Finish the references implementation for the extraction module and update roadmap documentation

internal/framework/pipeline/references.go

@@ -4,6 +4,7 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"fmt"
+	"mime"
 	"net/url"
 	"os"
 	"path/filepath"
@@ -17,7 +18,8 @@ import (
 
 const (
 	referenceOriginFile = "file"
-	referenceMediaType  = "text/plain; charset=utf-8"
+	referenceMediaType  = "text/plain"
+	unknownMediaType    = "application/octet-stream"
 )
 
 type ReferenceMaterializationOptions struct {
@@ -88,6 +90,10 @@ func materializeLaneReferences(
 		if !utf8.Valid(content) {
 			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q must be UTF-8 text", pipelineID, lane.ID, slotName, path)
 		}
+		mediaType := referenceMediaTypeForPath(path)
+		if !referenceMediaTypeAccepted(mediaType, slot.AcceptedMediaTypes) {
+			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q media type %q is not accepted", pipelineID, lane.ID, slotName, path, mediaType)
+		}
 		if slot.MaxBytes > 0 && int64(len(content)) > slot.MaxBytes {
 			return contracts.ReferenceSet{}, nil, fmt.Errorf("pipeline %q lane %q reference slot %q path %q is %d bytes, limit %d", pipelineID, lane.ID, slotName, path, len(content), slot.MaxBytes)
 		}
@@ -101,7 +107,7 @@ func materializeLaneReferences(
 
 		item := contracts.ReferenceItem{
 			SlotName:      slotName,
-			MediaType:     referenceMediaType,
+			MediaType:     mediaType,
 			Content:       append([]byte(nil), content...),
 			Digest:        referenceDigest(content),
 			Origin:        contracts.ReferenceOrigin{Type: referenceOriginFile, URI: fileURI(path)},
@@ -116,6 +122,43 @@ func materializeLaneReferences(
 	return set, warnings, nil
 }
 
+func referenceMediaTypeForPath(path string) string {
+	extension := strings.ToLower(filepath.Ext(path))
+	mediaType := mime.TypeByExtension(extension)
+	if strings.TrimSpace(mediaType) == "" {
+		if extension == ".md" || extension == ".markdown" {
+			return "text/markdown"
+		}
+		return unknownMediaType
+	}
+	return canonicalMediaType(mediaType)
+}
+
+func referenceMediaTypeAccepted(mediaType string, accepted []string) bool {
+	if len(accepted) == 0 {
+		return true
+	}
+	mediaType = canonicalMediaType(mediaType)
+	for _, value := range accepted {
+		if strings.EqualFold(mediaType, canonicalMediaType(value)) {
+			return true
+		}
+	}
+	return false
+}
+
+func canonicalMediaType(mediaType string) string {
+	trimmed := strings.TrimSpace(mediaType)
+	if trimmed == "" {
+		return ""
+	}
+	parsed, _, err := mime.ParseMediaType(trimmed)
+	if err != nil {
+		return strings.ToLower(trimmed)
+	}
+	return strings.ToLower(parsed)
+}
+
 func referencePath(binding ReferenceBinding, options ReferenceMaterializationOptions) (string, error) {
 	source := strings.TrimSpace(binding.Source)
 	if source == "" {