> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langstate.com/llms.txt
> Use this file to discover all available pages before exploring further.

# State formation and reduction

> A proposed loop for accumulating evidence and resolving canonical values.

<Note>
  **Design note.** The concrete state classes and `LLMMutator` exist, but the complete loop described here requires an application-defined `LangState` subclass and canonical projector.
</Note>

State formation and reduction are two complementary phases.

## Formation

Formation turns input into interpretive candidates:

```text theme={null}
input -> mutator -> candidate value + confidence + latest inference
```

The included `LLMMutator` demonstrates one formation adapter. It copies interpretive state, validates a JSON array of extractions, appends candidates, and records the latest inference per affected field.

An application may also form state from deterministic parsers, UI submissions, retrieved records, or tools. Each mutator should make the source and identity of its update inspectable.

## Reduction

Reduction chooses what becomes canonical:

```text theme={null}
interpretive candidates -> validation and resolution -> canonical value
```

Possible policies include:

* highest confidence above an application threshold;
* exact deterministic validation;
* explicit user confirmation;
* agreement between independent extractors; or
* domain-specific conflict resolution.

The source defines `BaseProjectorCanonicalState` and projection result models, but no concrete reduction policy is bundled.

## Iteration

A full application may alternate formation and reduction until required fields are resolved, then return `ActionResultData`. The application owns termination, retry limits, persistence, and error handling. Use explicit required-field lists; the base state does not infer business completeness from OpenAPI by itself.

## Design invariant

Keep candidate evidence and authoritative values distinguishable even if they share field paths. This makes correction and evaluation possible without pretending that every inferred candidate is already a business fact.