@koda-sl/baker-cli 0.388.0 → 0.390.0

package/dist/{chunk-FPJ5FXAX.js → chunk-6UE43HEQ.js}

@@ -1,7 +1,7 @@
 import {
   debugLogHttp,
   readBodyForLog
-} from "./chunk-QIQ57EIA.js";
+} from "./chunk-TWSWUIDI.js";
 import {
   API_KEY_FORMAT_MESSAGE,
   DIRECT_ROUTE,
@@ -18,7 +18,7 @@ import {
   refuseNonPublicUrl,
   requireConnection,
   shouldEscalate
-} from "./chunk-AOVFDDVW.js";
+} from "./chunk-7OVZ6SOA.js";
 
 // ../../node_modules/.pnpm/safe-stable-stringify@2.5.0/node_modules/safe-stable-stringify/index.js
 var require_safe_stable_stringify = __commonJS({
@@ -1340,12 +1340,17 @@ var IMAGE_GENERATE_MODELS = [
   "openai/gpt-image-2.5-sunburst",
   "openai/gpt-image-2",
   "openai/gpt-5.4-image-2",
-  "google/gemini-3.1-flash-image-preview",
+  "google/gemini-3.1-flash-image",
   "google/gemini-3.1-flash-lite-image",
-  "google/gemini-3-pro-image-preview",
-  "recraft/recraft-v4.1-pro-vector"
+  "google/gemini-3-pro-image",
+  "recraft/recraft-v4.1-pro-vector",
+  // LEGACY — the preview ids the Gemini image models shipped under until they went GA
+  // on 2026-06-18. Kept so every canvas written with them still validates and re-runs;
+  // never pick them for new work.
+  "google/gemini-3.1-flash-image-preview",
+  "google/gemini-3-pro-image-preview"
 ];
-var DEFAULT_IMAGE_GENERATE_MODEL = "google/gemini-3.1-flash-image-preview";
+var DEFAULT_IMAGE_GENERATE_MODEL = "google/gemini-3.1-flash-image";
 var VIDEO_GENERATE_MODELS = [
   "bytedance/seedance-2.0",
   "bytedance/seedance-2.5",
@@ -1536,6 +1541,32 @@ var MODEL_REGISTRY = {
         quality: { kind: "string", enum: OPENROUTER_IMAGE_QUALITY }
       }
     },
+    // The GA Nano Banana ids (2026-06-18). Same surface as the preview entries they
+    // replace — read off GET /api/v1/images/models/google/gemini-3.1-flash-image/endpoints
+    // and .../gemini-3-pro-image/endpoints — so a canvas moves between them unchanged.
+    "google/gemini-3.1-flash-image": {
+      label: "Google Gemini 3.1 Flash Image (Nano Banana 2)",
+      inputs: [],
+      optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES, max: GEMINI_IMAGE_MAX_REFERENCES }],
+      required: ["prompt"],
+      params: {
+        prompt: { kind: "string" },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR_EXTREME },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE_EXTENDED }
+      }
+    },
+    "google/gemini-3-pro-image": {
+      label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
+      inputs: [],
+      optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES, max: GEMINI_IMAGE_MAX_REFERENCES }],
+      required: ["prompt"],
+      params: {
+        prompt: { kind: "string" },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE }
+      }
+    },
+    // LEGACY preview ids — see IMAGE_GENERATE_MODELS.
     "google/gemini-3.1-flash-image-preview": {
       label: "Google Gemini 3.1 Flash Image (Preview)",
       inputs: [],
@@ -1573,7 +1604,7 @@ var MODEL_REGISTRY = {
       }
     },
     "google/gemini-3-pro-image-preview": {
-      label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
+      label: "Google Gemini 3 Pro Image (Preview)",
       inputs: [],
       optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES, max: GEMINI_IMAGE_MAX_REFERENCES }],
       required: ["prompt"],
@@ -1616,6 +1647,35 @@ var MODEL_REGISTRY = {
     // is baked into the backend handler — params here are semantic levers
     // only. Both models consume MULTIPLE reference images via the `references`
     // input slot (required: a sheet without source images is just image_generate).
+    "google/gemini-3-pro-image": {
+      label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
+      inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
+      required: ["subject_description", "subject_type"],
+      params: {
+        subject_description: { kind: "string" },
+        subject_type: { kind: "string", enum: ["character", "person", "product", "location"] },
+        views: { kind: "json" },
+        style: { kind: "string" },
+        prompt_override: { kind: "string" },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE }
+      }
+    },
+    "google/gemini-3.1-flash-image": {
+      label: "Google Gemini 3.1 Flash Image (Nano Banana 2)",
+      inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
+      required: ["subject_description", "subject_type"],
+      params: {
+        subject_description: { kind: "string" },
+        subject_type: { kind: "string", enum: ["character", "person", "product", "location"] },
+        views: { kind: "json" },
+        style: { kind: "string" },
+        prompt_override: { kind: "string" },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR_EXTREME },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE_EXTENDED }
+      }
+    },
+    // LEGACY preview ids, kept so existing canvases re-run.
     "google/gemini-3-pro-image-preview": {
       label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
       inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
@@ -1654,6 +1714,29 @@ var MODEL_REGISTRY = {
     // registry can't express "one of" or gate array elements), so `formats`
     // is not listed as registry-required. The source creative is a required
     // input slot.
+    "google/gemini-3-pro-image": {
+      label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
+      inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
+      required: [],
+      params: {
+        formats: { kind: "json" },
+        platform: { kind: "string", enum: AD_FORMAT_PLATFORMS },
+        guidance: { kind: "string" },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE }
+      }
+    },
+    "google/gemini-3.1-flash-image": {
+      label: "Google Gemini 3.1 Flash Image (Nano Banana 2)",
+      inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
+      required: [],
+      params: {
+        formats: { kind: "json" },
+        platform: { kind: "string", enum: AD_FORMAT_PLATFORMS },
+        guidance: { kind: "string" },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE_EXTENDED }
+      }
+    },
+    // LEGACY preview ids, kept so existing canvases re-run.
     "google/gemini-3-pro-image-preview": {
       label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
       inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
@@ -3133,7 +3216,7 @@ var LocalAssetStore = class {
         );
         const written = await readFile(tmp);
         const computed = sha256Hex(written);
-        if (computed !== args.sha256) {
+        if (computed !== args.sha256 && !cdnReencodedImage(res, args.kind)) {
           throw new Error(`asset-store: sha mismatch for ${args.url} (got ${computed}, expected ${args.sha256})`);
         }
         await rename(tmp, dest);
@@ -3154,6 +3237,9 @@ var LocalAssetStore = class {
     });
   }
 };
+function cdnReencodedImage(res, kind) {
+  return kind === "image" && res.headers.get("cf-polished") !== null;
+}
 function byteLimit(url, maxBytes) {
   let total = 0;
   return new Transform({
@@ -3571,13 +3657,13 @@ function spineInputFlags(work, lenS) {
 function spineInputOps(work, lenS, dims) {
   const fit = work.still?.fit ?? "fill";
   const scale = fit === "pad" ? `scale=${dims.w}:${dims.h}:force_original_aspect_ratio=decrease,pad=${dims.w}:${dims.h}:(ow-iw)/2:(oh-ih)/2:color=black` : `scale=${dims.w}:${dims.h}:force_original_aspect_ratio=increase,crop=${dims.w}:${dims.h}`;
-  const normalize = `${scale},format=yuv420p,fps=30,setsar=1,settb=AVTB`;
+  const normalize2 = `${scale},format=yuv420p,fps=30,setsar=1,settb=AVTB`;
   if (work.trim) {
     const start = work.trim.offset_s > 0 ? `start=${work.trim.offset_s.toFixed(3)}:` : "";
-    return `${normalize},trim=${start}duration=${lenS.toFixed(3)},setpts=PTS-STARTPTS`;
+    return `${normalize2},trim=${start}duration=${lenS.toFixed(3)},setpts=PTS-STARTPTS`;
   }
-  if (work.still) return `${normalize},trim=duration=${lenS.toFixed(3)}`;
-  return normalize;
+  if (work.still) return `${normalize2},trim=duration=${lenS.toFixed(3)}`;
+  return normalize2;
 }
 function parseSpineInputLens(args) {
   const lens = /* @__PURE__ */ new Map();
@@ -7296,10 +7382,10 @@ function applyDuck(params, labelFor, filterChains) {
   }
   const th = duck.threshold ?? 0.03;
   const ra = duck.ratio ?? 8;
-  const at = duck.attack ?? 5;
+  const at2 = duck.attack ?? 5;
   const re = duck.release ?? 300;
   filterChains.push(
-    `[${labelFor[trackIdx]}]${keyOut}sidechaincompress=threshold=${th}:ratio=${ra}:attack=${at}:release=${re}[ducked]`
+    `[${labelFor[trackIdx]}]${keyOut}sidechaincompress=threshold=${th}:ratio=${ra}:attack=${at2}:release=${re}[ducked]`
   );
   labelFor[trackIdx] = "ducked";
 }
@@ -7692,7 +7778,7 @@ async function collectFiles(root, current) {
 import { readFile as readFile9 } from "fs/promises";
 import path12 from "path";
 import { z as z10 } from "zod";
-var InputKind = z10.enum(["video", "image", "audio", "json"]);
+var InputKind = z10.enum(["video", "image", "audio", "json", "font"]);
 var InputSpec = z10.object({
   kind: InputKind,
   required: z10.boolean().optional().default(false),
@@ -7841,6 +7927,7 @@ function finalize(schema, dflt, required) {
 }
 function defaultFilenameForInput(key, kind) {
   if (kind === "video") return `${key}.mp4`;
+  if (kind === "font") return `${key}.font`;
   if (kind === "audio") return `${key}.mp3`;
   if (kind === "json") return `${key}.json`;
   return `${key}.png`;
@@ -8335,7 +8422,7 @@ async function validateComposition(rawParams) {
   }
   return issues;
 }
-async function validateCompositionParams(rawParams) {
+async function validateCompositionParams(rawParams, ownedKeys = NODE_OWNED_PARAM_KEYS) {
   const issues = [];
   if (!rawParams || typeof rawParams !== "object") return issues;
   const params = rawParams;
@@ -8357,7 +8444,7 @@ async function validateCompositionParams(rawParams) {
   }
   const dynamic = {};
   for (const [k, v] of Object.entries(params)) {
-    if (NODE_OWNED_PARAM_KEYS.has(k)) continue;
+    if (ownedKeys.has(k)) continue;
     dynamic[k] = v;
   }
   for (const key of Object.keys(dynamic)) {
@@ -8567,7 +8654,9 @@ var hyperframeSnapshotNode = defineNode({
   params: HyperframeSnapshotParams,
   outputs: HyperframeSnapshotOutputs,
   cost: () => ({ credits: 0, seconds_estimate: 3 }),
-  validateExtra: ({ rawParams }) => validateCompositionParams(rawParams),
+  // The snapshot's own keys (`wait_for`) are not composition params: checked against the
+  // render node's key set, a canvas that waited on a selector failed validate every time.
+  validateExtra: ({ rawParams }) => validateCompositionParams(rawParams, NODE_OWNED_PARAM_KEYS2),
   cacheKeyExtras: async ({ params }) => {
     const out = {};
     const composition = params.composition;
@@ -8923,7 +9012,16 @@ var imageGenerateNode = delegated({
 
 // src/engine/nodes/remote/imageAspectAdapt.ts
 import { z as z18 } from "zod";
-var ASPECT_ADAPT_MODELS = ["google/gemini-3-pro-image-preview", "google/gemini-3.1-flash-image-preview"];
+var ASPECT_ADAPT_MODELS = [
+  "google/gemini-3-pro-image",
+  "google/gemini-3.1-flash-image",
+  "google/gemini-3-pro-image-preview",
+  "google/gemini-3.1-flash-image-preview"
+];
+var PRO_ADAPT_MODELS = /* @__PURE__ */ new Set([
+  "google/gemini-3-pro-image",
+  "google/gemini-3-pro-image-preview"
+]);
 var ASPECT_ADAPT_FORMATS = ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"];
 var ImageAspectAdaptParams = z18.object({
   model: z18.enum(ASPECT_ADAPT_MODELS),
@@ -8940,7 +9038,7 @@ var imageAspectAdaptNode = delegated({
   version: "1.0.0",
   category: "image",
   summary: "Adapt ONE creative into multiple aspect ratios (Meta: 9:16 stories, 1:1 feed, 4:5, 16:9\u2026) in a single step. Give it either an explicit `formats` list OR a `platform` preset (meta_feed, meta_feed_stories, meta_all, linkedin, google_demandgen, tiktok, youtube) that expands to that platform's canonical set. AI recomposes the layout per format \u2014 identical subject, text, logos, colors, and style; the scene is extended/restructured, never stretched or cropped. Formats that already match the source ratio pass through unchanged at zero cost. Outputs are ordered exactly as the resolved format list.",
-  when_to_use: "Use after a hero creative exists (image_generate, ingest, image_search) to fan it out to every placement format \u2014 wire the creative into `source` and set EITHER `formats` (exact ratios) OR `platform` (e.g. `meta_feed_stories`). Cost is estimated per format; formats matching the source ratio are free pass-throughs. Off-grid platform targets (e.g. Google 1.91:1) are not rendered here \u2014 crop them from the nearest ratio with `baker images crop`. Pick `google/gemini-3.1-flash-image-preview` (Nano Banana flash) while iterating, `google/gemini-3-pro-image-preview` (Nano Banana Pro) for final-quality adaptation.",
+  when_to_use: "Use after a hero creative exists (image_generate, ingest, image_search) to fan it out to every placement format \u2014 wire the creative into `source` and set EITHER `formats` (exact ratios) OR `platform` (e.g. `meta_feed_stories`). Cost is estimated per format; formats matching the source ratio are free pass-throughs. Off-grid platform targets (e.g. Google 1.91:1) are not rendered here \u2014 crop them from the nearest ratio with `baker images crop`. Pick `google/gemini-3.1-flash-image` (Nano Banana 2) while iterating, `google/gemini-3-pro-image` (Nano Banana Pro) for final-quality adaptation.",
   inputs: z18.object({ source: ImageRef }).loose(),
   params: ImageAspectAdaptParams,
   outputs: z18.object({ images: z18.array(ImageRef).min(1) }).strict(),
@@ -8949,7 +9047,7 @@ var imageAspectAdaptNode = delegated({
     const p = params;
     const count = Math.max(1, resolveAdaptFormats(p ?? {}).length);
     return {
-      credits: count * (p?.model === "google/gemini-3-pro-image-preview" ? 20 : 5),
+      credits: count * (PRO_ADAPT_MODELS.has(String(p?.model)) ? 20 : 5),
       seconds_estimate: 30 + 30 * count
     };
   }
@@ -9035,7 +9133,16 @@ var imageLayerizeNode = delegated({
 
 // src/engine/nodes/remote/imageReferenceSheet.ts
 import { z as z22 } from "zod";
-var REFERENCE_SHEET_MODELS = ["google/gemini-3-pro-image-preview", "google/gemini-3.1-flash-image-preview"];
+var REFERENCE_SHEET_MODELS = [
+  "google/gemini-3-pro-image",
+  "google/gemini-3.1-flash-image",
+  "google/gemini-3-pro-image-preview",
+  "google/gemini-3.1-flash-image-preview"
+];
+var PRO_SHEET_MODELS = /* @__PURE__ */ new Set([
+  "google/gemini-3-pro-image",
+  "google/gemini-3-pro-image-preview"
+]);
 var ImageReferenceSheetParams = z22.object({
   model: z22.enum(REFERENCE_SHEET_MODELS),
   subject_description: z22.string().min(1),
@@ -9053,13 +9160,13 @@ var imageReferenceSheetNode = delegated({
   version: "1.0.0",
   category: "image",
   summary: "Fuse 1\u20136 images of a single subject (person, character, product, or location/set) into ONE multi-view reference sheet \u2014 a labeled grid in consistent style and lighting: a turnaround (FRONT / SIDE / BACK\u2026) for a person/character/product, or several camera angles of the same room (WIDE / REVERSE / DETAIL\u2026) for a location. Curated models: Gemini 3 Pro Image (best fusion + labels), Gemini 3.1 Flash Image (cheap iteration).",
-  when_to_use: "Use before image_generate / video_generate when a subject must stay consistent across many creatives \u2014 wire the `sheet` output into their `reference` input instead of re-describing the subject per prompt. `subject_description` should be the exact wording you reuse downstream. Pick `google/gemini-3-pro-image-preview` for final 6-view sheets at 2K+, `google/gemini-3.1-flash-image-preview` while iterating.",
+  when_to_use: "Use before image_generate / video_generate when a subject must stay consistent across many creatives \u2014 wire the `sheet` output into their `reference` input instead of re-describing the subject per prompt. `subject_description` should be the exact wording you reuse downstream. Pick `google/gemini-3-pro-image` for final 6-view sheets at 2K+, `google/gemini-3.1-flash-image` while iterating.",
   inputs: z22.object({ references: z22.array(ImageRef).min(1).max(6) }).loose(),
   params: ImageReferenceSheetParams,
   outputs: z22.object({ sheet: ImageRef }).strict(),
   outputKinds: { sheet: "image" },
   cost: ({ params }) => ({
-    credits: params?.model === "google/gemini-3-pro-image-preview" ? 20 : 5,
+    credits: PRO_SHEET_MODELS.has(String(params?.model)) ? 20 : 5,
     seconds_estimate: 30
   })
 });
@@ -9549,6 +9656,165 @@ ${detail.slice(-4e3)}`);
   }
 }
 
+// src/engine/lib/spell-number.ts
+import { toCardinal as nwAr } from "n2words/ar-SA";
+import { toCardinal as nwDe } from "n2words/de-DE";
+import { toCardinal as nwEn } from "n2words/en-US";
+import { toCardinal as nwEs } from "n2words/es-ES";
+import { toCardinal as nwFr } from "n2words/fr-FR";
+import { toCardinal as nwHi } from "n2words/hi-IN";
+import { toCardinal as nwIt } from "n2words/it-IT";
+import { toCardinal as nwJa } from "n2words/ja-JP";
+import { toCardinal as nwKo } from "n2words/ko-KR";
+import { toCardinal as nwNl } from "n2words/nl-NL";
+import { toCardinal as nwPl } from "n2words/pl-PL";
+import { toCardinal as nwPt } from "n2words/pt-PT";
+var INTEGER_SPELLERS = {
+  fr: nwFr,
+  es: nwEs,
+  en: nwEn,
+  de: nwDe,
+  it: nwIt,
+  pt: nwPt,
+  nl: nwNl,
+  pl: nwPl,
+  ar: nwAr,
+  ja: nwJa,
+  ko: nwKo,
+  hi: nwHi
+};
+function canSpellNumbers(langCode) {
+  return langCode in INTEGER_SPELLERS;
+}
+function spellNumber(langCode, n) {
+  const spell = langCode ? INTEGER_SPELLERS[langCode] : void 0;
+  if (!spell || !Number.isFinite(n)) return String(n);
+  try {
+    return spell(n);
+  } catch {
+    return String(n);
+  }
+}
+
+// src/engine/nodes/local/lib/script-word-timing.ts
+var UNBOUNDED_WORD_S = 0.3;
+var EXACT = 3;
+var NEAR = 2;
+var SUBSTITUTE = -1;
+var SKIP = -2;
+var NEAR_SIMILARITY = 0.7;
+function normalize(word) {
+  return word.normalize("NFD").replace(new RegExp("\\p{M}", "gu"), "").toLowerCase().replace(/[^\p{L}\p{N}]/gu, "");
+}
+function tokensOf(word, index, language) {
+  const key = normalize(word);
+  if (!key) return [];
+  if (language && /^\d{1,9}$/.test(key)) {
+    const spoken = spellNumber(language, Number.parseInt(key, 10));
+    if (spoken !== key) {
+      const parts = spoken.split(/[\s-]+/).map(normalize).filter(Boolean);
+      if (parts.length > 0) return parts.map((part) => ({ key: part, word: index }));
+    }
+  }
+  return [{ key, word: index }];
+}
+function similarity(a, b) {
+  if (a === b) return 1;
+  const longest = Math.max(a.length, b.length);
+  if (longest === 0) return 1;
+  let prev = Array.from({ length: b.length + 1 }, (_, j) => j);
+  for (let i = 1; i <= a.length; i++) {
+    const row = [i];
+    for (let j = 1; j <= b.length; j++) {
+      const cost = a[i - 1] === b[j - 1] ? 0 : 1;
+      row[j] = Math.min((prev[j] ?? 0) + 1, (row[j - 1] ?? 0) + 1, (prev[j - 1] ?? 0) + cost);
+    }
+    prev = row;
+  }
+  return 1 - (prev[b.length] ?? longest) / longest;
+}
+function pairScore(a, b) {
+  if (a === b) return EXACT;
+  return similarity(a, b) >= NEAR_SIMILARITY ? NEAR : SUBSTITUTE;
+}
+var at = (grid, i, j) => grid[i]?.[j] ?? 0;
+function diagonal(grid, script, transcript, i, j) {
+  return at(grid, i - 1, j - 1) + pairScore(script[i - 1]?.key ?? "", transcript[j - 1]?.key ?? "");
+}
+function scoreGrid(script, transcript) {
+  const grid = Array.from(
+    { length: script.length + 1 },
+    (_, i) => Array.from({ length: transcript.length + 1 }, (_2, j) => i === 0 ? j * SKIP : i * SKIP)
+  );
+  for (let i = 1; i <= script.length; i++) {
+    const row = grid[i];
+    for (let j = 1; j <= transcript.length; j++) {
+      row[j] = Math.max(diagonal(grid, script, transcript, i, j), at(grid, i - 1, j) + SKIP, at(grid, i, j - 1) + SKIP);
+    }
+  }
+  return grid;
+}
+function align(script, transcript) {
+  const grid = scoreGrid(script, transcript);
+  const pairs = new Array(script.length).fill(-1);
+  let i = script.length;
+  let j = transcript.length;
+  while (i > 0 && j > 0) {
+    const here = at(grid, i, j);
+    if (here === diagonal(grid, script, transcript, i, j)) {
+      pairs[i - 1] = j - 1;
+      i--;
+      j--;
+    } else if (here === at(grid, i - 1, j) + SKIP) {
+      i--;
+    } else {
+      j--;
+    }
+  }
+  return pairs;
+}
+var round = (s) => Math.round(s * 1e3) / 1e3;
+function pairedSpans(wordCount, scriptTokens, heardTokens, pairs, transcript) {
+  const spans = new Array(wordCount).fill(null);
+  pairs.forEach((heardIndex, t) => {
+    const token = scriptTokens[t];
+    const said = heardIndex >= 0 ? transcript[heardTokens[heardIndex]?.word ?? -1] : void 0;
+    if (!token || !said) return;
+    const current = spans[token.word];
+    spans[token.word] = current ? { start: Math.min(current.start, said.start), end: Math.max(current.end, said.end) } : { start: said.start, end: said.end };
+  });
+  return spans;
+}
+function fillRun(spans, first, end) {
+  const before = first > 0 ? spans[first - 1] : null;
+  const after = end < spans.length ? spans[end] : null;
+  const count = end - first;
+  const from = before ? before.end : Math.max(0, (after?.start ?? 0) - count * UNBOUNDED_WORD_S);
+  const to = after ? Math.max(after.start, from) : from + count * UNBOUNDED_WORD_S;
+  const each = (to - from) / count;
+  for (let w = first; w < end; w++) spans[w] = { start: from + (w - first) * each, end: from + (w - first + 1) * each };
+}
+function fillDropped(spans) {
+  const filled = [...spans];
+  let i = 0;
+  while (i < filled.length) {
+    let end = i;
+    while (end < filled.length && !filled[end]) end++;
+    if (end > i) fillRun(filled, i, end);
+    i = end + 1;
+  }
+  return filled.map((span) => span ?? { start: 0, end: 0 });
+}
+function timeScriptWords(script, transcript, language) {
+  const words = script.split(/\s+/).filter(Boolean);
+  if (words.length === 0 || transcript.length === 0) return [];
+  const scriptTokens = words.flatMap((word, i) => tokensOf(word, i, language));
+  const heardTokens = transcript.flatMap((w, i) => tokensOf(String(w.text ?? ""), i, language));
+  const pairs = align(scriptTokens, heardTokens);
+  const spans = fillDropped(pairedSpans(words.length, scriptTokens, heardTokens, pairs, transcript));
+  return words.map((text, i) => ({ text, start: round(spans[i]?.start ?? 0), end: round(spans[i]?.end ?? 0) }));
+}
+
 // src/engine/nodes/remote/videoTranscribe.ts
 var VideoTranscribeParams = z33.object({
   language: z33.string().min(2).max(8).optional(),
@@ -9558,6 +9824,9 @@ var VideoTranscribeParams = z33.object({
   transcriber: z33.enum(["groq", "deepgram"]).optional(),
   keyterms: z33.array(z33.string().min(2).max(60)).max(30).optional().describe(
     "Names the recogniser must not mangle \u2014 a product, a person, a phrase the script coins. The COMPANY'S OWN NAME is always applied server-side, so you never list it: this is for the rest. Every term is biased into the request AND its spelling enforced on the way out, because a caption prints a mishearing at full size over the ad (a real cut shipped with the brand name spelled wrong). Never patch a misspelling inside a caption composition \u2014 that fix dies with that one creative."
+  ),
+  script: z33.string().min(1).optional().describe(
+    "The words the track was asked to say, when there is a script: the transcript's words are then the script's, spelled as written, at the times the recogniser heard them. A misheard word stops being a typo on screen, and a word the recogniser added (a filler) is never printed. Aligned locally, never sent."
   )
 }).strict();
 var VideoTranscribeInputs = z33.object({
@@ -9588,16 +9857,40 @@ var videoTranscribeNode = defineNode({
   async execute({ inputs, params, ctx }) {
     const audioInput = await tryExtractAudio(inputs, ctx);
     const effectiveInputs = audioInput ?? inputs;
-    return await callBackendExec({
+    const { script, ...recogniserParams } = params;
+    const outputs = await callBackendExec({
       nodeType: "video_transcribe",
       nodeVersion: "2.4.0",
-      params,
+      params: recogniserParams,
       inputs: effectiveInputs,
       outputKinds: { transcript: "json", rich: "json" },
       ctx
     });
+    if (!script) return outputs;
+    return { ...outputs, transcript: await scriptTranscript(outputs.transcript, script, params.language, ctx) };
   }
 });
+async function scriptTranscript(heardRef, script, language, ctx) {
+  const local = heardRef.path ? heardRef : await ctx.assets.ingestRemote({
+    kind: "json",
+    url: String(heardRef.url),
+    sha256: heardRef.sha256,
+    mime: heardRef.mime
+  });
+  const heard = JSON.parse(await readFile13(String(local.path), "utf8"));
+  const words = Array.isArray(heard) ? heard.filter(isTimedWord) : [];
+  const timed = timeScriptWords(script, words, language);
+  ctx.log(`video_transcribe: ${timed.length} script words timed off ${words.length} heard`);
+  const bytes = Buffer.from(JSON.stringify(timed));
+  const metadata = { ...heardRef.metadata, text_of_record: "script", heard_sha256: heardRef.sha256 };
+  return uploadAndIngest({ bytes, kind: "json", mime: "application/json", metadata, ctx }).catch(
+    () => ctx.assets.ingestBytes({ bytes, kind: "json", mime: "application/json", metadata })
+  );
+}
+function isTimedWord(value) {
+  const w = value;
+  return Boolean(w) && typeof w?.start === "number" && typeof w?.end === "number" && w?.text !== void 0;
+}
 async function tryExtractAudio(inputs, ctx) {
   const video = inputs.video;
   if (!video.path || !video.mime?.startsWith("video/")) return null;
@@ -9920,6 +10213,7 @@ export {
   runFailureCode,
   AD_FORMAT_PLATFORMS,
   platformFormats,
+  resolveAdaptFormats,
   withoutCastName,
   frameRealismDirection,
   SEEDANCE_DURATIONS,
@@ -9975,6 +10269,9 @@ export {
   canonicalUrl,
   coercePathUrlToUrl,
   toModelSafeImage,
+  loadCompositionMeta,
+  canSpellNumbers,
+  spellNumber,
   catalogView,
   BackendClient2,
   Engine2 as Engine,
@@ -9986,4 +10283,4 @@ export {
   defaultRegistry,
   createEngineFromEnv
 };
-//# sourceMappingURL=chunk-FPJ5FXAX.js.map
+//# sourceMappingURL=chunk-6UE43HEQ.js.map