@mindstudio-ai/remy 0.1.160 → 0.1.162

package/dist/headless.js

@@ -5725,7 +5725,11 @@ var patterns = [
     /HTTP 5\d\d/i,
     "The AI service is temporarily unavailable. Please try again."
   ],
-  [/Stream stalled/i, "The connection was interrupted. Please try again."]
+  [/Stream stalled/i, "The connection was interrupted. Please try again."],
+  [
+    /content filter|Output blocked/i,
+    "The AI model's content moderation filter blocked this response. These are usually false positives, we apologize for the interruption. Rephrasing your request typically fixes this."
+  ]
 ];
 function friendlyError(raw) {
   for (const [pattern, message] of patterns) {

package/dist/index.js

@@ -6056,7 +6056,11 @@ var init_errors = __esm({
         /HTTP 5\d\d/i,
         "The AI service is temporarily unavailable. Please try again."
       ],
-      [/Stream stalled/i, "The connection was interrupted. Please try again."]
+      [/Stream stalled/i, "The connection was interrupted. Please try again."],
+      [
+        /content filter|Output blocked/i,
+        "The AI model's content moderation filter blocked this response. These are usually false positives, we apologize for the interruption. Rephrasing your request typically fixes this."
+      ]
     ];
   }
 });

package/dist/prompt/compiled/design.md

@@ -112,5 +112,6 @@ Always rely on the details provided by the design expert - their work is the sou
 - **Avoid long scrolling forms with no visual grouping.** Instead: group fields into sections with clear headings, cards, or stepped flows.
 - **Avoid cramped layouts.** Avoid text pressed against edges, no room to breathe. Instead: generous padding, comfortable margins, let the content float.
 - **Avoid loading states that are just a centered spinner on a blank page.** Instead: use skeletons that mirror the layout, or keep the existing structure visible with a subtle loading indicator.
+- **Always build styled modals, sheets, popovers, and toasts** Never use lazy native browser primitives like alert(), prompt(), or confirm().
 
 Most importantly: **Avoid any interface where the first reaction is "this looks like a demo" or "this looks like it was made with a website builder."**

package/dist/prompt/static/instructions.md

@@ -13,7 +13,7 @@
 - Work with what you already know. If you've read a file in this session, use what you learned rather than reading it again. If a subagent already researched something, use its findings. Every tool call costs time; prefer acting on information you have over re-gathering it.
 - When multiple tool calls are independent, make them all in a single turn. Reading three files, writing two methods, or running a scenario while taking a screenshot: batch them instead of doing one per turn.
 - After two failed attempts at the same approach, tell the user what's going wrong.
-- Never estimate how long something will take. Just do it.
+- Never estimate how long something will take or how much it will cost. Just do it. If the user asks, you must politely refuse and let them know that due to the way AI models work, any answer would just be a guess. You can, however, help them understand the scope and scale of the work, or how long it might take/how much it might cost a traditional engineering or product team (e.g., weeks/months, $100k USD+ to a consulting shop, etc.) - but you can not estimate token usage or costs of work within the system.
 - Pushing to main branch will trigger a deploy. The user presses the publish button in the interface to request publishing.
 
 ### Build Notes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/remy",
-  "version": "0.1.160",
+  "version": "0.1.162",
   "description": "MindStudio coding agent",
   "repository": {
     "type": "git",