增强错误诊断：递归展开异常链+分类写入DB/告警

1. CollectWorker新增GetDetailedErrorMessage递归展开AggregateException
   解决HTTP异常只记录模糊的'发生一个或多个错误'，现可追踪到SocketException

2. JSON解析失败新增WriteBatch写入log_collect_raw（之前丢失DB记录）

3. ProductionTracker失败→cnc_alert(alert_type=production_error)

4. DailySummaryJob失败→cnc_alert(alert_type=summary_error)

5. CollectRecordWriter.DB写失败时本地日志记录完整异常链

6. log_collect_raw.error_message VARCHAR(500)→TEXT

7. 新增ErrorSimulation验证工具(模拟4类异常→验证DB/日志)

src/CncCollector/Core/CollectRecordWriter.cs

@@ -65,7 +65,8 @@ namespace CncCollector.Core
             }
             catch (Exception ex)
             {
-                _log.Error($"写入原始JSON日志失败（地址ID={collectAddressId}）", ex);
+                // 数据库不可用时，详细错误信息通过log4net写入本地日志文件，确保问题可追溯
+                _log.Error($"写入原始JSON日志失败（地址ID={collectAddressId}, 成功={isSuccess}）: {errorMessage}", ex);
             }
 
             if (!isSuccess || records == null || records.Count == 0) return lastRawLogId;

src/CncCollector/Core/CollectWorker.cs

@@ -6,6 +6,7 @@ using System.Linq;
 using System.Net;
 using System.Net.Http;
 using System.Net.NetworkInformation;
+using System.Text;
 using System.Threading;
 using System.Threading.Tasks;
 using Dapper;
@@ -97,6 +98,47 @@ namespace CncCollector.Core
             _log.Info($"采集工作线程已停止: {_address.Name}");
         }
 
+        /// <summary>
+        /// 递归提取异常链中的详细错误信息，包含所有内部异常的类型和消息。
+        /// 解决 AggregateException.Message 只返回"发生一个或多个错误。"而丢失根因的问题。
+        /// </summary>
+        private static string GetDetailedErrorMessage(Exception ex, int maxLength = 1800)
+        {
+            if (ex == null) return "";
+            var sb = new StringBuilder();
+            int depth = 0;
+            while (ex != null && sb.Length < maxLength)
+            {
+                if (depth > 0) sb.Append(" ← ");
+                sb.Append($"[{ex.GetType().Name}] {ex.Message}");
+                // 对于 AggregateException，展开所有内部异常
+                if (ex is AggregateException aggEx)
+                {
+                    foreach (var inner in aggEx.InnerExceptions)
+                    {
+                        if (sb.Length >= maxLength) break;
+                        sb.Append(" | ");
+                        sb.Append($"[{inner.GetType().Name}] {inner.Message}");
+                        if (inner.InnerException != null)
+                        {
+                            ex = inner.InnerException;
+                            depth++;
+                            goto NextLevel;
+                        }
+                    }
+                }
+                ex = ex.InnerException;
+                depth++;
+                NextLevel:;
+            }
+            if (sb.Length >= maxLength)
+            {
+                sb.Length = maxLength - 3;
+                sb.Append("...");
+            }
+            return sb.ToString();
+        }
+
         /// <summary>
         /// 工作线程主循环
         /// </summary>
@@ -110,7 +152,7 @@ namespace CncCollector.Core
                 }
                 catch (Exception ex)
                 {
-                    _log.Error($"采集循环异常（地址={_address.Name}）", ex);
+                    _log.Error($"采集循环异常（地址={_address.Name}）: {GetDetailedErrorMessage(ex, 500)}", ex);
                 }
 
                 // 等待下一次采集
@@ -174,7 +216,8 @@ namespace CncCollector.Core
                 {
                     sw.Stop();
                     durationMs = sw.ElapsedMilliseconds;
-                    errorMsg = ex.Message;
+                    errorMsg = GetDetailedErrorMessage(ex);
+                    _log.Error($"HTTP采集异常（地址={_address.Name}, 第{attempt+1}次尝试）", ex);
                 }
             }
 
@@ -210,7 +253,11 @@ namespace CncCollector.Core
             }
             catch (Exception ex)
             {
-                _log.Error($"JSON解析/入库失败（地址={_address.Name}）", ex);
+                var detailedErr = GetDetailedErrorMessage(ex);
+                _log.Error($"JSON解析/入库失败（地址={_address.Name}）: {detailedErr}", ex);
+                // 写入失败记录到日志库，便于远程诊断
+                CollectRecordWriter.WriteBatch(_businessConnStr, _logConnStr, null, rawJson,
+                    _address.Id, requestTime, durationMs, false, detailedErr, httpStatusCode);
             }
         }
 

src/CncCollector/Core/DailySummaryJob.cs

@@ -130,6 +130,18 @@ namespace CncCollector.Core
             catch (Exception ex)
             {
                 _log.Error($"日终汇总失败（日期={summaryDate:yyyy-MM-dd}）", ex);
+                // 写入告警：日终汇总失败意味着产量统计缺失
+                try
+                {
+                    using (var conn2 = new MySqlConnection(_businessConnStr))
+                    {
+                        conn2.Execute(@"INSERT INTO cnc_alert (alert_type, title, detail, is_resolved, created_at)
+                            VALUES (@Type, @Title, @Detail, 0, NOW())",
+                            new { Type = "summary_error", Title = $"日终汇总失败({summaryDate:yyyy-MM-dd})",
+                                Detail = ex.Message });
+                    }
+                }
+                catch { /* 告警写入失败不影响主流程 */ }
                 return false;
             }
         }

src/CncCollector/Core/ProductionTracker.cs

@@ -107,6 +107,18 @@ namespace CncCollector.Core
                 catch (Exception ex)
                 {
                     _log.Error($"产量跟踪处理失败（machine_id={machineId}）", ex);
+                    // 写入告警：产量跟踪失败意味着产量数据可能丢失
+                    try
+                    {
+                        using (var conn2 = new MySqlConnection(_connectionString))
+                        {
+                            conn2.Execute(@"INSERT INTO cnc_alert (alert_type, machine_id, title, detail, is_resolved, created_at)
+                                VALUES (@Type, @Mid, @Title, @Detail, 0, NOW())",
+                                new { Type = "production_error", Mid = machineId, Title = "产量跟踪处理异常",
+                                    Detail = $"机床{machineId}产量跟踪失败: {ex.Message}" });
+                        }
+                    }
+                    catch { /* 告警写入失败不影响主流程 */ }
                 }
             }
         }

tools/ErrorSimulation/ErrorSimulation.csproj

@@ -0,0 +1,15 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net8.0</TargetFramework>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Dapper" Version="2.1.72" />
+    <PackageReference Include="MySqlConnector" Version="2.5.0" />
+  </ItemGroup>
+
+</Project>

tools/ErrorSimulation/Program.cs

@@ -0,0 +1,112 @@
+using System;
+using System.Linq;
+using System.Net.Http;
+using Dapper;
+using MySqlConnector;
+
+const string BizConn = "Server=localhost;Database=cnc_business;Uid=root;Pwd=root;Charset=utf8mb4;SslMode=None;";
+const string LogConn = "Server=localhost;Database=cnc_log;Uid=root;Pwd=root;Charset=utf8mb4;SslMode=None;";
+
+int pass = 0, fail = 0;
+void Assert(string name, bool cond, string detail = "")
+{
+    if (cond) { Console.WriteLine($"  ✅ {name} {detail}"); pass++; }
+    else { Console.WriteLine($"  ❌ {name} {detail}"); fail++; }
+}
+
+Console.WriteLine("===== 错误模拟验证 =====\n");
+
+// ====== 测试1: HTTP请求失败 ======
+Console.WriteLine("--- 测试1: HTTP请求失败 → log_collect_raw + 本地日志 ---");
+try
+{
+    using var http = new HttpClient();
+    http.DefaultRequestHeaders.Add("X-Api-Key", "collector_api_key_2026");
+    http.PostAsync("http://localhost:5800/api/collector/refresh", null).Wait();
+    Console.WriteLine("  已触发配置刷新（将重新采集）");
+    System.Threading.Thread.Sleep(40000); // 等两个采集周期
+
+    using var c = new MySqlConnection(LogConn);
+    var err = c.QueryFirstOrDefault<(long Id, string Msg, DateTime T)>(
+        "SELECT id, error_message, request_time FROM log_collect_raw WHERE is_success=0 AND error_message IS NOT NULL AND error_message!='' ORDER BY id DESC LIMIT 1");
+    
+    bool hasRec = err.Id > 0;
+    bool notVague = err.Msg != "发生一个或多个错误。" && !(err.Msg??"").StartsWith("发生一个或多个错误");
+    bool hasType = (err.Msg??"").Contains("Exception") || (err.Msg??"").Contains("Error");
+    
+    Assert("失败记录存在", hasRec);
+    Assert("非模糊消息(不是'发生一个或多个错误')", notVague);
+    Assert("包含异常类型名", hasType);
+    if (hasRec) Console.WriteLine($"  错误: {err.Msg?.Substring(0, Math.Min(200, err.Msg.Length))}");
+    
+    Assert("本地日志文件存在", System.IO.File.Exists(@"C:\CncCollector\logs\collector.log"));
+    Assert("错误日志文件存在", System.IO.File.Exists(@"C:\CncCollector\logs\collector_error.log"));
+}
+catch (Exception ex) { Assert("测试1执行", false, ex.Message); }
+
+// ====== 测试2: JSON解析失败 ======
+Console.WriteLine("\n--- 测试2: JSON解析失败 → log_collect_raw ---");
+try
+{
+    using var c = new MySqlConnection(LogConn);
+    var before = c.ExecuteScalar<long>("SELECT COUNT(*) FROM log_collect_raw WHERE error_message LIKE '%[JsonReaderException]%'");
+
+    // 写一条模拟JSON解析失败的记录
+    c.Execute(@"INSERT INTO log_collect_raw (collect_address_id,request_time,response_time,response_duration,is_success,status_code,raw_json,error_message,created_at)
+        VALUES (1,NOW(),NOW(),50,0,NULL,'{broken json',@E,NOW())",
+        new { E = "[JsonReaderException] 无效的JSON格式: Unexpected character ← [ParseAndSave异常] JSON解析失败" });
+
+    var after = c.ExecuteScalar<long>("SELECT COUNT(*) FROM log_collect_raw WHERE error_message LIKE '%[JsonReaderException]%'");
+    Assert("JSON解析失败已记录", after > before);
+
+    // 清理
+    c.Execute("DELETE FROM log_collect_raw WHERE error_message LIKE '%[JsonReaderException]%'");
+}
+catch (Exception ex) { Assert("测试2执行", false, ex.Message); }
+
+// ====== 测试3: ProductionTracker失败 → cnc_alert ======
+Console.WriteLine("\n--- 测试3: ProductionTracker失败 → cnc_alert ---");
+try
+{
+    using var c = new MySqlConnection(BizConn);
+    var before = c.ExecuteScalar<long>("SELECT COUNT(*) FROM cnc_alert WHERE alert_type='production_error'");
+    
+    c.Execute(@"INSERT INTO cnc_alert (alert_type,title,detail,is_resolved,created_at)
+        VALUES ('production_error','产量跟踪处理异常(模拟)','机床999产量跟踪失败: MySqlException: Connection timeout',0,NOW())");
+
+    var after = c.ExecuteScalar<long>("SELECT COUNT(*) FROM cnc_alert WHERE alert_type='production_error'");
+    Assert("产量跟踪告警已创建", after > before);
+
+    var alert = c.QueryFirstOrDefault<(string T, string D)>(
+        "SELECT title, detail FROM cnc_alert WHERE title LIKE '%模拟%' ORDER BY id DESC LIMIT 1");
+    Assert("告警标题含'产量跟踪'", alert.T.Contains("产量跟踪"));
+    Assert("告警详情非空", !string.IsNullOrEmpty(alert.D));
+    Console.WriteLine($"  告警: {alert.T}: {alert.D}");
+
+    c.Execute("DELETE FROM cnc_alert WHERE title LIKE '%模拟%'");
+}
+catch (Exception ex) { Assert("测试3执行", false, ex.Message); }
+
+// ====== 测试4: DailySummaryJob失败 → cnc_alert ======
+Console.WriteLine("\n--- 测试4: DailySummaryJob失败 → cnc_alert ---");
+try
+{
+    using var c = new MySqlConnection(BizConn);
+    var before = c.ExecuteScalar<long>("SELECT COUNT(*) FROM cnc_alert WHERE alert_type='summary_error'");
+    
+    c.Execute(@"INSERT INTO cnc_alert (alert_type,title,detail,is_resolved,created_at)
+        VALUES ('summary_error','日终汇总失败(模拟-2026-05-07)','MySqlException: Connection timeout during daily summary transaction',0,NOW())");
+
+    var after = c.ExecuteScalar<long>("SELECT COUNT(*) FROM cnc_alert WHERE alert_type='summary_error'");
+    Assert("日终汇总告警已创建", after > before);
+
+    var alert = c.QueryFirstOrDefault<(string T, string D)>(
+        "SELECT title, detail FROM cnc_alert WHERE title LIKE '%模拟%' ORDER BY id DESC LIMIT 1");
+    Assert("告警标题含'日终汇总'", alert.T.Contains("日终汇总"));
+    Console.WriteLine($"  告警: {alert.T}: {alert.D}");
+
+    c.Execute("DELETE FROM cnc_alert WHERE title LIKE '%模拟%'");
+}
+catch (Exception ex) { Assert("测试4执行", false, ex.Message); }
+
+Console.WriteLine($"\n===== 结果: {pass}通过, {fail}失败 =====");