ver 1.2

echo-memory.plugin.src/skills/echo-memory/scripts/sweep.py

@@ -99,6 +99,12 @@ def main(argv: list[str] | None = None) -> int:
                  if p.endswith(".md") and p.rsplit("/", 1)[-1] not in SKIP_BASENAMES
                  and not TEMPLATE_RE.search(p)]
 
+    # Fetch every note's content ONCE, concurrently. All three passes below (index,
+    # recall, link symmetrize) read from this shared cache, so no file is fetched
+    # twice and link targets aren't re-fetched per reference.
+    texts = echo.read_many(all_files)
+    print(f"sweep: read {len(texts)} notes (concurrent, keep-alive)\n")
+
     # ---- 2. (re)build entity index -------------------------------------------
     index = idx_mod.load()
     existing = dict(index.get("entities", {}))
@@ -110,10 +116,13 @@ def main(argv: list[str] | None = None) -> int:
             continue
         base = path.rsplit("/", 1)[-1][:-3]
         slug = idx_mod.slugify(base)
-        text = get(path) or ""
+        text = texts.get(path) or ""
         title = links.first_h1(text) or base
         prev = existing.get(slug)
-        aliases = prev.get("aliases", []) if prev else []
+        # Frontmatter aliases are authoritative and re-folded every rebuild; prior index
+        # aliases (e.g. mentions learned by capture) are preserved; upsert adds title variants.
+        prev_aliases = prev.get("aliases", []) if prev else []
+        aliases = list(prev_aliases) + idx_mod.aliases_in_frontmatter(text)
         idx_mod.upsert(rebuilt, slug, path, kind, title, aliases)
         if not prev:
             added += 1
@@ -126,7 +135,7 @@ def main(argv: list[str] | None = None) -> int:
 
     # ---- 2b. (re)build the recall (BM25) index -------------------------------
     if apply:
-        rix = echo_recall.rebuild()
+        rix = echo_recall.rebuild(prefetched=texts)
         print(f"sweep: {tag} recall index — {rix.n_docs} docs (BM25)")
     else:
         n_idx = sum(1 for p in all_files if echo_recall._indexable(p))
@@ -147,14 +156,14 @@ def main(argv: list[str] | None = None) -> int:
 
     missing = set()  # (target_path, source_path) — reciprocal link to add on target
     for path in all_files:
-        text = get(path)
+        text = texts.get(path)
         if text is None:
             continue
         for tgt in links.related_targets(text):
             tp = resolve_target(tgt)
             if not tp or tp == path:
                 continue
-            back = {resolve_target(t) for t in links.related_targets(get(tp) or "")}
+            back = {resolve_target(t) for t in links.related_targets(texts.get(tp) or "")}
             if path not in back:
                 missing.add((tp, path))
     missing = sorted(missing)