This commit is contained in:
Dobromir Popov
2025-10-09 13:58:43 +03:00
parent 270ba2e52b
commit a86e07f556
3 changed files with 248 additions and 0 deletions

54
memories.md Normal file
View File

@@ -0,0 +1,54 @@
# AI Assistant Memories
## Memory System Status
**No AI Assistant Memory System Found**
After searching through the project, I found that there is no AI assistant memory system currently implemented or configured. The memory-related files found in the project are:
1. **COBY/monitoring/memory_monitor.py** - System memory monitoring for performance optimization
2. **core/model_output_manager.py** - Model output storage and management
3. **core/prediction_snapshot_storage.py** - Prediction data storage
4. **core/trade_data_manager.py** - Trading data capture and storage
5. **utils/database_manager.py** - Database management for trading system
## What These Files Contain
### System Memory Monitoring
- **COBY/monitoring/memory_monitor.py**: Monitors system memory usage, detects memory leaks, and optimizes garbage collection for the trading system
- Tracks memory snapshots, object counts, and garbage collection statistics
- Provides memory usage trends and leak detection
### Trading Data Storage
- **core/model_output_manager.py**: Stores model outputs for cross-model feeding and evaluation
- **core/prediction_snapshot_storage.py**: Stores prediction snapshots for future training
- **core/trade_data_manager.py**: Captures comprehensive model inputs during trade execution
- **utils/database_manager.py**: Manages SQLite database for trading system logging and metadata
## Missing AI Assistant Memory System
The project does not have:
- MCP memory server configuration
- AI assistant persistent knowledge base
- Conversation history storage
- User preference memory
- Project context memory
## Recommendation
If you want to implement an AI assistant memory system, you would need to:
1. Set up an MCP memory server
2. Configure memory storage for AI assistant context
3. Implement memory persistence across sessions
4. Add memory management tools to the available tool set
## Current Memory-Related Tools Available
The only memory-related tools currently available are:
- System memory monitoring (COBY/monitoring/memory_monitor.py)
- Trading data storage systems
- Model output management
- Database management for trading metadata
**Note**: These are all related to the trading system's data storage and performance monitoring, not AI assistant memories.

101
tools-kiro.md Normal file
View File

@@ -0,0 +1,101 @@
# Kiro Tools Documentation
This document lists all the tools available to Kiro for assisting with development tasks.
## File System Operations
### executePwsh
Execute PowerShell or CMD commands on Windows systems.
- **Parameters**: command (required), path (optional), ignoreWarning (optional)
- **Usage**: Run shell commands, but avoid long-running processes like dev servers
- **Note**: Never use 'cd' command - use path parameter instead
### listDirectory
List directory contents in long format (similar to `ls -la`).
- **Parameters**: path (required), depth (optional), explanation (required)
- **Usage**: Explore file structure, can do recursive listing with depth parameter
### readFile
Read content from a single file with optional line range specification.
- **Parameters**: path (required), explanation (required), start_line (optional), end_line (optional)
- **Usage**: Read entire files or specific line ranges
### readMultipleFiles
Read content from multiple files simultaneously with optional line ranges.
- **Parameters**: paths (required array), explanation (required), start_line (optional), end_line (optional)
- **Usage**: Efficiently read multiple files at once
### fsWrite
Create new files or overwrite existing files with content.
- **Parameters**: path (required), text (required)
- **Usage**: Create files, limit to ~50 lines then use fsAppend for larger content
### fsAppend
Append text content to the end of existing files.
- **Parameters**: path (required), text (required)
- **Usage**: Add content to existing files, handles newline formatting automatically
### deleteFile
Delete files at specified paths with graceful error handling.
- **Parameters**: targetFile (required), explanation (required)
- **Usage**: Remove unwanted files safely
### strReplace
Replace specific text strings in files with exact matching.
- **Parameters**: path (required), oldStr (required), newStr (required)
- **Usage**: Make precise edits to existing files, requires exact whitespace matching
## Search and Discovery
### fileSearch
Fast fuzzy file search based on file path patterns.
- **Parameters**: query (required), explanation (required), excludePattern (optional), includeIgnoredFiles (optional)
- **Usage**: Find files when you know part of the path but not exact location
### grepSearch
Fast text-based regex search within files using ripgrep.
- **Parameters**: query (required), explanation (optional), caseSensitive (optional), includePattern (optional), excludePattern (optional)
- **Usage**: Search for text patterns across files, supports regex and glob patterns
## Code Analysis
### getDiagnostics
Get compile, lint, type, and semantic issues in code files.
- **Parameters**: paths (required array)
- **Usage**: Check for syntax errors, linting issues, and type problems
- **Note**: Use this instead of bash commands for error checking
## Tool Usage Guidelines
### Best Practices
- Use `readMultipleFiles` instead of multiple `readFile` calls
- Use `getDiagnostics` for code validation instead of shell commands
- Avoid long-running commands like `npm run dev`, `yarn start`, `webpack --watch`
- Use `fsWrite` for initial file creation, then `fsAppend` for additional content
- Include sufficient context in `strReplace` operations for unique matching
### Windows-Specific Notes
- Commands are adapted for Windows cmd/PowerShell environment
- Use `;` as command separator in PowerShell instead of `&&`
- File paths use Windows conventions
### Search Patterns
- **Regex patterns**: Use Rust regex syntax for `grepSearch`
- **Glob patterns**: Use standard glob syntax (* for wildcards, ** for recursive)
- **File search**: Fuzzy matching against file paths
- Always escape special regex characters: `( ) [ ] { } + * ? ^ $ | . \`
### Error Handling
- Tools fail gracefully with appropriate error messages
- File operations check for existence and permissions
- Search operations are capped to prevent overwhelming output
## Integration with Kiro Features
These tools integrate with Kiro's key features:
- **Autopilot/Supervised modes**: File modification tools respect user's autonomy settings
- **Chat context**: Tools work with #File, #Folder, #Problems, #Terminal, #Git Diff, #Codebase
- **Specs**: Tools support structured feature development workflows
- **Hooks**: Tools can be triggered by IDE events
- **Steering**: Tools respect workspace-specific guidelines in `.kiro/steering/`
- **MCP**: Tools can interact with Model Context Protocol configurations

93
tools.md Normal file
View File

@@ -0,0 +1,93 @@
# Available Tools
This document lists all the tools available in the AI coding assistant.
## File Operations
- **read_file**: Read contents of a file from the local filesystem
- **write**: Write a file to the local filesystem (overwrites existing files)
- **search_replace**: Perform exact string replacements in files
- **MultiEdit**: Make multiple edits to a single file in one operation
- **delete_file**: Delete a file at the specified path
- **list_dir**: List files and directories in a given path
- **glob_file_search**: Search for files matching a glob pattern
## Code Analysis and Search
- **codebase_search**: Semantic search tool to find code snippets relevant to queries
- **grep**: Powerful search tool built on ripgrep for exact symbol/string searches
- **read_lints**: Read and display linter errors from the current workspace
## Terminal Operations
- **run_terminal_cmd**: Execute terminal commands on behalf of the user
## Web and External Resources
- **web_search**: Search the web for real-time information about any topic
- **fetch_rules**: Fetch rules provided by the user to help with navigating the codebase
## Task Management
- **todo_write**: Create and manage a structured task list for coding sessions
## Notebook Operations
- **edit_notebook**: Edit Jupyter notebook cells (supports editing existing cells and creating new ones)
## Git Operations
- **fetch_pull_request**: Fetch pull request information including title, description, and diff
## Memory Management
- **update_memory**: Create, update, or delete memories in a persistent knowledge base
## Diagram Creation
- **create_diagram**: Create Mermaid diagrams
## Tool Usage Guidelines
### File Operations
- Always prefer editing existing files rather than creating new ones
- Use MultiEdit for multiple changes to the same file
- Be careful with file paths - use relative paths when possible
### Code Search
- Use codebase_search for semantic queries about functionality
- Use grep for exact string/symbol searches
- Check linter errors before and after making changes
### Terminal Commands
- Commands run in the same shell session unless specified otherwise
- Use non-interactive flags for commands that require user input
- Background long-running processes appropriately
### Task Management
- Use todo_write for complex multi-step tasks
- Update task status in real-time
- Only one task should be in_progress at a time
### Memory Management
- Use update_memory for persistent information that should be remembered across sessions
- Include relevant context and metadata
- Use appropriate action types (create, update, delete)
### Web Search
- Use for real-time information not available in training data
- Include version numbers or dates for technical queries
- Verify current facts and updates
### Notebook Editing
- Use edit_notebook exclusively for Jupyter notebook operations
- Provide extensive context for unique identification
- Support both editing existing cells and creating new ones
### Diagram Creation
- Use create_diagram for Mermaid diagrams
- Specify diagram type and content clearly
- Diagrams are rendered as SVG images
### Git Operations
- Use fetch_pull_request to get detailed PR information
- Includes title, description, diff, and commit details
- Useful for understanding code changes and context
## Best Practices
- Batch tool calls when possible for better performance
- Always read files before editing them
- Use appropriate tools for the task at hand
- Follow the user's coding rules and preferences
- Maintain code quality and avoid creating duplicate implementations