fix(retrieval): keep multi-word arguments on Windows

os.execv does not quote arguments on Windows, so the hand-off to the virtual
environment split every multi-word --query and search always failed. Run the
runtime with subprocess on Windows instead.

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

scripts/tests/test-retrieval-server.py

@@ -117,6 +117,13 @@ class RetrievalServerTests(unittest.TestCase):
 
             self.assertEqual(MODULE.runtime_python(script, 'C:/Python/python.exe', 'nt'), runtime.resolve())
 
+    def test_windows_runtime_handoff_keeps_multi_word_arguments(self):
+        calls = []
+        with patch.object(MODULE, 'runtime_python', return_value=Path('C:/runtime/python.exe')),                 patch.object(MODULE.sys, 'argv', ['server.py', 'search', '--query', 'two words']),                 patch.object(MODULE.subprocess, 'run', side_effect=lambda command: calls.append(command) or SimpleNamespace(returncode=3)),                 self.assertRaises(SystemExit) as stopped:
+            MODULE.use_runtime_python('nt')
+        self.assertEqual(stopped.exception.code, 3)
+        self.assertEqual(calls[0][2:], ['search', '--query', 'two words'])
+
     def test_preferred_device_uses_cuda_with_cpu_fallback(self):
         with patch.dict('sys.modules', torch=SimpleNamespace(cuda=SimpleNamespace(is_available=lambda: True))):
             self.assertEqual(MODULE.preferred_device(), 'cuda')

shared/retrieval/server.py

@@ -56,10 +56,14 @@ def runtime_python(script=__file__, executable=sys.executable, system=os.name):
     return None
 
 
-def use_runtime_python():
+def use_runtime_python(system=os.name):
     runtime = runtime_python()
     if runtime is not None:
-        os.execv(str(runtime), [str(runtime), str(Path(__file__).resolve()), *sys.argv[1:]])
+        command = [str(runtime), str(Path(__file__).resolve()), *sys.argv[1:]]
+        if system == 'nt':
+            # os.execv does not quote arguments on Windows, so a multi-word --query would be split.
+            sys.exit(subprocess.run(command).returncode)
+        os.execv(command[0], command)
 
 
 def sections(text: str, path: str):