Atharv Chandratre, Jai Datar · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.31351 · cited by 0 works (OpenAlex) · open-access PDF
As bandeiras de segurança são mecanismos de configuração de tempo de execução usados para o lançamento gradual dos recursos, a experimentação e as interrupções de morte. Uma vez que um recurso é totalmente lançado, a bandeira e seu código de porta se tornam uma dívida técnica e podem introduzir riscos operacionais através de possibilitar inadvertidamente caminhos de código dormente. Na DoorDash, mais de 56.000 bandeiras de características abrangem 623 repositórios, com 1.659 atualmente estagnados a partir de maio de 2026, com estimativas internas de uma a duas horas por limpeza manual. As ferramentas de limpeza baseadas em regras existentes provaram ser insuficientes nas bases de código da DoorDash. Nossa contribuição é um sistema de limpeza automatizada de bandeiras baseado em LLM que integra dados de rolagem de
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