@mrgoonie/multix 1.0.5 → 1.0.6

package/CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.0.6](https://github.com/mrgoonie/multix-cli/compare/v1.0.5...v1.0.6) (2026-10-11)
+
+
+### Fixed
+
+* **providers:** read model defaults after loading .env files ([#121](https://github.com/mrgoonie/multix-cli/issues/121)) ([5f36dba](https://github.com/mrgoonie/multix-cli/commit/5f36dba0fc7a1ccbe3d904e928c4ef82b3c6ce36))
+
 ## [1.0.5](https://github.com/mrgoonie/multix-cli/compare/v1.0.4...v1.0.5) (2026-10-11)
 
 

package/dist/cli.js

@@ -3006,6 +3006,11 @@ async function poll(opts) {
 // src/providers/byteplus/client.ts
 init_errors();
 
+// src/core/env-default.ts
+function envDefault(name, fallback) {
+  return process.env[name]?.trim() || fallback;
+}
+
 // src/providers/byteplus/models.ts
 var DEFAULT_BYTEPLUS_BASE_URL = "https://ark.ap-southeast.bytepluses.com/api/v3";
 var BYTEPLUS_ROUTING = {
@@ -3021,9 +3026,15 @@ var BYTEPLUS_3D_MODELS = [
   { id: "hitem3d-2-0-251223", name: "Hitem3d 2.0", family: "hitem3d" }
 ];
 var BYTEPLUS_DEFAULTS = {
-  imageModel: process.env.BYTEPLUS_IMAGE_MODEL ?? DEFAULT_BYTEPLUS_IMAGE_MODEL,
-  videoModel: process.env.BYTEPLUS_VIDEO_MODEL ?? DEFAULT_BYTEPLUS_VIDEO_MODEL,
-  threeDModel: process.env.BYTEPLUS_3D_MODEL ?? DEFAULT_BYTEPLUS_3D_MODEL,
+  get imageModel() {
+    return envDefault("BYTEPLUS_IMAGE_MODEL", DEFAULT_BYTEPLUS_IMAGE_MODEL);
+  },
+  get videoModel() {
+    return envDefault("BYTEPLUS_VIDEO_MODEL", DEFAULT_BYTEPLUS_VIDEO_MODEL);
+  },
+  get threeDModel() {
+    return envDefault("BYTEPLUS_3D_MODEL", DEFAULT_BYTEPLUS_3D_MODEL);
+  },
   videoResolution: "1080p",
   videoDuration: 8,
   videoAspectRatio: "16:9",
@@ -5024,11 +5035,17 @@ var FAL_ROUTING = {
 };
 var FAL_DEFAULTS = {
   // FLUX.1 [schnell] — fast, low-cost default text-to-image model.
-  imageModel: process.env.FAL_IMAGE_MODEL ?? "fal-ai/flux/schnell",
+  get imageModel() {
+    return envDefault("FAL_IMAGE_MODEL", "fal-ai/flux/schnell");
+  },
   // Stable, widely available default text-to-video model.
-  videoModel: process.env.FAL_VIDEO_MODEL ?? "fal-ai/kling-video/v1.6/standard/text-to-video",
+  get videoModel() {
+    return envDefault("FAL_VIDEO_MODEL", "fal-ai/kling-video/v1.6/standard/text-to-video");
+  },
   // Matching image-to-video model — used when --image-url is passed without -m.
-  videoImageModel: process.env.FAL_VIDEO_IMAGE_MODEL ?? "fal-ai/kling-video/v1.6/standard/image-to-video"
+  get videoImageModel() {
+    return envDefault("FAL_VIDEO_IMAGE_MODEL", "fal-ai/kling-video/v1.6/standard/image-to-video");
+  }
 };
 
 // src/providers/fal/run-helpers.ts
@@ -6098,15 +6115,15 @@ var ASPECT_RATIOS = [
 var IMAGE_SIZES = ["1K", "2K", "4K"];
 function getDefaultModel(task) {
   if (task === "generate") {
-    return process.env.IMAGE_GEN_MODEL ?? process.env.GEMINI_IMAGE_GEN_MODEL ?? IMAGE_MODEL_DEFAULT;
+    return envDefault("IMAGE_GEN_MODEL", envDefault("GEMINI_IMAGE_GEN_MODEL", IMAGE_MODEL_DEFAULT));
   }
   if (task === "generate-video") {
-    return process.env.VIDEO_GEN_MODEL ?? VIDEO_MODEL_DEFAULT;
+    return envDefault("VIDEO_GEN_MODEL", VIDEO_MODEL_DEFAULT);
   }
   if (task === "generate-speech") {
-    return process.env.GEMINI_TTS_MODEL ?? process.env.TTS_MODEL ?? TTS_MODEL_DEFAULT;
+    return envDefault("GEMINI_TTS_MODEL", envDefault("TTS_MODEL", TTS_MODEL_DEFAULT));
   }
-  return process.env.MULTIMODAL_MODEL ?? process.env.GEMINI_MODEL ?? ANALYSIS_MODEL_DEFAULT;
+  return envDefault("MULTIMODAL_MODEL", envDefault("GEMINI_MODEL", ANALYSIS_MODEL_DEFAULT));
 }
 
 // src/providers/gemini/result-formatter.ts
@@ -8969,8 +8986,12 @@ var LEONARDO_ROUTING = {
 };
 var DEFAULT_LEONARDO_MODEL_ID = "7b592283-e8a7-4c5a-9ba6-d18c31f258b9";
 var LEONARDO_DEFAULTS = {
-  modelId: process.env.LEONARDO_DEFAULT_MODEL ?? DEFAULT_LEONARDO_MODEL_ID,
-  videoModel: process.env.LEONARDO_VIDEO_MODEL ?? "MOTION2",
+  get modelId() {
+    return envDefault("LEONARDO_DEFAULT_MODEL", DEFAULT_LEONARDO_MODEL_ID);
+  },
+  get videoModel() {
+    return envDefault("LEONARDO_VIDEO_MODEL", "MOTION2");
+  },
   width: 1024,
   height: 1024,
   numImages: 1
@@ -9819,10 +9840,18 @@ var ALL_MINIMAX_MODELS = /* @__PURE__ */ new Set([
   ...MINIMAX_MUSIC_MODELS
 ]);
 var TASK_DEFAULTS2 = {
-  image: process.env.MINIMAX_IMAGE_MODEL ?? "image-01",
-  video: process.env.MINIMAX_VIDEO_MODEL ?? "MiniMax-Hailuo-2.3",
-  speech: process.env.MINIMAX_SPEECH_MODEL ?? "speech-2.8-hd",
-  music: process.env.MINIMAX_MUSIC_MODEL ?? "music-2.5"
+  get image() {
+    return envDefault("MINIMAX_IMAGE_MODEL", "image-01");
+  },
+  get video() {
+    return envDefault("MINIMAX_VIDEO_MODEL", "MiniMax-Hailuo-2.3");
+  },
+  get speech() {
+    return envDefault("MINIMAX_SPEECH_MODEL", "speech-2.8-hd");
+  },
+  get music() {
+    return envDefault("MINIMAX_MUSIC_MODEL", "music-2.5");
+  }
 };
 var VIDEO_DURATIONS = [6, 10];
 var VIDEO_RESOLUTIONS = ["720P", "1080P"];
@@ -10548,7 +10577,7 @@ async function transcribeOpenAIAudio(opts) {
 
 // src/providers/openai/commands/generate-speech.ts
 function registerOpenAIGenerateSpeechCommand(parent) {
-  parent.command("generate-speech").description("Generate speech with OpenAI TTS").option("--text <str>", "Text to speak").option("--prompt <str>", "Alias for --text").option("--model <id>", "TTS model", process.env.OPENAI_TTS_MODEL ?? DEFAULT_OPENAI_TTS_MODEL).option("--voice <name>", "OpenAI voice", "marin").option("--instructions <text>", "Voice/style instructions").option("--output-format <fmt>", "mp3|opus|aac|flac|wav|pcm", "mp3").option("--output <path>", "Copy generated audio to this path").option("-v, --verbose", "Verbose logging").action(async (opts) => {
+  parent.command("generate-speech").description("Generate speech with OpenAI TTS").option("--text <str>", "Text to speak").option("--prompt <str>", "Alias for --text").option("--model <id>", "TTS model", envDefault("OPENAI_TTS_MODEL", DEFAULT_OPENAI_TTS_MODEL)).option("--voice <name>", "OpenAI voice", "marin").option("--instructions <text>", "Voice/style instructions").option("--output-format <fmt>", "mp3|opus|aac|flac|wav|pcm", "mp3").option("--output <path>", "Copy generated audio to this path").option("-v, --verbose", "Verbose logging").action(async (opts) => {
     const text = opts.text ?? opts.prompt;
     if (!text) throw new ValidationError("Either --text or --prompt is required");
     validateTtsVoice(opts.voice);
@@ -10867,7 +10896,7 @@ function collect6(value, prev) {
 
 // src/providers/openai/commands/transcribe.ts
 function registerOpenAITranscribeCommand(parent) {
-  parent.command("transcribe").description("Transcribe audio/video with OpenAI STT").requiredOption("--input <path>", "Audio or video file").option("--model <id>", "STT model", process.env.OPENAI_STT_MODEL ?? DEFAULT_OPENAI_STT_MODEL).option("--format <fmt>", "json|text|diarized_json", "text").option("--language <code>", "ISO language code").option("--chunking-strategy <strategy>", "e.g. auto").option(
+  parent.command("transcribe").description("Transcribe audio/video with OpenAI STT").requiredOption("--input <path>", "Audio or video file").option("--model <id>", "STT model", envDefault("OPENAI_STT_MODEL", DEFAULT_OPENAI_STT_MODEL)).option("--format <fmt>", "json|text|diarized_json", "text").option("--language <code>", "ISO language code").option("--chunking-strategy <strategy>", "e.g. auto").option(
     "--known-speaker-name <name>",
     "Known speaker name; repeatable",
     collect7,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mrgoonie/multix",
-  "version": "1.0.5",
+  "version": "1.0.6",
   "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: 1.0.5 # x-release-please-version
+version: 1.0.6 # x-release-please-version
 ---
 
 # multix — AI Multimodal CLI