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
description: Fixes Claude Sonnet 4.5 model identifiers for AWS Bedrock and OpenRouter to prevent model ID errors.
3
+
keywords:
4
+
- roo code 3.28.11
5
+
- bug fixes
6
+
- bedrock
7
+
- claude sonnet 4.5
8
+
- openrouter
9
+
image: /img/social-share.jpg
10
+
---
11
+
12
+
# Roo Code 3.28.11 Release Notes (2025-09-29)
13
+
14
+
This patch fixes model identifier issues for Claude Sonnet 4.5 across AWS Bedrock and OpenRouter, so prompts run reliably without ID or selection errors.
15
+
16
+
## Bug Fixes
17
+
18
+
* AWS Bedrock: Use the correct Claude Sonnet 4.5 model ID so prompts run without “model not found” errors (thanks sunhyung!) ([#8372](https://github.com/RooCodeInc/Roo-Code/pull/8372))
19
+
* OpenRouter: Correct Claude Sonnet 4.5 model ID format to align with naming and prevent selection/API mismatches ([#8373](https://github.com/RooCodeInc/Roo-Code/pull/8373))
Copy file name to clipboardExpand all lines: docs/update-notes/v3.28.mdx
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -101,6 +101,7 @@ This gives teams a higher-capacity OpenAI option without extra configuration.[#8
101
101
## Bug Fixes
102
102
103
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
+
***OpenRouter Claude Sonnet 4.5**: Corrected model ID format to align with naming and prevent selection/API mismatches ([#8373](https://github.com/RooCodeInc/Roo-Code/pull/8373))
104
105
***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))
105
106
***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))
106
107
***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))
0 commit comments