Release v3.37.0 (#10295)

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

Author: mrubens

.changeset/v3.37.0.md

@@ -0,0 +1,23 @@
+---
+"roo-cline": minor
+---
+
+![3.37.0 Release - Custom Tool Calling](/releases/3.37.0-release.png)
+
+- Add MiniMax M2.1 and improve environment_details handling for Minimax thinking models (PR #10284 by @hannesrudolph)
+- Add GLM-4.7 model with thinking mode support for Zai provider (PR #10282 by @hannesrudolph)
+- Add experimental custom tool calling - define custom tools that integrate seamlessly with your AI workflow (PR #10083 by @cte)
+- Deprecate XML tool protocol selection and force native tool format for new tasks (PR #10281 by @daniel-lxs)
+- Fix: Emit tool_call_end events in OpenAI handler when streaming ends (#10275 by @torxeon, PR #10280 by @daniel-lxs)
+- Fix: Emit tool_call_end events in BaseOpenAiCompatibleProvider (PR #10293 by @hannesrudolph)
+- Fix: Disable strict mode for MCP tools to preserve optional parameters (PR #10220 by @daniel-lxs)
+- Fix: Move array-specific properties into anyOf variant in normalizeToolSchema (PR #10276 by @daniel-lxs)
+- Fix: Add CRLF line ending normalization to search_replace and search_and_replace tools (PR #10288 by @hannesrudolph)
+- Fix: Add graceful fallback for model parsing in Chutes provider (PR #10279 by @hannesrudolph)
+- Fix: Enable Requesty refresh models with credentials (PR #10273 by @daniel-lxs)
+- Fix: Improve reasoning_details accumulation and serialization (PR #10285 by @hannesrudolph)
+- Fix: Preserve reasoning_content in condense summary for DeepSeek-reasoner (PR #10292 by @hannesrudolph)
+- Refactor Zai provider to merge environment_details into tool result instead of system message (PR #10289 by @hannesrudolph)
+- Remove parallel_tool_calls parameter from litellm provider (PR #10274 by @roomote)
+- Add Cloud Team page with comprehensive team management features (PR #10267 by @roomote)
+- Add message log deduper utility for evals (PR #10286 by @hannesrudolph)

releases/3.37.0-release.png

@@ -153,7 +153,7 @@ export class ClineProvider
 
 	public isViewLaunched = false
 	public settingsImportedAt?: number
-	public readonly latestAnnouncementId = "dec-2025-v3.36.0-context-rewind-roo-provider" // v3.36.0 Context Rewind & Roo Provider Improvements
+	public readonly latestAnnouncementId = "dec-2025-v3.37.0-minimax-m21-glm47-custom-tools" // v3.37.0 MiniMax M2.1, GLM-4.7, & Experimental Custom Tools
 	public readonly providerSettingsManager: ProviderSettingsManager
 	public readonly customModesManager: CustomModesManager
 

src/core/webview/ClineProvider.ts

@@ -44,8 +44,9 @@ const Announcement = ({ hideAnnouncement }: AnnouncementProps) => {
 					<div className="mb-4">
 						<p className="mb-3">{t("chat:announcement.release.heading")}</p>
 						<ul className="list-disc list-inside text-sm space-y-1.5">
-							<li>{t("chat:announcement.release.contextRewind")}</li>
-							<li>{t("chat:announcement.release.rooProvider")}</li>
+							<li>{t("chat:announcement.release.minimaxM21")}</li>
+							<li>{t("chat:announcement.release.glm47")}</li>
+							<li>{t("chat:announcement.release.customTools")}</li>
 						</ul>
 					</div>
 

webview-ui/src/components/chat/Announcement.tsx

@@ -333,8 +333,9 @@
 		},
 		"release": {
 			"heading": "What's New:",
-			"contextRewind": "Improved context condensing now lets you restore the full previous context when rewinding to a checkpoint",
-			"rooProvider": "Roo Code Cloud provider now preserves reasoning content and defaults to native tools for better performance"
+			"minimaxM21": "Fast and affordable MiniMax M2.1 model now available in Roo Code Cloud, MiniMax, and more",
+			"glm47": "Z.AI GLM-4.7 model with thinking mode support added to Roo Code Cloud, Z.AI, and more",
+			"customTools": "Experimental custom tool support for defining your own tools in TypeScript"
 		},
 		"cloudAgents": {
 			"heading": "New in the Cloud:",