Skip to content

Commit 736ddd3

Browse files
hannesrudolphhannesrudolph
authored
docs: v3.30 release notes (combined + v3.30.0) (#401)
1 parent b97f290 commit 736ddd3

File tree

5 files changed

+107
-0
lines changed

5 files changed

+107
-0
lines changed

‎docs/update-notes/index.md‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,13 @@ image: /img/social-share.jpg
1717

1818
---
1919

20+
### Version 3.30
21+
22+
* [3.30](/update-notes/v3.30) (2025-11-03)
23+
* [3.30.0](/update-notes/v3.30.0) (2025-11-03)
24+
25+
---
26+
2027
### Version 3.29
2128

2229
* [3.29](/update-notes/v3.29) (Combined)

‎docs/update-notes/v3.30.0.mdx‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
---
2+
description: Roo Code 3.30.0 adds OpenRouter embeddings, reasoning handling improvements, and stability/UI fixes.
3+
keywords:
4+
- roo code 3.30.0
5+
- new features
6+
- bug fixes
7+
image: /img/v3.30.0/v3.30.0.png
8+
---
9+
10+
# Roo Code 3.30.0 Release Notes (2025-11-03)
11+
12+
This patch introduces OpenRouter embeddings, improves reasoning handling, and delivers stability and UI fixes.
13+
14+
<img src="/img/v3.30.0/v3.30.0.png" alt="Roo Code v3.30.0 Release" width="600" />
15+
16+
## OpenRouter Embeddings
17+
18+
We've added OpenRouter as an embedding provider for codebase indexing in Roo Code (thanks dmarkey!) ([#8973](https://github.com/RooCodeInc/Roo-Code/pull/8973)).
19+
20+
OpenRouter currently supports 7 embedding models, including the top‑ranking Qwen3 Embedding.
21+
22+
> **📚 Documentation**: See [Codebase Indexing](/features/codebase-indexing) and [OpenRouter Provider](/providers/openrouter).
23+
24+
## QOL Improvements
25+
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+
28+
## Bug Fixes
29+
30+
* Prevent message loss during queue drain race conditions to preserve message order and reliable chats ([#8955](https://github.com/RooCodeInc/Roo-Code/pull/8955))
31+
* Requesty OAuth: auto-create a stable "Requesty" profile with a default model so sign-in completes reliably (thanks Thibault00!) ([#8699](https://github.com/RooCodeInc/Roo-Code/pull/8699))
32+
* Cancel during streaming no longer causes flicker; you can resume in place, input stays enabled, and the spinner stops deterministically ([#8986](https://github.com/RooCodeInc/Roo-Code/pull/8986))
33+
* Remove newline-only reasoning blocks from OpenAI-compatible responses for cleaner output and logs ([#8990](https://github.com/RooCodeInc/Roo-Code/pull/8990))
34+
* "Disable Terminal Shell Integration" now links to the correct documentation section ([#8997](https://github.com/RooCodeInc/Roo-Code/pull/8997))
35+
36+
## Misc Improvements
37+
38+
* Add preserveReasoning flag to optionally include reasoning in API history so later turns can leverage prior reasoning; off by default and model‑gated ([#8934](https://github.com/RooCodeInc/Roo-Code/pull/8934))
39+
40+
## Provider Updates
41+
42+
* Chutes: dynamic/router provider so new models appear automatically; safer error logging and temperature applied only when supported ([#8980](https://github.com/RooCodeInc/Roo-Code/pull/8980))
43+
* OpenAI‑compatible providers: handle `<think>` reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
44+
* GLM 4.6: capture reasoning content in base OpenAI‑compatible provider during streaming ([#8976](https://github.com/RooCodeInc/Roo-Code/pull/8976))
45+
* 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))
46+
* 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))

‎docs/update-notes/v3.30.mdx‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
---
2+
description: Adds OpenRouter embeddings, improves reasoning handling, and delivers stability and UI fixes.
3+
keywords:
4+
- roo code 3.30
5+
- new features
6+
- bug fixes
7+
image: /img/v3.30.0/v3.30.0.png
8+
---
9+
10+
# Roo Code 3.30 Release Notes (2025-11-03)
11+
12+
This release adds OpenRouter embeddings, enhances reasoning handling, and delivers stability and UI improvements.
13+
14+
<img src="/img/v3.30.0/v3.30.0.png" alt="Roo Code v3.30 Release" width="600" />
15+
16+
## OpenRouter Embeddings
17+
18+
We've added OpenRouter as an embedding provider for codebase indexing in Roo Code (thanks dmarkey!) ([#8973](https://github.com/RooCodeInc/Roo-Code/pull/8973)).
19+
20+
OpenRouter currently supports 7 embedding models, including the top‑ranking Qwen3 Embedding.
21+
22+
> **📚 Documentation**: See [Codebase Indexing](/features/codebase-indexing) and [OpenRouter Provider](/providers/openrouter).
23+
24+
## QOL Improvements
25+
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+
28+
## Bug Fixes
29+
30+
* Prevent message loss during queue drain race conditions to preserve message order and reliable chats ([#8955](https://github.com/RooCodeInc/Roo-Code/pull/8955))
31+
* Requesty OAuth: auto-create a stable "Requesty" profile with a default model so sign-in completes reliably (thanks Thibault00!) ([#8699](https://github.com/RooCodeInc/Roo-Code/pull/8699))
32+
* Cancel during streaming no longer causes flicker; you can resume in place, input stays enabled, and the spinner stops deterministically ([#8986](https://github.com/RooCodeInc/Roo-Code/pull/8986))
33+
* Remove newline-only reasoning blocks from OpenAI-compatible responses for cleaner output and logs ([#8990](https://github.com/RooCodeInc/Roo-Code/pull/8990))
34+
* "Disable Terminal Shell Integration" now links to the correct documentation section ([#8997](https://github.com/RooCodeInc/Roo-Code/pull/8997))
35+
36+
## Misc Improvements
37+
38+
* Add preserveReasoning flag to optionally include reasoning in API history so later turns can leverage prior reasoning; off by default and model‑gated ([#8934](https://github.com/RooCodeInc/Roo-Code/pull/8934))
39+
40+
## Provider Updates
41+
42+
* Chutes: dynamic/router provider so new models appear automatically; safer error logging and temperature applied only when supported ([#8980](https://github.com/RooCodeInc/Roo-Code/pull/8980))
43+
* OpenAI‑compatible providers: handle `<think>` reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
44+
* GLM 4.6: capture reasoning content in base OpenAI‑compatible provider during streaming ([#8976](https://github.com/RooCodeInc/Roo-Code/pull/8976))
45+
* 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))
46+
* 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))

‎sidebars.ts‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -218,6 +218,14 @@ const sidebars: SidebarsConfig = {
218218
label: 'Update Notes',
219219
items: [
220220
'update-notes/index',
221+
{
222+
type: 'category',
223+
label: '3.30',
224+
items: [
225+
{ type: 'doc', id: 'update-notes/v3.30', label: '3.30 Combined' },
226+
{ type: 'doc', id: 'update-notes/v3.30.0', label: '3.30.0' },
227+
],
228+
},
221229
{
222230
type: 'category',
223231
label: '3.29',

‎static/img/v3.30.0/v3.30.0.png‎

1.91 MB
Loading

0 commit comments

Comments
 (0)