Skip to content

Commit 6ab9441

Browse files
docs: add release notes for v3.36.3 and v3.36.4 (#444)
1 parent cf9998f commit 6ab9441

File tree

6 files changed

+189
-0
lines changed

6 files changed

+189
-0
lines changed

docs/update-notes/index.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,8 @@ image: /img/social-share.jpg
1919

2020
### Version 3.36
2121

22+
* [3.36.4](/update-notes/v3.36.4) (2025-12-10)
23+
* [3.36.3](/update-notes/v3.36.3) (2025-12-10)
2224
* [3.36.2](/update-notes/v3.36.2) (2025-12-05)
2325
* [3.36.1](/update-notes/v3.36.1) (2025-12-04)
2426
* [3.36.0](/update-notes/v3.36.0) (2025-12-04)

docs/update-notes/v3.36.3.mdx

Lines changed: 67 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,67 @@
1+
---
2+
description: Browser screenshots, xhigh reasoning effort, native tools default for OpenRouter, provider updates, and fixes
3+
keywords:
4+
- roo code 3.36.3
5+
- browser screenshots
6+
- openrouter native tools
7+
- deepseek v3.2
8+
image: /img/v3.36.3/v3.36.3.png
9+
---
10+
11+
# Roo Code 3.36.3 Release Notes (2025-12-10)
12+
13+
This release adds browser screenshot saving, xhigh reasoning effort support, native tools default for OpenRouter, plus provider updates and bug fixes.
14+
15+
<img src="/img/v3.36.3/v3.36.3.png" alt="Roo Code v3.36.3 Release" width="600" />
16+
17+
## Browser Screenshot Saving
18+
19+
The browser tool now supports saving screenshots to a specified file path with a new `screenshot` action, enabling you to capture visual state during browser automation tasks. ([#9963](https://github.com/RooCodeInc/Roo-Code/pull/9963))
20+
21+
## Extra-High Reasoning Effort
22+
23+
Users of the gpt-5.1-codex-max model with the OpenAI provider can now select "Extra High" as a reasoning effort level, enabling maximum reasoning capability for complex tasks (thanks andrewginns!) ([#9900](https://github.com/RooCodeInc/Roo-Code/pull/9900))
24+
25+
## OpenRouter Native Tools Default
26+
27+
OpenRouter models that support native tools now automatically use native tool calling by default, improving tool calling reliability without manual configuration. ([#9878](https://github.com/RooCodeInc/Roo-Code/pull/9878))
28+
29+
## QOL Improvements
30+
31+
* **Unified Context-Management UX**: Real-time feedback for context operations with truncation notifications and condensation summaries ([#9795](https://github.com/RooCodeInc/Roo-Code/pull/9795))
32+
* **Better OpenAI Error Messages**: Enhanced error handler extracts detailed information from API errors for easier troubleshooting ([#9639](https://github.com/RooCodeInc/Roo-Code/pull/9639))
33+
* **Token Counting Optimization**: Removed separate API calls for token counting, improving performance ([#9884](https://github.com/RooCodeInc/Roo-Code/pull/9884))
34+
* **Tools Decoupled from System Prompt**: Tool-specific instructions are now self-contained in tool descriptions ([#9784](https://github.com/RooCodeInc/Roo-Code/pull/9784))
35+
36+
## Bug Fixes
37+
38+
* **Tool Protocol Selector**: Always show tool protocol selector for OpenAI-compatible providers (thanks bozoweed!) ([#9966](https://github.com/RooCodeInc/Roo-Code/pull/9966))
39+
* **apply_diff Filtering**: Properly exclude apply_diff from native tools when diff is disabled (thanks denis-kudelin!) ([#9920](https://github.com/RooCodeInc/Roo-Code/pull/9920))
40+
* **API Timeout Handling**: Fixed disabled API timeout (set to 0) causing immediate request failures (thanks dcbartlett!) ([#9960](https://github.com/RooCodeInc/Roo-Code/pull/9960))
41+
* **Reasoning Effort Dropdown**: Respect explicit supportsReasoningEffort array values and fix disable handling ([#9970](https://github.com/RooCodeInc/Roo-Code/pull/9970), [#9930](https://github.com/RooCodeInc/Roo-Code/pull/9930))
42+
* **Actual Error Messages**: Display actual API error messages instead of generic text on retry ([#9954](https://github.com/RooCodeInc/Roo-Code/pull/9954))
43+
* **Stream Hanging Fix**: Process finish_reason to emit tool_call_end events for OpenRouter, Roo, and xAI providers ([#9927](https://github.com/RooCodeInc/Roo-Code/pull/9927), [#9929](https://github.com/RooCodeInc/Roo-Code/pull/9929))
44+
* **tool_result ID Validation**: Validate and fix tool_result IDs before API requests to prevent Anthropic rejections ([#9952](https://github.com/RooCodeInc/Roo-Code/pull/9952))
45+
* **Suppressed Internal Error**: Fixed 'ask promise was ignored' error leaking to LLM conversations ([#9914](https://github.com/RooCodeInc/Roo-Code/pull/9914))
46+
* **Provider Sanitization**: Fixed infinite loop when using removed/invalid API providers ([#9869](https://github.com/RooCodeInc/Roo-Code/pull/9869))
47+
* **Context Icons Theme**: Context-management icons now use foreground color to match VSCode themes ([#9912](https://github.com/RooCodeInc/Roo-Code/pull/9912))
48+
* **Eval Runs Deletion**: Fixed foreign key constraint preventing eval run deletions ([#9909](https://github.com/RooCodeInc/Roo-Code/pull/9909))
49+
* **OpenAI-Compatible Timeout Reliability**: Added timeout handling to OpenAI-compatible providers to prevent indefinite hangs (thanks dcbartlett!) ([#9898](https://github.com/RooCodeInc/Roo-Code/pull/9898))
50+
51+
## Provider Updates
52+
53+
* **DeepSeek V3.2**: Updated to V3.2 with 50% price reduction, native tools enabled by default, and 8K max output ([#9962](https://github.com/RooCodeInc/Roo-Code/pull/9962))
54+
* **xAI Models Catalog**: Updated catalog with corrected context windows, image support for grok-3/grok-3-mini, and removed deprecated models ([#9872](https://github.com/RooCodeInc/Roo-Code/pull/9872))
55+
* **xAI Tool Preferences**: Configured xAI models to use search_replace for better file editing compatibility ([#9923](https://github.com/RooCodeInc/Roo-Code/pull/9923))
56+
* **DeepSeek V3.2 for Baseten**: Added DeepSeek V3.2 model support (thanks AlexKer!) ([#9861](https://github.com/RooCodeInc/Roo-Code/pull/9861))
57+
* **Baseten Model Tweaks**: Improved maxTokens limits and native tools support for stability ([#9866](https://github.com/RooCodeInc/Roo-Code/pull/9866))
58+
* **Bedrock Models**: Added Kimi, MiniMax, and Qwen model configurations (thanks jbearak!) ([#9905](https://github.com/RooCodeInc/Roo-Code/pull/9905))
59+
60+
## Misc Improvements
61+
62+
* **Announcement UI Updates**: Improved announcement visuals with updated social icons and GitHub stars CTA ([#9945](https://github.com/RooCodeInc/Roo-Code/pull/9945))
63+
* **Improved Error Logging**: Better error context for parseToolCall exceptions and cloud job errors ([#9857](https://github.com/RooCodeInc/Roo-Code/pull/9857), [#9924](https://github.com/RooCodeInc/Roo-Code/pull/9924))
64+
* **search_replace Native Tool**: New tool for single-replacement file operations with precise targeting via unique text matching ([#9918](https://github.com/RooCodeInc/Roo-Code/pull/9918))
65+
* **Versioned Settings Support**: Internal infrastructure for API-side versioning of model settings with minimum plugin version gating ([#9934](https://github.com/RooCodeInc/Roo-Code/pull/9934))
66+
* **OpenRouter Telemetry**: Added API error telemetry for better diagnostics ([#9953](https://github.com/RooCodeInc/Roo-Code/pull/9953))
67+
* **Evals Streaming Stats**: Tool usage stats now stream in real-time with token usage throttling ([#9926](https://github.com/RooCodeInc/Roo-Code/pull/9926))

docs/update-notes/v3.36.4.mdx

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
---
2+
description: Adds error details modal with on-demand display and fixes for MCP tools, TODO list display, and telemetry.
3+
keywords:
4+
- roo code 3.36.4
5+
- error details modal
6+
- mcp tools fix
7+
- bug fixes
8+
image: /img/v3.36.4/v3.36.4.png
9+
---
10+
11+
# Roo Code 3.36.4 Release Notes (2025-12-10)
12+
13+
This release adds an on-demand error details modal for improved debugging and fixes issues with MCP tool streaming, TODO list display order, and telemetry error filtering.
14+
15+
<img src="/img/v3.36.4/v3.36.4.png" alt="Roo Code v3.36.4 Release" width="600" />
16+
17+
## Error Details Modal
18+
19+
Hover over error rows to reveal an info icon that opens a modal with full error details and a copy button ([#9985](https://github.com/RooCodeInc/Roo-Code/pull/9985)).
20+
21+
## Bug Fixes
22+
23+
* **MCP Tool Streaming**: Fixes an issue where MCP tools failed with "unknown tool" errors due to premature clearing of internal streaming data ([#9993](https://github.com/RooCodeInc/Roo-Code/pull/9993))
24+
* **TODO List Display Order**: The TODO list in the chat view now displays items in their correct execution order instead of being grouped by status ([#9991](https://github.com/RooCodeInc/Roo-Code/pull/9991))
25+
* **Telemetry Improvements**: Filters out 429 rate limit errors from API error telemetry for cleaner metrics and better error tracking ([#9987](https://github.com/RooCodeInc/Roo-Code/pull/9987))

sidebars.ts

Lines changed: 95 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -176,6 +176,101 @@ const sidebars: SidebarsConfig = {
176176
label: 'Extension Release Notes',
177177
items: [
178178
'update-notes/index',
179+
{
180+
type: 'category',
181+
label: '3.36',
182+
items: [
183+
{ type: 'doc', id: 'update-notes/v3.36.4', label: '3.36.4' },
184+
{ type: 'doc', id: 'update-notes/v3.36.3', label: '3.36.3' },
185+
{ type: 'doc', id: 'update-notes/v3.36.2', label: '3.36.2' },
186+
{ type: 'doc', id: 'update-notes/v3.36.1', label: '3.36.1' },
187+
{ type: 'doc', id: 'update-notes/v3.36.0', label: '3.36.0' },
188+
],
189+
},
190+
{
191+
type: 'category',
192+
label: '3.35',
193+
items: [
194+
{ type: 'doc', id: 'update-notes/v3.35', label: '3.35 Combined' },
195+
{ type: 'doc', id: 'update-notes/v3.35.5', label: '3.35.5' },
196+
{ type: 'doc', id: 'update-notes/v3.35.4', label: '3.35.4' },
197+
{ type: 'doc', id: 'update-notes/v3.35.3', label: '3.35.3' },
198+
{ type: 'doc', id: 'update-notes/v3.35.2', label: '3.35.2' },
199+
{ type: 'doc', id: 'update-notes/v3.35.1', label: '3.35.1' },
200+
{ type: 'doc', id: 'update-notes/v3.35.0', label: '3.35.0' },
201+
],
202+
},
203+
{
204+
type: 'category',
205+
label: '3.34',
206+
items: [
207+
{ type: 'doc', id: 'update-notes/v3.34', label: '3.34 Combined' },
208+
{ type: 'doc', id: 'update-notes/v3.34.8', label: '3.34.8' },
209+
{ type: 'doc', id: 'update-notes/v3.34.7', label: '3.34.7' },
210+
{ type: 'doc', id: 'update-notes/v3.34.6', label: '3.34.6' },
211+
{ type: 'doc', id: 'update-notes/v3.34.5', label: '3.34.5' },
212+
{ type: 'doc', id: 'update-notes/v3.34.4', label: '3.34.4' },
213+
{ type: 'doc', id: 'update-notes/v3.34.3', label: '3.34.3' },
214+
{ type: 'doc', id: 'update-notes/v3.34.2', label: '3.34.2' },
215+
{ type: 'doc', id: 'update-notes/v3.34.1', label: '3.34.1' },
216+
{ type: 'doc', id: 'update-notes/v3.34.0', label: '3.34.0' },
217+
],
218+
},
219+
{
220+
type: 'category',
221+
label: '3.33',
222+
items: [
223+
{ type: 'doc', id: 'update-notes/v3.33', label: '3.33 Combined' },
224+
{ type: 'doc', id: 'update-notes/v3.33.3', label: '3.33.3' },
225+
{ type: 'doc', id: 'update-notes/v3.33.2', label: '3.33.2' },
226+
{ type: 'doc', id: 'update-notes/v3.33.1', label: '3.33.1' },
227+
{ type: 'doc', id: 'update-notes/v3.33.0', label: '3.33.0' },
228+
],
229+
},
230+
{
231+
type: 'category',
232+
label: '3.32',
233+
items: [
234+
{ type: 'doc', id: 'update-notes/v3.32', label: '3.32 Combined' },
235+
{ type: 'doc', id: 'update-notes/v3.32.1', label: '3.32.1' },
236+
{ type: 'doc', id: 'update-notes/v3.32.0', label: '3.32.0' },
237+
],
238+
},
239+
{
240+
type: 'category',
241+
label: '3.31',
242+
items: [
243+
{ type: 'doc', id: 'update-notes/v3.31', label: '3.31 Combined' },
244+
{ type: 'doc', id: 'update-notes/v3.31.3', label: '3.31.3' },
245+
{ type: 'doc', id: 'update-notes/v3.31.2', label: '3.31.2' },
246+
{ type: 'doc', id: 'update-notes/v3.31.1', label: '3.31.1' },
247+
{ type: 'doc', id: 'update-notes/v3.31.0', label: '3.31.0' },
248+
],
249+
},
250+
{
251+
type: 'category',
252+
label: '3.30',
253+
items: [
254+
{ type: 'doc', id: 'update-notes/v3.30', label: '3.30 Combined' },
255+
{ type: 'doc', id: 'update-notes/v3.30.3', label: '3.30.3' },
256+
{ type: 'doc', id: 'update-notes/v3.30.2', label: '3.30.2' },
257+
{ type: 'doc', id: 'update-notes/v3.30.1', label: '3.30.1' },
258+
{ type: 'doc', id: 'update-notes/v3.30.0', label: '3.30.0' },
259+
],
260+
},
261+
{
262+
type: 'category',
263+
label: '3.29',
264+
items: [
265+
{ type: 'doc', id: 'update-notes/v3.29', label: '3.29 Combined' },
266+
{ type: 'doc', id: 'update-notes/v3.29.5', label: '3.29.5' },
267+
{ type: 'doc', id: 'update-notes/v3.29.4', label: '3.29.4' },
268+
{ type: 'doc', id: 'update-notes/v3.29.3', label: '3.29.3' },
269+
{ type: 'doc', id: 'update-notes/v3.29.2', label: '3.29.2' },
270+
{ type: 'doc', id: 'update-notes/v3.29.1', label: '3.29.1' },
271+
{ type: 'doc', id: 'update-notes/v3.29.0', label: '3.29.0' },
272+
],
273+
},
179274
{
180275
type: 'category',
181276
label: '3.28',

static/img/v3.36.3/v3.36.3.png

1.14 MB
Loading

static/img/v3.36.4/v3.36.4.png

1.19 MB
Loading

0 commit comments

Comments
 (0)