| .. |
|
agent-eval-feedback-metrics.md
|
5dd4db68cd
docs: the occupancy baseline says our residual is higher — write that down (CG-13)
|
hace 1 mes |
|
answer-directly-vs-explore-agent.md
|
d6d17288be
docs(benchmarks): re-derive the token figures the result.usage bug touched
|
hace 1 mes |
|
call-sequence-analysis.md
|
d6d17288be
docs(benchmarks): re-derive the token figures the result.usage bug touched
|
hace 1 mes |
|
codegraph-ab-matrix.md
|
4509b45dd5
Add landing page + Starlight docs site (#375)
|
hace 3 meses |
|
explore-allocation-ab-1500.md
|
fa15d1046a
docs: allocation efficiency — the metric, its guards, and the 103-run baseline (CG-9)
|
hace 1 mes |
|
explore-allocation-efficiency.md
|
382791f11e
docs: one entry point for the three feedback metrics, and how to run them (CG-11)
|
hace 1 mes |
|
explore-dedup-ab-cg20.md
|
2cfd321b23
docs: CG-20 — the dedup gate, three bars pass and the fourth cannot (CG-2)
|
hace 1 mes |
|
explore-displacement-guard-ab-cg31.md
|
be7c968439
docs(benchmarks): record the CG-31 A/B — no regression, four repos stop truncating
|
hace 1 mes |
|
explore-oversize-member-ab-cg30.md
|
0d014a6582
docs(benchmarks): record the CG-30 A/B — deterministic win, no behavioural regression
|
hace 1 mes |
|
explore-reservation-invariant-ab-cg26.md
|
5f32478b57
docs(benchmarks): record the CG-26 A/B — the invariant holds on every path
|
hace 1 mes |
|
explore-sufficiency.md
|
382791f11e
docs: one entry point for the three feedback metrics, and how to run them (CG-11)
|
hace 1 mes |
|
residual-context-occupancy.md
|
d6d17288be
docs(benchmarks): re-derive the token figures the result.usage bug touched
|
hace 1 mes |
Colby McHenry
5f32478b57
docs(benchmarks): record the CG-26 A/B — the invariant holds on every path