Relax private D&D response schemas

This commit is contained in:
2026-07-22 14:38:35 +00:00
parent 7b2fb0880d
commit ab0b4e350c
19 changed files with 355 additions and 154 deletions

View File

@@ -157,11 +157,11 @@ schemas remain package-owned.
The spell, NPC, and combat extractors' package-owned prompts declare their
structured JSON inputs and private response schemas. Each private response
schema remains separate from its durable artifact codec schema; this work does
not use shared schema fragments or schema generation. The combat private schema
owns the transport envelope—required fields, JSON types, nullability, and
unknown-field rejection—while its deterministic validators own semantic
constraints such as enum membership, non-empty values and collections, and
positive numbers. The spell extractor's prompt declares a required
not use shared schema fragments or schema generation. Those private schemas own
the transport envelope—required fields, JSON types, nullability, and
unknown-field rejection—while deterministic validators own semantic constraints
such as enum membership, non-empty values and collections, and positive
numbers. The spell extractor's prompt declares a required
`application/json` `spell_catalog` input and an optional `application/json`
`npcs` input. The extractor generates
the catalog input from its prepared

View File

@@ -192,6 +192,12 @@ decodes the model response, assigns the generic source identity to every source
reference, canonicalizes duplicate references, orders spell casts by their
earliest cited unit, and returns `dnd.SpellList`.
Its private response schema admits only the structural transport envelope:
required fields, JSON types, array and object shapes, and unknown-field
rejection. It maps integer source-unit candidates directly without repairing
semantic values, so the deterministic shape, catalog, and source-reference
validators own blank values, empty evidence, and invalid or unresolved ranges.
The extractor owns its private model-response DTO, embedded prompt, LLM response
schema, strict option decoder, injected shared LLM client, and prompt/schema
manifest metadata. During preparation it resolves the optional `spell_catalog`
@@ -250,6 +256,11 @@ registry slot. Its prompt and private response schema are package-owned. The
prompt follows the shared D&D extraction ordering and cache policy documented
in [LLM Runtime](llm.md#dd-extraction-prompt-ordering-and-cache-boundaries).
The private response schema owns only structural transport validation and maps
integer source-unit candidates unchanged. Required semantic content, non-empty
evidence, and valid source ranges are rejected by the deterministic shape and
source-reference validators.
### `internal/modules/dnd/extract/combatturns`
The combat extractor prepares one structured request per supplied chunk using