diff --git a/docs/update-notes/index.md b/docs/update-notes/index.md
index ab7c3a4a..552f2e2b 100644
--- a/docs/update-notes/index.md
+++ b/docs/update-notes/index.md
@@ -21,6 +21,15 @@ If you want to live on the edge and try things out before it's released, we have
---
+### Version 3.44
+
+* [3.44](/update-notes/v3.44) (Combined)
+* [3.44.2](/update-notes/v3.44.2) (2026-01-27)
+* [3.44.1](/update-notes/v3.44.1) (2026-01-27)
+* [3.44.0](/update-notes/v3.44.0) (2026-01-27)
+
+---
+
### Version 3.43
* [3.43.0](/update-notes/v3.43.0) (2026-01-23)
diff --git a/docs/update-notes/v3.44.0.mdx b/docs/update-notes/v3.44.0.mdx
new file mode 100644
index 00000000..e2cc2a60
--- /dev/null
+++ b/docs/update-notes/v3.44.0.mdx
@@ -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.
+
+
+
+## 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))
diff --git a/docs/update-notes/v3.44.1.mdx b/docs/update-notes/v3.44.1.mdx
new file mode 100644
index 00000000..f58037e3
--- /dev/null
+++ b/docs/update-notes/v3.44.1.mdx
@@ -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))
diff --git a/docs/update-notes/v3.44.2.mdx b/docs/update-notes/v3.44.2.mdx
new file mode 100644
index 00000000..3691a69d
--- /dev/null
+++ b/docs/update-notes/v3.44.2.mdx
@@ -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))
diff --git a/docs/update-notes/v3.44.mdx b/docs/update-notes/v3.44.mdx
new file mode 100644
index 00000000..45a8321f
--- /dev/null
+++ b/docs/update-notes/v3.44.mdx
@@ -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.
+
+
+
+## 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
+
+* 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))
diff --git a/sidebars.ts b/sidebars.ts
index b67824ee..6d07e111 100644
--- a/sidebars.ts
+++ b/sidebars.ts
@@ -172,6 +172,16 @@ const sidebars: SidebarsConfig = {
label: 'Extension Release Notes',
items: [
'update-notes/index',
+ {
+ type: 'category',
+ label: '3.44',
+ items: [
+ { type: 'doc', id: 'update-notes/v3.44', label: '3.44 Combined' },
+ { type: 'doc', id: 'update-notes/v3.44.2', label: '3.44.2' },
+ { type: 'doc', id: 'update-notes/v3.44.1', label: '3.44.1' },
+ { type: 'doc', id: 'update-notes/v3.44.0', label: '3.44.0' },
+ ],
+ },
{
type: 'category',
label: '3.43',
diff --git a/static/img/v3.44.0/v3.44.0.png b/static/img/v3.44.0/v3.44.0.png
new file mode 100644
index 00000000..ca92998b
Binary files /dev/null and b/static/img/v3.44.0/v3.44.0.png differ