Release v3.41.1

[3.41.1] - 2026-01-16

• Feat: Aggregate subtask costs in parent task (#5376 by @hannesrudolph, PR #10757 by @taltas)
• Fix: Prevent duplicate tool_use IDs causing API 400 errors (PR #10760 by @daniel-lxs)
• Fix: Handle missing tool identity in OpenAI Native streams (PR #10719 by @hannesrudolph)
• Fix: Truncate call_id to 64 chars for OpenAI Responses API (PR #10763 by @daniel-lxs)
• Fix: Gemini thought signature validation errors (PR #10694 by @daniel-lxs)
• Fix: Filter out empty text blocks from user messages for Gemini compatibility (PR #10728 by @daniel-lxs)
• Fix: Flatten top-level anyOf/oneOf/allOf in MCP tool schemas (PR #10726 by @daniel-lxs)
• Fix: Filter Ollama models without native tool support (PR #10735 by @daniel-lxs)
• Feat: Add settings tab titles to search index (PR #10761 by @roomote)
• Feat: Clarify Slack and Linear are Cloud Team only features (PR #10748 by @roomote)

Release v3.41.0

[3.41.0] - 2026-01-15

• Add OpenAI - ChatGPT Plus/Pro Provider that gives subscription-based access to Codex models without per-token costs (PR #10736 by @hannesrudolph)
• 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)
• Fix: Clear terminal output buffers to prevent memory leaks that could cause gray screens and performance degradation (#10666, PR #7666 by @hannesrudolph)
• 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)
• Enable E2E tests with 39 passing tests, improving test coverage and reliability (PR #10720 by @ArchimedesCrypto)
• Add alwaysAllow config for MCP time server tools in E2E tests (PR #10733 by @ArchimedesCrypto)

Release v3.40.1

[3.40.1] - 2026-01-13

• Fix: Add allowedFunctionNames support for Gemini to prevent mode switch errors (#10711 by @hannesrudolph, PR #10708 by @hannesrudolph)

Release v3.40.0

[3.40.0] - 2026-01-13

• Add settings search functionality to quickly find and navigate to specific settings (PR #10619 by @mrubens)
• Improve settings search UI with better styling and usability (PR #10633 by @brunobergher)
• Add standardized stop button for improved task cancellation visibility (PR #10639 by @brunobergher)
• Display edit_file errors in UI after consecutive failures for better debugging feedback (PR #10581 by @daniel-lxs)
• Improve error display styling and visibility in chat messages (PR #10692 by @brunobergher)
• Improve stop button visibility and streamline error handling (PR #10696 by @brunobergher)
• Fix: Omit parallel_tool_calls when not explicitly enabled to prevent API errors (#10553 by @Idlebrand, PR #10671 by @daniel-lxs)
• Fix: Encode hyphens in MCP tool names before sanitization (#10642 by @pdecat, PR #10644 by @pdecat)
• Fix: Correct Gemini 3 thought signature injection format via OpenRouter (PR #10640 by @daniel-lxs)
• Fix: Sanitize tool_use IDs to match API validation pattern (PR #10649 by @daniel-lxs)
• Fix: Use placeholder for empty tool result content to fix Gemini API validation (PR #10672 by @daniel-lxs)
• Fix: Return empty string from getReadablePath when path is empty (PR #10638 by @daniel-lxs)
• Optimize message block cloning in presentAssistantMessage for better performance (PR #10616 by @ArchimedesCrypto)

Roo Code CLI v0.0.46

What's New

Added

• Interactive mode and model pickers for easy selection
• Improved task management and navigation
• CLI release script now supports local installation for testing (#10597)

Changed

• Default model changed to anthropic/claude-opus-4.5 (#10544)
• File organization improvements for better maintainability (#10599)
• Cleanup in ExtensionHost for better code organization (#10600)
• Updated README documentation
• Logging cleanup and improvements

Fixed

• Model switching issues (model ID mismatch)
• ACP task cancellation handling
• Command output streaming
• Use DEFAULT_FLAGS.model as single source of truth for default model ID

Tests

• Updated tests for model changes

Installation

curl -fsSL https://raw.githubusercontent.com/RooCodeInc/Roo-Code/main/apps/cli/install.sh | sh

Or install a specific version:

ROO_VERSION=0.0.46 curl -fsSL https://raw.githubusercontent.com/RooCodeInc/Roo-Code/main/apps/cli/install.sh | sh

Requirements

• Node.js 20 or higher
• macOS (Intel or Apple Silicon) or Linux (x64 or ARM64)

Usage

# Set your API key
export OPENROUTER_API_KEY=sk-or-v1-...

# Run a task
roo "What is this project?" ~/my-project

# See all options
roo --help

Platform Support

This release includes:

• roo-cli-darwin-arm64.tar.gz - Built on Darwin arm64

Note: Additional platforms will be added as needed. If you need a different platform, please open an issue.

Checksum

5404341a718f5f51812d2a9128c0b530feab0d5533817d2e121bcf1058f9b878  roo-cli-darwin-arm64.tar.gz

Release v3.39.3

[3.39.3] - 2026-01-10

• Rename Roo Code Cloud Provider to Roo Code Router for clearer branding (PR #10560 by @roomote)
• Update Roo Code Router service name throughout the codebase (PR #10607 by @mrubens)
• Update router name in types for consistency (PR #10605 by @mrubens)
• Improve ExtensionHost code organization and cleanup (PR #10600 by @cte)
• Add local installation option to CLI release script for testing (PR #10597 by @cte)
• Reorganize CLI file structure for better maintainability (PR #10599 by @cte)
• Add TUI to CLI (PR #10480 by @cte)

Release v3.39.2

[3.39.2] - 2026-01-09

• Fix: Ensure all tools have consistent strict mode values for Cerebras compatibility (#10334 by @brianboysen51, PR #10589 by @app/roomote)
• Fix: Remove convertToSimpleMessages to restore tool calling for OpenAI-compatible providers (PR #10575 by @daniel-lxs)
• Fix: Make edit_file matching more resilient to prevent false negatives (PR #10585 by @hannesrudolph)
• Fix: Order text parts before tool calls in assistant messages for vscode-lm (PR #10573 by @daniel-lxs)
• Fix: Ensure assistant message content is never undefined for Gemini compatibility (PR #10559 by @daniel-lxs)
• Fix: Merge approval feedback into tool result instead of pushing duplicate messages (PR #10519 by @daniel-lxs)
• Fix: Round-trip Gemini thought signatures for tool calls (PR #10590 by @hannesrudolph)
• Feature: Improve error messaging for stream termination errors from provider (PR #10548 by @daniel-lxs)
• Feature: Add debug setting to settings page for easier troubleshooting (PR #10580 by @hannesrudolph)
• Chore: Disable edit_file tool for Gemini/Vertex providers (PR #10594 by @hannesrudolph)
• Chore: Stop overriding tool allow/deny lists for Gemini (PR #10592 by @hannesrudolph)
• Chore: Change default CLI model to anthropic/claude-opus-4.5 (PR #10544 by @mrubens)
• Chore: Update Terms of Service effective January 9, 2026 (PR #10568 by @mrubens)
• Chore: Move more types to @roo-code/types for CLI support (PR #10583 by @cte)
• Chore: Add functionality to @roo-code/core for CLI support (PR #10584 by @cte)
• Chore: Add slash commands useful for CLI development (PR #10586 by @cte)

Release v3.39.1

[3.39.1] - 2026-01-08

• Fix: Stabilize file paths during native tool call streaming to prevent path corruption (PR #10555 by @daniel-lxs)
• Fix: Disable Gemini thought signature persistence to prevent corrupted signature errors (PR #10554 by @daniel-lxs)
• Fix: Change minItems from 2 to 1 for Anthropic API compatibility (PR #10551 by @daniel-lxs)

Release v3.39.0

[3.39.0] - 2026-01-08

• Implement sticky provider profile for task-level API config persistence (#8010 by @hannesrudolph, PR #10018 by @hannesrudolph)
• Add support for image file @mentions (PR #10189 by @hannesrudolph)
• Rename YOLO to BRRR (#8574 by @mojomast, PR #10507 by @roomote)
• Add debug-mode proxy routing for debugging API calls (#7042 by @SleeperSmith, PR #10467 by @hannesrudolph)
• Add Kimi K2 thinking model to Fireworks AI provider (#9201 by @kavehsfv, PR #9202 by @roomote)
• Add xhigh reasoning effort to OpenAI compatible endpoints (#10060 by @Soorma718, PR #10061 by @roomote)
• Filter @ mention file search results using .rooignore (#10169 by @jerrill-johnson-bitwerx, PR #10174 by @roomote)
• Add image support documentation to read_file native tool description (#10440 by @nabilfreeman, PR #10442 by @roomote)
• Add zai-glm-4.7 to Cerebras models (PR #10500 by @sebastiand-cerebras)
• VSCode shim and basic CLI for running Roo Code headlessly (PR #10452 by @cte)
• Add CLI installer for headless Roo Code (PR #10474 by @cte)
• Add option to use CLI for evals (PR #10456 by @cte)
• Remember last Roo model selection in web-evals and add evals skill (PR #10470 by @hannesrudolph)
• Tweak the style of follow up suggestion modes (PR #9260 by @mrubens)
• Fix: Handle PowerShell ENOENT error in os-name on Windows (#9859 by @Yang-strive, PR #9897 by @roomote)
• Fix: Make command chaining examples shell-aware for Windows compatibility (#10352 by @AlexNek, PR #10434 by @roomote)
• Fix: Preserve tool_use blocks for all tool_results in kept messages during condensation (PR #10471 by @daniel-lxs)
• Fix: Add additionalProperties: false to MCP tool schemas for OpenAI Responses API (PR #10472 by @daniel-lxs)
• Fix: Prevent duplicate tool_result blocks causing API errors (PR #10497 by @daniel-lxs)
• Fix: Add explicit deduplication for duplicate tool_result blocks (#10465 by @nabilfreeman, PR #10466 by @roomote)
• Fix: Use task stored API config as fallback for rate limit (PR #10266 by @roomote)
• Fix: Remove legacy Claude 2 series models from Bedrock provider (#9220 by @KevinZhao, PR #10501 by @roomote)
• Fix: Add missing description fields for debugProxy configuration (PR #10505 by @roomote)
• Fix: Glitchy kangaroo bounce animation on welcome screen (PR #10035 by @objectiveSee)

Roo Code CLI v0.0.45

What's New

Changed

• Major Refactor: Extracted ~1400 lines from App.tsx into reusable hooks and utilities for better maintainability:

• useExtensionHost - Extension host connection and lifecycle management

• useMessageHandlers - Message processing and state updates

• useTaskSubmit - Task submission logic

• useGlobalInput - Global keyboard shortcut handling

• useFollowupCountdown - Auto-approval countdown logic

• useFocusManagement - Input focus state management

• usePickerHandlers - Picker component event handling

• uiStateStore - UI-specific state (showExitHint, countdown, etc.)

• Tool data utilities (extractToolData, formatToolOutput, etc.)

• HorizontalLine component

• Performance Optimizations:

• Added RAF-style scroll throttling to reduce state updates

• Stabilized useExtensionHost hook return values with useCallback/useMemo

• Added streaming message debouncing to batch rapid partial updates

• Added shallow array equality checks to prevent unnecessary re-renders

• Simplified ModeTool layout to horizontal with mode suffix

• Simplified logging by removing verbose debug output and adding first/last partial message logging pattern

• Updated Nerd Font icon codepoints in Icon component

Added

• # shortcut in help trigger for quick access to task history autocomplete

Fixed

• Fixed a crash in message handling
• Added protected file warning in tool approval prompts
• Enabled alwaysAllowWriteProtected for non-interactive mode

Removed

• Removed unused renderLogger.ts utility file

Tests

• Updated extension-host tests to expect [Tool Request] format
• Updated Icon tests to expect single-char Nerd Font icons

Installation

curl -fsSL https://raw.githubusercontent.com/RooCodeInc/Roo-Code/main/apps/cli/install.sh | sh

Or install a specific version:

ROO_VERSION=0.0.45 curl -fsSL https://raw.githubusercontent.com/RooCodeInc/Roo-Code/main/apps/cli/install.sh | sh

Requirements

• Node.js 20 or higher
• macOS (Intel or Apple Silicon) or Linux (x64 or ARM64)

Usage

# Set your API key
export OPENROUTER_API_KEY=sk-or-v1-...

# Run a task
roo "What is this project?" ~/my-project

# See all options
roo --help

Platform Support

This release includes:

• roo-cli-darwin-arm64.tar.gz - Built on Darwin arm64

Note: Additional platforms will be added as needed. If you need a different platform, please open an issue.

Checksum

415ec2612648dff989ed3399a11e07e46e70ec8b6537ad180268f86efc2d6d12  roo-cli-darwin-arm64.tar.gz