# monSQLize v3.1.0

> Release date: 2026-07-15

## Highlights

- Pins the production dependency to registry `schema-dsl@3.0.0` and continues to compile Model schemas only through the isolated `schema-dsl/runtime` integration.
- Consumes the canonical schema-dsl validation result (`valid`, normalized `data`, and `errors[].path/message/keyword`) without relying on deprecated upstream `field/type/expected` aliases.
- Keeps `Model.validate()` compatible for monSQLize callers as `{ valid, errors: [{ field, message }], data }`, deriving `field` from the canonical upstream path.
- Persists successful normalized data across the six complete-document write paths: `insertOne`, `insertMany`, `insertBatch`, `replaceOne`, `findOneAndReplace`, and hydrated document `save()`.
- Applies bulk defaults before before-hooks, normalizes before timestamps/version fields, and validates replacement documents before optimistic-lock reads.
- Rejects null, primitive, or array normalized results before any driver operation; failed validation snapshots are never written.
- Preserves timestamps on hydrated `save()` when versioning is disabled, including documents normalized by schema-dsl.
- Includes the maintained Node 24 GitHub Actions runtime, release metadata checks, TypeScript lint coverage, shared memory-server policy, coverage/package/license budgets, derived-artifact dry-run cleanup, and the lightweight data-task CLI bundle introduced after v3.0.0.

## Compatibility boundaries

- Update operators and pipelines are partial mutations, so they are intentionally outside normalized complete-document persistence.
- `isRequired()` and `isOptional()` are not required by monSQLize; schema definitions already expose the required/optional state needed by this integration.
- The public monSQLize validation error shape remains stable even though its upstream adapter now consumes schema-dsl's canonical error fields.

## Verification

- The release candidate must pass `npm run release:preflight`, the Node 18/20/22 remote matrix, packed CJS/ESM/TypeScript/CLI consumers, the MongoDB 7/8 server matrix, production dependency audit, and the documentation browser gates.