Release v1.1.0
Added
- Database schema captured as evidence: the Extractor reads the full schema (column types, sizes, nullability, primary keys, foreign keys, unique constraints) from SQL Server and PostgreSQL sources and emits it as a
database-schemaobservation - Schema evidence drives interpretation: property types from column types, required/max-length validation rules, and unique constraints on the extracted model
Cratis.Prologue.Interpretationpackage — a resumable interpreter session engine with checkpoint questions: the language model can ask the user multiple-choice questions (always with a free-text option) when uncertain, one at a time, and sessions park, persist, and resume statelessly at any time- Structured LLM refinement producing intentful names, a derived system name, and descriptions for every module, feature, slice, and command
Cratis.Prologue.Screenplaypackage — generates a Screenplay.playdocument from an extraction result using the Screenplay syntax tree and printer- Interpreter service mode: an Orleans-backed session per Prologue behind an HTTP API, with MongoDB-persisted state, a configurable grace period for unanswered questions, and clean self-exit so orchestrators can restart-to-resume
- Interpreter batch mode now also writes the generated
.playfile next to the extraction result - Extraction contract carries the system name, descriptions, validation rules, and constraints
🤖 Generated with Claude Code