cubelinux-2

T

CUBELinux-2 15ce36d488 docs: auth-model A/B comparison — error rate is op-mix, not auth model

Two harness drivers (model A per-command auth, model B persistent auth-once)
run across the real release cube-server to settle the "auth-each-time had ~0%
errors" memory. Conclusion: error rate is driven by the slow `audit` op /
3s socket cap, NOT the auth model — with audit removed, model A hits 94.81%
and model B 100%. Adds docs/stress-comparison-20260811.md §5 and the two
reusable harness scripts under tools/.

2026-08-11 19:09:44 -04:00

.hermes/plans

docs: mark R5 done, reframe R1 in plan (owner/grant-native read gate)

2026-08-11 15:12:30 -04:00

cube-bench

feat(cubesys): Task 4 reader/writer sharding (Mutex -> RwLock)

2026-08-11 12:20:08 -04:00

cubecode

fix(cubecode): share one data stack across CALL_LINK frames

2026-08-10 19:59:17 -04:00

cubecoords

feat(system): bind cubefs+cubecode+cubecrypt into one running system (cubesys)