makaron-cli 0.13.4 → 0.13.6

package/.claude-plugin/plugin.json

@@ -1,12 +1,12 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.3",
-  "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.",
+  "version": "0.13.6",
+  "description": "Give Claude Code a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
-    "name": "Makaron AI",
+    "name": "Versa AI",
+    "email": "tianyi@versa-ai.com",
     "url": "https://www.makaron.app"
   },
   "homepage": "https://www.makaron.app/agent",
-  "repository": "https://github.com/vegekyd/ai-image-editor",
   "skills": "./skills/"
 }

package/.codex-plugin/plugin.json

@@ -1,21 +1,30 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.3",
-  "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",
-  "longDescription": "makaron.app is for humans. makaron-cli is for AI agents. Talk to Makaron Agent from the terminal — list, search, show, and install marketplace skills; create projects; edit images; generate videos; and compose music. Zero dependencies, single file, works with npx. Agents can self-register to get an API key without human intervention.",
+  "version": "0.13.6",
+  "description": "Give Codex a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
-    "name": "Makaron AI",
+    "name": "Versa AI",
+    "email": "tianyi@versa-ai.com",
     "url": "https://www.makaron.app"
   },
   "homepage": "https://www.makaron.app/agent",
-  "repository": "https://github.com/vegekyd/ai-image-editor",
   "license": "MIT",
-  "keywords": ["ai", "image-editing", "video", "music", "agent", "creative", "skills"],
-  "category": "Creative Tools",
-  "capabilities": ["image-editing", "video-generation", "music-creation", "text-to-image", "marketplace-skills"],
+  "keywords": ["creative-production", "image-editing", "video-generation", "music", "agent", "cli"],
   "skills": "./skills/",
-  "websiteURL": "https://www.makaron.app",
-  "brandColor": "#d946ef"
+  "interface": {
+    "displayName": "Makaron Creative Studio",
+    "shortDescription": "Give Codex a creative agent",
+    "longDescription": "Pass any complete creative request and source media to Makaron Chat. Makaron plans and produces images, video, music, and motion design in a persistent project that a human can continue editing in makaron.app.",
+    "developerName": "Versa AI",
+    "category": "Creative Tools",
+    "capabilities": ["Read", "Write"],
+    "websiteURL": "https://www.makaron.app/agent",
+    "privacyPolicyURL": "https://www.makaron.app/privacy",
+    "defaultPrompt": [
+      "Pass this complete creative brief and its source files to Makaron Chat.",
+      "Ask Makaron Chat to turn this image into the finished media described in my request.",
+      "Continue this Makaron project with my complete follow-up request."
+    ],
+    "brandColor": "#d946ef"
+  }
 }

package/README.md

@@ -151,6 +151,42 @@ npx makaron-cli project media <projectId> --json
 
 This is project-scoped. `responses get <runId> --pick output` only returns artifacts from one run; `project media` returns the whole project timeline: original uploads, references, generated images, video snapshots, and editable compositions.
 
+External source ranges can be added without uploading either the original video or a derivative clip:
+
+```bash
+npx makaron-cli project media add <projectId> \
+  --source-url "https://cdn.example.com/source.mp4" \
+  --start 12.5 --end 19 \
+  --description "Racket frame molding"
+
+# Batch form: a JSON array or {"clips": [...]}
+npx makaron-cli project media add <projectId> --input ranges.json --json
+```
+
+The returned `<<<media_N>>>` is immediately usable by a later Agent run. Its range remains non-destructive metadata; Remotion must trim the original URL to these exact source bounds.
+Use `description` as the provider-neutral media-understanding field. Put any
+already-known summary, editorial purpose, concrete scene evidence, confidence,
+and limitations there. Makaron exposes the full description in Media List
+context so the Agent can edit from it without repeating image/video analysis
+unless a required detail is missing or uncertain.
+
+For an agent-to-agent handoff, create the project, import the external ranges,
+and start the Agent in one command:
+
+```bash
+npx makaron-cli chat --project auto \
+  --media-manifest set-01.json \
+  --json -b \
+  "Make a 30-second 9:16 TikTok with English VO and burned-in captions"
+```
+
+The manifest is a JSON array or `{ "title": "...", "clips": [...] }`. Every
+clip contains exactly `source_url`, `start`, `end`, and `description`; the time
+values are seconds and array order is edit order. It is validated before project
+creation and supports up to 20 clips for one Makaron task. Batch planning remains
+the upstream orchestrator's responsibility: convert each plan into one manifest
+and start one independent Makaron task.
+
 ### Export editable Remotion compositions
 
 Animated Remotion compositions are saved as editable timeline/code artifacts first. To materialize one into an MP4 that CLI, V, or another service can read, call the backend export worker:

package/bin/makaron.mjs

@@ -156,6 +156,70 @@ function readJsonInput(filePath) {
   return JSON.parse(raw);
 }
 
+const MAX_MEDIA_MANIFEST_RANGES = 20;
+
+function normalizeMediaManifest(input) {
+  const manifest = Array.isArray(input) ? { clips: input } : input;
+  if (!manifest || typeof manifest !== 'object') {
+    throw new Error('Media manifest must be a JSON object or an array of source ranges.');
+  }
+  const rawRanges = Array.isArray(manifest.clips)
+    ? manifest.clips
+    : Array.isArray(manifest.source_ranges)
+      ? manifest.source_ranges
+      : Array.isArray(manifest.sourceRanges)
+        ? manifest.sourceRanges
+        : null;
+  if (!rawRanges?.length) {
+    throw new Error('Media manifest must contain a non-empty clips array.');
+  }
+  if (rawRanges.length > MAX_MEDIA_MANIFEST_RANGES) {
+    throw new Error(`Media manifest supports at most ${MAX_MEDIA_MANIFEST_RANGES} source ranges per Makaron task.`);
+  }
+
+  const sourceRanges = rawRanges.map((raw, index) => {
+    if (!raw || typeof raw !== 'object') throw new Error(`clips[${index}] must be an object.`);
+    const sourceUrl = typeof raw.source_url === 'string' ? raw.source_url.trim() : '';
+    let parsed;
+    try {
+      parsed = new URL(sourceUrl);
+    } catch {
+      throw new Error(`clips[${index}].source_url must be a valid HTTP(S) URL.`);
+    }
+    if (!['http:', 'https:'].includes(parsed.protocol)) {
+      throw new Error(`clips[${index}].source_url must use HTTP or HTTPS.`);
+    }
+    const start = Number(raw.start ?? raw.start_sec);
+    const end = Number(raw.end ?? raw.end_sec);
+    if (!Number.isFinite(start) || start < 0) {
+      throw new Error(`clips[${index}].start must be a finite number >= 0.`);
+    }
+    if (!Number.isFinite(end) || end <= start) {
+      throw new Error(`clips[${index}].end must be greater than start.`);
+    }
+    return {
+      source_url: sourceUrl,
+      start,
+      end,
+      description: typeof raw.description === 'string' ? raw.description.trim() : '',
+    };
+  });
+
+  return {
+    sourceRanges,
+    title: typeof manifest.title === 'string' && manifest.title.trim() ? manifest.title.trim() : undefined,
+  };
+}
+
+function readMediaManifest(filePath) {
+  try {
+    return normalizeMediaManifest(readJsonInput(filePath));
+  } catch (error) {
+    const message = error instanceof Error ? error.message : String(error);
+    throw new Error(`Invalid media manifest: ${message}`);
+  }
+}
+
 // ─── Auth ────────────────────────────────────────────────────────────────────
 
 function loadAuth() {
@@ -285,6 +349,7 @@ Options:
   --image <file|url>        Attach a reference image or screenshot. Repeatable.
   --video <file|url>        Attach a video to the project timeline. Repeatable.
   --audio <file|url>        Attach a song, beat, or voice reference. MP3/WAV, repeatable.
+  --media-manifest <file|-> Import source_url + start + end + description clips before this run.
   --skill <id|label|name>   Use an installed skill or auto-install a matched marketplace skill.
   --background, -b          Submit and print a runId.
   --json                    Output structured JSON.
@@ -313,6 +378,9 @@ What you can ask:
   Video cuts and assembly
     makaron chat --project <id> --video clip.mp4 "cut out the dead air and keep the best 20 seconds"
 
+  Agent-to-agent source-range handoff
+    makaron chat --project auto --media-manifest set-01.json -b --json "make a 30s vertical video"
+
   Music
     makaron chat --project <id> "add calm piano background music"
 
@@ -826,9 +894,33 @@ async function listProjectMedia(baseUrl, headers, projectId, opts = {}) {
     const status = item.status && item.status !== 'completed' ? ` ${item.status}` : '';
     const duration = typeof item.duration === 'number' ? ` ${item.duration}s` : '';
     const dimensions = item.width && item.height ? ` ${item.width}x${item.height}` : '';
-    const description = item.description ? ` — ${item.description}` : '';
+    const description = item.description ? ` — ${String(item.description).replace(/\s*\n\s*/g, ' | ')}` : '';
+    const sourceRange = item.source_range || item.sourceRange;
+    const range = sourceRange
+      ? ` source ${formatSeconds(sourceRange.start_sec)}-${formatSeconds(sourceRange.end_sec)}s`
+      : '';
     const url = item.url ? `\n      ${item.url}` : '';
-    console.log(`  ${String(item.index).padStart(2)}. ${ref} [${item.type}${status}${duration}${dimensions}]${description}${url}`);
+    console.log(`  ${String(item.index).padStart(2)}. ${ref} [${item.type}${status}${duration}${dimensions}${range}]${description}${url}`);
+  }
+  return data;
+}
+
+async function addProjectMediaSourceRanges(baseUrl, headers, projectId, ranges, opts = {}) {
+  const res = await fetch(`${baseUrl}/api/projects/${projectId}/media`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json', ...headers },
+    body: JSON.stringify({ clips: ranges }),
+  });
+  if (!res.ok) { console.error('Project media add failed:', await res.text()); process.exit(1); }
+  const data = await res.json();
+  if (opts.json && !opts.silent) {
+    console.log(JSON.stringify(data, null, 2));
+    return data;
+  }
+  if (!opts.silent) {
+    for (const item of data.media || []) {
+      console.log(`${item.ref} ${item.source_url} ${formatSeconds(item.start_sec)}-${formatSeconds(item.end_sec)}s${item.created ? '' : ' (existing)'}`);
+    }
   }
   return data;
 }
@@ -1593,6 +1685,8 @@ Commands:
   credits                            Show current credit balance
   list (ls)                          List all projects
   project media <projectId> --json    List timeline media for a project
+  project media add <projectId> --source-url <url> --start <n> --end <n>
+                                     Add an external source range without uploading video
   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)
@@ -1601,6 +1695,8 @@ Commands:
   chat --project <id> --skill <id>   Use a built-in or marketplace skill
   chat --project <id> --video <file> Attach video to conversation
   chat --project <id> --audio <file> Attach song/beat/voice reference
+  chat --project auto --media-manifest <file> "message"
+                                     Create, import external ranges, and run Agent
   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
@@ -1708,9 +1804,12 @@ function printHelp(topic, subtopic) {
   } else if (topic === 'credits' || topic === 'credit' || topic === 'balance') {
     console.log('Usage: makaron credits [--json]');
   } else if (topic === 'project' || topic === 'projects') {
-    if (subtopic === 'media') console.log('Usage: makaron project media <projectId> [--json]');
+    if (subtopic === 'media') console.log(`Usage: makaron project media <projectId> [--json]
+  makaron project media add <projectId> --source-url <url> --start <n> --end <n> [--description <text>] [--json]
+  makaron project media add <projectId> --input <ranges.json> [--json]`);
     else console.log(`Project commands:
   project media <projectId> --json      List timeline media for a project
+  project media add <projectId> ...     Add external source_url + start + end media
 `);
   } else if (topic === 'abort') {
     console.log('Usage: makaron abort <runId>');
@@ -1868,11 +1967,20 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   let background = false;
   let jsonOutput = false;
   let activeSkill = undefined;
+  let mediaManifestPath = undefined;
   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]);
     else if (args[i] === '--video' && args[i + 1]) chatVideos.push(args[++i]);
     else if (args[i] === '--audio' && args[i + 1]) chatAudios.push(args[++i]);
+    else if (args[i] === '--media-manifest') {
+      if (!args[i + 1] || args[i + 1].startsWith('--')) {
+        process.stderr.write('❌ --media-manifest requires a JSON file path or -.\n');
+        process.exit(1);
+      }
+      mediaManifestPath = args[++i];
+    }
+    else if (args[i].startsWith('--media-manifest=')) mediaManifestPath = args[i].slice('--media-manifest='.length);
     else if (args[i] === '--skill' && args[i + 1]) activeSkill = args[++i];
     else if (args[i].startsWith('--skill=')) activeSkill = args[i].slice('--skill='.length);
     else if (args[i] === '--stream') useStream = true;
@@ -1898,6 +2006,15 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     console.error('Run: makaron chat --help');
     process.exit(1);
   }
+  let mediaManifest;
+  if (mediaManifestPath) {
+    try {
+      mediaManifest = readMediaManifest(mediaManifestPath);
+    } catch (error) {
+      process.stderr.write(`❌ ${error instanceof Error ? error.message : String(error)}\n`);
+      process.exit(1);
+    }
+  }
   const { headers, baseUrl } = getAuth();
   // Split images into URLs vs local files
   const imageUrlList = chatImages.filter(p => p.startsWith('http://') || p.startsWith('https://'));
@@ -1954,13 +2071,31 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     const res = await fetch(`${baseUrl}/api/projects/create`, {
       method: 'POST',
       headers: { 'Content-Type': 'application/json', ...headers },
-      body: JSON.stringify({ title: prompt.slice(0, 50) }),
+      body: JSON.stringify({ title: mediaManifest?.title || prompt.slice(0, 50) }),
     });
     if (!res.ok) { process.stderr.write(`❌ Failed to create project: ${await res.text()}\n`); process.exit(1); }
     const data = await res.json();
     projectId = data.projectId;
     process.stderr.write(`📦 Project created: ${projectId}\n`);
   }
+  let importedManifestMedia = [];
+  if (mediaManifest) {
+    const imported = await addProjectMediaSourceRanges(
+      baseUrl,
+      headers,
+      projectId,
+      mediaManifest.sourceRanges,
+      { silent: true },
+    );
+    importedManifestMedia = imported.media || [];
+    if (importedManifestMedia.length !== mediaManifest.sourceRanges.length) {
+      process.stderr.write(`❌ Imported ${importedManifestMedia.length}/${mediaManifest.sourceRanges.length} source range(s); aborting run.\n`);
+      process.exit(1);
+    }
+    uploadedTurnMediaCount += importedManifestMedia.length;
+    uploadedTurnVideoCount += importedManifestMedia.length;
+    process.stderr.write(`📎 Imported ${importedManifestMedia.length} external source range(s) from media manifest\n`);
+  }
   // Upload additional images to existing project
   if (imageFileList.length > 0 || imageUrlList.length > 0) {
     const uploadedImageUrls = imageFileList.length
@@ -2106,7 +2241,20 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     if (background) {
       // Just print runId and exit
       if (jsonOutput) {
-        console.log(JSON.stringify({ runId, projectId, projectUrl: `${APP_URL}/projects/${projectId}`, status: 'running' }));
+        console.log(JSON.stringify({
+          runId,
+          projectId,
+          projectUrl: `${APP_URL}/projects/${projectId}`,
+          status: 'running',
+          ...(importedManifestMedia.length ? {
+            importedMedia: importedManifestMedia.map(item => ({
+              ref: item.ref,
+              source_url: item.source_url,
+              start_sec: item.start_sec,
+              end_sec: item.end_sec,
+            })),
+          } : {}),
+        }));
       } else {
         console.log(runId);
       }
@@ -2344,13 +2492,48 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   const { headers, baseUrl } = getAuth();
   const sub = args[1];
   if (sub === 'media') {
-    const projectId = args[2];
-    if (!projectId) { console.error('Usage: makaron project media <projectId> [--json]'); process.exit(1); }
     const jsonOutput = args.includes('--json');
-    await listProjectMedia(baseUrl, headers, projectId, { json: jsonOutput });
+    if (args[2] === 'add') {
+      const projectId = args[3];
+      if (!projectId) { console.error('Usage: makaron project media add <projectId> --source-url <url> --start <n> --end <n>'); process.exit(1); }
+      const readOption = (name) => {
+        const index = args.indexOf(name);
+        return index >= 0 ? args[index + 1] : undefined;
+      };
+      const inputPath = readOption('--input');
+      let ranges;
+      if (inputPath) {
+        const input = readJsonInput(inputPath);
+        ranges = Array.isArray(input) ? input : input.clips || input.source_ranges || input.sourceRanges;
+      } else {
+        const sourceUrl = readOption('--source-url');
+        const start = Number(readOption('--start') ?? readOption('--start-sec'));
+        const end = Number(readOption('--end') ?? readOption('--end-sec'));
+        if (!sourceUrl || !Number.isFinite(start) || !Number.isFinite(end)) {
+          console.error('Provide --source-url, --start, and --end, or --input <manifest.json>.');
+          process.exit(1);
+        }
+        ranges = [{
+          source_url: sourceUrl,
+          start,
+          end,
+          ...(readOption('--description') ? { description: readOption('--description') } : {}),
+        }];
+      }
+      if (!Array.isArray(ranges) || !ranges.length) {
+        console.error('Input must contain a non-empty clips array.');
+        process.exit(1);
+      }
+      await addProjectMediaSourceRanges(baseUrl, headers, projectId, ranges, { json: jsonOutput });
+    } else {
+      const projectId = args[2];
+      if (!projectId) { console.error('Usage: makaron project media <projectId> [--json]'); process.exit(1); }
+      await listProjectMedia(baseUrl, headers, projectId, { json: jsonOutput });
+    }
   } else {
     console.log(`Project commands:
   project media <projectId> --json      List timeline media for a project
+  project media add <projectId> ...     Add external source_url + start + end media
 `);
   }
 } else if (command === 'abort') {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.4",
+  "version": "0.13.6",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/SKILL.md

@@ -149,6 +149,21 @@ npx makaron-cli project media <projectId> --json
 
 This is project-scoped. `responses get <runId> --pick output` only returns artifacts from one run; `project media` returns the whole project timeline: original uploads, references, generated images, video snapshots, and editable compositions.
 
+Publish an external video interval directly into that Media List without uploading the original or a derivative MP4:
+
+```bash
+npx makaron-cli project media add <projectId> --source-url "https://cdn.example.com/source.mp4" --start 12.5 --end 19 --description "Racket frame molding"
+npx makaron-cli project media add <projectId> --input ranges.json --json
+```
+
+The JSON input may be an array or `{ "clips": [...] }`. Each clip has exactly `source_url + start + end + description`; `start` and `end` are seconds, array order is edit order, and `source_url` is opaque. Do not add or request provider-specific identity fields. Put existing media understanding (summary, editorial purpose, scene evidence, confidence, and limitations) in `description`. Makaron reads that provider-neutral Media List field before deciding whether any additional image/video analysis is needed.
+
+For one-call orchestration, use `chat --project auto --media-manifest plan.json`. Makaron validates the manifest, creates the project, imports its ranges, and starts the Agent. If an upstream service returns multiple plans, the caller should start one independent Makaron task per plan instead of passing the provider-specific batch response into Makaron.
+
+```bash
+npx makaron-cli chat --project auto --media-manifest set-01.json --json -b "Make a 30-second 9:16 TikTok with English VO and captions"
+```
+
 ### With video input (edit, compose, extend)
 
 ```bash