Colby McHenry 03069c9118 docs(benchmarks): current-build A/B on all 7 README repos + fix token-measurement bug ...

Re-ran the README benchmark on the current build (7 repos reindexed, median of 4): avg 35% cost / 57% tokens / 46% time / 71% tool calls saved — reproduces the published README (35/59/49/70), no regression. Adds bench-readme.sh + parse-bench-readme.mjs harness.

Fixes a token-measurement bug: result.usage is last-turn-only in current Claude Code; must sum per-turn assistant usage for cumulative tokens. Corrects the earlier excalidraw note (its '-34% tokens' was off this bug; real ~90%) and the cost MECHANISM (volume/fewer-turns, not cache-ability — the without-arm's huge token volume is mostly cheap cache-reads, so token savings 57% > cost savings 35%). Cost/time were always correct.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-24 03:41:16 -05:00

..

benchmarks

docs(benchmarks): current-build A/B on all 7 README repos + fix token-measurement bug

2026-05-24 03:41:16 -05:00

design

docs(playbook): record Java/Kotlin interface-DI synthesizer (probe-validated; agent A/B adoption-gated)

2026-05-23 18:52:03 -05:00

plans

feat: wire up framework route extraction (#89)

2026-05-07 22:03:33 -05:00

SEARCH_QUALITY_LOOP.md

feat: Add complete PHP language support with trait handling and property extraction

2026-04-07 13:44:14 -05:00