Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(benchmarks): pre-register what a release-candidate run should show
AkitaOnRailsd5bd987f60d5
diff --git a/docs/benchmarks/README.md b/docs/benchmarks/README.mdindex a9aeaf61..2af83d9b 100644--- a/docs/benchmarks/README.md+++ b/docs/benchmarks/README.md@@ -105,3 +105,11 @@ baseline-vs-baseline determinism check is clean (all accuracy/token deltas `0.00with the previous release (AGENTS.md, project maintenance rules). A dropdoes not block the release: the numbers are published and an issue opensfor the next release to decide whether it is a regression.+- **Pre-registration.** Before the release-candidate run, write down in the+ release's tracking issue what the run is meant to show: the question, the+ slices that matter for the change, and the expected direction for each.+ Judge the result against run-to-run noise (about ±0.005 overall,+ ±0.02–0.03 on small slices), not a percentage threshold. Writing the+ expectation first keeps a run from being read in whichever way suits it;+ a result that misses it still follows the release policy. The idea came+ from #1255.