Run a local AI code review trial before you add a team CI gate

Описание и применение

Тест локального AI‑ревью кода позволяет командам оценить набор правил и рабочий процесс, прежде чем внедрять его в CI.

Задача

Teams need to evaluate whether an AI‑assisted code review rule set is useful and non‑opaque before integrating it into CI.

Результат

The trial demonstrates that a local AI code review can detect high‑severity issues (e.g., command injection) and medium‑severity team conventions, providing structured findings and exit codes that teams can evaluate before committing to a CI gate.

Рабочий процесс

• Clone the trial repository or use the provided sample.
• Run the script with ./run-trial.sh.
• Review the generated local report for high and medium findings.
• Check the exit status (1 for high/medium, 2 for critical).
• If useful, consider purchasing the Team Rules Pack for broader coverage.
• Provide feedback via the structured team‑trial form on GitHub.

Доказательства

Run the included script: ./run-trial.sh

Источник

The sample produces a structured local report with: a High command‑injection finding for os.system(user_input); a Medium team‑convention finding for a direct print call; and exit status 1 for high or medium findings.

Источник