- Introduce "Fix using DevChat" as a preferred quick fix action
- Rename existing quick fix command to "Ask DevChat"
- Update package.json and TypeScript files to reflect new commands
The code changes include adding a new command to start the local service in the package.json file. This command will allow users to start the local service for DevChat.
Recent repository commits indicate that local service management has been implemented, including start and stop functionality, error handling, and integration tests. The commits also mention the integration of local service port discovery and setup, as well as updating the DevChatClient to use a dynamic port from the environment.
Based on the code changes and recent commits, the suggested commit message is "feat: Add command to start local service".
- Removed DevChat.InstallCommandPython from package.json commands array
- Commented out DevChat.InstallCommandPython execution in statusBarView.ts
- No longer triggers Python command installation in statusBarItem creation
- Implemented a new Quick Fix command in commands.ts and package.json
- Added the collapseFileExcludeSelectRange function for code analysis
- Registered the Quick Fix provider to suggest fixes via AI analysis
- Updated package.json to include support for claude-3 models
- Removed references to claude-2 models in extension and ApiKeyManager
- Added API functionality and configured default settings for new models
- Removed api_secret attribute from package.json
- Ensured no default or descriptions remained for api_secret
- API secrets should be managed via environment variables or secrets manager
- Added "max_input_tokens" property to configuration settings
- Adjusted default values for "max_tokens" to ensure proper limit
- Renamed "gpt-4-1106-preview" to "gpt-4-turbo-preview" for consistency
- Remove topic-related views, commands, and handlers from the codebase
- Refactor code to align with the new unified topic interaction method
- Streamline UI by eliminating unnecessary elements and consolidating views
- Add Model.CodeLlama-70b config settings support
- Implement Model.Mixtral-8x7B and Model.Minimax-abab6 support
- Modify UI and API integration to facilitate new model selections
- Remove deprecated 1106 and 16k GPT-3.5 model configs
- Update GPT-3.5 config to latest stable version
- Update Claude, Xinghuo, GLM, ERNIEbot to latest versions
- Adjust default model to Claude 2.1
- Validate and test latest model integrations
- Updated the ChatMark component to accept a new prop, messageDone. The component uses this prop to decide whether to disable its widgets.
- The MessageMarkdown component now passes the messageDone prop to the ChatMark component.
- The MessageBody component and the MessageList component have been updated to provide the messageDone prop for the MessageMarkdown component.
- Update package.json to include mdast dependencies
- Import necessary functions and types from mdast-util
- Update logic to use mdast functions and types
- Update rendering logic to work with new mdast structure
- Split markdown content by ```step blocks
- Pass step content to Step component
- Step component handles collapsing and highlighting
- Support Step and step case insensitive
- Extract first line starting with # as step title
- Use last line with # Done to show step completed
