docs: add v3.44 release notes #513
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,43 @@ | ||
| --- | ||
| description: This release improves worktree workflows, adds MCP configuration flexibility, and fixes context condensing issues. | ||
| keywords: | ||
| - roo code 3.44.0 | ||
| - new features | ||
| - bug fixes | ||
| image: /img/v3.44.0/v3.44.0.png | ||
| --- | ||
|
|
||
| # Roo Code 3.44.0 Release Notes (2026-01-27) | ||
|
|
||
| This release improves worktree workflows, adds MCP configuration flexibility, and fixes context condensing issues. | ||
|
|
||
| <img src="/img/v3.44.0/v3.44.0.png" alt="Roo Code v3.44.0 Release" width="600" /> | ||
|
|
||
| ## Worktrees | ||
|
|
||
| Worktrees are easier to work with in chat. The Worktree selector is more prominent, creating a worktree takes fewer steps, and the Create Worktree flow is clearer (including a native folder picker), so it’s faster to spin up an isolated branch/workspace and switch between worktrees while you work. ([#10940](https://github.com/RooCodeInc/Roo-Code/pull/10940)) | ||
|
|
||
| > **📚 Documentation**: See [Worktrees](/features/worktrees) for detailed usage. | ||
|
|
||
| ## QOL Improvements | ||
|
|
||
| * Makes subtasks easier to find and navigate by improving parent/child visibility across History and Chat (including clearer “back to parent” navigation), so you can move between related tasks faster. ([#10864](https://github.com/RooCodeInc/Roo-Code/pull/10864)) | ||
| * Lets you auto-approve all tools from a trusted MCP server by using `alwaysAllow: ["*"]`, so you don’t have to list each tool name individually. ([#10948](https://github.com/RooCodeInc/Roo-Code/pull/10948)) | ||
| * Reduces token overhead in prompts by removing a duplicate MCP server/tools section from internal instructions, leaving more room for your conversation context. ([#10895](https://github.com/RooCodeInc/Roo-Code/pull/10895)) | ||
| * Improves Traditional Chinese (zh-TW) UI text for better clarity and consistency. (thanks PeterDaveHello!) ([#10953](https://github.com/RooCodeInc/Roo-Code/pull/10953)) | ||
|
|
||
| ## Bug Fixes | ||
|
|
||
| * Fixes an issue where context condensing could accidentally pull in content that was already condensed earlier, which could reduce the effectiveness of long-conversation summaries. ([#10985](https://github.com/RooCodeInc/Roo-Code/pull/10985)) | ||
| * Fixes an issue where automatic context condensing could silently fail for VS Code LM API users when token counting returned 0 outside active requests, which could lead to unexpected context-limit errors. (thanks srulyt!) ([#10983](https://github.com/RooCodeInc/Roo-Code/pull/10983)) | ||
| * Fixes an issue where Roo didn’t record a successful truncation fallback when condensation failed, which could make Rewind restores unreliable after a condensing error. ([#10984](https://github.com/RooCodeInc/Roo-Code/pull/10984)) | ||
| * Fixes an issue where MCP tools with hyphens in their names could fail to resolve in native tool calling (for example when a provider/model rewrites `-` as `_`). (thanks hori-so!) ([#10775](https://github.com/RooCodeInc/Roo-Code/pull/10775)) | ||
| * Fixes an issue where tool calls could fail validation through AWS Bedrock when `toolUseId` exceeded Bedrock’s 64-character limit, improving reliability for longer tool-heavy sessions. ([#10902](https://github.com/RooCodeInc/Roo-Code/pull/10902)) | ||
| * Fixes an issue where Settings section headers could look transparent while scrolling, restoring an opaque background so the UI stays legible. ([#10951](https://github.com/RooCodeInc/Roo-Code/pull/10951)) | ||
| * Fixes a Fireworks provider type mismatch by removing unsupported model tool fields, keeping provider model metadata consistent and preventing breakage from schema changes. ([#10937](https://github.com/RooCodeInc/Roo-Code/pull/10937)) | ||
| * Fixes an issue where the `new_task` tool could miss creating a checkpoint before handing off, making task state more consistent and recoverable. ([#10982](https://github.com/RooCodeInc/Roo-Code/pull/10982)) | ||
| * Fixes an issue where leftover Power Steering experiment references could display raw translation keys in the UI. ([#10980](https://github.com/RooCodeInc/Roo-Code/pull/10980)) | ||
|
|
||
| ## Provider Updates | ||
|
|
||
| * Adds the latest Fireworks models to the Fireworks provider’s model list. (thanks ThanhNguyxn!) ([#10679](https://github.com/RooCodeInc/Roo-Code/pull/10679)) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,16 @@ | ||
| --- | ||
| description: This patch fixes LiteLLM + Amazon Bedrock proxy tool calling, adjusts Cerebras model defaults, and improves website deployment checks. | ||
| keywords: | ||
| - roo code 3.44.1 | ||
| - provider updates | ||
| - bug fixes | ||
| --- | ||
|
|
||
| # Roo Code 3.44.1 Release Notes (2026-01-27) | ||
|
|
||
| This patch fixes LiteLLM + Amazon Bedrock proxy tool calling, adjusts Cerebras model defaults, and improves website deployment checks. | ||
|
|
||
| ## Provider Updates | ||
|
|
||
| * Fixes an issue where tool-enabled chats could fail when using LiteLLM as a proxy to Amazon Bedrock due to Bedrock tool call ID validation limits. ([#10990](https://github.com/RooCodeInc/Roo-Code/pull/10990)) | ||
| * Sets default sampling parameters for the Cerebras `zai-glm-4.7` model (temperature and top_p) so outputs are more consistent without extra configuration. (thanks sebastiand-cerebras!) ([#10945](https://github.com/RooCodeInc/Roo-Code/pull/10945)) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| --- | ||
| description: This patch re-enables the “Parallel tool calls” experiment and fixes worktree indexing and provider tool-calling issues. | ||
| keywords: | ||
| - roo code 3.44.2 | ||
| - experimental features | ||
| - bug fixes | ||
| - provider updates | ||
| --- | ||
|
|
||
| # Roo Code 3.44.2 Release Notes (2026-01-27) | ||
|
|
||
| This patch re-enables the “Parallel tool calls” experiment and fixes worktree indexing and provider tool-calling issues. | ||
|
|
||
| ## Parallel tool calls (Experimental) | ||
|
|
||
| Re-enables parallel tool calling (with new_task isolation safeguards) so you can use the experimental “Parallel tool calls” setting again without breaking task delegation workflows. ([#11006](https://github.com/RooCodeInc/Roo-Code/pull/11006)) | ||
|
|
||
| ## Bug Fixes | ||
|
|
||
| * Fixes an issue where Roo could fail to index code in worktrees stored inside hidden directories (for example `~/.roo/worktrees/`), which could break search and other codebase features in those worktrees. ([#11009](https://github.com/RooCodeInc/Roo-Code/pull/11009)) | ||
|
|
||
| ## Provider Updates | ||
|
|
||
| * Fixes an issue where local Ollama models could be incorrectly flagged as unavailable due to validation running against an empty router model list. ([#10893](https://github.com/RooCodeInc/Roo-Code/pull/10893)) | ||
| * Fixes an issue where tools could appear twice when using OpenAI Responses API-based providers, reducing duplicate tool output and making results easier to follow. ([#11008](https://github.com/RooCodeInc/Roo-Code/pull/11008)) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| --- | ||
| description: This release improves worktree workflows, adds MCP configuration flexibility, and fixes context condensing and provider issues. | ||
| keywords: | ||
| - roo code 3.44 | ||
| - new features | ||
| - bug fixes | ||
| image: /img/v3.44.0/v3.44.0.png | ||
| --- | ||
|
|
||
| # Roo Code 3.44 Release Notes (2026-01-27) | ||
|
|
||
| This release improves worktree workflows, adds MCP configuration flexibility, and fixes context condensing and provider issues. | ||
|
|
||
| <img src="/img/v3.44.0/v3.44.0.png" alt="Roo Code v3.44 Release" width="600" /> | ||
|
|
||
| ## Worktrees | ||
|
|
||
| Worktrees are easier to work with in chat. The Worktree selector is more prominent, creating a worktree takes fewer steps, and the Create Worktree flow is clearer (including a native folder picker), so it’s faster to spin up an isolated branch/workspace and switch between worktrees while you work. ([#10940](https://github.com/RooCodeInc/Roo-Code/pull/10940)) | ||
|
|
||
| > **📚 Documentation**: See [Worktrees](/features/worktrees) for detailed usage. | ||
|
|
||
| ## Parallel tool calls (Experimental) | ||
|
|
||
| Re-enables parallel tool calling (with new_task isolation safeguards) so you can use the experimental “Parallel tool calls” setting again without breaking task delegation workflows. ([#11006](https://github.com/RooCodeInc/Roo-Code/pull/11006)) | ||
|
|
||
| ## QOL Improvements | ||
|
|
||
| * Makes subtasks easier to find and navigate by improving parent/child visibility across History and Chat (including clearer “back to parent” navigation), so you can move between related tasks faster. ([#10864](https://github.com/RooCodeInc/Roo-Code/pull/10864)) | ||
| * Lets you auto-approve all tools from a trusted MCP server by using `alwaysAllow: ["*"]`, so you don’t have to list each tool name individually. ([#10948](https://github.com/RooCodeInc/Roo-Code/pull/10948)) | ||
| * Reduces token overhead in prompts by removing a duplicate MCP server/tools section from internal instructions, leaving more room for your conversation context. ([#10895](https://github.com/RooCodeInc/Roo-Code/pull/10895)) | ||
| * Improves Traditional Chinese (zh-TW) UI text for better clarity and consistency. (thanks PeterDaveHello!) ([#10953](https://github.com/RooCodeInc/Roo-Code/pull/10953)) | ||
|
|
||
| ## Bug Fixes | ||
|
|
||
| * Fixes an issue where context condensing could accidentally pull in content that was already condensed earlier, which could reduce the effectiveness of long-conversation summaries. ([#10985](https://github.com/RooCodeInc/Roo-Code/pull/10985)) | ||
| * Fixes an issue where automatic context condensing could silently fail for VS Code LM API users when token counting returned 0 outside active requests, which could lead to unexpected context-limit errors. (thanks srulyt!) ([#10983](https://github.com/RooCodeInc/Roo-Code/pull/10983)) | ||
| * Fixes an issue where Roo didn’t record a successful truncation fallback when condensation failed, which could make Rewind restores unreliable after a condensing error. ([#10984](https://github.com/RooCodeInc/Roo-Code/pull/10984)) | ||
| * Fixes an issue where MCP tools with hyphens in their names could fail to resolve in native tool calling (for example when a provider/model rewrites `-` as `_`). (thanks hori-so!) ([#10775](https://github.com/RooCodeInc/Roo-Code/pull/10775)) | ||
| * Fixes an issue where tool calls could fail validation through AWS Bedrock when `toolUseId` exceeded Bedrock’s 64-character limit, improving reliability for longer tool-heavy sessions. ([#10902](https://github.com/RooCodeInc/Roo-Code/pull/10902)) | ||
| * Fixes an issue where Settings section headers could look transparent while scrolling, restoring an opaque background so the UI stays legible. ([#10951](https://github.com/RooCodeInc/Roo-Code/pull/10951)) | ||
| * Fixes a Fireworks provider type mismatch by removing unsupported model tool fields, keeping provider model metadata consistent and preventing breakage from schema changes. ([#10937](https://github.com/RooCodeInc/Roo-Code/pull/10937)) | ||
| * Fixes an issue where the `new_task` tool could miss creating a checkpoint before handing off, making task state more consistent and recoverable. ([#10982](https://github.com/RooCodeInc/Roo-Code/pull/10982)) | ||
| * Fixes an issue where leftover Power Steering experiment references could display raw translation keys in the UI. ([#10980](https://github.com/RooCodeInc/Roo-Code/pull/10980)) | ||
| * Fixes an issue where Roo could fail to index code in worktrees stored inside hidden directories (for example `~/.roo/worktrees/`), which could break search and other codebase features in those worktrees. ([#11009](https://github.com/RooCodeInc/Roo-Code/pull/11009)) | ||
| ## Provider Updates | ||
|
Contributor
There was a problem hiding this comment. In this file, Fix it with Roo Code or mention @roomote and request a fix. |
||
|
|
||
| * Adds the latest Fireworks models to the Fireworks provider’s model list. (thanks ThanhNguyxn!) ([#10679](https://github.com/RooCodeInc/Roo-Code/pull/10679)) | ||
| * Fixes an issue where tool-enabled chats could fail when using LiteLLM as a proxy to Amazon Bedrock due to Bedrock tool call ID validation limits. ([#10990](https://github.com/RooCodeInc/Roo-Code/pull/10990)) | ||
| * Sets default sampling parameters for the Cerebras `zai-glm-4.7` model (temperature and top_p) so outputs are more consistent without extra configuration. (thanks sebastiand-cerebras!) ([#10945](https://github.com/RooCodeInc/Roo-Code/pull/10945)) | ||
| * Fixes an issue where local Ollama models could be incorrectly flagged as unavailable due to validation running against an empty router model list. ([#10893](https://github.com/RooCodeInc/Roo-Code/pull/10893)) | ||
| * Fixes an issue where tools could appear twice when using OpenAI Responses API-based providers, reducing duplicate tool output and making results easier to follow. ([#11008](https://github.com/RooCodeInc/Roo-Code/pull/11008)) | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This note uses an emoji in the blockquote label ("📚"). Some markdown renderers or site style guides avoid emoji in docs; if consistency with the rest of the release notes matters, consider dropping the emoji and keeping the plain label.
Fix it with Roo Code or mention @roomote and request a fix.