Release v3.43.0

[3.43.0] - 2026-01-23

• 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)
• Improved context condensation with environment details, accurate token counts, and lazy evaluation for better performance (PR #10920 by @hannesrudolph)
• Move condense prompt editor to Context Management tab for better discoverability and organization (PR #10909 by @hannesrudolph)
• Update Z.AI models with new variants and pricing (#10859 by @ErdemGKSL, PR #10860 by @ErdemGKSL)
• Add pnpm install:vsix:nightly command for easier nightly build installation (PR #10912 by @hannesrudolph)
• Fix: Convert orphaned tool_results to text blocks after condensing to prevent API errors (PR #10927 by @daniel-lxs)
• Fix: Auto-migrate v1 condensing prompt and handle invalid providers on import (PR #10931 by @hannesrudolph)
• 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)
• Fix: Correct Gemini 3 pricing for Flash and Pro models (#10432 by @rossdonald, PR #10487 by @roomote)
• Fix: Skip thoughtSignature blocks during markdown export for cleaner output (#10199 by @rossdonald, PR #10932 by @rossdonald)
• Fix: Duplicate model display for OpenAI Codex provider (PR #10930 by @roomote)
• Remove diffEnabled and fuzzyMatchThreshold settings as they are no longer needed (#10648 by @hannesrudolph, PR #10298 by @hannesrudolph)
• Remove MULTI_FILE_APPLY_DIFF experiment (PR #10925 by @hannesrudolph)
• Remove POWER_STEERING experimental feature (PR #10926 by @hannesrudolph)
• Remove legacy XML tool calling code (getToolDescription) for cleaner codebase (PR #10929 by @hannesrudolph)

Release v3.42.0

[3.42.0] - 2026-01-22

• Added UI to track your ChatGPT usage limits in the OpenAI Codex provider (PR #10813 by @hannesrudolph)
• Removed deprecated Claude Code provider (PR #10883 by @daniel-lxs)
• Streamlined codebase by removing legacy XML tool calling functionality (#10848 by @hannesrudolph, PR #10841 by @hannesrudolph)
• Standardize model selectors across all providers: Improved consistency of model selection UI (#10650 by @hannesrudolph, PR #10294 by @hannesrudolph)
• Enable prompt caching for Cerebras zai-glm-4.7 model (#10601 by @jahanson, PR #10670 by @app/roomote)
• Add Kimi K2 thinking model to VertexAI provider (#9268 by @diwakar-s-maurya, PR #9269 by @app/roomote)
• Warn users when too many MCP tools are enabled (PR #10772 by @app/roomote)
• Migrate context condensing prompt to customSupportPrompts (PR #10881 by @hannesrudolph)
• Unify export path logic and default to Downloads folder (PR #10882 by @hannesrudolph)
• Performance improvements for webview state synchronization (PR #10842 by @hannesrudolph)
• Fix: Handle mode selector empty state on workspace switch (#10660 by @hannesrudolph, PR #9674 by @app/roomote)
• Fix: Resolve race condition in context condensing prompt input (PR #10876 by @hannesrudolph)
• Fix: Prevent double emission of text/reasoning in OpenAI native and codex handlers (PR #10888 by @hannesrudolph)
• Fix: Prevent task abortion when resuming via IPC/bridge (PR #10892 by @cte)
• Fix: Enforce file restrictions for all editing tools (PR #10896 by @app/roomote)
• Fix: Remove custom condensing model option (PR #10901 by @hannesrudolph)
• Unify user content tags to <user_message> for consistent prompt formatting (#10658 by @hannesrudolph, PR #10723 by @app/roomote)
• Clarify linked SKILL.md file handling in prompts (PR #10907 by @hannesrudolph)
• Fix: Padding on Roo Code Cloud teaser (PR #10889 by @app/roomote)

Release v3.41.3

[3.41.3] - 2026-01-18

• Fix: Thinking block word-breaking to prevent horizontal scroll in the chat UI (PR #10806 by @roomote)
• Add Claude-like CLI flags and authentication fixes for the Roo Code CLI (PR #10797 by @cte)
• Improve CLI authentication by using a redirect instead of a fetch (PR #10799 by @cte)
• Fix: Roo Code Router fixes for the CLI (PR #10789 by @cte)
• Release CLI v0.0.48 with latest improvements (PR #10800 by @cte)
• Release CLI v0.0.47 (PR #10798 by @cte)
• Revert E2E tests enablement to address stability issues (PR #10794 by @cte)

Roo Code CLI v0.0.49

What's New

Added

• Output Format Options: New --output-format flag to control CLI output format for scripting and automation:
• text (default) - Human-readable interactive output
• json - Single JSON object with all events and final result at task completion
• stream-json - NDJSON (newline-delimited JSON) for real-time streaming of events
• See json-events.ts for the complete event schema
• New JsonEventEmitter for structured output generation

Installation

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

Or install a specific version:

ROO_VERSION=0.0.49 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

# Run a task
roo "What is this 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

d8a0b8f8689d747906713a93663b74f90aa5af59c41f6bcc9eee0881f58bb97a  roo-cli-darwin-arm64.tar.gz

Roo Code CLI v0.0.48

What's New

Changed

• Simplified authentication callback flow by using HTTP redirects instead of POST requests with CORS headers for improved browser compatibility

Installation

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

Or install a specific version:

ROO_VERSION=0.0.48 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

# Run a task
roo "What is this 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

c756adba40328b5bcd5f084b2356ae4aab107b4caef74e49961864bd415138be  roo-cli-darwin-arm64.tar.gz

Roo Code CLI v0.0.47

What's New

Added

• Workspace flag: New -w, --workspace <path> option to specify a custom workspace directory instead of using the current working directory
• Oneshot mode: New --oneshot flag to exit upon task completion, useful for scripting and automation (can also be saved in settings via CliSettings.oneshot)

Changed

• Skip onboarding flow when a provider is explicitly specified via --provider flag or saved in settings
• Unified permission flags: Combined -y, --yes, and --dangerously-skip-permissions into a single option for Claude Code-like CLI compatibility
• Improved Roo Code Router authentication flow and error messaging

Fixed

• Removed unnecessary timeout that could cause issues with long-running tasks
• Fixed authentication token validation for Roo Code Router provider

Installation

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

Or install a specific version:

ROO_VERSION=0.0.47 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

# Run a task
roo "What is this 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

32008b2ddb6b28dc59f1176eb2f4c845b7d8be99960f2d016e7fa6a3e53375b6  roo-cli-darwin-arm64.tar.gz

Release v3.41.2

[3.41.2] - 2026-01-16

• Add button to open markdown in VSCode preview for easier reading of formatted content (PR #10773 by @brunobergher)
• Fix: Reset invalid model selection when using OpenAI Codex provider (PR #10777 by @hannesrudolph)
• Fix: Add openai-codex to providers that don't require an API key (PR #10786 by @roomote)
• Fix: Detect Gemini models with space-separated names for proper thought signature injection in LiteLLM (PR #10787 by @daniel-lxs)

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)