makaron-cli 0.15.2 → 0.15.4

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.15.2",
+  "version": "0.15.4",
   "description": "Give Claude Code a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
     "name": "Versa AI",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.15.2",
+  "version": "0.15.4",
   "description": "Give Codex a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
     "name": "Versa AI",

package/README.md

@@ -246,7 +246,7 @@ npx makaron-cli composition export --project <projectId> --snapshot <snapshotId>
 npx makaron-cli composition status <jobId> --wait
 ```
 
-`materialize` is the preferred high-level command for Remotion-to-MP4. It defaults to `--wait`, `--publish`, and the `fast_720p` profile (short side 720, no upscale), so the completed MP4 is also added back to the project timeline like CUI. Use `--no-publish` only when you need a file URL without a new timeline video. Use `--profile source` only when full source resolution is required.
+`materialize` is the preferred high-level command for Remotion-to-MP4. It defaults to `--wait`, `--publish`, and the `source` profile, preserving the composition's dimensions when the MP4 is added back to the project timeline. Use `--no-publish` when you need only a file URL. Use `--profile fast_720p` only when a 720-short-side export is acceptable.
 
 For a run that produced an animated composition, materialize before picking the video URL:
 
@@ -262,7 +262,7 @@ npx makaron-cli materialize --project <projectId> --design-json composition.json
 cat composition.json | npx makaron-cli materialize --project <projectId> --design-json - --pick url
 ```
 
-This JSON-to-MP4 path uses the same defaults as timeline materialize: `--wait`, `--publish`, and `fast_720p`. Add `--no-publish` only when another agent needs the MP4 URL but should not add a timeline video.
+This JSON-to-MP4 path uses the same defaults as timeline materialize: `--wait`, `--publish`, and `source`. Add `--no-publish` when another agent needs the MP4 URL without adding a timeline video.
 
 The completed export reports `duration_seconds`, `render_seconds`, and `realtime_ratio` so agents can compare video length against export time. Do not apply provider-video ETA rules to Remotion materialize; with a warm exporter it is often near video length to tens of seconds, while cold starts can be longer.
 
@@ -384,7 +384,7 @@ npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 npx makaron-cli edit --image-model gpt-image-2.5-flare --background transparent --out sticker.png "a magenta star sticker"
 ```
 
-Options: `--image`, `--image-model gemini|gemini-lite|qwen|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--background auto|opaque|transparent`, `--out <path>`. Qwen Spicy is an independent 1–3 image editor; `qwen` remains the existing self-hosted model. Transparent output routes strictly to GPT Image 2.5 Flare and is returned only when the provider supplies real PNG/WebP alpha.
+Options: `--image`, `--image-model gemini|gemini-lite|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--background auto|opaque|transparent`, `--out <path>`. Qwen Spicy supports 0–3 input images; legacy `qwen` requests map to it. Pony and WAI are retired. Transparent output routes strictly to GPT Image 2.5 Flare and is returned only when the provider supplies real PNG/WebP alpha.
 
 `wan2.7-image` uses Alibaba international for fast, approximately 1K generation and editing (default 6 credits/image). Failed or timed-out Wan requests are not automatically retried or switched to another model. Face identity can change. Example: `makaron edit --image portrait.jpg --image-model wan2.7-image --aspect 16:9 --out stadium.jpg "Place this woman in a baseball stadium, preserving her face."`
 

package/bin/makaron.mjs

@@ -1160,7 +1160,7 @@ async function exportComposition(baseUrl, headers, opts = {}) {
     designPath: opts.designPath,
     design: opts.design,
     outputType: opts.outputType || 'video',
-    renderProfile: opts.renderProfile || 'fast_720p',
+    renderProfile: opts.renderProfile || 'source',
     publish: opts.publish === true,
     name: opts.name,
   };
@@ -1936,7 +1936,7 @@ Usage:
 Options:
   --image <file|url>        Base image to edit. Omit for text-to-image.
   --ref <file|url>          Additional reference image. Repeatable, up to 3.
-  --image-model <id>        gemini, gemini-lite, qwen, qwen-spicy, openai, gpt-image-2.5-flare, gpt-image-2.5-sunburst, wan2.7-image, pony, or wai.
+  --image-model <id>        gemini, gemini-lite, qwen-spicy, openai, gpt-image-2.5-flare, gpt-image-2.5-sunburst, or wan2.7-image. Legacy qwen maps to qwen-spicy.
   --skill <id>              enhance, creative, wild, or captions.
   --aspect <ratio>          Output aspect ratio, for example 1:1, 16:9, or 9:16.
   --background <mode>       auto, opaque, or transparent.
@@ -1948,7 +1948,7 @@ Notes:
   and fails instead of returning an opaque fallback.
 
 Examples:
-  makaron edit --image portrait.jpg --image-model qwen --out result.jpg "cinematic warm light"
+  makaron edit --image portrait.jpg --image-model qwen-spicy --out result.jpg "cinematic warm light"
   makaron edit --image product.jpg --ref style.png --aspect 1:1 "use this visual style"
   makaron edit --image-model gpt-image-2.5-flare --background transparent --out sticker.png "a magenta star sticker"
 `);
@@ -2799,7 +2799,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   await listProjects(baseUrl, headers);
 } else if (command === 'materialize') {
   const { headers, baseUrl } = getAuth();
-  const opts = { wait: true, publish: true, json: false, outputType: 'video', renderProfile: 'fast_720p', pick: null, quiet: false };
+  const opts = { wait: true, publish: true, json: false, outputType: 'video', renderProfile: 'source', pick: null, quiet: false };
   for (let i = 1; i < args.length; i++) {
     if (args[i] === '--project' && args[i + 1]) opts.projectId = args[++i];
     else if (args[i] === '--media' && args[i + 1]) opts.mediaIndex = Number(args[++i]);
@@ -2827,7 +2827,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   const { headers, baseUrl } = getAuth();
   const sub = args[1];
   if (sub === 'export') {
-    const opts = { wait: false, publish: false, json: false, outputType: 'video', renderProfile: 'fast_720p', pick: null, quiet: false };
+    const opts = { wait: false, publish: false, json: false, outputType: 'video', renderProfile: 'source', pick: null, quiet: false };
     for (let i = 2; i < args.length; i++) {
       if (args[i] === '--project' && args[i + 1]) opts.projectId = args[++i];
       else if (args[i] === '--media' && args[i + 1]) opts.mediaIndex = Number(args[++i]);
@@ -3043,7 +3043,7 @@ 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>] [--image-model gemini|gemini-lite|qwen|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image|pony|wai] [--ref <file>] [--aspect <ratio>] [--background auto|opaque|transparent] [--out <file>] "prompt"'); process.exit(1); }
+  if (!editArgs.editPrompt) { console.error('Usage: makaron edit [--image <file|url>] [--image-model gemini|gemini-lite|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image] [--ref <file>] [--aspect <ratio>] [--background auto|opaque|transparent] [--out <file>] "prompt"'); process.exit(1); }
   process.stderr.write('🎨 Generating...\n');
   const result = await callMcpTool(baseUrl, headers, 'makaron_edit_image', editArgs);
   saveMcpImage(result, outputPath);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.15.2",
+  "version": "0.15.4",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/SKILL.md

@@ -315,7 +315,7 @@ npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 npx makaron-cli edit --image-model gpt-image-2.5-flare --background transparent --out sticker.png "a magenta star sticker"
 ```
 
-Options: `--image`, `--image-model gemini|gemini-lite|qwen|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image|pony|wai`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--background auto|opaque|transparent`, `--out <path>`. Qwen Spicy is an independent 1–3 image editor; `qwen` remains the existing self-hosted model. Transparent output routes strictly to GPT Image 2.5 Flare and fails instead of returning an opaque fallback. Wan 2.7 Image is an explicit fast ~1K route; do not automatically retry failures/timeouts, and do not promise exact face preservation.
+Options: `--image`, `--image-model gemini|gemini-lite|qwen-spicy|openai|gpt-image-2.5-flare|gpt-image-2.5-sunburst|wan2.7-image`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--background auto|opaque|transparent`, `--out <path>`. Qwen Spicy supports 0–3 input images; legacy `qwen` requests map to it. Pony and WAI are retired. Transparent output routes strictly to GPT Image 2.5 Flare and fails instead of returning an opaque fallback. Wan 2.7 Image is an explicit fast ~1K route; do not automatically retry failures/timeouts, and do not promise exact face preservation.
 
 ### `video` — Standalone video tools (no project timeline)
 
@@ -452,7 +452,7 @@ npx makaron-cli materialize --project <projectId> --design-json composition.json
 npx makaron-cli responses get <runId> --materialize --wait --pick first_video_url
 ```
 
-`materialize` defaults to `--wait`, `--publish`, and `fast_720p`, so the completed MP4 is added back to the timeline like CUI. Use `--no-publish` only when you need a file URL without a new timeline video. The completed export reports `duration_seconds`, `render_seconds`, and `realtime_ratio`; use those metrics instead of provider-video ETA rules.
+`materialize` defaults to `--wait`, `--publish`, and `source`, preserving composition dimensions when the MP4 is added back to the timeline. Use `--no-publish` when you need only a file URL, or `--profile fast_720p` when a 720-short-side export is acceptable. The completed export reports `duration_seconds`, `render_seconds`, and `realtime_ratio`; use those metrics instead of provider-video ETA rules.
 
 For JSON-to-MP4, pass a Makaron/Remotion composition JSON with `--design-json`. This is the correct CLI path when another agent already has the composition JSON and only needs the exported video:
 

package/skills/makaron/references/nsfw.md

@@ -11,7 +11,7 @@ If adult intent is ambiguous, ask one short question before choosing this lane.
 | Adult request | Route |
 |---|---|
 | Agent-driven work or a persistent Makaron project | `makaron chat` with Agent model `grok-4.6` |
-| Standalone image generation or editing | `makaron edit` with image model `qwen` |
+| Standalone image generation or editing | `makaron edit` with image model `qwen-spicy` |
 | Standalone video generation | `makaron video create` with video model `wan-3.0-prime` |
 
 For project-based work, keep the complete request in one `chat` job. Because
@@ -20,20 +20,20 @@ brief:
 
 ```bash
 npx makaron-cli chat --project <id|auto> --agent-model grok-4.6 --json \
-  -b "<complete adult request; use qwen for still images and wan-3.0-prime for video>"
+  -b "<complete adult request; use qwen-spicy for still images and wan-3.0-prime for video>"
 ```
 
 For explicit raw-tool work without a project timeline:
 
 ```bash
-npx makaron-cli edit --image-model qwen --image <file-or-url> --out <path> "<prompt>"
+npx makaron-cli edit --image-model qwen-spicy --image <file-or-url> --out <path> "<prompt>"
 npx makaron-cli video create --video-model wan-3.0-prime --script "<shot script>" --duration <seconds>
 ```
 
 ## Keep the exception scoped
 
-- Do not force SFW jobs onto Grok, Qwen, or Wan 3.0 Prime.
-- Never put `qwen` or `wan-3.0-prime` in `--agent-model`.
+- Do not force SFW jobs onto Grok, Qwen Spicy, or Wan 3.0 Prime.
+- Never put `qwen-spicy` or `wan-3.0-prime` in `--agent-model`.
 - Do not pass `--image-model` or `--video-model` to `makaron chat`; it rejects
   those flags. State those preferences in the chat brief or use the standalone
   commands.