kami
54c456801a
Panels, wavs, layers, clips, and the chapter mp4 leave the `manga` bucket for `panels`, `audio`, `layers`, and `video`. The key under the bucket is unchanged, so every reader that derives the bucket from the first path segment keeps working. The orchestrator half moves in the same commit, per invariant 7. The 2026-08-11 chapter run proves the split for `raw` and `panels` and produced the first quality read on speaker attribution, which is wrong in every sampled multi-character panel. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XD7cAy81MZrc7gCr6aZGWr