What it is
A stdlib-only Python decision service for developers using Jev (TypeSafe System One). It wraps typed questions with a confidence policy, per-lane decision logging, a blind eval harness, and a skill router over large skill rosters.
How it uses Jev
Jev answers typed questions (noul, choice, score) on a given state. The service returns calibrated probabilities, applies a confidence policy to route each answer to action, escalate, or abstain, and logs every decision for later threshold tuning.
Primitives:choicescorenoul
Technique worth stealing
Fuse Jev as a second semantic signal with deterministic retrieval; decompose judgments into atomic questions and combine with code.
Try it
export OPENCODE_ZEN_API_KEY=... then run python3 eval_preflight.py ground_truth.json or skill_router.py.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.95
- Shows a System One patternyes0.86
- Handles uncertaintyno0.35
- Measuredno0.21
- Runnableyes0.90
- Worth recommendingunclear0.54
- Model replicano0.03
- Problem scopescore on a 0–2 scale1.05
- About Jevyes0.99
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.