摘要：传统数据管道因脆弱性而众所周知，经常由于上游模式漂移（schema drift）、API 契约变更或网站 DOM 结构修改而崩溃。目前的可观测性工具仅能向人类工程师发送告警，导致平均修复时间（MTTR）居高不下并带来严重的运维疲劳。在本文中，我们提出了 AegisFlow（面向工作负载修复的智能自愈与图驱动操作 Agent 引擎，Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation），这是一个新型 Agent 框架，闭合了从故障检测到问题解决的闭环流程。AegisFlow 利用 Watchdog Agent 收集运行时遥测数据，并引入基于大语言模型（LLM）的 Repair Agent 自动创建、测试和部署代码补丁。该框架提出了一种名为“并行影子补丁（Parallel Shadow Patching）”的非侵入式执行模型，基于“监控、分析、规划、执行、知识”（MAPE-K）循环在数字孪生环境中生成并验证补丁。通过实验测试，我们在五种常见故障场景下评估了 AegisFlow，观察到 MTTR 提升了 98.1%（每个补丁的平均修复时间从 170 分钟大幅降至 3.2 分钟），补丁成功率达 92%。特别是在应对 JSON 模式变更（96%）和标点/格式漂移（98%）方面，系统表现尤为出色，而在 Shadow DOM 场景下的成功率相对较低（85%）。AegisFlow 释放了数据工程团队约 98% 用于“救火”排障的 On-call 时间，使其能够重新专注于技术创新。该框架与部署环境无关，支持以插件方式接入现有的管道编排系统，对现有系统的改造要求极低。

Abstract:Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise alerts but for human engineers, resulting in a high Mean Time to Repair (MTTR) and operational fatigue. In this paper we propose AegisFlow (Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation), a novel agentic framework that closes the loop between detection and resolution. AegisFlow uses a Watchdog agent to collect runtime telemetry and has a Repair agent to automatically create, test and deploy code patches based on Large Language Models (LLMs). The framework presents the non-intrusive execution model called Parallel Shadow Patching, a non-intrusive execution model based on the Monitor, Analyze, Plan, Execute, Knowledge (MAPE-K) loop to generate and verify patches in digital twin environments. Through experimental testing, we have evaluated AegisFlow across five common failure scenarios, and see 98.1 percent improvement in MTTR (from an average of 170 minutes per patch to 3.2 minutes) and a patch success rate of 92 percent . In particular, the system is successful in dealing with changes in the JSON schema (96 percent ) and punctuation drift (98 percent ), and is least successful in Shadow DOM cases (85 percent ). AegisFlow frees up about 98 percent of data engineering on-call time from firefighting and reallocates it towards innovation. The framework is deployment agnostic consisting of a system that can be deployed in a plugin fashion into an existing pipeline orchestration system with minimal uplift to the existing system.