@vosjs/cli 0.23.0 → 0.25.0

package/README.md

@@ -89,6 +89,8 @@ vos plan take --reuse                                   # re-time that cut onto
 
 **Digest first.** `vos digest <take>` is how an agent sees a recording without reading the video. It writes `digest/digest.json`: one moment per thing the cursor track says mattered (click clusters, typing sessions, scroll runs, dwells, idle gaps, head, tail, and frame-diff scene changes), each with source and output extents, a normalized `focus` and `rect` you can copy into a zoom span, per-second `activity`, and the planners' `proposed` span ids; plus one footage frame and a crop around the target per moment, and `sheet.png`, the contact sheet. Read the JSON, then the sheet, then a crop only where you must decide. `vos validate` then warns when a zoom does not contain what was clicked under it, and `vos frames --at-moments` renders the composed output at every moment so a still and its footage crop share an id.
 
+**Many media in one take (concat).** `doc.json` may carry `media: [{ id, videoKey, cursor, meta, … }]`, the take's OTHER recordings or uploads, each the `source` shape with an `id`; a segment on one (`{ in, out, media: "m1" }`) plays it, and a zoom, tilt, speed, freeze or cam-move span names the media its source seconds belong to (absent = the primary, `source`). The Video row shows the clips in order, a span is drawn where its media plays, `vos plan` proposes zoom and speed spans on every media from its own cursor track, `vos validate` measures each span against its own media's length, and `vos push` and `vos pull --media` carry every media through the recording door. A media wears its OWN card: `media[].frame` carries the card-owned fields (its placement and size as `inset`, the browser bar, the corner, the shadow, the border, the cover fit and its focus) over the take's frame while it plays; the bar names that media's recorded page, an upload with no page wears none, and the frame-wide fields (the aspect, the padding, the ground, the backdrop, the card's animation) stay the take's. Sound: the primary's tracks play at the primary's moments; another media's own audio is not spliced into the cut yet.
+
 **A series shares its look by data.** `vos plan <take> --style <seed doc.json | vosId>` copies the seed's `zoomStyle`, `zoomParams`, `speedParams`, `tiltStyle`, `frame`, `cursor`, `cam` and `export` onto a new take (never its spans, overlays or audio) and re-plans the automatic spans under them. A seed that is a POSTER carries its layout too: its card placement, its `stage-*` clips by id (with the release's words from LAUNCH.md's `headline` and `kicker` roles, BRAND.md's `wordmark`, or `--headline` and `--kicker` patched in; the brand's mark from BRAND.md `logoUrl` fetched into `<take>/brand/` for `stage-mark`), its rest lean, its trailing freeze. What could not follow is said in words.
 
 **The cut's motion is the document's, in one vocabulary.** Every visual thing carries `anim` (`enter`, `exit`, `idle`; a kind, or a step with its seconds and, for words, `unit`, `direction`, `stagger`): the card (`frame.anim`, entering by `tilt-in`, `pull-out`, `rise` or `fade` and leaving by `recede` or `fade`), a text, image or video clip, a prop. The output lasts until the last clip ends; the card is on screen exactly while its clip runs (the footage, freezes included) and leaves at its end, so its `exit` plays over the clip's last seconds like every clip's; past the footage the clips play over the ground alone. A FREEZE (`freeze: [{id, at, seconds}]`, a source moment held for output seconds, beside the speed spans on the retime lane) freezes the footage anywhere, the middle of the take included; a segment's older `hold` is read as a freeze at its end. There is no end-card field and no entrance field. A COMPONENT is a TEMPLATE: a plain take on a shelf whose clips carry stable ids, laid onto a take at an anchor and stamped `from` with where its clips came from. A fresh `vos plan` proposes the card's enter, the templates the recipe names (`LAUNCH.md` `with: <ref>[@end|@start|@step:<id>|@<seconds>], …` or `--with`, repeatable; `endCard: <ref>` names one at the end), the END CARD when `endCard` is on or absent: the official `End card` template on vos.so (the platform's `Templates` project, promoted; any official template resolves by its title, `--with "End card"`, `--style "Split cover, landscape"`), laid at the end with the release's words and BRAND.md's mark, stamped `from: endcard`; offline, the house clips stand in (a freeze of the last frame for the card's seconds, the card receding over it, the headline, the release line, the wordmark and the mark as clips over the freeze), a caption per `actions.json` step, a music bed and click sounds, from LAUNCH.md's `entrance`, `endCard`, `with`, `captions`, `music` and `clicks` roles (or the flags), as data in doc.json with stable ids (`bed`, `click-<n>`, `caption-<step>`), so the studio shows what the kit will render; a refresh never re-proposes (a deleted clip stays deleted) and `--motion` re-proposes on purpose, replacing only its own work. A document written in the older spellings (`frame.entrance`, `endCard`, a clip's `enter`/`exit`/`fx`, a prop's `animation`) is read into the vocabulary and `vos validate` says so.

package/dist/{chunk-SLCQCRNI.js → chunk-TYTUA5L5.js}

@@ -186,16 +186,17 @@ import {
   CAM_SPAN_MIN,
   CARD_ENTER_KINDS,
   CARD_EXIT_KINDS,
-  IDLE_KINDS,
-  MEDIA_ENTER_KINDS,
-  MEDIA_EXIT_KINDS,
-  TEXT_ENTER_KINDS,
-  TEXT_EXIT_KINDS,
   EXPORT_RESOLUTION_OPTIONS,
   FREEZE_SECONDS_MAX,
   FREEZE_SECONDS_MIN,
+  IDLE_KINDS,
+  MEDIA_ENTER_KINDS,
+  MEDIA_EXIT_KINDS,
+  MEDIA_FRAME_KEYS,
   SPEED_RATE_MAX,
   SPEED_RATE_MIN,
+  TEXT_ENTER_KINDS,
+  TEXT_EXIT_KINDS,
   TILT_DEG_MAX,
   TILT_SPAN_MIN,
   ZOOM_LEVEL_MAX,
@@ -357,6 +358,59 @@ function lintDoc(docIn) {
   const program = isObj(doc.program) ? doc.program : void 0;
   const programConfig = program && isObj(program.config) ? program.config : void 0;
   const duration = recording ? (isNum(meta.durationMs) ? meta.durationMs : 0) / 1e3 : program && isNum(program.duration) ? program.duration : programConfig && isNum(programConfig.duration) ? programConfig.duration : 0;
+  const mediaLen = /* @__PURE__ */ new Map();
+  if (recording && doc.media !== void 0) {
+    if (!Array.isArray(doc.media)) problems.push("media must be an array");
+    for (const [i, raw] of (Array.isArray(doc.media) ? doc.media : []).entries()) {
+      const m = isObj(raw) ? raw : {};
+      const id = typeof m.id === "string" ? m.id : "";
+      if (!id) problems.push(`media[${i}]: id must be a string`);
+      else if (mediaLen.has(id))
+        problems.push(`media[${i}] (${id}): duplicate id`);
+      const mf = m.frame;
+      if (mf !== void 0) {
+        if (!isObj(mf)) {
+          problems.push(
+            `media[${i}]${id ? ` (${id})` : ""}: frame must be an object`
+          );
+        } else {
+          for (const k of Object.keys(mf)) {
+            if (!MEDIA_FRAME_KEYS.includes(k))
+              problems.push(
+                `media[${i}]${id ? ` (${id})` : ""}.frame.${k}: not a card field (a media's frame carries ${MEDIA_FRAME_KEYS.join(", ")}; the rest is the take's frame)`
+              );
+          }
+        }
+      }
+      if (typeof m.videoKey !== "string")
+        problems.push(
+          `media[${i}]${id ? ` (${id})` : ""}: videoKey must be a string`
+        );
+      const mm = isObj(m.meta) ? m.meta : {};
+      const ms = isNum(mm.durationMs) ? mm.durationMs : 0;
+      if (id) mediaLen.set(id, ms / 1e3);
+    }
+  }
+  const checkByMedia = (list, label) => {
+    const groups = /* @__PURE__ */ new Map();
+    for (const s of list) {
+      const m = typeof s.media === "string" ? s.media : "";
+      if (m && !mediaLen.has(m)) {
+        problems.push(
+          `${spanName(label, s)}: media "${m}" is not one of media[].id`
+        );
+        continue;
+      }
+      groups.set(m, [...groups.get(m) ?? [], s]);
+    }
+    for (const [m, group] of groups)
+      checkSpanList(
+        group,
+        label,
+        m ? mediaLen.get(m) ?? 0 : duration,
+        problems
+      );
+  };
   if (!recording) {
     if (!program)
       problems.push(
@@ -373,7 +427,7 @@ function lintDoc(docIn) {
     problems.push("zoom must be an array of spans");
   const zoom = recording ? entries(doc.zoom) : [];
   if (recording) {
-    checkSpanList(zoom, "zoom", duration, problems);
+    checkByMedia(zoom, "zoom");
     for (const z of zoom) {
       const name = spanName("zoom", z);
       if (!isNum(z.level) || z.level < ZOOM_LEVEL_MIN - EPS || z.level > ZOOM_LEVEL_MAX + EPS) {
@@ -427,9 +481,13 @@ function lintDoc(docIn) {
         problems.push(`${name}: id must be a string`);
       else if (freezeIds.has(f.id)) problems.push(`${name}: duplicate id`);
       else freezeIds.add(f.id);
-      if (!isNum(f.at) || f.at < 0 || f.at > duration + EPS) {
+      const fm = typeof f.media === "string" ? f.media : "";
+      const fLen = fm ? mediaLen.get(fm) : duration;
+      if (fm && fLen === void 0) {
+        problems.push(`${name}: media "${fm}" is not one of media[].id`);
+      } else if (!isNum(f.at) || f.at < 0 || f.at > (fLen ?? duration) + EPS) {
         problems.push(
-          `${name}: at must be a SOURCE moment inside the recording (0..${duration.toFixed(2)}s, got ${String(f.at)})`
+          `${name}: at must be a SOURCE moment inside the recording (0..${(fLen ?? duration).toFixed(2)}s, got ${String(f.at)})`
         );
       }
       if (!isNum(f.seconds) || f.seconds < FREEZE_SECONDS_MIN - EPS || f.seconds > FREEZE_SECONDS_MAX + EPS) {
@@ -471,10 +529,10 @@ function lintDoc(docIn) {
     if (doc.segments !== void 0 && !Array.isArray(doc.segments)) {
       problems.push("segments must be an array of {in, out} spans");
     }
-    checkSpanList(entries(doc.segments), "segment", duration, problems);
+    checkByMedia(entries(doc.segments), "segment");
   }
   const speed = entries(doc.speed);
-  checkSpanList(speed, "speed", duration, problems);
+  checkByMedia(speed, "speed");
   for (const s of speed) {
     if (!isNum(s.rate) || s.rate < SPEED_RATE_MIN - EPS || s.rate > SPEED_RATE_MAX + EPS) {
       problems.push(
@@ -487,7 +545,7 @@ function lintDoc(docIn) {
       problems.push("tilt must be an array of spans");
     }
     const tilt = entries(doc.tilt);
-    checkSpanList(tilt, "tilt", duration, problems);
+    checkByMedia(tilt, "tilt");
     for (const t of tilt) {
       const name = spanName("tilt", t);
       for (const ax of ["rx", "ry"]) {
@@ -540,7 +598,7 @@ function lintDoc(docIn) {
       problems.push("camMotion must be an array of spans");
     }
     const camMotion = entries(doc.camMotion);
-    checkSpanList(camMotion, "camMotion", duration, problems);
+    checkByMedia(camMotion, "camMotion");
     if (camMotion.length && typeof source.camKey !== "string") {
       warnings.push(
         "camMotion has spans but the take has no cam track (source.camKey) \u2014 nothing renders them"
@@ -6104,6 +6162,35 @@ function applyStyle(seed, doc, opts) {
   if (opts.words) patchStageWords(next, opts.words);
   return { doc: next, layout: { ...parts, notes } };
 }
+function planOtherMedia(doc, activity) {
+  const zoom = [];
+  const speed = [];
+  for (const m of doc.media ?? []) {
+    const manualZoom = doc.zoom.filter(
+      (z) => z.media === m.id && z.source === "manual"
+    );
+    const rejected = (doc.rejected ?? []).filter((r) => r.media === m.id);
+    zoom.push(
+      ...planAutoZoom(m.cursor, {
+        width: m.meta.width,
+        height: m.meta.height,
+        style: doc.zoomStyle,
+        params: doc.zoomParams
+      }).filter((z) => !manualZoom.some((x) => overlaps(z, x))).filter((z) => !isRejected("zoom", z, rejected)).map((z) => ({ ...z, id: `${z.id}-${m.id}`, media: m.id }))
+    );
+    const manualSpeed = (doc.speed ?? []).filter(
+      (x) => x.media === m.id && x.source !== "auto"
+    );
+    speed.push(
+      ...planAutoSpeed(m.cursor, {
+        durationMs: m.meta.durationMs,
+        params: doc.speedParams,
+        activity
+      }).filter((x) => !manualSpeed.some((y) => x.in < y.out && x.out > y.in)).filter((x) => !isRejected("speed", x, rejected)).map((x) => ({ ...x, id: `${x.id}-${m.id}`, media: m.id }))
+    );
+  }
+  return { zoom, speed };
+}
 async function planTake(dir, opts = {}) {
   const take = await loadTake(dir);
   const { meta, cursor } = take;
@@ -6140,6 +6227,17 @@ async function planTake(dir, opts = {}) {
       activity
     }).filter((s) => !manualSpeed.some((m) => s.in < m.out && s.out > m.in)).filter((s) => !isRejected("speed", s, doc.rejected));
     doc.speed = [...manualSpeed, ...autoSpeed].sort((a, b) => a.in - b.in);
+    {
+      const others = planOtherMedia(doc, activity);
+      doc.zoom = [
+        ...doc.zoom.filter((z) => !z.media || z.source === "manual"),
+        ...others.zoom
+      ].sort((a, b) => a.in - b.in);
+      doc.speed = [
+        ...(doc.speed ?? []).filter((x) => !x.media || x.source !== "auto"),
+        ...others.speed
+      ].sort((a, b) => a.in - b.in);
+    }
     if (rt.tilt.length) doc.tilt = rt.tilt;
     if (prev.overlays?.length) doc.overlays = prev.overlays;
     if (prev.objects?.length) doc.objects = prev.objects;
@@ -6164,7 +6262,7 @@ async function planTake(dir, opts = {}) {
       doc = take.doc;
     }
     fresh = false;
-    const manual = doc.zoom.filter((z) => z.source === "manual");
+    const manual = doc.zoom.filter((z) => z.source === "manual" && !z.media);
     const auto = planAutoZoom(doc.source.cursor, {
       width: doc.source.meta.width,
       height: doc.source.meta.height,
@@ -6172,13 +6270,26 @@ async function planTake(dir, opts = {}) {
       params: doc.zoomParams
     }).filter((z) => !manual.some((m) => overlaps(z, m))).filter((z) => !isRejected("zoom", z, doc.rejected));
     doc.zoom = [...manual, ...auto].sort((a, b) => a.in - b.in);
-    const manualSpeed = (doc.speed ?? []).filter((s) => s.source !== "auto");
+    const manualSpeed = (doc.speed ?? []).filter(
+      (s) => s.source !== "auto" && !s.media
+    );
     const autoSpeed = planAutoSpeed(doc.source.cursor, {
       durationMs: doc.source.meta.durationMs,
       params: doc.speedParams,
       activity
     }).filter((s) => !manualSpeed.some((m) => s.in < m.out && s.out > m.in)).filter((s) => !isRejected("speed", s, doc.rejected));
     doc.speed = [...manualSpeed, ...autoSpeed].sort((a, b) => a.in - b.in);
+    {
+      const others = planOtherMedia(doc, activity);
+      doc.zoom = [
+        ...doc.zoom.filter((z) => !z.media || z.source === "manual"),
+        ...others.zoom
+      ].sort((a, b) => a.in - b.in);
+      doc.speed = [
+        ...(doc.speed ?? []).filter((x) => !x.media || x.source !== "auto"),
+        ...others.speed
+      ].sort((a, b) => a.in - b.in);
+    }
   } else {
     const artifact = {
       videoKey: RECORDING_NAME,
@@ -6256,6 +6367,34 @@ function isTakeRelativeKey(key) {
 var takeRelativeFile = (key) => key.replace(/^\/+/, "");
 function docMediaRefs(doc, keep = isTakeRelativeKey) {
   const out = [];
+  for (const m of doc.media ?? []) {
+    if (keep(m.videoKey))
+      out.push({
+        where: `media ${m.id}`,
+        key: m.videoKey,
+        set: (next) => {
+          m.videoKey = next;
+        }
+      });
+    const mic = m.micKey;
+    if (mic && keep(mic))
+      out.push({
+        where: `media ${m.id} mic`,
+        key: mic,
+        set: (next) => {
+          m.micKey = next;
+        }
+      });
+    const cam = m.camKey;
+    if (cam && keep(cam))
+      out.push({
+        where: `media ${m.id} cam`,
+        key: cam,
+        set: (next) => {
+          m.camKey = next;
+        }
+      });
+  }
   for (const clip of doc.overlays ?? []) {
     if (clip.kind === "text" || !keep(clip.key)) continue;
     out.push({
@@ -10220,4 +10359,4 @@ export {
   convertAgentBrowser,
   run
 };
-//# sourceMappingURL=chunk-SLCQCRNI.js.map
+//# sourceMappingURL=chunk-TYTUA5L5.js.map