diff --git a/packages/memory-host-sdk/src/host/internal.ts b/packages/memory-host-sdk/src/host/internal.ts
index 89fd0030a94..004d91d23e2 100644
--- a/packages/memory-host-sdk/src/host/internal.ts
+++ b/packages/memory-host-sdk/src/host/internal.ts
@@ -398,8 +398,13 @@ export function chunkMarkdown(
     if (line.length === 0) {
       segments.push("");
     } else {
-      for (let start = 0; start < line.length; start += maxChars) {
-        segments.push(line.slice(start, start + maxChars));
+      // Use token count (not maxChars) as the split step so that CJK lines
+      // – where 1 char ≈ 1 token – are sliced into budget-sized segments.
+      // For Latin text the token count is ≥ maxChars/4, which still produces
+      // segments well within the char budget after weighting.
+      const splitStep = Math.max(1, chunking.tokens);
+      for (let start = 0; start < line.length; start += splitStep) {
+        segments.push(line.slice(start, start + splitStep));
       }
     }
     for (const segment of segments) {
diff --git a/src/utils/cjk-chars.test.ts b/src/utils/cjk-chars.test.ts
index 0e8327d0a7d..50fe188dd1c 100644
--- a/src/utils/cjk-chars.test.ts
+++ b/src/utils/cjk-chars.test.ts
@@ -81,7 +81,6 @@ describe("estimateStringChars", () => {
     // "你" counts as 4, emoji remains 2 => total 6
     expect(estimateStringChars("你😀")).toBe(6);
   });
-
   it("yields ~1 token per CJK char when divided by CHARS_PER_TOKEN_ESTIMATE", () => {
     // 10 CJK chars should estimate as ~10 tokens
     const cjk = "这是一个测试用的句子呢";