Nanocoder v1.20.3 Release Notes — What's New

Fixed search_file_contents returning excessive tokens by truncating long matching lines to 300 characters. Previously, searching in files with long lines (minified JS, base64 data, etc.) could return ~100k tokens for just 30 matches.
Added validation to read_file to reject minified/binary files (lines >10,000 characters). These files consume excessive tokens without providing useful information to the model. Use metadata_only=true to still check file properties.
Fixed web_search result count display showing mismatched values (e.g., "10 / 5 results"). The formatter now correctly uses the same default as the search execution.
Improved web_search and fetch_url formatter layouts to match execute_bash style with consistent column alignment and spacing.

If there are any problems, feedback or thoughts please drop an issue or message us through Discord! Thank you for using Nanocoder. 🙌

npm install -g @nanocollective/nanocoder

nanocoder

Full Changelog: https://github.com/Nano-Collective/nanocoder/compare/v1.20.2...v1.20.3