@shop-os/modelkit 0.2.14 → 0.2.15

package/dist/index.cjs

@@ -104,6 +104,7 @@ __export(index_exports, {
   textUsageEvent: () => textUsageEvent,
   toGeneratedImage: () => toGeneratedImage,
   validateInputSpec: () => validateInputSpec,
+  videoLengthViolation: () => videoLengthViolation,
   withRetry: () => withRetry,
   xaiVideoAdapter: () => xaiVideoAdapter
 });
@@ -1482,7 +1483,8 @@ var VIDEO_MODELS = [
       // reference clip keeps its own framing.
       aspectRatios: [...OMNI_RATIOS],
       durations: [3, 4, 5, 6, 7, 8, 9, 10],
-      references: { images: 6, videos: 1 },
+      references: { images: 6, videos: 1, videoSeconds: { max: 10 } },
+      sourceVideoSeconds: { max: 10 },
       supports: []
     },
     defaults: {},
@@ -1508,7 +1510,8 @@ var VIDEO_MODELS = [
       aspectRatios: [...OMNI_RATIOS],
       resolutions: ["360p", "720p", "1080p", "4k"],
       durations: [3, 4, 5, 6, 7, 8, 9, 10],
-      references: { images: 6, videos: 1 },
+      references: { images: 6, videos: 1, videoSeconds: { max: 10 } },
+      sourceVideoSeconds: { max: 10 },
       supports: []
     },
     defaults: {},
@@ -1536,7 +1539,14 @@ var VIDEO_MODELS = [
       resolutions: ["480p", "720p", "1080p", "4k"],
       durations: { min: 4, max: 15 },
       durationPresets: [4, 6, 8, 10, 12, 15],
-      references: { images: 9, videos: 3, audios: 3, audioOnly: false },
+      references: {
+        images: 9,
+        videos: 3,
+        audios: 3,
+        audioOnly: false,
+        videoSeconds: { min: 2, max: 15, total: 15 }
+      },
+      sourceVideoSeconds: { min: 2, max: 15, inReferenceTotal: true },
       ratioIgnoredWith: ["firstFrame", "sourceVideo"],
       supports: ["generateAudio", "seed", "lastFrame", "watermark"]
     },
@@ -1568,7 +1578,14 @@ var VIDEO_MODELS = [
       aspectRatios: [...SEEDANCE_RATIOS],
       resolutions: ["480p", "720p"],
       durations: { min: 4, max: 15 },
-      references: { images: 9, videos: 3, audios: 3, audioOnly: false },
+      references: {
+        images: 9,
+        videos: 3,
+        audios: 3,
+        audioOnly: false,
+        videoSeconds: { min: 2, max: 15, total: 15 }
+      },
+      sourceVideoSeconds: { min: 2, max: 15, inReferenceTotal: true },
       ratioIgnoredWith: ["firstFrame", "sourceVideo"],
       supports: ["generateAudio", "seed", "lastFrame", "watermark"]
     },
@@ -1602,7 +1619,13 @@ var VIDEO_MODELS = [
       aspectRatios: [...SEEDANCE_RATIOS],
       resolutions: ["480p", "720p", "1080p"],
       durations: { min: 4, max: 30 },
-      references: { images: 30, videos: 10, audios: 10 },
+      references: {
+        images: 30,
+        videos: 10,
+        audios: 10,
+        videoSeconds: { min: 2, max: 30, total: 30, editMin: 4 }
+      },
+      sourceVideoSeconds: { min: 2, max: 30, editMin: 4, inReferenceTotal: true },
       ratioIgnoredWith: ["firstFrame", "sourceVideo"],
       supports: ["generateAudio", "seed", "lastFrame", "watermark", "taskType"]
     },
@@ -1814,7 +1837,14 @@ var VIDEO_MODELS = [
       aspectRatios: [...H3_REFERENCE_RATIOS],
       resolutions: ["480p", "768p", "2k", "4k"],
       durations: { min: 5, max: 15 },
-      references: { images: 9, videos: 3, audios: 3, total: 12, audioOnly: false },
+      references: {
+        images: 9,
+        videos: 3,
+        audios: 3,
+        total: 12,
+        audioOnly: false,
+        videoSeconds: { min: 2, max: 15, total: 15 }
+      },
       supports: ["seed", "promptExpansion", "safetyChecker"]
     },
     defaults: {
@@ -1845,7 +1875,14 @@ var VIDEO_MODELS = [
       aspectRatios: [...H3_REFERENCE_RATIOS],
       resolutions: ["480p", "768p"],
       durations: { min: 5, max: 15 },
-      references: { images: 9, videos: 3, audios: 3, total: 12, audioOnly: false },
+      references: {
+        images: 9,
+        videos: 3,
+        audios: 3,
+        total: 12,
+        audioOnly: false,
+        videoSeconds: { min: 2, max: 15, total: 15 }
+      },
       supports: ["seed", "promptExpansion", "safetyChecker"]
     },
     defaults: {
@@ -1877,6 +1914,7 @@ var VIDEO_MODELS = [
       aspectRatios: [...KLING_RATIOS],
       durations: { min: 3, max: 10 },
       requires: ["sourceVideo"],
+      sourceVideoSeconds: { min: 3, max: 10.05 },
       supports: []
     },
     defaults: { durationSeconds: 5, aspectRatio: "16:9" },
@@ -2236,13 +2274,20 @@ var ProviderOptionValueSchema = import_zod2.z.lazy(
   ])
 );
 var ProviderOptionsSchema = import_zod2.z.record(import_zod2.z.string(), import_zod2.z.record(import_zod2.z.string(), ProviderOptionValueSchema));
+var VideoSecondsLimitsSchema = import_zod2.z.looseObject({
+  min: import_zod2.z.number().optional(),
+  max: import_zod2.z.number().optional(),
+  total: import_zod2.z.number().optional(),
+  editMin: import_zod2.z.number().optional()
+});
 var ReferenceLimitsSchema = import_zod2.z.looseObject({
   images: import_zod2.z.number().optional(),
   imagesWithVideo: import_zod2.z.number().optional(),
   videos: import_zod2.z.number().optional(),
   audios: import_zod2.z.number().optional(),
   total: import_zod2.z.number().optional(),
-  audioOnly: import_zod2.z.boolean().optional()
+  audioOnly: import_zod2.z.boolean().optional(),
+  videoSeconds: VideoSecondsLimitsSchema.optional()
 });
 var ModelConstraintsSchema = import_zod2.z.looseObject({
   aspectRatios: import_zod2.z.array(AspectRatioSchema).optional(),
@@ -2255,14 +2300,20 @@ var ModelConstraintsSchema = import_zod2.z.looseObject({
   references: ReferenceLimitsSchema.optional(),
   requires: import_zod2.z.array(RequiredInputSchema).optional(),
   supports: import_zod2.z.array(SupportedOptionSchema).optional(),
-  ratioIgnoredWith: import_zod2.z.array(import_zod2.z.enum(["firstFrame", "sourceVideo"])).optional()
+  ratioIgnoredWith: import_zod2.z.array(import_zod2.z.enum(["firstFrame", "sourceVideo"])).optional(),
+  sourceVideoSeconds: VideoSecondsLimitsSchema.omit({ total: true }).extend({ inReferenceTotal: import_zod2.z.boolean().optional() }).optional()
 });
 var MediaRefSchema = import_zod2.z.union([
-  import_zod2.z.looseObject({ url: import_zod2.z.string(), label: import_zod2.z.string().optional() }),
+  import_zod2.z.looseObject({
+    url: import_zod2.z.string(),
+    label: import_zod2.z.string().optional(),
+    durationSeconds: import_zod2.z.number().optional()
+  }),
   import_zod2.z.looseObject({
     bytes: import_zod2.z.instanceof(Uint8Array),
     mime: import_zod2.z.string(),
-    label: import_zod2.z.string().optional()
+    label: import_zod2.z.string().optional(),
+    durationSeconds: import_zod2.z.number().optional()
   })
 ]);
 var ImageSafetySettingSchema = import_zod2.z.looseObject({ category: import_zod2.z.string(), threshold: import_zod2.z.string() });
@@ -6647,8 +6698,8 @@ function lyriaAudioInput(req, ctx) {
   if (negative) input.negative_prompt = negative;
   return input;
 }
-function elevenLabsMusicDuration(seconds) {
-  return Math.min(300, Math.max(5, seconds ?? 15));
+function elevenLabsMusicDuration(seconds2) {
+  return Math.min(300, Math.max(5, seconds2 ?? 15));
 }
 function elevenLabsMusicInput(req, ctx) {
   const prompt = req.prompt.trim();
@@ -6713,9 +6764,9 @@ async function generateReplicateAudio(req, ctx, deps) {
   const { url, predictTime, raw } = await runPrediction(ctx, input, deps);
   const usage2 = audioUsage(ctx, req);
   if (ctx.model.usage.unit === "seconds") {
-    const seconds = elevenLabsMusicDuration(req.durationSeconds);
-    usage2.quantity = seconds;
-    usage2.durationSeconds = seconds;
+    const seconds2 = elevenLabsMusicDuration(req.durationSeconds);
+    usage2.quantity = seconds2;
+    usage2.durationSeconds = seconds2;
   } else {
     usage2.quantity = predictTime;
   }
@@ -7355,6 +7406,49 @@ function trim(field, refs, limit, model, warnings) {
   });
   return refs.slice(0, limit);
 }
+function knownLength(value) {
+  return value !== void 0 && Number.isFinite(value) ? value : void 0;
+}
+function seconds(len, limit) {
+  let digits = 1;
+  while (digits < 3 && Number(len.toFixed(digits)) === limit) digits++;
+  return len.toFixed(digits);
+}
+function effectiveMin(limits, taskType) {
+  if (taskType !== "edit" || limits?.editMin === void 0) return limits?.min;
+  return Math.max(limits.min ?? 0, limits.editMin);
+}
+function videoLengthViolation(model, input) {
+  const limits = model.constraints.references?.videoSeconds;
+  const refMin = effectiveMin(limits, input.taskType);
+  const lengths = (input.referenceVideos ?? []).map(knownLength);
+  if (limits?.max !== void 0) {
+    const max = limits.max;
+    const i = lengths.findIndex((len) => len !== void 0 && len > max);
+    if (i >= 0)
+      return `${model.label} takes reference videos up to ${String(max)} s each; video ${i + 1} is ${seconds(lengths[i], max)} s.`;
+  }
+  if (refMin !== void 0) {
+    const i = lengths.findIndex((len) => len !== void 0 && len < refMin);
+    if (i >= 0)
+      return `${model.label} takes reference videos of at least ${String(refMin)} s each; video ${i + 1} is ${seconds(lengths[i], refMin)} s.`;
+  }
+  const source = knownLength(input.sourceVideo);
+  const sourceLimits = model.constraints.sourceVideoSeconds;
+  if (limits?.total !== void 0) {
+    const refSum = lengths.reduce((acc, len) => acc + (len ?? 0), 0);
+    const sum = refSum + (sourceLimits?.inReferenceTotal ? source ?? 0 : 0);
+    if (sum > limits.total)
+      return `${model.label} takes reference videos up to ${String(limits.total)} s combined; these add up to ${seconds(sum, limits.total)} s.`;
+  }
+  if (source === void 0) return void 0;
+  const sourceMin = effectiveMin(sourceLimits, input.taskType);
+  if (sourceLimits?.max !== void 0 && source > sourceLimits.max)
+    return `${model.label} takes a source video up to ${String(sourceLimits.max)} s; this one is ${seconds(source, sourceLimits.max)} s.`;
+  if (sourceMin !== void 0 && source < sourceMin)
+    return `${model.label} takes a source video of at least ${String(sourceMin)} s; this one is ${seconds(source, sourceMin)} s.`;
+  return void 0;
+}
 function resolveImageOptions(model, request, onUnsupported = "error") {
   const warnings = [];
   const c = model.constraints;
@@ -7540,6 +7634,21 @@ function resolveVideoOptions(model, request, onUnsupported = "error") {
       model: model.id
     });
   }
+  const lengthViolation = videoLengthViolation(model, {
+    referenceVideos: videos.map((v) => v.durationSeconds),
+    taskType: merged.taskType,
+    ...merged.sourceVideo?.durationSeconds !== void 0 && {
+      sourceVideo: merged.sourceVideo.durationSeconds
+    }
+  });
+  if (lengthViolation !== void 0) {
+    throw new ModelKitError({
+      code: "unsupported_option",
+      message: lengthViolation,
+      model: model.id,
+      retryable: false
+    });
+  }
   setOrDelete(merged, "referenceImages", images);
   setOrDelete(merged, "referenceVideos", videos);
   setOrDelete(merged, "referenceAudios", audios);
@@ -8090,7 +8199,7 @@ function createModelKit(config, adapters) {
       promptExpansion: _promptExpansion,
       mode: _mode
     } = req;
-    const seconds = duration ?? durationSeconds;
+    const seconds2 = duration ?? durationSeconds;
     const abortSignal = combineSignals(req.abortSignal, call.signal);
     const options = { model, prompt };
     if (call.maxRetries !== void 0) options.maxRetries = call.maxRetries;
@@ -8099,7 +8208,7 @@ function createModelKit(config, adapters) {
     if (ratio) options.aspectRatio = ratio;
     else if (aspectRatio !== void 0)
       pushIgnored(warnings, "aspectRatio", aspectRatio, model.modelId);
-    if (seconds !== void 0) options.duration = seconds;
+    if (seconds2 !== void 0) options.duration = seconds2;
     if (seed !== void 0) options.seed = seed;
     if (generateAudio2 !== void 0) options.generateAudio = generateAudio2;
     const frames = [
@@ -8146,8 +8255,8 @@ function createModelKit(config, adapters) {
         provider: model.provider,
         modality: "VIDEO",
         unit: "seconds",
-        quantity: seconds ?? 0,
-        ...seconds !== void 0 && { durationSeconds: seconds }
+        quantity: seconds2 ?? 0,
+        ...seconds2 !== void 0 && { durationSeconds: seconds2 }
       };
       settled = {
         video: { bytes: result.video.uint8Array, mime: result.video.mediaType },
@@ -8498,6 +8607,7 @@ var describe = (modelId) => createDefaultModelKit().describe(modelId);
   textUsageEvent,
   toGeneratedImage,
   validateInputSpec,
+  videoLengthViolation,
   withRetry,
   xaiVideoAdapter,
   ...require("ai")