@mindstudio-ai/remy 0.1.231 → 0.1.232

package/dist/headless.js

@@ -2882,6 +2882,19 @@ ${partial}` : "[INTERRUPTED] Tool execution was stopped.";
   }
 };
 
+// src/toolResultCap.ts
+var MAX_TOOL_RESULT_BYTES = 256 * 1024;
+function capToolResult(result) {
+  const total = Buffer.byteLength(result, "utf-8");
+  if (total <= MAX_TOOL_RESULT_BYTES) {
+    return result;
+  }
+  const head = Buffer.from(result, "utf-8").subarray(0, MAX_TOOL_RESULT_BYTES).toString("utf-8");
+  return head + `
+
+(tool result truncated at ${(MAX_TOOL_RESULT_BYTES / 1024).toFixed(0)}KB of ${(total / 1024).toFixed(0)}KB \u2014 too large to keep in context. Narrow the call (select fewer fields, paginate, or query a subset) instead of fetching everything.)`;
+}
+
 // src/statusWatcher.ts
 function startStatusWatcher(config) {
   const { apiConfig, getContext, onStatus, interval = 5e3, signal } = config;
@@ -3407,7 +3420,7 @@ ${partial}` : "[INTERRUPTED] Agent was interrupted before producing output.",
                   subAgentMessages
                 );
               }
-              safeSettle(result, result.startsWith("Error"));
+              safeSettle(capToolResult(result), result.startsWith("Error"));
             } catch (err) {
               safeSettle(`Error: ${err.message}`, true);
             }
@@ -3595,9 +3608,10 @@ var BROWSER_TOOLS = [
                   "evaluate",
                   "styles",
                   "screenshotFullPage",
-                  "screenshotViewport"
+                  "screenshotViewport",
+                  "setViewport"
                 ],
-                description: "snapshot: accessibility tree of the page (waits for network to settle). click: click an element (animated cursor, full event sequence). type: type text into input (one char at a time, works with React/Vue/Svelte). select: select a dropdown option by text. wait: wait for an element to appear (polls 100ms, waits for network). navigate: navigate to a URL within the app (waits for load, subsequent steps run on new page). evaluate: run JS in the page. styles: read computed CSS styles from elements (pass properties array with camelCase names, or omit for defaults). screenshotFullPage: full-page viewport-stitched screenshot (returns CDN url with dimensions). screenshotViewport: screenshot of just the visible viewport \u2014 pass `scrollToSelector` (or `scrollY`) on this step to scroll a section into view and capture it in one atomic step (no separate scroll needed)."
+                description: 'snapshot: accessibility tree of the page (waits for network to settle). click: click an element (animated cursor, full event sequence). type: type text into input (one char at a time, works with React/Vue/Svelte). select: select a dropdown option by text. wait: wait for an element to appear (polls 100ms, waits for network). navigate: navigate to a URL within the app (waits for load, subsequent steps run on new page). evaluate: run JS in the page. styles: read computed CSS styles from elements (pass properties array with camelCase names, or omit for defaults). screenshotFullPage: full-page viewport-stitched screenshot (returns CDN url with dimensions). screenshotViewport: screenshot of just the visible viewport \u2014 pass `scrollToSelector` (or `scrollY`) on this step to scroll a section into view and capture it in one atomic step (no separate scroll needed). setViewport: switch the browser between desktop and mobile rendering (pass `mode`: "desktop" or "mobile"). Reloads the page so responsive layouts, media queries, and matchMedia re-evaluate \u2014 use it to QA mobile/responsive views.'
               },
               ref: {
                 type: "string",
@@ -3651,6 +3665,11 @@ var BROWSER_TOOLS = [
               scrollY: {
                 type: "number",
                 description: "For screenshotViewport: absolute Y offset to scroll to before the shot, when no selector is available."
+              },
+              mode: {
+                type: "string",
+                enum: ["desktop", "mobile"],
+                description: 'For setViewport: the rendering mode to switch to. "mobile" emulates a phone (narrow width, touch, device pixel ratio); "desktop" is the standard wide viewport.'
               }
             },
             required: ["command"]
@@ -3700,6 +3719,14 @@ var log7 = createLogger("browser-automation");
 async function runBrowserAutomation(task, context, opts) {
   const release = await acquireBrowserLock();
   try {
+    try {
+      await sidecarRequest(
+        "/set-viewport",
+        { mode: "default" },
+        { timeout: 2e4 }
+      );
+    } catch {
+    }
     let lastBrowserCommandViewport;
     const result = await runSubAgent({
       system: getBrowserAutomationPrompt(),
@@ -6401,21 +6428,6 @@ function triggerBrandExtraction(apiConfig, model) {
 // src/session.ts
 import fs22 from "fs";
 import path11 from "path";
-
-// src/toolResultCap.ts
-var MAX_TOOL_RESULT_BYTES = 256 * 1024;
-function capToolResult(result) {
-  const total = Buffer.byteLength(result, "utf-8");
-  if (total <= MAX_TOOL_RESULT_BYTES) {
-    return result;
-  }
-  const head = Buffer.from(result, "utf-8").subarray(0, MAX_TOOL_RESULT_BYTES).toString("utf-8");
-  return head + `
-
-(tool result truncated at ${(MAX_TOOL_RESULT_BYTES / 1024).toFixed(0)}KB of ${(total / 1024).toFixed(0)}KB \u2014 too large to keep in context. Narrow the call (select fewer fields, paginate, or query a subset) instead of fetching everything.)`;
-}
-
-// src/session.ts
 var log12 = createLogger("session");
 var SESSION_FILE = ".remy-session.json";
 var ARCHIVE_DIR = ".logs/sessions";

package/dist/index.js

@@ -3513,6 +3513,25 @@ ${partial}` : "[INTERRUPTED] Tool execution was stopped.";
   }
 });
 
+// src/toolResultCap.ts
+function capToolResult(result) {
+  const total = Buffer.byteLength(result, "utf-8");
+  if (total <= MAX_TOOL_RESULT_BYTES) {
+    return result;
+  }
+  const head = Buffer.from(result, "utf-8").subarray(0, MAX_TOOL_RESULT_BYTES).toString("utf-8");
+  return head + `
+
+(tool result truncated at ${(MAX_TOOL_RESULT_BYTES / 1024).toFixed(0)}KB of ${(total / 1024).toFixed(0)}KB \u2014 too large to keep in context. Narrow the call (select fewer fields, paginate, or query a subset) instead of fetching everything.)`;
+}
+var MAX_TOOL_RESULT_BYTES;
+var init_toolResultCap = __esm({
+  "src/toolResultCap.ts"() {
+    "use strict";
+    MAX_TOOL_RESULT_BYTES = 256 * 1024;
+  }
+});
+
 // src/statusWatcher.ts
 function startStatusWatcher(config) {
   const { apiConfig, getContext, onStatus, interval = 5e3, signal } = config;
@@ -4053,7 +4072,7 @@ ${partial}` : "[INTERRUPTED] Agent was interrupted before producing output.",
                   subAgentMessages
                 );
               }
-              safeSettle(result, result.startsWith("Error"));
+              safeSettle(capToolResult(result), result.startsWith("Error"));
             } catch (err) {
               safeSettle(`Error: ${err.message}`, true);
             }
@@ -4189,6 +4208,7 @@ var init_runner = __esm({
     init_logger();
     init_usageLedger();
     init_toolRegistry();
+    init_toolResultCap();
     init_statusWatcher();
     init_cleanMessages();
     log7 = createLogger("sub-agent");
@@ -4258,9 +4278,10 @@ var init_tools = __esm({
                       "evaluate",
                       "styles",
                       "screenshotFullPage",
-                      "screenshotViewport"
+                      "screenshotViewport",
+                      "setViewport"
                     ],
-                    description: "snapshot: accessibility tree of the page (waits for network to settle). click: click an element (animated cursor, full event sequence). type: type text into input (one char at a time, works with React/Vue/Svelte). select: select a dropdown option by text. wait: wait for an element to appear (polls 100ms, waits for network). navigate: navigate to a URL within the app (waits for load, subsequent steps run on new page). evaluate: run JS in the page. styles: read computed CSS styles from elements (pass properties array with camelCase names, or omit for defaults). screenshotFullPage: full-page viewport-stitched screenshot (returns CDN url with dimensions). screenshotViewport: screenshot of just the visible viewport \u2014 pass `scrollToSelector` (or `scrollY`) on this step to scroll a section into view and capture it in one atomic step (no separate scroll needed)."
+                    description: 'snapshot: accessibility tree of the page (waits for network to settle). click: click an element (animated cursor, full event sequence). type: type text into input (one char at a time, works with React/Vue/Svelte). select: select a dropdown option by text. wait: wait for an element to appear (polls 100ms, waits for network). navigate: navigate to a URL within the app (waits for load, subsequent steps run on new page). evaluate: run JS in the page. styles: read computed CSS styles from elements (pass properties array with camelCase names, or omit for defaults). screenshotFullPage: full-page viewport-stitched screenshot (returns CDN url with dimensions). screenshotViewport: screenshot of just the visible viewport \u2014 pass `scrollToSelector` (or `scrollY`) on this step to scroll a section into view and capture it in one atomic step (no separate scroll needed). setViewport: switch the browser between desktop and mobile rendering (pass `mode`: "desktop" or "mobile"). Reloads the page so responsive layouts, media queries, and matchMedia re-evaluate \u2014 use it to QA mobile/responsive views.'
                   },
                   ref: {
                     type: "string",
@@ -4314,6 +4335,11 @@ var init_tools = __esm({
                   scrollY: {
                     type: "number",
                     description: "For screenshotViewport: absolute Y offset to scroll to before the shot, when no selector is available."
+                  },
+                  mode: {
+                    type: "string",
+                    enum: ["desktop", "mobile"],
+                    description: 'For setViewport: the rendering mode to switch to. "mobile" emulates a phone (narrow width, touch, device pixel ratio); "desktop" is the standard wide viewport.'
                   }
                 },
                 required: ["command"]
@@ -4371,6 +4397,14 @@ var init_prompt2 = __esm({
 async function runBrowserAutomation(task, context, opts) {
   const release = await acquireBrowserLock();
   try {
+    try {
+      await sidecarRequest(
+        "/set-viewport",
+        { mode: "default" },
+        { timeout: 2e4 }
+      );
+    } catch {
+    }
     let lastBrowserCommandViewport;
     const result = await runSubAgent({
       system: getBrowserAutomationPrompt(),
@@ -6755,25 +6789,6 @@ var init_tools7 = __esm({
   }
 });
 
-// src/toolResultCap.ts
-function capToolResult(result) {
-  const total = Buffer.byteLength(result, "utf-8");
-  if (total <= MAX_TOOL_RESULT_BYTES) {
-    return result;
-  }
-  const head = Buffer.from(result, "utf-8").subarray(0, MAX_TOOL_RESULT_BYTES).toString("utf-8");
-  return head + `
-
-(tool result truncated at ${(MAX_TOOL_RESULT_BYTES / 1024).toFixed(0)}KB of ${(total / 1024).toFixed(0)}KB \u2014 too large to keep in context. Narrow the call (select fewer fields, paginate, or query a subset) instead of fetching everything.)`;
-}
-var MAX_TOOL_RESULT_BYTES;
-var init_toolResultCap = __esm({
-  "src/toolResultCap.ts"() {
-    "use strict";
-    MAX_TOOL_RESULT_BYTES = 256 * 1024;
-  }
-});
-
 // src/session.ts
 import fs20 from "fs";
 import path9 from "path";

package/dist/subagents/browserAutomation/prompt.md

@@ -44,6 +44,7 @@ Note: the snapshot concatenates inline text and strips whitespace. If you need t
 - `evaluate`: Run arbitrary JavaScript in the page and return the result.
 - `styles`: Read computed CSS styles from page elements. Pass a `properties` array with camelCase CSS property names (e.g., `["backgroundColor", "borderRadius", "fontSize"]`). Omit `properties` for a default set covering colors, typography, spacing, borders, shadows, dimensions, and layout. Uses the same targeting as click/type (ref, text, role, label, selector). Omit the target to get styles for all elements from the last snapshot.
 - `screenshotViewport`: Take a screenshot of the visible viewport. Returns CDN url with full text analysis and dimensions. To capture a specific section, set `scrollToSelector` (a CSS selector) — or `scrollY` (an absolute offset) — on this same step; it scrolls the target into view and captures it atomically, so you do NOT need a separate scroll step. Do not use if you can get what you need with other tools - only use when you need to visually see the viewport.
+- `setViewport`: Switch the browser between desktop and mobile rendering. Set `mode` to `"desktop"` or `"mobile"`. Mobile emulates a phone (390-wide, touch, device pixel ratio 2); desktop is the standard wide viewport. This reloads the page so media queries, responsive layouts, and `matchMedia` re-evaluate — the reload clears in-page state, so switch before you set up the state you want to inspect. The mode persists across navigations within a run. Each run starts in the app's default mode, so only use this when you need to check the other one.
 
 ### Element targeting (tried in order)
 
@@ -118,6 +119,16 @@ Capture a specific below-the-fold section (scroll + capture in one atomic step):
 }
 ```
 
+Check the mobile layout of a page:
+```json
+{
+  "steps": [
+    { "command": "setViewport", "mode": "mobile" },
+    { "command": "screenshotViewport" }
+  ]
+}
+```
+
 Navigate to a sub-page and interact with it:
 ```json
 {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mindstudio-ai/remy",
-  "version": "0.1.231",
+  "version": "0.1.232",
   "description": "Remy coding agent",
   "repository": {
     "type": "git",