Every rule gets one home: 2,214 tokens off the fixed overhead

↗ view on GitHub · Eli Ziff · 2026-07-29 · 949656c4

Measured first: 12,833 fixed tokens per turn (2,131 prompt + 10,702
tool array). Then cut by single-homing - a tool's own contract lives in
its description, cross-tool routing in the prompt, corrective feedback
in result strings only where not taught elsewhere. Seventeen rules
deduplicated across prompt, descriptions, next_required_action, and
error strings; result-string re-teaching alone drops 599 tokens per
full fire set. Smoke first-input: full 8,369 to 6,937, lean 7,817 to
6,790, four-for-four behaviours and correct answers on both. Stale
assertions on the removed version_id requirement and the [^id] note
contract updated.

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 7d2167a0
Stats 17 files changed , +193 , -247
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-949656c4.md from inside the repo you want the change in.

⬇ Download capture-commit-949656c4.md