Jev Tool Selection

A zero-dependency tool selector that narrows a large pool of agent tools to the relevant few before the LLM call, running offline with TurboQuant or on TypeSafe Jev when a TYPESAFE_API_KEY is set.

Benchmark results for JEV 1.13 in Choice mode across MetaTool, When2Call and BFCL V4: tool selection, abstention and hallucination tables with bilingual reports and CSV data.

A Python research harness evaluating Jev (TypeSafe System One, jev-1.13.0) as a relevance judge for task-level tool spaces. One API call scores every tool with a yes/no noul question per tool, and the repo benchmarks keep-all versus per-request, per-task and trace-based spaces on TGB and BFCL.

An early step-10,626 checkpoint of a 0.6B agentic decision model on Qwen3-0.6B that scores supplied tool and action candidates, reaching 96.5% on a BFCL V1 function-selection adaptation under Apache-2.0.