DB Seed Generator

Before generating any output, read config/defaults.md and adapt all patterns, imports, and code examples to the user's configured stack.

Process

1. Read schema.prisma and extract all models, fields, types, constraints, relations, and enums.
2. Determine dependency order: models with no required relations first, then models that depend on them.
3. Generate a prisma/seed.ts file with realistic fake data that respects all constraints.
4. Output a ready-to-run seed file.

Dependency Ordering

Build a directed graph of model dependencies from @relation fields. Topologically sort so parent records are created before children.