mirror of
https://github.com/colbymchenry/codegraph.git
synced 2026-10-04 15:08:32 +08:00
On a gap that is >=95% one tool result, the measured context delta IS that result's token count, so the spread between it and the run-level ratio is the attribution error. Median over such gaps: +/-1-2% on real runs.