|
| 1 | +--- |
| 2 | +description: Message management improvements, GPT-5.1 Codex Max support, symlink support for slash commands, and stability fixes. |
| 3 | +keywords: |
| 4 | + - roo code 3.36.1 |
| 5 | + - gpt-5.1 codex max |
| 6 | + - slash commands symlinks |
| 7 | + - message management |
| 8 | + - bug fixes |
| 9 | +image: /img/v3.36.1/v3.36.1.png |
| 10 | +--- |
| 11 | + |
| 12 | +# Roo Code 3.36.1 Release Notes (2025-12-04) |
| 13 | + |
| 14 | +This release adds GPT-5.1 Codex Max support, enables symlinks for slash commands, improves message management with better checkpoint restore, and fixes several stability issues. |
| 15 | + |
| 16 | +<img src="/img/v3.36.1/v3.36.1.png" alt="Roo Code v3.36.1 Release" width="600" /> |
| 17 | + |
| 18 | +## GPT-5.1 Codex Max Support |
| 19 | + |
| 20 | +Roo Code now supports GPT-5.1 Codex Max ([#9848](https://github.com/RooCodeInc/Roo-Code/pull/9848)), OpenAI's most intelligent coding model optimized for long-horizon, agentic coding tasks. This release also adds model defaults for gpt-5.1, gpt-5, and gpt-5-mini variants with optimized configurations. |
| 21 | + |
| 22 | +> **📚 Documentation**: See [OpenAI Provider](/providers/openai) for configuration details. |
| 23 | +
|
| 24 | +## QOL Improvements |
| 25 | + |
| 26 | +* **Symlink support for slash commands**: Share and organize commands across projects using symlinks for individual files or directories, with command names derived from symlink names for easy aliasing ([#9838](https://github.com/RooCodeInc/Roo-Code/pull/9838)) |
| 27 | +* **Smoother chat scroll**: Chat view maintains scroll position more reliably during streaming, eliminating disruptive jumps ([#8999](https://github.com/RooCodeInc/Roo-Code/pull/8999)) |
| 28 | +* **Improved error messages**: Clearer, more actionable error messages with proper attribution and direct links to documentation ([#9777](https://github.com/RooCodeInc/Roo-Code/pull/9777)) |
| 29 | + |
| 30 | +## Bug Fixes |
| 31 | + |
| 32 | +* **Extension freeze prevention**: The extension no longer freezes when a model attempts to call a non-existent tool (thanks daniel-lxs!) ([#9834](https://github.com/RooCodeInc/Roo-Code/pull/9834)) |
| 33 | +* **Checkpoint restore reliability**: MessageManager layer ensures consistent message history handling across all rewind operations ([#9842](https://github.com/RooCodeInc/Roo-Code/pull/9842)) |
| 34 | +* **Context truncation fix**: Prevent cascading truncation loops by only truncating visible messages ([#9844](https://github.com/RooCodeInc/Roo-Code/pull/9844)) |
| 35 | +* **Reasoning models**: Models that require reasoning now always receive valid reasoning effort values ([#9836](https://github.com/RooCodeInc/Roo-Code/pull/9836)) |
| 36 | +* **Terminal input handling**: Inline terminal no longer hangs when commands require user input ([#9827](https://github.com/RooCodeInc/Roo-Code/pull/9827)) |
| 37 | +* **Large file safety**: Safer large file reads with proper token budget accounting for model output ([#9843](https://github.com/RooCodeInc/Roo-Code/pull/9843)) |
| 38 | +* **Follow-up button styling**: Fixed overly rounded corners on follow-up question suggestions ([#9829](https://github.com/RooCodeInc/Roo-Code/pull/9829)) |
| 39 | + |
| 40 | +## Misc Improvements |
| 41 | + |
| 42 | +* **Evals UI enhancements**: Added filtering by timeframe/model/provider, bulk delete actions, tool column consolidation, and run notes ([#9837](https://github.com/RooCodeInc/Roo-Code/pull/9837)) |
| 43 | +* **Multi-model evals launch**: Launch identical test runs across multiple models with automatic staggering ([#9845](https://github.com/RooCodeInc/Roo-Code/pull/9845)) |
| 44 | +* **New pricing page**: Updated website pricing page with clearer feature explanations ([#9821](https://github.com/RooCodeInc/Roo-Code/pull/9821)) |
0 commit comments