Add standalone D&D combat turn extraction

This commit is contained in:
2026-07-21 05:08:02 +00:00
parent 6dd695611c
commit 2fbb3813aa
22 changed files with 1924 additions and 4 deletions

View File

@@ -0,0 +1,156 @@
package sourcerelatedness
import (
"context"
"fmt"
"strings"
"unicode"
"unicode/utf8"
"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/npcs/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
combatshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/combatturns/shape"
)
const (
Key = "extract/dnd/combat-turns/source_relatedness"
WarningReasonCode = "combat_turn_not_near_source"
policy = "dnd.combat_turns.validator.source_relatedness.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.CombatTurnList] = (*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.CombatTurnList]) (contracts.ValidationResult, error) {
if combatshape.Validate(req.Value) != nil || !sourceRefsValid(req.Source, req.Value) {
return contracts.ValidationResult{Approved: true}, nil
}
warnings := make([]contracts.Warning, 0)
for turnIndex, turn := range req.Value.CombatTurns {
citedText := citedTextKey(req.Source, turn.SourceRefs)
issues := make([]string, 0)
if !actorAppearsInCitedText(citedText, turn.Actor) {
issues = append(issues, fmt.Sprintf("actor %s was not found in cited source text", diagnostics.Quote(turn.Actor)))
}
for actionIndex, action := range turn.Actions {
if !declarationAppearsInCitedText(citedText, action.Declaration) {
issues = append(issues, fmt.Sprintf("action %d declaration %s was not found in cited source text", actionIndex, diagnostics.Quote(action.Declaration)))
}
}
if len(issues) == 0 {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: fmt.Sprintf("combat_turns[%d]", turnIndex),
ReasonCode: WarningReasonCode,
Message: diagnostics.Aggregate("combat turn not near source", issues),
})
}
return contracts.ValidationResult{Approved: true, Warnings: warnings}, nil
}
func sourceRefsValid(doc *source.SourceDocument, value dnd.CombatTurnList) bool {
for _, turn := range value.CombatTurns {
for _, ref := range turn.SourceRefs {
if source.ValidateRef(doc, ref) != nil {
return false
}
}
}
return true
}
func citedTextKey(doc *source.SourceDocument, refs []source.SourceRef) string {
if doc == nil {
return ""
}
included := make([]bool, len(doc.Units))
for _, ref := range refs {
start, _ := source.UnitIndex(doc, ref.StartUnitID)
end, _ := source.UnitIndex(doc, ref.EndUnitID)
for index := start; index <= end && index < len(included); index++ {
included[index] = true
}
}
parts := make([]string, 0)
for index, unit := range doc.Units {
if included[index] {
parts = append(parts, unit.Text)
}
}
return identity.ComparisonKey(strings.Join(parts, " "))
}
func actorAppearsInCitedText(citedText string, actor string) bool {
key := identity.ComparisonKey(actor)
return key != "" && strings.Contains(citedText, key)
}
func declarationAppearsInCitedText(citedText string, declaration string) bool {
citedTokens := tokenSet(citedText)
for _, token := range comparisonTokens(declaration) {
if utf8.RuneCountInString(token) >= 4 {
if _, ok := citedTokens[token]; ok {
return true
}
}
}
return false
}
func comparisonTokens(value string) []string {
value = identity.ComparisonKey(value)
if value == "" {
return nil
}
return strings.FieldsFunc(value, func(r rune) bool { return !unicode.IsLetter(r) && !unicode.IsDigit(r) })
}
func tokenSet(value string) map[string]struct{} {
tokens := comparisonTokens(value)
set := make(map[string]struct{}, len(tokens))
for _, token := range tokens {
set[token] = struct{}{}
}
return set
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.CombatTurnListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.CombatTurnList], 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 +1,101 @@
package sourcerelatedness
import (
"context"
"strings"
"testing"
"unicode/utf8"
"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"
)
func TestValidatorUsesDocumentOrderAndUnicodeComparisonForActorAndDeclaration(t *testing.T) {
resolution := "The goblin is hit."
value := dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{
Actor: "O'Rin Thorn", TurnKind: dnd.CombatTurnKindTurn,
Actions: []dnd.CombatAction{{Category: dnd.CombatActionCategoryAttack, Declaration: "O'Rin attacks", Targets: []string{"unmentioned target"}, Resolution: &resolution}},
Summary: "O'Rin attacks.", SourceRefs: []source.SourceRef{
{SourceID: "session", StartUnitID: 2, EndUnitID: 2},
{SourceID: "session", StartUnitID: 1, EndUnitID: 2},
},
}}}
doc := &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{
{ID: 1, Kind: "message", Text: "orin\u2003thorn advances."},
{ID: 2, Kind: "message", Text: "Orin attacks the goblin."},
}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.CombatTurnList]{Source: doc, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("Validate() = %#v, %v; want Unicode-related approval without target warning", result, err)
}
}
func TestValidatorWarnsOncePerTurnForUnrelatedActorAndActions(t *testing.T) {
value := dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{
Actor: "Missing\nName", TurnKind: dnd.CombatTurnKindReaction,
Actions: []dnd.CombatAction{
{Category: dnd.CombatActionCategoryOther, Declaration: "hit", Targets: []string{}, Resolution: nil},
{Category: dnd.CombatActionCategoryOther, Declaration: "unseen monster", Targets: []string{}, Resolution: nil},
},
Summary: "An unrelated event.", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.CombatTurnList]{Source: relatednessDocument(), Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 1 {
t.Fatalf("Validate() = %#v, %v; want one warning for the turn", result, err)
}
warning := result.Warnings[0]
if warning.Scope != "combat_turns[0]" || warning.ReasonCode != WarningReasonCode || !strings.Contains(warning.Message, `Missing\nName`) || strings.Contains(warning.Message, "Missing\nName") || !strings.Contains(warning.Message, "action 0") || !strings.Contains(warning.Message, "action 1") || !utf8.ValidString(warning.Message) {
t.Fatalf("warning = %#v, want one safely quoted bounded warning", warning)
}
}
func TestValidatorDefersMalformedShapeAndInvalidRanges(t *testing.T) {
invalidShape := dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{Actor: "Aria"}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.CombatTurnList]{Source: relatednessDocument(), Value: invalidShape})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("shape deferral = %#v, %v; want approval without warning", result, err)
}
invalidRange := validCombatTurnList()
invalidRange.CombatTurns[0].SourceRefs[0].StartUnitID = 99
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.CombatTurnList]{Source: relatednessDocument(), Value: invalidRange})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("invalid-range deferral = %#v, %v; want approval without warning", result, err)
}
}
func TestValidatorIgnoresReferenceMaterialAndRegistersPolicy(t *testing.T) {
value := validCombatTurnList()
references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("Aria attacks")}}}}}
doc := &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "The party waits."}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.CombatTurnList]{Source: doc, References: references, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 1 {
t.Fatalf("reference-only relatedness = %#v, %v; want warning from transcript-only evidence", result, err)
}
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Name != "policy" || got[0].Value != policy {
t.Fatalf("CheckpointFingerprints() = %#v, want relatedness policy", got)
}
if Spec().Key != Key || Spec().ExecutionClass != contracts.ExecutionClassDeterministic {
t.Fatalf("Spec() = %#v, want deterministic relatedness validator", Spec())
}
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v", err)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
}
func validCombatTurnList() dnd.CombatTurnList {
return dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{
Actor: "Aria", TurnKind: dnd.CombatTurnKindTurn,
Actions: []dnd.CombatAction{{Category: dnd.CombatActionCategoryAttack, Declaration: "Aria attacks", Targets: []string{"absent target"}, Resolution: nil}},
Summary: "Aria attacks.", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
}}}
}
func relatednessDocument() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "The party waits."}}}
}