Benchmark runs: remove ask_inputs tool, raise child cap to 3h

↗ view on GitHub · Eli Ziff · 2026-07-28 · 9b74c8b3

Sonnet through the Beaver arm paused the banking run on ask_inputs
- there is no user in a benchmark run to answer, and the reference
harness has no ask-user affordance either (parity). Gate mirrors
MIKE_DISABLE_RESEARCH_TOOLS. The 30-min child cap would also have
killed any claude-p whole-deliverable run mid-flight (LAB's own
sonnet row took 48 min).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018bhP89cYSdEEjHNPnxacns
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 3b712e31
Stats 2 files changed , +16 , -2
Part of Chat backend features and prompt/context-budget management

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-9b74c8b3.md from inside the repo you want the change in.

⬇ Download capture-commit-9b74c8b3.md