feat: multi-language embedding with CleanTemplateText + three-branch vector strategy

- StaticEmbedder: pre-trained ConceptNet Numberbatch/fastText word embeddings,
  auto-download with TF-IDF fallback, comma-separated multi-model paths
- CleanTemplateText: regex stripping of QQ tool call templates and noise
- textForVector: per-source vector strategy (agent→Response, user→Input,
  cold_storage→both)
- Indexer.BuildContext and ExtractKeywords now clean input before vectorization
- Protect recent 10 events in Prune (regression fix: use local var not const)

internal/memory/cut.go

@@ -93,6 +93,7 @@ var stopWords = map[string]bool{
 }
 
 func ExtractKeywords(text string) []string {
+	text = CleanTemplateText(text)
 	x := GetJieba()
 	if x == nil {
 		return nil