@mindstudio-ai/agent 0.1.154 → 0.1.156

package/dist/index.d.ts

@@ -5288,7 +5288,7 @@ interface AnalyzeImageStepInput {
     imageUrl?: string;
     /** One or more image URLs to analyze together in a single model request */
     imageUrls?: string[];
-    /** Optional model configuration override. Uses the workflow's default vision model if not specified */
+    /** Optional model configuration override: a chat model that reads images. Uses the workflow's default image analysis model if not specified */
     visionModelOverride?: {
         model: string;
         config?: Record<string, unknown>;
@@ -9496,13 +9496,12 @@ interface StepMethods {
      */
     airtableGetTableRecords(step: AirtableGetTableRecordsStepInput, options?: StepExecutionOptions): Promise<StepExecutionResult<AirtableGetTableRecordsStepOutput>>;
     /**
-     * Analyze an image using a vision model based on a text prompt.
+     * Analyze one or more images with a chat model that reads images, based on a text prompt.
      *
      * @remarks
-     * - Uses the configured vision model to generate a text analysis of the image.
+     * - Runs on any chat model that reads images; the default is gemini-3.8-flash. `visionModelOverride` takes the same settings as a chat model's override (`model`, `temperature`, `maxResponseTokens`).
      * - The prompt should describe what to look for or extract from the image.
-     * - Pass imageUrl for a single image, or imageUrls for multiple images analyzed together in one request.
-     * - Most vision models (OpenAI, Grok, Gemini) accept multiple images in one request. Ideogram describe is single-image only.
+     * - Pass imageUrls for one or more images analyzed together in one request (imageUrl, a single image, still works).
      *
      * @example
      * ```typescript
@@ -11136,7 +11135,7 @@ interface StepMethods {
      * Render an HTML composition (HTML, CSS, media and seekable animation on a timeline) to a video file
      *
      * @remarks
-     * - Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.97, in Chrome off the app's own sandbox; author for that version
+     * - Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.113, in Chrome off the app's own sandbox; author for that version
      * - Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL
      * - `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`
      * - Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL

package/dist/index.js

@@ -4161,8 +4161,8 @@ var stepMetadata = {
   },
   "analyzeImage": {
     stepType: "analyzeImage",
-    description: "Analyze an image using a vision model based on a text prompt.",
-    usageNotes: "- Uses the configured vision model to generate a text analysis of the image.\n- The prompt should describe what to look for or extract from the image.\n- Pass imageUrl for a single image, or imageUrls for multiple images analyzed together in one request.\n- Most vision models (OpenAI, Grok, Gemini) accept multiple images in one request. Ideogram describe is single-image only.",
+    description: "Analyze one or more images with a chat model that reads images, based on a text prompt.",
+    usageNotes: "- Runs on any chat model that reads images; the default is gemini-3.8-flash. `visionModelOverride` takes the same settings as a chat model's override (`model`, `temperature`, `maxResponseTokens`).\n- The prompt should describe what to look for or extract from the image.\n- Pass imageUrls for one or more images analyzed together in one request (imageUrl, a single image, still works).",
     inputSchema: { "type": "object", "properties": { "prompt": { "type": "string", "description": "Instructions describing what to look for or extract from the image" }, "imageUrl": { "type": "string", "description": "URL of a single image to analyze. Kept for backward compatibility; prefer imageUrls." }, "imageUrls": { "type": "array", "items": { "type": "string" }, "description": "One or more image URLs to analyze together in a single model request" }, "visionModelOverride": { "anyOf": [{ "type": "object", "properties": { "model": { "type": "string" }, "config": { "type": "object", "properties": {}, "required": [] } }, "required": ["model"] }, { "type": "object", "properties": { "model": { "type": "string", "description": 'Model identifier (e.g. "gpt-4", "claude-3-opus")' }, "temperature": { "type": "number", "description": "Sampling temperature for the model (0-2)" }, "maxResponseTokens": { "type": "number", "description": "Maximum number of tokens in the model's response" }, "ignorePreamble": { "type": "boolean", "description": "Whether to skip the system preamble/instructions" }, "userMessagePreprocessor": { "type": "object", "properties": { "dataSource": { "type": "string", "description": "Data source identifier for the preprocessor" }, "messageTemplate": { "type": "string", "description": "Template string applied to user messages before sending to the model" }, "maxResults": { "type": "number", "description": "Maximum number of results to include from the data source" }, "enabled": { "type": "boolean", "description": "Whether the preprocessor is active" }, "shouldInherit": { "type": "boolean", "description": "Whether child steps should inherit this preprocessor configuration" } }, "description": "Preprocessor applied to user messages before sending to the model" }, "preamble": { "type": "string", "description": "System preamble/instructions for the model" }, "multiModelEnabled": { "type": "boolean", "description": "Whether multi-model candidate generation is enabled" }, "editResponseEnabled": { "type": "boolean", "description": "Whether the user can edit the model's response" }, "promptCaching": { "type": "boolean", "description": "Prompt caching, on models that bill cache writes. Absent: cached where something reads it back (the later steps of a run, a chat). `false` turns it off, for a single call such as a daily scheduled run. `true` caches even a single call, for a prompt resent unchanged within minutes." }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model", "temperature", "maxResponseTokens"] }] } }, "required": ["prompt"] },
     outputSchema: { "type": "object", "properties": { "analysis": { "type": "string", "description": "Text analysis of the image generated by the vision model" } }, "required": ["analysis"] }
   },
@@ -4879,7 +4879,7 @@ var stepMetadata = {
   "renderVideoFromHtmlComposition": {
     stepType: "renderVideoFromHtmlComposition",
     description: "Render an HTML composition (HTML, CSS, media and seekable animation on a timeline) to a video file",
-    usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.97, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
+    usageNotes: "- Renders an HTML composition in HyperFrames' format (https://hyperframes.heygen.com) with HyperFrames 0.8.113, in Chrome off the app's own sandbox; author for that version\n- Pass the composition as `html`, the page itself (up to 10 MB), or as `project`, the URL of a zip of a project's folder (`index.html` at its root, or the file `entryFile` names) or of one HTML file, up to 2 GiB: an app file or any public URL\n- `variables` overrides the composition's `data-composition-variables` defaults, which it reads with `window.__hyperframes.getVariables()`\n- Whatever the composition loads itself (fonts, scripts, images, video) is fetched as it renders, so each is in the project or at a public URL; a private app file needs a signed URL\n- fps 24, 30 or 60 (default 30); quality draft, standard or high (default standard); format mp4 (default), webm or mov (both keep transparency), or gif\n- An mp4, webm or mov renders in chunks of about 10 seconds side by side, so a long video takes little longer than a short one; a call finishes within about 30 minutes, and reports its progress as it goes. A gif renders whole, within 15 minutes\n- A composition HyperFrames can't render fails with HyperFrames' own reason",
     inputSchema: { "type": "object", "properties": { "html": { "type": "string", "description": "The composition's HTML, up to 10 MB; give this or project" }, "project": { "type": "string", "description": "URL of a zip of the project's folder, or of one self-contained HTML file; give this or html" }, "entryFile": { "type": "string", "description": "The entry HTML inside the zip, relative to its root; index.html when omitted" }, "variables": { "type": "object", "properties": {}, "required": [], "description": "Values over the composition's declared variables" }, "fps": { "enum": [24, 30, 60], "type": "number", "description": "Frames per second: 24, 30 (default) or 60" }, "quality": { "enum": ["draft", "standard", "high"], "type": "string", "description": "Encode quality: draft, standard (default) or high" }, "format": { "enum": ["mp4", "webm", "mov", "gif"], "type": "string", "description": "mp4 (default), webm or mov (both keep transparency), or gif" }, "intermediateAsset": { "type": "boolean", "description": "When true, the asset is created but hidden from the user's gallery (tagged as intermediate)" } } },
     outputSchema: { "type": "object", "properties": { "videoUrl": { "type": "string", "description": "URL of the rendered video" }, "durationSec": { "type": "number", "description": "Its length in seconds" }, "frames": { "type": "number", "description": "How many frames it has" } }, "required": ["videoUrl", "durationSec", "frames"] }
   },