@mindstudio-ai/remy 0.1.108 → 0.1.109

package/dist/headless.js

@@ -2454,8 +2454,6 @@ async function analyzeImage(params) {
 // src/tools/_helpers/screenshot.ts
 var SCREENSHOT_ANALYSIS_PROMPT = `Describe everything visible on screen from top to bottom \u2014 every element, its position, its size relative to the viewport, its colors, its content. Be comprehensive, thorough, and spatial. After the inventory, note anything that looks visually broken (overlapping elements, clipped text, misaligned components).
 
-Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
-
 Respond only with your analysis as Markdown and absolutely no other text. Do not use emojis - use unicode if you need symbols.`;
 async function captureAndAnalyzeScreenshot(promptOrOptions) {
   let prompt;
@@ -2489,7 +2487,10 @@ async function captureAndAnalyzeScreenshot(promptOrOptions) {
   if (prompt === false) {
     return url;
   }
-  const analysisPrompt = prompt || SCREENSHOT_ANALYSIS_PROMPT;
+  let analysisPrompt = prompt || SCREENSHOT_ANALYSIS_PROMPT;
+  analysisPrompt += `
+Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
+`;
   const analysis = await analyzeImage({
     prompt: analysisPrompt,
     imageUrl: url,
@@ -3462,8 +3463,6 @@ __export(analyzeImage_exports, {
 var DEFAULT_PROMPT = `
 Describe everything visible in this image \u2014 every element, its position, its size relative to the frame, its colors, its content. Be comprehensive, thorough and spatial. After the inventory, note anything that looks visually broken (overlapping elements, clipped text, misaligned components).
 
-Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
-
 Respond only with your analysis as Markdown and absolutely no other text. Do not use emojis - use unicode if you need symbols.`;
 var definition4 = {
   clearable: true,
@@ -3486,7 +3485,11 @@ var definition4 = {
 };
 async function execute4(input, onLog) {
   const imageUrl = input.imageUrl;
-  const prompt = input.prompt || DEFAULT_PROMPT;
+  let prompt = input.prompt || DEFAULT_PROMPT;
+  prompt += `
+
+  Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
+`;
   const analysis = await analyzeImage({
     prompt,
     imageUrl,
@@ -4576,7 +4579,7 @@ var SANITY_CHECK_TOOLS = [
   },
   {
     name: "askMindStudioSdk",
-    description: "Check if the MindStudio SDK has a managed action for something before writing custom code.",
+    description: "Check if the MindStudio SDK has a managed action for something before writing custom code. Use bullet points to ask many questions at once.",
     inputSchema: {
       type: "object",
       properties: {

package/dist/index.js

@@ -2186,7 +2186,10 @@ async function captureAndAnalyzeScreenshot(promptOrOptions) {
   if (prompt === false) {
     return url;
   }
-  const analysisPrompt = prompt || SCREENSHOT_ANALYSIS_PROMPT;
+  let analysisPrompt = prompt || SCREENSHOT_ANALYSIS_PROMPT;
+  analysisPrompt += `
+Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
+`;
   const analysis = await analyzeImage({
     prompt: analysisPrompt,
     imageUrl: url,
@@ -2202,8 +2205,6 @@ var init_screenshot = __esm({
     init_analyzeImage();
     SCREENSHOT_ANALYSIS_PROMPT = `Describe everything visible on screen from top to bottom \u2014 every element, its position, its size relative to the viewport, its colors, its content. Be comprehensive, thorough, and spatial. After the inventory, note anything that looks visually broken (overlapping elements, clipped text, misaligned components).
 
-Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
-
 Respond only with your analysis as Markdown and absolutely no other text. Do not use emojis - use unicode if you need symbols.`;
   }
 });
@@ -3289,7 +3290,11 @@ __export(analyzeImage_exports, {
 });
 async function execute4(input, onLog) {
   const imageUrl = input.imageUrl;
-  const prompt = input.prompt || DEFAULT_PROMPT;
+  let prompt = input.prompt || DEFAULT_PROMPT;
+  prompt += `
+
+  Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
+`;
   const analysis = await analyzeImage({
     prompt,
     imageUrl,
@@ -3305,8 +3310,6 @@ var init_analyzeImage2 = __esm({
     DEFAULT_PROMPT = `
 Describe everything visible in this image \u2014 every element, its position, its size relative to the frame, its colors, its content. Be comprehensive, thorough and spatial. After the inventory, note anything that looks visually broken (overlapping elements, clipped text, misaligned components).
 
-Note: ignore text wrapping issues. Screenshots occasionally show text wrapping onto an extra line compared to the live page \u2014 most noticeable in buttons, badges, and headings. This is a known limitation of SVG foreignObject rendering used the DOM-to-image capture library that took the screenshot. The browser's SVG renderer computes slightly wider text metrics than the HTML layout engine, so text that fits on one line in the live DOM can overflow by a fraction of a pixel in the capture - this is not a real issue.
-
 Respond only with your analysis as Markdown and absolutely no other text. Do not use emojis - use unicode if you need symbols.`;
     definition4 = {
       clearable: true,
@@ -4562,7 +4565,7 @@ var init_tools4 = __esm({
       },
       {
         name: "askMindStudioSdk",
-        description: "Check if the MindStudio SDK has a managed action for something before writing custom code.",
+        description: "Check if the MindStudio SDK has a managed action for something before writing custom code. Use bullet points to ask many questions at once.",
         inputSchema: {
           type: "object",
           properties: {

package/dist/prompt/static/instructions.md

@@ -17,7 +17,7 @@
 - Pushing to main branch will trigger a deploy. The user presses the publish button in the interface to request publishing.
 
 ### Build Notes
-For complex tasks — especially an initial buildout from a spec or making multiple changes in a single turn — write a `.remy-notes.md` scratchpad in the project root. Use it to track progress: a checklist of what's been built and what's remaining. Do not include implementation details in th notes. Read the spec files directly when you need reference data. Delete the notes file when your work is done.
+For complex tasks — especially an initial buildout from a spec or making multiple changes in a single turn — write a `.remy-notes.md` scratchpad in the project root. Use it to track progress: a checklist of what's been built and what's remaining. Never include implementation details or other decisions in the notes - it is solely for keeping track of tasks. Read the spec files directly when you need design details, implementation decisions, or other reference materials. Delete the notes file when your work is done.
 
 ## Communication
 The user can already see your tool calls, so most of your work is visible without narration. Focus text output on three things:

package/dist/prompt/static/intake.md

@@ -25,7 +25,7 @@ Don't recite this list to users. Use it to calibrate your sense of what's possib
 - **Automations** — cron jobs that monitor competitors and send alerts, webhook handlers that sync data between services, email processors that triage support requests — no UI needed
 - **Conversational AI agents** — custom chat UIs backed by any model, with tool access to the app's methods. Full control over what the agent can do and who can use it
 - **Bots & agent tools** — Discord slash-command bots, Telegram bots, MCP tool servers for AI assistants
-- **Creative projects** — browser games with p5.js or Three.js, interactive visualizations, generative art, portfolio sites with dynamic backends
+- **Creative projects** — browser games with p5.js or Three.js, interactive visualizations, 3D things, generative art, portfolio sites with dynamic backends
 - **Marketing & launch pages** — landing pages, waitlist pages with referral mechanics, product sites with scroll animations — visual polish is a strength here
 - **API services** — backend logic exposed as REST endpoints
 - **Simple static sites** — no backend needed, just a web interface with a build step

package/dist/subagents/designExpert/prompts/instructions.md

@@ -12,7 +12,7 @@ Think about the ways you can truly elevate the design. Use image generation to c
 
 ## Tool Usage
 - When multiple tool calls are independent, make them all in a single turn. Searching for three different products, or fetching two reference sites: batch them instead of doing one per turn.
-- The screenshot tool supports an `instructions` parameter for taking screenshots that require interaction first. If you need to screenshot a state that's behind a modal, a specific tab, or a multi-step flow, pass `instructions` describing how to get there (e.g., "dismiss the welcome modal, then click XYZ"). A browser automation agent will follow your instructions and capture the screenshot for you.
+- The screenshot tool supports an `instructions` parameter for taking screenshots that require interaction first. If you need to screenshot a state that's behind a modal, a specific tab, or a multi-step flow, pass `instructions` describing how to get there (e.g., "dismiss the welcome modal, then click XYZ"). A browser automation agent will follow your instructions and capture the screenshot for you. You can not use this to scroll - you will always receive a full page screenshot. Only use this if you need to trigger stateful changes within the app to get the full-page screenshot.
 - After you've taken a screenshot, use analyze image to ask different questions about it - don't re-screenshot the page unnecessarily.
 
 ## Voice

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/remy",
-  "version": "0.1.108",
+  "version": "0.1.109",
   "description": "MindStudio coding agent",
   "repository": {
     "type": "git",