Cline core
ComponentUpdates related to the core component of Cline.
All CORE Features
- Enabled showing plugin-provided tools and slash commands in the CLI settings dialog by hydrating them through the sandbox.(cli-v3.0.5)
- Introduced the new Cline Command Line Interface (CLI)(cli-v3.0.0)
- The new CLI includes a snappy Text User Interface (TUI)(cli-v3.0.0)
- Added a dedicated "Spend Limit Reached" error UI when spend caps are hit(v3.78.0)
- Added Cline SDK API interface for programmatic access to Cline features and tools, enabling integration into custom applications.(v3.67.1)
- Added support for the Codex 5.3 model.(v3.67.1)
- Added Gemini-3.1 Pro Preview model support.(v3.66.0)
- Added zai GLM 5 Free promotion access.(v3.64.0)
- Added zai GLM 5 Free promotion access.(v3.63.0)
- Added Minimax 2.5 Free Promo(v3.59.0)
- Added OpenAI gpt-5.2-codex model to the model picker(v3.51.0)
All CORE Bug Fixes
- Fixed issue where the CLI performed an unnecessary ChatGPT OAuth model refresh on session startup, improving launch speed.(cli-v3.0.7)
- Fixed the ChatGPT provider model list to correctly include codex variants and the gpt-5.2, gpt-5.4, and gpt-5.4-mini subscription models.(cli-v3.0.6)
- Fixed issue where hydrated plugin tools and config reload options disappeared after toggling settings.(cli-v3.0.5)
- Fixed token count display showing inflated numbers in the TUI.(cli-v3.0.2)
- Fixed CLI release cleanup scripts to function correctly on Windows.(cli-v3.0.1)
- Corrected the wording of the kanban migration notice displayed in the TUI.(cli-v3.0.1)
- Fixed showing incorrect line ranges in the chat UI for actual read_file operations(v3.78.0)
- Fixed an issue with OpenAI Codex by ensuring the `store` parameter is set to `false`.(v3.67.1)
- Corrected path containment checks by using `isLocatedInPath()` instead of unreliable string matching.(v3.67.1)
- Restored reasoning trace visibility in chat and improved the thinking row UX so reasoning is visible initially and collapsible after completion.(v3.64.0)
- Restored visibility of the reasoning trace in the chat interface.(v3.63.0)
- Fixed UI/UX issues specifically related to the minimax model family.(v3.61.0)
- Fixed issues related to the Minimax model family.(v3.60.0)
- Fixed response chaining when using OpenAI's Responses API(v3.59.0)
- Fixed an issue specific to Opus 4.6 when using the bedrock provider.(v3.57.1)
- Fixed a bug affecting the responses API.(v3.53.1)
- Removed the grok model from the free tier.(v3.53.0)
- Removed GLM 4.6 from the list of available free models.(v3.46.1)
Releases with CORE Changes
cli-v3.0.71 fixThis 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.
cli-v3.0.61 fixThis 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.
cli-v3.0.51 feature1 fixThis 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.
cli-v3.0.21 fixThis 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.
cli-v3.0.12 fixesThis 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.
cli-v3.0.02 featuresThis 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.
v3.78.01 feature1 fixThis 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.
v3.75.0This 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.
v3.67.12 features2 fixesThis 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.
v3.66.01 featureThis 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.
v3.64.01 feature1 fixThis 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.
v3.63.01 feature1 fixThis 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.
v3.61.01 fixThis 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.
v3.60.01 fixThis 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.
v3.59.01 feature1 fixThis 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.
v3.57.11 fixThis 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.
v3.53.11 fixThis minor release focuses on stability by addressing an issue within the responses API. Users should experience more reliable API interactions following this update.
v3.53.01 fixThis 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.
v3.51.01 featureThis 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.
v3.46.11 fixThis minor release focuses on updating the available free models by removing GLM 4.6. Users should note the change in the free model selection.