Roo Code 3.43.0 Release Notes (2026-01-23)
This release updates Intelligent Context Condensation, removes deprecated settings, and fixes export and settings issues.
Intelligent Context Condensation v2
Intelligent Context Condensation runs when the conversation is near the model’s context limit. It summarizes earlier messages instead of dropping them. After a condense, Roo continues from a single summary, not a mix of summary plus a long tail of older messages. If your task starts with a slash command, Roo preserves those slash-command-driven directives across condenses. Roo is less likely to break tool-heavy chats during a condense, which reduces failed requests and missing tool results.
Settings changes: the Condense prompt editor is now under Context Management and Reset clears your override. Condensing uses the active conversation model/provider. There is no separate model/provider selector for condensing.
(#10873, #10920, #10909, #10927, #10931, #10876, #10881, #10901)
QOL Improvements
- Removes the unused “Enable concurrent file edits” experimental toggle to reduce settings clutter. (#10925)
- Removes the experimental Power Steering setting (a deprecated experiment that no longer improves results). (#10926)
- Removes obsolete diff/match-precision provider settings that no longer affect behavior. (#10298)
- Adds a
pnpm install:vsix:nightlycommand to make installing nightly VSIX builds easier. (#10912)
Bug Fixes
- Fixes an issue where MCP config files saved via the UI could be rewritten as a single minified line. Files are now pretty-printed. (thanks Michaelzag!) (#9864)
- Fixes an issue where exporting tasks to Markdown could include
[Unexpected content type: thoughtSignature]lines for some models. Exports are now clean. (thanks rossdonald!) (#10932) - Fixes an issue where the Model section could appear twice in the OpenAI Codex provider settings. (#10930)
Misc Improvements
- Removes legacy XML tool-calling code paths that are no longer used, reducing maintenance surface area. (#10929)