---
title: "mova-nightingale-work — Mova code model"
description: "Mova code model of tools/nightingale/src/work.rs: components with their labels, obernants and the model text."
url: "https://groupants.elamur.ai/free/en/mova/tools/nightingale/src/work.rs.groupant/"
---
Elamur: [Mova](https://md.mova.elamur.ai/free/en/) · [Dictionary](https://md.dictionary.elamur.ai/free/en/) · [Translate](https://md.translate.elamur.ai/free/en/) · [Research](https://md.research.elamur.ai/free/en/) · **Groupants**

This page as HTML: <https://groupants.elamur.ai/free/en/mova/tools/nightingale/src/work.rs.groupant/>

# mova-nightingale-work

The groupant beside tools/nightingale/src/work.rs in the Mova repository: what the code computes, what it never does, how to go back from its outputs, its invariants, cost and checks.

## Facts

- **kind:** groupant
- **status:** partial source bound model
- **source:** [`tools/nightingale/src/work.rs`](https://github.com/ElamurAI/mova-free/blob/main/tools/nightingale/src/work.rs)
- **repository folder:** [`tools/nightingale/src/work.rs.groupant`](https://github.com/ElamurAI/mova-free/tree/main/tools/nightingale/src/work.rs.groupant)

> **Implementation material.** A Mova code model describes this code at one source revision: partial models, finite checks and their stated scope. It is not a reviewed general exposition, and its labels are shown as written, never raised.

## Components

| component | label | where |
|---|---|---|
| **Approximant** | partial | [Forward approximant](#forward-approximant) |
| **Ast** | partial | `syntax.json` |
| **Composition** | partial | [Composition](#composition) |
| **Cost** | partial | [Cost](#cost) |
| **Descriptant** | present | [Descriptant](#descriptant) |
| **Invariant** | partial | [Invariant](#invariant) |
| **Tests** | finite evidence | [Tests](#tests) |

## Obernants

The typed relations around the forward model: the behaviour complement (what the code never does), the reverse reconstruction (every input compatible with an output) and specialised views.

| relation | type | label | where |
|---|---|---|---|
| Behavior complement | behavior complement | partial source derived model | [Behavior complement](#behavior-complement) |
| Reverse reconstruction | reverse reconstruction | partial source derived model | [Reverse reconstruction](#reverse-reconstruction) |

## Model text


### Descriptant

The work loop beside the Eel: count new units, freeze the dev sample, hand off generations with READY, scan parallel pairs for loan-use, purist and loan-candidate flags, record translators' choices, and ask the Sol. Source: `tools/nightingale/src/work.rs`.

### Forward approximant

step: count_new -> freeze_dev -> build_handoff (lineage new and build_share reached; deltas learned) -> scan_step (cursor, flags once per kind/word/register; a copied word next to another copied word rare in the language is a code-switched fragment, not a loan candidate; proposals) -> consult_step (paced, at most 10 items, strict answer -> proposals) -> work.jsonl.

### Invariant

The same lineage is never built twice; nothing is deleted; proposals are review-only; a Sol question is never repeated; an error stops the loop.

### Cost

A step: its units' counting plus scan_per_step parsed rows.

### Composition

Parent: nightingale.

### Behavior complement

Never writes the hand list, a manual or an installed model; never holds the GPU. Evidence status: source-derived model with finite checks, not a proof.

### Reverse reconstruction

work.jsonl, proposals.jsonl, chosen.json, scan.json, sol-queue.jsonl and sol-asked.txt recover what was done.

### Tests

#### Checks

tests/english.rs work loop; tests/model.rs handoffs.
These are finite fixtures and measurements; not a proof.

## History


#### 2026-11-06 · document

##### Epoch 2026-11-06

First model, written with the source (the Nightingale: one per language under the Eel; a standard naturalness model with variety deltas).

##### Observation 2026-11-06

On 20 000 Europarl pairs the unlisted-copy flags fell from 84 (bigram orthography, any English frequency) to 68 (character-trigram orthography, 4× English ratio) to 26 (fragment rule, seen twice); about 9 of the 26 read as English loans in French use. Precision is unreviewed.

## Provenance

- **source SHA-256:** `79735364e3d76883…`
- **repository commit:** `2e25d7bfae9a`