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

Improve D&D validation reliability

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-29 01:24:45 +00:00
parent 4da9360d74
commit 917d150279
55 changed files with 1300 additions and 565 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
internal/modules/dnd/validate/npcregistry/source_refs/validator.go
View File

@@ -8,6 +8,7 @@ import (
"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/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
npcshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcregistry/shape"
)
@@ -15,7 +16,7 @@ import (
const (
Key = "extract/dnd/npc-registry/source_refs"
ReasonCode = "invalid_npc_source_refs"
policy = "dnd.npc_registry.validator.source_refs.v2"
policy = "dnd.npc_registry.validator.source_refs.v3"
)
type Options struct{}
@@ -41,56 +42,40 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
var coverage *chunkCoverage
var coverage shared.ChunkCoverage
if req.Stage == string(pipeline.StageExtract) {
coverage = newChunkCoverage(req.Chunk)
coverage = shared.NewChunkCoverage(req.Chunk)
}
issues := make([]string, 0)
var corrections diagnostics.Corrections
normalization := req.Stage == string(pipeline.StageNormalize)
validRangeRule := "Use positive source range endpoints that occur in the supplied transcript, with the earlier unit first."
guidancePrefix := "Correct every rejected NPC citation and return the complete replacement NPC registry"
if normalization {
validRangeRule = "Revise the duplicate-group proposals so every selected canonical NPC preserves valid transcript evidence; do not reproduce application IDs."
guidancePrefix = "Correct the duplicate-group proposals and return the complete replacement proposal response"
}
for npcIndex, npc := range req.Value.NPCs {
for refIndex, ref := range npc.SourceRefs {
record := fmt.Sprintf("Affected NPC %s, citing %s.", diagnostics.Quote(npc.Name), diagnostics.SourceRefRange(ref))
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("npcs[%d].source_refs[%d]: %s", npcIndex, refIndex, diagnostics.Truncate(err.Error())))
corrections.Add("valid-range", validRangeRule, record)
continue
}
if coverage != nil && !coverage.contains(req.Source, ref) {
if req.Stage == string(pipeline.StageExtract) && !coverage.Contains(index, req.Source, ref) {
issues = append(issues, fmt.Sprintf("npcs[%d].source_refs[%d]: source reference is outside the current extraction chunk", npcIndex, refIndex))
corrections.Add("chunk-range", "Use only source ranges wholly contained in the supplied extraction chunk.", record)
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return rejection(diagnostics.Aggregate("invalid NPC source references", issues)), nil
}
type chunkCoverage struct {
sourceID string
unitIDs map[int]struct{}
}
func newChunkCoverage(chunk *source.Chunk) *chunkCoverage {
coverage := &chunkCoverage{sourceID: chunk.SourceID, unitIDs: make(map[int]struct{}, len(chunk.Units))}
for _, unit := range chunk.Units {
coverage.unitIDs[unit.ID] = struct{}{}
}
return coverage
}
func (coverage *chunkCoverage) contains(doc *source.SourceDocument, ref source.SourceRef) bool {
if coverage == nil || doc == nil || ref.SourceID != coverage.sourceID {
return false
}
start, startOK := source.UnitIndex(doc, ref.StartUnitID)
end, endOK := source.UnitIndex(doc, ref.EndUnitID)
if !startOK || !endOK || start > end {
return false
}
for position := start; position <= end; position++ {
if _, found := coverage.unitIDs[doc.Units[position].ID]; !found {
return false
}
}
return true
return rejection(
diagnostics.Aggregate("invalid NPC source references", issues),
corrections.Guidance(guidancePrefix),
), nil
}
func Spec() pipeline.ValidatorSpec {
@@ -116,6 +101,6 @@ func DecodeOptions(options map[string]any) (Options, error) {
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }
func rejection(message string) contracts.ValidationResult {
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: message, CorrectionGuidance: "Return registry NPCs whose source references identify valid transcript ranges within the supplied extraction chunk and directly support each proper NPC name."}
func rejection(message, guidance string) contracts.ValidationResult {
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: message, CorrectionGuidance: guidance}
}