Predicting the growing season of temperate zone trees under climate change requires factoring in developmental constraints that determine tree resource allocation. Recent work has identified the summer solstice (21 June) as a phenological \"switch point,\" with pre-solstice warming advancing autumn bud set and post-solstice warming delaying it. However, the flexibility of this switch point remains poorly understood. We performed trans-solstice climate manipulation experiments on potted European beech (Fagus sylvatica) saplings to test (i) how spring leaf-out timing and June-August temperatures influence growth cessation (bud set), and (ii) whether daytime and nighttime temperatures before and after the solstice have different effects, given that trees primarily grow at night. Each day delay in spring leaf-out delayed bud set by 0.24 {+/-} 0.06 days on average. July cooling delayed bud set by 4.9 {+/-} 2.6 days in late-leafing individuals but had no effect in early-leafing ones. Conversely, August cooling advanced bud set by 4.4-4.5 {+/-} 2.6 days in all trees. Daytime cooling before the solstice had no effect, while after the solstice it advanced bud set. Nighttime cooling always delayed bud set. Our findings support the Solstice-as-Phenology-Switch model and highlight the central role of developmental progression in constraining the growing seasons of temperate trees. Faster early-season development-especially under nighttime warming-advances the point at which trees become sensitive to late-season cooling, thereby triggering senescence earlier. To improve growing season length projections, phenological models must account for these developmentally-mediated and diel-specific responses to warming.