@mindstudio-ai/agent 0.1.177 → 0.1.178

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -4,6 +4,13 @@ What changed in `@mindstudio-ai/agent`, newest first, each version under its own
4
4
 
5
5
  Versions before 0.1.163 aren't recorded here.
6
6
 
7
+ ## 0.1.178
8
+
9
+ ### Changed behavior
10
+
11
+ - `generateSound`'s default model is `elevenlabs-sound_v3`, ElevenLabs' SFX v3, in place of `elevenlabs-sound_v2`, which ElevenLabs removes on 2027-03-01. It takes the same settings at the same price, and the usage notes say so. A step that names `elevenlabs-sound_v2` runs as itself until then, and as v3 after. App code isn't affected.
12
+ - `generate3dModel`'s usage notes no longer list `wavespeed-tripo3d-v2.5` or `wavespeed-sam-3d-objects`, whose endpoints WaveSpeed took down. A step that names either runs on `wavespeed-tripo3d-h3.1`, from the same `image`; SAM 3D's `mask_images` are dropped. Check: code that names either model, if it counted on SAM 3D's masks.
13
+
7
14
  ## 0.1.177
8
15
 
9
16
  ### Changed behavior
package/dist/cli.js CHANGED
@@ -376,7 +376,7 @@ var init_metadata = __esm({
376
376
  "generate3dModel": {
377
377
  stepType: "generate3dModel",
378
378
  description: "Generate a 3D model using a 3D generation model.",
379
- 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- `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance.\n- The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.",
379
+ usageNotes: "- The default model is wavespeed-tripo3d-h3.1 (Tripo v3.1), which makes a model from the prompt, from one `image`, or from `images`: 2\u20134 views of the same object, in order front, left, back, right.\n- Models and what they take, set in `threeDModelOverride.config`:\n - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1\u20134 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1\u20135).\n - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1\u20134 views), seed3d-2.0.\n - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).\n- `$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.",
380
380
  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" } } },
381
381
  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"] }
382
382
  },
@@ -418,7 +418,7 @@ var init_metadata = __esm({
418
418
  "generateSound": {
419
419
  stepType: "generateSound",
420
420
  description: "Generate a sound effect from a text description using a sound model.",
421
- usageNotes: "- `text` describes the sound effect to generate.\n- The default model is elevenlabs-sound_v2. Options go in `soundModelOverride.config`:\n - `durationSeconds` \u2014 the length, from 0.5 to 30. Left out, the model picks one from the text, and the effect is billed as 5 seconds whatever its length.\n - `loop: true` \u2014 a sound that repeats with no audible start or end, for ambience and backgrounds.\n - `promptInfluence` \u2014 how literally the text is followed, from 0 to 1 (default 0.3).\n - `outputFormat` \u2014 MP3 (`mp3_44100_128` by default, up to `mp3_44100_192`) or Opus (`opus_48000_32` to `opus_48000_192`).\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
421
+ usageNotes: "- `text` describes the sound effect to generate.\n- The default model is elevenlabs-sound_v3. Options go in `soundModelOverride.config`:\n - `durationSeconds` \u2014 the length, from 0.5 to 30. Left out, the model picks one from the text, and the effect is billed as 5 seconds whatever its length.\n - `loop: true` \u2014 a sound that repeats with no audible start or end, for ambience and backgrounds.\n - `promptInfluence` \u2014 how literally the text is followed, from 0 to 1 (default 0.3).\n - `outputFormat` \u2014 MP3 (`mp3_44100_128` by default, up to `mp3_44100_192`) or Opus (`opus_48000_32` to `opus_48000_192`).\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
422
422
  inputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The description of the sound effect to generate" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "soundModelOverride": { "type": "object", "properties": { "model": { "type": "string" }, "config": { "type": "object", "properties": {}, "required": [] } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default sound model if not specified" } }, "required": ["text"] },
423
423
  outputSchema: { "type": "object", "properties": { "audioUrl": { "type": "string", "description": "URL of the generated audio file" } }, "required": ["audioUrl"] }
424
424
  },
@@ -10086,7 +10086,7 @@ async function startMcpServer(options) {
10086
10086
  capabilities: { tools: {} },
10087
10087
  serverInfo: {
10088
10088
  name: "mindstudio-agent",
10089
- version: "0.1.177"
10089
+ version: "0.1.178"
10090
10090
  },
10091
10091
  instructions: 'Welcome to MindStudio \u2014 a platform with 200+ AI models, 850+ third-party integrations, and pre-built agents.\n\nGetting started:\n1. Call `ask` with any question about the SDK \u2014 it knows every action, model, and connector and returns working code with real model IDs and config options. Examples: ask("generate an image with FLUX"), ask("what models support vision?"), ask("how do I send a Slack message?").\n2. Call `changeName` to set your display name \u2014 use your name or whatever your user calls you. This is how you\'ll appear in MindStudio request logs.\n3. If you have a profile picture, pass its public image URL to `changeProfilePicture`.\n4. For manual browsing, call `listActions` to discover all available actions.\n\nThen use the tools to generate text, images, video, audio, search the web, work with data sources, run agents, and more.\n\nImportant:\n- AI-powered actions (text generation, image generation, video, audio, etc.) cost money. Before running these, call `estimateActionCost` and confirm with the user before proceeding \u2014 unless they\'ve explicitly told you to go ahead.\n- Not all agents from `listAgents` are configured for API use. Do not try to run an agent just because it appears in the list \u2014 it will likely fail. Only run agents the user specifically asks you to run.'
10092
10092
  });
@@ -11126,7 +11126,7 @@ function isNewerVersion(current, latest) {
11126
11126
  return false;
11127
11127
  }
11128
11128
  async function checkForUpdate() {
11129
- const currentVersion = "0.1.177";
11129
+ const currentVersion = "0.1.178";
11130
11130
  if (!currentVersion || process.env.MINDSTUDIO_NO_UPDATE_CHECK) {
11131
11131
  return null;
11132
11132
  }
@@ -11161,7 +11161,7 @@ async function checkForUpdate() {
11161
11161
  }
11162
11162
  }
11163
11163
  function printUpdateNotice(latestVersion) {
11164
- const currentVersion = "0.1.177";
11164
+ const currentVersion = "0.1.178";
11165
11165
  process.stderr.write(
11166
11166
  `
11167
11167
  ${ansi2.cyanBright("Update available")} ${ansi2.gray(currentVersion + " \u2192")} ${ansi2.cyanBold(latestVersion)}
@@ -11174,7 +11174,7 @@ function isStandaloneBinary() {
11174
11174
  return !argv1.includes("node_modules");
11175
11175
  }
11176
11176
  async function cmdUpdate() {
11177
- const currentVersion = "0.1.177";
11177
+ const currentVersion = "0.1.178";
11178
11178
  process.stderr.write(
11179
11179
  ` ${ansi2.gray("Current version:")} ${currentVersion}
11180
11180
  `
@@ -11315,7 +11315,7 @@ async function cmdLogin(options) {
11315
11315
  process.stderr.write("\n");
11316
11316
  printLogo();
11317
11317
  process.stderr.write("\n");
11318
- const ver = "0.1.177";
11318
+ const ver = "0.1.178";
11319
11319
  process.stderr.write(
11320
11320
  ` ${ansi2.bold("MindStudio Agent")} ${ver ? " " + ansi2.gray("v" + ver) : ""}
11321
11321
  `
@@ -11643,7 +11643,7 @@ async function main() {
11643
11643
  const updatePromise = command !== "mcp" && command !== "login" && command !== "update" ? checkForUpdate() : Promise.resolve(null);
11644
11644
  try {
11645
11645
  if (command === "version" || command === "-v") {
11646
- process.stdout.write("0.1.177\n");
11646
+ process.stdout.write("0.1.178\n");
11647
11647
  return;
11648
11648
  }
11649
11649
  if (command === "login") {
@@ -812,7 +812,7 @@ export interface StepMethods {
812
812
  * - The default model is wavespeed-tripo3d-h3.1 (Tripo v3.1), which makes a model from the prompt, from one `image`, or from `images`: 2–4 views of the same object, in order front, left, back, right.
813
813
  * - Models and what they take, set in `threeDModelOverride.config`:
814
814
  * - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1–4 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1–5).
815
- * - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1–4 views), wavespeed-tripo3d-v2.5, seed3d-2.0, wavespeed-sam-3d-objects (with optional `mask_images`).
815
+ * - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1–4 views), seed3d-2.0.
816
816
  * - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).
817
817
  * - `$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.
818
818
  * - The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.
@@ -901,7 +901,7 @@ export interface StepMethods {
901
901
  *
902
902
  * @remarks
903
903
  * - `text` describes the sound effect to generate.
904
- * - The default model is elevenlabs-sound_v2. Options go in `soundModelOverride.config`:
904
+ * - The default model is elevenlabs-sound_v3. Options go in `soundModelOverride.config`:
905
905
  * - `durationSeconds` — the length, from 0.5 to 30. Left out, the model picks one from the text, and the effect is billed as 5 seconds whatever its length.
906
906
  * - `loop: true` — a sound that repeats with no audible start or end, for ambience and backgrounds.
907
907
  * - `promptInfluence` — how literally the text is followed, from 0 to 1 (default 0.3).
package/dist/index.js CHANGED
@@ -5188,7 +5188,7 @@ var stepMetadata = {
5188
5188
  "generate3dModel": {
5189
5189
  stepType: "generate3dModel",
5190
5190
  description: "Generate a 3D model using a 3D generation model.",
5191
- 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- `$mode` in the config picks a model's mode (`text-to-3d`, `image-to-3d`, or its multi-view mode). Left out, `images` picks the multi-view mode and `image` picks image-to-3d; with neither, the model's default mode. A text mode needs the prompt; in the others the prompt is optional guidance.\n- The output is standardized as a GLB URL plus optional FBX/OBJ/USDZ, thumbnail, texture maps, and provider task ID.",
5191
+ usageNotes: "- The default model is wavespeed-tripo3d-h3.1 (Tripo v3.1), which makes a model from the prompt, from one `image`, or from `images`: 2\u20134 views of the same object, in order front, left, back, right.\n- Models and what they take, set in `threeDModelOverride.config`:\n - From text or an image: wavespeed-tripo3d-h3.1, wavespeed-meshy7.1 (also `images`, 1\u20134 views), wavespeed-hunyuan3d-v3 (an `image`, plus optional `back_image_url`, `left_image_url`, `right_image_url`), wavespeed-hunyuan-3d-v3.1-rapid, wavespeed-tripo3d-p2, wavespeed-rodin-v2.5 (`images`, 1\u20135).\n - From an image only: trellis-2, wavespeed-meshy7 (or `images`, 1\u20134 views), seed3d-2.0.\n - From views: wavespeed-hi3d-v3.0 (`front_image`, and optional `back_image`, `left_image`, `right_image`).\n- `$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.",
5192
5192
  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" } } },
5193
5193
  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"] }
5194
5194
  },
@@ -5230,7 +5230,7 @@ var stepMetadata = {
5230
5230
  "generateSound": {
5231
5231
  stepType: "generateSound",
5232
5232
  description: "Generate a sound effect from a text description using a sound model.",
5233
- usageNotes: "- `text` describes the sound effect to generate.\n- The default model is elevenlabs-sound_v2. Options go in `soundModelOverride.config`:\n - `durationSeconds` \u2014 the length, from 0.5 to 30. Left out, the model picks one from the text, and the effect is billed as 5 seconds whatever its length.\n - `loop: true` \u2014 a sound that repeats with no audible start or end, for ambience and backgrounds.\n - `promptInfluence` \u2014 how literally the text is followed, from 0 to 1 (default 0.3).\n - `outputFormat` \u2014 MP3 (`mp3_44100_128` by default, up to `mp3_44100_192`) or Opus (`opus_48000_32` to `opus_48000_192`).\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
5233
+ usageNotes: "- `text` describes the sound effect to generate.\n- The default model is elevenlabs-sound_v3. Options go in `soundModelOverride.config`:\n - `durationSeconds` \u2014 the length, from 0.5 to 30. Left out, the model picks one from the text, and the effect is billed as 5 seconds whatever its length.\n - `loop: true` \u2014 a sound that repeats with no audible start or end, for ambience and backgrounds.\n - `promptInfluence` \u2014 how literally the text is followed, from 0 to 1 (default 0.3).\n - `outputFormat` \u2014 MP3 (`mp3_44100_128` by default, up to `mp3_44100_192`) or Opus (`opus_48000_32` to `opus_48000_192`).\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
5234
5234
  inputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The description of the sound effect to generate" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" }, "soundModelOverride": { "type": "object", "properties": { "model": { "type": "string" }, "config": { "type": "object", "properties": {}, "required": [] } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default sound model if not specified" } }, "required": ["text"] },
5235
5235
  outputSchema: { "type": "object", "properties": { "audioUrl": { "type": "string", "description": "URL of the generated audio file" } }, "required": ["audioUrl"] }
5236
5236
  },