Cline

This release introduces the ability to select free Cline models via the ClinePass provider. Key fixes include ensuring accurate diff reporting for str_replace edits and preserving canonical session history during context compaction. Several minor provider and telemetry updates have also been implemented.

This release focuses on improving the ClinePass experience by adding clearer error handling for limit-reached scenarios and enabling users to easily select free Cline models. Additionally, onboarding copy and link handling have been refined for better usability.

This release introduces a significant visual refresh with a new plan/act accent color palette and a restyled chat input for a cleaner look. Key functional updates include improved handling of malformed input from weaker models and setting a default context window for models that don't specify one.

This release significantly improves reliability when using weaker models by gracefully handling their malformed tool calls. Additionally, the system now correctly communicates plan/act mode switches to the model mid-session and fixes an issue causing unexpected restarts when switching modes in empty sessions.

This release significantly improves mode switching reliability, ensuring that when you switch from plan mode to act mode, the full act-mode toolset is immediately available. We also fixed a bug that could cause unapproved plans to start execution due to timing issues with mode toggles.

This release enables ClinePass for all CLI users and introduces Tencent TokenHub as a new supported provider. Key fixes include resolving an issue where high-output models truncated the first prompt due to premature compaction.

This release focuses on stability and clarity by generalizing the model capability warning to ensure it applies correctly across more scenarios. No major new features were introduced in this update.

This release introduces broad support for the new Claude Sonnet 5 model across all major integrated providers. Users can now select and utilize Claude Sonnet 5 through the updated model picker interface.

This release fully removes the ClinePass feature flag, making ClinePass accessible across the entire user interface. Users will now see ClinePass options in onboarding, settings, and promotional banners without needing a feature flag.

This release focuses on infrastructure changes by enabling the ClinePass provider universally for all users. This removes the previous fallback mechanism to the standard Cline provider.

This release focuses on refining the user experience, particularly around ClinePass onboarding and the provider selection interface. Users will notice fewer interruptions after setup and a cleaner provider picker interface.

This release focuses on improving the ClinePass subscription experience during onboarding by providing a fallback URL if the main screen fails to load. Additionally, the UI has been refined to hide promotions for existing subscribers and ensure ClinePass prompts visually match the user's current theme.

This release focuses heavily on refining the ClinePass experience, introducing a new intermediate step before model selection during onboarding. Users will also benefit from improved context compaction accuracy and clearer error messages stemming from an SDK update. Additionally, the UI copy and consistency around the ClinePass branding have been polished.

This release introduces enhanced reasoning capabilities for DeepSeek models by adding support for 'xhigh' effort levels. It also significantly improves the user experience for the ClinePass provider with clearer controls and fixes several bugs related to model resolution and webview state initialization.

This release focuses on stability by rolling back the VS Code extension to the pre-SDK-migration codebase to address regressions reported in version 4.0.0. Existing users of version 4.0.0 will automatically receive this fix.

This release focuses on improving the subscription experience by showing cost coverage and prompting users about ClinePass when credits run low. It also introduces marketplace uninstall support and surfaces bundled plugin skills for easier access.

This major release introduces the SDK-backed VS Code extension runtime, unifying agent coordination, tool execution, and configuration management under a shared SDK session layer. Key new user capabilities include the Customize marketplace for managing Plugins and Skills, and queued prompts in chat. Numerous fixes address stability in terminal execution and SDK budgeting, alongside significant architectural changes for improved provider and model configuration consistency.

This release introduces support for the SAP AI Core provider and adds a helpful token count display to the status bar. Several key improvements were made to model handling, including better caching for OpenRouter and routing fixes for LiteLLM, alongside general stability enhancements.

This release focuses on cost visibility and metadata accuracy. Costs are now hidden for free Cline models, and a critical bug affecting Z.ai model metadata resolution has been fixed. Additionally, the previous display behavior for model selection elements has been restored.

This release introduces a new ClinePass onboarding flow allowing users to select specific models and refreshes the hub dashboard with better organization. Key improvements include immediate application of auto-approve toggles and hardened guidance for faster multi-tool execution.

This release introduces enhanced command-line management with the new `cline skill` command for managing skills and a streamlined wizard command for quicker MCP server setup. Error handling has also been improved, particularly for OAuth authorization failures, and the CLI now provides clearer feedback for invalid commands.

This release focuses on reverting recent changes to the model selection interface. Specifically, the expandable sections in the model picker and the ClinePass models have been restored to their previous state.

This release introduces ClinePass model support and enhanced MCP server integration for plugins. Key improvements include better handling of large file reads and capped tool output to manage context limits, alongside several fixes for patching, command execution, and search tools.

This release introduces the ability for plugin commands to submit prompts to the agent and adds configuration support for overriding the API base URL. Key fixes include resolving issues with truncated tool output and suppressing flickering console windows on Windows.

This release focuses on resolving critical compatibility issues for users on VS Code 1.123+ utilizing the Anthropic provider. It ensures both the Anthropic and Vertex AI providers function correctly by updating underlying SDK dependencies to support the Node 24 runtime.

This release focuses on stability and compatibility, primarily restoring the Anthropic provider functionality for recent VS Code versions. It also includes necessary updates to correctly handle the DeepSeek V4 reasoning format.

This release introduces support for using configured agents as subagent tools, enhancing multi-agent workflows. Key fixes include resolving configuration issues with Vertex AI GCP and the Azure Foundry API version. Additionally, OAuth management has been centralized within the SDK.

This release introduces support for the new Claude Fable 5 model, expanding your available AI options. It also resolves critical issues related to MiniMax M3 thinking controls. Additionally, the model selection interface has been refined by cleaning up the Codex model list.

This release introduces support for the new Claude Fable 5 model, expanding the available AI capabilities. Additionally, a critical routing issue affecting MiniMax M3 thinking controls has been resolved.

This release introduces new configuration options, including a global auto-update setting and support for Vertex AI ADC with tool use. Several critical bugs were resolved, specifically addressing scrolling issues in responses and session handling for connectors.

This minor release introduces a new debug section within settings intended for Cline testers. It also resolves a critical bug where the initial walkthrough steps were not loading correctly in the VS Code extension.

This release introduces support for the latest Fireworks AI serverless models, setting Kimi K2.6 as the new default. Several critical bugs related to MCP server list management and Fireworks model caching have been resolved.

This release focuses on improving plugin management by renaming installed plugin wrappers to clearly reflect their source, making them much easier for users to identify. No major new features or bug fixes were noted in this specific update.

This release focuses on improving the reliability of the Command Line Interface (CLI) updates. The auto-update process has been fixed to ensure updates apply correctly while maintaining the user's chosen release channel.

This release focuses on improving integration reliability and ensuring the local environment uses the latest dependencies. Key fixes include ensuring Slack replies thread correctly and clearing task indicators immediately upon cancellation.

This release focuses heavily on stability, particularly around the interactive CLI and Hub daemon lifecycle. Key fixes address session recovery in the CLI and prevent premature daemon shutdowns during request abortions. Additionally, the Telegram connector now supports user authorization via a new flag.

This release introduces support for the new MiniMax M3 model, expanding available AI capabilities. Additionally, critical security vulnerabilities in the VS Code extension dependencies have been patched.

This release introduces significant plugin management capabilities, allowing users to install official plugins and manage bundled skills directly within settings. Key new integrations include support for Slack socket mode and custom base URLs for Anthropic providers. Additionally, a critical fix was implemented for OAuth token migration for legacy users.

This release focuses on resolving compatibility issues with recent VS Code updates. Specifically, it fixes problems related to file mentions and workspace searching when using VS Code version 1.122 and newer.

This release focuses on improving reliability for file mentions, specifically addressing issues where the @ file-mention feature failed in environments like VS Code Remote SSH. The fix ensures file searching continues to work even when the primary indexing tools are unavailable.

This release significantly expands model compatibility by adding support for GPT-5.5, DeepSeek V4, and Gemini 3.5 Flash across various providers. It also introduces a new webhook integration for LG dashboard flows and resolves an endpoint handling issue for Claude models on Vertex AI.

This release focuses on improving the user experience during session management. We introduced a loading dialog for session resumption and significantly sped up the `/clear` command by optimizing session creation timing.

This release focuses on improving user experience during configuration changes by adding loading indicators and updating how the ask question tool prompt is displayed. Additionally, users can now manually trigger immediate updates to the latest version.

This release introduces native Google authentication support for Vertex Gemini models, allowing users to access the full model list. It also resolves a critical bug affecting ChatGPT OAuth token limits and improves session history clarity by including tool names in result blocks.

This release significantly enhances provider support by adding Poolside and Gemini 3.5 Flash, while improving session management to keep interactive sessions alive longer. Key fixes include restoring AWS Bedrock profile authentication and optimizing global settings loading performance.

This release focuses heavily on performance and stability improvements, including faster CLI startup and configuration toggles. Key user experience updates include restoring fuzzy ranking for file mentions and ensuring interactive sessions remain active after task cancellation. Additionally, prompts starting with a dash are now correctly accepted.

This release focuses on improving configuration diagnostics and fixing critical bugs related to token counting and cloud provider setup. Key changes include persistent user linking in the Telegram connector and ensuring accurate token usage reporting by fixing double-counting issues.

This release introduces new integration capabilities by adding SAP AI Core support for more hosted models. A key fix addresses an issue where the server restart button could be incorrectly enabled. Additionally, the startup experience in the VS Code extension has been streamlined by removing the Kanban launch modal.

This release focuses on improving startup performance by skipping unnecessary OAuth refreshes during session initialization. Additionally, the available ChatGPT models have been synchronized with the Codex provider list to better match user subscription tiers.

This minor update focuses on correcting the available model list for the ChatGPT provider. Users will now see the correct codex variants and subscription models (gpt-5.2, gpt-5.4, gpt-5.4-mini) listed when configuring ChatGPT.

This release introduces the ability to view plugin-provided tools and slash commands directly within the CLI settings dialog. Additionally, settings related to plugin tools and configuration reloading are now correctly preserved when toggling options.

This release focuses on visual clarity and stability for plugin usage. We have enhanced the contrast of the light theme TUI elements, including chat and status bars. Additionally, a critical bug preventing plugin tools from working in production npm builds has been resolved.

This release introduces isolated task execution via the new --worktree flag, allowing users to resume experiments in clean environments. Key fixes include resolving issues with dropped macOS screenshots due to Unicode path problems. Additionally, the system prompt has been refined for better guidance on tool usage and verification steps.

This release focuses on improving the reliability and performance of file operations, particularly around @-mentions. Key updates include enabling cache control for Qwen models via OpenRouter and fixing validation issues for MCP servers.

This minor release focuses on correcting an issue within the Terminal User Interface (TUI). Specifically, it fixes an incorrect display of token counts that were previously showing inflated numbers.

This minor release focuses on stability and correctness for command-line users and TUI users. Key updates include fixing Windows compatibility issues with release cleanup scripts and correcting a message displayed during kanban migration.

This release introduces the brand new Cline CLI, which is built upon our updated SDK. Users will benefit from the snappy new Text User Interface (TUI) integrated directly into the command line experience.

This release focuses on restoring critical functionality by bringing back VS Code foreground terminal support and its settings. Additionally, the tool now supports the newest models from OpenAI, SAP AI Core, and Z AI.

This release introduces support for the new GPT-5.5 model for eligible users. It also resolves an issue where incorrect fallback content was displayed in the welcome banner. Significant improvements were made to memory diagnostics and logging to aid in debugging performance issues.

This release introduces significant enterprise integration by enabling remote, managed global skills with full UI support. It also improves stability by fixing Out-Of-Memory crashes during long sessions and enhances user feedback with more detailed error messages in the chat interface. Furthermore, task execution has been streamlined by defaulting all commands to background mode, removing the dependency on the VS Code integrated terminal.

This release introduces significant new capabilities, including support for the Claude Opus 4.7 model and Azure Blob Storage integration. Key fixes address issues with stuck command outputs and a security vulnerability related to action injection. Users will also benefit from improved remote configuration discovery.

This release introduces a new dedicated UI to clearly inform users when their spend limits have been reached. Additionally, a bug affecting the accuracy of line ranges displayed in the chat UI for file reads has been resolved.

This release introduces the experimental "Lazy Teammate Mode" toggle and enhances file reading capabilities with chunked support in the `read_file` tool. Several minor issues were resolved, including cleaning up system prompt usage in headless mode and polishing notification hook functionality.

This release introduces the Cline Kanban launch modal in the webview and sets Kanban as the default launch experience for the CLI. Key improvements include new loop detection to save tokens and a setting to disable feature tips in the chat.

This release focuses on performance enhancements, specifically improving latency for remote workspace usage. No major new features were introduced, and example hooks were removed in favor of directing users to the official documentation.

This release introduces dynamic free model detection for the Cline API and adds helpful feature tips tooltips during the thinking state. Several bugs were fixed, including improving error messaging for logged-out users and ensuring correct context window handling in LiteLLM. Performance is also improved via a new file read deduplication cache.

This release introduces W&B Inference by CoreWeave as a new supported API provider with 17 models. Key fixes address stability issues in the Claude Code Provider and ensure tool handlers return graceful errors instead of crashing. Parallel tool calling support has also been improved for OpenRouter and Cline.

This release introduces support for the new Anthropic Opus 4.6 fast mode variants, expanding model options for users. Several critical bugs were fixed, including issues with native tool placeholder interpolation and stability problems on Windows. Additionally, user experience improvements include requiring consent for Markdown image loading.

This release introduces the highly anticipated GPT-5.4 models for ChatGPT subscribers, significantly expanding available capabilities. Developers will benefit from the new Notification hook for better boundary management. Additionally, stability has been improved with more reliable handling of HTTP MCP reconnects.

This release introduces significant new capabilities with the addition of the Cline SDK API for custom application integration and support for the new Codex 5.3 model. Several key bugs were resolved, including a fix related to OpenAI Codex configuration and improved accuracy in path checking.

This release introduces significant configuration flexibility by adding support for skills and file-based agent configurations via the new AgentConfigLoader. Key fixes address stability issues, including a reasoning delta crash and compatibility problems with Gemini 3.1 Pro. Users will also benefit from reduced response latency due to websocket preconnection.

This release introduces support for the new Gemini-3.1 Pro Preview model. Users can now leverage this latest model for their coding tasks. Full details are available in the linked changelog.

This release introduces the new /skills slash command in the CLI, allowing users to easily view and manage their installed skills. Several critical bugs have been resolved, including issues related to context window management, file writing retries, and the default model selection.

This release introduces access to the zai GLM 5 Free promotion. A key fix addresses the visibility and usability of the reasoning trace within the chat interface, ensuring users can easily view and collapse the thinking process.

This release introduces access to the zai GLM 5 Free promotion. Additionally, the reasoning trace visibility in the chat has been restored and the thinking row UX has been improved for better readability and control over the displayed reasoning.

This release focuses primarily on security and stability by resolving 17 security vulnerabilities across several dependencies. Additionally, a minor usability issue was fixed where extension banners no longer require user interaction to appear upon launch.

This release focuses primarily on stability and user experience improvements. The main visible change is the resolution of UI/UX issues affecting the minimax model family.

This release focuses on stability and correctness by addressing known issues within the Minimax model family. Users should experience more reliable performance when utilizing these models.

This release introduces the Minimax 2.5 Free Promo for users. Additionally, a critical bug affecting response chaining with the OpenAI Responses API has been resolved.

This release is an automated CLI build from a specific commit (024bb65). No specific user-facing features, bug fixes, or improvements were detailed in these release notes beyond the build artifact itself.

This release introduces significant new capabilities, including native subagent support, parallel tool calling for Amazon Bedrock, and an experimental double-check feature for task verification. Several critical bugs were fixed across the CLI, VS Code Web, and Terminal, alongside UX improvements like moving reasoning effort into model settings.

This release appears to be a routine build update from a specific commit (6278382). No user-facing features or bug fixes were explicitly detailed in these notes, suggesting it might be a maintenance or internal build.

This release is an automated CLI build from a specific commit (a03642b). No user-facing features, bug fixes, or improvements were explicitly detailed in these release notes.

This release is an automated CLI build from commit b2bfc3d. No specific user-facing features, fixes, or improvements were detailed in these release notes.

This release appears to be a routine automated build from a specific commit (6b07e8c). No user-facing features, bug fixes, or improvements were explicitly detailed in these notes.

This release is a direct build from commit 4d455ea. No specific user-facing features, fixes, or improvements were detailed in these release notes, only the installation instructions for this specific build.

This minor release focuses on stability by addressing a specific issue related to Opus 4.6 when utilizing the bedrock provider. Users should experience more reliable operation with this configuration.

This release introduces Cline CLI 2.0 and expands model availability, adding Anthropic Opus 4.6, Minimax-2.1, Kimi-k2.5, and Codex-5.3. Several critical bugs were fixed, including issues with reading large files and crashes in price input fields, alongside a UX change making skills permanently enabled.

This minor release focuses on stability by addressing an issue within the responses API. Users should experience more reliable API interactions following this update.

This release focuses on a change to model availability, specifically removing the grok model from the free tier. Users should note this change in their access capabilities.

This release introduces support for the new OpenAI gpt-5.2-codex model, making it available directly in the model selection interface. Users can now leverage this latest model for their coding tasks.

This release introduces significant new capabilities, including support for the gpt-5.2-codex model and a new create-pull-request skill. Several critical bugs related to provider selection and tool call handling have also been resolved.

This release focuses primarily on stability and compatibility fixes, addressing issues with model selection, streaming API responses, and improving the search functionality for workflow slash commands. It also introduces a phased rollout for the Responses API usage.

This release introduces the ability to configure an OTEL collector at runtime for enhanced observability. We have also improved image display in MCP responses and ensured remote MCP server settings now automatically sync to your local configuration.