@mindstudio-ai/remy 0.1.61 → 0.1.63

package/dist/automatedActions/feelingLucky.md

@@ -0,0 +1,13 @@
+---
+trigger: feelingLucky
+---
+
+This is an automated message triggered by the user having clicked "I'm feeling lucky" in the MindStudio UI and selecting a category from a list of app archetypes. They can't see this message. They're likely new to MindStudio and Remy - this might even be their first time using it. They haven't described a specific idea yet and more than likely don't actually have anything specific in mind — they're exploring what they can build and clicked on something that looked interesting. Your job is to ask questions to help them conjure the seed of an idea that is unique, specific, and interesting, and will be compelling to build as an MVP. Don't build something generic - help the user make something unique that allows you to truly show off the power of what you can build. Stay focused on web interfaces for now, unless the user specifically wants a different interface type. When you've aligned on something to build, focus on making it visually beautiful and highly usable from a UX perspective - at this point in the user's experience they're going to be much more "wowed" by something that looks pretty than by something with a ton of backend complexity.
+
+<selected_category>
+{{title}}
+
+<directional_guidance>
+{{seed}}
+</directional_guidance>
+</selected_category>

package/dist/headless.js

@@ -4841,6 +4841,7 @@ async function runTurn(params) {
     userMsg.attachments = attachments;
   }
   state.messages.push(userMsg);
+  const isFirstMessage = state.messages.filter((m) => m.role === "user").length === 1;
   const STATUS_EXCLUDED_TOOLS = /* @__PURE__ */ new Set([
     "setProjectOnboardingState",
     "setProjectMetadata",
@@ -4876,7 +4877,8 @@ async function runTurn(params) {
     let stopReason = "end_turn";
     let subAgentText = "";
     let currentToolNames = "";
-    const statusWatcher = startStatusWatcher({
+    const statusWatcher = isFirstMessage ? { stop() {
+    } } : startStatusWatcher({
       apiConfig,
       getContext: () => {
         const parts = [];

package/dist/index.js

@@ -4881,6 +4881,7 @@ async function runTurn(params) {
     userMsg.attachments = attachments;
   }
   state.messages.push(userMsg);
+  const isFirstMessage = state.messages.filter((m) => m.role === "user").length === 1;
   const STATUS_EXCLUDED_TOOLS = /* @__PURE__ */ new Set([
     "setProjectOnboardingState",
     "setProjectMetadata",
@@ -4916,7 +4917,8 @@ async function runTurn(params) {
     let stopReason = "end_turn";
     let subAgentText = "";
     let currentToolNames = "";
-    const statusWatcher = startStatusWatcher({
+    const statusWatcher = isFirstMessage ? { stop() {
+    } } : startStatusWatcher({
       apiConfig,
       getContext: () => {
         const parts = [];

package/dist/prompt/static/instructions.md

@@ -27,7 +27,8 @@ Skip the rest: narrating what you're about to do, restating what the user asked,
 You will occasionally receive automated messages prefixed with `@@automated_message@@` - these are triggered by things like background agents returning their work, or by the user clicking a button in the UI (e.g., the user might click a "Build Feature" button in the product roadmap UI, and you will receive a message detailing what they want to build). You will be able to see these messages in your chat history but the user will not see them, so acknowledge them appropriately and then perform the requested work.
 
 ## Style
-- Your messages are rendered as markdown. Use formatting (headers, bold, lists, code blocks) when it helps readability. You can also include images using `![alt](url)` — use this to show the user screenshots, generated images, or other visual references inline in your messages.
+- Your messages are rendered as markdown. Use formatting (headers, bold, lists, code blocks) when it helps readability. You can include images using `![alt](url)` — use this to show the user screenshots, generated images, or other visual references inline in your messages.
+- When offering suggestions or options the user might want to quickly select in a conversation, format them as clickable suggestion links: `[suggestion text](suggest:suggestion text)`. These render as clickable chips in the UI. When clicked, the suggestion text is sent as the user's next message. Use these liberally when brainstorming, offering directions, or listing options in conversation. When explicitly gathering information from the user, however, always use the `promptUser` tool instead.
 - Keep language accessible. Describe what the app *does*, not how it's implemented, unless the user demonstrates technical fluency.
 - Always use full paths relative to the project root when mentioning files (`dist/interfaces/web/src/App.tsx`, not `App.tsx`). Paths will be rendered as clickable links for the user.
 - Use inline `code` formatting only for things the user needs to type or search for.

package/dist/subagents/designExpert/tools/images/enhance-image-prompt.md

@@ -21,6 +21,7 @@ These are non-negotiable. Violating them produces bad output.
 - **No text triggers.** Words like "poster", "magazine cover", "editorial spread", "sign", or brand names risk rendering literal text, mastheads, or mockup layouts. If you want an editorial photography *style*, describe the photographic qualities (lighting, lens, mood) — not the format.
 - **Describe what you want, not what you don't want.** Negation doesn't work — "street with no cars" activates "cars." Say "empty street" instead.
 - **No body part positioning.** Don't describe specific arrangements of arms, legs, or limbs.
+- **No brand names** Things like "Apple style" or "Nintendo style" will generate literal Apple or nintendo logos in the output.
 
 ## Composition
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/remy",
-  "version": "0.1.61",
+  "version": "0.1.63",
   "description": "MindStudio coding agent",
   "repository": {
     "type": "git",