Skip to content
This repository was archived by the owner on May 15, 2026. It is now read-only.

Commit d8949f9

Browse files
authored
Update CHANGELOG for version 3.43.0 release
Added details for version 3.43.0 release, including new features, improvements, and bug fixes.
1 parent e1a5cef commit d8949f9

1 file changed

Lines changed: 19 additions & 5 deletions

File tree

CHANGELOG.md

Lines changed: 19 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,24 @@
11
# Roo Code Changelog
22

3-
## 3.43.0
4-
5-
### Minor Changes
6-
7-
- ![3.43.0 Release - Intelligent Context Condensation](/releases/3.43.0-release.png)
3+
## [3.43.0] - 2026-01-23
4+
5+
![3.43.0 Release - Intelligent Context Condensation](/releases/3.43.0-release.png)
6+
7+
- Intelligent Context Condensation v2: New context condensation system that intelligently summarizes conversation history when approaching context limits, preserving important information while reducing token usage (PR #10873 by @hannesrudolph)
8+
- Improved context condensation with environment details, accurate token counts, and lazy evaluation for better performance (PR #10920 by @hannesrudolph)
9+
- Move condense prompt editor to Context Management tab for better discoverability and organization (PR #10909 by @hannesrudolph)
10+
- Update Z.AI models with new variants and pricing (#10859 by @ErdemGKSL, PR #10860 by @ErdemGKSL)
11+
- Add pnpm install:vsix:nightly command for easier nightly build installation (PR #10912 by @hannesrudolph)
12+
- Fix: Convert orphaned tool_results to text blocks after condensing to prevent API errors (PR #10927 by @daniel-lxs)
13+
- Fix: Auto-migrate v1 condensing prompt and handle invalid providers on import (PR #10931 by @hannesrudolph)
14+
- Fix: Use json-stream-stringify for pretty-printing MCP config files to prevent memory issues with large configs (#9862 by @Michaelzag, PR #9864 by @Michaelzag)
15+
- Fix: Correct Gemini 3 pricing for Flash and Pro models (#10432 by @rossdonald, PR #10487 by @roomote)
16+
- Fix: Skip thoughtSignature blocks during markdown export for cleaner output (#10199 by @rossdonald, PR #10932 by @rossdonald)
17+
- Fix: Duplicate model display for OpenAI Codex provider (PR #10930 by @roomote)
18+
- Remove diffEnabled and fuzzyMatchThreshold settings as they are no longer needed (#10648 by @hannesrudolph, PR #10298 by @hannesrudolph)
19+
- Remove MULTI_FILE_APPLY_DIFF experiment (PR #10925 by @hannesrudolph)
20+
- Remove POWER_STEERING experimental feature (PR #10926 by @hannesrudolph)
21+
- Remove legacy XML tool calling code (getToolDescription) for cleaner codebase (PR #10929 by @hannesrudolph)
822

923
## [3.42.0] - 2026-01-22
1024

0 commit comments

Comments
 (0)