Register item registry normalization

This commit is contained in:
2026-08-05 19:39:06 +00:00
parent ad9ee076b5
commit f91237e9c0
19 changed files with 1165 additions and 15 deletions

View File

@@ -0,0 +1,2 @@
Item candidates:
{{ input "candidates" }}

View File

@@ -0,0 +1,8 @@
Use candidate names and cited transcript windows only to determine whether
candidates identify the same item type or unique designation. Do not treat
nearby evidence, similar objects, or a shared owner as sufficient. Keep
currency denominations, materially different item types, and uncertain aliases
separate. Do not infer an item property or uniqueness.
When selecting a canonical display name, choose one supplied candidate name
that is the clearest established designation.

View File

@@ -0,0 +1,30 @@
id: dnd.item_registry.normalize
version: "v1"
default_profile: dnd-extraction
inputs:
- name: candidates
required: true
content_type: application/json
- name: transcript
required: true
content_type: application/json
messages:
- role: system
content_file: ./sharedassets/common-dnd-system.md
- role: user
content_file: ./instructions.md
- role: user
content_file: ./sharedassets/common-dnd-entity-reconciliation.md
cache_control:
type: ephemeral
- role: user
content_file: ./candidates.md
- role: user
content_file: ./sharedassets/common-dnd-transcript-windows.md
cache_control:
type: ephemeral
output:
format: json
validation_mode: json_schema
schema_path: dnd_entity_reconcile_llm.v1.json
repair_attempts: 0

View File

@@ -404,16 +404,16 @@ generated bindings.
| --- | --- |
| Input | **seriatim** |
| Chunk | **generic**, **dnd/scenes** |
| Extract | **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
| Extract | **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-events**, **dnd/item-registry**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
| Merge | **appendorder** |
| Normalize | **noop**, **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-events**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
| Normalize | **noop**, **dnd/spells**, **dnd/npc-registry**, **dnd/combat-turns**, **dnd/item-events**, **dnd/item-registry**, **dnd/npc-occurrences**, **dnd/scene-descriptions**, **dnd/enemy-events**, **dnd/location-registry**, **dnd/location-occurrences** |
| Output | **json** |
`dnd/location-registry` extraction and normalization are `llm_backed`; location
normalization may use the pipeline's selected LLM profile for bounded duplicate
proposals. `dnd/location-occurrences` extraction is `llm_backed`, while its
normalizer is `deterministic`. The complete example binds the registry in one
step and the occurrence lane in the next.
`dnd/location-registry` and `dnd/item-registry` extraction and normalization
are `llm_backed`; their normalizers may use the pipeline's selected LLM profile
for bounded duplicate proposals. `dnd/location-occurrences` extraction is
`llm_backed`, while its normalizer is `deterministic`. The complete example
binds the location registry in one step and the occurrence lane in the next.
The D&D artifact contracts define each emitted schema:
[spells](integrations/dnd-spell-artifacts.md),
@@ -421,6 +421,7 @@ The D&D artifact contracts define each emitted schema:
[NPC occurrences](integrations/dnd-npc-occurrence-artifacts.md),
[combat turns](integrations/dnd-combat-turn-artifacts.md),
[item events](integrations/dnd-item-event-artifacts.md),
[item registry](integrations/dnd-item-registry-artifacts.md),
[scene descriptions](integrations/dnd-scene-description-artifacts.md), and
[enemy events](integrations/dnd-enemy-event-artifacts.md),
[location registry](integrations/dnd-location-registry-artifacts.md), and
@@ -437,6 +438,7 @@ Available validator keys are:
| NPC registry | **extract/dnd/npc-registry/shape**, **extract/dnd/npc-registry/source_refs**, **extract/dnd/npc-registry/source_relatedness**, **normalize/dnd/npc-registry/identity** |
| Combat turns | **extract/dnd/combat-turns/shape**, **extract/dnd/combat-turns/source_refs**, **extract/dnd/combat-turns/source_relatedness**, **normalize/dnd/combat-turns/invariants** |
| Item events | **extract/dnd/item-events/shape**, **extract/dnd/item-events/source_refs**, **extract/dnd/item-events/source_relatedness**, **normalize/dnd/item-events/invariants** |
| Item registry | **extract/dnd/item-registry/shape**, **extract/dnd/item-registry/source_refs**, **extract/dnd/item-registry/source_relatedness**, **normalize/dnd/item-registry/identity** |
| NPC occurrences | **extract/dnd/npc-occurrences/shape**, **extract/dnd/npc-occurrences/registry**, **extract/dnd/npc-occurrences/source_refs**, **extract/dnd/npc-occurrences/source_relatedness**, **normalize/dnd/npc-occurrences/invariants** |
| Scene descriptions | **extract/dnd/scene-descriptions/shape**, **extract/dnd/scene-descriptions/source_refs**, **extract/dnd/scene-descriptions/source_relatedness**, **normalize/dnd/scene-descriptions/invariants** |
| Enemy events | **extract/dnd/enemy-events/shape**, **extract/dnd/enemy-events/engagements**, **extract/dnd/enemy-events/source_refs**, **extract/dnd/enemy-events/source_relatedness**, **normalize/dnd/enemy-events/invariants** |
@@ -453,6 +455,7 @@ same at both stages.
| NPC registry | generic/valid_json, extract/dnd/npc-registry/shape, extract/dnd/npc-registry/source_refs, generic/valid_json_schema, extract/dnd/npc-registry/source_relatedness | generic/valid_json, extract/dnd/npc-registry/shape, normalize/dnd/npc-registry/identity, extract/dnd/npc-registry/source_refs, generic/valid_json_schema, extract/dnd/npc-registry/source_relatedness |
| Combat turns | generic/valid_json, extract/dnd/combat-turns/shape, extract/dnd/combat-turns/source_refs, generic/valid_json_schema, extract/dnd/combat-turns/source_relatedness | generic/valid_json, extract/dnd/combat-turns/shape, normalize/dnd/combat-turns/invariants, extract/dnd/combat-turns/source_refs, generic/valid_json_schema, extract/dnd/combat-turns/source_relatedness |
| Item events | generic/valid_json, extract/dnd/item-events/shape, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness | generic/valid_json, extract/dnd/item-events/shape, normalize/dnd/item-events/invariants, extract/dnd/item-events/source_refs, generic/valid_json_schema, extract/dnd/item-events/source_relatedness |
| Item registry | generic/valid_json, extract/dnd/item-registry/shape, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness | generic/valid_json, extract/dnd/item-registry/shape, normalize/dnd/item-registry/identity, extract/dnd/item-registry/source_refs, generic/valid_json_schema, extract/dnd/item-registry/source_relatedness |
| NPC occurrences | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness | generic/valid_json, extract/dnd/npc-occurrences/shape, extract/dnd/npc-occurrences/registry, normalize/dnd/npc-occurrences/invariants, extract/dnd/npc-occurrences/source_refs, generic/valid_json_schema, extract/dnd/npc-occurrences/source_relatedness |
| Scene descriptions | generic/valid_json, extract/dnd/scene-descriptions/shape, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness | generic/valid_json, extract/dnd/scene-descriptions/shape, normalize/dnd/scene-descriptions/invariants, extract/dnd/scene-descriptions/source_refs, generic/valid_json_schema, extract/dnd/scene-descriptions/source_relatedness |
| Enemy events | generic/valid_json, extract/dnd/enemy-events/shape, extract/dnd/enemy-events/engagements, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness | generic/valid_json, extract/dnd/enemy-events/shape, normalize/dnd/enemy-events/invariants, extract/dnd/enemy-events/source_refs, generic/valid_json_schema, extract/dnd/enemy-events/source_relatedness |

View File

@@ -0,0 +1,86 @@
# D&D Item Registry Artifact
This contract defines the durable, source-grounded item registry produced by
`dnd/item-registry`. It records transcript-established item types and unique
designations for one source document; it is not an inventory, holder record,
quantity ledger, or item-occurrence artifact.
## Identity and compatibility
| Property | Value |
| --- | --- |
| Artifact kind | `dnd/item-registry` |
| Schema ID | `notarius.dnd.item_registry` |
| Schema name | `notarius_dnd_item_registry_v1` |
| Schema version | `v1` |
| Media type | `application/json` |
| Identity policy | `dnd.item_registry.identity.v1` |
`v1` accepts one strict JSON object with required `items`; the array may be
empty. Item and source-reference objects reject unknown fields. An incompatible
artifact shape or identity-policy change uses a new version or policy.
## Wire shape and identity
Each item has these required fields:
| Field | Contract |
| --- | --- |
| `id` | `item:sha256:` followed by 64 lowercase hexadecimal characters. |
| `name` | Non-empty transcript-established item type or unique designation. |
| `source_refs` | One or more transcript evidence ranges that establish the item. |
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
{
"items": [
{
"id": "item:sha256:31e73b6280ef98e4d8070e07fd4de9b2c3e842cc03af1a09ca631cb95b73e3b3",
"name": "Star Compass",
"source_refs": [
{"source_id": "session-7", "start_unit_id": 4, "end_unit_id": 5}
]
}
]
}
```
The ID is deterministic for an item name or type, rather than for one physical
instance. Notarius normalizes the display name for comparison with Unicode
NFKC, supported apostrophe normalization, collapsed whitespace, and case
folding. It hashes compact JSON for this array:
```text
["dnd.item_registry.identity.v1", comparison_name]
```
The canonical ID is the lowercase SHA-256 digest of those bytes with the
`item:sha256:` prefix. Equal comparison names represent one item identity;
normalization unions their transcript evidence when it safely consolidates a
candidate group.
## Scope, reconciliation, and evidence
The registry includes named unique items, concrete reusable item types, stable
unique designations, and separately established currency denominations. It
excludes vague loot or treasure, generic weapons, quantities, inferred
properties, and inferred uniqueness. Capitalization alone does not establish
eligibility.
Normalization first applies deterministic display, evidence, and ID rules. It
then may use a bounded LLM-assisted proposal to reconcile semantically duplicate
records. The proposal may choose only a supplied candidate display name;
invalid, uncertain, overlapping, or unsafe proposals retain the deterministic
result with retry or fallback diagnostics. Currency denominations, materially
different item types, and merely nearby objects remain distinct. Source
references establish registry provenance, not evidence for later artifacts.
## Publication
The registry is a selectable D&D artifact. See
[Configuration](../config.md#production-module-keys) for module keys and
validator chains, and the [JSON output contract](json-output.md) for
publication. It does not yet define a consumer handoff contract.

View File

@@ -7,7 +7,7 @@ selectable keys, bindings, reference syntax, and default validator chains.
## Durable Artifact Contracts
The nine lanes have separate durable wire contracts. This guide deliberately
The ten lanes have separate durable wire contracts. This guide deliberately
does not repeat their JSON shapes or schemas.
| Lane | Durable contract |
@@ -16,6 +16,7 @@ does not repeat their JSON shapes or schemas.
| NPC registry | [NPC registry artifacts](../integrations/dnd-npc-registry-artifacts.md) |
| Combat turns | [combat-turn artifacts](../integrations/dnd-combat-turn-artifacts.md) |
| Item events | [item-event artifacts](../integrations/dnd-item-event-artifacts.md) |
| Item registry | [item-registry artifacts](../integrations/dnd-item-registry-artifacts.md) |
| NPC occurrences | [NPC-occurrence artifacts](../integrations/dnd-npc-occurrence-artifacts.md) |
| Scene descriptions | [scene-description artifacts](../integrations/dnd-scene-description-artifacts.md) |
| Enemy events | [enemy-event artifacts](../integrations/dnd-enemy-event-artifacts.md) |
@@ -28,7 +29,7 @@ The D&D registrar registers the familys artifact codecs, extractors, typed
append-order mergers, normalizers, validators, prompt assets, fallback LLM
profile asset, and default validator chains. Each extractor and normalizer has
a stable module spec, explicit execution class, strict option decoding, and a
typed builder. Scene chunking, every extractor, NPC normalization, and location
typed builder. Scene chunking, every extractor, and NPC, location, and item-registry
normalization are registered as `llm_backed`; the remaining current D&D mergers
and normalizers are `deterministic`. The metadata is available to catalog inspection and
resolved-pipeline debug data and determines which selected bindings inherit the
@@ -163,6 +164,7 @@ shared helper changes.
| NPCs | Does not consume an NPC registry. Its normalizer is the LLM-assisted reconciliation exception described above. |
| Combat turns | Requires a scene-description artifact. It calls the LLM only for an exact `combat` classification; exact non-combat classifications return an accepted empty result, while missing or mismatched classifications return an empty result with a bounded warning. Optional NPC grounding never becomes evidence. |
| Item events | Uses campaign context for disambiguation but has no NPC-registry or scene-description dependency. |
| Item registry | Produces source-grounded item types and unique designations. Its LLM-assisted reconciliation is proposal-only, preserves distinct currency denominations and item types, and does not create per-instance identities. |
| NPC occurrences | Requires the normalized NPC registry at extraction and normalization, using it for canonical actor grounding only. |
| Scene descriptions | Produces the classifications consumed by combat routing; it does not consume an NPC registry or provide evidence for combat artifacts. |
| Enemy events | Requires NPC, scene-description, combat-turn, and NPC-occurrence artifacts. It calls the LLM only for an exact `combat` classification, records ordered observations rather than terminal state, and normalizes recognized names through the NPC registry while preserving grounded collective labels. |

View File

@@ -0,0 +1,350 @@
// Package itemregistry normalizes merged D&D item-registry candidates conservatively.
package itemregistry
import (
"context"
"errors"
"fmt"
"reflect"
"sort"
"strconv"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/entityreconcile"
)
const (
Key = "dnd/item-registry"
PromptID = "dnd.item_registry.normalize"
normalizationPolicy = "dnd.item_registry.normalize.v1"
semanticContextPolicy = "dnd.entity_reconcile.context.v1"
semanticContextRadius = 2
NormalizationPolicy = normalizationPolicy
ReasonCodeItemFieldsNormalized = "item_fields_normalized"
ReasonCodeItemIDRecomputed = "item_id_recomputed"
ReasonCodeSourceReferencesNormalized = "source_references_normalized"
ReasonCodeDuplicateItemCollapsed = "duplicate_item_collapsed"
ReasonCodeItemSemanticProposalInvalid = "item_semantic_proposal_invalid"
ReasonCodeItemSemanticReconciliationExhausted = "item_semantic_reconciliation_exhausted"
ReasonCodeItemNormalizationWarningsOmitted = "item_normalization_warnings_omitted"
)
var requiredCapabilities = []string{"merged"}
var providedCapabilities = []string{"normalized"}
var _ contracts.Normalizer[dnd.ItemRegistry] = (*Normalizer)(nil)
var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)
type Options struct{}
type Normalizer struct {
llm contracts.StructuredLLMClient
promptSHA string
responseSchemaSHA string
}
func New(llmClient contracts.StructuredLLMClient, _ Options) (*Normalizer, error) {
if llmClient == nil {
return nil, normalizerErrorf("LLM client must not be nil")
}
promptSHA, err := promptAssetMetadata()
if err != nil {
return nil, normalizerErrorf("load prompt metadata: %w", err)
}
responseSchema, err := entityreconcile.LoadResponseSchema()
if err != nil {
return nil, normalizerErrorf("load response schema: %w", err)
}
return &Normalizer{llm: llmClient, promptSHA: promptSHA, responseSchemaSHA: responseSchema.SHA256}, nil
}
func (n *Normalizer) Key() string { return Key }
func (n *Normalizer) ReferenceSlots() []contracts.ReferenceSlot { return nil }
func (n *Normalizer) ManifestMetadata() map[string]any {
if n == nil {
return nil
}
return map[string]any{
"prompt_id": PromptID, "prompt_version": entityreconcile.SchemaVersion, "prompt_sha256": n.promptSHA,
"response_schema_key": string(entityreconcile.ResponseSchemaKey), "response_schema_id": entityreconcile.ResponseSchemaID,
"response_schema_name": entityreconcile.ResponseSchemaName, "response_schema_version": entityreconcile.SchemaVersion,
"response_schema_sha256": n.responseSchemaSHA, "identity_policy": identity.Policy,
"normalization_policy": normalizationPolicy, "semantic_context_policy": semanticContextPolicy, "semantic_context_radius": semanticContextRadius,
}
}
func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if n == nil {
return nil
}
return []pipeline.CheckpointFingerprint{
{Name: "prompt", Value: n.promptSHA}, {Name: "response_schema", Value: n.responseSchemaSHA},
{Name: "identity_policy", Value: identity.Policy}, {Name: "normalization_policy", Value: normalizationPolicy},
{Name: "semantic_context_policy", Value: fmt.Sprintf("%s:%d", semanticContextPolicy, semanticContextRadius)},
}
}
func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalizeRequest[dnd.ItemRegistry]) (contracts.TypedNormalizeResult[dnd.ItemRegistry], error) {
if n == nil {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("normalizer must not be nil")
}
if n.llm == nil {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("LLM client must not be nil")
}
if ctx == nil {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("context error before normalize: %w", err)
}
order := shared.NewSourceRefOrder(req.Source)
records, warnings := preprocessRecords(req.MergeOutput.Value, order)
deterministic := recordList(records)
materials, ready, err := entityreconcile.BuildContext(req.Source, reconciliationCandidates(records), semanticContextRadius)
if err != nil {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("build semantic context: %w", err)
}
if !ready {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{Value: deterministic, Warnings: limitWarnings(warnings)}, nil
}
var response entityreconcile.ProposalResponse
if _, err := n.llm.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
StageName: Key, PromptID: PromptID, PromptVersion: entityreconcile.SchemaVersion,
ProfileID: req.LLMProfile, SessionID: req.SessionID,
Inputs: contracts.LLMInputSet{"candidates": materials.Candidates, "transcript": materials.Transcript},
}, &response); err != nil {
if errors.Is(err, contracts.ErrInvalidStructuredOutput) {
return n.invalidStructuredResult(deterministic, warnings), nil
}
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{}, normalizerErrorf("complete structured output: %w", err)
}
assessment := materials.Assess(response)
applied, semanticWarnings, rejectedGroups := applySafeGroups(records, reconciliationGroups(assessment, materials.CandidateKeys()), order)
warnings = append(warnings, semanticWarnings...)
if rejectedGroups > 0 {
return currencyRetryResult(recordList(applied), warnings, rejectedGroups), nil
}
if assessment.DiscardedGroups() == 0 {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{Value: recordList(applied), Warnings: limitWarnings(warnings)}, nil
}
return retryResult(recordList(applied), warnings, assessment), nil
}
func (n *Normalizer) invalidStructuredResult(value dnd.ItemRegistry, warnings []contracts.Warning) contracts.TypedNormalizeResult[dnd.ItemRegistry] {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{Value: value, Warnings: limitWarningsForRetry(warnings), Retry: &contracts.NormalizeRetry{
ReasonCode: ReasonCodeItemSemanticProposalInvalid, Message: "semantic proposal requires retry: invalid structured output",
FallbackWarnings: []contracts.Warning{semanticFallbackWarning(-1)},
}}
}
func retryResult(value dnd.ItemRegistry, warnings []contracts.Warning, assessment entityreconcile.Assessment) contracts.TypedNormalizeResult[dnd.ItemRegistry] {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{Value: value, Warnings: limitWarningsForRetry(warnings), Retry: &contracts.NormalizeRetry{
ReasonCode: ReasonCodeItemSemanticProposalInvalid, Message: diagnostics.Aggregate("semantic proposal requires retry", reconciliationIssues(assessment)),
FallbackWarnings: []contracts.Warning{semanticFallbackWarning(assessment.DiscardedGroups())},
}}
}
func currencyRetryResult(value dnd.ItemRegistry, warnings []contracts.Warning, rejectedGroups int) contracts.TypedNormalizeResult[dnd.ItemRegistry] {
return contracts.TypedNormalizeResult[dnd.ItemRegistry]{Value: value, Warnings: limitWarningsForRetry(warnings), Retry: &contracts.NormalizeRetry{
ReasonCode: ReasonCodeItemSemanticProposalInvalid, Message: "semantic proposal requires retry: currency denominations must remain distinct",
FallbackWarnings: []contracts.Warning{semanticFallbackWarning(rejectedGroups)},
}}
}
func semanticFallbackWarning(discarded int) contracts.Warning {
message := "semantic proposal could not be applied"
if discarded >= 0 {
message = fmt.Sprintf("%d proposal group(s) omitted after semantic proposal retry exhaustion", discarded)
}
return contracts.Warning{Scope: "items", ReasonCode: ReasonCodeItemSemanticReconciliationExhausted, Message: message}
}
func limitWarnings(warnings []contracts.Warning) []contracts.Warning {
return diagnostics.LimitWarnings(warnings, "items", ReasonCodeItemNormalizationWarningsOmitted)
}
func limitWarningsForRetry(warnings []contracts.Warning) []contracts.Warning {
if warnings == nil {
return nil
}
if len(warnings) < diagnostics.MaxWarnings {
return append([]contracts.Warning(nil), warnings...)
}
displayed := diagnostics.MaxWarnings - 2
bounded := append([]contracts.Warning(nil), warnings[:displayed]...)
return append(bounded, contracts.Warning{Scope: "items", ReasonCode: ReasonCodeItemNormalizationWarningsOmitted, Message: fmt.Sprintf("%d additional warning(s) omitted", len(warnings)-displayed)})
}
type normalizedRecord struct {
item dnd.Item
inputIndexes []int
earliest int
}
func preprocessRecords(input dnd.ItemRegistry, order shared.SourceRefOrder) ([]normalizedRecord, []contracts.Warning) {
if input.Items == nil {
return nil, nil
}
records := make([]normalizedRecord, len(input.Items))
warnings := make([]contracts.Warning, 0)
for index, inputItem := range input.Items {
item, fieldsChanged, refsChanged := normalizeRecord(inputItem, order)
records[index] = normalizedRecord{item: item, inputIndexes: []int{index}, earliest: index}
if fieldsChanged {
warnings = append(warnings, contracts.Warning{Scope: itemScope(index), ReasonCode: ReasonCodeItemFieldsNormalized, Message: fmt.Sprintf("input index %d: item name normalized for %s", index, diagnostics.Quote(inputItem.Name))})
}
if refsChanged {
warnings = append(warnings, contracts.Warning{Scope: itemScope(index), ReasonCode: ReasonCodeSourceReferencesNormalized, Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)", index, len(inputItem.SourceRefs), len(item.SourceRefs))})
}
if inputItem.ID != item.ID {
warnings = append(warnings, contracts.Warning{Scope: itemScope(index), ReasonCode: ReasonCodeItemIDRecomputed, Message: fmt.Sprintf("input index %d: item ID recomputed from %s", index, diagnostics.Quote(item.Name))})
}
}
groups := exactDuplicateGroups(records)
output := make([]normalizedRecord, 0, len(groups))
for _, members := range groups {
retained := cloneRecord(records[members[0]])
for _, member := range members[1:] {
retained.inputIndexes = append(retained.inputIndexes, records[member].inputIndexes...)
}
retained.inputIndexes = sortedUniqueIndexes(retained.inputIndexes)
output = append(output, retained)
if len(members) > 1 {
warnings = append(warnings, duplicateWarning(retained.earliest, memberInputIndexes(records, members[1:])))
}
}
return output, warnings
}
func normalizeRecord(input dnd.Item, order shared.SourceRefOrder) (dnd.Item, bool, bool) {
output := cloneItem(input)
output.Name = identity.NormalizeDisplay(input.Name)
output.SourceRefs = order.Canonicalize(input.SourceRefs)
output.ID = identity.DeriveID(output.Name)
return output, input.Name != output.Name, !reflect.DeepEqual(input.SourceRefs, output.SourceRefs)
}
func exactDuplicateGroups(records []normalizedRecord) [][]int {
groups := make([][]int, 0, len(records))
for index, record := range records {
key := identity.ComparisonKey(record.item.Name)
found := false
for groupIndex, members := range groups {
first := records[members[0]]
if identity.ComparisonKey(first.item.Name) == key && reflect.DeepEqual(first.item.SourceRefs, record.item.SourceRefs) {
groups[groupIndex] = append(groups[groupIndex], index)
found = true
break
}
}
if !found {
groups = append(groups, []int{index})
}
}
return groups
}
func cloneItem(input dnd.Item) dnd.Item {
input.SourceRefs = cloneSourceRefs(input.SourceRefs)
return input
}
func cloneRecord(input normalizedRecord) normalizedRecord {
input.item = cloneItem(input.item)
input.inputIndexes = append([]int(nil), input.inputIndexes...)
return input
}
func cloneSourceRefs(input []source.SourceRef) []source.SourceRef {
return append([]source.SourceRef(nil), input...)
}
func sortedUniqueIndexes(indexes []int) []int {
if len(indexes) == 0 {
return nil
}
out := append([]int(nil), indexes...)
sort.Ints(out)
write := 1
for _, index := range out[1:] {
if index != out[write-1] {
out[write] = index
write++
}
}
return out[:write]
}
func memberInputIndexes(records []normalizedRecord, members []int) []int {
indexes := make([]int, 0, len(members))
for _, member := range members {
indexes = append(indexes, records[member].inputIndexes...)
}
return sortedUniqueIndexes(indexes)
}
func recordValues(records []normalizedRecord) []dnd.Item {
if records == nil {
return nil
}
values := make([]dnd.Item, len(records))
for index, record := range records {
values[index] = cloneItem(record.item)
}
return values
}
func recordList(records []normalizedRecord) dnd.ItemRegistry {
if records == nil {
return dnd.ItemRegistry{}
}
return dnd.ItemRegistry{Items: recordValues(records)}
}
func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
const maxDisplayedIndices = 20
displayed := removed
if len(displayed) > maxDisplayedIndices {
displayed = displayed[:maxDisplayedIndices]
}
indices := make([]string, len(displayed))
for index, removedIndex := range displayed {
indices[index] = strconv.Itoa(removedIndex)
}
message := fmt.Sprintf("retained input index %d; removed input indices [%s]", retainedIndex, strings.Join(indices, ", "))
if omitted := len(removed) - len(displayed); omitted > 0 {
message += fmt.Sprintf("; %d additional removed input indices omitted", omitted)
}
return contracts.Warning{Scope: itemScope(retainedIndex), ReasonCode: ReasonCodeDuplicateItemCollapsed, Message: message}
}
func itemScope(index int) string { return fmt.Sprintf("items[%d]", index) }
func ModuleSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassLLMBacked, Requires: append([]string(nil), requiredCapabilities...), Provides: append([]string(nil), providedCapabilities...), ArtifactKind: dnd.ItemRegistryKind}
}
func Register(registry *pipeline.NormalizerRegistry) error {
return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.ItemRegistry], error) {
options, err := DecodeOptions(request.Options)
if err != nil {
return nil, err
}
return New(request.Dependencies.LLM, options)
})
}
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }
func DecodeOptions(options map[string]any) (Options, error) {
if err := pipeline.RejectUnknownOptions(options); err != nil {
return Options{}, normalizerErrorf("%w", err)
}
return Options{}, nil
}
func normalizerErrorf(format string, args ...any) error {
return fmt.Errorf("dnd item registry normalizer: "+format, args...)
}

View File

@@ -0,0 +1,193 @@
package itemregistry
import (
"context"
"encoding/json"
"errors"
"reflect"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/entityreconcile"
"gitea.maximumdirect.net/eric/promptkit"
)
func TestModuleContractAndMetadata(t *testing.T) {
want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassLLMBacked, Requires: []string{"merged"}, Provides: []string{"normalized"}, ArtifactKind: dnd.ItemRegistryKind}
if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
}
registry := pipeline.NewNormalizerRegistry()
if err := Register(registry); err != nil {
t.Fatal(err)
}
if _, err := New(nil, Options{}); err == nil {
t.Fatal("New() accepted nil client")
}
metadata := newNormalizer(t, &recordingNormalizerClient{}).ManifestMetadata()
if metadata["identity_policy"] != identity.Policy || metadata["response_schema_id"] != entityreconcile.ResponseSchemaID || metadata["normalization_policy"] != normalizationPolicy || metadata["semantic_context_radius"] != semanticContextRadius {
t.Fatalf("metadata = %#v", metadata)
}
}
func TestNormalizePreprocessesExactDuplicatesWithoutMutation(t *testing.T) {
input := dnd.ItemRegistry{Items: []dnd.Item{
{Name: " Rope ", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}},
{Name: "rope", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}},
{Name: "Rope", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}},
}}
before := dnd.ItemRegistry{Items: append([]dnd.Item(nil), input.Items...)}
result, err := newNormalizer(t, &recordingNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil || len(result.Value.Items) != 2 || !reflect.DeepEqual(input, before) {
t.Fatalf("Normalize() = %#v, %v; want non-mutating exact deduplication", result, err)
}
if result.Value.Items[0].ID != result.Value.Items[1].ID || !hasWarning(result.Warnings, ReasonCodeDuplicateItemCollapsed) {
t.Fatalf("items = %#v, warnings = %#v; want type identity and duplicate warning", result.Value.Items, result.Warnings)
}
}
func TestNormalizeAppliesSafeAliasProposalAndPreservesCurrency(t *testing.T) {
doc := semanticDocument()
input := dnd.ItemRegistry{Items: []dnd.Item{
{Name: "Star Compass", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
{Name: "Compass of the Stars", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
{Name: "Gold Pieces", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}},
}}
client := &recordingNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000002"}]}`}
result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
if err != nil || result.Retry != nil || len(result.Value.Items) != 2 {
t.Fatalf("Normalize() = %#v, %v", result, err)
}
merged := result.Value.Items[0]
if merged.Name != "Compass of the Stars" || merged.ID != identity.DeriveID(merged.Name) || len(merged.SourceRefs) != 2 || !hasWarning(result.Warnings, ReasonCodeDuplicateItemCollapsed) {
t.Fatalf("merged item = %#v, warnings = %#v", merged, result.Warnings)
}
encoded := string(client.requests[0].Inputs["candidates"].Content) + string(client.requests[0].Inputs["transcript"].Content)
if strings.Contains(encoded, doc.ID) || !strings.Contains(encoded, "candidate-000001") || strings.Contains(encoded, merged.ID) {
t.Fatalf("private inputs = %s", encoded)
}
currencyClient := &recordingNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000001"}]}`}
currency := dnd.ItemRegistry{Items: []dnd.Item{{Name: "Gold Pieces", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "Silver Pieces", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}}}
result, err = newNormalizer(t, currencyClient).Normalize(context.Background(), normalizeRequestWithSource(currency, doc))
if err != nil || result.Retry == nil || len(result.Value.Items) != 2 || !hasWarning(result.Warnings, ReasonCodeItemSemanticProposalInvalid) {
t.Fatalf("currency result = %#v, %v; want denominations retained", result, err)
}
}
func TestNormalizePreservesCandidatesForUnsafeProposalGroups(t *testing.T) {
doc := semanticDocument()
input := dnd.ItemRegistry{Items: []dnd.Item{
{Name: "Star Compass", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
{Name: "Compass", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
{Name: "Rope", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}},
}}
client := &recordingNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000001"},{"members":["candidate-000002","candidate-000003"],"canonical":"candidate-000003"},{"members":["candidate-000001","candidate-000003"],"canonical":"candidate-000099"}]}`}
result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
if err != nil || result.Retry == nil || len(result.Value.Items) != 3 || !strings.Contains(result.Retry.Message, "overlapping_member") || !strings.Contains(result.Retry.Message, "canonical_unknown") || strings.Contains(result.Retry.Message, "Star Compass") || len(result.Retry.Message) > 4096 {
t.Fatalf("Normalize() = %#v, %v; want deterministic retry fallback", result, err)
}
}
func TestNormalizeRetryFallbackErrorsWarningsAndIdempotence(t *testing.T) {
doc := semanticDocument()
input := dnd.ItemRegistry{Items: []dnd.Item{{Name: "Star Compass", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "Compass", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}}}
invalid, err := newNormalizer(t, &recordingNormalizerClient{err: contracts.ErrInvalidStructuredOutput}).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
if err != nil || invalid.Retry == nil || invalid.Retry.ReasonCode != ReasonCodeItemSemanticProposalInvalid {
t.Fatalf("invalid result = %#v, %v", invalid, err)
}
_, err = newNormalizer(t, &recordingNormalizerClient{err: errors.New("provider unavailable")}).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
if err == nil || !strings.Contains(err.Error(), "provider unavailable") {
t.Fatalf("provider error = %v", err)
}
if bounded := limitWarningsForRetry(make([]contracts.Warning, diagnostics.MaxWarnings+5)); len(bounded) != diagnostics.MaxWarnings-1 || bounded[len(bounded)-1].ReasonCode != ReasonCodeItemNormalizationWarningsOmitted {
t.Fatalf("retry warning limit = %#v", bounded)
}
first, err := newNormalizer(t, &recordingNormalizerClient{}).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
second, secondErr := newNormalizer(t, &recordingNormalizerClient{}).Normalize(context.Background(), normalizeRequestWithSource(first.Value, doc))
if err != nil || secondErr != nil || !reflect.DeepEqual(first.Value, second.Value) {
t.Fatalf("normalization must be idempotent: first=%#v err=%v second=%#v err=%v", first, err, second, secondErr)
}
}
func TestRegisterPromptAssetsPreparesItemNormalizationPrompt(t *testing.T) {
registry := llm.NewAssetRegistry()
if err := entityreconcile.RegisterSchemaAssets(registry); err != nil {
t.Fatal(err)
}
if err := RegisterPromptAssets(registry); err != nil {
t.Fatal(err)
}
options, err := registry.PromptKitOptions()
if err != nil {
t.Fatal(err)
}
options = append(options, promptkit.WithProfiles(promptkit.OpenAICompatibleProfile(promptkit.OpenAICompatibleProfileConfig{ID: "item-normalize-test", Endpoint: "http://127.0.0.1:1/v1", Model: "test"})))
engine, err := promptkit.NewEngine(promptkit.Config{Timeout: time.Second}, options...)
if err != nil {
t.Fatal(err)
}
prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{PromptID: PromptID, PromptVersion: entityreconcile.SchemaVersion, ProfileID: "item-normalize-test", Inputs: map[string]promptkit.ArtifactRef{"candidates": promptkit.Inline(`{"candidates":[{"key":"candidate-000001","name":"Rope","source_refs":[]}]}`), "transcript": promptkit.Inline(`{"windows":[{"units":[]}]}`)}})
if err != nil {
t.Fatal(err)
}
if prepared.OutputContract.SchemaPath != "dnd_entity_reconcile_llm.v1.json" || !strings.Contains(prepared.Messages[1].Content, "currency denominations") || !strings.Contains(prepared.Messages[1].Content, "materially different item types") {
t.Fatalf("prepared prompt = %#v", prepared)
}
}
type recordingNormalizerClient struct {
response string
err error
requests []contracts.StructuredCompletionRequest
}
func (c *recordingNormalizerClient) CompleteStructured(_ context.Context, request contracts.StructuredCompletionRequest, output any) (contracts.StructuredCompletionResponse, error) {
c.requests = append(c.requests, request)
if c.err != nil {
return contracts.StructuredCompletionResponse{}, c.err
}
response := c.response
if response == "" {
response = `{"duplicate_groups":[]}`
}
if err := json.Unmarshal([]byte(response), output); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
return contracts.StructuredCompletionResponse{Content: json.RawMessage(response)}, nil
}
func newNormalizer(t *testing.T, client contracts.StructuredLLMClient) *Normalizer {
t.Helper()
normalizer, err := New(client, Options{})
if err != nil {
t.Fatalf("New() error = %v", err)
}
return normalizer
}
func normalizeRequest(value dnd.ItemRegistry) contracts.TypedNormalizeRequest[dnd.ItemRegistry] {
return contracts.TypedNormalizeRequest[dnd.ItemRegistry]{MergeOutput: contracts.MergeArtifact[dnd.ItemRegistry]{Value: value}}
}
func normalizeRequestWithSource(value dnd.ItemRegistry, doc *source.SourceDocument) contracts.TypedNormalizeRequest[dnd.ItemRegistry] {
request := normalizeRequest(value)
request.Source = doc
return request
}
func semanticDocument() *source.SourceDocument {
return &source.SourceDocument{ID: "item-session", Units: []source.SourceUnit{{ID: 10, Text: "The Star Compass points north."}, {ID: 20, Text: "The compass of the stars glows."}, {ID: 30, Text: "The chest holds gold pieces."}}}
}
func hasWarning(warnings []contracts.Warning, reason string) bool {
for _, warning := range warnings {
if warning.ReasonCode == reason {
return true
}
}
return false
}

View File

@@ -0,0 +1,62 @@
package itemregistry
import (
"fmt"
"io/fs"
"sync"
rootassets "gitea.maximumdirect.net/eric/notarius/assets"
"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/notarius/internal/framework/promptfs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
)
const promptAssetRoot = "assets/prompts"
var promptAssetManifest = shared.PromptAssetManifest{
ModuleDir: PromptID,
ModuleFiles: []promptfs.ModulePromptFile{
{Name: "prompt.yaml", Path: "prompts/prompt.yaml"},
{Name: "instructions.md", Path: "prompts/instructions.md"},
{Name: "candidates.md", Path: "prompts/candidates.md"},
},
SharedFiles: []string{"common-dnd-system.md", "common-dnd-entity-reconciliation.md", "common-dnd-transcript-windows.md"},
}
func moduleAssetFS() (fs.FS, error) {
assets, err := fs.Sub(rootassets.FS(), "dnd/item-registry/normalize")
if err != nil {
return nil, fmt.Errorf("scope item normalization assets: %w", err)
}
return assets, nil
}
func RegisterPromptAssets(registry *llm.AssetRegistry) error {
assets, err := moduleAssetFS()
if err != nil {
return err
}
promptFS, err := promptAssetManifest.PromptFS(assets)
if err != nil {
return fmt.Errorf("prepare item normalization prompt assets: %w", err)
}
return registry.RegisterPromptFS(promptFS, promptAssetRoot)
}
func promptAssetMetadata() (string, error) {
promptAssetHashOnce.Do(func() {
assets, err := moduleAssetFS()
if err != nil {
promptAssetHashErr = err
return
}
promptAssetHash, promptAssetHashErr = promptAssetManifest.Hash(assets)
})
return promptAssetHash, promptAssetHashErr
}
var (
promptAssetHashOnce sync.Once
promptAssetHash string
promptAssetHashErr error
)

View File

@@ -0,0 +1,153 @@
package itemregistry
import (
"fmt"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/entityreconcile"
)
type safeReconciliationGroup struct {
members []int
canonical int
}
func reconciliationCandidates(records []normalizedRecord) []entityreconcile.Candidate {
candidates := make([]entityreconcile.Candidate, len(records))
for index, record := range records {
candidates[index] = entityreconcile.Candidate{Name: record.item.Name, SourceRefs: cloneSourceRefs(record.item.SourceRefs)}
}
return candidates
}
func reconciliationGroups(assessment entityreconcile.Assessment, candidateKeys []string) []safeReconciliationGroup {
positions := make(map[string]int, len(candidateKeys))
for index, key := range candidateKeys {
positions[key] = index
}
safeGroups := assessment.SafeGroups()
groups := make([]safeReconciliationGroup, 0, len(safeGroups))
for _, group := range safeGroups {
members := group.Members()
memberPositions := make([]int, len(members))
valid := true
for index, key := range members {
position, ok := positions[key]
if !ok {
valid = false
break
}
memberPositions[index] = position
}
canonical, ok := positions[group.Canonical()]
if valid && ok {
groups = append(groups, safeReconciliationGroup{members: memberPositions, canonical: canonical})
}
}
return groups
}
func reconciliationIssues(assessment entityreconcile.Assessment) []string {
issues := assessment.Issues()
details := make([]string, len(issues))
for index, issue := range issues {
details[index] = fmt.Sprintf("group %d: %s", issue.GroupIndex, issue.Category)
}
return details
}
func applySafeGroups(records []normalizedRecord, groups []safeReconciliationGroup, order shared.SourceRefOrder) ([]normalizedRecord, []contracts.Warning, int) {
byMember := make(map[int]safeReconciliationGroup, len(groups)*2)
for _, group := range groups {
for _, member := range group.members {
byMember[member] = group
}
}
output := make([]normalizedRecord, 0, len(records)-len(groups))
warnings := make([]contracts.Warning, 0, len(groups))
rejectedGroups := 0
for index, record := range records {
group, grouped := byMember[index]
if !grouped {
output = append(output, cloneRecord(record))
continue
}
if group.members[0] != index {
continue
}
if !canConsolidate(records, group) {
for _, member := range group.members {
output = append(output, cloneRecord(records[member]))
}
warnings = append(warnings, contracts.Warning{Scope: itemScope(records[group.members[0]].earliest), ReasonCode: ReasonCodeItemSemanticProposalInvalid, Message: "proposal group preserved because currency denominations must remain distinct"})
rejectedGroups++
continue
}
consolidated := consolidateSemanticGroup(records, group, order)
output = append(output, consolidated)
warnings = append(warnings, semanticDuplicateWarning(consolidated, records[group.canonical]))
}
return output, warnings, rejectedGroups
}
func canConsolidate(records []normalizedRecord, group safeReconciliationGroup) bool {
denomination := ""
for _, member := range group.members {
current := currencyDenomination(records[member].item.Name)
if current == "" {
continue
}
if denomination != "" && denomination != current {
return false
}
denomination = current
}
return true
}
func currencyDenomination(name string) string {
switch identity.ComparisonKey(name) {
case "copper piece", "copper pieces", "cp":
return "copper"
case "silver piece", "silver pieces", "sp":
return "silver"
case "electrum piece", "electrum pieces", "ep":
return "electrum"
case "gold piece", "gold pieces", "gp":
return "gold"
case "platinum piece", "platinum pieces", "pp":
return "platinum"
default:
return ""
}
}
func consolidateSemanticGroup(records []normalizedRecord, group safeReconciliationGroup, order shared.SourceRefOrder) normalizedRecord {
output := cloneRecord(records[group.members[0]])
output.item.Name = records[group.canonical].item.Name
for _, member := range group.members[1:] {
output.item.SourceRefs = append(output.item.SourceRefs, records[member].item.SourceRefs...)
output.inputIndexes = append(output.inputIndexes, records[member].inputIndexes...)
if records[member].earliest < output.earliest {
output.earliest = records[member].earliest
}
}
output.inputIndexes = sortedUniqueIndexes(output.inputIndexes)
output.item.SourceRefs = order.Canonicalize(output.item.SourceRefs)
output.item.ID = identity.DeriveID(output.item.Name)
return output
}
func semanticDuplicateWarning(record normalizedRecord, canonical normalizedRecord) contracts.Warning {
details := make([]string, 0, len(record.inputIndexes)+1)
for _, inputIndex := range record.inputIndexes {
details = append(details, fmt.Sprintf("input index %d", inputIndex))
}
if canonical.earliest != record.earliest {
details = append(details, fmt.Sprintf("canonical display name from input index %d", canonical.earliest))
}
return contracts.Warning{Scope: itemScope(record.earliest), ReasonCode: ReasonCodeDuplicateItemCollapsed, Message: diagnostics.Aggregate("semantic duplicate consolidation", details)}
}

View File

@@ -5,6 +5,7 @@ import (
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemevents"
itemregistryextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemregistry"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locationextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
@@ -14,6 +15,7 @@ import (
combatnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/combatturns"
enemyeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/enemyevents"
itemeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemevents"
itemregistrynormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemregistry"
locationoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationoccurrences"
locationnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationregistry"
occurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcoccurrences"
@@ -33,6 +35,10 @@ import (
itemeventshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/shape"
itemeventrefs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/source_refs"
itemeventrelatedness "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/source_relatedness"
itemidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/identity"
itemshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/shape"
itemrefs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/source_refs"
itemrelatedness "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/source_relatedness"
locationoccurrenceinvariants "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/invariants"
locationoccurrenceregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/registry"
locationoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/shape"
@@ -202,6 +208,24 @@ func registerDefaultChains(registry *pipeline.ValidatorChainRegistry) error {
},
})
}},
{name: "item registry validator chain", register: func() error {
return registry.Register(pipeline.ValidatorChainMapping{
Stage: pipeline.StageExtract, Module: itemregistryextract.Key,
Validators: []pipeline.ModuleBinding{
pipeline.Binding(validjson.Key), pipeline.Binding(itemshape.Key), pipeline.Binding(itemrefs.Key),
pipeline.Binding(validjsonschema.Key), pipeline.Binding(itemrelatedness.Key),
},
})
}},
{name: "item registry normalize validator chain", register: func() error {
return registry.Register(pipeline.ValidatorChainMapping{
Stage: pipeline.StageNormalize, Module: itemregistrynormalize.Key,
Validators: []pipeline.ModuleBinding{
pipeline.Binding(validjson.Key), pipeline.Binding(itemshape.Key), pipeline.Binding(itemidentity.Key),
pipeline.Binding(itemrefs.Key), pipeline.Binding(validjsonschema.Key), pipeline.Binding(itemrelatedness.Key),
},
})
}},
{name: "npc occurrences validator chain", register: func() error {
return registry.Register(pipeline.ValidatorChainMapping{
Stage: pipeline.StageExtract,

View File

@@ -19,6 +19,9 @@ func registerEvidence(registry *pipeline.ArtifactEvidenceRegistry) error {
{name: "item events evidence", register: func() error {
return pipeline.RegisterArtifactEvidence(registry, dnd.ItemEventListKind, itemEventEvidence)
}},
{name: "item registry evidence", register: func() error {
return pipeline.RegisterArtifactEvidence(registry, dnd.ItemRegistryKind, itemRegistryEvidence)
}},
{name: "npc occurrences evidence", register: func() error {
return pipeline.RegisterArtifactEvidence(registry, dnd.NPCOccurrenceListKind, npcOccurrenceEvidence)
}},
@@ -74,6 +77,14 @@ func itemEventEvidence(value dnd.ItemEventList) []source.SourceRef {
return append([]source.SourceRef(nil), refs...)
}
func itemRegistryEvidence(value dnd.ItemRegistry) []source.SourceRef {
var refs []source.SourceRef
for _, item := range value.Items {
refs = append(refs, item.SourceRefs...)
}
return append([]source.SourceRef(nil), refs...)
}
func npcOccurrenceEvidence(value dnd.NPCOccurrenceList) []source.SourceRef {
var refs []source.SourceRef
for _, record := range value.Occurrences {

View File

@@ -112,6 +112,27 @@ func appendItemEventLists(values []dnd.ItemEventList) (dnd.ItemEventList, error)
return combined, nil
}
func appendItemRegistries(values []dnd.ItemRegistry) (dnd.ItemRegistry, error) {
count := 0
present := false
for _, value := range values {
if value.Items != nil {
present = true
}
count += len(value.Items)
}
if !present {
return dnd.ItemRegistry{}, nil
}
combined := dnd.ItemRegistry{Items: make([]dnd.Item, 0, count)}
for _, value := range values {
for _, item := range value.Items {
combined.Items = append(combined.Items, cloneItem(item))
}
}
return combined, nil
}
func appendNPCOccurrenceLists(values []dnd.NPCOccurrenceList) (dnd.NPCOccurrenceList, error) {
count := 0
present := false
@@ -216,6 +237,12 @@ func cloneItemEvent(value dnd.ItemEvent) dnd.ItemEvent {
return clone
}
func cloneItem(value dnd.Item) dnd.Item {
clone := value
clone.SourceRefs = cloneSourceRefs(value.SourceRefs)
return clone
}
func cloneSpellCast(value dnd.SpellCast) dnd.SpellCast {
clone := value
clone.SourceRefs = cloneSourceRefs(value.SourceRefs)

View File

@@ -8,6 +8,7 @@ import (
combatcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/combatturns"
enemyeventcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/enemyevents"
itemeventcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemevents"
itemregistrycodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/itemregistry"
locationoccurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/locationoccurrences"
locationcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/locationregistry"
occurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcoccurrences"
@@ -17,6 +18,7 @@ import (
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemevents"
itemregistryextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemregistry"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locationextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
@@ -26,6 +28,7 @@ import (
combatnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/combatturns"
enemyeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/enemyevents"
itemeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemevents"
itemregistrynormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemregistry"
locationoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationoccurrences"
locationnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationregistry"
occurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcoccurrences"
@@ -45,6 +48,9 @@ func registerModules(registries pipeline.Registries) error {
{name: "combat turns codec", register: func() error { return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, combatcodec.New()) }},
{name: "enemy events codec", register: func() error { return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, enemyeventcodec.New()) }},
{name: "item events codec", register: func() error { return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, itemeventcodec.New()) }},
{name: "item registry codec", register: func() error {
return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, itemregistrycodec.New())
}},
{name: "npc occurrences codec", register: func() error { return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, occurrencecodec.New()) }},
{name: "scene descriptions codec", register: func() error {
return pipeline.RegisterArtifactCodec(registries.ArtifactCodecs, scenedescriptioncodec.New())
@@ -59,6 +65,7 @@ func registerModules(registries pipeline.Registries) error {
{name: "combat turns extractor", register: func() error { return combatextract.Register(registries.Extractors) }},
{name: "enemy events extractor", register: func() error { return enemyeventextract.Register(registries.Extractors) }},
{name: "item events extractor", register: func() error { return itemeventextract.Register(registries.Extractors) }},
{name: "item registry extractor", register: func() error { return itemregistryextract.Register(registries.Extractors) }},
{name: "npc occurrences extractor", register: func() error { return occurrenceextract.Register(registries.Extractors) }},
{name: "scene descriptions extractor", register: func() error { return scenedescriptionextract.Register(registries.Extractors) }},
{name: "location registry extractor", register: func() error { return locationextract.Register(registries.Extractors) }},
@@ -78,6 +85,9 @@ func registerModules(registries pipeline.Registries) error {
{name: "item-event-list appendorder merger", register: func() error {
return appendorder.RegisterTyped(registries.Mergers, dnd.ItemEventListKind, appendItemEventLists)
}},
{name: "item-registry appendorder merger", register: func() error {
return appendorder.RegisterTyped(registries.Mergers, dnd.ItemRegistryKind, appendItemRegistries)
}},
{name: "npc-occurrence-list appendorder merger", register: func() error {
return appendorder.RegisterTyped(registries.Mergers, dnd.NPCOccurrenceListKind, appendNPCOccurrenceLists)
}},
@@ -95,6 +105,7 @@ func registerModules(registries pipeline.Registries) error {
{name: "combat turns normalizer", register: func() error { return combatnormalize.Register(registries.Normalizers) }},
{name: "enemy events normalizer", register: func() error { return enemyeventnormalize.Register(registries.Normalizers) }},
{name: "item events normalizer", register: func() error { return itemeventnormalize.Register(registries.Normalizers) }},
{name: "item registry normalizer", register: func() error { return itemregistrynormalize.Register(registries.Normalizers) }},
{name: "npc occurrences normalizer", register: func() error { return occurrencenormalize.Register(registries.Normalizers) }},
{name: "scene descriptions normalizer", register: func() error { return scenedescriptionnormalize.Register(registries.Normalizers) }},
{name: "location registry normalizer", register: func() error { return locationnormalize.Register(registries.Normalizers) }},
@@ -114,6 +125,9 @@ func registerModules(registries pipeline.Registries) error {
{name: "item-event-list noop normalizer", register: func() error {
return noop.RegisterTyped[dnd.ItemEventList](registries.Normalizers, dnd.ItemEventListKind)
}},
{name: "item-registry noop normalizer", register: func() error {
return noop.RegisterTyped[dnd.ItemRegistry](registries.Normalizers, dnd.ItemRegistryKind)
}},
{name: "npc-occurrence-list noop normalizer", register: func() error {
return noop.RegisterTyped[dnd.NPCOccurrenceList](registries.Normalizers, dnd.NPCOccurrenceListKind)
}},
@@ -139,6 +153,8 @@ func registerPromptAssets(assets *llm.AssetRegistry) error {
{name: "combat turns prompt assets", register: func() error { return combatextract.RegisterPromptAssets(assets) }},
{name: "enemy events prompt assets", register: func() error { return enemyeventextract.RegisterPromptAssets(assets) }},
{name: "item events prompt assets", register: func() error { return itemeventextract.RegisterPromptAssets(assets) }},
{name: "item registry prompt assets", register: func() error { return itemregistryextract.RegisterPromptAssets(assets) }},
{name: "item registry normalization prompt assets", register: func() error { return itemregistrynormalize.RegisterPromptAssets(assets) }},
{name: "npc occurrences prompt assets", register: func() error { return occurrenceextract.RegisterPromptAssets(assets) }},
{name: "scene descriptions prompt assets", register: func() error { return scenedescriptionextract.RegisterPromptAssets(assets) }},
{name: "locations prompt assets", register: func() error { return locationextract.RegisterPromptAssets(assets) }},

View File

@@ -11,6 +11,7 @@ import (
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemevents"
itemregistryextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemregistry"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locationextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
@@ -51,6 +52,7 @@ func TestExtractionPromptComposition(t *testing.T) {
{name: "npcs", promptID: npcextract.PromptID, promptVersion: npcextract.SchemaVersion, inputs: commonInputs, suffixGroups: [][]string{{evidenceSentinel}}},
{name: "locations", promptID: locationextract.PromptID, promptVersion: locationextract.SchemaVersion, inputs: commonInputs, suffixGroups: [][]string{{evidenceSentinel}}},
{name: "item events", promptID: itemeventextract.PromptID, promptVersion: itemeventextract.SchemaVersion, inputs: commonInputs, suffixGroups: [][]string{{evidenceSentinel}}},
{name: "item registry", promptID: itemregistryextract.PromptID, promptVersion: itemregistryextract.SchemaVersion, inputs: commonInputs, suffixGroups: [][]string{{evidenceSentinel}}},
{name: "scene descriptions", promptID: scenedescriptionextract.PromptID, promptVersion: scenedescriptionextract.SchemaVersion, inputs: commonInputs},
{
name: "combat turns",

View File

@@ -15,6 +15,7 @@ import (
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemeventextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemevents"
itemregistryextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemregistry"
locationoccurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationoccurrences"
locationextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/locationregistry"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
@@ -24,6 +25,7 @@ import (
combatnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/combatturns"
enemyeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/enemyevents"
itemeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemevents"
itemregistrynormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemregistry"
locationoccurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationoccurrences"
locationnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/locationregistry"
occurrencenormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcoccurrences"
@@ -52,6 +54,8 @@ func TestRegisterAddsDNDFamily(t *testing.T) {
"dnd.combat_turns/prompt.yaml",
"dnd.enemy_events/prompt.yaml",
"dnd.item_events/prompt.yaml",
"dnd.item_registry/prompt.yaml",
"dnd.item_registry.normalize/prompt.yaml",
"dnd.npc_occurrences/prompt.yaml",
"dnd.scene_descriptions/prompt.yaml",
"dnd.npc_registry.normalize/prompt.yaml",
@@ -82,16 +86,17 @@ func TestRegisterAddsDNDFamily(t *testing.T) {
t.Fatalf("entity reconciliation schema asset = %v, want registered shared schema", err)
}
assertContainsKeys(t, "chunkers", registries.Chunkers.RegisteredKeys(), []string{"dnd/scenes"})
assertContainsKeys(t, "extractors", registries.Extractors.RegisteredKeys(), []string{"dnd/spells", npcextract.Key, combatextract.Key, enemyeventextract.Key, itemeventextract.Key, occurrenceextract.Key, scenedescriptionextract.Key, locationextract.Key, locationoccurrenceextract.Key})
assertContainsKeys(t, "normalizers", registries.Normalizers.RegisteredKeys(), []string{spellnormalize.Key, npcnormalize.Key, combatnormalize.Key, enemyeventnormalize.Key, itemeventnormalize.Key, occurrencenormalize.Key, scenedescriptionnormalize.Key, locationnormalize.Key, locationoccurrencenormalize.Key, pipeline.DefaultNormalizeModule})
assertContainsArtifactKinds(t, registries.ArtifactCodecs.RegisteredKinds(), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.ArtifactEvidence.RegisteredKinds(), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Mergers.RegisteredArtifactKinds(pipeline.DefaultMergeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(pipeline.DefaultNormalizeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsKeys(t, "extractors", registries.Extractors.RegisteredKeys(), []string{"dnd/spells", npcextract.Key, combatextract.Key, enemyeventextract.Key, itemeventextract.Key, itemregistryextract.Key, occurrenceextract.Key, scenedescriptionextract.Key, locationextract.Key, locationoccurrenceextract.Key})
assertContainsKeys(t, "normalizers", registries.Normalizers.RegisteredKeys(), []string{spellnormalize.Key, npcnormalize.Key, combatnormalize.Key, enemyeventnormalize.Key, itemeventnormalize.Key, itemregistrynormalize.Key, occurrencenormalize.Key, scenedescriptionnormalize.Key, locationnormalize.Key, locationoccurrencenormalize.Key, pipeline.DefaultNormalizeModule})
assertContainsArtifactKinds(t, registries.ArtifactCodecs.RegisteredKinds(), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.ItemRegistryKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.ArtifactEvidence.RegisteredKinds(), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.ItemRegistryKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Mergers.RegisteredArtifactKinds(pipeline.DefaultMergeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.ItemRegistryKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(pipeline.DefaultNormalizeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCRegistryKind, dnd.CombatTurnListKind, dnd.EnemyEventListKind, dnd.ItemEventListKind, dnd.ItemRegistryKind, dnd.NPCOccurrenceListKind, dnd.SceneDescriptionListKind, dnd.LocationRegistryKind, dnd.LocationOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(npcnormalize.Key), []contracts.ArtifactKind{dnd.NPCRegistryKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(combatnormalize.Key), []contracts.ArtifactKind{dnd.CombatTurnListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(enemyeventnormalize.Key), []contracts.ArtifactKind{dnd.EnemyEventListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(itemeventnormalize.Key), []contracts.ArtifactKind{dnd.ItemEventListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(itemregistrynormalize.Key), []contracts.ArtifactKind{dnd.ItemRegistryKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(occurrencenormalize.Key), []contracts.ArtifactKind{dnd.NPCOccurrenceListKind})
assertContainsArtifactKinds(t, registries.Normalizers.RegisteredArtifactKinds(scenedescriptionnormalize.Key), []contracts.ArtifactKind{dnd.SceneDescriptionListKind})
assertContainsKeys(t, "validators", registries.Validators.RegisteredKeys(), []string{
@@ -118,6 +123,7 @@ func TestRegisterAddsDNDFamily(t *testing.T) {
"extract/dnd/item-events/source_refs",
"extract/dnd/item-events/source_relatedness",
"normalize/dnd/item-events/invariants",
"extract/dnd/item-registry/shape", "normalize/dnd/item-registry/identity", "extract/dnd/item-registry/source_refs", "extract/dnd/item-registry/source_relatedness",
"extract/dnd/npc-occurrences/shape",
"extract/dnd/npc-occurrences/registry",
"extract/dnd/npc-occurrences/source_refs",
@@ -245,6 +251,27 @@ func TestRegisterAddsDNDFamily(t *testing.T) {
if got := registries.ValidatorChains.Validators(pipeline.StageNormalize, itemeventnormalize.Key); !reflect.DeepEqual(got, itemEventNormalizeChain) {
t.Fatalf("item event normalize validator chain = %#v, want %#v", got, itemEventNormalizeChain)
}
itemRegistryExtractChain := []pipeline.ModuleBinding{
pipeline.Binding("generic/valid_json"),
pipeline.Binding("extract/dnd/item-registry/shape"),
pipeline.Binding("extract/dnd/item-registry/source_refs"),
pipeline.Binding("generic/valid_json_schema"),
pipeline.Binding("extract/dnd/item-registry/source_relatedness"),
}
itemRegistryNormalizeChain := []pipeline.ModuleBinding{
pipeline.Binding("generic/valid_json"),
pipeline.Binding("extract/dnd/item-registry/shape"),
pipeline.Binding("normalize/dnd/item-registry/identity"),
pipeline.Binding("extract/dnd/item-registry/source_refs"),
pipeline.Binding("generic/valid_json_schema"),
pipeline.Binding("extract/dnd/item-registry/source_relatedness"),
}
if got := registries.ValidatorChains.Validators(pipeline.StageExtract, itemregistryextract.Key); !reflect.DeepEqual(got, itemRegistryExtractChain) {
t.Fatalf("item registry extract validator chain = %#v, want %#v", got, itemRegistryExtractChain)
}
if got := registries.ValidatorChains.Validators(pipeline.StageNormalize, itemregistrynormalize.Key); !reflect.DeepEqual(got, itemRegistryNormalizeChain) {
t.Fatalf("item registry normalize validator chain = %#v, want %#v", got, itemRegistryNormalizeChain)
}
npcOccurrenceExtractChain := []pipeline.ModuleBinding{
pipeline.Binding("generic/valid_json"),
pipeline.Binding("extract/dnd/npc-occurrences/shape"),
@@ -418,6 +445,9 @@ func TestEvidenceProjectorsPreserveDirectReferencesWithIndependentStorage(t *tes
{name: "item events", project: func() []source.SourceRef {
return itemEventEvidence(dnd.ItemEventList{Events: []dnd.ItemEvent{{SourceRefs: []source.SourceRef{first, second}}}})
}, want: []source.SourceRef{first, second}},
{name: "item registry", project: func() []source.SourceRef {
return itemRegistryEvidence(dnd.ItemRegistry{Items: []dnd.Item{{SourceRefs: []source.SourceRef{first, second}}}})
}, want: []source.SourceRef{first, second}},
{name: "npc occurrences", project: func() []source.SourceRef {
return npcOccurrenceEvidence(dnd.NPCOccurrenceList{Occurrences: []dnd.NPCOccurrence{{SourceRefs: []source.SourceRef{first, second}}}})
}, want: []source.SourceRef{first, second}},
@@ -690,6 +720,25 @@ func TestAppendItemEventListsPreservesOrderPresenceAndOwnership(t *testing.T) {
}
}
func TestAppendItemRegistriesPreservesOrderPresenceAndOwnership(t *testing.T) {
refs := []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}
input := []dnd.ItemRegistry{{}, {Items: []dnd.Item{}}, {Items: []dnd.Item{{ID: "one", Name: "First", SourceRefs: refs}}}, {Items: []dnd.Item{{ID: "two", Name: "Second", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}}}}}
got, err := appendItemRegistries(input)
if err != nil || got.Items == nil || !reflect.DeepEqual([]string{got.Items[0].Name, got.Items[1].Name}, []string{"First", "Second"}) {
t.Fatalf("appendItemRegistries() = %#v, %v", got, err)
}
got.Items[0].SourceRefs[0].StartUnitID = 99
if input[2].Items[0].SourceRefs[0].StartUnitID != 1 {
t.Fatal("merged items share source-reference storage")
}
for _, values := range [][]dnd.ItemRegistry{nil, {{}, {}}} {
result, err := appendItemRegistries(values)
if err != nil || result.Items != nil {
t.Fatalf("nil-only merge = %#v, %v", result, err)
}
}
}
func TestAppendListsPreserveNestedSourceReferencePresence(t *testing.T) {
spells, err := appendSpellLists([]dnd.SpellList{{SpellCasts: []dnd.SpellCast{{SourceRefs: []source.SourceRef{}}}}})
if err != nil || spells.SpellCasts[0].SourceRefs == nil {
@@ -720,6 +769,11 @@ func TestAppendListsPreserveNestedSourceReferencePresence(t *testing.T) {
if err != nil || events.Events[0].SourceRefs == nil {
t.Fatalf("appendItemEventLists() = %#v, %v; want present-empty source refs", events, err)
}
items, err := appendItemRegistries([]dnd.ItemRegistry{{Items: []dnd.Item{{SourceRefs: []source.SourceRef{}}}}})
if err != nil || items.Items[0].SourceRefs == nil {
t.Fatalf("appendItemRegistries() = %#v, %v; want present-empty source refs", items, err)
}
}
func TestRegisterRejectsMissingDNDDependenciesBeforeMutation(t *testing.T) {

View File

@@ -16,6 +16,10 @@ import (
itemeventshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/shape"
itemeventrefs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/source_refs"
itemeventrelatedness "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/source_relatedness"
itemidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/identity"
itemshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/shape"
itemrefs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/source_refs"
itemrelatedness "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/source_relatedness"
locationoccurrenceinvariants "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/invariants"
locationoccurrenceregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/registry"
locationoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/shape"
@@ -69,6 +73,10 @@ func registerValidators(registries pipeline.Registries) error {
{name: "item event source references validator", register: func() error { return itemeventrefs.Register(registries.Validators) }},
{name: "item event source relatedness validator", register: func() error { return itemeventrelatedness.Register(registries.Validators) }},
{name: "item event normalized invariants validator", register: func() error { return itemeventinvariants.Register(registries.Validators) }},
{name: "item shape validator", register: func() error { return itemshape.Register(registries.Validators) }},
{name: "item identity validator", register: func() error { return itemidentity.Register(registries.Validators) }},
{name: "item source references validator", register: func() error { return itemrefs.Register(registries.Validators) }},
{name: "item source relatedness validator", register: func() error { return itemrelatedness.Register(registries.Validators) }},
{name: "npc occurrence shape validator", register: func() error { return npcoccurrenceshape.Register(registries.Validators) }},
{name: "npc occurrence registry validator", register: func() error { return npcoccurrenceregistry.Register(registries.Validators) }},
{name: "npc occurrence source references validator", register: func() error { return npcoccurrencerefs.Register(registries.Validators) }},
@@ -117,6 +125,12 @@ func registerValidators(registries pipeline.Registries) error {
{name: "item-event-list always reject validator", register: func() error {
return alwaysreject.RegisterTyped[dnd.ItemEventList](registries.Validators, dnd.ItemEventListKind)
}},
{name: "item-registry always accept validator", register: func() error {
return alwaysaccept.RegisterTyped[dnd.ItemRegistry](registries.Validators, dnd.ItemRegistryKind)
}},
{name: "item-registry always reject validator", register: func() error {
return alwaysreject.RegisterTyped[dnd.ItemRegistry](registries.Validators, dnd.ItemRegistryKind)
}},
{name: "npc-occurrence-list always accept validator", register: func() error {
return alwaysaccept.RegisterTyped[dnd.NPCOccurrenceList](registries.Validators, dnd.NPCOccurrenceListKind)
}},

View File

@@ -0,0 +1,73 @@
// Package identity validates stable D&D item-type identity after normalization.
package identity
import (
"context"
"fmt"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
domainidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
itemshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemregistry/shape"
)
const (
Key = "normalize/dnd/item-registry/identity"
ReasonCode = "invalid_item_identity"
policy = domainidentity.Policy
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.ItemRegistry] = (*Validator)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
func New(Options) *Validator { return &Validator{} }
func (v *Validator) Name() string { return Key }
func (v *Validator) ExecutionClass() contracts.ExecutionClass {
return contracts.ExecutionClassDeterministic
}
func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
}
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemRegistry]) (contracts.ValidationResult, error) {
if err := itemshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
identityIssues := domainidentity.ValidateList(req.Value)
if len(identityIssues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
issues := make([]string, len(identityIssues))
for index, issue := range identityIssues {
issues[index] = fmt.Sprintf("items[%d] %s: %s", issue.RecordIndex, issue.Code, diagnostics.Quote(issue.Value))
}
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: diagnostics.Aggregate("invalid item identity", issues)}, nil
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemRegistryKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemRegistry], error) {
options, err := DecodeOptions(request.Options)
if err != nil {
return nil, err
}
return New(options), nil
})
}
func DecodeOptions(options map[string]any) (Options, error) {
if err := pipeline.RejectUnknownOptions(options); err != nil {
return Options{}, err
}
return Options{}, nil
}
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }

View File

@@ -0,0 +1,40 @@
package identity
import (
"context"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
domainidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/items/identity"
)
func TestValidatorRejectsInvalidAndDuplicateItemIdentity(t *testing.T) {
value := dnd.ItemRegistry{Items: []dnd.Item{
{ID: "wrong", Name: "Rope", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}},
{ID: domainidentity.DeriveID("rope"), Name: "rope", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}},
}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemRegistry]{Value: value})
if err != nil || result.Approved || result.ReasonCode != ReasonCode || !strings.Contains(result.Message, "invalid_id") || !strings.Contains(result.Message, "duplicate_canonical_identity") {
t.Fatalf("Validate() = %#v, %v; want identity rejection", result, err)
}
}
func TestValidatorRegistersPolicy(t *testing.T) {
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatal(err)
}
if got, ok := registry.Spec(Key); !ok || got != Spec() || got.ExecutionClass != contracts.ExecutionClassDeterministic {
t.Fatalf("registered spec = %#v, present = %t", got, ok)
}
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Value != domainidentity.Policy {
t.Fatalf("fingerprints = %#v", got)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions accepted unknown options")
}
}