Merge pull request #1395 from RooVetGit/changeset-release/main

Changeset version bump

.changeset/nine-cameras-applaud.md

@@ -1,5 +0,0 @@
----
-"roo-cline": patch
----
-
-Disable repo-per-workspace checkpoints

.changeset/shiny-mugs-care.md

@@ -1,5 +0,0 @@
----
-"roo-cline": patch
----
-
-Remove item number from history preview cards

.changeset/tame-carpets-bake.md

@@ -1,5 +0,0 @@
----
-"roo-cline": patch
----
-
-Add credentials auth for Google vertex

.changeset/wise-bats-perform.md

@@ -1,5 +0,0 @@
----
-"roo-cline": patch
----
-
-Handle outputless commands

.changeset/wise-pears-join.md

@@ -1,5 +0,0 @@
----
-"roo-cline": patch
----
-
-Improved observability of openai compatible APIs, by sending x-title and http-referer headers, as per Open Router standard.

.changeset/young-wolves-add.md

@@ -1,5 +0,0 @@
----
-"roo-cline": minor
----
-
-v3.8

CHANGELOG.md

@@ -1,5 +1,24 @@
 # Roo Code Changelog
 
+## [3.8.0]
+
+- Add opt-in telemetry to help us improve Roo Code faster (thanks Cline!)
+- Fix terminal overload / gray screen of death, and other terminal issues
+- Add a new experimental diff editing strategy that applies multiple diff edits at once (thanks @qdaxb!)
+- Add support for a .rooignore to prevent Roo Code from read/writing certain files, with a setting to also exclude them from search/lists (thanks Cline!)
+- Update the new_task tool to return results to the parent task on completion, supporting better orchestration (thanks @shaybc!)
+- Support running Roo in multiple editor windows simultaneously (thanks @samhvw8!)
+- Make checkpoints asynchronous and exclude more files to speed them up
+- Redesign the settings page to make it easier to navigate
+- Add credential-based authentication for Vertex AI, enabling users to easily switch between Google Cloud accounts (thanks @eonghk!)
+- Update the DeepSeek provider with the correct baseUrl and track caching correctly (thanks @olweraltuve!)
+- Add a new “Human Relay” provider that allows you to manually copy information to a Web AI when needed, and then paste the AI's response back into Roo Code (thanks @NyxJae)!
+- Add observability for OpenAI providers (thanks @refactorthis!)
+- Support speculative decoding for LM Studio local models (thanks @adamwlarson!)
+- Improve UI for mode/provider selectors in chat
+- Improve styling of the task headers (thanks @monotykamary!)
+- Improve context mention path handling on Windows (thanks @samhvw8!)
+
 ## [3.7.12]
 
 - Expand max tokens of thinking models to 128k, and max thinking budget to over 100k (thanks @monotykamary!)

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "roo-cline",
-	"version": "3.7.12",
+	"version": "3.8.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "roo-cline",
-			"version": "3.7.12",
+			"version": "3.8.0",
 			"dependencies": {
 				"@anthropic-ai/bedrock-sdk": "^0.10.2",
 				"@anthropic-ai/sdk": "^0.37.0",

package.json

@@ -3,7 +3,7 @@
 	"displayName": "Roo Code (prev. Roo Cline)",
 	"description": "A whole dev team of AI agents in your editor.",
 	"publisher": "RooVeterinaryInc",
-	"version": "3.7.12",
+	"version": "3.8.0",
 	"icon": "assets/icons/rocket.png",
 	"galleryBanner": {
 		"color": "#617A91",