Preserve Second Pass audio and scoped Review conditioning, strengthen Take compatibility, and align Review Driving Audio.
Keep v5 history readable, document v6 restart requirements, and describe the fixes at the top of both READMEs. Remove workstation-specific paths and private operational records from public documentation.
Preserve V3.8/V3.9 external dimension links across workflow restore, disable linked facade editing and keep saved Manual reserve values. Document Manual versus First Image authority in both READMEs; add frontend/CPU regressions without changing backend schemas, Sampling, Run Storage or earlier Review/cache repairs.
Validation: 1569 CPU passed, 1 skipped; 22/22 new frontend and 60/60 Review cases; Chrome save/reload and five tab round trips. One V3.9 GPU smoke generation produced exactly 480x640, 96 frames at 24fps and 4-second audio in 107.3s. This is a single short resolution check, not long-form acceptance. Official workflows/ZIPs, package version and historical Releases unchanged.
Reuse the existing bounded prompt-conditioning cache only for safe reference-free Fixed groups. Preserve Reference, List/Timeline, terminal-pair, Sampling and Run Storage paths; add 22 regression cases and bilingual update guidance.
Local validation: 1558 CPU passed, 1 skipped; eight successful GPU generations. Post-fix same-session warm total medians: V3.8 273.579s vs V3.9 273.779s, with overlapping ranges. This scoped result is not a universal speed or GPU-kernel claim. Official workflows/ZIPs and historical Releases are unchanged.
Wait for graph rehydration before history loading and reject stale graph/node results. Preserve real-edit safety guards and saved Take selection.
Add lifecycle regressions and bilingual update guidance. Validated with 60 frontend cases, 108 focused CPU tests, five Chrome tab round trips and a Base Seed edit/restore check. GPU continuation was not tested.
Publish the supplied ZIP unchanged alongside existing prompt resources.
Add English and Japanese README links for all three prompt/skill packages.
No runtime or workflow changes.
Publish separate v1 archives with prompt routing, continuity, audio reference
and append guidance. Archive extraction/hash checks and skill validation passed.
No runtime, workflow or README changes. LLM output quality is not evaluated.