From 9b33766478dd05605904bfaae8b4c605e9113c00 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?L=C4=93sa=20AI?= <lesaai@icloud.com>
Date: Fri, 24 Apr 2026 13:01:40 -0700
Subject: [PATCH] fix(memory-core): stream seedEmbeddingCache via iterate to
 prevent V8 heap OOM

The embedding_cache table sync in MemoryManager.seedEmbeddingCache called
.all() on SELECT * FROM embedding_cache, materializing the full result set
into a JS array. embedding_cache rows contain serialized embedding text
(~20 KB each on text-embedding-3-small) and can grow into hundreds of
thousands of rows on long-running deployed databases. On a local 16 GB
main.sqlite (435,136 rows, 8.68 GB of embedding text), the .all() call
exceeds V8's ~4 GB default heap limit and aborts the gateway with:

  FATAL ERROR: Reached heap limit Allocation failed - JavaScript heap
  out of memory
  ... node::sqlite::StatementSync::All ...

Switching .all() -> .iterate() streams rows one at a time through the
same BEGIN/COMMIT upsert transaction. Peak V8 heap stays bounded by a
single row (~20 KB) plus the prepared statement, not the whole table.

Also drops the empty-check on the materialized array's .length; an
empty iterator commits a no-op transaction, which is cheap and
preserves the observable behavior for empty caches.

Scope note: this is the primary R2.A target (seedEmbeddingCache); a
follow-up patch will address the secondary listChunks / keyword fallback
.all() path in manager-search.ts.

Validation:
- pnpm tsgo:prod: green (core + extensions graphs)
- pnpm test extensions/memory-core: 512 passed, 3 skipped, 0 failed
---
 extensions/memory-core/src/memory/manager-sync-ops.ts | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/extensions/memory-core/src/memory/manager-sync-ops.ts b/extensions/memory-core/src/memory/manager-sync-ops.ts
index 5985fa3ef013..1b82f0c8f770 100644
--- a/extensions/memory-core/src/memory/manager-sync-ops.ts
+++ b/extensions/memory-core/src/memory/manager-sync-ops.ts
@@ -304,7 +304,7 @@ export abstract class MemoryManagerSyncOps {
         .prepare(
           `SELECT provider, model, provider_key, hash, embedding, dims, updated_at FROM ${EMBEDDING_CACHE_TABLE}`,
         )
-        .all() as Array<{
+        .iterate() as IterableIterator<{
         provider: string;
         model: string;
         provider_key: string;
@@ -313,9 +313,7 @@ export abstract class MemoryManagerSyncOps {
         dims: number | null;
         updated_at: number;
       }>;
-      if (!rows.length) {
-        return;
-      }
+      // Note: no early-return on empty iterator; BEGIN/COMMIT over an empty tx is cheap.
       const insert = this.db.prepare(
         `INSERT INTO ${EMBEDDING_CACHE_TABLE} (provider, model, provider_key, hash, embedding, dims, updated_at)
          VALUES (?, ?, ?, ?, ?, ?, ?)