4 people 78b8e28b67 docs(perf): preserve negative small-capture token and timing results ...

Record repeated public SDK/Codex comparisons, real CLI parity, independent raw-frame validation and grading regressions. Keep whole-resource counters and broader capture/platform coverage explicitly unknown; no production change is justified.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>

2026-10-14 02:40:31 +08:00

..

analysis-efficiency

docs(perf): preserve negative small-capture token and timing results

2026-10-14 02:40:31 +08:00