_data = {
+                "messages_received": 0,
+                "messages_sent": 0,
+                "total_commands": 0,
+            }
+            command_stats_data = []
 
         # 4. 异步获取系统信息
-        system_data = await run_in_thread_pool(_get_system_info)
+        # 设置超时，防止 psutil 阻塞过久
+        try:
+            system_data = await asyncio.wait_for(run_in_thread_pool(_get_system_info), timeout=5.0)
+        except asyncio.TimeoutError:
+            logger.error("获取系统信息超时")
+            system_data = {
+                "cpu_percent": "Timeout",
+                "mem_percent": "Timeout",
+                "bot_mem_mb": "Timeout",
+            }
+        except Exception as e:
+            logger.error(f"获取系统信息异常: {e}")
+            system_data = {
+                "cpu_percent": "Error",
+                "mem_percent": "Error",
+                "bot_mem_mb": "Error",
+            }
 
         # 5. 准备模板所需的所有数据
         template_data = {
@@ -125,18 +159,22 @@ async def handle_status(bot: Bot, event: MessageEvent, args: list[str]):
         }
 
         # 6. 渲染图片
-        base64_str = await image_manager.render_template_to_base64(
-            template_name="status.html",
-            data=template_data,
-            output_name="status.png",
-            image_type="png"
-        )
+        try:
+            base64_str = await image_manager.render_template_to_base64(
+                template_name="status.html",
+                data=template_data,
+                output_name="status.png",
+                image_type="png"
+            )
 
-        if base64_str:
-            await event.reply(MessageSegment.image(base64_str))
-        else:
-            # 如果渲染失败，image_manager 内部会记录错误，这里给用户一个通用提示
-            await event.reply("状态图片生成失败，可能是渲染服务出现问题，请联系管理员。")
+            if base64_str:
+                await event.reply(MessageSegment.image(base64_str))
+            else:
+                # 如果渲染失败，image_manager 内部会记录错误，这里给用户一个通用提示
+                await event.reply("状态图片生成失败，可能是渲染服务出现问题，请联系管理员。")
+        except Exception as e:
+            logger.error(f"渲染图片失败: {e}")
+            await event.reply("状态图片渲染过程中发生错误。")
 
     except Exception as e:
         logger.exception(f"生成状态图时发生意外错误, 用户: {event.user_id}")