Improve D&D validation reliability

This commit is contained in:
2026-08-29 01:24:45 +00:00
parent 4da9360d74
commit 917d150279
55 changed files with 1300 additions and 565 deletions

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"
combatshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/combatturns/shape"
)
@@ -15,7 +16,7 @@ import (
const (
Key = "extract/dnd/combat-turns/source_refs"
ReasonCode = "invalid_combat_turn_source_refs"
policy = "dnd.combat_turns.validator.source_refs.v2"
policy = "dnd.combat_turns.validator.source_refs.v3"
)
type Options struct{}
@@ -40,11 +41,11 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
if err := combatshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
var coverage *chunkCoverage
var coverage shared.ChunkCoverage
if req.Stage == string(pipeline.StageExtract) {
coverage = newChunkCoverage(req.Chunk)
coverage = shared.NewChunkCoverage(req.Chunk)
}
issues := sourceRefIssues(source.NewDocumentIndex(req.Source), req.Source, coverage, req.Value)
issues, corrections := sourceRefIssues(source.NewDocumentIndex(req.Source), req.Source, coverage, req.Stage == string(pipeline.StageExtract), req.Value)
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
@@ -52,54 +53,28 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
Approved: false,
ReasonCode: ReasonCode,
Message: diagnostics.Aggregate("invalid combat turn source references", issues),
CorrectionGuidance: "Return combat turns whose source references identify valid transcript ranges within the supplied extraction chunk and directly support each turn.",
CorrectionGuidance: corrections.Guidance("Correct every rejected combat-turn citation and return the complete replacement combat-turn list"),
}, nil
}
func sourceRefIssues(index source.DocumentIndex, doc *source.SourceDocument, coverage *chunkCoverage, value dnd.CombatTurnList) []string {
func sourceRefIssues(index source.DocumentIndex, doc *source.SourceDocument, coverage shared.ChunkCoverage, checkCoverage bool, value dnd.CombatTurnList) ([]string, diagnostics.Corrections) {
issues := make([]string, 0)
var corrections diagnostics.Corrections
for turnIndex, turn := range value.CombatTurns {
for refIndex, ref := range turn.SourceRefs {
record := fmt.Sprintf("Affected %s for actor %s, citing %s.", diagnostics.Quote(string(turn.TurnKind)), diagnostics.Quote(turn.Actor), diagnostics.SourceRefRange(ref))
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("combat_turns[%d].source_refs[%d]: %s", turnIndex, refIndex, diagnostics.Truncate(err.Error())))
corrections.Add("valid-range", "Use positive source range endpoints that occur in the supplied transcript, with the earlier unit first.", record)
continue
}
if coverage != nil && !coverage.contains(doc, ref) {
if checkCoverage && !coverage.Contains(index, doc, ref) {
issues = append(issues, fmt.Sprintf("combat_turns[%d].source_refs[%d]: source reference is outside the current extraction chunk", turnIndex, refIndex))
corrections.Add("chunk-range", "Use only source ranges wholly contained in the supplied extraction chunk.", record)
}
}
}
return issues
}
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 issues, corrections
}
func Spec() pipeline.ValidatorSpec {