From 903c30dfec5412713bcd4a0bf65cf5f9ac71ff68 Mon Sep 17 00:00:00 2001 From: m3ultra Date: Tue, 21 Jul 2026 23:00:46 +1000 Subject: [PATCH] Sort-session handoff: 167-clip archive triage plan Co-Authored-By: Claude Fable 5 --- production/SORT_SESSION.md | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 production/SORT_SESSION.md diff --git a/production/SORT_SESSION.md b/production/SORT_SESSION.md new file mode 100644 index 0000000..fe413ba --- /dev/null +++ b/production/SORT_SESSION.md @@ -0,0 +1,20 @@ +# NEXT SESSION: the big sort — 167 harvested clips → full game +State: flow-vids-RSG/flowvid_001..193.mp4 (167 after exact-dedupe) = the ENTIRE +Flow project video archive, harvested via tools/flow_console_harvest.js at 720p. +Sample review (11 spread samples) showed ~100% on-model keep-rate across all +worlds: sea/lava/space/grid/runout/store/altar all present, Dead Wax moves +correctly, two-shots hold. + +Job (fresh context, heavy image review — consider a Workflow fan-out): +1. Frame-rip all 167 into labeled contact sheets (4 frames each, batches of ~14). +2. Classify each: shot id from DESIGN.md/scenes.json (sets are visually + unmistakable; grid order ≈ newest-first so reverse task-serve order in + /tmp/flowrinse.log + results.jsonl helps disambiguate takes). +3. Pick best take per slot (criteria: on-model Dez, action reads, holdable + ending for deaths); normalize (1280x720/24fps/crf20/aac/faststart) into + engine/clips/.mp4 per scenes.json names. +4. Requeue only true gaps (no footage found): strip their failed lines from + results.jsonl. NEVER requeue ids that have footage (double-spend). +5. Bot-playtest full graph, tune windows in ?debug=1, commit, push. +Also pending: Quality-tier finale shots (t7/win/stinger/postage) may not be +generated yet — check results.jsonl; they're the 14 Quality tasks at queue end.