Long-form media: one playbook, measured levers, quality-first defaults for pieces longer than one clip #1199

Make long pieces easy for an agent and good by default: chained takes, cut scenes, long music and narration. An agent asked for a minute, five minutes, an episode or a music video treats the 15-second clip as a render detail. It blocks and storyboards the piece, picks a length per scene, picks how each scene gets past the clip ceiling, and handles what goes wrong during the run, without the requester knowing what a seam, a guide or an anchor is.

• Design (approved by Don 2026-11-03): docs/proposals/long-form-media.md
• Plan (approved by Don 2026-11-03): docs/superpowers/plans/2026-11-03-long-form-media.md
• Branch: feat/long-form-media. It merges to develop after the 0.19.0 release PR Release 0.19.0 #1198.

How this is being worked

Don's own session builds, deploys and bench-tests this, with subagents. It does not go through the harnest implementer. The work runs on a second bench dw.serve on lem (port 8766, its own card and workspace), so the main server stays on develop for the tester and the 0.19.0 preflight. No loop role should act on this issue or the ideas parked under it until the hand-off comment arrives. At hand-off, this issue moves to owner:tester, with one stage issue per shipped behaviour carrying the acceptance intent the tester writes cases from.

Ideas folded in

Every one of these gets a measured verdict on the shared long-take bench. Each is either built or promoted to a default, or closed with its numbers:

• New: idea: H3 chain anchors from segment 1 as sequence rows - keystone keyframe and a late-locked capstone past the tail (revives #1166 arm 4) #1187, idea: H3 one long render in overlapping windows (hybrid windows) - no chain, one soundtrack, segment-1 keystone and capstone in every window #1188, idea: H3 guide chain - hand over from one block before the previous segment's end and drop its last 17 frames #1189, H3 latent anchor: latent_anchor_strength, a partial statistics match (#1166 Q5 follow-up) #1190, idea: pixel-domain drift set for last_frame chains - grade at the pickup, creep and texture ease-out, pre-compensated handoff frame #1191, idea: H3 audio-only pass over a finished picture - video rows held, audio generated, half-size listen #1192, docs: minimax-h3 skill - claims from MiniMax-H3-LongVideos to probe (acted-out lines, unmentioned pictures, face crops, portraits on continued shots, hum lines) #1193, idea: replace a performer in an existing clip - cuts, person tracks, per-cut masked Ref2VA edit with a portrait, rejoin with the source audio (Second Take) #1194, idea: SelfLift resolution transition for H3 - first steps at half canvas, lift, finish at full size inside one schedule (no extra NFEs) #1195, idea: TST temporal-attention correction for H3 flicker and identity drift (per-head spectral-tension patch, ~1-2% runtime) #1196, idea: export_timeline task - an OpenTimelineIO .otioz of a joined piece's shots for DaVinci Resolve #1197
• Parked chain family: idea: decode a segment chain once - carry latents between segments, decode the take a single time #1030, idea: last_frame continuity carries the sharpest of the last N frames #1032, idea: colour-match the start of each chained segment to its carried frames #1033, idea: H3 chain seams - carry the overlap as latents and crossfade it, A/B against guide + trim #1044, idea: colour-match a generated region to the source where they overlap (reframe, chain seams) #1067, idea: H3 chain continuity from the previous segment's latent tail under a denoise mask (no pixel re-encode) #1150, idea: repair a bad H3 chain segment in place - re-render it with head and tail locked to its neighbours #1169
• Also scored: FastH3 Omni 8-step BF16 checkpoint as the Ref2VA transformer: investigate and onboard #980 (FastH3 Omni) and the anti-burn LoRA trial from idea: H3 Anti-Burn LoRA on chain continuation segments only #1151

Decided by Don

• Defaults favour quality, with a dial toward speed. standard sits at the knee of the quality-per-minute curve. A 2-minute take over about 3 h on one card goes back to Don first.
• Speedups with no marked quality loss become defaults.
• Automatic per-segment re-rolls are allowed within a budget quoted up front.
• Every knob stays.
• Kandinsky 6 is out of scope.
• Taste calls go to Don with a recommendation.

Filed by claude-opus-5-5 (anthropic) in Don's session, 2026-11-03.