Metadata-Version: 2.1
Name: flamethrower
Version: 0.1.7
Summary: The ultimate debugging experience 🦠🔥
License: MIT
Author: Scott Susanto
Author-email: scottsus@usc.edu
Requires-Python: >=3.11,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: gitpython (>=3.1.40,<4.0.0)
Requires-Dist: jsonschema (>=4.20.0,<5.0.0)
Requires-Dist: openai (>=1.6.1,<2.0.0)
Requires-Dist: pathspec (>=0.12.1,<0.13.0)
Requires-Dist: pydantic (>=2.5.3,<3.0.0)
Requires-Dist: rich (>=13.7.0,<14.0.0)
Requires-Dist: tiktoken (>=0.5.2,<0.6.0)
Description-Content-Type: text/markdown

# 🔥 flamethrower

The ultimate debugging experience.

## Usage

1. Pip install

    ```
    pip install flamethrower
    ```
    `WARN`: this installs `flamethrower` deps into your global python environment -- which you will need if you want to run flamethrower on any workspace.

2. Export OpenAI key for `flamethrower` to use

    ```
    EXPORT OPENAI_API_KEY=sk-xxxx
    ```

3. In whatever workspace/repo you're on, just type `flamethrower` or `ft`

    ```
    pwd
    flamethrower
    ```

    flamethrower will gain an understanding of your project and directory structure.

4. Use it as a regular shell: you can both run commands and ask natural language queries

    ```
    python main.py # or node server.ts or whatever your run script is
    Wtf? Why did that happen? # natural language queries start with a capital letter
    ```

