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.
TypeScript agentic-aiaiai-agentsai-videocompilerdslffmpeggenerative-aillmmarkup-languagemonorepoplugin-systemprogramming-languagetext-to-videotypescriptvideovideo-automationvideo-clonevideo-editingvideo-generation
fix(hypit): close the gaps between the render scripts and the route
rpone77cdbf695b3c
diff --git a/.agents/skills/hypit/references/preview.md b/.agents/skills/hypit/references/preview.mdindex 827c76f4..9cf86984 100644--- a/.agents/skills/hypit/references/preview.md+++ b/.agents/skills/hypit/references/preview.md@@ -66,7 +66,24 @@ collide — lines that overlap, type too large for the plate it sits on — whildrawn from different values, stays perfect. A route that compares the catalogue picture is answeringa question about the catalogue.-The comparison render has one command, shared by every package:+Each has its own command, and both are shared by every package.++**The catalogue preview** is drawn from a Source the package ships — `preview/preview.svml`,+`preview/recipes.svs` and `preview/build.svrun`, holding its own copy, its own Recipe values and its+own Canvas:++```bash+node --import tsx .agents/skills/hypit/scripts/render-previews.mjs packages/<name>+```++Which element draws which file comes from the Manifest's naming: a Surface tagged `Track` declares+`preview/Track.png`, so that picture is drawn from the element carrying that tag under the package's+own import alias. It **overwrites the picture in place**, so run it when the package's drawing has+changed and look at what came out before committing it. Anything the preview Run satisfies with a+`<file>` of its own is carried through and never mocked over, which is how a preview shows the+component holding a picture rather than a placeholder.++**The comparison render** has one command too:```bashnode --import tsx .agents/skills/hypit/scripts/render-element.mjs projects/<name>/build.svrun \diff --git a/.agents/skills/hypit/references/reconstruction/reconstruction-loop.md b/.agents/skills/hypit/references/reconstruction/reconstruction-loop.mdindex 5b4403d6..c8254d4c 100644--- a/.agents/skills/hypit/references/reconstruction/reconstruction-loop.md+++ b/.agents/skills/hypit/references/reconstruction/reconstruction-loop.md@@ -45,11 +45,11 @@ card.The thing compared is the element **as this video places it**: the Recipe values the Source actuallypasses, the Script text the Source actually feeds it, and the windows the Source actually binds. A-package's catalogue preview is a different picture with different inputs — the harness supplies its-own sample copy and its own Recipe so a reader can see the Surface's range — and a Source can fill+package's catalogue preview is a different picture drawn from different values — the package's own+sample copy and sample Recipe, chosen to show a reader the Surface's range — and a Source can fillevery one of those parameters with values that collide while the preview stays perfect. Comparing the-preview answers a question nobody asked. `../preview.md` renders both, from the same harness, with-different arguments; this loop uses the Source-configured one.+preview answers a question nobody asked. `../preview.md` keeps the two apart and says which command+draws which.One command produces it, and it is not written per package:@@ -63,9 +63,17 @@ speech with the Source's own `estimate:Speech`, mocks every layer a Build has nothe package's Producer. Nothing is transcribed by hand, so nothing is transcribed one line at a time— which is what made a caption system look correct while its lines collided.-The window is named in words. `--segment` and `--selection` take a Script name, not a timestamp: a-shot of the reference is found by the words spoken over it, and those words are where the Script-says they are. No reference clock is read across.+The window is named in words. `--segment` and `--selection` take a Script name, never a timestamp,+and the way to find the right name for a given shot is:++1. take the shot's `start_seconds` and `end_seconds` from the reference's `state.json`;+2. read the words spoken over that stretch out of the reference's `transcript.json`, which carries+ one entry per word with its own timings;+3. find those words in the Script you wrote, and name the Selection or Segment that encloses them.++The reference clock is read exactly once, at step 1, and only to index a table. Everything after it+is words. The reconstruction's own frames come from estimated take lengths, so its clock and the+reference's do not correspond and matching them would put the window in the wrong place.### Mock the layers a Build has not madediff --git a/.agents/skills/hypit/scripts/render-element.mjs b/.agents/skills/hypit/scripts/render-element.mjsindex 946d4371..d1512b29 100644--- a/.agents/skills/hypit/scripts/render-element.mjs+++ b/.agents/skills/hypit/scripts/render-element.mjs@@ -91,7 +91,10 @@ const out = flag("out") ?? fail("--out is required");const invokedFrom = process.env.INIT_CWD ?? process.cwd();const runPath = resolve(invokedFrom, runArgument);-const packageRoot = resolve(invokedFrom);+// The repository, found from this file rather than from wherever it was called. Deriving it from the+// working directory means the command works from the root and crashes anywhere else, on a missing+// module rather than on anything a reader could act on.+const packageRoot = fileURLToPath(new URL("../../../../", import.meta.url));const projectRoot = dirname(runPath);const outPath = resolve(invokedFrom, out);