makaron-cli 0.7.1 → 0.7.5

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.6.2",
+  "version": "0.7.3",
   "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": "0.6.2",
+  "version": "0.7.3",
   "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

@@ -97,6 +97,23 @@ Returns immediately:
 npx makaron-cli chat --project <id> --image ref1.jpg --image ref2.jpg -b "use these as style reference"
 ```
 
+### With video input (MP4/MOV/WebM)
+
+```bash
+# Upload a video and ask the agent to edit it
+npx makaron-cli chat --project auto --video clip.mp4 -b "put Iron Man armor on me in this video"
+
+# Combine video + image references
+npx makaron-cli chat --project <id> --video party.mp4 --image kid.jpg -b "make this kid appear in the party"
+
+# Multiple videos (for composition / continuation)
+npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "splice these into one seamless video"
+```
+
+Video files are uploaded via signed URL. CLI local video uploads follow the same compatibility contract as the normal frontend flow: `.mp4`, `.mov`, or `.webm`, max 200MB, max 15s, and <=1080p / 2,086,876 frame pixels. The frontend can transcode oversized videos; the CLI rejects them so later Seedance editing does not fail.
+The agent understands video content natively — it can analyze scenes, edit, extend, and compose videos. Seedance video-reference editing is supported for <=15s videos that meet the same upload limits; Kling remains the base/direct edit path.
+Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct `video create` is standalone and does not write timeline entries.
+
 ### Check status (single query)
 
 ```bash
@@ -153,20 +170,35 @@ npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 
 Options: `--image`, `--model gemini|qwen|openai|pony|wai`, `--skill enhance|creative|wild|captions`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
 
-### `video` — Video generation (3 steps)
+### `video` — Standalone video tools (no project timeline)
 
 ```bash
 # 1. Write script from images
 npx makaron-cli video script --image img1.jpg "cinematic story"
 
-# 2. Submit rendering (images must be public URLs from step 1 or uploaded)
+# 2. Analyze a video (standalone, no timeline write)
+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
 
-# 3. Check status
+# 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
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance
+
+# 4. Check status
 npx makaron-cli video status <taskId>
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--duration 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+For project/timeline video editing, use:
+
+```bash
+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 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires <=15s, <=1080p input.
 
 ### `music` — Music generation
 
@@ -224,6 +256,9 @@ type MakaronOutput =
 | Text-to-image | "generate a cyberpunk cityscape" |
 | Video from image | "create a 5 second video of her walking" |
 | Video with model | "use seedance model, make a 5s video" |
+| **Edit video** | **"put Iron Man armor on me in this video"** |
+| **Compose videos** | **"combine @1 and @2 into one party video"** |
+| **Extend video** | **"continue the story for 10 more seconds"** |
 | Background music | "add calm piano music" |
 | Motion design | "create an Instagram story with animated text" |
 | Multi-step | "edit the photo then make a video from it" |

package/SKILL.md

@@ -86,20 +86,25 @@ Returns immediately:
 npx makaron-cli chat --project <id> --image ref1.jpg --image ref2.jpg -b "use these as style reference"
 ```
 
-### With video input
+### With video input (edit, compose, extend)
 
 ```bash
-# Upload a video file — Agent can analyze, edit, or use it as reference
-npx makaron-cli chat --project <id> --video clip.mp4 -b "edit this video to be more cinematic"
+# Upload a video and transform it — Agent understands video content natively
+npx makaron-cli chat --project auto --video selfie.mp4 -b "put Iron Man armor on me"
 
-# Video URL (public, downloadable)
-npx makaron-cli chat --project auto --video https://example.com/video.mp4 -b "make a 10s highlight reel"
+# Combine a person's photo with a video scene
+npx makaron-cli chat --project <id> --video party.mp4 --image kid.jpg -b "make this kid join the party"
+
+# Multiple videos — compose or splice
+npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "combine into one seamless video"
 
-# Mix images + video
-npx makaron-cli chat --project auto --image photo.jpg --video clip.mp4 -b "combine the photo style with this video"
+# Video URL (public, downloadable)
+npx makaron-cli chat --project auto --video https://example.com/dance.mp4 -b "extend this to 15 seconds"
 ```
 
-Supported formats: MP4, MOV, WebM (max 200MB). Videos are uploaded to the project timeline and available to the Agent for analysis and editing.
+Supported formats: MP4, MOV, WebM. CLI local video uploads follow the same compatibility contract as the normal frontend flow: max 200MB, max 15s, and <=1080p / 2,086,876 frame pixels. The frontend can transcode oversized videos; the CLI rejects them so later Seedance editing does not fail. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance video-reference editing is supported for <=15s videos that meet these upload limits; Kling remains the base/direct edit path.
+
+Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct video commands are standalone raw-tool calls.
 
 ### Check status (single query)
 
@@ -157,20 +162,35 @@ npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 
 Options: `--image`, `--model gemini|qwen|openai|pony|wai`, `--skill enhance|creative|wild|captions`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
 
-### `video` — Video generation (3 steps)
+### `video` — Standalone video tools (no project timeline)
 
 ```bash
 # 1. Write script from images
 npx makaron-cli video script --image img1.jpg "cinematic story"
 
-# 2. Submit rendering (images must be public URLs from step 1 or uploaded)
+# 2. Analyze a video (standalone, no timeline write)
+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
 
-# 3. Check status
+# 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
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance
+
+# 4. Check status
 npx makaron-cli video status <taskId>
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--duration 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+`video create` returns a provider task id and does not create or update a Makaron project timeline. For project/timeline video editing, use:
+
+```bash
+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 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires <=15s, <=1080p input.
 
 ### `music` — Music generation
 

package/bin/makaron.mjs

@@ -14,6 +14,7 @@
 import fs from 'fs';
 import path from 'path';
 import { createInterface } from 'readline';
+import { execFileSync } from 'child_process';
 
 // ─── Config ──────────────────────────────────────────────────────────────────
 
@@ -26,6 +27,10 @@ const APP_URL = process.env.MAKARON_APP_URL || DEFAULT_URL;
 const SUPABASE_URL = 'https://sdyrtztrjgmmpnirswxt.supabase.co';
 const SUPABASE_ANON_KEY = 'sb_publishable_FJFN2YYaWaQjABUKLqxQcA_fhxPLFDY';
 
+const MAX_VIDEO_FILE_SIZE = 200 * 1024 * 1024;
+const MAX_VIDEO_DURATION = 15;
+const MAX_VIDEO_FRAME_PIXELS = 2_086_876;
+
 // ─── Auth ────────────────────────────────────────────────────────────────────
 
 function loadAuth() {
@@ -116,6 +121,15 @@ function getAuth() {
   };
 }
 
+function normalizeRunResponse(data) {
+  const projectId = data.projectId || data.project_id;
+  if (projectId) {
+    data.projectId = projectId;
+    data.projectUrl = `${APP_URL}/projects/${projectId}`;
+  }
+  return data;
+}
+
 // ─── SSE Consumer ────────────────────────────────────────────────────────────
 
 async function abortRun(baseUrl, headers, runId) {
@@ -351,8 +365,7 @@ async function pollRun(baseUrl, headers, runId, opts = {}) {
 
       if (json) {
         // Structured JSON output — add projectUrl
-        data.projectUrl = `${APP_URL}/projects/${data.projectId}`;
-        console.log(JSON.stringify(data, null, 2));
+        console.log(JSON.stringify(normalizeRunResponse(data), null, 2));
       } else {
         process.stderr.write('\n━━━ Results ━━━\n');
         if (data.result) {
@@ -360,6 +373,7 @@ async function pollRun(baseUrl, headers, runId, opts = {}) {
           for (const d of data.result.designs || []) process.stderr.write(`🎨  Design (${d.width}x${d.height})\n`);
           for (const v of data.result.videos || []) {
             if (v.videoUrl) process.stderr.write(`🎬  Video: ${v.videoUrl}\n`);
+            else if (v.status === 'failed') process.stderr.write(`🎬  Video ${v.taskId}: failed${v.error ? ` — ${v.error}` : ''}\n`);
             else process.stderr.write(`🎬  Video ${v.taskId}: ${v.status || 'submitted'}\n`);
           }
           for (const m of data.result.music || []) {
@@ -432,7 +446,7 @@ async function watchRun(baseUrl, headers, runId, opts = {}) {
       } else if (JSON.stringify(prev) !== JSON.stringify(item)) {
         // Updated item (e.g. video status changed)
         if (jsonl) console.log(JSON.stringify({ event: 'output.updated', item }));
-        else process.stderr.write(`~ [${item.type}] ${item.status} ${item.url || ''}\n`);
+        else process.stderr.write(`~ [${item.type}] ${item.status} ${item.url || item.error || ''}\n`);
       }
     }
 
@@ -468,7 +482,7 @@ async function pollVideo(baseUrl, headers, taskId, snapshotId) {
       if (!res.ok) continue;
       const data = await res.json();
       if (data.videoUrl) { process.stderr.write(`\r🎬 Video done (${elapsed}s): ${data.videoUrl}\n`); return data.videoUrl; }
-      if (data.status === 'failed' || data.status === 'abandoned') { process.stderr.write(`\r🎬 Video ${data.status} (${elapsed}s)\n`); return null; }
+      if (data.status === 'failed' || data.status === 'abandoned') { process.stderr.write(`\r🎬 Video ${data.status} (${elapsed}s)${data.error ? `: ${data.error}` : ''}\n`); return null; }
       process.stderr.write(`\r🎬 Video rendering... ${elapsed}s`);
     } catch { /* retry */ }
     if (elapsed > 600) { process.stderr.write(`\r🎬 Video timeout (${elapsed}s)\n`); return null; }
@@ -652,6 +666,104 @@ function imageToArg(imgPath) {
   return readImageAsDataUrl(imgPath);
 }
 
+function isHttpUrl(value) {
+  return value?.startsWith('http://') || value?.startsWith('https://');
+}
+
+function probeVideoWithFfprobe(videoPath) {
+  try {
+    const out = execFileSync('ffprobe', [
+      '-v', 'error',
+      '-select_streams', 'v:0',
+      '-show_entries', 'stream=width,height:format=duration',
+      '-of', 'json',
+      videoPath,
+    ], { encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'] });
+    const data = JSON.parse(out);
+    const stream = data.streams?.[0] || {};
+    const duration = Number(data.format?.duration);
+    const width = Number(stream.width);
+    const height = Number(stream.height);
+    if (Number.isFinite(duration) && width > 0 && height > 0) {
+      return { duration, width, height };
+    }
+  } catch { /* ffprobe unavailable or file unsupported */ }
+  return null;
+}
+
+function probeVideoWithFfmpeg(videoPath) {
+  try {
+    const out = execFileSync('ffmpeg', ['-i', videoPath], {
+      encoding: 'utf8',
+      stdio: ['ignore', 'pipe', 'pipe'],
+    });
+    return parseFfmpegProbe(out);
+  } catch (e) {
+    const text = `${e.stdout || ''}\n${e.stderr || ''}`;
+    return parseFfmpegProbe(text);
+  }
+}
+
+function parseFfmpegProbe(text) {
+  const durationMatch = text.match(/Duration:\s*(\d+):(\d+):(\d+(?:\.\d+)?)/);
+  const sizeMatch = text.match(/Video:.*?(\d{2,5})x(\d{2,5})/);
+  if (!durationMatch || !sizeMatch) return null;
+  const duration = Number(durationMatch[1]) * 3600 + Number(durationMatch[2]) * 60 + Number(durationMatch[3]);
+  const width = Number(sizeMatch[1]);
+  const height = Number(sizeMatch[2]);
+  if (!Number.isFinite(duration) || width <= 0 || height <= 0) return null;
+  return { duration, width, height };
+}
+
+function probeLocalVideo(videoPath) {
+  return probeVideoWithFfprobe(videoPath) || probeVideoWithFfmpeg(videoPath);
+}
+
+function validateVideoFile(videoPath) {
+  if (!fs.existsSync(videoPath)) {
+    return { ok: false, error: `Video file not found: ${videoPath}` };
+  }
+  const stat = fs.statSync(videoPath);
+  if (stat.size > MAX_VIDEO_FILE_SIZE) {
+    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max 200MB)` };
+  }
+  const ext = path.extname(videoPath).slice(1).toLowerCase();
+  if (!['mp4', 'mov', 'webm'].includes(ext)) {
+    return { ok: false, error: `Unsupported video format: .${ext}. Use MP4, MOV, or WebM.` };
+  }
+  const meta = probeLocalVideo(videoPath);
+  if (!meta) {
+    return { ok: false, error: 'Cannot read video duration/resolution. Install ffmpeg/ffprobe or use the normal frontend upload flow.' };
+  }
+  if (meta.duration > MAX_VIDEO_DURATION) {
+    return { ok: false, error: `Video too long: ${Math.round(meta.duration)}s (max ${MAX_VIDEO_DURATION}s)` };
+  }
+  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 mime = ext === 'mov' ? 'video/quicktime' : ext === 'webm' ? 'video/webm' : 'video/mp4';
+  return { ok: true, mime, meta };
+}
+
+function validateVideoFileForAnalysis(videoPath) {
+  if (!fs.existsSync(videoPath)) {
+    return { ok: false, error: `Video file not found: ${videoPath}` };
+  }
+  const stat = fs.statSync(videoPath);
+  if (stat.size === 0) {
+    return { ok: false, error: `Video file is empty: ${videoPath}` };
+  }
+  if (stat.size > MAX_VIDEO_FILE_SIZE) {
+    return { ok: false, error: `Video too large: ${(stat.size / 1024 / 1024).toFixed(1)}MB (max 200MB)` };
+  }
+  const ext = path.extname(videoPath).slice(1).toLowerCase();
+  if (!['mp4', 'mov', 'webm'].includes(ext)) {
+    return { ok: false, error: `Unsupported video format: .${ext}. Use MP4, MOV, or WebM.` };
+  }
+  const mime = ext === 'mov' ? 'video/quicktime' : ext === 'webm' ? 'video/webm' : 'video/mp4';
+  return { ok: true, mime };
+}
+
 function saveMcpImage(result, outputPath) {
   const content = result?.content || [];
   const textBlock = content.find(c => c.type === 'text');
@@ -667,6 +779,29 @@ function saveMcpImage(result, outputPath) {
   return null;
 }
 
+async function analyzeVideoCli(baseUrl, headers, rawVideo, questionParts) {
+  if (!rawVideo) {
+    console.error('Usage: makaron analyze --video <file|url> ["question"]');
+    process.exit(1);
+  }
+  let videoUrl = isHttpUrl(rawVideo) ? rawVideo : null;
+  if (videoUrl) {
+    process.stderr.write('📹 Using public video URL for analysis; provider limits apply.\n');
+  } else {
+    const valid = validateVideoFileForAnalysis(rawVideo);
+    if (!valid.ok) { console.error(`❌ ${valid.error}`); process.exit(1); }
+    process.stderr.write(`📹 Uploading ${path.basename(rawVideo)} (${(fs.statSync(rawVideo).size/1024/1024).toFixed(1)}MB)...\n`);
+    videoUrl = await uploadFileViaSignedUrl(baseUrl, headers, undefined, rawVideo, valid.mime);
+    if (!videoUrl) process.exit(1);
+    process.stderr.write(`📹 Uploaded: ${path.basename(rawVideo)}\n`);
+  }
+  process.stderr.write('🔎 Analyzing video...\n');
+  const question = questionParts.join(' ').trim() || undefined;
+  const result = await callMcpTool(baseUrl, headers, 'makaron_analyze_video', { videoUrl, question });
+  const text = result?.content?.find(c => c.type === 'text')?.text;
+  if (text) console.log(text);
+}
+
 // ─── Main ────────────────────────────────────────────────────────────────────
 
 const args = process.argv.slice(2);
@@ -723,6 +858,17 @@ if (command === 'login') {
   // Split images into URLs vs local files
   const imageUrlList = chatImages.filter(p => p.startsWith('http://') || p.startsWith('https://'));
   const imageFileList = chatImages.filter(p => !p.startsWith('http://') && !p.startsWith('https://'));
+  const prevalidatedVideoUrlList = chatVideos.filter(p => p.startsWith('http://') || p.startsWith('https://'));
+  const prevalidatedVideoFileList = chatVideos.filter(p => !p.startsWith('http://') && !p.startsWith('https://'));
+  const prevalidatedVideoMetas = new Map();
+  for (const videoPath of prevalidatedVideoFileList) {
+    const valid = validateVideoFile(videoPath);
+    if (!valid.ok) {
+      process.stderr.write(`❌ ${valid.error}\n`);
+      process.exit(1);
+    }
+    prevalidatedVideoMetas.set(videoPath, valid.meta);
+  }
 
   // --project auto: create a new project (with images/videos if provided)
   if (!projectId || projectId === 'auto') {
@@ -788,40 +934,36 @@ if (command === 'login') {
   // Upload videos to project timeline (via /api/projects/create with videoUrls)
   let finalPrompt = prompt;
   if (chatVideos.length > 0) {
-    const videoUrlList = chatVideos.filter(p => p.startsWith('http://') || p.startsWith('https://'));
-    const videoFileList = chatVideos.filter(p => !p.startsWith('http://') && !p.startsWith('https://'));
-
-    // Validate local video files
-    const validVideoFiles = [];
-    for (const videoPath of videoFileList) {
-      if (!fs.existsSync(videoPath)) { process.stderr.write(`⚠️ Video file not found: ${videoPath}\n`); continue; }
-      const stat = fs.statSync(videoPath);
-      if (stat.size > 200 * 1024 * 1024) { process.stderr.write(`⚠️ Video too large: ${(stat.size/1024/1024).toFixed(1)}MB (max 200MB)\n`); continue; }
-      const ext = path.extname(videoPath).slice(1).toLowerCase();
-      if (!['mp4', 'mov', 'webm'].includes(ext)) { process.stderr.write(`⚠️ Unsupported video format: .${ext}. Use MP4, MOV, or WebM.\n`); continue; }
-      validVideoFiles.push(videoPath);
-    }
-
     // Upload local files via signed URL (no size limit, works with API key auth)
-    const uploadedVideoUrls = [...videoUrlList];
-    for (const videoPath of validVideoFiles) {
+    const uploadedVideoUrls = [...prevalidatedVideoUrlList];
+    const uploadedVideoMetas = prevalidatedVideoUrlList.map(() => null);
+    if (prevalidatedVideoUrlList.length) {
+      process.stderr.write(`📹 Assuming public video URL(s) already match Makaron upload limits: ≤${MAX_VIDEO_DURATION}s, ≤200MB, ≤1080p.\n`);
+    }
+    for (const videoPath of prevalidatedVideoFileList) {
       process.stderr.write(`📹 Uploading ${path.basename(videoPath)} (${(fs.statSync(videoPath).size/1024/1024).toFixed(1)}MB)...\n`);
       const ext = path.extname(videoPath).slice(1).toLowerCase();
       const mime = ext === 'mov' ? 'video/quicktime' : ext === 'webm' ? 'video/webm' : 'video/mp4';
       const url = await uploadFileViaSignedUrl(baseUrl, headers, projectId, videoPath, mime);
       if (url) {
         uploadedVideoUrls.push(url);
+        uploadedVideoMetas.push(prevalidatedVideoMetas.get(videoPath) || null);
         process.stderr.write(`📹 Uploaded: ${path.basename(videoPath)}\n`);
       }
     }
 
     // Add videos to project via projects/create (same as images)
+    if (uploadedVideoUrls.length === 0) {
+      process.stderr.write(`❌ No valid videos were uploaded. Local videos must be MP4/MOV/WebM, ≤${MAX_VIDEO_DURATION}s, ≤200MB, and ≤1080p.\n`);
+      process.exit(1);
+    }
+
     if (uploadedVideoUrls.length > 0) {
-      if (videoUrlList.length) process.stderr.write(`📹 Adding ${uploadedVideoUrls.length} video(s) to timeline...\n`);
+      if (prevalidatedVideoUrlList.length) process.stderr.write(`📹 Adding ${uploadedVideoUrls.length} video(s) to timeline...\n`);
       const res = await fetch(`${baseUrl}/api/projects/create`, {
         method: 'POST',
         headers: { 'Content-Type': 'application/json', ...headers },
-        body: JSON.stringify({ _addToProject: projectId, videoUrls: uploadedVideoUrls }),
+        body: JSON.stringify({ _addToProject: projectId, videoUrls: uploadedVideoUrls, videoMetas: uploadedVideoMetas }),
       });
       if (res.ok) {
         const data = await res.json();
@@ -881,6 +1023,7 @@ if (command === 'login') {
       const res = await fetch(`${baseUrl}/api/agent/run/${runId}`, { headers });
       if (!res.ok) { process.stderr.write(`Error ${res.status}: ${await res.text()}\n`); process.exit(1); }
       const data = await res.json();
+      normalizeRunResponse(data);
       if (pick) {
         const picked = applyPick(data, pick);
         if (picked !== undefined) console.log(typeof picked === 'string' ? picked : JSON.stringify(picked));
@@ -970,6 +1113,16 @@ if (command === 'login') {
   const result = await callMcpTool(baseUrl, headers, 'makaron_edit_image', editArgs);
   saveMcpImage(result, outputPath);
 
+} else if (command === 'analyze') {
+  const { headers, baseUrl } = getAuth();
+  let video = null;
+  const questionParts = [];
+  for (let i = 1; i < args.length; i++) {
+    if (args[i] === '--video' && args[i + 1]) video = args[++i];
+    else questionParts.push(args[i]);
+  }
+  await analyzeVideoCli(baseUrl, headers, video, questionParts);
+
 } else if (command === 'video') {
   const { headers, baseUrl } = getAuth();
   const sub = args[1];
@@ -991,52 +1144,61 @@ if (command === 'login') {
 
   } else if (sub === 'create') {
     const images = [];
-    let script = '', duration = undefined, aspectRatio = undefined, videoModel = undefined, projectId = null, wait = false;
+    let script = '', duration = undefined, aspectRatio = undefined, videoModel = undefined, wait = false;
+    let video = null, keepOriginalSound = false;
     for (let i = 2; i < args.length; i++) {
       if (args[i] === '--image' && args[i + 1]) images.push(args[++i]);
+      else if (args[i] === '--video' && args[i + 1]) video = args[++i];
       else if (args[i] === '--script' && args[i + 1]) script = args[++i];
       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] === '--project' && args[i + 1]) projectId = args[++i];
+      else if (args[i] === '--keep-original-sound') keepOriginalSound = true;
+      else if (args[i] === '--project') {
+        console.error('Usage: video create no longer supports --project. Use: makaron chat --project <id> --video <file|url> "your request"');
+        process.exit(1);
+      }
       else if (args[i] === '--wait') wait = true;
     }
-    if (!images.length || !script) { console.error('Usage: makaron video create --script "..." --image <url> [--project <id>] [--duration 10] [--aspect 9:16] [--model kling|seedance] [--wait]'); process.exit(1); }
-
-    if (projectId) {
-      // v2: submit to /api/video-snapshot → writes into timeline
-      process.stderr.write('🎬 Submitting video to timeline...\n');
-      const body = { projectId, imageUrls: images, prompt: script };
-      if (duration) body.duration = duration;
-      if (aspectRatio) body.aspectRatio = aspectRatio;
-      if (videoModel) body.videoModel = videoModel;
-      const res = await fetch(`${baseUrl}/api/video-snapshot`, {
-        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();
-      process.stderr.write(`✅ Video snapshot: ${data.snapshotId} (task: ${data.taskId})\n`);
-      if (wait) {
-        const url = await pollVideo(baseUrl, headers, data.taskId, data.snapshotId);
-        if (url) console.log(url);
-      } else {
-        console.log(JSON.stringify(data, null, 2));
-      }
-    } else {
-      // No project: use MCP tool (standalone, no timeline write)
-      process.stderr.write('🎬 Submitting video...\n');
-      const vArgs = { script, images };
-      if (duration) vArgs.duration = duration;
-      if (aspectRatio) vArgs.aspectRatio = aspectRatio;
-      if (videoModel) vArgs.videoModel = videoModel;
-      const result = await callMcpTool(baseUrl, headers, 'makaron_create_video', vArgs);
-      const text = result?.content?.find(c => c.type === 'text')?.text;
-      if (text) console.log(text);
+    if ((!images.length && !video) || !script) {
+      console.error('Usage: makaron video create --script "..." (--image <url> | --video <public-url>) [--duration 10] [--aspect 9:16] [--model kling|seedance] [--keep-original-sound]');
+      process.exit(1);
+    }
+
+    if (wait) {
+      console.error('Usage: --wait is only supported for project timeline tasks. Use chat --project for project video generation, or poll the returned taskId with video status.');
+      process.exit(1);
     }
 
+    let videoUrl = isHttpUrl(video) ? video : null;
+    let inputVideoMeta = null;
+    if (videoUrl) {
+      process.stderr.write(`📹 Assuming public video URL already matches Makaron upload limits: ≤${MAX_VIDEO_DURATION}s, ≤200MB, ≤1080p.\n`);
+    }
+    if (video && !videoUrl) {
+      const valid = validateVideoFile(video);
+      if (!valid.ok) { console.error(`❌ ${valid.error}`); process.exit(1); }
+      inputVideoMeta = valid.meta;
+      process.stderr.write(`📹 Uploading ${path.basename(video)} (${(fs.statSync(video).size/1024/1024).toFixed(1)}MB)...\n`);
+      videoUrl = await uploadFileViaSignedUrl(baseUrl, headers, undefined, video, valid.mime);
+      if (!videoUrl) process.exit(1);
+      process.stderr.write(`📹 Uploaded: ${path.basename(video)}\n`);
+    }
+    // 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' }
+      : { script, images };
+    const effectiveDuration = duration || (inputVideoMeta?.duration ? Math.round(inputVideoMeta.duration) : undefined);
+    if (effectiveDuration) vArgs.duration = effectiveDuration;
+    if (aspectRatio) vArgs.aspectRatio = aspectRatio;
+    if (videoModel && !videoUrl) vArgs.videoModel = videoModel;
+    if (keepOriginalSound && videoUrl) vArgs.keepOriginalSound = true;
+    const result = await callMcpTool(baseUrl, headers, videoUrl ? 'makaron_edit_video' : 'makaron_create_video', vArgs);
+    const text = result?.content?.find(c => c.type === 'text')?.text;
+    if (text) console.log(text);
+
   } else if (sub === 'status') {
     let taskId = null, snapshotId = null, wait = false;
     for (let i = 2; i < args.length; i++) {
@@ -1074,6 +1236,7 @@ if (command === 'login') {
     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
 `);
@@ -1341,7 +1504,8 @@ Commands:
   abort <runId>                      Abort a running Agent
 
   edit [--image <file>] "prompt"     AI image edit / text-to-image
-  video script|create|status         Video generation (v2 timeline support)
+  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)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.7.1",
+  "version": "0.7.5",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "bin": {

package/skills/makaron/SKILL.md

@@ -86,6 +86,26 @@ Returns immediately:
 npx makaron-cli chat --project <id> --image ref1.jpg --image ref2.jpg -b "use these as style reference"
 ```
 
+### With video input (edit, compose, extend)
+
+```bash
+# Upload a video and transform it — Agent understands video content natively
+npx makaron-cli chat --project auto --video selfie.mp4 -b "put Iron Man armor on me"
+
+# Combine a person's photo with a video scene
+npx makaron-cli chat --project <id> --video party.mp4 --image kid.jpg -b "make this kid join the party"
+
+# Multiple videos — compose or splice
+npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "combine into one seamless video"
+
+# Video URL (public, downloadable)
+npx makaron-cli chat --project auto --video https://example.com/dance.mp4 -b "extend this to 15 seconds"
+```
+
+Supported formats: MP4, MOV, WebM. CLI local video uploads follow the same compatibility contract as the normal frontend flow: max 200MB, max 15s, and <=1080p / 2,086,876 frame pixels. The frontend can transcode oversized videos; the CLI rejects them so later Seedance editing does not fail. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance video-reference editing is supported for <=15s videos that meet these upload limits; Kling remains the base/direct edit path.
+
+Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct video commands are standalone raw-tool calls.
+
 ### Check status (single query)
 
 ```bash
@@ -142,20 +162,35 @@ npx makaron-cli edit --image photo.jpg --out result.jpg "make it dramatic"
 
 Options: `--image`, `--model gemini|qwen|openai|pony|wai`, `--skill enhance|creative|wild|captions`, `--ref <file>` (up to 3), `--aspect <ratio>`, `--out <path>`
 
-### `video` — Video generation (3 steps)
+### `video` — Standalone video tools (no project timeline)
 
 ```bash
 # 1. Write script from images
 npx makaron-cli video script --image img1.jpg "cinematic story"
 
-# 2. Submit rendering (images must be public URLs from step 1 or uploaded)
+# 2. Analyze a video (standalone, no timeline write)
+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
 
-# 3. Check status
+# 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
+npx makaron-cli video create --script "make it warmer and cinematic" --video https://example.com/input.mp4 --duration 5 --model seedance
+
+# 4. Check status
 npx makaron-cli video status <taskId>
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to 7), `--duration 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+`video create` returns a provider task id and does not create or update a Makaron project timeline. For project/timeline video editing, use:
+
+```bash
+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 3|5|7|10|15`, `--aspect 9:16|16:9|1:1`, `--model kling|seedance`
+
+Video edit model behavior: `--model kling --video` uses Kling base/direct edit internally; `--model seedance --video` uses the Seedance video-reference path and requires <=15s, <=1080p input.
 
 ### `music` — Music generation
 
@@ -184,7 +219,7 @@ type MakaronOutput =
   | { id: string; type: "text"; status: "completed"; content: string }
   | { id: string; type: "image"; status: "completed"; url: string; snapshot_id: string }
   | { id: string; type: "design"; status: "completed"; url: string; width: number; height: number; animated: boolean; duration?: number }
-  | { id: string; type: "video"; status: "queued"|"rendering"|"completed"|"failed"; task_id: string; url?: string; elapsed_seconds?: number }
+  | { id: string; type: "video"; status: "queued"|"rendering"|"completed"|"failed"; task_id: string; snapshot_id?: string; url?: string; elapsed_seconds?: number; width?: number; height?: number }
   | { id: string; type: "music"; status: "queued"|"rendering"|"completed"|"failed"; task_id: string; url?: string; elapsed_seconds?: number }
 ```