makaron-cli 0.12.2 → 0.13.1

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.11.5",
+  "version": "0.13.1",
   "description": "AI image editing, video generation, music creation, and marketplace skill workflows via CLI. Agents can self-register, install skills, create projects, and produce creative media.",
   "author": {
     "name": "Makaron AI",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.11.5",
+  "version": "0.13.1",
   "description": "AI image editing, video generation, music creation, and marketplace skill workflows via CLI. Agents can self-register, install skills, create projects, and produce creative media.",
   "displayName": "Makaron",
   "shortDescription": "AI image/video/music creation from the terminal",

package/README.md

@@ -90,8 +90,13 @@ npx makaron-cli chat --project <id> --json -b "<prompt>"
 # Auto-create project (with or without images)
 npx makaron-cli chat --project auto --image photo.jpg --json -b "make it cinematic"
 npx makaron-cli chat --project auto --image img1.jpg --image img2.jpg --json -b "combine these"
+
+# Choose each model role explicitly
+npx makaron-cli chat --project auto --agent-model deepseek-v4-pro --image-model qwen "design a product poster"
 ```
 
+Model flags are role-specific: `--agent-model` controls reasoning and tool use, `--image-model` controls image generation/editing, and `--video-model` controls video generation. `--agent-model` accepts `auto|gpt-5.6-terra|gpt-5.6-sol|gpt-5.6-luna|grok-4.5|deepseek-v4-pro`. `auto` currently uses GPT-5.6 Terra. `MAKARON_AGENT_MODEL` can set the default for automation; the command flag takes precedence. The legacy `--model` flag remains temporarily supported with a deprecation warning.
+
 Returns immediately:
 ```json
 {"runId": "xxx", "projectId": "...", "projectUrl": "https://www.makaron.app/projects/...", "status": "running"}
@@ -280,7 +285,7 @@ npx makaron-cli edit --image photo.jpg --ref style.jpg "match this style"
 npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 ```
 
-Options: `--image`, `--model gemini|gemini-lite|qwen|openai|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
+Options: `--image`, `--image-model gemini|gemini-lite|qwen|openai|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
 
 ### `video` — Standalone video tools (no project timeline)
 
@@ -292,13 +297,16 @@ npx makaron-cli video script --image img1.jpg "cinematic story"
 npx makaron-cli analyze --video input.mp4 "describe the key actions and pacing"
 
 # 3a. Submit image-to-video rendering (images must be public URLs from step 1 or uploaded)
-npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --model kling
-npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> slow cinematic push-in with native ambience" --image https://...jpg --duration 5 --model grok
-npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_2>>> build a neon one-person studio" --image https://...jpg --image https://...webp --duration 15 --model seedance-mini --video-resolution 480p --aspect 9:16
+npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --video-model kling
+npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> slow cinematic push-in with native ambience" --image https://...jpg --duration 5 --video-model grok
+npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_2>>> build a neon one-person studio" --image https://...jpg --image https://...webp --duration 15 --video-model seedance-mini --video-resolution 480p --aspect 9:16
+
+# 3b. Native SeeDance text-to-video (no image required)
+npx makaron-cli video create --script "Shot 1 (5s): A neon one-person studio wakes at dawn" --duration 5 --video-model seedance-fast --aspect 16:9
 
-# 3b. Edit a video from a local file or public URL
-npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance-fast
-npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance --video-resolution 1080p
+# 3c. Edit a video from a local file or public URL
+npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --video-model seedance-fast
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --video-model seedance --video-resolution 1080p
 
 # 4. Check status
 npx makaron-cli video status <taskId>
@@ -310,9 +318,9 @@ 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 seedance-fast|seedance-mini|seedance|kling|grok|google-omni`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio. For `--model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
+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`, `--video-model seedance-fast|seedance-mini|seedance|kling|grok|google-omni`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance-fast --video`, `--model seedance-mini --video`, or `--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. `--model google-omni --video` uses Gemini Omni direct video editing and accepts one reference video in Makaron. Output duration is clamped to 3-10s. Grok does not support video references.
+Video edit model behavior: `--video-model kling --video` uses Kling base/direct edit internally; `--video-model seedance-fast --video`, `--video-model seedance-mini --video`, or `--video-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. `--video-model google-omni --video` uses Gemini Omni direct video editing and accepts one reference video in Makaron. Output duration is clamped to 3-10s. Grok does not support video references.
 
 ### `music` — Music generation
 
@@ -443,8 +451,23 @@ Admin commands require an API key with admin privileges. Ask your admin to run `
 
 ```bash
 npx makaron-cli admin skills
+npx makaron-cli admin skills --json
+```
+
+The human-readable list includes assigned categories plus title/prompt locale completeness.
+
+### Manage marketplace categories
+
+```bash
+npx makaron-cli admin skill-categories
+npx makaron-cli admin skill-categories --json
+npx makaron-cli admin skill-categories add '{"id":"portrait-effects","labels":{"en":"Portrait Effects","zh":"人像特效","zh-Hant":"人像特效","ja":"ポートレート効果"},"icon":"✨","sort_order":10}'
+npx makaron-cli admin skill-categories update portrait-effects '{"icon":"📸"}'
+npx makaron-cli admin skill-categories delete portrait-effects
 ```
 
+Deleting a category is blocked while any marketplace skill still uses it.
+
 ### Upload assets to Storage
 
 ```bash
@@ -467,9 +490,10 @@ Storage paths follow this convention:
 
 ```bash
 npx makaron-cli admin skills add '{
-  "labels": {"zh": "中文名", "en": "English Name"},
+  "labels": {"en": "English Name", "zh": "中文名", "zh-Hant": "繁體名稱", "ja": "日本語名"},
   "image": "https://sdyrtztrjgmmpnirswxt.supabase.co/storage/v1/object/public/images/marketplace/covers/skill-name.jpg",
-  "prompt": "Default prompt shown to users",
+  "prompts": {"en": "Default prompt", "zh": "默认提示词", "zh-Hant": "預設提示詞", "ja": "デフォルトプロンプト"},
+  "categories": ["portrait-effects"],
   "skill_path": "https://sdyrtztrjgmmpnirswxt.supabase.co/storage/v1/object/public/images/marketplace/skills/skill-name.zip",
   "image_count": 2,
   "sort_order": 10,
@@ -478,6 +502,8 @@ npx makaron-cli admin skills add '{
 }'
 ```
 
+New skills require all four localized titles, all four localized default prompts, and at least one existing category. Partial `labels` or `prompts` updates are merged with existing locales, so updating one language does not erase the others.
+
 ### Update / delete a skill
 
 ```bash
@@ -512,7 +538,7 @@ npx makaron-cli admin fetch-skill https://www.makaron.app/s/4c4cbd57
    ```
 6. **Add to marketplace**:
    ```bash
-   npx makaron-cli admin skills add '{"labels":{"zh":"...","en":"..."},"image":"<cover_url>","skill_path":"<zip_url>","before_images":["<before_url>"],"image_count":2,"sort_order":10,"is_active":true}'
+   npx makaron-cli admin skills add '{"labels":{"en":"...","zh":"...","zh-Hant":"...","ja":"..."},"prompts":{"en":"...","zh":"...","zh-Hant":"...","ja":"..."},"categories":["portrait-effects"],"image":"<cover_url>","skill_path":"<zip_url>","before_images":["<before_url>"],"image_count":2,"sort_order":10,"is_active":true}'
    ```
 7. **Verify** — visit https://www.makaron.app/home and confirm the skill appears, can be clicked, and works
 

package/bin/makaron.mjs

@@ -27,6 +27,7 @@ const APP_URL = process.env.MAKARON_APP_URL || DEFAULT_URL;
 const NPM_PACKAGE_NAME = 'makaron-cli';
 const UPDATE_CHECK_INTERVAL_MS = 24 * 60 * 60 * 1000;
 const UPDATE_CHECK_TIMEOUT_MS = 400;
+const AGENT_MODELS = ['auto', 'gpt-5.6-terra', 'gpt-5.6-sol', 'gpt-5.6-luna', 'grok-4.5', 'deepseek-v4-pro'];
 
 // Public anon key (safe to embed — only enables auth, not data access)
 const SUPABASE_URL = 'https://sdyrtztrjgmmpnirswxt.supabase.co';
@@ -50,6 +51,18 @@ const SEEDANCE_MAX_VIDEO_SIDE = 6000;
 const SEEDANCE_MIN_VIDEO_ASPECT = 0.4;
 const SEEDANCE_MAX_VIDEO_ASPECT = 2.5;
 
+function warnLegacyModelFlag(replacement) {
+  process.stderr.write(`⚠️  --model is deprecated here; use ${replacement}.\n`);
+}
+
+function validateAgentModel(value) {
+  if (!AGENT_MODELS.includes(value)) {
+    process.stderr.write(`❌ Unknown agent model: ${value}\nChoose one of: ${AGENT_MODELS.join(', ')}\n`);
+    process.exit(1);
+  }
+  return value;
+}
+
 function getCliVersion() {
   try {
     const pkg = JSON.parse(fs.readFileSync(new URL('../package.json', import.meta.url), 'utf-8'));
@@ -277,8 +290,9 @@ Options:
   --video <file|url>        Attach a video to the project timeline. Repeatable.
   --audio <file|url>        Attach a song, beat, or voice reference. MP3/WAV, repeatable.
   --skill <id|label|name>   Use an installed skill or auto-install a matched marketplace skill.
-  --model <name>            Preferred image/model route.
+  --image-model <name>      Image model: gemini, gemini-lite, qwen, openai, pony, or wai.
   --video-model <name>      Preferred video model: seedance-fast, seedance-mini, seedance, kling, grok, or google-omni.
+  --agent-model <name>      Agent model: auto, gpt-5.6-terra, gpt-5.6-sol, gpt-5.6-luna, grok-4.5, or deepseek-v4-pro.
   --video-resolution <res>  Video resolution: auto, 480p, 720p, 1080p, or 4k.
   --background, -b          Submit and print a runId.
   --json                    Output structured JSON.
@@ -333,7 +347,7 @@ async function abortRun(baseUrl, headers, runId) {
   } catch { /* best effort */ }
 }
 
-async function streamAgent(baseUrl, headers, projectId, prompt) {
+async function streamAgent(baseUrl, headers, projectId, prompt, opts = {}) {
   const controller = new AbortController();
   const res = await fetch(`${baseUrl}/api/agent`, {
     method: 'POST',
@@ -345,6 +359,10 @@ async function streamAgent(baseUrl, headers, projectId, prompt) {
       projectId,
       prompt,
       headless: true,
+      ...(opts.preferredModel ? { preferredModel: opts.preferredModel } : {}),
+      ...(opts.videoModel ? { videoModel: opts.videoModel } : {}),
+      ...(opts.videoResolution ? { videoResolution: opts.videoResolution } : {}),
+      ...(opts.agentModel && opts.agentModel !== 'auto' ? { agentModel: opts.agentModel } : {}),
     }),
     signal: controller.signal,
   });
@@ -452,6 +470,7 @@ async function streamAgent(baseUrl, headers, projectId, prompt) {
 async function submitRun(baseUrl, headers, projectId, prompt, opts = {}) {
   const body = { projectId, prompt };
   if (opts.preferredModel) body.preferredModel = opts.preferredModel;
+  if (opts.agentModel && opts.agentModel !== 'auto') body.agentModel = opts.agentModel;
   if (opts.videoModel) body.videoModel = opts.videoModel;
   if (opts.videoResolution) body.videoResolution = opts.videoResolution;
   if (opts.currentSnapshotIndex != null) body.currentSnapshotIndex = opts.currentSnapshotIndex;
@@ -971,6 +990,17 @@ function timeSince(date) {
 
 // ─── Skill Marketplace ──────────────────────────────────────────────────────
 
+const MARKETPLACE_LOCALES = ['en', 'zh', 'zh-Hant', 'ja'];
+
+function localizedValues(value) {
+  if (!value || typeof value !== 'object' || Array.isArray(value)) return [];
+  return Object.values(value).filter(item => typeof item === 'string' && item.trim());
+}
+
+function localizedCoverage(value) {
+  return MARKETPLACE_LOCALES.filter(locale => typeof value?.[locale] === 'string' && value[locale].trim()).length;
+}
+
 function getSkillLabel(skill) {
   return skill.labels?.en || skill.labels?.zh || skill.label || skill.name || skill.id;
 }
@@ -1013,15 +1043,15 @@ async function fetchMarketplaceSkills(baseUrl, opts = {}) {
 }
 
 function marketplaceSearchText(skill) {
+  const localized = [...localizedValues(skill.labels), ...localizedValues(skill.prompts)];
   return [
     skill.id,
     skill.label,
-    skill.labels?.en,
-    skill.labels?.zh,
+    ...localized,
     skill.prompt,
+    ...(Array.isArray(skill.categories) ? skill.categories : []),
     slugifySkill(skill.label),
-    slugifySkill(skill.labels?.en),
-    slugifySkill(skill.labels?.zh),
+    ...localized.map(slugifySkill),
   ].filter(Boolean).join(' ').toLowerCase();
 }
 
@@ -1029,9 +1059,10 @@ function marketplaceSkillTokens(skill) {
   return [
     skill.id,
     skill.label,
-    skill.labels?.en,
-    skill.labels?.zh,
+    ...localizedValues(skill.labels),
+    ...localizedValues(skill.prompts),
     skill.prompt,
+    ...(Array.isArray(skill.categories) ? skill.categories : []),
   ].filter(Boolean).map(value => String(value).toLowerCase());
 }
 
@@ -1079,8 +1110,13 @@ function printMarketplaceSkill(skill) {
   console.log(`${skill.label}`);
   console.log(`ID: ${skill.id}`);
   console.log(`Type: ${skill.hasSkill ? 'installable skill' : 'prompt template'}`);
-  if (skill.labels?.zh && skill.labels.zh !== skill.label) console.log(`ZH: ${skill.labels.zh}`);
-  if (skill.prompt) console.log(`Prompt: ${skill.prompt}`);
+  for (const locale of MARKETPLACE_LOCALES) {
+    const label = skill.labels?.[locale];
+    if (label && label !== skill.label) console.log(`${locale}: ${label}`);
+  }
+  if (Array.isArray(skill.categories) && skill.categories.length) console.log(`Categories: ${skill.categories.join(', ')}`);
+  console.log(`i18n: titles ${localizedCoverage(skill.labels)}/4 · prompts ${localizedCoverage(skill.prompts)}/4`);
+  if (skill.prompts?.en || skill.prompt) console.log(`Prompt (en): ${skill.prompts?.en || skill.prompt}`);
   if (skill.image) console.log(`Cover: ${skill.image}`);
   if (skill.hasSkill) console.log(`Install: makaron skills install ${skill.id}`);
 }
@@ -1551,9 +1587,26 @@ Commands:
 
   admin                              Admin commands (skills, upload, set-admin)
 
+Model selection:
+  --agent-model <name>               Reasoning/tool model: auto, gpt-5.6-terra, gpt-5.6-sol,
+                                     gpt-5.6-luna, grok-4.5, or deepseek-v4-pro
+  --image-model <name>               Image model: gemini, gemini-lite, qwen, openai,
+                                     pony, or wai
+  --video-model <name>               Video model: seedance-fast, seedance-mini, seedance,
+                                     kling, grok, or google-omni
+
+Examples:
+  makaron chat --project auto --agent-model deepseek-v4-pro "plan a launch poster"
+  makaron chat --project <id> --agent-model gpt-5.6-terra --image-model qwen "make it cinematic"
+  makaron chat --project <id> --video-model seedance-fast "turn this into a short video"
+
+Run makaron <command> --help for command-specific options.
+The legacy --model flag is deprecated; use the role-specific flags above.
+
 Environment:
-  MAKARON_API_KEY  API key (mk_live_xxx) — recommended for agents
-  MAKARON_URL      API base (default: ${DEFAULT_URL})
+  MAKARON_API_KEY       API key (mk_live_xxx) — recommended for agents
+  MAKARON_URL           API base (default: ${DEFAULT_URL})
+  MAKARON_AGENT_MODEL   Default Agent model; --agent-model takes precedence
 `);
 }
 
@@ -1660,17 +1713,18 @@ Use with chat:
   composition status <jobId> [--wait] [--json]
 `);
   } else if (topic === 'edit') {
-    console.log('Usage: makaron edit [--image <file|url>] [--model gemini|gemini-lite|qwen|openai|pony|wai] [--skill enhance|creative|wild|captions] [--ref <file>] [--out <file>] "prompt"');
+    console.log('Usage: makaron edit [--image <file|url>] [--image-model gemini|gemini-lite|qwen|openai|pony|wai] [--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 seedance-fast|seedance-mini|seedance|kling|grok|google-omni] [--video-resolution auto|480p|720p|1080p|4k] [--keep-original-sound]');
+    else if (subtopic === 'create') console.log('Usage: makaron video create --script "..." [--image <url> | --video <public-url>] [--duration 10] [--aspect 9:16] [--video-model seedance-fast|seedance-mini|seedance|kling|grok|google-omni] [--video-resolution auto|480p|720p|1080p|4k] [--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 "..." --video-model seedance-fast    Native text-to-video (no image required)
   video create --script "..." --image <url> [--duration 10]  Submit video task
-  video create --script "..." --video <public-url> [--model seedance-fast|seedance-mini|seedance|kling|google-omni]  Edit a video (standalone; Grok does not support video refs)
+  video create --script "..." --video <public-url> [--video-model seedance-fast|seedance-mini|seedance|kling|google-omni]  Edit a video (standalone; Grok does not support video refs)
   video status <taskId>                                      Check video status
   video status --snapshot <snapshotId> [--wait]              Check v2 video snapshot
 `);
@@ -1682,7 +1736,8 @@ Use with chat:
   music status <taskId>                                      Check music status
 `);
   } else if (topic === 'admin') {
-    if (subtopic === 'skills') console.log('Usage: makaron admin skills [add|update|delete] ...');
+    if (subtopic === 'skills') console.log('Usage: makaron admin skills [--json|add|update|delete] ...');
+    else if (subtopic === 'skill-categories') console.log('Usage: makaron admin skill-categories [--json|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>');
@@ -1691,6 +1746,10 @@ Use with chat:
   admin skills add '<json>'            Add a new skill
   admin skills update <id> '<json>'    Update a skill
   admin skills delete <id>             Delete a skill
+  admin skill-categories               List marketplace categories
+  admin skill-categories add '<json>'  Add a category
+  admin skill-categories update <id> '<json>'
+  admin skill-categories delete <id>   Delete a category
   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
@@ -1756,6 +1815,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   let videoModel = undefined;
   let videoResolution = undefined;
   let preferredModel = undefined;
+  let agentModel = process.env.MAKARON_AGENT_MODEL || 'auto';
   for (let i = 1; i < args.length; i++) {
     if (args[i] === '--project' && args[i + 1]) projectId = args[++i];
     else if (args[i] === '--image' && args[i + 1]) chatImages.push(args[++i]);
@@ -1768,7 +1828,12 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     else if (args[i] === '--json') jsonOutput = true;
     else if (args[i] === '--video-model' && args[i + 1]) videoModel = args[++i];
     else if (args[i] === '--video-resolution' && args[i + 1]) videoResolution = args[++i];
-    else if (args[i] === '--model' && args[i + 1]) preferredModel = args[++i];
+    else if (args[i] === '--image-model' && args[i + 1]) preferredModel = args[++i];
+    else if (args[i] === '--agent-model' && args[i + 1]) agentModel = args[++i];
+    else if (args[i] === '--model' && args[i + 1]) {
+      warnLegacyModelFlag('--image-model');
+      preferredModel = args[++i];
+    }
     else promptParts.push(args[i]);
   }
   const prompt = promptParts.join(' ');
@@ -1777,6 +1842,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     console.error('Run: makaron chat --help');
     process.exit(1);
   }
+  agentModel = validateAgentModel(agentModel);
   const { headers, baseUrl } = getAuth();
   // Split images into URLs vs local files
   const imageUrlList = chatImages.filter(p => p.startsWith('http://') || p.startsWith('https://'));
@@ -1962,7 +2028,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
 
   if (useStream) {
     // Legacy SSE mode
-    const { results } = await streamAgent(baseUrl, headers, projectId, finalPrompt);
+    const { results } = await streamAgent(baseUrl, headers, projectId, finalPrompt, { videoModel, videoResolution, preferredModel, agentModel });
     process.stderr.write('\n━━━ Results ━━━\n');
     for (const img of results.images) process.stderr.write(`🖼️  Image: ${img.imageUrl}\n`);
     for (const d of results.designs) process.stderr.write(`🎨  ${d.desc}\n`);
@@ -1971,7 +2037,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     for (const task of results.musicTasks) await pollMusic(baseUrl, headers, task.taskId);
   } else {
     // Default: fire-and-forget + poll
-    const { runId } = await submitRun(baseUrl, headers, projectId, finalPrompt, { videoModel, videoResolution, preferredModel, audioAttachments });
+    const { runId } = await submitRun(baseUrl, headers, projectId, finalPrompt, { videoModel, videoResolution, preferredModel, agentModel, audioAttachments });
     if (background) {
       // Just print runId and exit
       if (jsonOutput) {
@@ -2238,7 +2304,11 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   let outputPath = null;
   for (let i = 1; i < args.length; i++) {
     if (args[i] === '--image' && args[i + 1]) editArgs.image = imageToArg(args[++i]);
-    else if (args[i] === '--model' && args[i + 1]) editArgs.model = args[++i];
+    else if (args[i] === '--image-model' && args[i + 1]) editArgs.model = args[++i];
+    else if (args[i] === '--model' && args[i + 1]) {
+      warnLegacyModelFlag('--image-model');
+      editArgs.model = args[++i];
+    }
     else if (args[i] === '--skill' && args[i + 1]) editArgs.skill = args[++i];
     else if (args[i] === '--ref' && args[i + 1]) {
       editArgs.referenceImages = editArgs.referenceImages || [];
@@ -2249,7 +2319,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     else promptParts.push(args[i]);
   }
   editArgs.editPrompt = promptParts.join(' ');
-  if (!editArgs.editPrompt) { console.error('Usage: makaron edit [--image <file|url>] [--model gemini|gemini-lite|qwen|openai|pony|wai] [--ref <file>] [--out <file>] "prompt"'); process.exit(1); }
+  if (!editArgs.editPrompt) { console.error('Usage: makaron edit [--image <file|url>] [--image-model gemini|gemini-lite|qwen|openai|pony|wai] [--ref <file>] [--out <file>] "prompt"'); process.exit(1); }
   process.stderr.write('🎨 Generating...\n');
   const result = await callMcpTool(baseUrl, headers, 'makaron_edit_image', editArgs);
   saveMcpImage(result, outputPath);
@@ -2294,7 +2364,11 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       else if (args[i] === '--script-file' && args[i + 1]) script = fs.readFileSync(args[++i], 'utf-8');
       else if (args[i] === '--duration' && args[i + 1]) duration = Number(args[++i]);
       else if (args[i] === '--aspect' && args[i + 1]) aspectRatio = args[++i];
-      else if (args[i] === '--model' && args[i + 1]) videoModel = args[++i];
+      else if (args[i] === '--video-model' && args[i + 1]) videoModel = args[++i];
+      else if (args[i] === '--model' && args[i + 1]) {
+        warnLegacyModelFlag('--video-model');
+        videoModel = args[++i];
+      }
       else if (args[i] === '--video-resolution' && args[i + 1]) videoResolution = args[++i];
       else if (args[i] === '--resolution' && args[i + 1]) videoResolution = args[++i];
       else if (args[i] === '--keep-original-sound') keepOriginalSound = true;
@@ -2304,8 +2378,10 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       }
       else if (args[i] === '--wait') wait = true;
     }
-    if ((!images.length && !video) || !script) {
-      console.error('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model seedance-fast|seedance-mini|seedance|kling|grok|google-omni] [--video-resolution auto|480p|720p|1080p|4k] [--keep-original-sound]');
+    const selectedVideoModel = videoModel || 'seedance-fast';
+    const isSeedanceModel = selectedVideoModel === 'seedance-fast' || selectedVideoModel === 'seedance-mini' || selectedVideoModel === 'seedance';
+    if (!script || (!images.length && !video && !isSeedanceModel)) {
+      console.error('Usage: makaron video create --script "..." [--image <url> | --video <public-url>] [--duration 10] [--aspect 9:16] [--video-model seedance-fast|seedance-mini|seedance|kling|grok|google-omni] [--video-resolution auto|480p|720p|1080p|4k] [--keep-original-sound]');
       process.exit(1);
     }
 
@@ -2316,7 +2392,6 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
 
     let videoUrl = isHttpUrl(video) ? video : null;
     let inputVideoMeta = null;
-    const selectedVideoModel = videoModel || 'seedance-fast';
     if (videoUrl) {
       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; Google Omni accepts one reference video in Makaron; Grok does not support video references.\n`);
     }
@@ -2391,8 +2466,9 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   } else {
     console.log(`Video commands:
   video script --image <file> [--image <file>] "direction"   Write video script
+  video create --script "..." --video-model seedance-fast    Native text-to-video (no image required)
   video create --script "..." --image <url> [--duration 10]  Submit video task
-  video create --script "..." --video <public-url> [--model seedance-fast|seedance-mini|seedance|kling|google-omni]  Edit a video (standalone; Grok does not support video refs)
+  video create --script "..." --video <public-url> [--video-model seedance-fast|seedance-mini|seedance|kling|google-omni]  Edit a video (standalone; Grok does not support video refs)
   video status <taskId>                                      Check video status
   video status --snapshot <snapshotId> [--wait]              Check v2 video snapshot
 `);
@@ -2438,18 +2514,23 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   const sub = args[1];
 
   if (sub === 'skills') {
-    const action = args[2]; // add, update, delete, or none (list)
+    const action = args[2] === '--json' ? null : args[2]; // add, update, delete, or none (list)
     if (!action) {
       // List all skills
       const res = await fetch(`${baseUrl}/api/admin/home-skills`, { headers });
       if (!res.ok) { console.error(`Error ${res.status}:`, await res.text()); process.exit(1); }
       const skills = await res.json();
+      if (args.includes('--json')) {
+        console.log(JSON.stringify(skills, null, 2));
+        process.exit(0);
+      }
       console.log(`📋 ${skills.length} skills\n`);
       for (const s of skills) {
         const label = s.labels?.en || s.labels?.zh || '(no label)';
         const active = s.is_active ? '✅' : '❌';
         const hasZip = s.skill_path ? '📦' : '  ';
-        console.log(`  ${active} ${hasZip} ${String(s.sort_order).padStart(3)}  ${s.id}  ${label}`);
+        const categories = Array.isArray(s.categories) && s.categories.length ? s.categories.join(',') : 'uncategorized';
+        console.log(`  ${active} ${hasZip} ${String(s.sort_order).padStart(3)}  ${s.id}  ${label}  [${categories}]  title ${localizedCoverage(s.labels)}/4 · prompt ${localizedCoverage(s.prompts)}/4`);
       }
     } else if (action === 'add') {
       const json = args.slice(3).join(' ');
@@ -2487,6 +2568,59 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       process.exit(1);
     }
 
+  } else if (sub === 'skill-categories') {
+    const action = args[2] === '--json' ? null : args[2];
+    if (!action) {
+      const res = await fetch(`${baseUrl}/api/admin/skill-categories`, { headers });
+      if (!res.ok) { console.error(`Error ${res.status}:`, await res.text()); process.exit(1); }
+      const categories = await res.json();
+      if (args.includes('--json')) {
+        console.log(JSON.stringify(categories, null, 2));
+        process.exit(0);
+      }
+      console.log(`📂 ${categories.length} skill categories\n`);
+      for (const category of categories) {
+        const label = category.labels?.en || category.labels?.zh || category.id;
+        const active = category.is_active ? '✅' : '❌';
+        const icon = category.icon || ' ';
+        console.log(`  ${active} ${icon} ${String(category.sort_order).padStart(3)}  ${category.id}  ${label}  title ${localizedCoverage(category.labels)}/4`);
+      }
+    } else if (action === 'add') {
+      const json = args.slice(3).join(' ');
+      if (!json) { console.error('Usage: makaron admin skill-categories add \'{"id":"...","labels":{...}}\''); process.exit(1); }
+      let body;
+      try { body = JSON.parse(json); } catch { console.error('Invalid JSON'); process.exit(1); }
+      const res = await fetch(`${baseUrl}/api/admin/skill-categories`, {
+        method: 'POST', headers: { 'Content-Type': 'application/json', ...headers }, body: JSON.stringify(body),
+      });
+      if (!res.ok) { console.error(`Error ${res.status}:`, await res.text()); process.exit(1); }
+      const data = await res.json();
+      console.log(`✅ Skill category created: ${data.id}`);
+    } else if (action === 'update') {
+      const id = args[3];
+      const json = args.slice(4).join(' ');
+      if (!id || !json) { console.error('Usage: makaron admin skill-categories update <id> \'{"field":"value"}\''); process.exit(1); }
+      let body;
+      try { body = JSON.parse(json); } catch { console.error('Invalid JSON'); process.exit(1); }
+      body.id = id;
+      const res = await fetch(`${baseUrl}/api/admin/skill-categories`, {
+        method: 'PUT', headers: { 'Content-Type': 'application/json', ...headers }, body: JSON.stringify(body),
+      });
+      if (!res.ok) { console.error(`Error ${res.status}:`, await res.text()); process.exit(1); }
+      console.log(`✅ Skill category ${id} updated`);
+    } else if (action === 'delete') {
+      const id = args[3];
+      if (!id) { console.error('Usage: makaron admin skill-categories delete <id>'); process.exit(1); }
+      const res = await fetch(`${baseUrl}/api/admin/skill-categories`, {
+        method: 'DELETE', headers: { 'Content-Type': 'application/json', ...headers }, body: JSON.stringify({ id }),
+      });
+      if (!res.ok) { console.error(`Error ${res.status}:`, await res.text()); process.exit(1); }
+      console.log(`✅ Skill category ${id} deleted`);
+    } else {
+      console.error(`Unknown action: ${action}. Use: add, update, delete, or omit to list.`);
+      process.exit(1);
+    }
+
   } else if (sub === 'upload') {
     const filePath = args[2];
     const storagePath = args[3];
@@ -2546,6 +2680,10 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   admin skills add '<json>'            Add a new skill
   admin skills update <id> '<json>'    Update a skill
   admin skills delete <id>             Delete a skill
+  admin skill-categories               List marketplace categories
+  admin skill-categories add '<json>'  Add a category
+  admin skill-categories update <id> '<json>'
+  admin skill-categories delete <id>   Delete a category
   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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.12.2",
+  "version": "0.13.1",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/SKILL.md

@@ -77,8 +77,13 @@ npx makaron-cli chat --project <id> --json -b "<prompt>"
 # Auto-create project (with or without images)
 npx makaron-cli chat --project auto --image photo.jpg --json -b "make it cinematic"
 npx makaron-cli chat --project auto --image img1.jpg --image img2.jpg --json -b "combine these"
+
+# Choose each model role explicitly
+npx makaron-cli chat --project auto --agent-model deepseek-v4-pro --image-model qwen "design a product poster"
 ```
 
+Model flags are role-specific: `--agent-model` controls reasoning and tool use, `--image-model` controls image generation/editing, and `--video-model` controls video generation. `--agent-model` accepts `auto|gpt-5.6-terra|gpt-5.6-sol|gpt-5.6-luna|grok-4.5|deepseek-v4-pro`. `auto` currently uses GPT-5.6 Terra. `MAKARON_AGENT_MODEL` can set the default for automation; the command flag takes precedence. The legacy `--model` flag remains temporarily supported with a deprecation warning.
+
 Returns immediately:
 ```json
 {"runId": "xxx", "projectId": "...", "projectUrl": "https://www.makaron.app/projects/...", "status": "running"}
@@ -121,7 +126,9 @@ npx makaron-cli chat --project auto \
   -b "make this with the selected skill"
 ```
 
-`--skill` accepts an installed skill name, a marketplace UUID, or a unique marketplace label. If a marketplace skill is matched, the CLI installs or reuses it and sends `[Active skill: <installed-skill-name>]` to Makaron Agent. Do not call admin skill commands for ordinary users. There is intentionally no user-facing CLI delete command for marketplace skills.
+`--skill` accepts an installed skill name, a marketplace UUID, or a unique marketplace label. Marketplace search matches every localized title, every localized default prompt, and category ids. If a marketplace skill is matched, the CLI installs or reuses it and sends `[Active skill: <installed-skill-name>]` to Makaron Agent. Do not call admin skill commands for ordinary users. There is intentionally no user-facing CLI delete command for marketplace skills.
+
+For an explicitly authorized marketplace administrator, `admin skills` shows category assignment and 4-locale title/prompt completeness, while `admin skill-categories` supports list/add/update/delete. New skills must include `en`, `zh`, `zh-Hant`, and `ja` in both `labels` and `prompts`, plus at least one existing `categories` id. Partial localized updates are safely merged server-side.
 
 ### With additional images (existing project)
 
@@ -238,7 +245,7 @@ npx makaron-cli edit --image photo.jpg --ref style.jpg "match this style"
 npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 ```
 
-Options: `--image`, `--model gemini|gemini-lite|qwen|openai|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
+Options: `--image`, `--image-model gemini|gemini-lite|qwen|openai|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
 
 ### `video` — Standalone video tools (no project timeline)
 
@@ -250,12 +257,15 @@ npx makaron-cli video script --image img1.jpg "cinematic story"
 npx makaron-cli analyze --video input.mp4 "describe the key actions and pacing"
 
 # 3a. Submit image-to-video rendering (images must be public URLs from step 1 or uploaded)
-npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --model kling
-npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_2>>> build a neon one-person studio" --image https://...jpg --image https://...webp --duration 15 --model seedance-mini --video-resolution 480p --aspect 9:16
+npx makaron-cli video create --script "Shot 1 (5s): <<<image_1>>> ..." --image https://...jpg --duration 5 --video-model kling
+npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_2>>> build a neon one-person studio" --image https://...jpg --image https://...webp --duration 15 --video-model seedance-mini --video-resolution 480p --aspect 9:16
+
+# 3b. Native SeeDance text-to-video (no image required)
+npx makaron-cli video create --script "Shot 1 (5s): A neon one-person studio wakes at dawn" --duration 5 --video-model seedance-fast --aspect 16:9
 
-# 3b. Edit a video from a local file or public URL
-npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --model seedance-fast
-npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance --video-resolution 1080p
+# 3c. Edit a video from a local file or public URL
+npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --video-model seedance-fast
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --video-model seedance --video-resolution 1080p
 
 # 4. Check status
 npx makaron-cli video status <taskId>
@@ -267,9 +277,9 @@ 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 seedance-fast|seedance-mini|seedance|kling|grok|google-omni`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio. For `--model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
+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`, `--video-model seedance-fast|seedance-mini|seedance|kling|grok|google-omni`, `--video-resolution auto|480p|720p|1080p|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
-Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance-fast --video`, `--model seedance-mini --video`, or `--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. `--model google-omni --video` uses Gemini Omni direct video editing and accepts one reference video in Makaron. Output duration is clamped to 3-10s. Grok does not support video references.
+Video edit model behavior: `--video-model kling --video` uses Kling base/direct edit internally; `--video-model seedance-fast --video`, `--video-model seedance-mini --video`, or `--video-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. `--video-model google-omni --video` uses Gemini Omni direct video editing and accepts one reference video in Makaron. Output duration is clamped to 3-10s. Grok does not support video references.
 
 ### `music` — Music generation