fix(qmd): keep models loaded until the daemon's own idle exit

QMD 2.8.3 createStore unloads the models after 5 idle minutes, which
made the next search reload them.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/tests/test-qmd-daemon.mjs

@@ -5,7 +5,7 @@ import { execFileSync } from 'node:child_process';
 import { mkdtempSync, rmSync, utimesSync, writeFileSync } from 'node:fs';
 import { tmpdir } from 'node:os';
 import { join, resolve } from 'node:path';
-import { createServer, gitFingerprint } from '../../shared/qmd/qmd-daemon.mjs';
+import { createServer, gitFingerprint, keepModelsLoaded } from '../../shared/qmd/qmd-daemon.mjs';
 import { collectionName } from '../../shared/qmd/qmd-lib.mjs';
 
 const defaultHits = () => [{ displayPath: `${collectionName('/r')}/src/a.ts`, body: 'x\nretry here', bestChunkPos: 2, bestChunk: 'retry here', score: 0.91 }];
@@ -168,3 +168,9 @@ test('refresh, stop, 404 and 403 on POST routes', async (t) => {
   assert.deepEqual(await (await s.call('/stop', {})).json(), { stopping: true });
   assert.equal(s.idle.length, 1);
 });
+
+test('keepModelsLoaded disables QMD unloading models after 5 idle minutes', () => {
+  const llm = { inactivityTimeoutMs: 5 * 60 * 1000, disposeModelsOnInactivity: true };
+  keepModelsLoaded({ internal: { llm } });
+  assert.deepEqual(llm, { inactivityTimeoutMs: 0, disposeModelsOnInactivity: false });
+});

shared/qmd/qmd-daemon.mjs

@@ -27,6 +27,14 @@ export function gitFingerprint(repo) {
   }
 }
 
+// QMD 2.8.3 createStore unloads models after 5 idle minutes (store.internal.llm); the daemon's own idle exit replaces that.
+export function keepModelsLoaded(store) {
+  const llm = store.internal?.llm;
+  if (!llm) return;
+  llm.inactivityTimeoutMs = 0;
+  llm.disposeModelsOnInactivity = false;
+}
+
 const REPO_COLLECTION = /^repo-[0-9a-f]{12}$/;
 
 function tokenMatches(given, expected) {
@@ -136,6 +144,7 @@ async function main() {
   }
   const { createStore, extractSnippet } = await importQmd();
   const store = await createStore({ dbPath: qmdDbPath(), configPath: qmdConfigPath() });
+  keepModelsLoaded(store);
   const collectionsFile = join(dir, 'collections.json');
   const token = randomBytes(32).toString('hex');
   let stopping = false;