@shop-os/modelkit 0.2.14 → 0.2.16

package/dist/index.js

@@ -1373,7 +1373,8 @@ 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: {},
@@ -1399,8 +1400,16 @@ 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 },
-      supports: []
+      references: { images: 6, videos: 1, videoSeconds: { max: 10 } },
+      sourceVideoSeconds: { max: 10 },
+      // Extension (probe 2026-09-24, 360p): each `taskType: "extend"` call
+      // renders `durationSeconds` more and returns the FULL cumulative clip
+      // (3 s -> 6 s -> 9 s); the provider caps the clip at 40 s. A first
+      // extension can upload a <= 10 s source with task "extend"; later ones
+      // chain by `previousInteractionId` (the API rejects the id together
+      // with a video task, so those calls carry the prompt alone).
+      supports: ["videoExtension"],
+      extension: { segmentSeconds: 10, maxTotalSeconds: 40 }
     },
     defaults: {},
     usage: { ...VIDEO_USAGE },
@@ -1408,7 +1417,7 @@ var VIDEO_MODELS = [
     display: {
       provider: "google",
       logo: GOOGLE_LOGO2,
-      description: "Google Gemini Omni Flash 1.1 conversational video generation and editing; text, image, and up to 10-second video input, 3-10 second output at up to 4K and 24 FPS."
+      description: "Google Gemini Omni Flash 1.1 conversational video generation, editing and extension; text, image, and up to 10-second video input, 3-10 second output at up to 4K and 24 FPS, extendable to 40 seconds."
     },
     capabilities: { acceptsSourceVideo: true }
   },
@@ -1427,7 +1436,14 @@ 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"]
     },
@@ -1459,7 +1475,14 @@ 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"]
     },
@@ -1493,7 +1516,13 @@ 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"]
     },
@@ -1705,7 +1734,14 @@ 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: {
@@ -1736,7 +1772,14 @@ 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: {
@@ -1768,6 +1811,7 @@ 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" },
@@ -2107,6 +2151,7 @@ var SupportedOptionSchema = z2.enum([
   "watermark",
   "safetyChecker",
   "taskType",
+  "videoExtension",
   "instrumental"
 ]);
 var UsageUnitSchema = z2.enum([
@@ -2127,13 +2172,20 @@ var ProviderOptionValueSchema = z2.lazy(
   ])
 );
 var ProviderOptionsSchema = z2.record(z2.string(), z2.record(z2.string(), ProviderOptionValueSchema));
+var VideoSecondsLimitsSchema = z2.looseObject({
+  min: z2.number().optional(),
+  max: z2.number().optional(),
+  total: z2.number().optional(),
+  editMin: z2.number().optional()
+});
 var ReferenceLimitsSchema = z2.looseObject({
   images: z2.number().optional(),
   imagesWithVideo: z2.number().optional(),
   videos: z2.number().optional(),
   audios: z2.number().optional(),
   total: z2.number().optional(),
-  audioOnly: z2.boolean().optional()
+  audioOnly: z2.boolean().optional(),
+  videoSeconds: VideoSecondsLimitsSchema.optional()
 });
 var ModelConstraintsSchema = z2.looseObject({
   aspectRatios: z2.array(AspectRatioSchema).optional(),
@@ -2146,14 +2198,21 @@ var ModelConstraintsSchema = z2.looseObject({
   references: ReferenceLimitsSchema.optional(),
   requires: z2.array(RequiredInputSchema).optional(),
   supports: z2.array(SupportedOptionSchema).optional(),
-  ratioIgnoredWith: z2.array(z2.enum(["firstFrame", "sourceVideo"])).optional()
+  ratioIgnoredWith: z2.array(z2.enum(["firstFrame", "sourceVideo"])).optional(),
+  sourceVideoSeconds: VideoSecondsLimitsSchema.omit({ total: true }).extend({ inReferenceTotal: z2.boolean().optional() }).optional(),
+  extension: z2.looseObject({ segmentSeconds: z2.number(), maxTotalSeconds: z2.number() }).optional()
 });
 var MediaRefSchema = z2.union([
-  z2.looseObject({ url: z2.string(), label: z2.string().optional() }),
+  z2.looseObject({
+    url: z2.string(),
+    label: z2.string().optional(),
+    durationSeconds: z2.number().optional()
+  }),
   z2.looseObject({
     bytes: z2.instanceof(Uint8Array),
     mime: z2.string(),
-    label: z2.string().optional()
+    label: z2.string().optional(),
+    durationSeconds: z2.number().optional()
   })
 ]);
 var ImageSafetySettingSchema = z2.looseObject({ category: z2.string(), threshold: z2.string() });
@@ -4410,12 +4469,34 @@ async function generateOmniVideo(req, ctx, createGenAIClient) {
   const modelId = ctx.model.id;
   const providerModelId = ctx.model.providerModelId;
   const duration = req.durationSeconds ?? 10;
-  const images = req.referenceImages ?? [];
-  const videos = req.referenceVideos ?? [];
-  const task = req.sourceVideo ? "edit" : req.firstFrame ? "image_to_video" : images.length > 0 || videos.length > 0 ? "reference_to_video" : "text_to_video";
+  const extend = req.taskType === "extend";
+  const previousId = extend ? req.previousInteractionId : void 0;
+  const chained = previousId !== void 0;
+  for (const field of ["referenceImages", "referenceVideos", "firstFrame"]) {
+    const value = req[field];
+    if (!chained || value === void 0 || Array.isArray(value) && value.length === 0)
+      continue;
+    ctx.warnings.push({
+      code: "option_ignored",
+      field,
+      from: Array.isArray(value) ? value.length : "set",
+      message: `${modelId} chained extension sends the prompt alone; ${field} ignored`
+    });
+  }
+  const images = chained ? [] : req.referenceImages ?? [];
+  const videos = chained ? [] : req.referenceVideos ?? [];
+  const firstFrame = chained ? void 0 : req.firstFrame;
+  if (extend && !chained && req.sourceVideo === void 0) {
+    throw new ModelKitError({
+      code: "missing_input",
+      message: `${modelId} extend needs a source video or a previousInteractionId`,
+      model: modelId
+    });
+  }
+  const task = extend ? "extend" : req.sourceVideo ? "edit" : firstFrame ? "image_to_video" : images.length > 0 || videos.length > 0 ? "reference_to_video" : "text_to_video";
   const isOmniV1 = providerModelId === "gemini-omni-flash-preview";
   const responseFormat = { type: "video", delivery: "uri" };
-  if (req.sourceVideo === void 0 && req.aspectRatio !== void 0 && req.aspectRatio !== "adaptive") {
+  if (req.sourceVideo === void 0 && !extend && req.aspectRatio !== void 0 && req.aspectRatio !== "adaptive") {
     responseFormat.aspect_ratio = toOmniAspect(req.aspectRatio);
   }
   if (!isOmniV1) {
@@ -4447,18 +4528,26 @@ async function generateOmniVideo(req, ctx, createGenAIClient) {
   const cleanupUploads = async () => {
     for (const fileName of uploadedNames) await deleteGoogleFile(fileName, apiKey, ctx.fetch);
   };
-  const callCreate = (input) => client2.interactions.create({
-    model: providerModelId,
-    input,
-    response_format: responseFormat,
-    generation_config: { video_config: { task } },
-    store: true
-  });
+  const callCreate = (input) => client2.interactions.create(
+    previousId !== void 0 ? {
+      model: providerModelId,
+      input,
+      response_format: responseFormat,
+      store: true,
+      previous_interaction_id: previousId
+    } : {
+      model: providerModelId,
+      input,
+      response_format: responseFormat,
+      generation_config: { video_config: { task } },
+      store: true
+    }
+  );
   const createRetryOptions = mediaRetryOptions(ctx.call, ctx.signal);
   let interaction;
   try {
     const parts = [];
-    if (req.sourceVideo) {
+    if (req.sourceVideo && !chained) {
       const media = await resolveMedia(
         req.sourceVideo,
         ctx.fetch,
@@ -4481,11 +4570,11 @@ async function generateOmniVideo(req, ctx, createGenAIClient) {
         mime_type: media.mime
       });
     }
-    if (req.firstFrame) {
-      if (req.firstFrame.label !== void 0)
-        parts.push({ type: "text", text: req.firstFrame.label });
+    if (firstFrame) {
+      if (firstFrame.label !== void 0)
+        parts.push({ type: "text", text: firstFrame.label });
       const media = await resolveMedia(
-        req.firstFrame,
+        firstFrame,
         ctx.fetch,
         ctx.signal,
         "image/png",
@@ -4588,6 +4677,7 @@ async function generateOmniVideo(req, ctx, createGenAIClient) {
         return void 0;
       }, pollOptions);
       const video = extractOmniVideo(done, modelId);
+      const providerRef = { interactionId: done.id ?? jobId };
       if (video.data) {
         return {
           video: {
@@ -4595,14 +4685,16 @@ async function generateOmniVideo(req, ctx, createGenAIClient) {
             mime: video.mime_type ?? "video/mp4"
           },
           usage: usage2,
-          raw: done
+          raw: done,
+          providerRef
         };
       }
       if (video.uri)
         return {
           video: await downloadVideo(ctx, video.uri, apiKey, signal),
           usage: usage2,
-          raw: done
+          raw: done,
+          providerRef
         };
       throw classifyHttpError(
         void 0,
@@ -6540,8 +6632,8 @@ 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();
@@ -6606,9 +6698,9 @@ 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;
   }
@@ -7248,6 +7340,49 @@ 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 ${seconds(source, sourceMin)} s.`;
+  return void 0;
+}
 function resolveImageOptions(model, request, onUnsupported = "error") {
   const warnings = [];
   const c = model.constraints;
@@ -7433,9 +7568,25 @@ function resolveVideoOptions(model, request, onUnsupported = "error") {
       model: model.id
     });
   }
+  const lengthViolation = videoLengthViolation(model, {
+    referenceVideos: videos.map((v) => v.durationSeconds),
+    taskType: merged.taskType,
+    ...merged.sourceVideo?.durationSeconds !== void 0 && {
+      sourceVideo: merged.sourceVideo.durationSeconds
+    }
+  });
+  if (lengthViolation !== void 0) {
+    throw new ModelKitError({
+      code: "unsupported_option",
+      message: lengthViolation,
+      model: model.id,
+      retryable: false
+    });
+  }
   setOrDelete(merged, "referenceImages", images);
   setOrDelete(merged, "referenceVideos", videos);
   setOrDelete(merged, "referenceAudios", audios);
+  const keepExtend = merged.taskType === "extend" && (model.constraints.supports ?? []).includes("videoExtension");
   dropUnsupported(merged, model, warnings, [
     "seed",
     "negativePrompt",
@@ -7445,8 +7596,17 @@ function resolveVideoOptions(model, request, onUnsupported = "error") {
     "lastFrame",
     "watermark",
     "safetyChecker",
-    "taskType"
+    ...keepExtend ? [] : ["taskType"]
   ]);
+  if (merged.previousInteractionId !== void 0 && !keepExtend) {
+    warnings.push({
+      code: "option_ignored",
+      field: "previousInteractionId",
+      from: merged.previousInteractionId,
+      message: `${model.id} does not support previousInteractionId; ignored`
+    });
+    delete merged.previousInteractionId;
+  }
   return { request: merged, warnings };
 }
 function resolveAudioOptions(model, request, onUnsupported = "error") {
@@ -7990,7 +8150,7 @@ 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;
@@ -7999,7 +8159,7 @@ 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 = [
@@ -8046,8 +8206,8 @@ 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 },
@@ -8397,6 +8557,7 @@ export {
   textUsageEvent,
   toGeneratedImage,
   validateInputSpec,
+  videoLengthViolation,
   withRetry,
   xaiVideoAdapter
 };