3.14.3b

docs/update-notes/index.md

@@ -5,6 +5,7 @@ This section contains notes about recent updates to Roo Code, listed by version
 ## Version 3.14
 
 *   [3.14](/update-notes/v3.14) (2025-04-24)
+*   [3.14.3](/update-notes/v3.14.3) (2025-04-25)
 *   [3.14.2](/update-notes/v3.14.2) (2025-04-24)
 *   [3.14.1](/update-notes/v3.14.1) (2025-04-24)
 *   [3.14.0](/update-notes/v3.14.0) (2025-04-23)

docs/update-notes/v3.14.3.md

@@ -0,0 +1,23 @@
+# Roo Code 3.14.3 Release Notes (2025-04-25)
+
+This patch release introduces the Boomerang Orchestrator mode, UI improvements, performance enhancements, and several bug fixes.
+
+## Boomerang is now default!
+
+*   Added Boomerang Orchestrator as a built-in mode. See the [Boomerang Tasks documentation](/features/boomerang-tasks) for more details.
+    <img src="/img/v3.14.3/v3.14.3-1.png" alt="Boomerang Orchestrator Mode" width="600" />
+
+## Sexy new minimalist look
+
+*   Improved the home screen user interface for a better initial experience.
+    <img src="/img/v3.14.3/v3.14.3.png" alt="New Minimalist Home Screen" width="600" />
+
+## QOL Updates and Bug Fixes
+
+*   Made token count estimation more efficient, reducing occurrences of gray screens during processing.
+*   Reverted the change to automatically close files after edits. This feature will be revisited once diagnostic integration issues are resolved.
+*   Cleaned up the internal settings data model for better maintainability.
+*   Optimized API calls by omitting reasoning parameters for models that do not support reasoning.
+*   Corrected word wrapping in Roo message titles (thanks zhangtony239!).
+*   Updated the default model ID for the Unbound provider from `claude-3.5-sonnet` to `claude-3.7-sonnet` (thanks pugazhendhi-m!).
+*   Improved clarity in the documentation regarding adding custom settings (thanks shariqriazz!).

docs/update-notes/v3.14.md

@@ -9,6 +9,16 @@
     *   **Why the checkbox?** This setting is provided as a temporary workaround for potential response delays sometimes observed with Google's caching mechanism when accessed via these two providers. Caching is *not* enabled by default for them.
     *   **Requesty:** Caching remains automatic for supported models via Requesty.
 
+## Boomerang Orchestrator Mode
+
+*   Added Boomerang Orchestrator as a built-in mode. See the [Boomerang Tasks documentation](/features/boomerang-tasks) for more details.
+    <img src="/img/v3.14.3/v3.14.3-1.png" alt="Boomerang Orchestrator Mode" width="600" />
+
+## Sexy new minimalist look
+
+*   Improved the home screen user interface for a better initial experience.
+    <img src="/img/v3.14.3/v3.14.3.png" alt="New Minimalist Home Screen" width="600" />
+=
 ## Apply Diff and Other Major File Edit Improvements
 
 *   Improve [`apply_diff`](/features/tools/apply-diff) to work better with **Google Gemini 2.5** and other models 
@@ -21,7 +31,6 @@
 *   Ensure user feedback is added to conversation history even during API errors (thanks System233!).
 *   Prevent redundant 'TASK RESUMPTION' prompts from appearing when resuming a task (thanks System233!).
 *   Fix issue where error messages sometimes didn't display after cancelling an API request (thanks System233!).
-*   Preserve editor state and prevent tab unpinning during diffs (thanks seedlord!)
 
 ## Terminal Fixes
 
@@ -59,11 +68,12 @@
 *   Improvements to Requesty model list fetching (thanks dtrugman!)
 *   Make the VS Code LM provider show the correct model information (thanks QuinsZouls!)
 *   Remove unnecessary calculation from VS Code LM provider (thanks d-oit!)
+*   Updated the default model ID for the Unbound provider from `claude-3.5-sonnet` to `claude-3.7-sonnet` (thanks pugazhendhi-m!).
 
 ## Bug Fixes and General QOL Improvements and Misc.
 
 *   Make the [`list_files`](/features/tools/list-files) tool more efficient and smarter about excluding directories like `.git/`
-*   Performance improvements to task size calculations
+*   Performance improvements to task size calculations, including more efficient token count estimation to reduce gray screens.
 *   Give better loading feedback on chat rows (thanks elianiva!)
 *   Use a more sensible task export icon
 *   Fix file drag and drop on Windows and when using SSH tunnels (thanks NyxJae!)
@@ -75,3 +85,11 @@
 *   Track tool use errors in evals
 *   Use path aliases in webview source files
 *   Better handling of FakeAI “controller” object (thanks wkordalski)
+*   Ensure user feedback is added to conversation history even during API errors (thanks System233!).
+*   Prevent redundant 'TASK RESUMPTION' prompts from appearing when resuming a task (thanks System233!).
+*   Fix issue where error messages sometimes didn't display after cancelling an API request (thanks System233!).
+*   Preserve editor state and prevent tab unpinning during diffs (thanks seedlord!)
+*   Cleaned up the internal settings data model for better maintainability.
+*   Optimized API calls by omitting reasoning parameters for models that do not support reasoning.
+*   Corrected word wrapping in Roo message titles (thanks zhangtony239!).
+*   Improved clarity in the documentation regarding adding custom settings (thanks shariqriazz!).

sidebars.ts

@@ -144,6 +144,7 @@ const sidebars: SidebarsConfig = {
           label: '3.14',
           items: [
 { type: 'doc', id: 'update-notes/v3.14', label: '3.14 Combined' },
+{ type: 'doc', id: 'update-notes/v3.14.3', label: '3.14.3' },
 { type: 'doc', id: 'update-notes/v3.14.2', label: '3.14.2' },
             { type: 'doc', id: 'update-notes/v3.14.1', label: '3.14.1' },
             { type: 'doc', id: 'update-notes/v3.14.0', label: '3.14.0' },