@mrgoonie/multix 1.0.2 → 1.0.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mrgoonie/multix",
-  "version": "1.0.2",
+  "version": "1.0.4",
   "description": "AI multimodal CLI — OpenAI, Gemini, MiniMax, OpenRouter, Leonardo, BytePlus, ElevenLabs, fal.ai, Atlas Cloud, Replicate, HeyGen, ffmpeg, ImageMagick, doc-to-md",
   "type": "module",
   "bin": {

package/skill/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multix
 description: AI multimodal CLI — generate and edit images (OpenAI, Codex driver, Gemini Nano Banana, Imagen, MiniMax, OpenRouter, Leonardo, BytePlus Seedream, Cloudflare Workers AI FLUX.1 Schnell, fal.ai FLUX, Replicate FLUX), generate video (Gemini Veo, MiniMax Hailuo, OpenRouter via Veo/Seedance/Kling, Leonardo via Motion/Veo/Kling/Hailuo/Seedance/LTX, BytePlus Seedance, Cloudflare AI Gateway via Replicate, fal.ai queue models, Replicate direct API models incl. P-Video, HeyGen Video Agent and scripted avatar videos), video translation and lipsync (HeyGen), TTS/STT/music (OpenAI, Gemini Flash TTS incl. Gemini 3.8 with delivery-style control, MiniMax, Cloudflare Workers AI MeloTTS, ElevenLabs), 3D models (BytePlus Hyper3D/Hitem3d), analyze/transcribe media, convert documents to Markdown, optimize media via ffmpeg/ImageMagick, and self-update the CLI. Use whenever the user wants to create, edit, or transform images/video/audio/3D/documents from a CLI, mentions any of: OpenAI, Codex image driver, image-to-image, i2i, image edit, watercolor/cyberpunk style transfer, reference image, OpenRouter, Nano Banana, Flux, Seedream, Veo, Hailuo, Seedance, Kling, Cloudflare Workers AI, AI Gateway, fal.ai, Atlas Cloud, Replicate, replicate.com models, Replicate predictions, HeyGen, avatar video, talking head, Video Agent, video translation, dubbing, lipsync, video generation, text-to-video, image-to-video, i2v, ElevenLabs voice cloning, updating/upgrading multix, or asks for batch media optimization.
-version: 1.0.2 # x-release-please-version
+version: 1.0.4 # x-release-please-version
 ---
 
 # multix — AI Multimodal CLI
@@ -138,7 +138,7 @@ multix fal result <model> <requestId> [--download]
 
 ## Atlas Cloud
 
-Auth is `Authorization: Bearer $ATLASCLOUD_API_KEY`; the media API base is `https://api.atlascloud.ai/api/v1`. Each job is an async prediction: commands wait (bounded by `--wait-timeout`) and download to `MULTIX_OUTPUT_DIR` as `atlas-<idprefix>-NN.<ext>`. `--async` prints only the prediction id on stdout (progress goes to stderr) so scripts can capture it. A failed prediction, or a partial download, exits non-zero with a resume command.
+Auth is `Authorization: Bearer $ATLASCLOUD_API_KEY`; the media API base is `https://api.atlascloud.ai/api/v1`. Each job is an async prediction: commands wait (bounded by `--wait-timeout`) and download to `MULTIX_OUTPUT_DIR` as `atlas-<prediction id>-NN.<ext>`. These names are fixed per output, so rerunning `multix atlas status <id> --wait --download` after a partial failure keeps the saved files ("already saved") and fetches only the missing ones; an explicit single-file `--output` is overwritten, and multi-output `--output` names get a `-1`, `-2`, ... suffix instead of overwriting. An error naming a `.part` file means another live multix process is downloading that output: wait and retry (a `.part` left by a stopped run is taken over automatically, so never delete it by hand). `--async` prints only the prediction id on stdout (progress goes to stderr) so scripts can capture it. A failed prediction, or a partial download, exits non-zero with a resume command that keeps your `--output`. Output and thumbnail downloads are https-only and refuse `localhost` and loopback/private/link-local/special-purpose IP literals, also on redirects (hostnames are not resolved): "Refusing to download from ..." means the API returned such a URL, and `--no-download` prints it instead. Each file stops at `MULTIX_MAX_DOWNLOAD_MB` (default 2048); inline `data:` outputs are still saved. Thumbnails come only from the prediction's outputs, never from echoed input.
 
 Inputs are model-specific. multix reads the model's published schema and maps flags onto its field names (`size`/`image_size`, `images[]`/`image`, `audio_url`/`audio`). Unsupported flags and invalid values fail before anything is billed, and the error lists the accepted values. Pass `--no-validate` to skip this check.
 
@@ -386,7 +386,7 @@ Requires `cwebp` (libwebp: `brew install webp`, `apt install webp`) on `PATH`.
 | Variable | Purpose |
 |---|---|
 | `MULTIX_OUTPUT_DIR` | Override default output dir |
-| `MULTIX_MAX_DOWNLOAD_MB` | Size limit per downloaded Replicate output file (default 2048) |
+| `MULTIX_MAX_DOWNLOAD_MB` | Size limit per downloaded Replicate or Atlas Cloud output file (default 2048) |
 | `MULTIX_UPLOAD_MIN_KBPS` | Slowest Gemini Files API upload speed to allow for, in KB/s (default 1000); lower it on slow links |
 | `OPENAI_IMAGE_MODEL` / `OPENAI_TTS_MODEL` / `OPENAI_STT_MODEL` | OpenAI model defaults |
 | `OPENROUTER_IMAGE_MODEL` | Default OpenRouter image model |
@@ -400,7 +400,7 @@ Requires `cwebp` (libwebp: `brew install webp`, `apt install webp`) on `PATH`.
 | `BYTEPLUS_VIDEO_PARAMS_MODE` | `flags` (default) or `structured` |
 | `FAL_BASE_URL` | Override fal queue base (default `https://queue.fal.run`) |
 | `FAL_IMAGE_MODEL` / `FAL_VIDEO_MODEL` | fal.ai default model ids (default `fal-ai/flux/schnell`, `fal-ai/kling-video/v1.6/standard/text-to-video`) |
-| `ATLASCLOUD_BASE_URL` | Override Atlas Cloud media API base (default `https://api.atlascloud.ai/api/v1`) |
+| `ATLASCLOUD_BASE_URL` | Override Atlas Cloud media API base (default `https://api.atlascloud.ai/api/v1`; `https://` required, `http://` only for localhost, 127.0.0.1 or [::1]) |
 | `ATLASCLOUD_IMAGE_MODEL` / `ATLASCLOUD_IMAGE_EDIT_MODEL` / `ATLASCLOUD_VIDEO_MODEL` / `ATLASCLOUD_IMAGE_TO_VIDEO_MODEL` / `ATLASCLOUD_TTS_MODEL` / `ATLASCLOUD_STT_MODEL` / `ATLASCLOUD_TEXT_TO_3D_MODEL` / `ATLASCLOUD_IMAGE_TO_3D_MODEL` | Atlas Cloud default model ids per command |
 | `ATLASCLOUD_MAX_UPLOAD_MB` | Size limit for local files uploaded to Atlas Cloud (default 200) |
 | `GEMINI_TTS_MODEL` / `TTS_MODEL` | Override Gemini TTS model (default `gemini-3.8-flash-lite-tts`) |