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
* File path tooltips show full paths on hover across reads/edits, directory listings, and search, reducing confusion in narrow layouts (thanks da2ce7!) ([#9030](https://github.com/RooCodeInc/Roo-Code/pull/9030))
24
+
* Optional pre-push full test run via RUN_TESTS_ON_PUSH=true in .env.local; default behavior keeps pushes fast (tests skipped) ([#9055](https://github.com/RooCodeInc/Roo-Code/pull/9055))
25
+
26
+
## Bug Fixes
27
+
28
+
* Eliminates brief UI flicker when cancelling a task; the task view remains stable ([#9037](https://github.com/RooCodeInc/Roo-Code/pull/9037))
29
+
* Pinned models remain visible at the top while scrolling long lists for quicker access (thanks XiaoYingYo!) ([#8813](https://github.com/RooCodeInc/Roo-Code/pull/8813))
30
+
* Checkpoints always commit to Roo’s shadow repository even when GIT_DIR is set in Dev Containers, preventing leaks to external repos (thanks heyseth, nonsleepr!) ([#8811](https://github.com/RooCodeInc/Roo-Code/pull/8811))
31
+
* Restores correct 32K maxTokens for Claude Opus 4.1 to avoid premature truncation on long generations (thanks kaveh-deriv!) ([#9046](https://github.com/RooCodeInc/Roo-Code/pull/9046))
32
+
* Fixes dynamic provider model validation so switching providers uses a valid default model and avoids TypeErrors (thanks NotADev137!) ([#9054](https://github.com/RooCodeInc/Roo-Code/pull/9054))
33
+
* AWS Bedrock requests now report full user agent details in CloudTrail for better auditing and troubleshooting (thanks ajjuaire!) ([#9043](https://github.com/RooCodeInc/Roo-Code/pull/9043))
34
+
35
+
## Provider Updates
36
+
37
+
* Sets Claude Sonnet 4.5 as the default where available across Anthropic, Bedrock, OpenRouter, Claude Code, and Unbound ([#8922](https://github.com/RooCodeInc/Roo-Code/pull/8922))
38
+
* Updates Cerebras zai‑glm‑4.6 limits to 40,960 output tokens with a 131,072‑token context window; reflects faster response rates (~1,000 tokens/s) (thanks sebastiand-cerebras!) ([#9024](https://github.com/RooCodeInc/Roo-Code/pull/9024))
39
+
* Adds Qwen3-Embedding-0.6B (1024‑dim) and Qwen3-Embedding-4B (2560‑dim) to OpenRouter for code indexing (thanks dmarkey!) ([#9060](https://github.com/RooCodeInc/Roo-Code/pull/9060))
Copy file name to clipboardExpand all lines: docs/update-notes/v3.30.mdx
+14-3Lines changed: 14 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,5 @@
1
1
---
2
-
description: Adds OpenRouter embeddings, improves reasoning handling, and delivers stability and UI fixes.
2
+
description: Adds OpenRouter embeddings, Bedrock Global Inference, provider defaults/limits updates, and stability/UI fixes.
3
3
keywords:
4
4
- roo code 3.30
5
5
- new features
@@ -9,7 +9,7 @@ image: /img/v3.30.0/v3.30.0.png
9
9
10
10
# Roo Code 3.30 Release Notes (2025-11-03)
11
11
12
-
This release adds OpenRouter embeddings, enhances reasoning handling, and delivers stability and UI improvements.
12
+
This release adds OpenRouter embeddings and Bedrock Global Inference, updates provider defaults and limits, and delivers stability and UI improvements.
@@ -24,6 +24,8 @@ OpenRouter currently supports 7 embedding models, including the top‑ranking Qw
24
24
## QOL Improvements
25
25
26
26
* Terminal settings cleanup with Inline as the default terminal and clearer options; shell integration default is disabled to reduce environment conflicts ([#8342](https://github.com/RooCodeInc/Roo-Code/pull/8342))
27
+
* File path tooltips show full paths on hover across reads/edits, directory listings, and search, reducing confusion in narrow layouts (thanks da2ce7!) ([#9030](https://github.com/RooCodeInc/Roo-Code/pull/9030))
28
+
* Optional pre-push full test run via RUN_TESTS_ON_PUSH=true in .env.local; default behavior keeps pushes fast (tests skipped) ([#9055](https://github.com/RooCodeInc/Roo-Code/pull/9055))
27
29
28
30
## Bug Fixes
29
31
@@ -34,6 +36,12 @@ OpenRouter currently supports 7 embedding models, including the top‑ranking Qw
34
36
* "Disable Terminal Shell Integration" now links to the correct documentation section ([#8997](https://github.com/RooCodeInc/Roo-Code/pull/8997))
35
37
* Correct OpenRouter Mistral embedding dimension to 1536 to prevent vector size errors; existing Qdrant collections are recreated with the correct size for consistent similarity search ([#9028](https://github.com/RooCodeInc/Roo-Code/pull/9028))
36
38
* Revert the recent cancel/resume change that caused UI flicker and unreliable resumption, restoring the previous stable behavior ([#9032](https://github.com/RooCodeInc/Roo-Code/pull/9032))
39
+
* Eliminate UI flicker during task cancellation; the task view remains stable ([#9037](https://github.com/RooCodeInc/Roo-Code/pull/9037))
40
+
* Keep pinned models fixed at the top of long lists for faster access (thanks XiaoYingYo!) ([#8813](https://github.com/RooCodeInc/Roo-Code/pull/8813))
41
+
* Ensure Checkpoints commit to Roo’s shadow repository even when GIT_DIR is set in Dev Containers (thanks nonsleepr!) ([#8811](https://github.com/RooCodeInc/Roo-Code/pull/8811))
42
+
* Restore correct 32K maxTokens for Claude Opus 4.1 to avoid premature truncation (thanks kaveh-deriv!) ([#9046](https://github.com/RooCodeInc/Roo-Code/pull/9046))
43
+
* Fix dynamic provider model validation so provider switches use a valid default model without TypeErrors (thanks NotADev137!) ([#9054](https://github.com/RooCodeInc/Roo-Code/pull/9054))
44
+
* Include full user agent details in AWS Bedrock requests for better auditing and troubleshooting (thanks ajjuaire!) ([#9043](https://github.com/RooCodeInc/Roo-Code/pull/9043))
37
45
38
46
## Misc Improvements
39
47
@@ -45,4 +53,7 @@ OpenRouter currently supports 7 embedding models, including the top‑ranking Qw
45
53
* OpenAI‑compatible providers: handle `<think>` reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
46
54
* GLM 4.6: capture reasoning content in base OpenAI‑compatible provider during streaming ([#8976](https://github.com/RooCodeInc/Roo-Code/pull/8976))
47
55
* Fireworks: add GLM‑4.6 to the model dropdown for stronger coding performance and longer context (thanks mmealman!) ([#8754](https://github.com/RooCodeInc/Roo-Code/pull/8754))
48
-
* Fireworks: add MiniMax M2 with 204.8K context and 4K output tokens; correct pricing metadata (thanks dmarkey!) ([#8962](https://github.com/RooCodeInc/Roo-Code/pull/8962))
56
+
* Fireworks: add MiniMax M2 with 204.8K context and 4K output tokens; correct pricing metadata (thanks dmarkey!) ([#8962](https://github.com/RooCodeInc/Roo-Code/pull/8962))
57
+
* Set Claude Sonnet 4.5 as the default where available across Anthropic, Bedrock, OpenRouter, Claude Code, and Unbound ([#8922](https://github.com/RooCodeInc/Roo-Code/pull/8922))
58
+
* Cerebras zai‑glm‑4.6: 40,960 max output tokens and a 131,072‑token context window; faster responses (~1,000 tok/s) (thanks sebastiand-cerebras!) ([#9024](https://github.com/RooCodeInc/Roo-Code/pull/9024))
59
+
* OpenRouter: add Qwen3‑Embedding‑0.6B (1024‑dim) and 4B (2560‑dim) for code indexing (thanks dmarkey!) ([#9060](https://github.com/RooCodeInc/Roo-Code/pull/9060))
0 commit comments