|
| 1 | +--- |
| 2 | +description: Combined notes for Roo Code 3.33, including Gemini 3 Pro Preview support, native tool calling for OpenAI-compatible providers, and various native tool reliability fixes. |
| 3 | +keywords: |
| 4 | + - roo code 3.33 |
| 5 | + - release notes |
| 6 | + - gemini 3 pro |
| 7 | + - native tool protocol |
| 8 | + - openai compatible |
| 9 | + - bug fixes |
| 10 | +image: /img/v3.33.0/v3.33.0.png |
| 11 | +--- |
| 12 | + |
| 13 | +# Roo Code 3.33 Release Notes (2025-11-18) |
| 14 | + |
| 15 | +Roo Code 3.33 introduces support for Gemini 3 Pro Preview and native tool calling for OpenAI-compatible providers, along with improved Gemini defaults and numerous native tool protocol fixes. |
| 16 | + |
| 17 | +<img src="/img/v3.33.0/v3.33.0.png" alt="Roo Code v3.33 Release" width="600" /> |
| 18 | + |
| 19 | +## Major Features |
| 20 | + |
| 21 | +### Gemini 3 Pro Preview |
| 22 | + |
| 23 | +Roo Code now supports Google’s Gemini 3 Pro Preview model through direct Gemini, Vertex AI, and aggregator providers like OpenRouter and Requesty ([#9357](https://github.com/RooCodeInc/Roo-Code/pull/9357), [#9327](https://github.com/RooCodeInc/Roo-Code/pull/9327)): |
| 24 | + |
| 25 | +- **1M-token, reasoning-capable model**: Handles very large conversations while providing higher-quality multi-step reasoning on complex coding and refactoring tasks. |
| 26 | +- **Strong eval performance**: Achieves a 100% score on internal Roo Code evals and 76.2% on SWE-bench Verified, giving more consistent solutions on real-world coding tasks. |
| 27 | +- **Reliable tool usage**: Executes complex multi-step tool workflows without getting stuck or losing track, especially in long, tool-heavy tasks. |
| 28 | +- **Better out-of-the-box defaults**: Uses `gemini-2.5-pro` by default where supported, sets a more natural temperature of 1, cleans up the Gemini model list, and includes reasoning / “thought” tokens in cost reporting so usage numbers better match provider billing. |
| 29 | + |
| 30 | +## QOL Improvements |
| 31 | + |
| 32 | +- **Native Tool Calling for OpenAI-compatible Providers** ([#9369](https://github.com/RooCodeInc/Roo-Code/pull/9369)): Enables native tool use with a wider range of models and providers that support the OpenAI format, offering more robust tool interactions in both streaming and non-streaming modes (thanks mrubens!). |
| 33 | + |
| 34 | +- **Git status in environment details** ([#9310](https://github.com/RooCodeInc/Roo-Code/pull/9310)): Shows git status information in environment details so agents have more context about untracked, modified, and staged files. |
| 35 | +- **Tool protocol selector in advanced settings** ([#9324](https://github.com/RooCodeInc/Roo-Code/pull/9324)): Lets you choose which tool protocol to use (such as XML vs native) without editing config files. |
| 36 | +- **Dynamic tool protocol resolution** ([#9286](https://github.com/RooCodeInc/Roo-Code/pull/9286)): Resolves the active tool protocol using a clear precedence hierarchy. |
| 37 | +- **Improved Modes view toolbar** ([#9077](https://github.com/RooCodeInc/Roo-Code/pull/9077)): Moves Import/Export into the Modes view toolbar and cleans up the Mode edit view. |
| 38 | +- **Cloud agent CTA points to setup page** ([#9338](https://github.com/RooCodeInc/Roo-Code/pull/9338)): Updates the cloud agent call-to-action to link directly to the setup page. |
| 39 | +- **Roo Code Cloud provider pricing page** ([#9195](https://github.com/RooCodeInc/Roo-Code/pull/9195)): Adds a pricing page and related Cloud provider tweaks. |
| 40 | + |
| 41 | +## Bug Fixes |
| 42 | + |
| 43 | +- **Native Tool Protocol Race Condition** ([#9363](https://github.com/RooCodeInc/Roo-Code/pull/9363)): Fixed a race condition where switching profiles or changing API configuration could cause 400 errors. |
| 44 | +- **Native Tool Repetition Detection** ([#9377](https://github.com/RooCodeInc/Roo-Code/pull/9377)): Fixed false positive "stuck in a loop" errors when using native tools repeatedly. |
| 45 | +- **Strict Native Protocol Parsing** ([#9371](https://github.com/RooCodeInc/Roo-Code/pull/9371)): Ensured no XML parsing occurs when the native protocol is active. |
| 46 | +- **Gemini Reasoning Config** ([#9375](https://github.com/RooCodeInc/Roo-Code/pull/9375)): Fixed an issue where high/low reasoning effort configuration was not being applied correctly. |
| 47 | +- **Gemini Thought Validation** ([#9380](https://github.com/RooCodeInc/Roo-Code/pull/9380)): Resolved integration errors with Gemini reasoning models. |
| 48 | +- **Prevent duplicate tool_result blocks in native protocol** ([#9248](https://github.com/RooCodeInc/Roo-Code/pull/9248)): Ensures each native tool call emits a single tool_result block. |
| 49 | +- **Format tool responses for native protocol** ([#9270](https://github.com/RooCodeInc/Roo-Code/pull/9270)): Normalizes the structure of tool responses for easier model comprehension. |
| 50 | +- **Centralize toolProtocol configuration checks** ([#9279](https://github.com/RooCodeInc/Roo-Code/pull/9279)): Uses a single source of truth for toolProtocol configuration. |
| 51 | +- **Preserve tool blocks in conversation history** ([#9319](https://github.com/RooCodeInc/Roo-Code/pull/9319)): Keeps native protocol tool blocks intact in history. |
| 52 | +- **Prevent infinite loops after successful finalization** ([#9325](https://github.com/RooCodeInc/Roo-Code/pull/9325)): Fixes a regression where certain native tool flows could loop. |
| 53 | +- **Sync parser state with profile and model changes** ([#9355](https://github.com/RooCodeInc/Roo-Code/pull/9355)): Keeps the conversation parser aligned with the active profile and model. |
| 54 | +- **Pass tool protocol to truncation errors** ([#9358](https://github.com/RooCodeInc/Roo-Code/pull/9358)): Ensures truncation errors know which tool protocol is active. |
| 55 | +- **Structured JSON Returns** ([#9373](https://github.com/RooCodeInc/Roo-Code/pull/9373)): Updated tools to consistently return structured JSON when using the native protocol. |
| 56 | +- **VS Code theme-colored outline button borders** ([#9336](https://github.com/RooCodeInc/Roo-Code/pull/9336)): Aligns outline button borders with the current VS Code theme. |
| 57 | +- **Use shields.io badges instead of badgen.net** ([#9318](https://github.com/RooCodeInc/Roo-Code/pull/9318)): Replaces broken badge URLs with shields.io. |
| 58 | +- **Cap git status file sampling in evals** ([#9322](https://github.com/RooCodeInc/Roo-Code/pull/9322)): Adds a maximum for git status files in eval settings. |
0 commit comments