Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

fix: a whole-reference question sees every frame, not one per shot

rpone435feacbca25
diff --git a/.agents/skills/hypit/references/reconstruction/observers.md b/.agents/skills/hypit/references/reconstruction/observers.md
index c5f04809..c1066e7b 100644
--- a/.agents/skills/hypit/references/reconstruction/observers.md
+++ b/.agents/skills/hypit/references/reconstruction/observers.md
@@ -39,11 +39,15 @@ This is the one question this route asks about how it runs. Everything else it d
## What the `agent` observer reads
Each shot arrives as one picture: its frames sampled evenly across its duration and tiled in reading
-order, left to right then top to bottom. Read the grid as time passing. The whole reference arrives as
-the storyboard of representative frames. A task that carries a single picture carries one moment.
-
-The number of frames follows the shot's length, from four for a short one to nine for a long one, so
-a cell stays wide enough to read detail in.
+order, left to right then top to bottom. Read the grid as time passing. A task that carries a single
+picture carries one moment. The number of frames follows the shot's length, from four for a short one
+to nine for a long one, so a cell stays wide enough to read detail in.
+
+A whole-reference task carries the storyboard — every shot's representative frame in one picture, for
+reading the video at a glance — followed by every shot's tile, so the question sees every frame the
+shot observations see. On a long reference that is a lot of pictures, and it is the whole evidence:
+answer from all of them rather than from the storyboard alone, which shows one moment per shot and
+therefore answers neither what moves nor what recurs.
## How sound is answered on the `agent` observer
diff --git a/packages/reference-video-tools/src/tools.ts b/packages/reference-video-tools/src/tools.ts
index 12d5ade4..c24b17ef 100644
--- a/packages/reference-video-tools/src/tools.ts
+++ b/packages/reference-video-tools/src/tools.ts
@@ -179,7 +179,11 @@ function asPictures(media: readonly string[], state: ReferenceState): readonly s
for (const path of media) {
const tile = tiles.get(path);
if (tile !== undefined) pictures.push(tile);
- else if (path === state.analysis_video_ref) pictures.push(state.storyboard_ref);
+ // A whole-reference question is asked over the whole reference. The storyboard puts every shot in
+ // one picture and is how the video is read at a glance, but one frame per shot answers neither
+ // what moves nor what recurs, so the shot tiles come with it and the question sees every frame
+ // the shot observations see.
+ else if (path === state.analysis_video_ref) pictures.push(state.storyboard_ref, ...state.shots.map((shot) => shot.frames_tile_ref));
else if (!path.toLowerCase().endsWith(".wav")) pictures.push(path);
}
return [...new Set(pictures)];