|
1 | 1 | # Roo Code Changelog |
2 | 2 |
|
| 3 | +## [3.41.0] - 2026-01-15 |
| 4 | + |
| 5 | + |
| 6 | + |
| 7 | +- Add OpenAI - ChatGPT Plus/Pro Provider that gives subscription-based access to Codex models without per-token costs (PR #10736 by @hannesrudolph) |
| 8 | +- Add gpt-5.2-codex model to openai-native provider, providing access to the latest GPT model with enhanced coding capabilities (PR #10731 by @hannesrudolph) |
| 9 | +- Fix: Clear terminal output buffers to prevent memory leaks that could cause gray screens and performance degradation (#10666, PR #7666 by @hannesrudolph) |
| 10 | +- Fix: Inject dummy thought signatures on ALL tool calls for Gemini models, resolving issues with Gemini tool call handling through LiteLLM (PR #10743 by @daniel-lxs) |
| 11 | +- Enable E2E tests with 39 passing tests, improving test coverage and reliability (PR #10720 by @ArchimedesCrypto) |
| 12 | +- Add alwaysAllow config for MCP time server tools in E2E tests (PR #10733 by @ArchimedesCrypto) |
| 13 | + |
| 14 | +## [3.40.1] - 2026-01-13 |
| 15 | + |
| 16 | +- Fix: Add allowedFunctionNames support for Gemini to prevent mode switch errors (#10711 by @hannesrudolph, PR #10708 by @hannesrudolph) |
| 17 | + |
| 18 | +## [3.40.0] - 2026-01-13 |
| 19 | + |
| 20 | + |
| 21 | + |
| 22 | +- Add settings search functionality to quickly find and navigate to specific settings (PR #10619 by @mrubens) |
| 23 | +- Improve settings search UI with better styling and usability (PR #10633 by @brunobergher) |
| 24 | +- Add standardized stop button for improved task cancellation visibility (PR #10639 by @brunobergher) |
| 25 | +- Display edit_file errors in UI after consecutive failures for better debugging feedback (PR #10581 by @daniel-lxs) |
| 26 | +- Improve error display styling and visibility in chat messages (PR #10692 by @brunobergher) |
| 27 | +- Improve stop button visibility and streamline error handling (PR #10696 by @brunobergher) |
| 28 | +- Fix: Omit parallel_tool_calls when not explicitly enabled to prevent API errors (#10553 by @Idlebrand, PR #10671 by @daniel-lxs) |
| 29 | +- Fix: Encode hyphens in MCP tool names before sanitization (#10642 by @pdecat, PR #10644 by @pdecat) |
| 30 | +- Fix: Correct Gemini 3 thought signature injection format via OpenRouter (PR #10640 by @daniel-lxs) |
| 31 | +- Fix: Sanitize tool_use IDs to match API validation pattern (PR #10649 by @daniel-lxs) |
| 32 | +- Fix: Use placeholder for empty tool result content to fix Gemini API validation (PR #10672 by @daniel-lxs) |
| 33 | +- Fix: Return empty string from getReadablePath when path is empty (PR #10638 by @daniel-lxs) |
| 34 | +- Optimize message block cloning in presentAssistantMessage for better performance (PR #10616 by @ArchimedesCrypto) |
| 35 | + |
3 | 36 | ## [3.39.3] - 2026-01-10 |
4 | 37 |
|
5 | 38 |  |
|
0 commit comments