grounding runners: bounded concurrency with per-model lane caps

↗ view on GitHub · Eli Ziff · 2026-07-30 · 0b581df1

Cells are independent (model, arm, case) triples; both runners now pump
them through a bounded pool (--concurrency, default 4) with a per-model
cap (--per-model-concurrency, default 2) so parallel Claude lanes buy
wall-clock while the overload-prone provider stays throttled and
concurrency cannot manufacture transport errors. Receipts append in
completion order; per-cell latency is measured inside the cell, and the
pool changes wall-clock only, never inputs. Stage 4 matrix relaunched
under 4/2 after 6 sequential control cells; noted for the log.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012AgUm5EcRKbT3duVFMbrQD
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents b0338f65
Stats 2 files changed , +136 , -47
Part of Legal grounding and retrieval research

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-0b581df1.md from inside the repo you want the change in.

⬇ Download capture-commit-0b581df1.md