Stage 21 harness: bounded backoff on Codex 429, per-attempt trace reset
Without backoff a rate-limit burst is worse than slowness: every queued cell fails in milliseconds, so one storm consumes an entire pass and leaves a receipt full of error rows instead of answers. Three storms were observed, each triggered by raising harness concurrency (12 and 18 concurrent requests; six ran clean). Transport now retries up to five times with exponential backoff and jitter, and only on 429/rate-limit - a scoring failure is never retried. Each attempt resets the trace buffer and turn counter, or a cell that 429'd mid-loop would report one navigation as two. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01H9ToHYJVDxfeJcJwdzrP2H
| Repository | eliziff/Beaver |
|---|---|
| Author | Eli Ziff <eliasziff@gmail.com> |
| Authored | |
| Parents | a33c2249 |
| Stats | 1 file changed , +28 , -3 |
| Part of | Evaluation harness: Beaver-CAN and LegalBench-RAG adapters |
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-3c847e4c.md
from inside the repo you want the change in.