ck-loop

Automating iterative code optimization loops involves running multiple experiments against a mechanical metric, tracking results in git history, and automatically keeping or discarding code changes based on performance. You configure the goal, scope, and verification commands to start the loop.

Yes, git integration tracks experiments and automatically rolls back code changes if a regression is detected in the mechanical metric. This ensures your codebase only retains modifications that demonstrably improve the targeted performance or quality measurements.

Autonomous experimentation runs N iterations against a mechanical metric without manual intervention, automatically testing code modifications to improve measurable targets like test coverage, performance, or bundle size. It discards failed experiments and retains successful optimizations.

Yes, you must provide user input for configuration and specific Python scripts for verification and guard commands. The loop relies on these dependencies, including pandas, numpy, and gitpython, to handle automated experimentation, code changes, and version control rollback.

The automated optimization loop handles code changes by running experiments, measuring metrics, and using gitpython for version control to auto-keep improvements or rollback regressions. It requires configuration input and specific verification scripts to validate each iteration's impact.

You should not use an autonomous loop when your optimization goal lacks a strictly mechanical metric for verification, or when you cannot provide specific guard commands. The loop depends on measurable, automated verification to safely evaluate code changes and execute git rollbacks.