eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Harmonize D&D artifact contracts

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-26 13:43:45 +00:00
parent 2f506f4985
commit f6981e2264
6 changed files with 281 additions and 800 deletions
Download Patch File Download Diff File Expand all files Collapse all files

199
docs/integrations/dnd-combat-turn-artifacts.md
View File

@@ -1,10 +1,10 @@
# D&D Combat-Turn Artifact Contract # D&D Combat-Turn Artifact
This document defines the durable artifact, serialization, extraction, This contract defines the durable combat-action occurrence list produced by
candidate-validation, normalization, and production lane boundaries for D&D `dnd/combat-turns`. It records source-grounded turns and actions; it is not a
combat turns. complete initiative tracker, combat summary, or state model.
## Artifact identity ## Identity and compatibility
| Property | Value | | Property | Value |
| --- | --- | | --- | --- |
@@ -14,167 +14,56 @@ combat turns.
| Schema version | `v1` | | Schema version | `v1` |
| Media type | `application/json` | | Media type | `application/json` |
The top-level JSON object contains the required `combat_turns` array, which `v1` is a strict JSON object with required `combat_turns`; the array may be
may be empty. Every object rejects unknown fields. empty. Turn and source-reference objects reject unknown fields. A future
incompatible shape requires a new schema version.
## JSON shape ## Wire shape
Each combat turn contains these required fields: Each combat turn has these required fields:
| Field | Shape | | Field | Contract |
| --- | --- | | --- | --- |
| `actor` | Non-empty string. | | `actor` | Non-empty acting character or creature name. |
| `turn_kind` | One of `turn`, `reaction`, `legendary_action`, `lair_action`, or `other`. | | `turn_kind` | `turn`, `reaction`, `legendary_action`, `lair_action`, or `other`. |
| `source_refs` | Required array with at least one source reference. | | `source_refs` | One or more transcript evidence ranges. |
Source references use the shared source-reference shape: Each source reference has exactly `source_id`, `start_unit_id`, and
`end_unit_id`. It identifies an inclusive current-transcript range; unit IDs
are positive and the start may not follow the end.
```json ```json
{ {
"source_id": "session-alpha", "combat_turns": [
"start_unit_id": 1, {
"end_unit_id": 2 "actor": "Mira Thorn",
"turn_kind": "turn",
"source_refs": [
{"source_id": "session-7", "start_unit_id": 31, "end_unit_id": 32}
]
}
]
} }
``` ```
`source_id` must be non-empty and both unit IDs must be positive integers. The ## Eligibility, evidence, and normalized form
codec does not resolve references against a source document or enforce source
range ordering; those checks belong to the later source-reference validation
boundary.
## Codec behavior The extractor requires an approved [scene-description artifact](dnd-scene-description-artifacts.md).
It emits combat turns only for a chunk with an exact matching scene classified
`combat`; an exact non-combat scene produces an accepted empty list. The scene
record controls eligibility only: its title, summary, and reference do not
become turn evidence. No exact matching scene also produces an empty list and
the `scene_classification_unavailable` warning.
The codec exposes two representations of the same typed artifact: An optional normalized [NPC artifact](dnd-npc-artifacts.md) can ground an
actor name. Its registry references are provenance, never combat evidence.
Normalization trims and, where possible, canonicalizes actor names; orders and
deduplicates exact source references; orders valid-evidence turns by source
chronology; and collapses only duplicates with the same actor identity, turn
kind, and complete valid evidence. It does not infer turns, initiative, or
actions from registry or scene data.
- Candidate encode/decode preserves invalid actor and turn-kind values, The [NPC-interaction artifact](dnd-npc-interaction-artifacts.md) records
collection presence, and source references so later validators can report broader NPC occurrences. The [JSON output contract](json-output.md) defines
them. Candidate decoding still requires valid JSON, one JSON value, known publication, and [D&D module internals](../internal/dnd.md) describes routing
fields, and compatible JSON types. and validation mechanics.
- Approved encode/decode enforces the structural rules in this contract.
The codec owns the durable JSON Schema, whose object layers all set
`additionalProperties` to `false`. Codec metadata contains only
`combat_turn_count`.
The maintained compact fixture is
`internal/modules/dnd/codec/combatturns/testdata/dnd_combat_turns.v1.json`.
## Extraction boundary
The standalone extractor uses these identities:
| Property | Value |
| --- | --- |
| Extractor key | `dnd/combat-turns` |
| Capability | `dnd.combat_turns` |
| Prompt ID | `dnd.combat_turns` |
| Prompt version | `v1` |
| Private response-schema key | `dnd_combat_turns_llm` |
| Private response-schema ID | `notarius.dnd.combat_turns.llm` |
| Default profile | `gemini-2-flash` |
It requires `chunks` and `source.transcript`, accepts no options, and requires
one `scene_descriptions` reference. That reference must be exactly one approved
`dnd/scene-description-list` artifact with media type `application/json` and a
maximum size of 1 MiB (1048576 bytes). It may be an external file validated
during preparation or a canonical generated artifact supplied at an ordered
step handoff. An unbound slot is a configuration error.
The scene artifact controls eligibility, not evidence. The extractor calls the
LLM only when exactly one record has the current chunk's ID, source ID, start
unit ID, and end unit ID, and that record has `kind: combat`. An exact
`narrative`, `recap`, or `meta` record returns an accepted empty
`combat_turns` array without an LLM call, warning, or retry attempt. A missing
or mismatched exact record returns the same accepted empty result without an
LLM call or retry and emits one content-safe
`scene_classification_unavailable` warning. The scene artifact, its title and
summary, and its source references are never copied into combat turns.
For an eligible combat chunk, the prompt receives the chunk-scoped transcript
plus the existing `players`, `party`, and `glossary` inputs, and optionally the
deprecated `roster` reference through the shared party mapping. The optional
`npcs` reference is an approved normalized NPC artifact used only for identity
grounding; it never supplies combat evidence. `scene_descriptions` is never a
combat prompt input.
The private response envelope has the same turn fields and JSON types as the
durable shape except that source references contain only `start_unit_id`
and `end_unit_id`. It enforces required field presence, types, and
unknown-field rejection, while deterministic validators own enum membership,
non-empty values and collections, and positive-number requirements. The
extractor assigns the current source ID, removes exact duplicate ranges, and
stable-sorts turns by the earliest valid source-document position. Numeric unit
IDs are identifiers; source-document slice position determines chronology.
Semantically malformed candidate fields remain in the typed result for the
configured validation and retry boundary.
## Deterministic candidate validation
The standalone validator keys are:
| Validator | Responsibility |
| --- | --- |
| `extract/dnd/combat-turns/shape` | Required list, actor, turn kind, and source references, plus supported turn-kind values. |
| `extract/dnd/combat-turns/source_refs` | Source identity, source-unit existence, and range order through the source document. |
| `extract/dnd/combat-turns/source_relatedness` | At most one advisory warning per turn when the actor is not related to cited transcript text. |
Source-reference and relatedness validators defer malformed shape to the shape
validator. Relatedness also defers when any cited source range is invalid. It
combines overlapping cited ranges once in document order and compares actors
with the shared Unicode-aware NPC identity policy.
The production D&D registrar exposes the extractor and these validators. Its
default extraction chain preserves this order: JSON syntax, combat shape,
source references, private response schema, then source relatedness.
## Normalization boundary
The standalone normalizer uses key `dnd/combat-turns`, requires `merged`,
provides `normalized`, accepts no options, and accepts only the optional
structured `npcs` reference. Campaign references are LLM extraction context and
are not normalizer inputs. For an external file, the NPC registry is resolved
during preparation; for a generated binding, it is resolved at the operation-
time handoff. Runtime normalization uses that immutable prepared or handed-off
view.
Normalization policy is `dnd.combat_turns.normalize.v1`. It display-normalizes
the actor, canonicalizes exact registry actor matches, orders and deduplicates
exact source references, stable-sorts records by earliest valid source-document
position, and collapses only records with the same actor identity, turn kind,
and complete valid evidence set. The first normalized record is retained.
Invalid evidence is never eligible for duplicate collapse. Every mutation and
collapse emits a bounded warning using the merged input index in its scope.
The normalizer reports `normalization_policy` and `identity_policy` metadata
and fingerprints. An external registry may additionally contribute
`npc_registry_digest` and `npc_count`; generated registry identity is retained
in framework handoff provenance and dependency fingerprints. The
normalized-invariants validator is
`normalize/dnd/combat-turns/invariants`; it defers shape and source-reference
failures, then checks actor display normalization, canonical evidence ordering,
chronology, and duplicate identity. It rejects
with `invalid_combat_turn_normalization` under policy
`dnd.combat_turns.validator.normalized.v1`.
The production D&D registrar exposes the normalizer and normalized-invariants
validator. Its default normalization chain is JSON syntax, combat shape,
normalized invariants, source references, durable schema, then source
relatedness. The lane uses the framework's typed append-order merger and has no
merge validator chain.
## Production manifest and references
The selectable lane uses extractor and normalizer key `dnd/combat-turns`,
`appendorder` for the typed merger, and the durable codec above. Bound external
references contribute raw-file provenance to the run manifest. Generated
bindings contribute artifact kind, schema identity, media type, canonical
digest, size, and bounded producer provenance. This includes the generated
scene-description artifact for the combat extractor. Consumer metadata and
checkpoint fingerprints contain no reference names, content, paths, source
ranges, scene titles, or scene summaries. For an external scene artifact,
component metadata records the gate policy plus a semantic eligibility digest
and record count; generated scene identity remains in framework handoff
provenance and dependencies. The eligibility digest changes with scene ID,
exact source range, or kind, but not with title or summary. The normalized lane
is emitted as `lanes/<lane-id>.json` by the JSON output module, and warnings
and rejection summaries remain in their shared companion files.

147
docs/integrations/dnd-item-event-artifacts.md
View File

@@ -1,133 +1,78 @@
# D&D Item-Event Artifact Contract # D&D Item-Event Artifact
This document defines the durable D&D item-event artifact and its production This contract defines the durable item and currency occurrence list produced by
boundaries. It records source-grounded discoveries and possession changes; it `dnd/item-events`. It records source-grounded discoveries and possession
does not maintain an inventory or ledger. changes; it does not maintain an inventory, balance, or ledger.
## Artifact Identity ## Identity and compatibility
| Property | Value | | Property | Value |
| --- | --- | | --- | --- |
| Extractor key | `dnd/item-events` |
| Extract capability | `dnd.item_events` |
| Artifact kind | `dnd/item-event-list` | | Artifact kind | `dnd/item-event-list` |
| Schema ID | `notarius.dnd.item_events` | | Schema ID | `notarius.dnd.item_events` |
| Schema name | `notarius_dnd_item_events_v1` | | Schema name | `notarius_dnd_item_events_v1` |
| Schema version | `v1` | | Schema version | `v1` |
| Media type | `application/json` | | Media type | `application/json` |
| Normalizer key | `dnd/item-events` |
The payload is one strict JSON object containing a required `events` array, `v1` is a strict JSON object with required `events`; the array may be empty.
which may be empty. Objects reject unknown fields. Event and source-reference objects reject unknown fields. A future incompatible
shape requires a new schema version.
## Event Shape And Categories ## Wire shape
Every event has `name`, `kind`, and a non-empty `source_refs` array. `quantity` Every event has required `name`, `kind`, and `source_refs`. `quantity`, `from`,
is optional and, when present, is a positive integer. `from` and `to` are and `to` are optional where the event kind permits them.
optional display values whose presence depends on `kind`.
| Field | Rule | | Field | Contract |
| --- | --- | | --- | --- |
| `name` | Non-empty, transcript-supported display value. | | `name` | Non-empty item or currency display name. |
| `kind` | One of the categories below. | | `kind` | `discovered`, `acquired`, `lost`, `consumed`, or `transferred`. |
| `quantity` | Optional positive integer; omitted when the source does not establish a count. | | `quantity` | Optional positive integer; omit it when no count is established. |
| `from` | Holder that loses possession when the category permits it. | | `from` | Optional non-empty losing holder, when allowed by `kind`. |
| `to` | Holder that gains possession when the category permits it. | | `to` | Optional non-empty gaining holder, when allowed by `kind`. |
| `source_refs` | One or more current-source references. | | `source_refs` | One or more transcript evidence ranges. |
| Kind | Meaning and holder rule | Each source reference has exactly `source_id`, `start_unit_id`, and
| --- | --- | `end_unit_id`. It identifies an inclusive current-transcript range; unit IDs
| `discovered` | The party learns of or encounters an item without established possession; neither holder is present. | are positive and the start may not follow the end.
| `acquired` | A party member or `party` gains possession; `to` is required and `from` is absent. |
| `lost` | A party member or `party` ceases to possess an item without consuming it; `from` is required and `to` is absent. |
| `consumed` | Use depletes, expends, or destroys an item; `from` is required and `to` is absent. |
| `transferred` | Possession moves between distinct party members; both holders are required and neither may be `party`. |
`party` is the reserved display holder for collective party possession when an
individual holder is not established. Its comparison is case- and
Unicode-insensitive. Transfers require distinct normalized holder values.
Giving an item to an NPC, spending currency, selling an item, or another move
outside party possession is `lost`, not `transferred` or `consumed`. Monetary
spending, purchases, and payments are always `lost`. Currency is `consumed` only
when the source explicitly describes its physical destruction or expenditure as
a non-payment component. Ordinary non-depleting use is not an event.
Currency is represented as an ordinary event name plus an explicit quantity
when the transcript supplies one. Each denomination remains separate. The
artifact never converts denominations, infers a missing count, calculates a
balance, or sums nearby events.
## Source Evidence And Normalization
Each source reference contains `source_id`, `start_unit_id`, and `end_unit_id`.
It must identify an ordered range in the current source document. During
extraction, every cited range must also be wholly contained in the current
accepted chunk. Campaign references may disambiguate names, but never provide
event evidence.
The deterministic normalizer trims only display-edge whitespace in names and
holders, canonicalizes source-reference order and exact duplicate references,
then orders events by earliest valid source position and stable tie-breakers
over name, kind, holders, quantity, and complete evidence. It removes only
events with the same normalized fields and complete valid evidence sequence.
Invalid evidence is never collapsed. It does not rename, singularize, resolve
aliases, infer holders or quantities, or merge nearby events.
The default extraction validation chain is JSON syntax, item-event shape,
source references, durable JSON Schema, then advisory source relatedness. The
normalization chain adds normalized invariants after shape validation and before
source references and schema validation. Relatedness warnings are advisory so
contextual names and currency notation do not reject otherwise valid evidence.
## Representative JSON
```json ```json
{ {
"events": [ "events": [
{
"name": "Hidden Cache",
"kind": "discovered",
"source_refs": [{"source_id": "session-7", "start_unit_id": 1, "end_unit_id": 1}]
},
{ {
"name": "Silver Pieces", "name": "Silver Pieces",
"kind": "acquired", "kind": "acquired",
"quantity": 20, "quantity": 20,
"to": "party", "to": "party",
"source_refs": [{"source_id": "session-7", "start_unit_id": 2, "end_unit_id": 2}] "source_refs": [
}, {"source_id": "session-7", "start_unit_id": 2, "end_unit_id": 2}
{ ]
"name": "Torch",
"kind": "lost",
"from": "party",
"source_refs": [{"source_id": "session-7", "start_unit_id": 3, "end_unit_id": 3}]
},
{
"name": "Healing Potion",
"kind": "consumed",
"from": "Aria",
"source_refs": [{"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 4}]
},
{
"name": "Moonblade",
"kind": "transferred",
"from": "Aria",
"to": "Borin",
"source_refs": [{"source_id": "session-7", "start_unit_id": 5, "end_unit_id": 5}]
} }
] ]
} }
``` ```
## Production Boundary ## Holder rules and minimal extraction
The extractor requires `chunks` and `source.transcript`, and accepts optional `discovered` has neither holder; `acquired` requires `to` and forbids `from`;
`glossary`, `party`, `players`, and deprecated `roster` campaign references for `lost` and `consumed` require `from` and forbid `to`; `transferred` requires
disambiguation only. It has no generated NPC, scene-description, or item-registry both holders. `party` denotes collective possession. A transfer cannot use
dependency. The append-order merger preserves chunk order, and the normalizer `party` for either holder and its two normalized holders must differ.
has no reference slots.
The normalized lane is emitted as `lanes/<lane-id>.json` by the JSON output Only an evidenced discovery or possession change belongs in this artifact.
module. See [Configuration](../config.md#implemented-production-modules) for It does not infer quantities or holders, convert currency denominations,
the selectable keys and default chains, and the calculate balances, or merge nearby events. Campaign references may
[JSON output contract](json-output.md) for bundle paths. disambiguate names but are never event evidence. Currency uses the ordinary
`name` field and an explicit `quantity` only when the transcript establishes
one; each denomination remains a separate event.
Normalization trims display whitespace, orders and removes exact duplicate
source references, then orders events by valid source chronology, name identity
and display value, kind, holders, quantity, and reference sequence. It
collapses only entries with the same normalized durable fields and complete
valid evidence.
The [JSON output contract](json-output.md) defines publication. See
[D&D module internals](../internal/dnd.md) for implementation details and the
[NPC-interaction artifact](dnd-npc-interaction-artifacts.md) for a distinct
kind of occurrence.

199
docs/integrations/dnd-npc-artifacts.md
View File

@@ -1,160 +1,69 @@
# D&D NPC Artifact # D&D NPC Artifact
This document defines the durable D&D NPC-list artifact, its JSON codec, and This contract defines the durable NPC registry produced by `dnd/npcs`. It is a
the selectable production NPC pipeline. The normalized JSON payload can be minimal, source-grounded identity registry for other D&D artifacts, not a
passed explicitly to the spell extractor as an optional caster-name registry character sheet or a relationship summary.
or to the combat extractor and normalizer as an actor registry. It
remains a reference, not spell or combat evidence.
The NPC interaction extractor and normalizer also consume this registry for
canonical identity; registry source references remain provenance and never
become interaction evidence. Their occurrence contract is defined in the
[D&D NPC interaction artifact](dnd-npc-interaction-artifacts.md).
## Identity ## Identity and compatibility
- Artifact kind: `dnd/npc-list` | Property | Value |
- Durable schema ID: `notarius.dnd.npcs` | --- | --- |
- Durable schema name: `notarius_dnd_npcs_v1` | Artifact kind | `dnd/npc-list` |
- Durable schema version: `v1` | Schema ID | `notarius.dnd.npcs` |
- Media type: `application/json` | Schema name | `notarius_dnd_npcs_v1` |
- Identity policy: `dnd.npcs.identity.v1` | Schema version | `v1` |
| Media type | `application/json` |
| Identity policy | `dnd.npcs.identity.v1` |
The durable JSON Schema is owned by the D&D NPC codec. NPC IDs are derived from `v1` accepts one strict JSON object with required `npcs`; the array may be
the Unicode-normalized, case-folded canonical name using the identity policy. empty. NPC and source-reference objects reject unknown fields. A future
The durable codec enforces the artifact shape and ID syntax; registry identity incompatible artifact shape or identity policy uses a new version or policy.
validation remains a separate deterministic concern.
The extractor's private LLM response schema is a separate structural transport ## Wire shape and identity
contract. It omits framework-assigned NPC and source IDs and admits semantic
candidates for the deterministic shape and source-reference validators; it is
not part of this durable contract.
## Output Shape Each NPC has these required fields:
The payload is one object with a required top-level `npcs` array: | Field | Contract |
| --- | --- |
| `id` | `npc:sha256:` followed by 64 lowercase hexadecimal characters. |
| `name` | Non-empty canonical display name. |
| `source_refs` | One or more transcript evidence ranges for the identity. |
A source reference has exactly `source_id`, `start_unit_id`, and `end_unit_id`.
The source ID identifies the transcript, unit IDs are positive inclusive unit
identifiers, and the start may not follow the end.
```json ```json
{"npcs": []} {
"npcs": [
{
"id": "npc:sha256:99a16589618a04f535a7d21fdcc71a0b1c05d22f752cd492065b1086d97bc3d7",
"name": "Mira Thorn",
"source_refs": [
{"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
]
}
]
}
``` ```
The array may be empty. Every object and nested object rejects unknown fields. The ID is deterministic: normalize the name to Unicode NFKC, normalize the
supported apostrophe forms, collapse whitespace, case-fold it, SHA-256 the
result, then prefix the lowercase hexadecimal digest with `npc:sha256:`. Each
canonical identity and ID appears at most once. Normalization collapses records
with the same canonical identity, retains their earliest position, and merges
their canonicalized evidence; it does not add aliases, roles, descriptions, or
relationship fields.
## NPC Fields ## Scope and consumers
Each NPC contains exactly these required fields: Only individually identifiable NPC names with transcript evidence belong in
this artifact. Groups, generic roles, invented labels, and descriptive
enrichment are excluded. Its source references prove registry provenance; they
do not become evidence for a spell, interaction, or combat occurrence.
- `id`: `npc:sha256:` followed by 64 lowercase hexadecimal characters; This registry can ground actor or caster names in the [spell](dnd-spell-artifacts.md)
- `name`: the canonical display name; and [combat-turn](dnd-combat-turn-artifacts.md) artifacts. It is required to
- `source_refs`: at least one source reference supporting the NPC record. resolve the canonical `name` in an [NPC interaction](dnd-npc-interaction-artifacts.md).
The [JSON output contract](json-output.md) defines publication, and
Each source reference contains required `source_id`, `start_unit_id`, and [D&D module internals](../internal/dnd.md) owns pipeline mechanics.
`end_unit_id`; unit IDs are positive integers. Source document identity, unit
existence, and range ordering are validated by the source-reference validator
when the artifact is used by a pipeline.
## Codec Boundary
`EncodeCandidate` and `DecodeCandidate` provide strict single-value JSON
serialization while preserving typed values that still need semantic
validation. `Encode` and `Decode` are the approved-artifact boundary and
require all durable structural fields, non-empty required strings, valid source
reference shapes, and the NPC ID pattern.
Codec metadata contains only `npc_count`. Schema bytes and returned metadata
are independent values so callers cannot mutate codec-owned state.
## Production Pipeline
The production identities are:
- extractor: `dnd/npcs`;
- artifact kind: `dnd/npc-list`;
- normalizer: `dnd/npcs`; and
- durable schema: `notarius.dnd.npcs`, version `v1`, media type
`application/json`.
The extractor maps private model records to the current source identity and
assigns deterministic IDs. Extraction validation checks shape, source
references, and source relatedness. The normalizer first consolidates equal
canonical-name matches, then may make one document-level LLM-assisted identity
decision per configured normalize attempt for eligible distinctly named
records. Consolidation is name-based: it retains a supplied canonical display
name, keeps the earliest affected output position, derives its ID again, and
unions exact evidence in canonical order. Ambiguous, invalid, or conflicting
proposals are not applied; independently safe matches may still be retained.
After the retry budget is exhausted, the safe result is accepted with bounded
normalization warnings and the usual validation. The durable v1 artifact shape
does not add aliases, proposal fields, or any other semantic-normalization
representation.
The extraction prompt asks only for individually identifiable NPC names backed
by source evidence. Groups, generic roles, invented labels, and descriptive or
relationship enrichment are outside the contract.
The default extraction chain is `generic/valid_json`,
`extract/dnd/npcs/shape`, `extract/dnd/npcs/source_refs`,
`generic/valid_json_schema`, and `extract/dnd/npcs/source_relatedness`. The
default normalize chain is `generic/valid_json`, `extract/dnd/npcs/shape`,
`normalize/dnd/npcs/identity`, `extract/dnd/npcs/source_refs`,
`generic/valid_json_schema`, and `extract/dnd/npcs/source_relatedness`.
Relatedness emits bounded warnings when an NPC canonical name is not present
near its cited transcript text; opaque campaign
references may explain such a warning but do not become evidence.
## Manifest And Artifact Handoff
The NPC extractor records prompt and response-schema identities. The durable
codec records only `npc_count`; raw names, source references, and payload bytes
stay in the lane file rather than manifest
metadata. The normalized lane can be consumed by a later ordered step through
the registered canonical codec:
```yaml
steps:
- id: identify-npcs
artifacts:
npcs:
extract: dnd/npcs
normalize: dnd/npcs
scene-descriptions:
extract: dnd/scene-descriptions
normalize: dnd/scene-descriptions
- id: grounded-events
references:
npcs:
artifact:
step: identify-npcs
lane: npcs
scene_descriptions:
artifact:
step: identify-npcs
lane: scene-descriptions
artifacts:
spells:
extract: dnd/spells
normalize: dnd/spells
combat:
extract: dnd/combat-turns
normalize: dnd/combat-turns
```
The framework hands only accepted normalized artifacts across the barrier. It
validates the canonical bytes against each consumer slot and clones the NPC
operation-time reference for spell and combat consumers. The accompanying
scene-description reference is required by the combat extractor for eligibility
only; its consumer contract is defined in the
[D&D combat-turn artifact contract](dnd-combat-turn-artifacts.md). Generated
provenance records the artifact kind, schema identity, media type, canonical
digest, size, and producer step/lane/module, but not names, source ranges, or
payload bytes. External normalized files remain supported as explicit references
and retain their file provenance.
NPC source references are registry provenance and are never accepted as spell
or combat evidence. Current transcript units remain the only event evidence.
Consumers receive a separate names-only projection in normalized registry
order, for example `{"npcs":[{"name":"Mira Thorn"}]}`. The projection omits
IDs and evidence. Its digest covers the exact projected bytes and is used for
consumer-local checkpoint identity, while the full durable artifact digest
remains the manifest and generated-reference provenance identity. The unbound
projection is exactly `{"npcs":[]}` and also has a projection digest.

168
docs/integrations/dnd-npc-interaction-artifacts.md
View File

@@ -1,20 +1,38 @@
# D&D NPC Interaction Artifact # D&D NPC Interaction Artifact
This document defines the durable D&D NPC-interaction-list artifact and its This contract defines the durable occurrence list produced by
two-step production pipeline. It records discrete, source-grounded occurrences `dnd/npc-interactions`. It records discrete, source-grounded interactions with
for NPCs already accepted into a normalized NPC registry; it does not expand NPCs already present in a normalized registry; it does not extend that registry
the registry or summarize events. or summarize the session.
## Identity And JSON ## Identity and compatibility
- Artifact kind: `dnd/npc-interaction-list` | Property | Value |
- Durable schema ID: `notarius.dnd.npc_interactions` | --- | --- |
- Durable schema name: `notarius_dnd_npc_interactions_v1` | Artifact kind | `dnd/npc-interaction-list` |
- Durable schema version: `v1` | Schema ID | `notarius.dnd.npc_interactions` |
- Media type: `application/json` | Schema name | `notarius_dnd_npc_interactions_v1` |
| Schema version | `v1` |
| Media type | `application/json` |
The payload is one strict JSON object with only an `interactions` array. The `v1` is a strict JSON object with required `interactions`; the array may be
array may be empty. Each item has exactly `name`, `kind`, and `source_refs`: empty. Interaction and source-reference objects reject unknown fields. A future
incompatible shape requires a new schema version.
## Wire shape
Each interaction has these required fields:
| Field | Contract |
| --- | --- |
| `name` | Non-empty canonical display name from the required NPC registry. |
| `kind` | One of the interaction categories below. |
| `source_refs` | One or more transcript evidence ranges. |
Each source reference has exactly `source_id`, `start_unit_id`, and
`end_unit_id`. It identifies an inclusive range in the current transcript;
unit IDs are positive and the start may not follow the end. Extraction evidence
for an interaction is confined to its accepted chunk.
```json ```json
{ {
@@ -30,119 +48,31 @@ array may be empty. Each item has exactly `name`, `kind`, and `source_refs`:
} }
``` ```
`name` is the canonical display name from the required NPC registry. ## Interaction categories
`source_refs` contains one or more current-source ranges with required
`source_id`, `start_unit_id`, and `end_unit_id`; unit IDs are positive integers.
During extraction, every range must be wholly contained in the current accepted
chunk. This prevents a candidate from citing valid units that were not presented
to that extraction call.
Unknown fields are rejected.
## Interaction Categories
`kind` is exactly one of:
| Kind | Meaning | | Kind | Meaning |
| --- | --- | | --- | --- |
| `mentioned` | The NPC is referred to, but is not established as present or communicating in the evidenced passage. | | `mentioned` | The NPC is referred to but is not established as present or communicating. |
| `noncombat_presence` | The NPC is present and relevant to the passage but does not meaningfully participate in dialogue or combat. | | `noncombat_presence` | The NPC is present and relevant without meaningful dialogue or combat participation. |
| `dialogue` | The NPC speaks, responds, or is directly engaged in a meaningful non-combat exchange. | | `dialogue` | The NPC speaks, responds, or meaningfully participates in a non-combat exchange. |
| `combat_ally` | The NPC actively participates in combat on the party's side. | | `combat_ally` | The NPC actively participates in combat on the party's side. |
| `combat_opponent` | The NPC actively participates in combat against the party. | | `combat_opponent` | The NPC actively participates in combat against the party. |
| `other` | The transcript clearly establishes a direct NPC occurrence that fits none of the preceding kinds. | | `other` | A clearly evidenced direct occurrence not covered by another category. |
`other` is a residual category for positively evidenced activity, not a fallback The categories do not represent motives, relationships, state, or events that
for uncertain classification. When activities overlap, active combat the cited transcript does not establish. An `other` entry is not a substitute
participation outranks dialogue, presence, and mention; dialogue outranks for uncertain classification.
non-combat presence and mention; and non-combat presence outranks mention.
Combat alignment is not resolved by precedence: a meaningful change between
ally and opponent creates separate occurrences.
These categories do not encode summaries, relationships, state, motives, or ## Identity, evidence, and order
unobserved events.
## Occurrence Boundaries And Ordering The required normalized [NPC artifact](dnd-npc-artifacts.md) resolves `name`.
Registry references are provenance only and never replace an interaction's own
evidence. Normalization canonicalizes recognized registry names, orders and
deduplicates exact source references, then orders interactions by valid source
chronology, NPC comparison identity, display name, kind, and reference sequence.
Only entries with the same canonical name, kind, and complete valid evidence
sequence are collapsed; distinct categories or evidence remain separate.
One occurrence represents one NPC, one kind, and one locally coherent passage See the [combat-turn artifact](dnd-combat-turn-artifacts.md) for combat-action
within one accepted chunk. Repeated evidence belongs to the same occurrence occurrences and the [JSON output contract](json-output.md) for publication.
only while it supports the same uninterrupted activity. A kind change, combat Pipeline mechanics are described in [D&D module internals](../internal/dnd.md).
alignment change, intervening scene or meaningful absence, or transition from
mention to presence starts a new occurrence. Occurrences never span chunks, and
merge or normalization never semantically combines nearby, overlapping, or
cross-chunk records.
Normalization orders records by:
1. earliest valid source-document position;
2. the NPC identity comparison key;
3. the exact canonical NPC display name;
4. interaction kind in lexical order; and
5. the complete canonical source-reference sequence, ordered by source ID and
the source-document positions of each range's start and end.
Only records with identical canonical names, kinds, and complete valid evidence
sequences are duplicates. Different categories, ranges, or separately grounded
occurrences remain separate.
## Evidence, Registry, And Normalization
The registry proves only the canonical NPC identity. Its source references are
registry provenance and are never interaction evidence. Every durable
interaction must cite current transcript units supporting both the name and its
classification.
The extractor receives a names-only registry projection such as
`{"npcs":[{"name":"Mira Thorn"}]}`. The normalizer uses the full immutable
registry for exact canonical-name lookup. It canonicalizes source references
and applies the ordering and exact-duplicate rules above.
## Production Pipeline
The extractor and normalizer key is `dnd/npc-interactions`. Both require the
structured `npcs` slot, so an accepted normalized registry must come from an
earlier step:
```yaml
pipelines:
dnd-npc-interactions:
input: seriatim
steps:
- id: identify-npcs
artifacts:
npcs:
extract: dnd/npcs
normalize: dnd/npcs
- id: extract-interactions
references:
npcs:
artifact:
step: identify-npcs
lane: npcs
artifacts:
interactions:
extract: dnd/npc-interactions
normalize: dnd/npc-interactions
```
The framework passes only the accepted normalized producer. A missing, rejected,
or incompatible NPC artifact prevents the consumer step from executing. It
records generated artifact identity and bounded producer provenance without
copying registry names, source ranges, or payload content into the manifest.
## Validation And Metadata
The default extract chain is `generic/valid_json`, interaction shape, registry,
and source-reference validation, `generic/valid_json_schema`, then warning-only
source relatedness. The normalize chain runs normalized invariants after
registry validation and before source-reference and schema validation, followed
by relatedness. Normalizer and relatedness warnings are bounded and end with an
omission summary when necessary. The codec metadata contains only
`interaction_count`. Extractor metadata identifies its prompt and private
response schema; component-local checkpoint identities include the names-only
registry projection where relevant. Generated registry identity stays in
framework provenance and dependency fingerprints.
See [Configuration](../config.md#implemented-production-modules) for selectable
keys and chains, [the NPC artifact contract](dnd-npc-artifacts.md) for the
registry boundary, and the copyable
[complete D&D example](../../examples/dnd-complete.config.yml).

127
docs/integrations/dnd-scene-description-artifacts.md
View File

@@ -1,9 +1,10 @@
# D&D Scene Description Artifact Contract # D&D Scene-Description Artifact
This document defines the durable `dnd/scene-description-list` artifact This contract defines the durable output of `dnd/scene-descriptions`. Each
emitted by the D&D scene-description lane. record classifies one accepted transcript chunk and gives it a minimal
source-grounded title and summary.
## Artifact identity ## Identity and compatibility
| Property | Value | | Property | Value |
| --- | --- | | --- | --- |
@@ -13,38 +14,32 @@ emitted by the D&D scene-description lane.
| Schema version | `v1` | | Schema version | `v1` |
| Media type | `application/json` | | Media type | `application/json` |
The normalized payload is written by the JSON output module to `v1` is a strict JSON object with required non-empty `scenes`. Scene and
`lanes/<lane-id>.json`. See [JSON output](json-output.md) for the surrounding source-reference objects reject unknown fields. A future incompatible shape
output bundle. requires a new schema version.
## JSON shape ## Wire shape
The payload is a JSON object containing exactly one required field, `scenes`. Each scene has exactly these required fields:
Each scene object contains exactly these required fields:
| Field | Shape and ownership | | Field | Contract |
| --- | --- | | --- | --- |
| `id` | Non-empty accepted chunk ID, assigned by Notarius. | | `id` | Non-empty accepted chunk ID, assigned by Notarius. |
| `source_ref` | Exact inclusive accepted chunk range, assigned by Notarius. | | `source_ref` | The assigned inclusive source range for that chunk. |
| `kind` | One of `combat`, `narrative`, `recap`, or `meta`. | | `kind` | `combat`, `narrative`, `recap`, or `meta`. |
| `title` | Non-empty, trimmed, source-grounded title. | | `title` | Non-empty, trimmed, source-grounded title. |
| `summary` | Non-empty, trimmed, source-grounded summary. | | `summary` | Non-empty, trimmed, source-grounded summary. |
All object layers reject unknown fields. The `scenes` array must be present and `source_ref` has exactly `source_id`, `start_unit_id`, and `end_unit_id`.
non-empty. `source_ref` has exactly `source_id`, `start_unit_id`, and Its source ID identifies the input transcript; its positive unit IDs identify
`end_unit_id`; its source ID is non-empty and its unit IDs are positive the chunk's inclusive range, with the start no later than the end.
integers.
```json ```json
{ {
"scenes": [ "scenes": [
{ {
"id": "chunk-000001", "id": "chunk-000001",
"source_ref": { "source_ref": {"source_id": "session-7", "start_unit_id": 1, "end_unit_id": 3},
"source_id": "session-alpha",
"start_unit_id": 1,
"end_unit_id": 3
},
"kind": "narrative", "kind": "narrative",
"title": "Arrival at the watchtower", "title": "Arrival at the watchtower",
"summary": "The party reaches the ruined watchtower and begins to investigate it." "summary": "The party reaches the ruined watchtower and begins to investigate it."
@@ -53,78 +48,22 @@ integers.
} }
``` ```
`id` and `source_ref` are application-owned identity and evidence. The model ## Meaning and normalized form
provides only `kind`, `title`, and `summary`; it is not asked for chunk IDs,
source IDs, unit IDs, ranges, participants, or confidence.
## Scene kinds `combat` identifies a chunk where active combat is the central activity.
`narrative` is current in-world play that is not principally combat, recap, or
meta discussion. `recap` is primarily a recounting of an earlier session, and
`meta` is primarily out-of-character discussion. The artifact does not add
participants, confidence, events, or information absent from the chunk.
| Kind | Meaning | Normalization trims title and summary, orders scenes by source position and
| --- | --- | then ID, and removes exact duplicate records. A reused ID with different
| `combat` | Active combat is a substantive central activity. | durable fields, or the same source range with different kind, title, or
| `narrative` | Current-session in-world play that is not principally combat, recap, or meta discussion. | summary, is invalid. It does not merge adjacent ranges, alter prose, or infer
| `recap` | The table is primarily recounting a previous session. | missing scenes.
| `meta` | Sustained out-of-character discussion is the scene's primary purpose. |
For a mixed accepted chunk, classification prefers `combat`, then `recap`, The [combat-turn artifact](dnd-combat-turn-artifacts.md) uses an exact matching
then `meta`, then `narrative`. Brief table talk, rules clarification, or a `combat` scene only as eligibility control; scene title, summary, and source
short recollection does not replace the main current-session activity. reference never become combat evidence. Publication is defined by the
[JSON output contract](json-output.md); implementation details live in
## Extraction and evidence [D&D module internals](../internal/dnd.md).
The extractor runs once for each accepted chunk and maps one successful model
response to one scene record. It copies the current chunk ID and exact chunk
range, preserves the model kind without repair, and trims only surrounding
whitespace from title and summary. A model response cannot represent an empty
result; extraction failure follows the configured retry and rejection policy.
Optional `players`, `party`, and `glossary` campaign references can help
disambiguate names or setting terms. They never supply scene evidence or add
events absent from the accepted chunk. The lane requires no NPC registry or
other generated artifact reference.
## Merge and normalization
Accepted per-chunk lists are appended in chunk order. Normalization then:
1. validates the current-source range, non-empty ID and prose, and closed kind;
2. trims only title and summary whitespace;
3. sorts records by source-document start position, then ID;
4. removes records only when all five durable fields are identical;
5. rejects a reused ID when any remaining durable field differs; and
6. rejects the same exact range when `kind`, `title`, or `summary` differs.
Two different IDs with the same range and identical model-owned content remain
separate records. Normalization does not join adjacent ranges, rewrite prose,
repair kinds, infer missing scenes, or use chunk annotations.
## Validation and warnings
Extraction validation requires exactly one record with an ID and range exactly
equal to its current chunk. Later validation checks source membership without a
current chunk. Shape, source-range, kind, ID, and normalized-invariant failures
reject the artifact.
Relatedness checks are advisory. They separately warn when a scene title or
summary has no significant lexical token in its cited transcript range. The
check ignores short tokens and common function words, uses transcript text only,
and does not treat campaign references as evidence. Warning diagnostics are
bounded and do not copy transcript or campaign-reference content.
## Configuration
Use `dnd/scenes` to form accepted scene chunks, then select
`dnd/scene-descriptions` for extraction and normalization. The maintained
[complete D&D configuration](../../examples/dnd-complete.config.yml) includes
this lane alongside the other D&D artifacts. Selectable keys and default
validator chains are defined in [Configuration](../config.md).
## Downstream combat use
The combat-turn extractor consumes this approved artifact as required
eligibility control context through an explicit ordered reference binding. It
uses only an exact chunk ID and source-range match with `kind: combat` to permit
combat extraction; titles, summaries, and scene references do not become combat
prompt material or evidence. The complete downstream behavior, including empty
results and warnings for unavailable coverage, is defined in the
[D&D combat-turn artifact contract](dnd-combat-turn-artifacts.md).

241
docs/integrations/dnd-spell-artifacts.md
View File

@@ -1,204 +1,73 @@
# D&D Spell Artifact # D&D Spell Artifact
This document is the durable serialized artifact contract for the production This contract defines the durable output of the `dnd/spells` extractor and
D&D spell extractor. Selectable extractor keys are cataloged in normalizer. It records source-grounded spell-casting occurrences; it is not a
[Configuration](../config.md#implemented-production-modules). spellbook, a rules lookup result, or a record of hypothetical casts.
## Identity ## Identity and compatibility
- Artifact kind: `dnd/spell-list` | Property | Value |
- Prompt ID: `dnd.spells`
- Response schema key: `dnd_spells`
- Response schema ID: `notarius.dnd.spells`
- Response schema name: `notarius_dnd_spells_v1`
- Response schema version: `v1`
- Media type: `application/json`
The durable JSON Schema is owned by the D&D spell artifact codec. The
extractor's private LLM response schema is a separate transport contract: its
source-reference objects omit `source_id`, which the extractor assigns while
mapping the response to the canonical artifact. The LLM DTO and transport
schema are not part of this durable contract. The private schema owns required
fields, JSON types, object and array shapes, and unknown-field rejection;
deterministic validators own the durable artifact's semantic constraints.
The output contains canonical spell casts derived from transcript evidence.
Source IDs are assigned from the input identity; source-unit ranges identify
the evidence location.
## Output Shape
The extractor payload is a JSON object with one required top-level array. Its
structure is:
```text
{"spell_casts": [<spell-cast object>, ...]}
```
`spell_casts` must be present. It may be empty when no spell casts are found.
When multiple chunk results are combined, spell casts remain in chunk order.
When the payload is written as durable output, its logical path is derived from
the configured artifact lane ID as defined by the
[JSON output contract](json-output.md#output-payload-files).
## Spell-Cast Fields
Each spell cast contains exactly these required fields:
- `caster`: in-world character or creature casting the spell;
- `spell`: spell name;
- `source_refs`: transcript source references with extractor-assigned source
IDs and evidence unit ranges. It must contain at least one entry.
Both string fields must be non-empty. `caster` is the canonical in-world
caster, not the human player, transcript speaker, or GM when the associated
character or creature can be identified. Player and party references may
disambiguate that identity, but do not independently establish that a cast
occurred. The `spell` value must resolve through the effective SRD-plus-overlay
catalog as either a canonical name or alias. Catalog validation accepts aliases
but does not rewrite them; unknown fields are rejected.
The artifact includes an actual casting event or an unambiguous declared
casting attempt. Spell mentions, hypothetical plans, rules discussion, and
catalog matches without a casting event are excluded. The spell catalog is a
name-recognition policy and never evidence that a cast occurred.
## Source References
Each source reference contains exactly three required fields: `source_id`,
`start_unit_id`, and `end_unit_id`. The source ID must match the input identity.
The unit IDs must be positive integers present in the input, and the start unit
must not appear after the end unit. Unknown fields are rejected.
For each cast, the complete `source_refs` collection identifies the transcript
evidence for the caster, spell name, and occurrence of the cast or declared
attempt. The deterministic validators establish that ranges are structurally
valid and that the spell name is related to cited text. Semantic evidence
sufficiency is an extraction policy and remains subject to evaluation rather
than deterministic proof.
Reference slot keys and accepted file types are defined in
[Configuration](../config.md#implemented-production-modules). References are
supporting disambiguation material, not source evidence, and are not
addressable through `source_refs`.
## Optional NPC Grounding
The `dnd/spells` extractor accepts an optional `npcs` reference containing one
normalized NPC artifact as `application/json`, up to 1 MiB. An external file is
validated during preparation; an ordered generated binding is validated at the
step handoff. Both paths use the approved NPC codec and identity policy,
re-encode canonical durable JSON for registry provenance, and supply only the
registry's ordered names as the operation-time spell prompt input. It helps the
model prefer canonical caster names; it does not establish that a spell was
cast.
NPC source references may identify the run that produced the registry or any
other session. They remain registry provenance and are never copied into a
spell cast's `source_refs`; every spell evidence range must still identify the
current transcript. Generated provenance records producer and canonical
artifact identity without payload content or a path. When the slot is absent,
the prompt receives exactly `{"npcs":[]}` with its projection digest, and the
run has no NPC reference provenance.
## Normalization Behavior
When the `dnd/spells` normalizer is selected, each recognized spell name is
rewritten to the effective catalog's canonical display name. Lookup uses the
catalog's case-insensitive, whitespace-normalizing, apostrophe-normalizing, and
alias rules. Unknown names are preserved exactly for the normalize validators;
the normalizer does not guess or apply fuzzy matching.
Each cast's `source_refs` is copied, sorted by exact `source_id`,
`start_unit_id`, and `end_unit_id`, and stripped of exact structural
duplicates. Adjacent or overlapping ranges are not merged, and the normalizer
does not synthesize references or change their boundaries.
After those per-cast changes, duplicate identity requires the same canonical
spell name, the same caster after case folding and whitespace normalization,
and the same complete, non-empty set of source references valid for the source
document. Only the first occurrence is retained, in stable order. Its caster
and canonical references are preserved. Unknown names, empty or invalid
evidence, and casts with different evidence remain separate.
Mutation and duplicate decisions are returned through the normal warnings
surface. Warning scopes use the merged input index, such as `spell_casts[0]`,
so they remain meaningful even when a later duplicate is removed. The
normalizer uses these reason codes:
| Reason code | Meaning |
| --- | --- | | --- | --- |
| `spell_name_canonicalized` | A catalog lookup replaced an input name with its canonical display name. | | Artifact kind | `dnd/spell-list` |
| `spell_name_unresolved` | A name was not found in the effective catalog and was retained unchanged. | | Schema ID | `notarius.dnd.spells` |
| `source_references_normalized` | Reference order changed or exact duplicate references were removed. | | Schema name | `notarius_dnd_spells_v1` |
| `duplicate_spell_cast_collapsed` | A later cast matched the retained cast's complete duplicate identity. | | Schema version | `v1` |
| Media type | `application/json` |
Only warnings from an accepted normalize attempt are promoted to `v1` is a single strict JSON object. It requires `spell_casts`; the array may
`warnings.json`. If an unresolved name reaches the default normalize validator be empty. Each spell-cast object and source-reference object rejects unknown
chain, the catalog validator rejects the candidate with `unknown_spell`; the fields. A future incompatible shape requires a new schema version.
`spell_name_unresolved` warning remains in the attempt's debug artifact. An
explicit validator override that accepts the candidate promotes the unresolved
warning normally.
The default extraction and normalization chains both preserve this registered ## Wire shape
order: JSON syntax, spell shape, catalog membership, source references, JSON
Schema, then source relatedness. Extraction validates the private response
schema; normalization validates the durable artifact schema.
## Manifest Metadata Each `spell_casts` entry has these required fields:
The extractor adds prompt and response-schema provenance under the artifact lane | Field | Contract |
manifest metadata: | --- | --- |
| `caster` | Non-empty in-world character or creature name. |
| `spell` | Non-empty spell name. |
| `source_refs` | One or more transcript evidence ranges. |
Every source reference has exactly `source_id`, `start_unit_id`, and
`end_unit_id`. The source ID identifies the input transcript; the unit IDs are
positive inclusive unit identifiers, and the start may not follow the end in
that source. References are evidence for the cast, not campaign-reference or
NPC-registry provenance.
```json ```json
{ {
"metadata": { "spell_casts": [
"extractor": { {
"prompt_id": "dnd.spells", "caster": "Mira Thorn",
"prompt_version": "v1", "spell": "Fireball",
"prompt_sha256": "sha256:...", "source_refs": [
"response_schema_key": "dnd_spells", {"source_id": "session-7", "start_unit_id": 12, "end_unit_id": 13}
"response_schema_id": "notarius.dnd.spells", ]
"response_schema_name": "notarius_dnd_spells_v1",
"response_schema_version": "v1",
"response_schema_sha256": "sha256:...",
"catalog_base_id": "dnd-5e-2014-srd-spells",
"catalog_digest": "sha256:...",
"catalog_overlay_ids": ["campaign.example"],
"npc_registry_digest": "sha256:...",
"npc_count": 3
},
"normalizer": {
"catalog_base_id": "dnd-5e-2014-srd-spells",
"catalog_digest": "sha256:...",
"catalog_overlay_ids": ["campaign.example"]
} }
} ]
} }
``` ```
`catalog_digest` identifies the effective semantic catalog, while ## Evidence and normalized form
`catalog_overlay_ids` is sorted and empty for a base-only configuration. Raw
prompt, schema, catalog, alias, and local overlay-file content are not
included in manifest metadata. The `normalizer` metadata uses the same catalog
identity fields when that module is selected. Overlay origin, media type, byte
size, and raw digest are recorded separately in the manifest's reference
provenance; see the [JSON output contract](json-output.md#manifestjson).
The `npc_registry_digest` and `npc_count` fields in the example are present for An entry represents an actual cast or an unambiguous declared attempt. A spell
an external NPC registry when the extractor publishes its prepared module mention, rules discussion, plan, or catalog match alone is not an occurrence.
metadata. They contain no NPC names, source references, paths, or raw The configured catalog checks the name; it does not establish evidence.
bytes. A generated registry's identity is instead represented by the framework
handoff provenance and dependency fingerprint, so the consumer module metadata
does not duplicate it.
The extractor's prompt hash, private response-schema hash, and effective catalog When normalization is selected, recognized spell names use the effective
digest also contribute independently scoped semantic checkpoint fingerprints. catalog's canonical display name. Source references are put in canonical source
Changing any of those prepared contracts intentionally produces a cold order and exact duplicate references are removed. A later entry is collapsed
checkpoint miss. Fingerprints contain only digests, never prompt, schema, only when it has the same canonical spell, the same case- and
catalog, or reference content. When an NPC registry is bound, its semantic whitespace-insensitive caster identity, and the same complete valid reference
digest contributes an additional local `npc_registry` fingerprint for an sequence. Remaining entries retain their merged order.
external binding; the manifest metadata contains only that digest and
`npc_count`. Raw NPC file provenance remains independently recorded in the The optional normalized [NPC artifact](dnd-npc-artifacts.md) can ground a
manifest's `references` list. Generated bindings contribute the canonical caster name. Its own references remain registry provenance and are never copied
artifact dependency fingerprint and bounded producer provenance instead. into `source_refs`.
## Related contracts
The [spell-catalog overlay contract](dnd-spell-catalog-overlays.md) defines
the configured catalog additions. The [JSON output contract](json-output.md)
defines where this logical artifact is published; [D&D module internals](../internal/dnd.md)
describes extraction and validation mechanics.