|
1 | 1 | # Roo Code Changelog |
2 | 2 |
|
| 3 | +## [3.36.3] - 2025-12-09 |
| 4 | + |
| 5 | + |
| 6 | + |
| 7 | +- Refactor: Unified context-management architecture with improved UX for better context control (PR #9795 by @hannesrudolph) |
| 8 | +- Add new `search_replace` native tool for single-replacement operations with improved editing precision (PR #9918 by @hannesrudolph) |
| 9 | +- Streaming tool stats and token usage throttling for better real-time feedback during generation (PR #9926 by @hannesrudolph) |
| 10 | +- Add versioned settings support with minPluginVersion gating for Roo provider (PR #9934 by @hannesrudolph) |
| 11 | +- Make Architect mode save plans to `/plans` directory and gitignore it (PR #9944 by @brunobergher) |
| 12 | +- Add announcement support CTA and social icons to UI (PR #9945 by @hannesrudolph) |
| 13 | +- Add ability to save screenshots from the browser tool (PR #9963 by @mrubens) |
| 14 | +- Refactor: Decouple tools from system prompt for cleaner architecture (PR #9784 by @daniel-lxs) |
| 15 | +- Update DeepSeek models to V3.2 with new pricing (PR #9962 by @hannesrudolph) |
| 16 | +- Add minimal and medium reasoning effort levels for Gemini models (PR #9973 by @hannesrudolph) |
| 17 | +- Update xAI models catalog with latest model options (PR #9872 by @hannesrudolph) |
| 18 | +- Add DeepSeek V3-2 support for Baseten provider (PR #9861 by @AlexKer) |
| 19 | +- Tweaks to Baseten model definitions for better defaults (PR #9866 by @mrubens) |
| 20 | +- Fix: Add xhigh reasoning effort support for gpt-5.1-codex-max (#9891 by @andrewginns, PR #9900 by @andrewginns) |
| 21 | +- Fix: Add Kimi, MiniMax, and Qwen model configurations for Bedrock (#9902 by @jbearak, PR #9905 by @app/roomote) |
| 22 | +- Configure tool preferences for xAI models (PR #9923 by @hannesrudolph) |
| 23 | +- Default to using native tools when supported on OpenRouter (PR #9878 by @mrubens) |
| 24 | +- Fix: Exclude apply_diff from native tools when diffEnabled is false (#9919 by @denis-kudelin, PR #9920 by @app/roomote) |
| 25 | +- Fix: Always show tool protocol selector for openai-compatible provider (#9965 by @bozoweed, PR #9966 by @hannesrudolph) |
| 26 | +- Fix: Respect explicit supportsReasoningEffort array values for proper model configuration (PR #9970 by @hannesrudolph) |
| 27 | +- Add timeout configuration to OpenAI Compatible Provider Client (PR #9898 by @dcbartlett) |
| 28 | +- Revert default tool protocol change from xml to native for stability (PR #9956 by @mrubens) |
| 29 | +- Remove defaultTemperature from Roo provider configuration (PR #9932 by @mrubens) |
| 30 | +- Improve OpenAI error messages to be more useful for debugging (PR #9639 by @mrubens) |
| 31 | +- Better error logs for parseToolCall exceptions (PR #9857 by @cte) |
| 32 | +- Improve cloud job error logging for RCC provider errors (PR #9924 by @cte) |
| 33 | +- Fix: Display actual API error message instead of generic text on retry (PR #9954 by @hannesrudolph) |
| 34 | +- Add API error telemetry to OpenRouter provider for better diagnostics (PR #9953 by @daniel-lxs) |
| 35 | +- Fix: Sanitize removed/invalid API providers to prevent infinite loop (PR #9869 by @hannesrudolph) |
| 36 | +- Fix: Use foreground color for context-management icons (PR #9912 by @hannesrudolph) |
| 37 | +- Fix: Suppress 'ask promise was ignored' error in handleError (PR #9914 by @daniel-lxs) |
| 38 | +- Fix: Process finish_reason to emit tool_call_end events properly (PR #9927 by @daniel-lxs) |
| 39 | +- Fix: Add finish_reason processing to xai.ts provider (PR #9929 by @daniel-lxs) |
| 40 | +- Fix: Validate and fix tool_result IDs before API requests (PR #9952 by @daniel-lxs) |
| 41 | +- Fix: Return undefined instead of 0 for disabled API timeout (PR #9960 by @hannesrudolph) |
| 42 | +- Stop making unnecessary count_tokens requests for better performance (PR #9884 by @mrubens) |
| 43 | +- Refactor: Consolidate ThinkingBudget components and fix disable handling (PR #9930 by @hannesrudolph) |
| 44 | +- Forbid time estimates in architect mode for more focused planning (PR #9931 by @app/roomote) |
| 45 | +- Web: Add product pages (PR #9865 by @brunobergher) |
| 46 | +- Make eval runs deleteable in the web UI (PR #9909 by @mrubens) |
| 47 | +- Feat: Change defaultToolProtocol default from xml to native (later reverted) (PR #9892 by @app/roomote) |
| 48 | + |
3 | 49 | ## [3.36.2] - 2025-12-04 |
4 | 50 |
|
5 | 51 |  |
|
243 | 289 |
|
244 | 290 | ## [3.33.0] - 2025-11-18 |
245 | 291 |
|
246 | | - |
| 292 | + |
247 | 293 |
|
248 | 294 | - Add Gemini 3 Pro Preview model (PR #9357 by @hannesrudolph) |
249 | 295 | - Improve Google Gemini defaults with better temperature and cost reporting (PR #9327 by @hannesrudolph) |
|
0 commit comments