A log-cleaning idea for better Hermes Agent inputs
BJIR is a local tool that cleans up material before it is given to an . It focuses on long build logs, code changes mixed with lockfile noise, error traces tangled with Docker output, and repeated agent trace chatter. A code diff can be reduced to the real changes, while a build or test run can be narrowed down to the failing parts.
A long error log can become a short report that is ready to paste. The report includes the original size, the cleaned size, an estimated , detected signals, and the cleaned output. Secret-looking values, tokens, and -like text are hidden by default.
The main idea is that the cleanup happens locally and follows fixed rules instead of calling another AI model to summarize the material.
Key points
- Clean long logs before giving them to .
- BJIR reduces noisy build logs, test output, diffs, and error logs.
- The cleaned report shows size reduction, estimated token use, detected signals, and the final output.
- Secret-looking values and are masked by default.
- The cleanup and does not use another AI model for summarizing.