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

Update D&D schemas to require integer unit_id values

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-06 14:41:24 -05:00
parent 79a585d17e
commit aec807fcb0
18 changed files with 403 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
internal/modules/chunk/dnd/scenes/assets/prompts/instructions.md
View File

@@ -22,7 +22,8 @@ dnd/scenes boundary policy:
- return sequential scenes with no gaps;
- do not overlap scenes;
- preserve source-unit order;
- use exact source-unit IDs from the transcript;
- use 1-based integer source-unit numbers from the transcript, where 1 is the
first provided source unit;
- each scene must have start_unit_id and end_unit_id;
- do not include final chunk IDs or chunk indexes.

8
internal/modules/chunk/dnd/scenes/assets/schemas/dnd_scenes.v1.json
View File

@@ -26,12 +26,12 @@
],
"properties": {
"start_unit_id": {
"type": "string",
"minLength": 1
"type": "integer",
"minimum": 1
},
"end_unit_id": {
"type": "string",
"minLength": 1
"type": "integer",
"minimum": 1
},
"short_title": {
"type": "string",

29
internal/modules/chunk/dnd/scenes/chunker.go
View File

@@ -150,7 +150,7 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
chunks := make([]contracts.SourceChunk, 0, len(response.Scenes))
previousEnd := -1
for i, scene := range response.Scenes {
normalized, err := normalizeScene(i, scene)
normalized, err := normalizeScene(doc, i, scene)
if err != nil {
return nil, err
}
@@ -206,10 +206,19 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
return chunks, nil
}
func normalizeScene(index int, scene sceneResponse) (sceneResponse, error) {
out := sceneResponse{
StartUnitID: strings.TrimSpace(scene.StartUnitID),
EndUnitID: strings.TrimSpace(scene.EndUnitID),
func normalizeScene(doc *source.SourceDocument, index int, scene sceneResponse) (normalizedScene, error) {
startUnitID, err := dnd.ResolveUnitID(doc, "start_unit_id", scene.StartUnitID)
if err != nil {
return normalizedScene{}, fmt.Errorf("scene[%d] %w", index, err)
}
endUnitID, err := dnd.ResolveUnitID(doc, "end_unit_id", scene.EndUnitID)
if err != nil {
return normalizedScene{}, fmt.Errorf("scene[%d] %w", index, err)
}
out := normalizedScene{
StartUnitID: startUnitID,
EndUnitID: endUnitID,
ShortTitle: strings.TrimSpace(scene.ShortTitle),
PrimaryMode: strings.TrimSpace(scene.PrimaryMode),
Summary: strings.TrimSpace(scene.Summary),
@@ -228,23 +237,23 @@ func normalizeScene(index int, scene sceneResponse) (sceneResponse, error) {
}
for field, value := range required {
if value == "" {
return sceneResponse{}, fmt.Errorf("scene[%d] %s must not be empty", index, field)
return normalizedScene{}, fmt.Errorf("scene[%d] %s must not be empty", index, field)
}
}
if !validPrimaryMode(out.PrimaryMode) {
return sceneResponse{}, fmt.Errorf("scene[%d] primary_mode %q is not supported", index, out.PrimaryMode)
return normalizedScene{}, fmt.Errorf("scene[%d] primary_mode %q is not supported", index, out.PrimaryMode)
}
if !validBoundaryConfidence(out.BoundaryConfidence) {
return sceneResponse{}, fmt.Errorf("scene[%d] boundary_confidence %q is not supported", index, out.BoundaryConfidence)
return normalizedScene{}, fmt.Errorf("scene[%d] boundary_confidence %q is not supported", index, out.BoundaryConfidence)
}
if len(scene.MainParticipants) == 0 {
return sceneResponse{}, fmt.Errorf("scene[%d] main_participants must not be empty", index)
return normalizedScene{}, fmt.Errorf("scene[%d] main_participants must not be empty", index)
}
out.MainParticipants = make([]string, 0, len(scene.MainParticipants))
for participantIndex, participant := range scene.MainParticipants {
trimmed := strings.TrimSpace(participant)
if trimmed == "" {
return sceneResponse{}, fmt.Errorf("scene[%d] main_participants[%d] must not be empty", index, participantIndex)
return normalizedScene{}, fmt.Errorf("scene[%d] main_participants[%d] must not be empty", index, participantIndex)
}
out.MainParticipants = append(out.MainParticipants, trimmed)
}

24
internal/modules/chunk/dnd/scenes/chunker_test.go
View File

@@ -105,8 +105,8 @@ func TestChunkReturnsSceneChunksFromStructuredOutput(t *testing.T) {
response: chunkResponse{
Scenes: []sceneResponse{
{
StartUnitID: "seg-001",
EndUnitID: "seg-002",
StartUnitID: dnd.UnitRefFromInt(1),
EndUnitID: dnd.UnitRefFromInt(2),
ShortTitle: " Goblin parley ",
PrimaryMode: "Discussion",
MainParticipants: []string{" Aria ", "Goblin scout"},
@@ -115,8 +115,8 @@ func TestChunkReturnsSceneChunksFromStructuredOutput(t *testing.T) {
BoundaryConfidence: "High",
},
{
StartUnitID: "seg-003",
EndUnitID: "seg-004",
StartUnitID: dnd.UnitRefFromInt(3),
EndUnitID: dnd.UnitRefFromInt(4),
ShortTitle: "Ambush at the gate",
PrimaryMode: "Combat",
MainParticipants: []string{"Aria", "Goblin ambushers"},
@@ -204,8 +204,8 @@ func TestChunkPassesReferencesAsPromptInputs(t *testing.T) {
client := &fakeScenesLLMClient{response: chunkResponse{
Scenes: []sceneResponse{
{
StartUnitID: "seg-001",
EndUnitID: "seg-004",
StartUnitID: dnd.UnitRefFromInt(1),
EndUnitID: dnd.UnitRefFromInt(4),
ShortTitle: "Ambush",
PrimaryMode: "Combat",
MainParticipants: []string{"Aria"},
@@ -445,8 +445,8 @@ func TestChunkRejectsMalformedStructuredOutput(t *testing.T) {
name: "empty metadata field",
response: replaceScenes(validSceneResponse(), []sceneResponse{
{
StartUnitID: "seg-001",
EndUnitID: "seg-004",
StartUnitID: dnd.UnitRefFromString("seg-001"),
EndUnitID: dnd.UnitRefFromString("seg-004"),
ShortTitle: " ",
PrimaryMode: "Narrative",
MainParticipants: []string{"Aria"},
@@ -461,8 +461,8 @@ func TestChunkRejectsMalformedStructuredOutput(t *testing.T) {
name: "empty participant",
response: replaceScenes(validSceneResponse(), []sceneResponse{
{
StartUnitID: "seg-001",
EndUnitID: "seg-004",
StartUnitID: dnd.UnitRefFromString("seg-001"),
EndUnitID: dnd.UnitRefFromString("seg-004"),
ShortTitle: "Title",
PrimaryMode: "Narrative",
MainParticipants: []string{"Aria", " "},
@@ -553,8 +553,8 @@ func replaceScenes(response chunkResponse, scenes []sceneResponse) chunkResponse
func scene(startUnitID string, endUnitID string) sceneResponse {
return sceneResponse{
StartUnitID: startUnitID,
EndUnitID: endUnitID,
StartUnitID: dnd.UnitRefFromString(startUnitID),
EndUnitID: dnd.UnitRefFromString(endUnitID),
ShortTitle: "Scene title",
PrimaryMode: "Narrative",
MainParticipants: []string{"Aria"},

29
internal/modules/chunk/dnd/scenes/model.go
View File

@@ -1,17 +1,30 @@
package scenes
import "gitea.maximumdirect.net/eric/notarius/internal/modules/sharedassets/dnd"
type chunkResponse struct {
Scenes []sceneResponse `json:"scenes"`
BoundaryCaveats []string `json:"boundary_caveats"`
}
type sceneResponse struct {
StartUnitID string `json:"start_unit_id"`
EndUnitID string `json:"end_unit_id"`
ShortTitle string `json:"short_title"`
PrimaryMode string `json:"primary_mode"`
MainParticipants []string `json:"main_participants"`
Summary string `json:"summary"`
BoundaryNote string `json:"boundary_note"`
BoundaryConfidence string `json:"boundary_confidence"`
StartUnitID dnd.UnitRef `json:"start_unit_id"`
EndUnitID dnd.UnitRef `json:"end_unit_id"`
ShortTitle string `json:"short_title"`
PrimaryMode string `json:"primary_mode"`
MainParticipants []string `json:"main_participants"`
Summary string `json:"summary"`
BoundaryNote string `json:"boundary_note"`
BoundaryConfidence string `json:"boundary_confidence"`
}
type normalizedScene struct {
StartUnitID string
EndUnitID string
ShortTitle string
PrimaryMode string
MainParticipants []string
Summary string
BoundaryNote string
BoundaryConfidence string
}

21
internal/modules/chunk/dnd/scenes/schema_test.go
View File

@@ -64,8 +64,11 @@ func TestResponseSchemaShapeUsesSourceUnitBoundaries(t *testing.T) {
}
for _, field := range []string{"start_unit_id", "end_unit_id"} {
property := sceneProperties[field].(map[string]any)
if property["type"] != "string" {
t.Fatalf("%s type = %#v, want string", field, property["type"])
if property["type"] != "integer" {
t.Fatalf("%s type = %#v, want integer", field, property["type"])
}
if property["minimum"] != float64(1) {
t.Fatalf("%s minimum = %#v, want 1", field, property["minimum"])
}
}
@@ -87,7 +90,7 @@ func TestResponseSchemaShapeUsesSourceUnitBoundaries(t *testing.T) {
}
}
func TestResponseStructRejectsIntegerBoundaries(t *testing.T) {
func TestResponseStructAcceptsIntegerBoundaries(t *testing.T) {
raw := []byte(`{
"scenes": [
{
@@ -105,12 +108,14 @@ func TestResponseStructRejectsIntegerBoundaries(t *testing.T) {
}`)
var response chunkResponse
err := json.Unmarshal(raw, &response)
if err == nil {
t.Fatalf("Unmarshal() error = nil, want integer boundary type error: %#v", response)
if err := json.Unmarshal(raw, &response); err != nil {
t.Fatalf("Unmarshal() error = %v, want nil", err)
}
if !strings.Contains(err.Error(), "string") {
t.Fatalf("Unmarshal() error = %v, want string type error", err)
if got := response.Scenes[0].StartUnitID.String(); got != "1" {
t.Fatalf("StartUnitID = %q, want 1", got)
}
if got := response.Scenes[0].EndUnitID.String(); got != "3" {
t.Fatalf("EndUnitID = %q, want 3", got)
}
}