Files
notarius/internal/modules/chunk/dnd/scenes/chunker.go

304 lines
9.1 KiB
Go

package scenes
import (
"context"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
const Key = "dnd/scenes"
var requiredCapabilities = []string{
"source.transcript",
}
var providedCapabilities = []string{
"chunks",
"chunks.scenes",
}
var _ contracts.Chunker = (*Chunker)(nil)
var _ contracts.ManifestMetadataProvider = (*Chunker)(nil)
type Chunker struct{}
func New() *Chunker {
return &Chunker{}
}
func (c *Chunker) Key() string {
return Key
}
func (c *Chunker) ManifestMetadata() map[string]any {
promptMetadata := scenesPromptBundle.Metadata()
metadata := map[string]any{
"prompt_id": PromptID,
"prompt_version": promptMetadata.PromptVersion,
"prompt_sha256": promptMetadata.SHA256,
"response_schema_key": string(ResponseSchemaKey),
"response_schema_id": ResponseSchemaID,
"response_schema_name": ResponseSchemaName,
}
if schema, err := loadResponseSchema(); err == nil {
metadata["response_schema_version"] = schema.Version
metadata["response_schema_sha256"] = schema.SHA256
}
return metadata
}
func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
if c == nil {
return contracts.ChunkResult{}, chunkerErrorf("chunker must not be nil")
}
if ctx == nil {
return contracts.ChunkResult{}, chunkerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.ChunkResult{}, chunkerErrorf("context error before chunking: %w", err)
}
if req.Source == nil {
return contracts.ChunkResult{}, chunkerErrorf("source must not be nil")
}
if len(req.Source.Units) == 0 {
return contracts.ChunkResult{}, chunkerErrorf("source units must not be empty")
}
if err := source.ValidateDocument(req.Source); err != nil {
return contracts.ChunkResult{}, chunkerErrorf("validate source document: %w", err)
}
if req.LLMClient == nil {
return contracts.ChunkResult{}, chunkerErrorf("LLM client must not be nil")
}
if len(req.Options) > 0 {
return contracts.ChunkResult{}, chunkerErrorf("options are not supported")
}
system, user, _, err := renderPrompt(req)
if err != nil {
return contracts.ChunkResult{}, chunkerErrorf("render prompt: %w", err)
}
schema, err := loadResponseSchema()
if err != nil {
return contracts.ChunkResult{}, chunkerErrorf("load response schema %q: %w", ResponseSchemaKey, err)
}
var response chunkResponse
if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
StageName: Key,
Messages: []contracts.LLMMessage{
{Role: "system", Content: system},
{Role: "user", Content: user},
},
ResponseSchemaName: schema.Name,
ResponseSchema: schema.JSONSchema,
}, &response); err != nil {
return contracts.ChunkResult{}, chunkerErrorf("complete structured output: %w", err)
}
chunks, err := chunksFromResponse(req.Source, response)
if err != nil {
return contracts.ChunkResult{}, chunkerErrorf("malformed structured output: %w", err)
}
return contracts.ChunkResult{
Chunks: chunks,
Warnings: warningsFromCaveats(response.BoundaryCaveats),
}, nil
}
func ModuleSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageChunk,
Requires: append([]string(nil), requiredCapabilities...),
Provides: append([]string(nil), providedCapabilities...),
}
}
func Register(registry *pipeline.ChunkerRegistry) error {
return registry.RegisterWithSpec(ModuleSpec(), func() (contracts.Chunker, error) {
return New(), nil
})
}
func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]contracts.SourceChunk, error) {
if response.Scenes == nil {
return nil, fmt.Errorf("scenes must be present")
}
if len(response.Scenes) == 0 {
return nil, fmt.Errorf("scenes must not be empty")
}
unitIndexes := make(map[string]int, len(doc.Units))
for i, unit := range doc.Units {
unitIndexes[unit.ID] = i
}
chunks := make([]contracts.SourceChunk, 0, len(response.Scenes))
previousEnd := -1
for i, scene := range response.Scenes {
normalized, err := normalizeScene(i, scene)
if err != nil {
return nil, err
}
startIndex, ok := unitIndexes[normalized.StartUnitID]
if !ok {
return nil, fmt.Errorf("scene[%d] start_unit_id %q was not found", i, normalized.StartUnitID)
}
endIndex, ok := unitIndexes[normalized.EndUnitID]
if !ok {
return nil, fmt.Errorf("scene[%d] end_unit_id %q was not found", i, normalized.EndUnitID)
}
if startIndex > endIndex {
return nil, fmt.Errorf("scene[%d] start_unit_id %q appears after end_unit_id %q", i, normalized.StartUnitID, normalized.EndUnitID)
}
if i == 0 && startIndex != 0 {
return nil, fmt.Errorf("first scene must start at first source unit %q", doc.Units[0].ID)
}
if i > 0 {
if startIndex <= previousEnd {
return nil, fmt.Errorf("scene[%d] overlaps previous scene", i)
}
if startIndex > previousEnd+1 {
return nil, fmt.Errorf("scene[%d] leaves a gap after previous scene", i)
}
}
previousEnd = endIndex
units := cloneUnits(doc.Units[startIndex : endIndex+1])
chunks = append(chunks, contracts.SourceChunk{
ID: fmt.Sprintf("scene-%06d", i+1),
SourceID: doc.ID,
Index: i,
Units: units,
Metadata: map[string]any{
"scene_title": normalized.ShortTitle,
"primary_mode": normalized.PrimaryMode,
"main_participants": append([]string(nil), normalized.MainParticipants...),
"summary": normalized.Summary,
"boundary_note": normalized.BoundaryNote,
"boundary_confidence": normalized.BoundaryConfidence,
"start_unit_id": normalized.StartUnitID,
"end_unit_id": normalized.EndUnitID,
"unit_count": len(units),
},
})
}
if previousEnd != len(doc.Units)-1 {
return nil, fmt.Errorf("final scene must end at final source unit %q", doc.Units[len(doc.Units)-1].ID)
}
return chunks, nil
}
func normalizeScene(index int, scene sceneResponse) (sceneResponse, error) {
out := sceneResponse{
StartUnitID: strings.TrimSpace(scene.StartUnitID),
EndUnitID: strings.TrimSpace(scene.EndUnitID),
ShortTitle: strings.TrimSpace(scene.ShortTitle),
PrimaryMode: strings.TrimSpace(scene.PrimaryMode),
Summary: strings.TrimSpace(scene.Summary),
BoundaryNote: strings.TrimSpace(scene.BoundaryNote),
BoundaryConfidence: strings.TrimSpace(scene.BoundaryConfidence),
}
required := map[string]string{
"start_unit_id": out.StartUnitID,
"end_unit_id": out.EndUnitID,
"short_title": out.ShortTitle,
"primary_mode": out.PrimaryMode,
"summary": out.Summary,
"boundary_note": out.BoundaryNote,
"boundary_confidence": out.BoundaryConfidence,
}
for field, value := range required {
if value == "" {
return sceneResponse{}, 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)
}
if !validBoundaryConfidence(out.BoundaryConfidence) {
return sceneResponse{}, 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)
}
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)
}
out.MainParticipants = append(out.MainParticipants, trimmed)
}
return out, nil
}
func validPrimaryMode(value string) bool {
switch value {
case "Recap", "Discussion", "Combat", "Narrative":
return true
default:
return false
}
}
func validBoundaryConfidence(value string) bool {
switch value {
case "High", "Medium", "Low":
return true
default:
return false
}
}
func warningsFromCaveats(caveats []string) []contracts.Warning {
if len(caveats) == 0 {
return nil
}
warnings := make([]contracts.Warning, 0, len(caveats))
for _, caveat := range caveats {
warnings = append(warnings, contracts.Warning{
Scope: Key,
ReasonCode: "scene_boundary_caveat",
Message: caveat,
})
}
return warnings
}
func cloneUnits(units []source.SourceUnit) []source.SourceUnit {
out := make([]source.SourceUnit, 0, len(units))
for _, unit := range units {
out = append(out, source.SourceUnit{
ID: unit.ID,
Kind: unit.Kind,
Text: unit.Text,
Metadata: cloneMetadata(unit.Metadata),
})
}
return out
}
func cloneMetadata(metadata map[string]any) map[string]any {
if len(metadata) == 0 {
return nil
}
out := make(map[string]any, len(metadata))
for key, value := range metadata {
out[key] = value
}
return out
}
func chunkerErrorf(format string, args ...any) error {
return fmt.Errorf("dnd scenes chunker: "+format, args...)
}