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

Order spell and NPC extraction by document position

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-24 14:29:19 +00:00
parent 83fde83a58
commit 9bbf2535dd
8 changed files with 138 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
internal/modules/dnd/extract/npcs/canonicalize.go
View File

@@ -6,18 +6,19 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"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"
)
func canonicalizeResponse(response *extractionResponse, doc *source.SourceDocument) {
func canonicalizeResponse(response *extractionResponse, order shared.SourceRefOrder, sourceID string) {
if response == nil {
return
}
for index := range response.NPCs {
canonicalizeNPC(&response.NPCs[index])
canonicalizeNPC(&response.NPCs[index], order, sourceID)
}
sort.SliceStable(response.NPCs, func(i, j int) bool {
left, leftOK := earliestSourceIndex(doc, response.NPCs[i])
right, rightOK := earliestSourceIndex(doc, response.NPCs[j])
left, leftOK := order.EarliestValid(canonicalSourceRefs(response.NPCs[i].SourceRefs, sourceID))
right, rightOK := order.EarliestValid(canonicalSourceRefs(response.NPCs[j].SourceRefs, sourceID))
if leftOK != rightOK {
return leftOK
}
@@ -28,67 +29,11 @@ func canonicalizeResponse(response *extractionResponse, doc *source.SourceDocume
})
}
func canonicalizeNPC(npc *npcResponse) {
func canonicalizeNPC(npc *npcResponse, order shared.SourceRefOrder, sourceID string) {
if npc == nil {
return
}
sort.SliceStable(npc.SourceRefs, func(i, j int) bool {
left := npc.SourceRefs[i]
right := npc.SourceRefs[j]
if unitSortValue(left.StartUnitID) != unitSortValue(right.StartUnitID) {
return unitSortValue(left.StartUnitID) < unitSortValue(right.StartUnitID)
}
return unitSortValue(left.EndUnitID) < unitSortValue(right.EndUnitID)
})
npc.SourceRefs = dedupeSourceRefs(npc.SourceRefs)
}
func dedupeSourceRefs(refs []npcSourceRefResponse) []npcSourceRefResponse {
if len(refs) < 2 {
return refs
}
out := refs[:0]
var previous npcSourceRefResponse
for index, ref := range refs {
if index > 0 && sameSourceRef(previous, ref) {
continue
}
out = append(out, ref)
previous = ref
}
return out
}
func sameSourceRef(left npcSourceRefResponse, right npcSourceRefResponse) bool {
return left.StartUnitID == right.StartUnitID && left.EndUnitID == right.EndUnitID
}
func earliestSourceIndex(doc *source.SourceDocument, npc npcResponse) (int, bool) {
earliest := 0
found := false
for _, ref := range npc.SourceRefs {
start := ref.StartUnitID
end := ref.EndUnitID
if start > 0 && end > 0 {
startIndex, startOK := source.UnitIndex(doc, start)
endIndex, endOK := source.UnitIndex(doc, end)
if !startOK || !endOK || startIndex > endIndex {
continue
}
if !found || startIndex < earliest {
earliest = startIndex
found = true
}
}
}
return earliest, found
}
func unitSortValue(value int) int {
if value <= 0 {
return int(^uint(0) >> 1)
}
return value
npc.SourceRefs = npcResponseRefs(order.Canonicalize(canonicalSourceRefs(npc.SourceRefs, sourceID)))
}
func canonicalNPCList(response extractionResponse, sourceID string) dnd.NPCList {
@@ -120,3 +65,14 @@ func canonicalSourceRefs(values []npcSourceRefResponse, sourceID string) []sourc
}
return out
}
func npcResponseRefs(values []source.SourceRef) []npcSourceRefResponse {
if values == nil {
return nil
}
out := make([]npcSourceRefResponse, len(values))
for index, value := range values {
out[index] = npcSourceRefResponse{StartUnitID: value.StartUnitID, EndUnitID: value.EndUnitID}
}
return out
}

5
internal/modules/dnd/extract/npcs/extractor.go
View File

@@ -13,7 +13,7 @@ import (
const Key = "dnd/npcs"
const mappingPolicy = "dnd.npcs.extract_mapping.v1"
const mappingPolicy = "dnd.npcs.extract_mapping.v2"
var requiredCapabilities = []string{
"chunks",
@@ -129,6 +129,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if err != nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("%w", err)
}
order := shared.NewSourceRefOrder(req.Source)
var response extractionResponse
if _, err := e.llm.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
@@ -141,7 +142,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
}, &response); err != nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("complete structured output: %w", err)
}
canonicalizeResponse(&response, req.Source)
canonicalizeResponse(&response, order, req.Source.ID)
return contracts.TypedExtractionResult[dnd.NPCList]{Value: canonicalNPCList(response, req.Source.ID)}, nil
}

37
internal/modules/dnd/extract/npcs/extractor_test.go
View File

@@ -84,6 +84,43 @@ func TestExtractOrdersNPCsBySourcePositionRatherThanUnitID(t *testing.T) {
}
}
func TestExtractUsesDocumentOrderForNPCReferencesAndStableTies(t *testing.T) {
client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{
{Name: "Later", SourceRefs: responseSourceRefs(10, 10)},
{Name: "First", SourceRefs: []npcSourceRefResponse{
{StartUnitID: 10, EndUnitID: 10},
{StartUnitID: 30, EndUnitID: 30},
{StartUnitID: 30, EndUnitID: 30},
{StartUnitID: 999, EndUnitID: 0},
}},
{Name: "Second", SourceRefs: responseSourceRefs(30, 30)},
}}}
req := extractionRequest()
req.Source.Units = []source.SourceUnit{{ID: 30}, {ID: 10}}
req.Chunk.Units = append([]source.SourceUnit(nil), req.Source.Units...)
req.Chunk.Ref = source.SourceRef{SourceID: req.Source.ID, StartUnitID: 30, EndUnitID: 10}
result, err := newExtractor(t, client).Extract(context.Background(), req)
if err != nil {
t.Fatalf("Extract() error = %v", err)
}
if got := []string{result.Value.NPCs[0].Name, result.Value.NPCs[1].Name, result.Value.NPCs[2].Name}; !reflect.DeepEqual(got, []string{"First", "Second", "Later"}) {
t.Fatalf("NPC order = %#v, want document chronology with stable equal-evidence ties", got)
}
refs := result.Value.NPCs[0].SourceRefs
if got := []int{refs[0].StartUnitID, refs[1].StartUnitID, refs[2].StartUnitID}; !reflect.DeepEqual(got, []int{30, 10, 999}) {
t.Fatalf("source refs = %#v, want document order with exact duplicate removed", refs)
}
refs[0].StartUnitID = 777
for _, npc := range client.response.NPCs {
for _, ref := range npc.SourceRefs {
if ref.StartUnitID == 777 {
t.Fatal("result source references alias the model response")
}
}
}
}
func TestExtractPassesCampaignReferencesAsPromptInputs(t *testing.T) {
client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{}}}
req := extractionRequest()