Bayesian Two-Stage Design with Window-Cohort and Controlled Roll-on for Time-to-Event Estimand R package WCRBayesDesign version 1.0.1 Calibrates Bayesian two-stage designs for single-arm phase II trials with time-to-event endpoints using a window-cohort with controlled roll-on. Interim monitoring is anchored to a locked interim cohort and a pre-specified follow-up requirement, so analysis timing remains predictable while preserving follow-up maturity. The package searches feasible interim rules, optimizes final sample size and decision thresholds, evaluates operating characteristics by Monte Carlo simulation, and supports exponential, Weibull, log-normal, log-logistic, and user-defined baseline survival models. Related published foundations include Simon (1989) <doi:10.1016/0197-2456(89)90015-9> and Cotterill and Whitehead (2015) <doi:10.1002/sim.6426>. Software Depends: R (>= 4.4.0) Imports: foreach, doParallel, stats, parallel Suggests: devtools, roxygen2, knitr, rmarkdown, testthat (>= 3.0.0) Zhongheng Cai <zhonghengcai123@gmail.com> Comprehensive R Archive Network (CRAN) Zhongheng Cai [aut, cre], Haitao Pan [aut] GPL-3 2026-04-10 application/tgz https://CRAN.R-project.org/package=WCRBayesDesign doi:10.32614/CRAN.package.WCRBayesDesign