Atharv Chandratre, Jai Datar · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.31351 · cited by 0 works (OpenAlex) · open-access PDF
在DoorDash,超过56,000个功能旗覆盖了623个存储库,截至2026年5月,1659个功能目前处于停滞状态,每一个手动清洁的内部估计为1到2小时。现有的基于规则的清洁工具在DoorDash的代码库中被证明是不够的。我们的贡献是基于LLM的自动化端到端旗清洁系统,该系统结合了使用MCP、Jira票价流程和端到端清洁请求的内部估计。我们的系统成功地生产了类似的工程师批准的旗帜清除成本(90%)为50个旗板上的50个自动旗帜清洁系统,当它测试了可操作性时,我们根据每台计量系统的运行率和平均清洁度为每8分钟进行评估。
Machine translation (Meta M2M100); the English original follows.
Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and its gated code become technical debt and can introduce operational risk through inadvertently enabling dormant code paths. At DoorDash, over 56,000 feature flags span 623 repositories, with 1,659 currently stale as of May 2026, with internal estimates of one to two hours per manual cleanup. Existing rule-based cleanup tools proved insufficient in DoorDash's codebases. Our contribution is an end-to-end automated LLM-based feature flag cleanup system that integrates querying live feature flag rollout data using MCP, Jira ticket processing, and end-to-end pull request creation. Our system successfully produced engineer-approved flag removal PRs for 45 (90%) of the 50 stale flags it was evaluated on, proving the system's operational viability at scale with each cleanup averaging only $4.79 and 13.8 minutes. We evaluated the system's quality and reliability boundary based on success rates, cost per cleanup and time metrics. Furthermore, we discuss our lessons learned when architecting this system, to provide practical guidance for developing similar multi-agent systems.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Flag (linear algebra), FLAGS register, Feature (linguistics), Computer science, Scale (ratio), Reliability (semiconductor)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31351, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange