@shop-os/modelkit 0.2.14 → 0.2.16

package/CHANGELOG.md

@@ -9,6 +9,24 @@ header in the release PR.
 
 ## [Unreleased]
 
+## [0.2.16] - Unreleased
+
+### Added
+- Gemini Omni 1.1 Flash video extension. The row declares `supports: ["videoExtension"]` and `constraints.extension: { segmentSeconds: 10, maxTotalSeconds: 40 }`. A `taskType: "extend"` request continues the clip by `durationSeconds` and the result is the **full cumulative clip** (probe 2026-09-24). The first extension may upload a source video (≤ 10 s, `sourceVideo`); follow-ups chain with `VideoRequest.previousInteractionId`, taken from the previous result's new `VideoResult.providerRef.interactionId`. The Interactions API rejects `previous_interaction_id` together with a video task, so chained calls carry only the prompt (no `generation_config`) and no aspect ratio.
+- `SupportedOption` / catalog `supports` gain `"videoExtension"`; `ModelConstraints.extension` is typed and validated.
+- A chained extension (`previousInteractionId` set) sends the prompt alone: `referenceImages`, `referenceVideos` and `firstFrame` are dropped with an `option_ignored` warning each, since the API rejects the id next to a video task.
+- `resolveVideoOptions` keeps `taskType: "extend"` on a `videoExtension` row (it is otherwise dropped as unsupported) and drops `previousInteractionId` with an `option_ignored` warning on rows without the capability.
+
+## [0.2.15] - Unreleased
+
+### Added
+- `MediaRef.durationSeconds`: the measured length of a video or audio ref. The kit never measures it; callers pass it when known.
+- `ReferenceLimits.videoSeconds` (`VideoSecondsLimits`: `min`, `max`, `total`, `editMin`): per-video and combined length limits for reference videos. `editMin` raises the per-video minimum when `taskType` is `edit` (Seedance 2.5: 4 s). Rows without it accept any length.
+- `ModelConstraints.sourceVideoSeconds` (`min`, `max`, `editMin`, `inReferenceTotal`): length limits for the source video. `inReferenceTotal` counts the source toward the combined reference limit where the provider sends it as a reference video (Seedance).
+- `videoLengthViolation(model, input)`: pure checker that returns the first length violation as a user-facing message, else `undefined`. Unknown lengths are skipped. Exported from the root and `/catalog` entries.
+- `resolveVideoOptions` rejects a reference or source video outside the row limits with a non-retryable `unsupported_option` error before any provider call. Videos dropped by the reference caps do not count.
+- Snapshot rows carry the provider limits: MiniMax H3 and H3 Max reference (2-15 s each, 15 s combined), Seedance 2.0 and 2.0 Fast (2-15 s each, 15 s combined), Seedance 2.5 (2-30 s each, 30 s combined, 4 s minimum for edit), Gemini Omni 1.0 and 1.1 (10 s), Kling O1 v2v source video (3-10.05 s).
+
 ## [0.2.14] - Unreleased
 
 - Keep AI SDK 6 and its compatible provider packages, including Bedrock and usage tracking.

package/dist/catalog.cjs

@@ -48,7 +48,8 @@ __export(catalog_entry_exports, {
   resolveImageOptions: () => resolveImageOptions,
   resolveOptions: () => resolveOptions,
   resolveVideoOptions: () => resolveVideoOptions,
-  sortCatalogRows: () => sortCatalogRows
+  sortCatalogRows: () => sortCatalogRows,
+  videoLengthViolation: () => videoLengthViolation
 });
 module.exports = __toCommonJS(catalog_entry_exports);
 
@@ -1416,7 +1417,8 @@ 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: {},
@@ -1442,8 +1444,16 @@ 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 },
@@ -1451,7 +1461,7 @@ 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 }
   },
@@ -1470,7 +1480,14 @@ 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"]
     },
@@ -1502,7 +1519,14 @@ 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"]
     },
@@ -1536,7 +1560,13 @@ 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"]
     },
@@ -1748,7 +1778,14 @@ 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: {
@@ -1779,7 +1816,14 @@ 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: {
@@ -1811,6 +1855,7 @@ 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" },
@@ -2147,6 +2192,7 @@ var SupportedOptionSchema = import_zod2.z.enum([
   "watermark",
   "safetyChecker",
   "taskType",
+  "videoExtension",
   "instrumental"
 ]);
 var UsageUnitSchema = import_zod2.z.enum([
@@ -2167,13 +2213,20 @@ 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(),
@@ -2186,14 +2239,21 @@ 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(),
+  extension: import_zod2.z.looseObject({ segmentSeconds: import_zod2.z.number(), maxTotalSeconds: import_zod2.z.number() }).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() });
@@ -2682,6 +2742,49 @@ 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 ${seconds(source, sourceMin)} s.`;
+  return void 0;
+}
 function resolveImageOptions(model, request, onUnsupported = "error") {
   const warnings = [];
   const c = model.constraints;
@@ -2867,9 +2970,25 @@ function resolveVideoOptions(model, request, onUnsupported = "error") {
       model: model.id
     });
   }
+  const lengthViolation = videoLengthViolation(model, {
+    referenceVideos: videos.map((v) => v.durationSeconds),
+    taskType: merged.taskType,
+    ...merged.sourceVideo?.durationSeconds !== void 0 && {
+      sourceVideo: merged.sourceVideo.durationSeconds
+    }
+  });
+  if (lengthViolation !== void 0) {
+    throw new ModelKitError({
+      code: "unsupported_option",
+      message: lengthViolation,
+      model: model.id,
+      retryable: false
+    });
+  }
   setOrDelete(merged, "referenceImages", images);
   setOrDelete(merged, "referenceVideos", videos);
   setOrDelete(merged, "referenceAudios", audios);
+  const keepExtend = merged.taskType === "extend" && (model.constraints.supports ?? []).includes("videoExtension");
   dropUnsupported(merged, model, warnings, [
     "seed",
     "negativePrompt",
@@ -2879,8 +2998,17 @@ function resolveVideoOptions(model, request, onUnsupported = "error") {
     "lastFrame",
     "watermark",
     "safetyChecker",
-    "taskType"
+    ...keepExtend ? [] : ["taskType"]
   ]);
+  if (merged.previousInteractionId !== void 0 && !keepExtend) {
+    warnings.push({
+      code: "option_ignored",
+      field: "previousInteractionId",
+      from: merged.previousInteractionId,
+      message: `${model.id} does not support previousInteractionId; ignored`
+    });
+    delete merged.previousInteractionId;
+  }
   return { request: merged, warnings };
 }
 function resolveAudioOptions(model, request, onUnsupported = "error") {