NOVA and TOON: the same tables, in a typed format
NOVA’s tables come from TOON: name the columns once and declare the row count. TOON is an encoding of JSON for LLM prompts. In NOVA the table is one representation of a typed document, so the model can read it with a revision and write back a conditional patch.
prompt.toon services[2]{id,port,replicas}:
auth,8080,3
api,3000,5nvf get @revision sha256:91cf16db…
[2]{id,port,replicas}:
auth,8080,3
api,3000,5Query responses use the compact profile, so a projected list of uniform records comes back as a table, with the revision of the whole document. Queries, spec §7.3
What changes
| Topic | TOON | NOVA | Spec |
|---|---|---|---|
| What it is | An encoding of JSON for LLM input; keep JSON elsewhere | One value model with human text, compact tables, binary and patches | §3 |
| Types | JSON’s: objects, arrays, strings, numbers, booleans, null | Also timestamps, decimals, rationals, sets, tuples and variants | §2 |
| Row count | Required; checked in strict mode, the default | Required; always checked | §4.9 |
| Delimiters | Comma, tab or pipe | Comma; a cell is a flow value, quoted when needed | §4.9 |
| Comments | Full-line #, dropped when decoding | Full-line and trailing, kept by the formatter and by patches | §4.1 |
| Writing back | The model writes TOON or JSON; you decode it | The model writes a conditional patch against the revision | §8 |
Migrating
You do not need a prompt encoder: ask for the fields the model needs, and the answer is already a table. The model then answers with one line instead of the whole document.
nvf get infrastructure.nova 'services[*].{id,port,replicas}'What the model writes back @patch sha256:91cf16db
services[id=api].replicas: 5 -> 8Compare the sizes of your own file $ nvf stats infrastructure.nova
representation bytes ~tokens
nova (human) 306 114
nova (compact) 305 114
json (pretty) 454 190
json (compact) 301 166
yaml 325 121
toml 312 142
(token counts are a tokenizer-independent heuristic; see spec §10)Fewer input tokens do not always mean fewer total tokens or more correct results. Measure with your model’s tokenizer and your tasks. Token-aware selection, spec §10
When to stay with TOON
- Your data is JSON end to end and you only want a smaller prompt. That is what TOON is built for, and it has implementations in many languages.
- You want tab or pipe delimiters, or a configurable indentation size.
- You need a format that is stable today. NOVA is a 0.1 draft.
Questions
Is NOVA compact text the same as TOON?
No. The table header is the same idea, key[N]{columns}:, but the cells are NOVA flow values and the rest of the document is NOVA text. Do not expect a TOON decoder to read NOVA, or the other way round.
When does NOVA write a table?
The compact profile writes a list as a table when it has at least two records, every field value is a scalar, and the rows are at least half filled. Irregular data stays in block layout, where tables have no advantage.
What does an empty cell mean?
The field is absent from that row’s record. Write null for a field that is present and null.