This directory contains a suite of AI-powered tools for analyzing GitHub issues and determining implementation effort levels for the Gemini CLI project.

📁 Directory Structure

data/: Contains the issue data in JSON and CSV formats.
- bugs.json: The primary source of truth for bug analysis.
*.py: Analysis and utility scripts.
loop_analyzer.sh: A shell script for running iterative analysis until all issues are processed.

🚀 Workflows

1. Initial Triage (Static)

Use this for a quick, first-pass estimation.

python3 analyze_bugs.py

2. Deep Agentic Analysis

Uses Gemini as an agent with access to the codebase.

python3 bug_analyzer_final.py

3. Iterative Analysis

Runs the single-turn analyzer in a loop until all issues have a valid analysis.

./loop_analyzer.sh

4. Validation & Export

Run these after analysis to ensure consistency and generate a readable report.

python3 validate_effort.py
python3 generate_bugs_csv.py

🧠 Effort Level Criteria

Ratings are based on technical complexity and reproduction difficulty:

Small (1 day): Trivial logic changes, localized fixes (1-2 files), easy to reproduce.
Medium (2-3 days): Requires tracing across multiple components, UI state management (React/Ink), or harder reproduction.
Large (3+ days): Architectural issues, platform-specific (Windows, PTY, Signals), performance bottlenecks, or core protocol changes.

Note: Any bug that is difficult to reproduce or platform-specific must not be rated as Small.

🛠 Usage Notes

API Key: Ensure you have a valid Gemini API key set in the scripts.
Paths: Scripts are configured to look for data in the data/ subdirectory and the codebase in ../../packages.
Requirements: Requires Python 3 and jq (for the shell script).