- Add new command registration and menu item
- Add new code action type and command ID
- Add support prompt config for adding code to context
- Add message handling in webview for setting chat box content
- Add logic to append selected code to existing chat input
Replace Create React App with Vite build system
Add ESLint configuration and improve TypeScript types
Create VSCode UI component mocks for better testing
Update test files with proper async handling
Add Tailwind CSS integration
Fix accessibility by adding ARIA roles
Change ExperimentId type to be value-based rather than key-based
Make experiment record types more strict with proper typing
Pass full experiment config object instead of single boolean flag
Update type definitions and usages across codebase
- Add experiments.ts to manage experimental features
- Refactor experimental diff strategy into experiments system
- Add UI components for managing experimental features
- Add tests for experimental tools
- Update system prompts to handle experiments
Implements automatic approval for mode switching operations when enabled, following
existing auto-approval patterns in the codebase.
Implementation:
- Added `alwaysAllowModeSwitch` to state management
- Updated `isAutoApproved` function in ChatView to handle mode switch requests
- Added mode switch option to AutoApproveMenu with appropriate handler
- Integrated with existing auto-approval flow
Tests:
- Added three test cases in ChatView.auto-approve.test.tsx:
1. Verifies mode switch auto-approval when enabled
2. Verifies no auto-approval when mode switch setting is disabled
3. Verifies no auto-approval when global auto-approval is disabled
The implementation follows existing patterns for other auto-approve features
(read, write, browser, etc.) to maintain consistency in the codebase.
- Replace console.error with outputChannel.appendLine for better error visibility
- Add detailed error information using JSON.stringify with full error properties
- Improve error message formatting and consistency across all error handlers
Adds ability to fix code within the context of an active task instead of starting a new one. This allows for more efficient workflow when already working with Roo.
Add new FIX_IN_CURRENT_TASK code action and command
Enhance ClineProvider to support context-aware code fixing
Update tests to verify new action functionality
- Rename customPrompts to customModePrompts for mode-specific prompts
- Add new customSupportPrompts type for support action prompts
- Update types to be more specific (CustomModePrompts and CustomSupportPrompts)
- Fix all related tests and component implementations
- Rename enhance-prompt.ts to single-completion-handler.ts for better clarity
- Refactor enhancement logic to be more generic and reusable
- Update prompt template handling to use template literals
- Adjust tests and imports accordingly
- Rename codeActionPrompt to supportPrompt for better clarity
- Move enhance prompt functionality into support prompts system
- Add ENHANCE tab alongside other support prompt types
- Update UI to show enhancement configuration in ENHANCE tab
- Update tests to reflect new unified structure
This change simplifies the prompt system by treating enhancement as another type of support prompt rather than a separate system.
- Move code action prompts from core/prompts to shared/support-prompt
- Migrate enhance prompt functionality from modes to support-prompt
- Add UI for managing code action prompts in PromptsView
- Update types and interfaces for better prompt management
Add ability to provide custom input when using code actions
Make code action templates customizable and resettable
Refactor code action handling for better maintainability
Add state management for utility prompts
- Extract prompt templates into constants
- Add createPrompt utility for template string handling
- Consolidate code action handling in ClineProvider
- Update tests to use new parameter object pattern
- Add openAiUseAzure flag to force Azure OpenAI client initialization
- Add "Use Azure" checkbox in API settings UI
This change improves Azure OpenAI configuration flexibility by allowing users to explicitly opt-in to Azure client, regardless of the base URL pattern.
- Rename openAiCusModelInfo to openAiCustomModelInfo across all files for better readability
- Update related variable names and references to maintain consistency
- Affects OpenAI provider, ClineProvider, WebviewMessage, API interfaces, and UI components
Adds support for configuring custom OpenAI-compatible model capabilities and pricing, including:
Max output tokens
Context window size
Image/computer use support
Input/output token pricing
Cache read/write pricing
- Added `updateDiffStrategy` method to dynamically adjust the diff strategy based on the current state and experimental settings.
- Updated ClineProvider to call `updateDiffStrategy` when the experimental diff strategy is modified, ensuring real-time updates in the Cline instance.
