mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-11 21:57:14 +03:00
Paul BakausandClaude Opus 5
ec189f4536
Two defects in the same few lines, both from `enterComp` hand-building a media slot after the deal instead of reaching the shape a comp-first render serves. A code-led card carrying catalog art shows that art as its face. Flipping to comp inserted a fresh shimmer slot above the body and left the face alone, so the card rendered the inspiration full-bleed with the rendering comp stacked under it: two images of equal weight, which is the one thing the corner treatment exists to prevent. The flip now converts that slot in place, moving the art into the `figure.pip` and dropping the face label, and flipping back restores it, so a round-trip leaves the card as it was dealt. The slot it built also carried no chips, and the zoom handlers were bound per element at load, so a comp that streamed in after a flip could not be opened at all: no expand affordance, and no click handler on the art. The three lightbox handlers are now delegated, which is what makes any later-built slot work, and a converted slot keeps the chips it already had. Polling learned to stop on a slot that stays in the DOM but loses its pending state, which only happens now that a flip back can restore rather than remove. The existing toggle test covered a wireframe card, where the schematic is hidden and a fresh slot inserted; that branch was fine, which is why this went unseen. The new test drives the art-carrying card and fails on the stacking assertion without this change. Written with AI assistance (Claude Code). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>