fix(search): 限制 FTS5 查询 token 数并统一去重

src/core/store/fts-query-budget.test.ts

@@ -0,0 +1,61 @@
+import { afterEach, describe, expect, it } from "vitest";
+
+import {
+  _resetJiebaForTest,
+  _setJiebaForTest,
+  buildFtsQuery,
+} from "./sqlite.js";
+
+describe("buildFtsQuery query budget", () => {
+  afterEach(() => {
+    _resetJiebaForTest();
+  });
+
+  it("deduplicates fallback tokens while preserving first-seen order", () => {
+    _setJiebaForTest(null);
+
+    expect(buildFtsQuery("alpha beta alpha beta gamma")).toBe(
+      '"alpha" OR "beta" OR "gamma"',
+    );
+  });
+
+  it("caps fallback output at 64 unique tokens", () => {
+    _setJiebaForTest(null);
+    const raw = Array.from({ length: 100 }, (_, index) => `term${index}`).join(" ");
+
+    const query = buildFtsQuery(raw);
+    const terms = query?.split(" OR ") ?? [];
+
+    expect(terms).toHaveLength(64);
+    expect(terms[0]).toBe('"term0"');
+    expect(terms[63]).toBe('"term63"');
+    expect(query).not.toContain('"term64"');
+  });
+
+  it("applies the same cap to tokenizer output", () => {
+    _setJiebaForTest({
+      cutForSearch: () => Array.from({ length: 100 }, (_, index) => `token${index}`),
+    });
+
+    const terms = buildFtsQuery("ignored")?.split(" OR ") ?? [];
+
+    expect(terms).toHaveLength(64);
+    expect(terms[0]).toBe('"token0"');
+    expect(terms[63]).toBe('"token63"');
+  });
+
+  it("deduplicates tokenizer output before spending the token budget", () => {
+    _setJiebaForTest({
+      cutForSearch: () => [
+        ...Array.from({ length: 100 }, () => "repeated"),
+        ...Array.from({ length: 70 }, (_, index) => `unique${index}`),
+      ],
+    });
+
+    const terms = buildFtsQuery("ignored")?.split(" OR ") ?? [];
+
+    expect(terms).toHaveLength(64);
+    expect(terms[0]).toBe('"repeated"');
+    expect(terms[63]).toBe('"unique62"');
+  });
+});

src/core/store/sqlite.ts

@@ -143,6 +143,9 @@ function requireNodeSqlite(): typeof import("node:sqlite") {
 // Lazy-loaded singleton: initialised on first call to `buildFtsQuery`.
 // If @node-rs/jieba is unavailable, falls back to Unicode-regex splitting.
 
+/** Bound generated MATCH term count for untrusted or oversized input. */
+const FTS_MAX_QUERY_TOKENS = 64;
+
 interface JiebaInstance {
   cutForSearch(text: string, hmm: boolean): string[];
 }
@@ -184,6 +187,9 @@ const ZH_STOP_WORDS = new Set([
  * Falls back to Unicode-regex splitting (`/[\p{L}\p{N}_]+/gu`) if
  * jieba is not installed.
  *
+ * Duplicate terms are removed in first-seen order and output is limited to
+ * 64 terms so oversized input cannot create an unbounded number of OR clauses.
+ *
  * Tokens are OR-joined as quoted FTS5 phrase terms so that a document
  * matching *any* token is returned.  BM25 naturally ranks documents that
  * match more tokens higher, so precision is preserved while recall is
@@ -225,7 +231,10 @@ export function buildFtsQuery(raw: string): string | null {
   }
 
   if (tokens.length === 0) return null;
-  const quoted = tokens.map((t) => `"${t.replaceAll('"', "")}"`);
+  // Apply one final first-seen dedupe so fallback and tokenizer behavior match.
+  const quoted = [...new Set(tokens)]
+    .slice(0, FTS_MAX_QUERY_TOKENS)
+    .map((t) => `"${t.replaceAll('"', "")}"`);
   return quoted.join(" OR ");
 }