daf-jev

# daf-jev
[](https://doi.org/10.5281/zenodo.22816187)
[](pyproject.toml)
[](LICENSE)
[](https://zenodo.org/records/23266335)


Modular, composable Python client and decision toolkit for the **TypeSafe Jev
(System One) API**. One HTTP endpoint, three question primitives, and a set of
pure-logic composition patterns built on top of the answers — plus a
concurrent batch evaluation harness, an MCP server, a figure registry, and a
reproducible manuscript pipeline. An explicit benchmark backend interface adds
local priors/classifiers, local model servers and OpenRouter decision candidates,
with prepared datasets, durable attempt receipts and separate quality/cost evidence.

**Contents**: [What it provides](#what-it-provides) ·
[Architecture at a glance](#architecture-at-a-glance) ·
[How a decision flows](#how-a-decision-flows) · [Quickstart](#quickstart) ·
[Examples](#examples) · [Evaluating a corpus](#evaluating-a-corpus) ·
[Usage accounting and resilience](#usage-accounting-and-resilience) ·
[Decision-point decider](#decision-point-decider) ·
[Graphical models](#graphical-models) ·
[Jev to RxInfer.jl pipeline](#jev-to-rxinferjl-pipeline) · [CLI](#cli) ·
[MCP server](#mcp-server) · [Configuration](#configuration) ·
[Providers](#providers) · [Figures and manuscript](#figures-and-manuscript) ·
[Decision-model benchmarks](#decision-model-benchmarks) ·
[Tests and benchmarks](#tests-and-benchmarks) · [Map](#map) ·
[Documentation](#documentation)

## What it provides

- **Primitives** — `noul` (yes/no), `choice` (pick an option from a
  probability distribution), `score` (rated on ordered levels). Build
  questions with `noul()` / `choice()` / `score()` and group them in a
  `QuestionSet`; batch questions within the selected backend's capacity.
- **Client** — `JevClient` / `AsyncJ