makaron-cli 0.8.3 → 0.8.4

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.3",
+  "version": "0.8.4",
   "description": "AI image editing, video generation, and music creation via CLI. Agents can self-register, create projects, and produce creative media.",
   "author": {
     "name": "Makaron AI",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.3",
+  "version": "0.8.4",
   "description": "AI image editing, video generation, and music creation via CLI. Agents can self-register, create projects, and produce creative media.",
   "displayName": "Makaron",
   "shortDescription": "AI image/video/music creation from the terminal",

package/README.md

@@ -206,9 +206,9 @@ For project/timeline video editing, use:
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-10s.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=1080p input. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
 
 ### `music` — Music generation
 

package/SKILL.md

@@ -198,9 +198,9 @@ npx makaron-cli video status <taskId>
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-10s.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=1080p input. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
 
 ### `music` — Music generation
 

package/bin/makaron.mjs

@@ -34,6 +34,11 @@ const MAX_VIDEO_UPLOAD_DURATION_TOLERANCE = 1;
 const MAX_VIDEO_PROVIDER_REFERENCE_DURATION = 15;
 const MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE = 0.5;
 const MAX_VIDEO_FRAME_PIXELS = 2_086_876;
+const SEEDANCE_MIN_VIDEO_FRAME_PIXELS = 409_600;
+const SEEDANCE_MIN_VIDEO_SIDE = 300;
+const SEEDANCE_MAX_VIDEO_SIDE = 6000;
+const SEEDANCE_MIN_VIDEO_ASPECT = 0.4;
+const SEEDANCE_MAX_VIDEO_ASPECT = 2.5;
 
 function getCliVersion() {
   try {
@@ -768,6 +773,11 @@ function probeLocalVideo(videoPath) {
 function validateVideoFile(videoPath, options = {}) {
   const maxDuration = options.maxDuration ?? MAX_VIDEO_UPLOAD_DURATION;
   const durationTolerance = options.durationTolerance ?? MAX_VIDEO_UPLOAD_DURATION_TOLERANCE;
+  const minFramePixels = options.minFramePixels ?? 0;
+  const minSide = options.minSide ?? 0;
+  const maxSide = options.maxSide ?? Infinity;
+  const minAspect = options.minAspect ?? 0;
+  const maxAspect = options.maxAspect ?? Infinity;
   if (!fs.existsSync(videoPath)) {
     return { ok: false, error: `Video file not found: ${videoPath}` };
   }
@@ -789,6 +799,19 @@ function validateVideoFile(videoPath, options = {}) {
   if (meta.width * meta.height > MAX_VIDEO_FRAME_PIXELS) {
     return { ok: false, error: `Video resolution too high: ${meta.width}x${meta.height} (${meta.width * meta.height} px). Max is <=1080p (${MAX_VIDEO_FRAME_PIXELS} px). Re-upload through the frontend to transcode, or export a smaller video.` };
   }
+  const framePixels = meta.width * meta.height;
+  const aspect = meta.width / meta.height;
+  if (
+    framePixels < minFramePixels ||
+    meta.width < minSide ||
+    meta.height < minSide ||
+    meta.width > maxSide ||
+    meta.height > maxSide ||
+    aspect < minAspect ||
+    aspect > maxAspect
+  ) {
+    return { ok: false, error: `Video size does not meet provider limits: ${meta.width}x${meta.height} (${framePixels} px, aspect ${aspect.toFixed(2)}). Required: frame pixels >=${minFramePixels}, sides ${minSide}-${Number.isFinite(maxSide) ? maxSide : '∞'}px, aspect ${minAspect}-${Number.isFinite(maxAspect) ? maxAspect : '∞'}. Resize/pad with FFmpeg before submitting.` };
+  }
   const mime = ext === 'mov' ? 'video/quicktime' : ext === 'webm' ? 'video/webm' : 'video/mp4';
   return { ok: true, mime, meta };
 }
@@ -850,12 +873,133 @@ async function analyzeVideoCli(baseUrl, headers, rawVideo, questionParts) {
   if (text) console.log(text);
 }
 
+// ─── Help ───────────────────────────────────────────────────────────────────
+
+function hasHelpFlag(values) {
+  return values.includes('--help') || values.includes('-h');
+}
+
+function printRootHelp() {
+  console.log(`Makaron CLI — Talk to Makaron Agent from the terminal
+
+Commands:
+  register --json                    Get challenge for agent self-registration
+  register --verify --challenge-id <id> --answer <n>  Verify and save API key
+  claim                              Get claim URL for human to link account
+  login                              Log in to Makaron (human interactive)
+  list (ls)                          List all projects
+  project media <projectId> --json    List timeline media for a project
+  create --image <file>              Create project from local image
+  create --image-url <url>           Create project from URL
+  create --title "name"              Create empty project (text-to-image)
+
+  chat --project <id> "message"      Chat (non-blocking, polls for result)
+  chat --project <id> --video <file> Attach video to conversation
+  chat --project <id> -b "message"   Background: submit and print runId
+  chat --project <id> --stream "msg" Legacy: stream SSE in real-time
+  chat --project <id> --json "msg"   Output structured JSON result
+
+  responses get <runId>              Get run status and results
+  responses get <runId> --wait       Poll until completed
+  responses list --project <id>      List runs for a project
+  abort <runId>                      Abort a running Agent
+
+  edit [--image <file>] "prompt"     AI image edit / text-to-image
+  analyze --video <file|url>         Analyze video content
+  video script|create|status         Video generation
+  music create|status                Music generation
+
+  admin                              Admin commands (skills, upload, set-admin)
+
+Environment:
+  MAKARON_API_KEY  API key (mk_live_xxx) — recommended for agents
+  MAKARON_URL      API base (default: ${DEFAULT_URL})
+`);
+}
+
+function printHelp(topic, subtopic) {
+  if (topic === 'login') {
+    console.log('Usage: makaron login');
+  } else if (topic === 'create') {
+    console.log('Usage: makaron create --image <file> [--image <file2>] | --image-url <url> | --title "name"');
+  } else if (topic === 'chat') {
+    console.log('Usage: makaron chat --project <id|auto> [--image <file>] [--video <file|url>] [--stream] [--background|-b] [--json] "your message"');
+  } else if (topic === 'responses' || topic === 'run') {
+    if (subtopic === 'get') console.log('Usage: makaron responses get <runId> [--wait] [--json] [--pick <field>]');
+    else if (subtopic === 'watch') console.log('Usage: makaron responses watch <runId> [--jsonl] [--interval <ms>]');
+    else if (subtopic === 'list') console.log('Usage: makaron responses list --project <id>');
+    else console.log(`Responses commands:
+  responses get <runId>                  Get status and output (JSON)
+  responses get <runId> --wait           Poll until completed
+  responses get <runId> --pick <field>   Extract: first_image_url, first_video_url, project_url, output
+  responses watch <runId> --jsonl        Watch until done (incremental events)
+  responses list --project <id>          List runs for a project
+`);
+  } else if (topic === 'list' || topic === 'ls') {
+    console.log('Usage: makaron list');
+  } else if (topic === 'project' || topic === 'projects') {
+    if (subtopic === 'media') console.log('Usage: makaron project media <projectId> [--json]');
+    else console.log(`Project commands:
+  project media <projectId> --json      List timeline media for a project
+`);
+  } else if (topic === 'abort') {
+    console.log('Usage: makaron abort <runId>');
+  } else if (topic === 'edit') {
+    console.log('Usage: makaron edit [--image <file|url>] [--model gemini|qwen|openai] [--skill enhance|creative|wild|captions] [--ref <file>] [--out <file>] "prompt"');
+  } else if (topic === 'analyze') {
+    console.log('Usage: makaron analyze --video <file|url> ["question"]');
+  } else if (topic === 'video') {
+    if (subtopic === 'script') console.log('Usage: makaron video script --image <file> [--image <file>] [--lang en|zh] "direction"');
+    else if (subtopic === 'create') console.log('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model kling|seedance] [--keep-original-sound]');
+    else if (subtopic === 'status') console.log('Usage: makaron video status <taskId> | --snapshot <snapshotId> [--wait]');
+    else console.log(`Video commands:
+  video script --image <file> [--image <file>] "direction"   Write video script
+  video create --script "..." --image <url> [--duration 10]  Submit video task
+  video create --script "..." --video <public-url> [--model kling|seedance]  Edit a video (standalone)
+  video status <taskId>                                      Check video status
+  video status --snapshot <snapshotId> [--wait]              Check v2 video snapshot
+`);
+  } else if (topic === 'music') {
+    if (subtopic === 'create') console.log('Usage: makaron music create [--vocals] [--style "genre"] "description"');
+    else if (subtopic === 'status') console.log('Usage: makaron music status <taskId>');
+    else console.log(`Music commands:
+  music create [--vocals] [--style "genre"] "description"    Generate music
+  music status <taskId>                                      Check music status
+`);
+  } else if (topic === 'admin') {
+    if (subtopic === 'skills') console.log('Usage: makaron admin skills [add|update|delete] ...');
+    else if (subtopic === 'upload') console.log('Usage: makaron admin upload <local-file> <storage-path>');
+    else if (subtopic === 'fetch-skill') console.log('Usage: makaron admin fetch-skill <share-code|url>');
+    else if (subtopic === 'set-admin') console.log('Usage: makaron admin set-admin <email>');
+    else console.log(`Admin commands:
+  admin skills                         List all marketplace skills
+  admin skills add '<json>'            Add a new skill
+  admin skills update <id> '<json>'    Update a skill
+  admin skills delete <id>             Delete a skill
+  admin upload <file> <storage-path>   Upload file to Storage
+  admin fetch-skill <code|url>         Download skill from share link
+  admin set-admin <email>              Grant admin access to a user
+`);
+  } else if (topic === 'register') {
+    if (subtopic === '--verify') console.log('Usage: makaron register --verify --challenge-id <id> --answer <number>');
+    else console.log('Usage: makaron register --json | makaron register --verify --challenge-id <id> --answer <number>');
+  } else if (topic === 'claim') {
+    console.log('Usage: makaron claim');
+  } else {
+    printRootHelp();
+  }
+}
+
 // ─── Main ────────────────────────────────────────────────────────────────────
 
 const args = process.argv.slice(2);
 const command = args[0];
 
-if (command === '--version' || command === '-v' || command === 'version') {
+if (!command || command === '--help' || command === '-h' || command === 'help') {
+  printRootHelp();
+} else if (hasHelpFlag(args)) {
+  printHelp(command, args[1]);
+} else if (command === '--version' || command === '-v' || command === 'version') {
   console.log(getCliVersion());
 } else if (command === 'login') {
   await login();
@@ -886,11 +1030,7 @@ if (command === '--version' || command === '-v' || command === 'version') {
   let videoModel = undefined;
   let preferredModel = undefined;
   for (let i = 1; i < args.length; i++) {
-    if (args[i] === '--help' || args[i] === '-h') {
-      console.error('Usage: makaron chat --project <id|auto> [--image <file>] [--video <file|url>] [--stream] [--background|-b] [--json] "your message"');
-      process.exit(0);
-    }
-    else if (args[i] === '--project' && args[i + 1]) projectId = args[++i];
+    if (args[i] === '--project' && args[i + 1]) projectId = args[++i];
     else if (args[i] === '--image' && args[i + 1]) chatImages.push(args[++i]);
     else if (args[i] === '--video' && args[i + 1]) chatVideos.push(args[++i]);
     else if (args[i] === '--stream') useStream = true;
@@ -1236,13 +1376,21 @@ if (command === '--version' || command === '-v' || command === 'version') {
 
     let videoUrl = isHttpUrl(video) ? video : null;
     let inputVideoMeta = null;
+    const selectedVideoModel = videoModel || 'kling';
     if (videoUrl) {
-      process.stderr.write(`📹 Assuming public video URL already matches provider reference limits: ≤${MAX_VIDEO_PROVIDER_REFERENCE_DURATION}s, ≤${MAX_VIDEO_UPLOAD_FILE_SIZE_MB}MB, ≤1080p.\n`);
+      process.stderr.write(`📹 Assuming public video URL already matches provider reference limits. Seedance requires ≤${MAX_VIDEO_PROVIDER_REFERENCE_DURATION}s, ≤50MB, sides 300-6000px, frame pixels 409,600-${MAX_VIDEO_FRAME_PIXELS}; Kling requires ≤200MB and ≤2K.\n`);
     }
     if (video && !videoUrl) {
       const valid = validateVideoFile(video, {
         maxDuration: MAX_VIDEO_PROVIDER_REFERENCE_DURATION,
         durationTolerance: MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE,
+        ...(selectedVideoModel === 'seedance' ? {
+          minFramePixels: SEEDANCE_MIN_VIDEO_FRAME_PIXELS,
+          minSide: SEEDANCE_MIN_VIDEO_SIDE,
+          maxSide: SEEDANCE_MAX_VIDEO_SIDE,
+          minAspect: SEEDANCE_MIN_VIDEO_ASPECT,
+          maxAspect: SEEDANCE_MAX_VIDEO_ASPECT,
+        } : {}),
       });
       if (!valid.ok) { console.error(`❌ ${valid.error}`); process.exit(1); }
       inputVideoMeta = valid.meta;
@@ -1254,7 +1402,7 @@ if (command === '--version' || command === '-v' || command === 'version') {
     // Standalone MCP tool (no project timeline write)
     process.stderr.write('🎬 Submitting video...\n');
     const vArgs = videoUrl
-      ? { videoUrl, editPrompt: script, images, videoModel: videoModel || 'kling', referType: (videoModel || 'kling') === 'seedance' ? 'feature' : 'base' }
+      ? { videoUrl, editPrompt: script, images, videoModel: selectedVideoModel, referType: selectedVideoModel === 'seedance' ? 'feature' : 'base' }
       : { script, images };
     const effectiveDuration = duration || (inputVideoMeta?.duration ? Math.min(MAX_VIDEO_PROVIDER_REFERENCE_DURATION, Math.round(inputVideoMeta.duration)) : undefined);
     if (effectiveDuration) vArgs.duration = effectiveDuration;
@@ -1549,39 +1697,5 @@ if (command === '--version' || command === '-v' || command === 'version') {
   console.log(JSON.stringify(data));
   console.error(`🔗 Share this link with a human: ${data.claim_url}`);
 } else {
-  console.log(`Makaron CLI — Talk to Makaron Agent from the terminal
-
-Commands:
-  register --json                    Get challenge for agent self-registration
-  register --verify --challenge-id <id> --answer <n>  Verify and save API key
-  claim                              Get claim URL for human to link account
-  login                              Log in to Makaron (human interactive)
-  list (ls)                          List all projects
-  project media <projectId> --json    List timeline media for a project
-  create --image <file>              Create project from local image
-  create --image-url <url>           Create project from URL
-  create --title "name"              Create empty project (text-to-image)
-
-  chat --project <id> "message"      Chat (non-blocking, polls for result)
-  chat --project <id> --video <file> Attach video to conversation
-  chat --project <id> -b "message"   Background: submit and print runId
-  chat --project <id> --stream "msg" Legacy: stream SSE in real-time
-  chat --project <id> --json "msg"   Output structured JSON result
-
-  responses get <runId>              Get run status and results
-  responses get <runId> --wait       Poll until completed
-  responses list --project <id>      List runs for a project
-  abort <runId>                      Abort a running Agent
-
-  edit [--image <file>] "prompt"     AI image edit / text-to-image
-  analyze --video <file|url>         Analyze video content
-  video script|create|status         Video generation
-  music create|status                Music generation
-
-  admin                              Admin commands (skills, upload, set-admin)
-
-Environment:
-  MAKARON_API_KEY  API key (mk_live_xxx) — recommended for agents
-  MAKARON_URL      API base (default: ${DEFAULT_URL})
-`);
+  printRootHelp();
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.8.3",
+  "version": "0.8.4",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {
@@ -9,7 +9,7 @@
     "test:live": "MAKARON_LIVE=1 node test/live-smoke.mjs"
   },
   "bin": {
-    "makaron": "./bin/makaron.mjs"
+    "makaron": "bin/makaron.mjs"
   },
   "files": [
     "bin/",
@@ -30,6 +30,6 @@
   "license": "MIT",
   "repository": {
     "type": "git",
-    "url": "https://github.com/vegekyd/ai-image-editor"
+    "url": "git+https://github.com/vegekyd/ai-image-editor.git"
   }
 }

package/skills/makaron/SKILL.md

@@ -198,9 +198,9 @@ npx makaron-cli video status <taskId>
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-10s.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--video <file|url>`, `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`. SeeDance accepts integer output duration 4-15s (default 5s); Kling supports 5-15s.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=1080p input. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires target <=15s, <=50MB, width/height 300-6000px, aspect ratio 0.4-2.5, and frame pixels 409,600-2,086,876. Tiny metadata padding up to 15.5s is accepted and output duration is clamped to 15s.
 
 ### `music` — Music generation