Add release notes for versions 3.25.16 and 3.25.17 (#311)

Author: hannesrudolph

docs/update-notes/index.md

@@ -19,6 +19,8 @@ This section contains notes about recent updates to Roo Code, listed by version
 
 ## Version 3.25
 
+*   [3.25.17](/update-notes/v3.25.17) (2025-08-18)
+*   [3.25.16](/update-notes/v3.25.16) (2025-08-17)
 *   [3.25.15](/update-notes/v3.25.15) (2025-08-14)
 *   [3.25.14](/update-notes/v3.25.14) (2025-08-13)
 *   [3.25.13](/update-notes/v3.25.13) (2025-08-13)

docs/update-notes/v3.25.16.mdx

@@ -0,0 +1,39 @@
+---
+description: Improves Ollama integration, adds GPT-5 chat support, and fixes multiple UI and stability issues.
+keywords:
+  - roo code 3.25.16
+  - ollama native api
+  - gpt-5 chat
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.25.16 Release Notes (2025-08-17)
+
+This release improves provider integrations with native Ollama API support and GPT-5 chat model, enhances task history handling, and fixes several UI and stability issues.
+
+## Provider Updates
+
+* **Native Ollama API**: Fixed Ollama models to use native API instead of OpenAI compatibility layer for improved performance and reliability ([#7137](https://github.com/RooCodeInc/Roo-Code/pull/7137))
+* **OpenAI GPT-5 Chat**: Added support for gpt-5-chat-latest model optimized for conversational AI and non-reasoning tasks ([#7058](https://github.com/RooCodeInc/Roo-Code/pull/7058))
+
+## QOL Improvements
+
+* **Enhanced Task History**: Made "enhance with task history" default to true for better context retention in conversations (thanks liwilliam2021!) ([#7140](https://github.com/RooCodeInc/Roo-Code/pull/7140))
+* **Improved Scrollbar**: Fixed scrollbar jumping in long conversations by removing the 500-message limit ([#7064](https://github.com/RooCodeInc/Roo-Code/pull/7064))
+
+## Bug Fixes
+
+* **Settings UI**: Fixed allowedMaxRequests and allowedMaxCost values not displaying properly (thanks chrarnoldus!) ([#6925](https://github.com/RooCodeInc/Roo-Code/pull/6925))
+* **Provider Settings**: Fixed save button not enabling for provider dropdown and checkbox changes ([#7113](https://github.com/RooCodeInc/Roo-Code/pull/7113))
+* **XML Entity Handling**: Fixed XML entity decoding issues in diff tools that caused content mismatches ([#7108](https://github.com/RooCodeInc/Roo-Code/pull/7108))
+* **Condensing State**: Fixed condensing state not resetting when switching between tasks (thanks f14XuanLv!) ([#6922](https://github.com/RooCodeInc/Roo-Code/pull/6922))
+* **Workspace Paths**: Fixed workspace path resolution in codebase search tool (thanks NaccOll!) ([#6902](https://github.com/RooCodeInc/Roo-Code/pull/6902))
+* **Multi-folder Workspaces**: Fixed checkpoint handling for multi-folder workspace configurations (thanks NaccOll!) ([#6903](https://github.com/RooCodeInc/Roo-Code/pull/6903))
+* **Diff Processing**: Added type checking to prevent errors when processing diff content ([#6906](https://github.com/RooCodeInc/Roo-Code/pull/6906))
+
+## Misc Improvements
+
+* **Task System**: Added API for resuming tasks, improved event handling, and enhanced metadata support ([#7122](https://github.com/RooCodeInc/Roo-Code/pull/7122), [#7128](https://github.com/RooCodeInc/Roo-Code/pull/7128), [#7117](https://github.com/RooCodeInc/Roo-Code/pull/7117), [#7092](https://github.com/RooCodeInc/Roo-Code/pull/7092))
+* **Web Infrastructure**: Improved sitemap generation and SEO metadata (thanks elianiva, abumalick!) ([#7102](https://github.com/RooCodeInc/Roo-Code/pull/7102), [#7096](https://github.com/RooCodeInc/Roo-Code/pull/7096), [#6206](https://github.com/RooCodeInc/Roo-Code/pull/6206))
+* **Task Execution**: Refactored task execution system for better call stack management (thanks catrielmuller!) ([#7035](https://github.com/RooCodeInc/Roo-Code/pull/7035))

docs/update-notes/v3.25.17.mdx

@@ -0,0 +1,17 @@
+---
+description: Fixes LM Studio model duplication and terminal reuse issues.
+keywords:
+  - roo code 3.25.17
+  - lm studio
+  - bug fixes
+image: /img/social-share.jpg
+---
+
+# Roo Code 3.25.17 Release Notes (2025-08-18)
+
+This release fixes issues with LM Studio model management and terminal reuse logic.
+
+## Bug Fixes
+
+* **LM Studio Models**: Fixed duplicate model entries by implementing case-insensitive deduplication, ensuring models appear only once in the provider configuration ([#7185](https://github.com/RooCodeInc/Roo-Code/pull/7185))
+* **Terminal Reuse**: Fixed terminal reuse logic to properly handle terminal lifecycle management ([#7157](https://github.com/RooCodeInc/Roo-Code/pull/7157))

docs/update-notes/v3.25.mdx

@@ -133,6 +133,8 @@ Small changes that make a big difference in your daily workflow:
 * **Marketplace Updates**: Auto-refresh marketplace data when organization settings change ([#6446](https://github.com/RooCodeInc/Roo-Code/pull/6446))
 * **`codebase_search` Tool**: Clarified that the `path` parameter is optional and the tool searches the entire workspace by default
 * **Token Usage Reporting**: Fixed an issue where token usage and cost were underreported, providing more accurate cost tracking
+* **Enhanced Task History**: Made "enhance with task history" default to true for better context retention in conversations
+* **Improved Scrollbar**: Fixed scrollbar jumping in long conversations by removing the 500-message limit
 
 ### Bug Fixes
 
@@ -189,13 +191,17 @@ Critical fixes that improve stability and compatibility:
 * **`max_tokens` Calculation**: Fixed an error for models with very large context windows where requests would fail due to incorrect calculation of maximum output tokens
 * **AWS Bedrock Connection**: Fixed a connection issue when using AWS Bedrock with LiteLLM
 * **Search Tool Reliability**: Fixed the search_files tool failing when encountering permission-denied files - it now continues working and returns results from accessible files
+* **Native Ollama API**: Fixed Ollama models to use native API instead of OpenAI compatibility layer for improved performance and reliability
+* **Terminal Reuse**: Fixed terminal reuse logic to properly handle terminal lifecycle management
+* **LM Studio Models**: Fixed duplicate model entries by implementing case-insensitive deduplication, ensuring models appear only once in the provider configuration
 
 ### Provider Updates
 
 * **GPT-5 Model Support**: Added support for OpenAI's latest GPT-5 model family:
   - `gpt-5-2025-08-07`: The full GPT-5 model, now set as the default for OpenAI Native provider
   - `gpt-5-mini-2025-08-07`: A smaller, faster variant for quick responses
   - `gpt-5-nano-2025-08-07`: The most compact version for resource-constrained scenarios
+  - `gpt-5-chat-latest`: Optimized for conversational AI and non-reasoning tasks
 * **GPT-5 Verbosity Controls**: New settings to control model output detail levels (low, medium, high), allowing you to fine-tune response length and detail based on your needs
 * **Fireworks AI Models**: Added GLM-4.5 series models (355B and 106B parameters with 128K context) and OpenAI gpt-oss models (20b for edge deployments, 120b for production use) to expand model selection options
 * **Claude Opus 4.1 Support**: Added support for the new Claude Opus 4.1 model across Anthropic, Claude Code, Bedrock, Vertex AI, and LiteLLM providers with 8192 max tokens, reasoning budget support, and prompt caching

sidebars.ts

@@ -212,6 +212,8 @@ const sidebars: SidebarsConfig = {
           label: '3.25',
           items: [
             { type: 'doc', id: 'update-notes/v3.25', label: '3.25 Combined' },
+            { type: 'doc', id: 'update-notes/v3.25.17', label: '3.25.17' },
+            { type: 'doc', id: 'update-notes/v3.25.16', label: '3.25.16' },
             { type: 'doc', id: 'update-notes/v3.25.15', label: '3.25.15' },
             { type: 'doc', id: 'update-notes/v3.25.14', label: '3.25.14' },
             { type: 'doc', id: 'update-notes/v3.25.13', label: '3.25.13' },