Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions docs/update-notes/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,9 @@ image: /img/social-share.jpg
### Version 3.28

* [3.28](/update-notes/v3.28) (Combined)
* [3.28.14](/update-notes/v3.28.14) (2025-09-30)
* [3.28.13](/update-notes/v3.28.13) (2025-09-29)
* [3.28.12](/update-notes/v3.28.12) (2025-09-29)
* [3.28.11](/update-notes/v3.28.11) (2025-09-29)
* [3.28.10](/update-notes/v3.28.10) (2025-09-29)
* [3.28.9](/update-notes/v3.28.9) (2025-09-26)
Expand Down
21 changes: 21 additions & 0 deletions docs/update-notes/v3.28.12.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
---
description: Fixes Anthropic Sonnet 4.5 model ID and adds Bedrock 1M context checkbox.
keywords:
- roo code 3.28.12
- anthropic sonnet 4.5
- bedrock 1m context
- bug fixes
image: /img/social-share.jpg
---

# Roo Code 3.28.12 Release Notes (2025-09-29)

This release fixes the Anthropic Sonnet 4.5 model ID and adds Bedrock 1M context checkbox support.

## Bug Fixes

* **Anthropic Sonnet 4.5 Model ID**: Corrects the model ID to the official `claude-sonnet-4-5`, resolving API errors when using Claude Sonnet 4.5 ([#8384](https://github.com/RooCodeInc/Roo-Code/pull/8384))

## QOL Improvements

* **Bedrock 1M Context Checkbox**: Adds checkbox to enable 1M context window support for Claude Sonnet 4 and 4.5 on Bedrock, providing more flexibility for large-scale projects ([#8384](https://github.com/RooCodeInc/Roo-Code/pull/8384))
18 changes: 18 additions & 0 deletions docs/update-notes/v3.28.13.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
---
description: Fixes Vertex AI Sonnet 4.5 configuration and removes AWS Bedrock topP to improve reliability.
keywords:
- roo code 3.28.13
- new features
- bug fixes
image: /img/social-share.jpg
---

# Roo Code 3.28.13 Release Notes (2025-09-29)

This patch improves provider reliability: Vertex AI Sonnet 4.5 now works with the correct model ID and AWS Bedrock requests avoid conflicts by removing topP.


## Bug Fixes

* Vertex AI: Fix Sonnet 4.5 model configuration so requests no longer 404; sets the correct default ID and enables computer‑use via LiteLLM (thanks nickcatal!) ([#8391](https://github.com/RooCodeInc/Roo-Code/pull/8391))
* AWS Bedrock: Remove topP parameter to avoid conflicts with extended thinking, improving reliability for streaming and non‑streaming responses (thanks ronyblum!) ([#8388](https://github.com/RooCodeInc/Roo-Code/pull/8388))
27 changes: 27 additions & 0 deletions docs/update-notes/v3.28.14.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
---
description: Adds GLM-4.6 support for the z.ai provider with a 200k context window and availability across international and mainland APIs.
keywords:
- roo code 3.28.14
- new features
- bug fixes
image: /img/v3.28.14/v3.28.14.png
---

# Roo Code 3.28.14 Release Notes (2025-09-30)

This patch adds GLM-4.6 support for the z.ai provider, enabling a 200k context window and availability across both international and mainland APIs.

<img src="/img/v3.28.14/v3.28.14.png" alt="Roo Code v3.28.14 Release" width="600" />

## Provider Updates

### GLM‑4.6 on Z.ai

We’ve added the GLM‑4.6 model to the Z.ai provider (thanks dmarkey!) ([#8408](https://github.com/RooCodeInc/Roo-Code/pull/8408)). What you get:

- 200k (204,800) token context window for longer files and multi‑turn conversations
- Better real‑world coding performance, including cleaner front‑end output
- Improved reasoning with tool‑use support for steadier multi‑step tasks
- Stronger agent behavior for search/tool workflows

To use it, select GLM‑4.6 under the Z.ai provider in Settings.
6 changes: 6 additions & 0 deletions docs/update-notes/v3.28.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,7 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
* **Welcome screen Roo provider experiment**: Surfaces the Roo provider on the welcome screen (localized, with click telemetry) to speed up setup. ([#8317](https://github.com/RooCodeInc/Roo-Code/pull/8317))
* **Cleaner prompts (no “thinking” tags)**: Removes `<thinking>` tags for cleaner output, fewer tokens, and better model compatibility; preserves the plain‑language rule to confirm tool success. ([#8319](https://github.com/RooCodeInc/Roo-Code/pull/8319))
* **Simpler Requesty model refresh**: Removes an unnecessary warning when refreshing the Requesty models list so you can fetch new policies without leaving the screen. ([#7710](https://github.com/RooCodeInc/Roo-Code/pull/7710))
* **Bedrock 1M Context Checkbox**: Adds checkbox to enable 1M context window support for Claude Sonnet 4 and 4.5 on Bedrock, providing more flexibility for large-scale projects ([#8384](https://github.com/RooCodeInc/Roo-Code/pull/8384))

## Bug Fixes

Expand Down Expand Up @@ -133,6 +134,10 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8


* **Tool‑use guidance clarity**: Clarifies the retry suggestion so the model selects the correct file‑reading step during apply‑diff retries, reducing failed file edits. ([#8315](https://github.com/RooCodeInc/Roo-Code/pull/8315))
* **Anthropic Sonnet 4.5 Model ID**: Corrects the model ID to the official `claude-sonnet-4-5`, resolving API errors when using Claude Sonnet 4.5 ([#8384](https://github.com/RooCodeInc/Roo-Code/pull/8384))

* **AWS Bedrock**: Removed `topP` parameter to avoid conflicts with extended thinking, improving reliability for streaming and non‑streaming responses (thanks ronyblum!) ([#8388](https://github.com/RooCodeInc/Roo-Code/pull/8388))
* **Vertex AI**: Fixed Sonnet 4.5 model configuration to prevent 404s and align with the correct default model ID (thanks nickcatal!) ([#8391](https://github.com/RooCodeInc/Roo-Code/pull/8391))

## Provider Updates

Expand All @@ -146,6 +151,7 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
* **SambaNova models**: Added DeepSeek-V3.1 and GPT-OSS 120B to the SambaNova provider (thanks snova-jorgep!) ([#8186](https://github.com/RooCodeInc/Roo-Code/pull/8186))

* **Supernova 1M context**: Upgrades the default Supernova to roo/code-supernova-1-million (1,000,000‑token context). Existing settings auto‑migrate; expect fewer truncations on long tasks. ([#8330](https://github.com/RooCodeInc/Roo-Code/pull/8330))
* **Z.ai GLM‑4.6**: Adds GLM‑4.6 model support with a 200k (204,800) context window and availability across both international and mainland API lines (thanks dmarkey!) ([#8408](https://github.com/RooCodeInc/Roo-Code/pull/8408))

## Misc Improvements

Expand Down
3 changes: 3 additions & 0 deletions sidebars.ts
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,9 @@ const sidebars: SidebarsConfig = {
label: '3.28',
items: [
{ type: 'doc', id: 'update-notes/v3.28', label: '3.28 Combined' },
{ type: 'doc', id: 'update-notes/v3.28.14', label: '3.28.14' },
{ type: 'doc', id: 'update-notes/v3.28.13', label: '3.28.13' },
{ type: 'doc', id: 'update-notes/v3.28.12', label: '3.28.12' },
{ type: 'doc', id: 'update-notes/v3.28.11', label: '3.28.11' },
{ type: 'doc', id: 'update-notes/v3.28.10', label: '3.28.10' },
{ type: 'doc', id: 'update-notes/v3.28.9', label: '3.28.9' },
Expand Down
Binary file added static/img/v3.28.14/v3.28.14.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.