Cleanup and complete the pipeline refactor

internal/modules/extract/dnd/spells/extractor.go

@@ -1,6 +1,7 @@
 package spells
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"fmt"
@@ -89,6 +90,10 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.ExtractionRequest
 	if req.LLMClient == nil {
 		return contracts.ExtractionResult{}, extractorErrorf("LLM client must not be nil")
 	}
+	sourceInput, err := chunkSourceInput(req)
+	if err != nil {
+		return contracts.ExtractionResult{}, err
+	}
 
 	var response extractionResponse
 	completion, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
@@ -97,7 +102,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.ExtractionRequest
 		PromptVersion: SchemaVersion,
 		ProfileID:     req.LLMProfile,
 		SessionID:     req.SessionID,
-		Inputs:        dnd.PromptInputs(req.SourceInput, req.References),
+		Inputs:        dnd.PromptInputs(sourceInput, req.References),
 	}, &response)
 	if err != nil {
 		return contracts.ExtractionResult{}, extractorErrorf("complete structured output: %w", err)
@@ -128,6 +133,26 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.ExtractionRequest
 	}, nil
 }
 
+func chunkSourceInput(req contracts.ExtractionRequest) (contracts.LLMInputMaterial, error) {
+	material := req.SourceInput.Clone()
+	if len(material.Content) == 0 {
+		material = contracts.NewLLMInputMaterial("source", req.Chunk.MediaType, req.Chunk.Content, "", "")
+	}
+	if !bytes.Equal(material.Content, req.Chunk.Content) {
+		return contracts.LLMInputMaterial{}, extractorErrorf("source input must match chunk %q content", req.Chunk.ID)
+	}
+	if material.Name == "" {
+		material.Name = "source"
+	}
+	if material.MediaType == "" {
+		material.MediaType = req.Chunk.MediaType
+	}
+	if material.SizeBytes == 0 {
+		material.SizeBytes = int64(len(material.Content))
+	}
+	return material, nil
+}
+
 func ModuleSpec() pipeline.ModuleSpec {
 	return pipeline.ModuleSpec{
 		Key:            Key,