@mindstudio-ai/agent 0.1.153 → 0.1.154

package/dist/index.d.ts

@@ -10151,7 +10151,7 @@ interface StepMethods {
      * - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1–4 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1–5).
      * - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1–4 views), wavespeed-tripo3d-v2.5, seed3d-2.0, wavespeed-sam-3d-objects (with optional `mask_images`).
      * - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).
-     * - `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance. A prompt longer than the model reads is refused, not cut.
+     * - `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance.
      * - The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.
      *
      * @example
@@ -10161,13 +10161,15 @@ interface StepMethods {
      */
     generate3dModel(step: Generate3dModelStepInput, options?: StepExecutionOptions): Promise<StepExecutionResult<Generate3dModelStepOutput>>;
     /**
-     * Generate an image from a text prompt using an AI model.
+     * Generate an image from a text prompt, or edit one, using an AI model.
      *
      * @remarks
      * - Prompts should be descriptive but concise (roughly 3–6 sentences).
+     * - The default model is seedream-4.5. Options go in `imageModelOverride.config` under the model's own names, and differ by model, so look the model up before writing the call. Images to edit or draw from go there too, as URLs: `images` on most models, `source_images` on the Gemini and GPT Image models, one `image` on qwen-image, z-image-turbo, krea-v2-turbo, ideogram-v4 and the MAI models, `source_image` on Grok Imagine, `image_url` on the Ideogram remix and FLUX Kontext models, and `reference` on krea-v2-large.
+     * - A model that makes and edits images by separate means takes `$mode` in its config (`text-to-image`, and `edit`, `image-edit` or `image-to-image`, as it lists). Left out, images in the config pick the edit mode, and otherwise the model makes the image from the prompt.
      * - Images are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` — a private store keeps the image private.
      * - In foreground mode, the image is displayed to the user. In background mode, the URL is saved to a variable.
-     * - When generateVariants is true with numVariants > 1, multiple images are generated in parallel.
+     * - When generateVariants is true with numVariants > 1 (up to 10), the images are generated in parallel. One that fails is left out of the URLs returned, and the step fails only when every one does.
      * - In direct execution, foreground mode behaves as background, and userSelect variant behavior behaves as saveAll.
      *
      * @example
@@ -10194,7 +10196,7 @@ interface StepMethods {
      * Generate an audio file from provided instructions (text) using a music model.
      *
      * @remarks
-     * - `text` describes the song: genre, mood, instruments, tempo, vocals, and for Lyria its structure (`[Verse]`, `[Chorus]`, timestamps such as `[0:00-0:20] Intro`). A text longer than the model reads is refused, not cut.
+     * - `text` describes the song: genre, mood, instruments, tempo, vocals, and for Lyria its structure (`[Verse]`, `[Chorus]`, timestamps such as `[0:00-0:20] Intro`).
      * - The default model is elevenlabs-music_v2.5. Options go in `musicModelOverride.config`, and differ by model:
      * - elevenlabs-music_v2.5, elevenlabs-music_v2: `musicLengthMs`, the song's length from 3,000 to 600,000 (the model chooses one from the text otherwise, and holds a length it's given), and `forceInstrumental: true` for no vocals.
      * - lyria-3.5: songs of up to about three minutes, their length steered from the text; `image`, the URL of an image for the song to take its mood and subject from. lyria-3 makes 30-second clips, lyria-3-pro songs of up to about three minutes.
@@ -10270,7 +10272,7 @@ interface StepMethods {
      * Generate a video from a text prompt, an image or references, using an AI model.
      *
      * @remarks
-     * - Prompts should be descriptive but concise (roughly 3–6 sentences): the subject, the motion, the camera and the sound. A prompt longer than the model reads is refused, not cut.
+     * - Prompts should be descriptive but concise (roughly 3–6 sentences): the subject, the motion, the camera and the sound.
      * - The default model is wan3.0-video. Options go in `videoModelOverride.config` under the model's own names, and differ by model, so look the model up before writing the call. Images, videos and audio go there too, as URLs: a first frame is `image` on most models, `image_url` on Veo, gemini-omni-flash, Runway's and minimax-h3-max, `source_image` on Grok Imagine, `start_frame` on ray-2 and `first_frame_image` on skyreels-v4.
      * - A model that makes video more than one way takes `$mode` in its config (`text-to-video`, `image-to-video`, `reference-to-video`, `video-edit` and others it lists). Left out, a first frame or reference images in the config pick their mode, and otherwise the model's default runs.
      * - Videos are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` — a private store keeps the video private, with no public copy left behind.

package/dist/index.js

@@ -4430,7 +4430,7 @@ var stepMetadata = {
   "generate3dModel": {
     stepType: "generate3dModel",
     description: "Generate a 3D model using a 3D generation model.",
-    usageNotes: "- The default model is wavespeed-tripo3d-h3.1 (Tripo v3.1), which makes a model from the prompt, from one `image`, or from `images`: 2\u20134 views of the same object, in order front, left, back, right.\n- Models and what they take, set in `threeDModelOverride.config`:\n  - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1\u20134 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1\u20135).\n  - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1\u20134 views), wavespeed-tripo3d-v2.5, seed3d-2.0, wavespeed-sam-3d-objects (with optional `mask_images`).\n  - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).\n- `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance. A prompt longer than the model reads is refused, not cut.\n- The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.",
+    usageNotes: "- The default model is wavespeed-tripo3d-h3.1 (Tripo v3.1), which makes a model from the prompt, from one `image`, or from `images`: 2\u20134 views of the same object, in order front, left, back, right.\n- Models and what they take, set in `threeDModelOverride.config`:\n  - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1\u20134 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1\u20135).\n  - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1\u20134 views), wavespeed-tripo3d-v2.5, seed3d-2.0, wavespeed-sam-3d-objects (with optional `mask_images`).\n  - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).\n- `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance.\n- The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.",
     inputSchema: { "type": "object", "properties": { "prompt": { "type": "string", "description": "Text prompt for text-to-3D models, or optional guidance for image-to-3D models" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "threeDModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "3D generation model identifier" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default 3D model if not specified" } } },
     outputSchema: { "type": "object", "properties": { "prompt": { "type": "string" }, "glbUrl": { "type": "string" }, "fbxUrl": { "type": "string" }, "objUrl": { "type": "string" }, "usdzUrl": { "type": "string" }, "thumbnailUrl": { "type": "string" }, "textureUrls": { "type": "array", "items": { "type": "object", "properties": {}, "required": [] } }, "providerTaskId": { "type": "string" }, "resolvedConfig": { "type": "object", "properties": {}, "required": [] } }, "required": ["glbUrl"] }
   },
@@ -4443,8 +4443,8 @@ var stepMetadata = {
   },
   "generateImage": {
     stepType: "generateImage",
-    description: "Generate an image from a text prompt using an AI model.",
-    usageNotes: "- Prompts should be descriptive but concise (roughly 3\u20136 sentences).\n- Images are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` \u2014 a private store keeps the image private.\n- In foreground mode, the image is displayed to the user. In background mode, the URL is saved to a variable.\n- When generateVariants is true with numVariants > 1, multiple images are generated in parallel.\n- In direct execution, foreground mode behaves as background, and userSelect variant behavior behaves as saveAll.",
+    description: "Generate an image from a text prompt, or edit one, using an AI model.",
+    usageNotes: "- Prompts should be descriptive but concise (roughly 3\u20136 sentences).\n- The default model is seedream-4.5. Options go in `imageModelOverride.config` under the model's own names, and differ by model, so look the model up before writing the call. Images to edit or draw from go there too, as URLs: `images` on most models, `source_images` on the Gemini and GPT Image models, one `image` on qwen-image, z-image-turbo, krea-v2-turbo, ideogram-v4 and the MAI models, `source_image` on Grok Imagine, `image_url` on the Ideogram remix and FLUX Kontext models, and `reference` on krea-v2-large.\n- A model that makes and edits images by separate means takes `$mode` in its config (`text-to-image`, and `edit`, `image-edit` or `image-to-image`, as it lists). Left out, images in the config pick the edit mode, and otherwise the model makes the image from the prompt.\n- Images are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` \u2014 a private store keeps the image private.\n- In foreground mode, the image is displayed to the user. In background mode, the URL is saved to a variable.\n- When generateVariants is true with numVariants > 1 (up to 10), the images are generated in parallel. One that fails is left out of the URLs returned, and the step fails only when every one does.\n- In direct execution, foreground mode behaves as background, and userSelect variant behavior behaves as saveAll.",
     inputSchema: { "type": "object", "properties": { "prompt": { "type": "string", "description": "Text prompt describing the image to generate" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "imageModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Image generation model identifier" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default image model if not specified" }, "generateVariants": { "type": "boolean", "description": "Whether to generate multiple image variants in parallel" }, "numVariants": { "type": "number", "description": "Number of variants to generate (max 10)" }, "addWatermark": { "type": "boolean", "description": "Whether to add a MindStudio watermark to the generated image.\n\nThe watermark is a product mark on assets generated in the MindStudio UI. A step run directly via the SDK or API is producing the app's own asset, so it is never watermarked and this flag has no effect there." } }, "required": ["prompt"] },
     outputSchema: { "type": "object", "properties": { "imageUrl": { "anyOf": [{ "type": "string" }, { "type": "array", "items": { "type": "string" } }] } }, "required": ["imageUrl"] }
   },
@@ -4458,7 +4458,7 @@ var stepMetadata = {
   "generateMusic": {
     stepType: "generateMusic",
     description: "Generate an audio file from provided instructions (text) using a music model.",
-    usageNotes: "- `text` describes the song: genre, mood, instruments, tempo, vocals, and for Lyria its structure (`[Verse]`, `[Chorus]`, timestamps such as `[0:00-0:20] Intro`). A text longer than the model reads is refused, not cut.\n- The default model is elevenlabs-music_v2.5. Options go in `musicModelOverride.config`, and differ by model:\n  - elevenlabs-music_v2.5, elevenlabs-music_v2: `musicLengthMs`, the song's length from 3,000 to 600,000 (the model chooses one from the text otherwise, and holds a length it's given), and `forceInstrumental: true` for no vocals.\n  - lyria-3.5: songs of up to about three minutes, their length steered from the text; `image`, the URL of an image for the song to take its mood and subject from. lyria-3 makes 30-second clips, lyria-3-pro songs of up to about three minutes.\n  - minimax-music-3.0: `lyrics` (written from the text when left out), `is_instrumental: true`, `bitrate`, `sample_rate`. minimax-music-2.5 requires `lyrics`.\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
+    usageNotes: "- `text` describes the song: genre, mood, instruments, tempo, vocals, and for Lyria its structure (`[Verse]`, `[Chorus]`, timestamps such as `[0:00-0:20] Intro`).\n- The default model is elevenlabs-music_v2.5. Options go in `musicModelOverride.config`, and differ by model:\n  - elevenlabs-music_v2.5, elevenlabs-music_v2: `musicLengthMs`, the song's length from 3,000 to 600,000 (the model chooses one from the text otherwise, and holds a length it's given), and `forceInstrumental: true` for no vocals.\n  - lyria-3.5: songs of up to about three minutes, their length steered from the text; `image`, the URL of an image for the song to take its mood and subject from. lyria-3 makes 30-second clips, lyria-3-pro songs of up to about three minutes.\n  - minimax-music-3.0: `lyrics` (written from the text when left out), `is_instrumental: true`, `bitrate`, `sample_rate`. minimax-music-2.5 requires `lyrics`.\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
     inputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The instructions (prompt) for the music generation" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "musicModelOverride": { "type": "object", "properties": { "model": { "type": "string" }, "config": { "type": "object", "properties": {}, "required": [] } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default music model if not specified" } }, "required": ["text"] },
     outputSchema: { "type": "object", "properties": { "audioUrl": { "type": "string", "description": "URL of the generated audio file" } }, "required": ["audioUrl"] }
   },
@@ -4504,7 +4504,7 @@ var stepMetadata = {
   "generateVideo": {
     stepType: "generateVideo",
     description: "Generate a video from a text prompt, an image or references, using an AI model.",
-    usageNotes: "- Prompts should be descriptive but concise (roughly 3\u20136 sentences): the subject, the motion, the camera and the sound. A prompt longer than the model reads is refused, not cut.\n- The default model is wan3.0-video. Options go in `videoModelOverride.config` under the model's own names, and differ by model, so look the model up before writing the call. Images, videos and audio go there too, as URLs: a first frame is `image` on most models, `image_url` on Veo, gemini-omni-flash, Runway's and minimax-h3-max, `source_image` on Grok Imagine, `start_frame` on ray-2 and `first_frame_image` on skyreels-v4.\n- A model that makes video more than one way takes `$mode` in its config (`text-to-video`, `image-to-video`, `reference-to-video`, `video-edit` and others it lists). Left out, a first frame or reference images in the config pick their mode, and otherwise the model's default runs.\n- Videos are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` \u2014 a private store keeps the video private, with no public copy left behind.\n- In foreground mode, the video is displayed to the user. In background mode, the URL is saved to a variable.\n- When generateVariants is true with numVariants > 1, multiple videos are generated in parallel.\n- In direct execution, foreground mode behaves as background, and userSelect variant behavior behaves as saveAll.",
+    usageNotes: "- Prompts should be descriptive but concise (roughly 3\u20136 sentences): the subject, the motion, the camera and the sound.\n- The default model is wan3.0-video. Options go in `videoModelOverride.config` under the model's own names, and differ by model, so look the model up before writing the call. Images, videos and audio go there too, as URLs: a first frame is `image` on most models, `image_url` on Veo, gemini-omni-flash, Runway's and minimax-h3-max, `source_image` on Grok Imagine, `start_frame` on ray-2 and `first_frame_image` on skyreels-v4.\n- A model that makes video more than one way takes `$mode` in its config (`text-to-video`, `image-to-video`, `reference-to-video`, `video-edit` and others it lists). Left out, a first frame or reference images in the config pick their mode, and otherwise the model's default runs.\n- Videos are hosted on the public CDN by default, or in one of the app's own file stores when the call passes `store` \u2014 a private store keeps the video private, with no public copy left behind.\n- In foreground mode, the video is displayed to the user. In background mode, the URL is saved to a variable.\n- When generateVariants is true with numVariants > 1, multiple videos are generated in parallel.\n- In direct execution, foreground mode behaves as background, and userSelect variant behavior behaves as saveAll.",
     inputSchema: { "type": "object", "properties": { "prompt": { "type": "string", "description": "Text prompt describing the video to generate" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "videoModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Video generation model identifier" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default video model if not specified" }, "generateVariants": { "type": "boolean", "description": "Whether to generate multiple video variants in parallel" }, "numVariants": { "type": "number", "description": "Number of variants to generate (max 10)" }, "addWatermark": { "type": "boolean", "description": "Whether to add a MindStudio watermark to the generated video.\n\nThe watermark is a product mark on assets generated in the MindStudio UI. A step run directly via the SDK or API is producing the app's own asset, so it is never watermarked and this flag has no effect there." } }, "required": ["prompt"] },
     outputSchema: { "type": "object", "properties": { "videoUrl": { "anyOf": [{ "type": "string" }, { "type": "array", "items": { "type": "string" } }] } }, "required": ["videoUrl"] }
   },