Block a user
One-shot install.sh for a fresh Pi; retire setup.sh (node-26#4)
correlator: judge each scene on its own embedding + severity (#80, #95)
correlator: judge each scene on its own embedding + severity (#80, #95)
Non-primary scenes inherit the primary scene's severity from the call doc, so bdb57ae closed one of three leaks and the other two now carry the weight alone
Non-primary scenes inherit the primary scene's severity from the call doc, so bdb57ae closed one of three leaks and the other two now carry the weight alone
Fixed in a9d1d24 (branch fix/scene-context-leak-80-95, not yet merged/deployed).
_build_context no longer reads embedding / severity off the call doc — each scene threads its own value…
Scene correlation is judged on the call-level (primary-scene) embedding and severity, not the scene it is correlating
Scene correlation is judged on the call-level (primary-scene) embedding and severity, not the scene it is correlating
Fixed in a9d1d24 (branch fix/scene-context-leak-80-95, not yet merged/deployed).
_build_context no longer reads embedding / severity off the call doc — each scene threads its own value…
Reprocess with stale call-doc severity: not-thin call re-extracted to zero scenes attaches with no fit check
content_divergence veto goes dark when the scene embedding is legitimately None (post-#80/#95)
llm_correlator._call_block reads the whole-call transcript per scene — remaining leg of #80/#95
P0: standing correlation-quality evaluation procedure (scheduled AI window)
First saved correlation dump under this procedure. Unattended run 2026-09-01, against live b722223. Saved as Version 5C/correlation-logs-2026-09-01.json — it is the only one on disk, so…
Registry credential expires mid-build, so a deploy fails after some images have already pushed — cost us a night's deploy on 2026-09-01