docs: add release notes for v3.36.12 and v3.36.13 (#462)

Author: hannesrudolph

docs/update-notes/index.md

@@ -24,6 +24,8 @@ If you want to live on the edge and try things out before it's released, we have
 
 ### Version 3.36
 
+*   [3.36.13](/update-notes/v3.36.13) (2025-12-18)
+*   [3.36.12](/update-notes/v3.36.12) (2025-12-18)
 *   [3.36.11](/update-notes/v3.36.11) (2025-12-17)
 *   [3.36.10](/update-notes/v3.36.10) (2025-12-17)
 *   [3.36.9](/update-notes/v3.36.9) (2025-12-16)

docs/update-notes/v3.36.12.mdx

@@ -0,0 +1,27 @@
+---
+description: Improved tool preferences for Gemini and OpenAI models, Bedrock embedder fix, and better error tracking.
+keywords:
+  - roo code 3.36.12
+  - gemini tool preferences
+  - openai tool preferences
+  - bedrock embedder
+image: /img/v3.36.12/v3.36.12.png
+---
+
+# Roo Code 3.36.12 Release Notes (2025-12-18)
+
+This release improves default tool preferences for Gemini and OpenAI models, fixes Bedrock embedder identification, and enhances error tracking.
+
+<img src="/img/v3.36.12/v3.36.12.png" alt="Roo Code v3.36.12 Release" width="600" />
+
+## QOL Improvements
+
+* **Smarter Tool Defaults for Gemini and OpenAI**: Gemini and OpenAI models now use better default tools for file editing, improving reliability out of the box. ([#10170](https://github.com/RooCodeInc/Roo-Code/pull/10170))
+
+## Bug Fixes
+
+* **Bedrock Embedder CloudTrail Fix**: AWS Bedrock users now see Roo Code identified in CloudTrail logs when using Codebase Indexing. (thanks jackrein!) ([#10166](https://github.com/RooCodeInc/Roo-Code/pull/10166))
+
+## Misc Improvements
+
+* **Better Error Grouping**: Improved error tracking for faster issue resolution. ([#10163](https://github.com/RooCodeInc/Roo-Code/pull/10163))

docs/update-notes/v3.36.13.mdx

@@ -0,0 +1,34 @@
+---
+description: Native tool protocol becomes the new default for compatible models, plus new edit_file tool and VS Code LM native tool support.
+keywords:
+  - roo code 3.36.13
+  - native tool protocol
+  - edit_file tool
+  - vs code language model
+  - litellm
+image: /img/v3.36.13/v3.36.13.png
+---
+
+# Roo Code 3.36.13 Release Notes (2025-12-18)
+
+This release switches to native tool protocol by default, improves file editing for Gemini models, and adds native tool support for VS Code Language Model providers.
+
+<img src="/img/v3.36.13/v3.36.13.png" alt="Roo Code v3.36.13 Release" width="600" />
+
+## Native Tool Protocol Default
+
+Models that support native tool calling now default to using native protocol instead of XML. The XML protocol is still available in provider settings ([#10186](https://github.com/RooCodeInc/Roo-Code/pull/10186)).
+
+## QOL Improvements
+
+* **Improved File Editing with Gemini Models**: New edit_file tool makes Gemini models more effective at editing files ([#9983](https://github.com/RooCodeInc/Roo-Code/pull/9983))
+* **VS Code LM Native Tools**: Native tool calling now works with VS Code's built-in Copilot models ([#10191](https://github.com/RooCodeInc/Roo-Code/pull/10191))
+
+## Bug Fixes
+
+* **LiteLLM Tool Protocol Dropdown**: The Native/XML protocol selector now appears correctly for LiteLLM models ([#10187](https://github.com/RooCodeInc/Roo-Code/pull/10187))
+* **Task Resumption**: Tasks no longer break when resuming after changing the Native Tool Calling setting ([#10192](https://github.com/RooCodeInc/Roo-Code/pull/10192))
+
+## Misc Improvements
+
+* **Error Monitoring**: Improved tracking of consecutive mistake errors ([#10193](https://github.com/RooCodeInc/Roo-Code/pull/10193))

docs/update-notes/v3.36.mdx

@@ -53,7 +53,11 @@ The `gemini-3-flash-preview` model is now available in the Roo Code Cloud provid
 
 ## DeepSeek reasoner: interleaved thinking during tool use
 
-The DeepSeek provider’s `deepseek-reasoner` model now supports “interleaved thinking” and native tool calling. In our internal evals, tool calling succeeded 100% of the time, and the extended-run score improved to 93.4% (thanks zbww_!) ([#9969](https://github.com/RooCodeInc/Roo-Code/pull/9969), [#10141](https://github.com/RooCodeInc/Roo-Code/pull/10141)).
+The DeepSeek provider's `deepseek-reasoner` model now supports "interleaved thinking" and native tool calling. In our internal evals, tool calling succeeded 100% of the time, and the extended-run score improved to 93.4% (thanks zbww_!) ([#9969](https://github.com/RooCodeInc/Roo-Code/pull/9969), [#10141](https://github.com/RooCodeInc/Roo-Code/pull/10141)).
+
+## Native Tool Protocol Default
+
+Models that support native tool calling now default to using native protocol instead of XML. The XML protocol is still available in provider settings ([#10186](https://github.com/RooCodeInc/Roo-Code/pull/10186)).
 
 ## QOL Improvements
 
@@ -69,6 +73,9 @@ The DeepSeek provider’s `deepseek-reasoner` model now supports “interleaved
 * **Simplified Auto-Approve settings**: Removes separate toggles for retry and todo updates, reducing configuration overhead ([#10062](https://github.com/RooCodeInc/Roo-Code/pull/10062))
 * **Richer error details dialog**: Adds extra context (extension version, provider/model, timestamp, etc.) to the error details dialog to make debugging and reporting issues faster ([#10050](https://github.com/RooCodeInc/Roo-Code/pull/10050))
 * **Fewer read_file failures on large files**: Improves large-file reading by incrementally reading up to a token budget and returning cleaner truncation when needed ([#10052](https://github.com/RooCodeInc/Roo-Code/pull/10052))
+* **Improved File Editing with Gemini Models**: New edit_file tool makes Gemini models more effective at editing files ([#9983](https://github.com/RooCodeInc/Roo-Code/pull/9983))
+* **VS Code LM Native Tools**: Native tool calling now works with VS Code's built-in Copilot models ([#10191](https://github.com/RooCodeInc/Roo-Code/pull/10191))
+* **Smarter Tool Defaults for Gemini and OpenAI**: Gemini and OpenAI models now use better default tools for file editing, improving reliability out of the box. ([#10170](https://github.com/RooCodeInc/Roo-Code/pull/10170))
 
 ## Bug Fixes
 
@@ -120,6 +127,9 @@ The DeepSeek provider’s `deepseek-reasoner` model now supports “interleaved
 * **MCP Tool Names with Bedrock**: Fixes validation errors when using MCP servers with dots or colons in their names (like `awslabs.aws-documentation-mcp-server`) with Amazon Bedrock ([#10152](https://github.com/RooCodeInc/Roo-Code/pull/10152))
 * **Bedrock Task Resumption**: Fixes an error when resuming tasks with Amazon Bedrock when native tools are disabled, where users would encounter `The toolConfig field must be defined` errors ([#10155](https://github.com/RooCodeInc/Roo-Code/pull/10155))
 * **Roo Code Cloud Model Refresh**: Fixes an issue where authentication-required models (like `google/gemini-3-flash`) wouldn't appear immediately after logging into Roo Code Cloud ([#10156](https://github.com/RooCodeInc/Roo-Code/pull/10156))
+* **LiteLLM Tool Protocol Dropdown**: The Native/XML protocol selector now appears correctly for LiteLLM models ([#10187](https://github.com/RooCodeInc/Roo-Code/pull/10187))
+* **Task Resumption**: Tasks no longer break when resuming after changing the Native Tool Calling setting ([#10192](https://github.com/RooCodeInc/Roo-Code/pull/10192))
+* **Bedrock Embedder CloudTrail Fix**: AWS Bedrock users now see Roo Code identified in CloudTrail logs when using Codebase Indexing. (thanks jackrein!) ([#10166](https://github.com/RooCodeInc/Roo-Code/pull/10166))
 
 ## Misc Improvements
 
@@ -142,6 +152,8 @@ The DeepSeek provider’s `deepseek-reasoner` model now supports “interleaved
 * **Improved web-evals run logs**: Makes evaluation runs easier to inspect by improving run logs and formatting ([#10081](https://github.com/RooCodeInc/Roo-Code/pull/10081))
 * **Control public task sharing**: Adds an organization-level setting to disable public task sharing links ([#10105](https://github.com/RooCodeInc/Roo-Code/pull/10105))
 * **Evals UI: clearer tool grouping + duration fixes**: Improves the evals UI by grouping related tools and fixing cases where run duration could be missing or incorrect ([#10133](https://github.com/RooCodeInc/Roo-Code/pull/10133))
+* **Error Monitoring**: Improved tracking of consecutive mistake errors ([#10193](https://github.com/RooCodeInc/Roo-Code/pull/10193))
+* **Better Error Grouping**: Improved error tracking for faster issue resolution. ([#10163](https://github.com/RooCodeInc/Roo-Code/pull/10163))
 
 ## Provider Updates
 

sidebars.ts

@@ -173,6 +173,8 @@ const sidebars: SidebarsConfig = {
           label: '3.36',
           items: [
             { type: 'doc', id: 'update-notes/v3.36', label: '3.36 Combined' },
+            { type: 'doc', id: 'update-notes/v3.36.13', label: '3.36.13' },
+            { type: 'doc', id: 'update-notes/v3.36.12', label: '3.36.12' },
             { type: 'doc', id: 'update-notes/v3.36.11', label: '3.36.11' },
             { type: 'doc', id: 'update-notes/v3.36.10', label: '3.36.10' },
             { type: 'doc', id: 'update-notes/v3.36.9', label: '3.36.9' },