You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
fix: update Docker run command for Qdrant setup with optimizations (#371)
* fix: update Docker run command for Qdrant setup with optimizations
* feat: add release notes for version 3.28.10 with Claude 4.5 support and bug fixes
* fix: correct model identifier for Claude Sonnet 4.5 on AWS Bedrock
We've added support for Anthropic's latest Claude 4.5 Sonnet model across all Claude-supporting providers ([#8368](https://github.com/RooCodeInc/Roo-Code/pull/8368)).
20
+
21
+
According to [Anthropic's announcement](https://www.anthropic.com/news/claude-sonnet-4-5), Claude 4.5 Sonnet is:
22
+
23
+
- State-of-the-art on SWE-bench Verified, maintaining focus for more than 30 hours on complex, multi-step tasks
24
+
- Showing a significant leap forward on computer use with 61.4% on OSWorld benchmark (up from 42.2% just four months ago)
25
+
- Delivering substantial gains in reasoning, math, and domain-specific knowledge across finance, law, medicine, and STEM
26
+
27
+
<imgsrc="/img/v3.28.10/v3.28.10-1.png"alt="Claude 4.5 Sonnet model selection"width="600" />
28
+
29
+
The model is now available in the model selection dropdown for all supported providers.
30
+
31
+
## Bug Fixes
32
+
33
+
***AWS Bedrock Claude Sonnet 4.5**: Corrected model identifier for Claude Sonnet 4.5 on AWS Bedrock (thanks sunhyung!) ([#8371](https://github.com/RooCodeInc/Roo-Code/pull/8371))
34
+
***GPT-5 LiteLLM Compatibility**: Fixed GPT-5 models failing with LiteLLM provider by using correct `max_completion_tokens` parameter (thanks lx1054331851!) ([#6980](https://github.com/RooCodeInc/Roo-Code/pull/6980))
35
+
36
+
## QOL Improvements
37
+
38
+
***Chat Icon Sizing**: Chat interface icons now maintain consistent size in limited space ([#8343](https://github.com/RooCodeInc/Roo-Code/pull/8343))
39
+
40
+
## Misc Improvements
41
+
42
+
***Telemetry Tracking**: Enhanced analytics to track when users change telemetry settings ([#8339](https://github.com/RooCodeInc/Roo-Code/pull/8339))
43
+
***Website Testimonials**: Updated website with enhanced testimonials section ([#8360](https://github.com/RooCodeInc/Roo-Code/pull/8360))
Copy file name to clipboardExpand all lines: docs/update-notes/v3.28.mdx
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -65,6 +65,7 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
65
65
## QOL Improvements
66
66
67
67
***Cloud Account Management**: Added account switcher and "Create Team Account" option for logged-in users, making it easier to manage multiple accounts ([#8291](https://github.com/RooCodeInc/Roo-Code/pull/8291))
68
+
***Chat Icon Sizing**: Chat interface icons now maintain consistent size in limited space ([#8343](https://github.com/RooCodeInc/Roo-Code/pull/8343))
68
69
***Social Media Sharing**: Improved OpenGraph images for better preview cards when sharing Roo Code links on Slack, Twitter, and Facebook ([#8285](https://github.com/RooCodeInc/Roo-Code/pull/8285))
69
70
***Auto-approve keyboard shortcut**: Toggle approvals with Cmd/Ctrl+Alt+A from anywhere in the editor so you can stay in the flow while reviewing changes (via [#8214](https://github.com/RooCodeInc/Roo-Code/pull/8214))
70
71
***Click-to-Edit Chat Messages**: Click directly on any message text to edit it, with ESC to cancel and improved padding consistency ([#7790](https://github.com/RooCodeInc/Roo-Code/pull/7790))
@@ -99,6 +100,8 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
99
100
100
101
## Bug Fixes
101
102
103
+
***AWS Bedrock Claude Sonnet 4.5**: Corrected model identifier for Claude Sonnet 4.5 on AWS Bedrock (thanks sunhyung!) ([#8371](https://github.com/RooCodeInc/Roo-Code/pull/8371))
104
+
***GPT-5 LiteLLM Compatibility**: Fixed GPT-5 models failing with LiteLLM provider by using correct `max_completion_tokens` parameter (thanks lx1054331851!) ([#6980](https://github.com/RooCodeInc/Roo-Code/pull/6980))
102
105
***Fixed "No tool used" Errors**: Resolved the situation where LLMs would sometimes not make tool calls in their response which improves Roo's overall flow. ([#8292](https://github.com/RooCodeInc/Roo-Code/pull/8292))
103
106
***Context Condensing**: Fixed an issue where the initial task request was being lost during context condensing, causing Roo to try to re-answer the original task ask when resuming after condensing ([#8298](https://github.com/RooCodeInc/Roo-Code/pull/8298))
104
107
***Roo provider stays signed in**: Roo provider tokens refresh automatically and the local evals app binds to port 3446 for predictable scripts (via [#8224](https://github.com/RooCodeInc/Roo-Code/pull/8224))
@@ -132,6 +135,7 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
132
135
133
136
## Provider Updates
134
137
138
+
***Claude 4.5 Sonnet**: Added support for Anthropic's latest Claude 4.5 Sonnet model across all providers (Anthropic, AWS Bedrock, Claude Code, Google Vertex AI, and OpenRouter) with 1M context window support ([#8368](https://github.com/RooCodeInc/Roo-Code/pull/8368))
135
139
***New Free Models**: Added two more free models to the Roo provider - xai/grok-4-fast and deepseek/deepseek-chat-v3.1 ([#8304](https://github.com/RooCodeInc/Roo-Code/pull/8304))
136
140
***Vertex AI Models**: Added support for 6 new models including DeepSeek-V3, GPT-OSS, and Qwen models, plus the us-south1 region (thanks ssweens!) ([#7727](https://github.com/RooCodeInc/Roo-Code/pull/7727))
137
141
***DeepSeek Pricing**: Updated to new unified rates effective September 5, 2025 - $0.56/M input tokens, $1.68/M output tokens (thanks NaccOll!) ([#7687](https://github.com/RooCodeInc/Roo-Code/pull/7687))
@@ -145,6 +149,9 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
145
149
## Misc Improvements
146
150
147
151
***Website improvements**: New pricing page, clearer homepage messaging, and tighter navigation/visuals (including mobile). No changes to the extension UX. ([#8303](https://github.com/RooCodeInc/Roo-Code/pull/8303), [#8326](https://github.com/RooCodeInc/Roo-Code/pull/8326))
152
+
***Telemetry Tracking**: Enhanced analytics to track when users change telemetry settings ([#8339](https://github.com/RooCodeInc/Roo-Code/pull/8339))
153
+
***Website Testimonials**: Updated website with enhanced testimonials section ([#8360](https://github.com/RooCodeInc/Roo-Code/pull/8360))
***Internal cleanup**: Removes the deprecated pr-reviewer mode. No changes to the extension UX. ([#8222](https://github.com/RooCodeInc/Roo-Code/pull/8222))
149
156
***Infrastructure**: Set port 3446 for web-evals service in production mode ([#8288](https://github.com/RooCodeInc/Roo-Code/pull/8288))
150
157
***Cloud Task Button**: Added a new button for opening tasks in Roo Code Cloud with QR codes and shareable URLs ([#7572](https://github.com/RooCodeInc/Roo-Code/pull/7572))
0 commit comments