@docyrus/animaguru 0.7.1 → 0.8.1

package/README.md

@@ -80,7 +80,7 @@ CLI 0.7.1 can select a cloud workspace for project listing, project creation, an
 animaguru workspaces list
 animaguru workspaces use team_0123456789abcdef0123456789abcdef
 animaguru projects list
-animaguru projects create --name "Shared cast" --style pixel
+animaguru projects create --name "Shared cast"
 animaguru credits
 animaguru workspaces use personal
 ```
@@ -89,10 +89,12 @@ Use a team ID returned by `workspaces list`. The choice is saved per server in t
 
 ## Agent workflow
 
+Remote projects are neutral containers. `projects create` has no `--style` flag. Choose a style when generating a sprite; local film setup keeps its separate style interview.
+
 ```sh
-animaguru projects create --name "Forest cast" --style pixel
+animaguru projects create --name "Forest cast"
 # Read the returned project.id and use it below.
-animaguru generate PROJECT_ID --name "Knight" --description "A blue knight with a red scarf" --actions idle,walk --yes
+animaguru generate PROJECT_ID --name "Knight" --description "A blue knight with a red scarf" --style pixel --actions idle,walk --yes
 animaguru jobs wait PROJECT_ID JOB_ID --timeout 600
 animaguru jobs list PROJECT_ID
 animaguru projects get PROJECT_ID
@@ -123,7 +125,7 @@ animaguru models PROJECT_ID --image-model gpt-image-2.5 --video-model pruna/p-vi
 # Either selection can be changed independently:
 animaguru models PROJECT_ID --video-model heygen/heygen-video-1
 # Or choose them when creating a project:
-animaguru projects create --name "Forest cast" --style pixel \
+animaguru projects create --name "Forest cast" \
   --image-model gpt-image-2.5 --video-model heygen/heygen-video-1
 ```
 
@@ -136,7 +138,7 @@ These flags are available in CLI 0.2.0 and later. Rerun the macOS installer to u
 CLI 0.4.0 adds standalone assets alongside the existing sprite commands. Use any project, or create an empty one first. `assets list` returns saved asset ids, image blob hashes for video references, and the models configured on that server.
 
 ```sh
-animaguru projects create --name "Adventure assets" --style hd-cartoon
+animaguru projects create --name "Adventure assets"
 animaguru assets list PROJECT_ID
 
 animaguru assets generate PROJECT_ID --type image --name "Forest" \
@@ -177,6 +179,27 @@ animaguru assets generate PROJECT_ID --type sfx --name "Magic spell" \
 
 Replace `--dry-run` with `--yes` to generate within your authorized credit budget. ElevenLabs accepts a voice ID in `--voice` and defaults to George when omitted. Use audio tags in the transcript; `--delivery` is only for Gemini and is rejected for ElevenLabs. SFX has a single model, `eleven_text_to_sound_v2`; `--seconds` accepts 0.5–30 (default 5), `--loop` requests a seamless loop, and `--prompt-influence` accepts 0–1 (default 0.3). Both return MP3. `catalog` includes `sfxModels` and `elevenLabsVoices`. The server needs `AI_PROVIDER_KEY_ELEVENLABS`; provider keys never belong in CLI credentials.
 
+CLI 0.8.0 adds MiniMax H3 Max Turbo and the H3 workflows. MiniMax H3 Max and H3 Max Turbo on fal.ai (`fal/minimax-h3-max`, `fal/minimax-h3-max-turbo`) also write videos from text and extend saved videos. Choose with `--workflow`:
+
+```sh
+# End on a pose, pin saved audio as the soundtrack, and keep a repeatable seed.
+animaguru assets generate PROJECT_ID --type video --model fal/minimax-h3-max-turbo \
+  --name "Hero lands" --prompt "The hero leaps and lands in a crouch" \
+  --reference START_IMAGE_SHA --end-reference END_IMAGE_SHA --soundtrack AUDIO_SHA \
+  --prompt-expansion balanced --seed 42 --resolution 1080p --dry-run
+# Write a scene from text alone.
+animaguru assets generate PROJECT_ID --type video --model fal/minimax-h3-max \
+  --workflow text-to-video --name "Harbor" --prompt "A foggy harbor at dawn" \
+  --aspect-ratio 21:9 --seconds 8 --resolution 768p --dry-run
+# Add six seconds to a saved video at 2K, guided by saved audio.
+animaguru assets generate PROJECT_ID --type video --model fal/minimax-h3-max \
+  --workflow extend-video --source VIDEO_SHA --name "Harbor, continued" \
+  --prompt "Audio 1 for the gulls. The fog lifts and a ship sails out" \
+  --audio-references AUDIO_SHA --seconds 6 --resolution 2k --dry-run
+```
+
+`--end-reference` can be used without `--reference`; the video then ends on that image. `--soundtrack` takes a music, speech or SFX asset's `file` SHA and replaces the generated sound; the video must be at least 2 seconds. Text-to-video takes `--aspect-ratio` 21:9, 16:9 (default), 4:3, 1:1, 3:4 or 9:16. Extensions take a video asset's SHA as `--source` (1.6–60 seconds, up to 50 MB), bill `--seconds` of new footage, offer 2K, and keep the source's shape unless `--aspect-ratio` crops it. `--extend-output continuation` returns only a 1.625-second overlap and the new footage. Extensions take up to three comma-separated `--audio-references` (2–15 seconds each, 15 seconds in total); refer to them in the prompt as Audio 1, Audio 2 and so on. `--prompt-expansion` is `disabled` (default), `balanced` or `quality`; for extensions, any value other than `disabled` turns expansion on. Each model's `videoProfiles` entry in `catalog` lists its workflows, resolutions and options. The server needs `AI_PROVIDER_KEY_FAL`.
+
 Images have a full background by default; `--transparent` requests a cutout. Gemini speech's `--prompt` is the verbatim transcript, and `--delivery` controls how it sounds without being spoken. Gemini speech supports both `gemini-3.8-flash-tts` and `gemini-3.8-flash-lite-tts`. Music uses Lyria. Google audio requires the server's `AI_PROVIDER_KEY_GOOGLE` secret; no provider keys are stored in the CLI.
 
 Preview a validated request and its estimated credits offline with `--dry-run`, without signing in or spending credits:

package/dist/animaguru.js

@@ -542,7 +542,7 @@ var init_dist = __esm({
 // cli/package.json
 var package_default = {
   name: "@docyrus/animaguru",
-  version: "0.7.1",
+  version: "0.8.1",
   description: "Agent-friendly AnimaGuru CLI built with CrustJS",
   type: "module",
   bin: {
@@ -6111,11 +6111,20 @@ var SPRITE_IMAGE_MODEL_IDS = SPRITE_IMAGE_MODELS.map((m) => m.id);
 function spriteImageModel(id2) {
   return SPRITE_IMAGE_MODELS.find((m) => m.id === id2) ?? SPRITE_IMAGE_MODELS[0];
 }
+var VIDEO_WORKFLOWS = ["image-to-video", "text-to-video", "extend-video"];
+var VIDEO_RESOLUTIONS = ["480p", "768p", "1080p", "2k"];
+var VIDEO_ASPECT_RATIOS = ["21:9", "16:9", "4:3", "1:1", "3:4", "9:16"];
+var PROMPT_EXPANSION_MODES = ["disabled", "balanced", "quality"];
+var EXTEND_OUTPUTS = ["extended", "continuation"];
+var SOUNDTRACK_MAX_BYTES = 15 * 1024 * 1024;
+var EXTEND_SOURCE_MAX_BYTES = 50 * 1024 * 1024;
+var MAX_AUDIO_REFERENCES = 3;
 var SPRITE_VIDEO_MODELS = [
   {
     id: "pruna/p-video-2-pro",
     label: "Pruna P-Video 2 Pro",
     provider: "pruna",
+    workflows: ["image-to-video"],
     resolutions: ["480p", "768p"],
     modes: ["cost", "speed", "quality"],
     lastFrame: true,
@@ -6126,6 +6135,7 @@ var SPRITE_VIDEO_MODELS = [
     id: "heygen/heygen-video-1",
     label: "HeyGen Video 1",
     provider: "heygen",
+    workflows: ["image-to-video"],
     resolutions: ["480p", "768p"],
     modes: ["cost"],
     lastFrame: false,
@@ -6136,13 +6146,40 @@ var SPRITE_VIDEO_MODELS = [
     id: "fal/minimax-h3-max",
     label: "MiniMax H3 Max (fal.ai)",
     provider: "fal",
-    endpoint: "minimax/h3-max/image-to-video",
+    workflows: VIDEO_WORKFLOWS,
+    endpoints: { "image-to-video": "minimax/h3-max/image-to-video", "text-to-video": "minimax/h3-max/text-to-video", "extend-video": "minimax/h3-max/extend-video" },
     resolutions: ["480p", "768p", "1080p"],
+    extendResolutions: VIDEO_RESOLUTIONS,
     modes: ["quality"],
     lastFrame: true,
-    // Regular rates, not the temporary promotion ending 2026-10-15.
-    // https://fal.ai/models/minimax/h3-max/image-to-video
-    usdPerSecond: { "480p": { quality: 0.05 }, "768p": { quality: 0.08 }, "1080p": { quality: 0.16 } },
+    endFrameOnly: true,
+    seed: true,
+    promptExpansion: PROMPT_EXPANSION_MODES,
+    audio: true,
+    // Regular rates, not the temporary promotion ending 2026-10-15; the same for every workflow,
+    // 2K extensions only. Extensions bill reference input beyond 4,096 tokens a request too
+    // ($0.02 per 1,000), which fal doesn't report back, so it isn't charged.
+    // https://fal.ai/models/minimax/h3-max/image-to-video, …/text-to-video, …/extend-video
+    usdPerSecond: { "480p": { quality: 0.05 }, "768p": { quality: 0.08 }, "1080p": { quality: 0.16 }, "2k": { quality: 0.32 } },
+    seconds: { min: 1, max: 15 }
+  },
+  {
+    id: "fal/minimax-h3-max-turbo",
+    label: "MiniMax H3 Max Turbo (fal.ai)",
+    provider: "fal",
+    workflows: VIDEO_WORKFLOWS,
+    endpoints: { "image-to-video": "minimax/h3-max-turbo/image-to-video", "text-to-video": "minimax/h3-max-turbo/text-to-video", "extend-video": "minimax/h3-max-turbo/extend-video" },
+    resolutions: ["480p", "768p", "1080p"],
+    extendResolutions: VIDEO_RESOLUTIONS,
+    modes: ["speed"],
+    lastFrame: true,
+    endFrameOnly: true,
+    seed: true,
+    promptExpansion: PROMPT_EXPANSION_MODES,
+    audio: true,
+    // Regular rates, not the temporary promotion ending 2026-10-15; extensions bill only the new footage.
+    // https://fal.ai/models/minimax/h3-max-turbo/image-to-video, …/text-to-video, …/extend-video
+    usdPerSecond: { "480p": { speed: 0.025 }, "768p": { speed: 0.04 }, "1080p": { speed: 0.08 }, "2k": { speed: 0.16 } },
     seconds: { min: 1, max: 15 }
   }
 ];
@@ -6151,6 +6188,9 @@ var DEFAULT_SPRITE_VIDEO_MODEL = "pruna/p-video-2-pro";
 function spriteVideoModel(id2) {
   return SPRITE_VIDEO_MODELS.find((m) => m.id === id2) ?? SPRITE_VIDEO_MODELS[0];
 }
+function videoResolutions(model, workflow = "image-to-video") {
+  return workflow === "extend-video" ? model.extendResolutions ?? model.resolutions : model.resolutions;
+}
 function spriteVideoCostUsd(model, p) {
   const byMode = model.usdPerSecond[p.resolution] ?? model.usdPerSecond[model.resolutions[0]];
   const perSecond = byMode[p.mode] ?? byMode[model.modes[0]] ?? 0;
@@ -26811,7 +26851,7 @@ var VIDEO_WORKFLOW_IDS = [
   "ambient-loop",
   "visual-essay"
 ];
-var VIDEO_WORKFLOWS = VIDEO_WORKFLOW_IDS.map((id2, index) => ({
+var VIDEO_WORKFLOWS2 = VIDEO_WORKFLOW_IDS.map((id2, index) => ({
   id: id2,
   category: index < 8 ? "advertisement" : "general-video",
   name: animation_styles_default.workflows[id2].name,
@@ -26840,10 +26880,10 @@ function videoTemplateCatalog() {
       name: animation_styles_default.categories[id2].name,
       description: animation_styles_default.categories[id2].description,
       templates: VIDEO_TEMPLATES.filter((template) => template.categories.some((category) => category === id2)),
-      workflows: VIDEO_WORKFLOWS.filter((workflow) => workflow.category === id2)
+      workflows: VIDEO_WORKFLOWS2.filter((workflow) => workflow.category === id2)
     })),
     templates: VIDEO_TEMPLATES,
-    workflows: VIDEO_WORKFLOWS
+    workflows: VIDEO_WORKFLOWS2
   };
 }
 
@@ -27076,14 +27116,59 @@ var isElevenLabsSpeech = (model) => ELEVENLABS_SPEECH_MODEL_IDS.includes(model);
 var MUSIC_MODELS = [{ id: "lyria-3.5", label: "Lyria 3.5" }];
 var SPEECH_VOICES = ["Kore", "Puck", "Charon", "Fenrir", "Aoede", "Leda", "Orus", "Zephyr"];
 var base = { name: external_exports.string().trim().min(1).max(80), prompt: external_exports.string().trim().min(3).max(4e3) };
+var blob = external_exports.string().regex(/^[a-f0-9]{64}$/);
+var videoAsset = external_exports.object({
+  ...base,
+  type: external_exports.literal("video"),
+  model: external_exports.enum(SPRITE_VIDEO_MODEL_IDS).default(DEFAULT_SPRITE_VIDEO_MODEL),
+  workflow: external_exports.enum(VIDEO_WORKFLOWS).default("image-to-video"),
+  /** First frame. */
+  reference: blob.optional(),
+  /** Last frame. */
+  endReference: blob.optional(),
+  /** The saved clip to extend. */
+  source: blob.optional(),
+  /** Saved audio pinned as the soundtrack (at least two seconds of video). */
+  soundtrack: blob.optional(),
+  /** Saved audio guiding an extension's new sound; name each clip's role in the prompt. */
+  audioReferences: external_exports.array(blob).max(MAX_AUDIO_REFERENCES).default([]),
+  seconds: external_exports.number().int().min(1).max(15).default(5),
+  resolution: external_exports.enum(VIDEO_RESOLUTIONS).default("480p"),
+  mode: external_exports.enum(["cost", "speed", "quality"]).default("cost"),
+  /** A clip written from text (default 16:9), or an extension cropped to a new canvas ("auto" keeps the source's). */
+  aspectRatio: external_exports.enum(["auto", ...VIDEO_ASPECT_RATIOS]).optional(),
+  promptExpansion: external_exports.enum(PROMPT_EXPANSION_MODES).default("disabled"),
+  seed: external_exports.number().int().min(0).max(2 ** 32 - 1).optional(),
+  /** An extension returns the whole clip, or only the new footage after a short overlap. */
+  extendOutput: external_exports.enum(EXTEND_OUTPUTS).default("extended")
+}).superRefine((p, ctx) => {
+  const model = spriteVideoModel(p.model);
+  const issue2 = (path, message) => ctx.addIssue({ code: "custom", message, path: [path] });
+  if (!model.workflows.includes(p.workflow)) return issue2("workflow", "Choose a way of making video supported by the video model.");
+  const extend2 = p.workflow === "extend-video";
+  if (p.seconds < model.seconds.min || p.seconds > model.seconds.max) issue2("seconds", "Choose a duration supported by the video model.");
+  if (!videoResolutions(model, p.workflow).includes(p.resolution)) issue2("resolution", "Choose a resolution supported by the video model.");
+  if (!model.modes.includes(p.mode)) issue2("mode", "Choose a mode supported by the video model.");
+  if (p.workflow === "image-to-video") {
+    if (!p.reference && !(p.endReference && model.endFrameOnly)) issue2("reference", "Choose a starting image.");
+    if (p.endReference && !model.lastFrame) issue2("endReference", "This video model can't end on a chosen image.");
+  } else {
+    if (p.reference) issue2("reference", "Only image-to-video starts from an image.");
+    if (p.endReference) issue2("endReference", "Only image-to-video ends on an image.");
+  }
+  if (extend2 !== Boolean(p.source)) issue2("source", extend2 ? "Choose a saved video to extend." : "Only an extension starts from a saved video.");
+  if (p.aspectRatio && p.workflow === "image-to-video") issue2("aspectRatio", "A video made from an image keeps the image's shape.");
+  if (p.aspectRatio === "auto" && p.workflow === "text-to-video") issue2("aspectRatio", "Choose an aspect ratio for a video written from text.");
+  if (p.soundtrack && (!model.audio || extend2)) issue2("soundtrack", extend2 ? "An extension keeps its source's soundtrack; add audio references instead." : "This video model can't use a soundtrack.");
+  if (p.soundtrack && p.seconds < 2) issue2("seconds", "A video with a soundtrack must be at least 2 seconds long.");
+  if (p.audioReferences.length && (!model.audio || !extend2)) issue2("audioReferences", "Only an extension takes audio references.");
+  if (p.promptExpansion !== "disabled" && !model.promptExpansion?.includes(p.promptExpansion)) issue2("promptExpansion", "This video model doesn't rewrite prompts.");
+  if (p.seed !== void 0 && !model.seed) issue2("seed", "This video model doesn't take a seed.");
+  if (p.extendOutput !== "extended" && !extend2) issue2("extendOutput", "Only an extension can return the new footage alone.");
+});
 var assetRequest = external_exports.discriminatedUnion("type", [
   external_exports.object({ ...base, type: external_exports.literal("image"), model: external_exports.enum(SPRITE_IMAGE_MODEL_IDS).default(DEFAULT_SPRITE_IMAGE_MODEL), aspectRatio: external_exports.enum(["1:1", "3:2", "2:3"]).default("1:1"), transparent: external_exports.boolean().default(false) }),
-  external_exports.object({ ...base, type: external_exports.literal("video"), model: external_exports.enum(SPRITE_VIDEO_MODEL_IDS).default(DEFAULT_SPRITE_VIDEO_MODEL), reference: external_exports.string().regex(/^[a-f0-9]{64}$/), seconds: external_exports.number().int().min(1).max(15).default(5), resolution: external_exports.enum(["480p", "768p", "1080p"]).default("480p"), mode: external_exports.enum(["cost", "speed", "quality"]).default("cost") }).superRefine((p, ctx) => {
-    const model = spriteVideoModel(p.model);
-    if (p.seconds < model.seconds.min || p.seconds > model.seconds.max) ctx.addIssue({ code: "custom", message: "Choose a duration supported by the video model.", path: ["seconds"] });
-    if (!model.resolutions.includes(p.resolution)) ctx.addIssue({ code: "custom", message: "Choose a resolution supported by the video model.", path: ["resolution"] });
-    if (!model.modes.includes(p.mode)) ctx.addIssue({ code: "custom", message: "Choose a mode supported by the video model.", path: ["mode"] });
-  }),
+  videoAsset,
   external_exports.object({ ...base, type: external_exports.literal("music"), model: external_exports.literal("lyria-3.5").default("lyria-3.5") }),
   external_exports.object({ ...base, type: external_exports.literal("speech"), model: external_exports.enum(["gemini-3.8-flash-tts", "gemini-3.8-flash-lite-tts", ...ELEVENLABS_SPEECH_MODEL_IDS]).default("gemini-3.8-flash-lite-tts"), voice: external_exports.string().trim().max(80).default(""), delivery: external_exports.string().trim().max(600).default("") }).superRefine((p, ctx) => {
     if (p.voice && (isElevenLabsSpeech(p.model) ? !/^[a-zA-Z0-9]{20}$/.test(p.voice) : !SPEECH_VOICES.includes(p.voice))) ctx.addIssue({ code: "custom", message: "Choose a voice supported by the speech provider.", path: ["voice"] });
@@ -27310,25 +27395,46 @@ async function submitVideo(client, options) {
 // cli/src/assets.ts
 import { readFile as readFile7, writeFile as writeFile7 } from "node:fs/promises";
 import { resolve as resolve8 } from "node:path";
-var extras = { image: ["aspect-ratio", "transparent"], video: ["reference", "seconds", "resolution", "mode"], music: [], speech: ["voice", "delivery"], sfx: ["seconds", "loop", "prompt-influence"] };
+var extras = { image: ["aspect-ratio", "transparent"], video: ["workflow", "reference", "end-reference", "source", "soundtrack", "audio-references", "seconds", "resolution", "mode", "aspect-ratio", "prompt-expansion", "seed", "extend-output"], music: [], speech: ["voice", "delivery"], sfx: ["seconds", "loop", "prompt-influence"] };
+function parseAsset(input2) {
+  const parsed = assetRequest.safeParse(input2);
+  if (parsed.success) return parsed.data;
+  throw new Error(parsed.error.issues.map((issue2) => `${issue2.path.length ? `${issue2.path.join(".")}: ` : ""}${issue2.message}`).join("\n"));
+}
 function assetFromFlags(flags) {
   for (const name of Object.values(extras).flat()) {
     const value = flags[name];
     if (value !== void 0 && value !== false && !extras[flags.type]?.includes(name)) throw new Error(`--${name} is not an option for ${flags.type} assets.`);
   }
   const base2 = { type: flags.type, name: flags.name, prompt: flags.prompt, model: flags.model };
-  if (flags.type === "image") return assetRequest.parse({ ...base2, aspectRatio: flags["aspect-ratio"], transparent: flags.transparent });
+  if (flags.type === "image") return parseAsset({ ...base2, aspectRatio: flags["aspect-ratio"], transparent: flags.transparent });
   if (flags.type === "video") {
     const model = spriteVideoModel(flags.model);
-    return assetRequest.parse({ ...base2, reference: flags.reference, seconds: flags.seconds ?? Math.max(5, model.seconds.min), resolution: flags.resolution ?? model.resolutions[0], mode: flags.mode ?? model.modes[0] });
+    const workflow = flags.workflow ?? "image-to-video";
+    return parseAsset({
+      ...base2,
+      workflow: flags.workflow,
+      reference: flags.reference,
+      endReference: flags["end-reference"],
+      source: flags.source,
+      soundtrack: flags.soundtrack,
+      audioReferences: flags["audio-references"]?.split(",").map((sha) => sha.trim()).filter(Boolean),
+      seconds: flags.seconds ?? Math.max(5, model.seconds.min),
+      resolution: flags.resolution ?? videoResolutions(model, workflow)[0],
+      mode: flags.mode ?? model.modes[0],
+      aspectRatio: flags["aspect-ratio"],
+      promptExpansion: flags["prompt-expansion"],
+      seed: flags.seed,
+      extendOutput: flags["extend-output"]
+    });
   }
-  if (flags.type === "sfx") return assetRequest.parse({ ...base2, seconds: flags.seconds, loop: flags.loop, promptInfluence: flags["prompt-influence"] });
-  return assetRequest.parse({ ...base2, ...flags.type === "speech" ? { voice: flags.voice, delivery: flags.delivery } : {} });
+  if (flags.type === "sfx") return parseAsset({ ...base2, seconds: flags.seconds, loop: flags.loop, promptInfluence: flags["prompt-influence"] });
+  return parseAsset({ ...base2, ...flags.type === "speech" ? { voice: flags.voice, delivery: flags.delivery } : {} });
 }
 async function assetFromFile(file2, model) {
   const input2 = JSON.parse(await readFile7(file2, "utf8"));
   if (!input2 || typeof input2 !== "object" || Array.isArray(input2)) throw new Error("The asset file must contain a JSON object.");
-  return assetRequest.parse({ ...input2, ...model ? { model } : {} });
+  return parseAsset({ ...input2, ...model ? { model } : {} });
 }
 async function submitAsset(client, project, body, options) {
   if (options["dry-run"]) return { dryRun: true, request: body, estimatedCredits: assetEstimate(body) };
@@ -27457,10 +27563,10 @@ Confirm code: ${device.user_code}`);
   }))).add(defineCommand("catalog", { description: "List styles, kinds, actions, asset types, models, video settings and speech voices" }, (command) => command.action(({ stdout }) => out(stdout, { styles: SPRITE_STYLES, kinds: SPRITE_KINDS, actions: ALL_SPRITE_ACTIONS, imageModels: SPRITE_IMAGE_MODEL_IDS, videoModels: SPRITE_VIDEO_MODEL_IDS, assetTypes: ASSET_TYPES, musicModels: MUSIC_MODELS.map((m) => m.id), speechModels: SPEECH_MODELS.map((m) => m.id), sfxModels: SFX_MODELS.map((m) => m.id), elevenLabsVoices: ELEVENLABS_VOICES, voices: SPEECH_VOICES, videoProfiles: SPRITE_VIDEO_MODELS })))).command("projects", (projects) => projects.add(defineCommand("list", { description: "List projects in the selected workspace" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).action(async ({ flags, stdout, signal }) => {
     const client = new Client(flags.url, signal);
     out(stdout, await client.request(`/api/v1/projects${await workspaceQuery(client)}`));
-  }))).add(defineCommand("create", { description: "Create an empty sprite project; generate artwork with jobs submit" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).flags(...modelFlags).flags({ name: "name", type: "string", required: true }, { name: "style", type: "string", required: true, choices: SPRITE_STYLES }).action(async ({ flags, stdout, signal }) => {
+  }))).add(defineCommand("create", { description: "Create an empty sprite project; generate artwork with jobs submit" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).flags(...modelFlags).flags({ name: "name", type: "string", required: true }).action(async ({ flags, stdout, signal }) => {
     const client = new Client(flags.url, signal);
     const selected = await selectedWorkspace(client.origin);
-    out(stdout, await client.request("/api/v1/sprites", { method: "POST", body: { owner: selected, name: flags.name, style: flags.style, ...selectedModels(flags) } }));
+    out(stdout, await client.request("/api/v1/sprites", { method: "POST", body: { owner: selected, name: flags.name, ...selectedModels(flags) } }));
   }))).add(defineCommand("get", { description: "Read project, subjects, animations, estimates and job state" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).args(id).action(async ({ args, flags, stdout, signal }) => out(stdout, await new Client(flags.url, signal).request(projectPath(args.id)))))).add(defineCommand("rename", { description: "Rename a project" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).args(id).flags({ name: "name", type: "string", required: true }).action(async ({ args, flags, stdout, signal }) => out(stdout, await new Client(flags.url, signal).request(`/api/v1/projects/${encodeURIComponent(args.id)}`, { method: "PATCH", body: { name: flags.name } }))))).add(defineCommand("delete", { description: "Delete a project; requires --yes" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).args(id).flags({ name: "yes", type: "boolean", required: true }).action(async ({ args, flags, stdout, signal }) => {
     if (!flags.yes) throw new Error("Pass --yes to delete this project.");
     out(stdout, await new Client(flags.url, signal).request(`/api/v1/projects/${encodeURIComponent(args.id)}`, { method: "DELETE" }));
@@ -27469,12 +27575,20 @@ Confirm code: ${device.user_code}`);
     { name: "name", type: "string", required: true },
     { name: "prompt", type: "string", required: true, description: "Description to generate, or verbatim transcript for speech" },
     { name: "model", type: "string", choices: assetModelIds, description: "Model for the chosen asset type" },
-    { name: "aspect-ratio", type: "string", choices: ["1:1", "3:2", "2:3"], description: "Image aspect ratio (default 1:1)" },
+    { name: "aspect-ratio", type: "string", choices: [.../* @__PURE__ */ new Set(["1:1", "3:2", "2:3", "auto", ...VIDEO_ASPECT_RATIOS])], description: "Image: 1:1 (default), 3:2 or 2:3. Video from text: 21:9\u20139:16 (default 16:9). Extension: auto (default, the source's) or a ratio to crop to" },
     { name: "transparent", type: "boolean", description: "Image: transparent background" },
+    { name: "workflow", type: "string", choices: VIDEO_WORKFLOWS, description: "Video: image-to-video (default), text-to-video or extend-video, as the model's videoProfiles allow" },
     { name: "reference", type: "string", description: "Video: starting image blob SHA from this project's assets or sprites" },
-    { name: "seconds", type: "number", description: "Video or SFX duration in seconds (default 5); SFX supports 0.5\u201330" },
-    { name: "resolution", type: "string", choices: ["480p", "768p", "1080p"], description: "Video resolution supported by the selected model" },
+    { name: "end-reference", type: "string", description: "Video: ending image blob SHA; models with endFrameOnly accept it without --reference" },
+    { name: "source", type: "string", description: "Extension: blob SHA of a video asset in this project to extend" },
+    { name: "soundtrack", type: "string", description: "Video from an image or text: blob SHA of a music, speech or SFX asset pinned as the soundtrack (2 s or longer)" },
+    { name: "audio-references", type: "string", description: "Extension: up to 3 comma-separated audio asset blob SHAs (2\u201315 s each, 15 s total) guiding the new sound; refer to them as Audio 1, Audio 2\u2026 in the prompt" },
+    { name: "seconds", type: "number", description: "Video or SFX duration in seconds (default 5); extensions add this many seconds; SFX supports 0.5\u201330" },
+    { name: "resolution", type: "string", choices: VIDEO_RESOLUTIONS, description: "Video resolution supported by the selected model and workflow (2k for extensions)" },
     { name: "mode", type: "string", choices: ["cost", "speed", "quality"], description: "Video generation mode supported by the selected model" },
+    { name: "prompt-expansion", type: "string", choices: PROMPT_EXPANSION_MODES, description: "Video: how much the model may rewrite the prompt (default disabled); extensions treat any other value as on" },
+    { name: "seed", type: "number", description: "Video: seed for repeatable results, where the model takes one" },
+    { name: "extend-output", type: "string", choices: EXTEND_OUTPUTS, description: "Extension: extended (default, source plus new footage) or continuation (a 1.625 s overlap, then the new footage)" },
     { name: "voice", type: "string", description: "Gemini voice name or ElevenLabs voice ID (defaults: Kore / George)" },
     { name: "delivery", type: "string", description: "Gemini speech delivery instructions; ElevenLabs uses audio tags in the transcript" },
     { name: "loop", type: "boolean", description: "SFX: create a seamless loop" },
@@ -27502,9 +27616,9 @@ Confirm code: ${device.user_code}`);
     const body = selectedModels(flags);
     if (!Object.keys(body).length) throw new Error("Pass --image-model or --video-model.");
     out(stdout, await new Client(flags.url, signal).request(`${projectPath(args.id)}/models`, { method: "PUT", body }));
-  }))).add(defineCommand("generate", { description: "Draw a subject; --yes authorizes generation costs" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).args(id).flags(...modelFlags).flags({ name: "name", type: "string", required: true }, { name: "description", type: "string", required: true }, { name: "kind", type: "string", choices: SPRITE_KINDS, default: "character" }, { name: "actions", type: "string", description: "Comma-separated built-in actions to animate after drawing" }, { name: "yes", type: "boolean", required: true }).action(async ({ args, flags, stdout, signal }) => {
+  }))).add(defineCommand("generate", { description: "Draw a subject; --yes authorizes generation costs" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" }, description: "Server origin" }).args(id).flags(...modelFlags).flags({ name: "name", type: "string", required: true }, { name: "description", type: "string", required: true }, { name: "style", type: "string", choices: SPRITE_STYLES, description: "Artwork style for this sprite" }, { name: "kind", type: "string", choices: SPRITE_KINDS, default: "character" }, { name: "actions", type: "string", description: "Comma-separated built-in actions to animate after drawing" }, { name: "yes", type: "boolean", required: true }).action(async ({ args, flags, stdout, signal }) => {
     if (!flags.yes) throw new Error("Pass --yes to authorize spending credits.");
-    const body = spriteJobBody.parse({ kind: "character", name: flags.name, description: flags.description, subjectKind: flags.kind, actions: actions(flags.actions), ...selectedModels(flags) });
+    const body = spriteJobBody.parse({ kind: "character", name: flags.name, description: flags.description, ...flags.style ? { style: flags.style } : {}, subjectKind: flags.kind, actions: actions(flags.actions), ...selectedModels(flags) });
     out(stdout, await new Client(flags.url, signal).request(`${projectPath(args.id)}/jobs`, { method: "POST", body }));
   }))).add(defineCommand("schema", { description: "Print the Crust command schema for agent discovery" }, (command) => command.action(async ({ stdout }) => out(stdout, await createCli().snapshot())))).command("files", (files) => files.add(defineCommand("import", { description: "Import a PNG, JPEG or WebP reference; --yes authorizes redraw costs when configured" }, (command) => command.flags({ name: "url", type: "string", default: "https://animaguru.com", env: { name: "ANIMAGURU_URL" } }).args(id).flags(...modelFlags).flags({ name: "file", type: "string", required: true }, { name: "name", type: "string", required: true }, { name: "description", type: "string" }, { name: "yes", type: "boolean", required: true }).action(async ({ args, flags, stdout, signal }) => {
     if (!flags.yes) throw new Error("Pass --yes to authorize reference redraw costs.");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@docyrus/animaguru",
-  "version": "0.7.1",
+  "version": "0.8.1",
   "description": "Agent-friendly AnimaGuru CLI built with CrustJS",
   "type": "module",
   "bin": {

package/skills/animaguru/SKILL.md

@@ -24,9 +24,9 @@ Share the [animation-style gallery](https://animaguru.com/animation-styles), or
 Reuse the user's chosen project. Otherwise inspect `animaguru projects list` before creating one. Read `animaguru projects get PROJECT_ID` for subjects, character identifiers, generation estimates, and current job state. Use identifiers returned by the service rather than guessing slugs.
 
 ```sh
-animaguru projects create --name "Forest cast" --style pixel
+animaguru projects create --name "Forest cast"
 animaguru generate PROJECT_ID --name "Knight" \
-  --description "A blue knight with a red scarf" --actions idle,walk --yes
+  --description "A blue knight with a red scarf" --style pixel --actions idle,walk --yes
 ```
 
 Read the project ID from `projects create` and job IDs from submission responses. Supported actions depend on the subject kind. Use `--kind` for a different subject kind, based on the catalog.
@@ -63,7 +63,7 @@ Import reference artwork with `animaguru files import PROJECT_ID --file knight.p
 
 ## Standalone images, video, music and speech
 
-CLI 0.4.0 adds `assets generate`, `assets submit`, `assets list`, and `assets download`. Use `assets list PROJECT_ID` to discover saved assets and configured provider models. New asset projects can be created with `projects create --name NAME --style hd-cartoon`; that style does not constrain standalone prompts.
+CLI 0.4.0 adds `assets generate`, `assets submit`, `assets list`, and `assets download`. Use `assets list PROJECT_ID` to discover saved assets and configured provider models. Create neutral asset projects with `projects create --name NAME`. Projects have no art style; choose style when generating an individual sprite.
 
 ```sh
 animaguru assets generate PROJECT_ID --type image --name "Forest" \
@@ -77,7 +77,7 @@ animaguru assets generate PROJECT_ID --type speech --name "Welcome" \
   --prompt "Welcome, traveler." --voice Kore --delivery "Warm and welcoming" --yes
 ```
 
-Use `--model` to select a model for any asset type; discover the choices with `catalog` and the server's configured subset with `assets list`. Asset defaults are per type, independently of sprite project defaults. Image backgrounds are retained unless `--transparent` is supplied. Videos require an image asset's `file` SHA from `assets list`, or a character's `art` SHA from `projects get`, in the same project. Validate video options against the selected model's `videoProfiles` in `catalog`; omitted video settings use five seconds and that provider's first resolution/mode. For Gemini speech, `--prompt` is spoken verbatim and `--delivery` is a separate instruction. Music uses Lyria; the Gemini TTS models are for speech.
+Use `--model` to select a model for any asset type; discover the choices with `catalog` and the server's configured subset with `assets list`. Asset defaults are per type, independently of sprite project defaults. Image backgrounds are retained unless `--transparent` is supplied. Videos require an image asset's `file` SHA from `assets list`, or a character's `art` SHA from `projects get`, in the same project. Validate video options against the selected model's `videoProfiles` in `catalog`; omitted video settings use five seconds and that provider's first resolution/mode. MiniMax H3 Max and H3 Max Turbo (`fal/minimax-h3-max`, `fal/minimax-h3-max-turbo`) also take `--workflow text-to-video` (with `--aspect-ratio`) and `--workflow extend-video` (with `--source VIDEO_SHA`, 2K resolution, `--extend-output`, and up to three comma-separated `--audio-references`). From images, they accept `--end-reference` with or without `--reference` and a `--soundtrack AUDIO_SHA`. All workflows take `--prompt-expansion` and `--seed`. These need CLI 0.8.0 or newer. For Gemini speech, `--prompt` is spoken verbatim and `--delivery` is a separate instruction. Music uses Lyria; the Gemini TTS models are for speech.
 
 For ElevenLabs speech, choose `eleven_v4` or `eleven_v4_turbo`, pass an ElevenLabs voice ID with `--voice` (George is the default), and put audio tags in `--prompt` rather than using `--delivery`. For sound effects, use `--type sfx`; the only model is `eleven_text_to_sound_v2`. SFX supports `--seconds` from 0.5 to 30 (default 5), `--loop`, and `--prompt-influence` from 0 to 1 (default 0.3). These additions require CLI 0.5.0 or newer; check `catalog` before using them with an installed CLI.
 

package/skills/animaguru-cutout-animation/SKILL.md

@@ -24,7 +24,7 @@ Read [visual and motion guidance](references/visual-style.md) when designing sce
 
 Use image tools for bitmap artwork, cutouts and textures, and PixiJS for composition, typography, masks and motion. Treat people, products, objects, landscapes and abstract forms as equally valid cutout subjects. Choose coherent edge treatment, material, lighting and movement so the film feels intentionally assembled.
 
-Use the user's selected generation models and budget. Otherwise inspect the current AnimaGuru catalog and configured providers to select models suited to the assets and motion. MiniMax H3 Max (`fal/minimax-h3-max`) is one option for animated photographic assets when available; cutout motion can also be built directly in PixiJS from still layers. Validate supported settings before submission.
+Use the user's selected generation models and budget. Otherwise inspect the current AnimaGuru catalog and configured providers to select models suited to the assets and motion. MiniMax H3 Max (`fal/minimax-h3-max`) or its faster, cheaper Turbo (`fal/minimax-h3-max-turbo`) is one option for animated photographic assets when available; cutout motion can also be built directly in PixiJS from still layers. Validate supported settings before submission.
 
 Deliver the film described in the brief with consistent cutout visuals and intentional animation. Keep story development responsive to the project's purpose rather than borrowing the narrative of an example film.
 

package/templates/video/scripts/workspace-plugin.mjs

@@ -1,4 +1,4 @@
-import { readFile, cp, mkdir } from "node:fs/promises";
+import { readFile, cp, mkdir, stat } from "node:fs/promises";
 import { createReadStream } from "node:fs";
 import path from "node:path";
 import { listAnimations, projectContext, publicFile, readBranding } from "./project-context.mjs";
@@ -50,9 +50,19 @@ void mountPlayer({config,Film,chapters,branding:${JSON.stringify(context.brandin
           }
           const file = await publicFile(context, match[2]);
           const type = ({svg:"image/svg+xml",png:"image/png",jpg:"image/jpeg",jpeg:"image/jpeg",webp:"image/webp",mp3:"audio/mpeg",wav:"audio/wav",m4a:"audio/mp4",woff2:"font/woff2",woff:"font/woff",ttf:"font/ttf",mp4:"video/mp4",webm:"video/webm"})[file.split(".").at(-1).toLowerCase()] ?? "application/octet-stream";
-          response.writeHead(200, { "Content-Type": type, "Cache-Control": "no-store" });
+          // Media elements seek with byte ranges; without them Chrome cannot load or seek video.
+          const { size } = await stat(file);
+          const range = /^bytes=(\d*)-(\d*)$/.exec(request.headers.range ?? "");
+          let start = 0, end = size - 1;
+          if (range && (range[1] || range[2])) {
+            start = range[1] ? Number(range[1]) : Math.max(0, size - Number(range[2]));
+            if (range[1] && range[2]) end = Math.min(Number(range[2]), size - 1);
+            if (start > end) { response.writeHead(416, { "Content-Range": `bytes */${size}` }).end(); return; }
+          }
+          const partial = Boolean(range && (range[1] || range[2]));
+          response.writeHead(partial ? 206 : 200, { "Content-Type": type, "Cache-Control": "no-store", "Accept-Ranges": "bytes", "Content-Length": String(end - start + 1), ...(partial ? { "Content-Range": `bytes ${start}-${end}/${size}` } : {}) });
           if (request.method === "HEAD") { response.end(); return; }
-          const stream = createReadStream(file); response.once("close", () => stream.destroy()); stream.pipe(response);
+          const stream = createReadStream(file, { start, end }); response.once("close", () => stream.destroy()); stream.pipe(response);
         })().catch((error) => { if (!response.headersSent) response.writeHead(404).end(error.message); });
       });
     },

package/templates/video/src/player.ts

@@ -110,10 +110,11 @@ export async function mountPlayer({ config, Film, chapters, branding, exportEndp
       if (request !== playbackRequest) { audio?.pause(); return; }
       last = performance.now(); playing = true; update();
     }
-    function toggleSound() {
+    function setMuted(value: boolean) {
       if (!audio) return;
-      muted = !muted; audio.muted = muted; update();
+      muted = value; audio.muted = muted; update();
     }
+    function toggleSound() { setMuted(!muted); }
     function setCaptions(value: boolean) { film.captions = value; void render(time); update(); }
     async function fullscreen() {
       try { if (document.fullscreenElement) await document.exitFullscreen(); else await theater.requestFullscreen(); }
@@ -206,12 +207,12 @@ export async function mountPlayer({ config, Film, chapters, branding, exportEndp
     }
     await render(time); update();
     const api = {
-      ready: true, width: config.width, height: config.height, duration: config.duration, fps: config.fps, language: config.language, canvas: app.canvas,
+      ready: true, width: config.width, height: config.height, duration: config.duration, fps: config.fps, language: config.language, languages: [{ code: config.language, name: config.language }], canvas: app.canvas,
       get state() { return { time, playing, muted, captions: film.captions, audio: { configured: Boolean(audio), readyState: audio?.readyState ?? 0, error: audio?.error?.code ?? null } }; },
       resources: film.resources,
       get texts() { return film.texts; },
       get cues() { return film.cues; },
-      seek, play, pause, setCaptions, saveFrame,
+      seek, play, pause, setMuted, setCaptions, saveFrame,
       async renderFrame(frame: number, fps = config.fps) { await seek(frame / fps); },
     };
     Object.assign(window, { animaguru: api });