feat: add release notes for version 3.25.8 and update sidebars configuration (#302)

Author: hannesrudolph

docs/update-notes/index.md

@@ -19,6 +19,7 @@ This section contains notes about recent updates to Roo Code, listed by version
 
 ## Version 3.25
 
+*   [3.25.8](/update-notes/v3.25.8) (2025-01-13)
 *   [3.25.7](/update-notes/v3.25.7) (2025-08-05)
 *   [3.25.6](/update-notes/v3.25.6) (2025-08-02)
 *   [3.25.5](/update-notes/v3.25.5) (2025-08-01)

docs/update-notes/v3.25.8.mdx

@@ -0,0 +1,54 @@
+---
+description: Memory leak fix for long conversations and Gemini 2.5 Pro thinking budget flexibility, plus multiple stability improvements.
+keywords:
+  - roo code 3.25.8
+  - memory leak fix
+  - gemini thinking budget
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.25.8 Release Notes (2025-01-13)
+
+This release fixes a critical memory leak in long conversations, prevents disabled MCP servers from starting, and provides more flexibility for Gemini 2.5 Pro thinking budgets, along with numerous stability improvements.
+
+## Disabled MCP Servers No Longer Start
+
+We've fixed a significant issue where disabled MCP servers were still starting processes and consuming resources ([#6084](https://github.com/RooCodeInc/Roo-Code/pull/6084)):
+
+- **No Wasted Resources**: Disabled servers now truly stay disabled and don't start background processes
+- **Clear Status Indicators**: Server status now accurately reflects whether a server is enabled or disabled
+- **Immediate Cleanup**: When MCP is globally disabled, all servers immediately disconnect
+
+This ensures your system resources are only used for the MCP servers you actually want to run.
+
+## Memory Leak Fix for Long Conversations
+
+We've resolved a critical memory leak that was causing excessive memory usage and grey screens in long conversations (thanks xyOz-dev!) ([#6697](https://github.com/RooCodeInc/Roo-Code/pull/6697)):
+
+- **Bounded Memory Usage**: Virtual scrolling now limits viewport rendering to 1000px below the current view instead of rendering infinitely
+- **Optimized Caching**: Reduced cache size and TTL to prevent memory accumulation
+- **Stable Performance**: Memory usage remains constant regardless of conversation length
+
+Your long conversations will now remain responsive and stable without the dreaded grey screen appearing.
+
+## Gemini 2.5 Pro Thinking Budget Flexibility
+
+Gemini 2.5 Pro users now have much more control over the thinking budget ([#6588](https://github.com/RooCodeInc/Roo-Code/pull/6588)):
+
+- **Lower Minimum**: The minimum thinking budget is reduced from 1024 to 128 tokens
+- **More Concise Coding**: Perfect for tasks that need quick, focused responses without extensive reasoning
+- **Manual Adjustment Required**: You'll need to manually adjust the thinking budget to 128 in your settings to take advantage of this feature
+
+This change gives you the flexibility to optimize for either deep reasoning or more concise, rapid responses depending on your needs.
+
+## Bug Fixes
+
+* **MCP Server Refresh**: Settings changes no longer trigger unnecessary MCP server refreshes ([#6779](https://github.com/RooCodeInc/Roo-Code/pull/6779))
+* **Codebase Search**: The tool now correctly searches the entire workspace when using "." as the path ([#6517](https://github.com/RooCodeInc/Roo-Code/pull/6517))
+* **Swift File Support**: Fixed VS Code crashes when indexing projects containing Swift files (thanks niteshbalusu11, sealad886!) ([#6724](https://github.com/RooCodeInc/Roo-Code/pull/6724))
+* **Context Management**: Model max tokens now intelligently capped at 20% of context window to prevent excessive condensing ([#6761](https://github.com/RooCodeInc/Roo-Code/pull/6761))
+* **OpenAI Configuration**: Extra whitespace in base URLs no longer breaks model detection (thanks vauhochzett!) ([#6560](https://github.com/RooCodeInc/Roo-Code/pull/6560))
+* **URL Fetching**: Better error recovery when fetching content from URLs (thanks QuinsZouls!) ([#6635](https://github.com/RooCodeInc/Roo-Code/pull/6635))
+* **Qdrant Recovery**: Code indexing automatically recovers when Qdrant becomes available after startup errors ([#6661](https://github.com/RooCodeInc/Roo-Code/pull/6661))
+* **Chat Scrolling**: Eliminated scroll jitter during message streaming ([#6780](https://github.com/RooCodeInc/Roo-Code/pull/6780))

docs/update-notes/v3.25.mdx

@@ -96,6 +96,7 @@ This feature provides peace of mind when using expensive models or running long
 
 Small changes that make a big difference in your daily workflow:
 
+* **Gemini 2.5 Pro Thinking Budget Flexibility**: The minimum thinking budget is reduced from 1024 to 128 tokens, perfect for tasks that need quick, focused responses without extensive reasoning. You'll need to manually adjust the thinking budget to 128 in your settings to take advantage of this feature.
 * **Multi-Folder Workspace Support**: Code indexing now works correctly across all folders in multi-folder workspaces
 * **Checkpoint Timing**: Checkpoints now save before file changes are made, allowing easy undo of unwanted modifications
 * **Redesigned Task Header**: Cleaner, more intuitive interface with improved visual hierarchy
@@ -129,6 +130,16 @@ Small changes that make a big difference in your daily workflow:
 
 Critical fixes that improve stability and compatibility:
 
+* **Memory Leak Fix**: Resolved a critical memory leak in long conversations that was causing excessive memory usage and grey screens. Virtual scrolling now limits viewport rendering and optimizes caching for stable performance regardless of conversation length.
+* **Disabled MCP Servers**: Fixed issue where disabled MCP servers were still starting processes and consuming resources. Disabled servers now truly stay disabled with clear status indicators and immediate cleanup when MCP is globally disabled.
+* **MCP Server Refresh**: Settings changes no longer trigger unnecessary MCP server refreshes
+* **Codebase Search**: The tool now correctly searches the entire workspace when using "." as the path
+* **Swift File Support**: Fixed VS Code crashes when indexing projects containing Swift files
+* **Context Management**: Model max tokens now intelligently capped at 20% of context window to prevent excessive condensing
+* **OpenAI Configuration**: Extra whitespace in base URLs no longer breaks model detection
+* **URL Fetching**: Better error recovery when fetching content from URLs
+* **Qdrant Recovery**: Code indexing automatically recovers when Qdrant becomes available after startup errors
+* **Chat Scrolling**: Eliminated scroll jitter during message streaming
 * **Mode Name Validation**: Prevents empty mode names from causing YAML parsing errors
 * **Text Highlight Alignment**: Fixed misalignment in chat input area highlights
 * **MCP Server Setting**: Properly respects the "Enable MCP Server Creation" setting

sidebars.ts

@@ -211,6 +211,7 @@ const sidebars: SidebarsConfig = {
           label: '3.25',
           items: [
             { type: 'doc', id: 'update-notes/v3.25', label: '3.25 Combined' },
+            { type: 'doc', id: 'update-notes/v3.25.8', label: '3.25.8' },
             { type: 'doc', id: 'update-notes/v3.25.7', label: '3.25.7' },
             { type: 'doc', id: 'update-notes/v3.25.6', label: '3.25.6' },
             { type: 'doc', id: 'update-notes/v3.25.5', label: '3.25.5' },