|
| 1 | +--- |
| 2 | +description: Combined notes for Roo Code 3.34, including Browser Use 2.0, the Baseten provider, OpenAI-compatible improvements, Roo Code Cloud eval jobs, image generation UI tweaks, todo list cleanup, and cloud sync fixes. |
| 3 | +keywords: |
| 4 | + - roo code 3.34 |
| 5 | + - browser use 2.0 |
| 6 | + - baseten provider |
| 7 | + - openai compatible |
| 8 | + - evals roo code cloud |
| 9 | + - image generation ui |
| 10 | + - todo list ui |
| 11 | + - cloud sync bug fix |
| 12 | +image: /img/v3.34.0/v3.34.0.png |
| 13 | +--- |
| 14 | + |
| 15 | +# Roo Code 3.34 Release Notes (2025-11-21) |
| 16 | + |
| 17 | +Roo Code 3.34 combines Browser Use 2.0, the Baseten provider, OpenAI-compatible improvements, and refined onboarding and native tool descriptions with a patch that adds Roo Code Cloud eval support, clearer image generation prompts, todo list cleanup, and cloud sync fixes. |
| 18 | + |
| 19 | +<img src="/img/v3.34.0/v3.34.0.png" alt="Roo Code v3.34 Release" width="600" /> |
| 20 | + |
| 21 | +## Browser Use 2.0 |
| 22 | + |
| 23 | +Browser Use now supports a more capable "2.0" experience ([#8941](https://github.com/RooCodeInc/Roo-Code/pull/8941)): |
| 24 | + |
| 25 | +- **Richer browser interaction**: Enables more advanced navigation and interaction patterns so Roo can better follow multi-step web workflows. |
| 26 | +- **More reliable automation**: Improves stability for sequences of clicks, typing, and scrolling, reducing the chance of flaky browser runs. |
| 27 | +- **Better fit for complex sites**: Makes it easier to work with modern web apps that require multiple steps or stateful interactions. |
| 28 | + |
| 29 | +> **📚 Documentation**: See [Browser Use](/features/browser-use) for details on how to enable and use browser workflows. Note: We have not yet updated these docs with images and a video of the new experiance. |
| 30 | +
|
| 31 | +## QOL Improvements |
| 32 | + |
| 33 | +- **Provider-oriented welcome screen**: Added a provider-focused welcome screen so new users can more quickly choose and configure a working model setup ([#9484](https://github.com/RooCodeInc/Roo-Code/pull/9484)). |
| 34 | +- **Pinned Roo provider**: Pinned the Roo provider to the top of the provider list so it is easier to discover and select ([#9485](https://github.com/RooCodeInc/Roo-Code/pull/9485)). |
| 35 | +- **Clearer native tool descriptions**: Enhanced built-in tool descriptions with examples and clarifications so Roo can choose the right tools and use them more accurately ([#9486](https://github.com/RooCodeInc/Roo-Code/pull/9486)). |
| 36 | +- **Clearer image generation prompts**: The full prompt and path for image generation now appear directly in the chat UI with clearer spacing and typography, making it easier to inspect, debug, and reuse prompts ([#9505](https://github.com/RooCodeInc/Roo-Code/pull/9505), [#9522](https://github.com/RooCodeInc/Roo-Code/pull/9522)). |
| 37 | +- **Eval jobs on Roo Code Cloud**: You can now run evaluation jobs directly on Roo Code Cloud models, reusing the same managed models and job tokens as regular cloud runs ([#9492](https://github.com/RooCodeInc/Roo-Code/pull/9492), [#9522](https://github.com/RooCodeInc/Roo-Code/pull/9522)). |
| 38 | + |
| 39 | +## Bug Fixes |
| 40 | + |
| 41 | +- **Streaming cancel responsiveness**: Fixed the cancel button so it responds immediately during streaming, making it easier to stop long or unwanted runs ([#9448](https://github.com/RooCodeInc/Roo-Code/pull/9448)). |
| 42 | +- **apply_diff performance regression**: Resolved a recent performance regression in `apply_diff`, restoring fast patch application on larger edits ([#9474](https://github.com/RooCodeInc/Roo-Code/pull/9474)). |
| 43 | +- **Model cache refresh**: Implemented cache refreshing to avoid using stale disk-cached models, ensuring configuration updates are picked up correctly ([#9478](https://github.com/RooCodeInc/Roo-Code/pull/9478)). |
| 44 | +- **Tool call fallbacks**: Added a fallback to always yield tool calls regardless of `finish_reason`, preventing cases where valid tool calls were dropped ([#9476](https://github.com/RooCodeInc/Roo-Code/pull/9476)). |
| 45 | +- **Single todo list in updates**: Removed a redundant todo list block from chat updates so you only see one clean, focused list when the updateTodoList tool runs ([#9517](https://github.com/RooCodeInc/Roo-Code/pull/9517), [#9522](https://github.com/RooCodeInc/Roo-Code/pull/9522)). |
| 46 | +- **Cloud message deduplication**: Fixed cloud message syncing so duplicate copies of the same reasoning or assistant message are no longer re-synced, keeping task histories cleaner and less confusing ([#9518](https://github.com/RooCodeInc/Roo-Code/pull/9518), [#9522](https://github.com/RooCodeInc/Roo-Code/pull/9522)). |
| 47 | + |
| 48 | +## Provider Updates |
| 49 | + |
| 50 | +- **Baseten provider**: Added Baseten as a new AI provider, giving you another option for hosted models and deployments ([#9461](https://github.com/RooCodeInc/Roo-Code/pull/9461)). |
| 51 | +- **OpenAI-compatible improvements**: Improved the base OpenAI-compatible provider configuration and error handling so more OpenAI-style endpoints work smoothly without special tweaks ([#9462](https://github.com/RooCodeInc/Roo-Code/pull/9462)). |
| 52 | +- **OpenRouter capabilities**: Improved copying of model-level capabilities onto OpenRouter endpoint models so routing respects each model's real abilities ([#9483](https://github.com/RooCodeInc/Roo-Code/pull/9483)). |
0 commit comments