@spira-lab/cli 0.0.13 → 0.0.15

package/dist/index.cjs

@@ -18083,8 +18083,353 @@ var cliResultSchema = external_exports.object({
   error: cliErrorSchema.optional()
 });
 
+// ../../packages/contracts/dist/cli/kie-ai-model-docs.js
+function videoDoc(input) {
+  const exampleInputs = {
+    prompt: "A cinematic camera move through a bright modern studio",
+    duration: input.durations[0]
+  };
+  if (input.sizes?.[0])
+    exampleInputs.size = input.sizes[0];
+  if (input.resolutions?.[0])
+    exampleInputs.resolution = input.resolutions[0];
+  if (input.sound)
+    exampleInputs.sound = false;
+  if (input.acceptsImage || input.requiresImage)
+    exampleInputs.referenceImage = ["https://example.com/reference.png"];
+  if (input.requiresVideo)
+    exampleInputs.referenceVideo = ["https://example.com/motion.mp4"];
+  return {
+    id: input.id,
+    name: input.name,
+    mediaType: "video",
+    description: input.description,
+    capabilities: input.capabilities,
+    variants: input.variants,
+    fields: [
+      { name: "prompt", type: "string", required: true, description: "Text instruction for the video." },
+      {
+        name: "duration",
+        type: "string",
+        description: "Output duration in seconds.",
+        values: input.durations,
+        defaultValue: input.durations[0]
+      },
+      ...input.sizes ? [
+        {
+          name: "size",
+          type: "string",
+          description: "Output aspect ratio.",
+          values: input.sizes,
+          defaultValue: input.sizes[0]
+        }
+      ] : [],
+      ...input.resolutions ? [
+        {
+          name: "resolution",
+          type: "string",
+          description: "Output resolution.",
+          values: input.resolutions,
+          defaultValue: input.resolutions[0]
+        }
+      ] : [],
+      ...input.sound ? [
+        {
+          name: "sound",
+          type: "boolean",
+          description: "Generate native audio.",
+          defaultValue: false
+        }
+      ] : [],
+      ...input.acceptsImage || input.requiresImage ? [
+        {
+          name: "referenceImage",
+          type: "string[]",
+          required: input.requiresImage,
+          description: input.requiresImage ? "Exactly one public image URL is required." : input.maxReferenceImages === 2 ? "Optional one or two public image URLs. Two URLs are used as first and last frames." : "Optional single public image URL for image-to-video."
+        }
+      ] : [],
+      ...input.requiresVideo ? [
+        {
+          name: "referenceVideo",
+          type: "string[]",
+          required: true,
+          description: "Exactly one public 3-30 second motion reference video URL is required."
+        }
+      ] : []
+    ],
+    examples: [{ label: "Generate video", inputs: exampleInputs }],
+    notes: input.notes
+  };
+}
+function imageDoc(input) {
+  const exampleInputs = {
+    prompt: input.requiresImage ? "Change the background to pale yellow" : "A clean editorial product photograph",
+    size: input.sizes[0]
+  };
+  if (input.resolutions?.[0])
+    exampleInputs.resolution = input.resolutions[0];
+  if (input.modes?.[0])
+    exampleInputs.mode = input.modes[0];
+  if (input.outputFormats?.[0])
+    exampleInputs.outputFormat = input.outputFormats[0];
+  if (input.acceptsImage || input.requiresImage)
+    exampleInputs.referenceImage = ["https://example.com/reference.png"];
+  return {
+    id: input.id,
+    name: input.name,
+    mediaType: "image",
+    description: input.description,
+    capabilities: input.capabilities,
+    variants: input.variants,
+    fields: [
+      { name: "prompt", type: "string", required: true, description: "Text instruction for the image." },
+      {
+        name: "size",
+        type: "string",
+        description: "Output aspect ratio.",
+        values: input.sizes,
+        defaultValue: input.sizes[0]
+      },
+      ...input.resolutions ? [
+        {
+          name: "resolution",
+          type: "string",
+          description: "Output resolution.",
+          values: input.resolutions,
+          defaultValue: input.resolutions[0]
+        }
+      ] : [],
+      ...input.modes ? [
+        {
+          name: "mode",
+          type: "string",
+          description: "Generation tier.",
+          values: input.modes,
+          defaultValue: input.modes[0]
+        }
+      ] : [],
+      ...input.outputFormats ? [
+        {
+          name: "outputFormat",
+          type: "string",
+          description: "Output image format.",
+          values: input.outputFormats,
+          defaultValue: input.outputFormats[0]
+        }
+      ] : [],
+      ...input.acceptsImage || input.requiresImage ? [
+        {
+          name: "referenceImage",
+          type: "string[]",
+          required: input.requiresImage,
+          description: input.requiresImage ? "Exactly one public image URL is required." : "Optional public image URL for image editing."
+        }
+      ] : []
+    ],
+    examples: [{ label: input.requiresImage ? "Edit image" : "Generate image", inputs: exampleInputs }]
+  };
+}
+var perSecond = (key, display, creditsPerUnit, conditions = {}) => ({ key, display, conditions, billingUnit: "per_second", creditsPerUnit });
+var perGeneration = (key, display, creditsPerUnit, conditions = {}) => ({ key, display, conditions, billingUnit: "per_generation", creditsPerUnit });
+var KIE_CLI_AI_MODEL_DOCS = [
+  videoDoc({
+    id: "kling-2.6",
+    name: "Kling 2.6",
+    description: "Native-audio video generation with synchronized dialogue from text or image.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [
+      perSecond("silent", "Sound off", 5.5, { sound: false }),
+      perSecond("sound", "Sound on", 11, { sound: true })
+    ],
+    durations: ["5", "10"],
+    sizes: ["16:9", "9:16", "1:1"],
+    acceptsImage: true,
+    sound: true
+  }),
+  videoDoc({
+    id: "kling-2.6-motion-control",
+    name: "Kling 2.6 Motion Control",
+    description: "Reference-motion transfer with character consistency and controllable output resolution.",
+    capabilities: ["image-to-video", "motion-control"],
+    variants: [
+      perSecond("720p", "720p", 5.5, { resolution: "720p" }),
+      perSecond("1080p", "1080p", 9, { resolution: "1080p" })
+    ],
+    durations: ["3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15", "20", "25", "30"],
+    resolutions: ["720p", "1080p"],
+    requiresImage: true,
+    requiresVideo: true
+  }),
+  videoDoc({
+    id: "kling-2.5-turbo-pro",
+    name: "Kling 2.5",
+    description: "Kling 2.5 Turbo Pro text/image-to-video through KIE.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [perSecond("default", "Per second", 4.2)],
+    durations: ["5", "10"],
+    sizes: ["16:9", "9:16", "1:1"],
+    acceptsImage: true
+  }),
+  videoDoc({
+    id: "kling-2.1-master",
+    name: "Kling 2.1 Master",
+    description: "Kling 2.1 Master text/image-to-video through KIE.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [perSecond("default", "Per second", 16)],
+    durations: ["5", "10"],
+    sizes: ["16:9", "9:16", "1:1"],
+    acceptsImage: true
+  }),
+  videoDoc({
+    id: "kling-2.1-pro",
+    name: "Kling 2.1 Pro",
+    description: "Kling 2.1 Pro image-to-video through KIE.",
+    capabilities: ["image-to-video"],
+    variants: [perSecond("default", "Per second", 5)],
+    durations: ["5", "10"],
+    requiresImage: true
+  }),
+  videoDoc({
+    id: "kling-2.1-standard",
+    name: "Kling 2.1 Standard",
+    description: "Kling 2.1 Standard image-to-video through KIE.",
+    capabilities: ["image-to-video"],
+    variants: [perSecond("default", "Per second", 2.5)],
+    durations: ["5", "10"],
+    requiresImage: true
+  }),
+  videoDoc({
+    id: "wan-2.2-a14b-turbo",
+    name: "Wan 2.2",
+    description: "Wan 2.2 A14B Turbo text/image-to-video through KIE.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [
+      perGeneration("480p", "480p / 5 seconds", 20, { resolution: "480p" }),
+      perGeneration("720p", "720p / 5 seconds", 40, { resolution: "720p" })
+    ],
+    durations: ["5"],
+    sizes: ["16:9", "9:16", "1:1"],
+    resolutions: ["480p", "720p"],
+    acceptsImage: true
+  }),
+  videoDoc({
+    id: "wan-2.5",
+    name: "Wan 2.5",
+    description: "Cinematic text and image video generation with synchronized dialogue, ambience, and music.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [
+      perSecond("720p", "720p", 6, { resolution: "720p" }),
+      perSecond("1080p", "1080p", 10, { resolution: "1080p" })
+    ],
+    durations: ["5", "10"],
+    sizes: ["16:9", "9:16", "1:1"],
+    resolutions: ["720p", "1080p"],
+    acceptsImage: true
+  }),
+  videoDoc({
+    id: "wan-2.6",
+    name: "Wan 2.6",
+    description: "Multi-shot HD video generation with stable characters and synchronized native audio.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [
+      perGeneration("720p-5", "720p / 5 seconds", 35, { resolution: "720p", duration: "5" }),
+      perGeneration("720p-10", "720p / 10 seconds", 70, { resolution: "720p", duration: "10" }),
+      perGeneration("720p-15", "720p / 15 seconds", 105, { resolution: "720p", duration: "15" }),
+      perGeneration("1080p-5", "1080p / 5 seconds", 52.25, { resolution: "1080p", duration: "5" }),
+      perGeneration("1080p-10", "1080p / 10 seconds", 104.75, { resolution: "1080p", duration: "10" }),
+      perGeneration("1080p-15", "1080p / 15 seconds", 157.5, { resolution: "1080p", duration: "15" })
+    ],
+    durations: ["5", "10", "15"],
+    resolutions: ["720p", "1080p"],
+    acceptsImage: true
+  }),
+  videoDoc({
+    id: "wan-2.7",
+    name: "Wan 2.7",
+    description: "Controllable cinematic video generation with first and last frame guidance.",
+    capabilities: ["text-to-video", "image-to-video"],
+    variants: [
+      perSecond("720p", "720p", 8, { resolution: "720p" }),
+      perSecond("1080p", "1080p", 12, { resolution: "1080p" })
+    ],
+    durations: ["5", "2", "3", "4", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15"],
+    sizes: ["16:9", "9:16", "1:1", "4:3", "3:4"],
+    resolutions: ["720p", "1080p"],
+    acceptsImage: true,
+    maxReferenceImages: 2,
+    notes: ["Aspect ratio applies to text-to-video. Image-to-video inherits framing from the reference images."]
+  }),
+  imageDoc({
+    id: "seedream-4.5",
+    name: "Seedream 4.5",
+    description: "Precise 4K image generation and consistent multi-image editing.",
+    capabilities: ["text-to-image", "image-to-image"],
+    variants: [perGeneration("default", "Per image", 3.25)],
+    sizes: ["1:1", "4:3", "3:4", "16:9", "9:16", "2:3", "3:2", "21:9"],
+    resolutions: ["2K", "4K"],
+    acceptsImage: true
+  }),
+  imageDoc({
+    id: "nano-banana",
+    name: "Nano Banana",
+    description: "Fast, cost-efficient image generation powered by Gemini 2.5 Flash Image.",
+    capabilities: ["text-to-image"],
+    variants: [perGeneration("default", "Per image", 2)],
+    sizes: ["1:1", "9:16", "16:9", "4:3", "3:4", "3:2", "2:3", "5:4", "4:5", "21:9", "auto"],
+    outputFormats: ["png", "jpg"]
+  }),
+  imageDoc({
+    id: "seedream-4.0",
+    name: "Seedream 4.0",
+    description: "Seedream 4.0 image generation/editing through KIE.",
+    capabilities: ["text-to-image", "image-to-image"],
+    variants: [perGeneration("default", "Per image", 2.5)],
+    sizes: ["1:1", "4:3", "3:4", "3:2", "2:3", "16:9", "9:16", "21:9"],
+    resolutions: ["1K", "2K", "4K"],
+    acceptsImage: true
+  }),
+  imageDoc({
+    id: "flux-kontext",
+    name: "Flux.1 Kontext",
+    description: "Flux.1 Kontext image generation/editing through KIE.",
+    capabilities: ["text-to-image", "image-to-image"],
+    variants: [perGeneration("pro", "Pro", 2.5, { mode: "pro" }), perGeneration("max", "Max", 5, { mode: "max" })],
+    sizes: ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"],
+    modes: ["pro", "max"],
+    outputFormats: ["png", "jpg"],
+    acceptsImage: true
+  }),
+  imageDoc({
+    id: "qwen-image-edit",
+    name: "Qwen Image Edit",
+    description: "Precise semantic, appearance, and bilingual text editing while preserving visual coherence.",
+    capabilities: ["image-to-image"],
+    variants: [
+      perGeneration("1:1", "1:1", 0.5, { size: "1:1" }),
+      perGeneration("1:1-hd", "1:1 HD", 1.75, { size: "1:1 HD" }),
+      perGeneration("3:4", "3:4", 1.25, { size: "3:4" }),
+      perGeneration("9:16", "9:16", 1, { size: "9:16" }),
+      perGeneration("4:3", "4:3", 1.25, { size: "4:3" }),
+      perGeneration("16:9", "16:9", 1, { size: "16:9" })
+    ],
+    sizes: ["1:1", "1:1 HD", "3:4", "9:16", "4:3", "16:9"],
+    outputFormats: ["png", "jpg"],
+    requiresImage: true
+  }),
+  imageDoc({
+    id: "z-image",
+    name: "Z-Image",
+    description: "Fast photorealistic image generation with strong bilingual text rendering.",
+    capabilities: ["text-to-image"],
+    variants: [perGeneration("default", "Per image", 0.4)],
+    sizes: ["1:1", "4:3", "3:4", "16:9", "9:16"]
+  })
+];
+
 // src/ai/model-docs.ts
 var cliAiModelDocs = [
+  ...KIE_CLI_AI_MODEL_DOCS,
   {
     "id": "ai-influencer-image",
     "name": "AI Influencer",
@@ -19135,11 +19480,141 @@ var cliAiModelDocs = [
       "image_to_video requires exactly 1 referenceImage and does not send aspect ratio; size applies to text_to_video and reference_to_video."
     ]
   },
+  {
+    "id": "wan-3.0",
+    "name": "Wan 3.0",
+    "mediaType": "video",
+    "description": "Alibaba Wan 3.0 all-in-one video generation with text, frame, image, video, and audio guidance plus native sound.",
+    "capabilities": ["text-to-video", "image-to-video", "video-to-video"],
+    "variants": [
+      {
+        "key": "480p",
+        "display": "480p",
+        "conditions": { "resolution": "480p" },
+        "billingUnit": "per_second",
+        "creditsPerUnit": 3.09
+      },
+      {
+        "key": "720p",
+        "display": "720p",
+        "conditions": { "resolution": "720p" },
+        "billingUnit": "per_second",
+        "creditsPerUnit": 6.18
+      },
+      {
+        "key": "1080p",
+        "display": "1080p",
+        "conditions": { "resolution": "1080p" },
+        "billingUnit": "per_second",
+        "creditsPerUnit": 12.35
+      }
+    ],
+    "fields": [
+      {
+        "name": "prompt",
+        "type": "string",
+        "description": "Optional with reference media; otherwise required. Up to 20000 characters."
+      },
+      {
+        "name": "generationType",
+        "type": "string",
+        "description": "Optional; inferred from references when omitted.",
+        "values": ["text_to_video", "image_to_video", "first_last_frames_to_video", "reference_to_video"]
+      },
+      {
+        "name": "duration",
+        "type": "string",
+        "description": "Whole-second output duration from 2 through 30.",
+        "defaultValue": "5"
+      },
+      {
+        "name": "resolution",
+        "type": "string",
+        "description": "Output resolution.",
+        "values": ["720p", "480p", "1080p"],
+        "defaultValue": "720p"
+      },
+      {
+        "name": "size",
+        "type": "string",
+        "description": "Output aspect ratio, or adaptive to infer it from the reference media.",
+        "values": ["adaptive", "16:9", "4:3", "1:1", "3:4", "9:16"],
+        "defaultValue": "adaptive"
+      },
+      {
+        "name": "referenceImage",
+        "type": "string[]",
+        "description": "Public URLs. One image is a first frame and two are first/last frames unless reference_to_video is explicit. Reference mode accepts up to 10."
+      },
+      {
+        "name": "referenceVideo",
+        "type": "string[]",
+        "description": "Up to 5 public URLs in reference mode, totaling at most 15 seconds."
+      },
+      {
+        "name": "referenceAudio",
+        "type": "string[]",
+        "description": "Up to 5 public URLs in reference mode, totaling at most 15 seconds."
+      },
+      {
+        "name": "sound",
+        "type": "boolean",
+        "description": "Generate native audio with the video.",
+        "defaultValue": true
+      },
+      {
+        "name": "seed",
+        "type": "number",
+        "description": "Optional integer from 0 through 2147483647."
+      }
+    ],
+    "examples": [
+      {
+        "label": "Text to video",
+        "inputs": {
+          "prompt": "A cinematic feast above the clouds with native ambience",
+          "generationType": "text_to_video",
+          "duration": "5",
+          "resolution": "720p",
+          "size": "16:9",
+          "sound": true
+        }
+      },
+      {
+        "label": "First and last frames",
+        "inputs": {
+          "prompt": "Move naturally from dawn to night while preserving the same temple",
+          "generationType": "first_last_frames_to_video",
+          "referenceImage": ["https://example.com/first.png", "https://example.com/last.png"],
+          "duration": "8",
+          "resolution": "1080p"
+        }
+      },
+      {
+        "label": "Multimodal reference",
+        "inputs": {
+          "prompt": "Keep the image identity, clip movement, and audio rhythm",
+          "generationType": "reference_to_video",
+          "referenceImage": ["https://example.com/character.png"],
+          "referenceVideo": ["https://example.com/motion.mp4"],
+          "referenceAudio": ["https://example.com/rhythm.mp3"],
+          "duration": "10",
+          "resolution": "720p",
+          "sound": true
+        }
+      }
+    ],
+    "notes": [
+      "Frame mode and ordinary reference mode cannot be mixed.",
+      "Reference inputs are free; only output duration and resolution determine the price. Sound costs the same.",
+      "Document and webpage inputs are not exposed by Spira."
+    ]
+  },
   {
     "id": "minimax-h3",
     "name": "MiniMax H3",
     "mediaType": "video",
-    "description": "MiniMax H3 multimodal video model. The only model that accepts image, video, and audio references in the same request.",
+    "description": "MiniMax H3 multimodal video model with image, video, and audio references in the same request.",
     "capabilities": [
       "text-to-video",
       "image-to-video"
@@ -20275,6 +20750,65 @@ var cliAiModelDocs = [
       "generationType=text_to_video rejects reference inputs; first_last_frames_to_video requires exactly 2 reference images; only reference_to_video accepts video or audio references."
     ]
   },
+  {
+    id: "bria-video-background-removal",
+    name: "Bria Video Background Removal",
+    mediaType: "video",
+    description: "Remove a video background with Bria VRMBG 3.0 and replace it with a solid colour.",
+    capabilities: ["video-to-video"],
+    variants: [
+      {
+        key: "default",
+        display: "Per second of source video",
+        conditions: {},
+        billingUnit: "per_second",
+        creditsPerUnit: 0.42
+      }
+    ],
+    fields: [
+      {
+        name: "referenceVideo",
+        type: "string[]",
+        description: "Exactly one public HTTP/HTTPS source video URL, up to 100 MiB.",
+        required: true
+      },
+      {
+        name: "mode",
+        type: "string",
+        description: "Solid replacement background colour.",
+        values: ["Green", "Black", "White", "Gray", "Red", "Blue", "Yellow", "Cyan", "Magenta", "Orange"],
+        defaultValue: "Green"
+      },
+      {
+        name: "preserveAudio",
+        type: "boolean",
+        description: "Keep the source audio track in the output.",
+        defaultValue: true
+      },
+      {
+        name: "autoZoom",
+        type: "boolean",
+        description: "Crop the output to the tightest rectangle that contains the subject for the whole clip.",
+        defaultValue: false
+      }
+    ],
+    examples: [
+      {
+        label: "Remove a video background",
+        inputs: {
+          referenceVideo: ["https://example.com/source.mp4"],
+          mode: "Green",
+          preserveAudio: true,
+          autoZoom: false
+        }
+      }
+    ],
+    notes: [
+      "No prompt is required or accepted; provide exactly one referenceVideo URL.",
+      "Every colour uses the same rate, billed from the measured source-video duration.",
+      "The output is H.264 MP4 with a solid background; transparent output is not available through this model integration."
+    ]
+  },
   {
     "id": "veo3.1",
     "name": "Veo 3.1",
@@ -20716,7 +21250,13 @@ var cliAiModelDocs = [
   }
 ];
 function listCliAiModelDocs(mediaType) {
-  return cliAiModelDocs.filter((model) => !mediaType || model.mediaType === mediaType);
+  const docs = cliAiModelDocs.filter((model) => !mediaType || model.mediaType === mediaType);
+  const wan = docs.find((model) => model.id === "wan-3.0");
+  if (!wan) return docs;
+  const ordered = docs.filter((model) => model.id !== "wan-3.0");
+  const miniMaxIndex = ordered.findIndex((model) => model.id === "minimax-h3");
+  if (miniMaxIndex < 0) return docs;
+  return [...ordered.slice(0, miniMaxIndex + 1), wan, ...ordered.slice(miniMaxIndex + 1)];
 }
 function getCliAiModelDoc(modelId) {
   return cliAiModelDocs.find((model) => model.id === modelId);
@@ -21706,35 +22246,29 @@ var commandDefinitions = [
   },
   {
     path: ["media", "video"],
-    purpose: "Download the video file behind a social link.",
+    purpose: "Resolve the original video and optional audio files behind a social link.",
     arguments: [{ name: "url", description: "Public post or video URL.", required: true }],
     options: [
       {
         name: "formatId",
         flag: "--format-id <id>",
-        description: "A format_id from `spira media info`. Omit for the best rung that plays everywhere. Every rung is delivered with audio.",
-        type: "string"
-      },
-      {
-        name: "output",
-        flag: "--output <path>",
-        description: "Also save a local copy from the returned URL.",
+        description: "A format_id from `spira media info`. Omit for the highest available rung. Video-only rungs return a second audio file.",
         type: "string"
       }
     ],
     http: {
       method: "POST",
-      path: "/api/tools/media/video",
+      path: "/api/tools/media/video/urls",
       authRequired: true,
       body: [
         { name: "url", source: "argument", from: "url" },
         { name: "formatId", source: "option", from: "formatId" }
       ]
     },
-    resultType: "mediaAsset",
+    resultType: "generic",
     examples: [
       "spira media video https://www.tiktok.com/@user/video/123",
-      "spira media video https://www.youtube.com/watch?v=dQw4w9WgXcQ --output ./downloads/",
+      "spira media video https://www.youtube.com/watch?v=dQw4w9WgXcQ",
       "spira media video https://www.tiktok.com/@user/video/123 --format-id bytevc1_1080p_612574-0"
     ],
     relatedCommands: ["spira media info <url>", "spira media thumbnail <url>"]
@@ -23412,8 +23946,8 @@ function renderCommandIndex() {
 `;
 }
 async function packageVersion() {
-  if ("0.0.13".length > 0) {
-    return "0.0.13";
+  if ("0.0.15".length > 0) {
+    return "0.0.15";
   }
   try {
     const packageUrl = new URL("../package.json", import_meta.url);
@@ -23634,7 +24168,7 @@ ${url2}
       poll: () => executeHttpCommand({ command: statusCommand, args: { jobId }, options: {} })
     });
   }
-  if (commandKey(definition.path) === "media video" || commandKey(definition.path) === "media thumbnail") {
+  if (commandKey(definition.path) === "media thumbnail") {
     const downloaded = await executeHttpCommand({ command: definition, args, options });
     if (typeof options.output !== "string" || options.output.length === 0) return downloaded;
     return saveMediaAsset(downloaded, options.output);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@spira-lab/cli",
-  "version": "0.0.13",
+  "version": "0.0.15",
   "description": "Command line client for Spira.",
   "type": "module",
   "bin": {