A developer tool that logs agent reasoning traces (why code changed) and integrates with podcast learning retention via spaced-repetition notes.

Quick Start • Features • Examples • Contributing

What is this?

AgentTrace is a developer tool that logs the reasoning behind code changes and integrates with a spaced repetition system for podcast notes. It helps software engineers understand why code changes were made and aids in retaining valuable insights from podcasts.

Example Usage

$ python cli.py log-change --file main.py --line 10 --description "Fixed typo"
{"file": "main.py", "line": 10, "description": "Fixed typo"}

Problem

Developers struggle to understand why colleagues made certain code changes, and listeners forget podcast insights within hours, losing valuable knowledge.

Features

Feature	Description
Log Code Changes	Log the reasoning behind each code change with file name, line number, and a brief description.
Spaced Repetition for Podcast Notes	Add new notes with a timestamp and a brief description, and schedule reminders for reviewing the notes at intervals (1 day, 3 days, 1 week).
Retrieve and Display Logs and Notes	Retrieve and display all logged code changes and active podcast notes with their next review times.
Command Line Interface	Use a simple and intuitive command line interface for all operations.
JSON Storage	Store logs and notes in JSON files for easy access and manipulation.
Filtering by Date Range	Filter logs and notes by a specified date range.

Quick Start

1. Clone the repository:

   git clone https://github.com/m2ai-portfolio/AgentTrace.git
   cd AgentTrace

2. Install dependencies:

   pip install -r requirements.txt

3. Run your first command:

   python cli.py log-change --file main.py --line 10 --description "Fixed typo"

Examples

Log a Code Change

Command:

python cli.py log-change --file main.py --line 10 --description "Fixed typo"

Output:

{"file": "main.py", "line": 10, "description": "Fixed typo"}

Add a Podcast Note

Command:

python cli.py add-note --timestamp "2023-10-01 12:00:00" --description "Key concept: Dijkstra's Algorithm"

Output:

{"timestamp": "2023-10-01 12:00:00", "description": "Key concept: Dijkstra's Algorithm", "next_review": "2023-10-02 12:00:00"}

Review Podcast Notes

Command:

python cli.py review-notes

Output:

{"timestamp": "2023-10-01 12:00:00", "description": "Key concept: Dijkstra's Algorithm"}

File Structure

AgentTrace/
├── src/          # Core source code
│   ├── agenttrace.py
│   ├── cli.py
│   ├── data.py
│   ├── spaced_repetition.py
│   └── utils.py
├── tests/        # Test suite
│   ├── __init__.py
│   ├── test_agenttrace.py
│   ├── test_cli.py
│   └── test_spaced_repetition.py
├── .gitignore
├── .heartbeat-callback
├── conftest.py
├── pytest.ini
├── requirements.txt
├── README.md
├── spec.md
└── .self-healing-pipeline/  # Continuous integration and deployment configurations
    ├── builder-log-1.md
    ├── judge-brief-1.md
    ├── plan.md
    ├── retry-report.md
    ├── review-report.md
    └── test-contract.md

Tech Stack

Technology	Purpose
Python 3.11+	Core programming language
click	Command line interface library
pytest	Testing framework

Contributing

1. Fork the repository.
2. Create a new branch: git checkout -b feature/new-feature.
3. Make your changes and run tests.
4. Submit a pull request.

License

MIT

Author

Matthew Snow -- M2AI | @m2ai-portfolio