UI refactor #36
Merged
UI refactor #36
Conversation
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
- Added DebugManager class to handle debug events and UI interactions. - Created session-manager.ts to manage chat sessions and their states. - Introduced tools-manager.ts for managing tools configuration. - Developed main.ts to initialize the chat application and manage message sending. - Updated index.html to include the new bundle.js script. - Defined types for messages, tools, chat sessions, and debug events in types.ts. - Adjusted tsconfig.json to support new TypeScript features and configurations.
- Deleted tools-manager.ts and moved its logic to tools.ts. - Updated tsconfig.json to include new tools.ts file. - Implemented new ApiManager, ChatUIManager, DebugManager, and SessionManager classes in their respective files. - Enhanced API interactions for session management, tool loading, and debug event handling. - Improved UI management for chat messages and debug events. - Added error handling and loading states for better user experience.
Removing ChatUIManager and replacing it with ChatManager; update imports and initialization in main app.
Add WebScraper tool and integrate with WebLoader for advanced web scraping
Refactor WebScraper output to use 'content' key instead of 'text'
Refactor WebLoader tests to remove url_pattern and update file assertions
Enhance RAG system with multi-stage retrieval, semantic chunking, query expansion, and result fusion - Added a comprehensive RAG System Enhancement Roadmap document detailing improvements to the hybrid knowledge graph and embeddings architecture. - Implemented an enhanced retrieval pipeline with multi-stage retrieval and graph-based context enrichment. - Improved WebLoader with semantic chunking and content deduplication. - Introduced query expansion and intent detection capabilities. - Developed a result fusion mechanism to combine multiple retrieval strategies. - Added performance monitoring and caching to optimize repeated queries. - Enhanced the GitHub search tool to integrate all new features. - Established a comprehensive testing strategy for reliability and safety. - Updated MCPSession to parse environment variables, allowing for dynamic environment configuration.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This pull request introduces several enhancements across different areas of the project, including build system improvements, agent functionality updates, and documentation enhancements. Key changes include the addition of a new
WebScrapertool, a revamped build process usingesbuild, and optimizations to theWebLoaderclass for better web scraping capabilities.Environment and Configuration Updates:
.env.example: AddedMCP_GITHUB_TOKENandMCP_ATLASSIAN_TOKENfor authentication, enabling integration with GitHub and Atlassian services.config/mcp.template.json: Updated environment variable handling to allow dynamic substitution from the.envfile usingThis pull request introduces several enhancements across different areas of the project, including build system improvements, agent functionality updates, and documentation enhancements. Key changes include the addition of a newWebScrapertool, a revamped build process usingesbuild, and optimizations to theWebLoader` class for better web scraping capabilities.notation.
Build System Enhancements:
build.js: Introduced a new build script usingesbuildfor efficient bundling and watching ofsrc/ui/main.ts. This replaces the previous TypeScript compilation workflow.package.json: Updated scripts to integrate the new build system (ui:build,ui:dev,ui:clean,ui:copy-assets) and addedesbuildas a development dependency.Agent Functionality Improvements:
src/agent.py: Added a newWebScrapertool to the agent's toolset, enabling advanced web scraping capabilities. [1] [2]src/core/mcp/session.py: Implemented_parse_envto dynamically resolve environment variables during session initialization, improving flexibility and reducing hardcoded values. [1] [2]Web Scraper Tool Implementation:
src/libs/dataloader/web.py: Enhanced theWebLoaderclass with URL replacement functionality and improved recursion handling for web scraping. Added a mechanism to limit the number of processed URLs. [1] [2] [3] [4]src/tools/web_scraper.py: Created theWebScrapertool to extract content from web pages, supporting features like JavaScript rendering and structured data extraction.Documentation Enhancements:
docs/ideas/agent-behavior.md: Added a comprehensive strategy document outlining optimizations for agent behavior, including context-aware prompts, specialized capabilities, and proactive error prevention.UI Updates:
src/ui/index.html: Updated the script reference fromchat.jstobundle.jsto align with the new build system.