fix(retrieval): version the daemon by code hash

Derive the daemon address and start lock from a hash of server.py, so an
updated server never reuses a daemon still running older code.

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

scripts/lib/semantic-retrieval.py

@@ -97,7 +97,7 @@ def check_runtime(target, state):
         if path.name == 'data' and (not path.is_dir() or any(
                 child.is_symlink() or not (
                     child.is_file() and (child.name in ('daemon.key', 'daemon.starting') or re.fullmatch(
-                        r'[0-9a-f]{64}\.sqlite3(?:-(?:wal|shm|journal))?', child.name))
+                        r'[0-9a-f]{64}\.sqlite3(?:-(?:wal|shm|journal))?|daemon-[0-9a-f]{12}\.starting', child.name))
                     or child.is_socket() and re.fullmatch(r'daemon-[0-9a-f]{16}\.sock', child.name))
                 for child in path.iterdir())):
             raise ValueError('Foreign or linked semantic retrieval path: data')

scripts/tests/test-retrieval-server.py

@@ -124,6 +124,15 @@ class RetrievalServerTests(unittest.TestCase):
         self.assertEqual(stopped.exception.code, 3)
         self.assertEqual(calls[0][2:], ['search', '--query', 'two words'])
 
+    def test_daemon_identity_changes_with_code_version(self):
+        with TemporaryDirectory() as temporary:
+            data_dir = Path(temporary)
+            with patch.object(MODULE, 'code_version', return_value='aaaaaaaaaaaa'):
+                old_address, old_lock = MODULE.daemon_address(data_dir), MODULE.daemon_lock_path(data_dir)
+            with patch.object(MODULE, 'code_version', return_value='bbbbbbbbbbbb'):
+                self.assertNotEqual(MODULE.daemon_address(data_dir), old_address)
+                self.assertNotEqual(MODULE.daemon_lock_path(data_dir), old_lock)
+
     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

@@ -226,12 +226,18 @@ def reciprocal_rank_fusion(*rankings):
     return sorted(scores, key=lambda identifier: (-scores[identifier], identifier))
 
 
+def code_version() -> str:
+    """Hash of this file, so a daemon started by older code is never reused after an update."""
+    return hashlib.sha256(Path(__file__).read_bytes()).hexdigest()[:12]
+
+
 def daemon_lock_path(data_dir: Path) -> Path:
-    return data_dir / "daemon.starting"
+    return data_dir / f"daemon-{code_version()}.starting"
 
 
 def daemon_address(data_dir: Path) -> str:
-    digest = hashlib.sha256(os.path.normcase(str(data_dir.resolve())).encode()).hexdigest()[:16]
+    identity = os.path.normcase(str(data_dir.resolve())) + "|" + code_version()
+    digest = hashlib.sha256(identity.encode()).hexdigest()[:16]
     if os.name == "nt":
         return r"\\.\pipe\ai-config-retrieval-" + digest
     return str(data_dir / f"daemon-{digest}.sock")