daf-jev

# daf-jev
[](https://doi.org/10.5281/zenodo.22816187)
[](pyproject.toml)
[](LICENSE)
[](https://zenodo.org/records/22817425)


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.

## 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 any number of questions into a single API call.
- **Client** — `JevClient` / `AsyncJevClient` wrapping
  `POST https://api.typesafe.ai/v1/systemone`, with retries (429/529,
  exponential backoff, `Retry-After`), typed error mapping, and a
  `models()` listing. Retry policy, default timeout, and default model
  resolve from the environment (see [Configuration](#configuration)); every
  `ask` call also accepts a per-call `timeout` override and extra
  `request_headers` (merged over the defaults for that call only).
- **Composition patterns** — pure functions over answers:
  `composite_score` (probability-weighted expected value over score levels),
  `confidence_gate` (auto-escalate low-confidence answers), `route` /
  `pick` (intent routing by choice).
- **Evaluation** — `Evaluator` runs a fixed question set over many states
  concurrently (thread pool for `JevClient`, `asyncio` semaphore for
  `AsyncJevClient`) without aborting the batch: per-state failures are
  captured in `EvaluationRecord.error`. `summary()` aggregates per-question
  means/p95s; `to_json()` seria