Conversation
- Convert all single quotes to double quotes for consistency - Update import statements, object properties, and string literals - Maintain existing code structure and functionality while ensuring consistent string quote usage throughout the component
This commit introduces integration with external coding agents through the Agent Client Protocol (ACP). Users can now configure external CLI tools like iFlow, Gemini CLI, Codex, or Claude as the coding agent instead of using the built-in adk-rust based agent. The feature includes: - Configuration for external agent type, command, and transport mode - Support for stdio and websocket transport protocols - Automatic fallback to built-in agent on external agent failure - Enhanced configuration examples for common external agents
Remove WebSocket dependencies and refactor ACP client to provide real-time message streaming. The execute_with_external_agent function now returns a channel for agent messages alongside the result future, enabling better UI integration for live agent output.
- Remove CLI config argument and example config file - Add config_commands.rs with Tauri commands for config management - Create SettingsPanel.jsx component for GUI configuration - Update config loading to use standardized config path - Add embedding configuration support</think> feat: Add GUI settings panel and refactor config loading - Remove CLI config argument and example config file - Add config_commands.rs with Tauri commands for config management - Create SettingsPanel.jsx component for GUI configuration - Update config loading to use standardized config path - Add embedding configuration support
Add comprehensive console.log and println! statements throughout the PM message sending pipeline to help with debugging. Fix a bug where the LLM request was sending an empty model name instead of using the configured model. Improve error handling by adding more context to error messages and logging them properly.
- Display welcome message when first entering PM agent mode - Add colorful action buttons with icons for PM agent interactions - Enhance project startup notifications with URL/port information - Support Chinese language responses for PM agent - Check for running projects before attempting to start
Implement backend commands to check path existence and create projects at specific locations. Replace the open directory flow with a comprehensive project creation modal that includes path validation, directory creation, and project initialization. Increase default window size to accommodate the new UI elements.
- Add isExecuting flag to track execution state accurately - Update iteration status for pause/resume/feedback scenarios - Increase request timeout from 5 to 50 minutes - Preserve current iteration status while executing
- Use absolute paths for iteration workspace and directory methods - Add Windows-specific command execution with cmd /C - Replace string formatting with PathBuf for proper path joins - Fix Unicode character counting for display truncation - Convert relative paths to absolute with fallback logic
- Add PM agent with LLM integration for post-delivery chat - Enhance memory queries with category, stage, and limit filters - Support both iteration and project memory in search - Improve project deletion cleanup and file handle release - Add processing indicator for PM agent responses
The delete project function now only removes the project from the registry without touching any files. This removes the complex file deletion logic, process stopping, and retry mechanisms that were prone to issues with locked files on Windows. The UI is simplified to a single delete action.
Add validation for required settings and test with actual API request to verify end-to-end connectivity rather than just client creation.
- Add create_iteration tool definition and documentation - Implement backend handling for creating new iterations - Add frontend action handler for iteration creation - Update type definitions for new iteration fields
Add parsing for GOTO_STAGE signals embedded in tool error messages. The format "GOTO_STAGE:stage:reason" enables tools to trigger jumps to specific stages with contextual warning messages displayed to users.
This implements real-time streaming of PM Agent responses, displaying chunks as they're generated similar to ChatGPT. The change improves UX by providing immediate feedback during agent responses. Key implementation details: - Enabled SSE streaming mode in stage executor - Modified PM message handling to process and emit chunks in real-time - Added streaming start/end signal handling in the frontend - Split PM Agent streaming logic from regular agent streaming - Updated state management to support incremental message updates Documentation updates reflect changes in panel structure and TypeScript migration.
Improves debugging visibility for the PM agent workflow by adding console logging throughout the message sending process and artifact loading. Also fixes iteration state management when artifacts are requested by refreshing the latest iteration.
Avoid loading the base iteration since the inheritance mode is now passed as a parameter instead of being extracted from the loaded base iteration data.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.