fix: Disable thinking for qwen3 preference extractor

apps/memos-local-plugin/adapters/hermes/memos_provider/__init__.py

@@ -66,7 +66,13 @@
     sys.path.insert(0, str(_PLUGIN_DIR))
 
 from bridge_client import BridgeError, MemosBridgeClient, MemosHttpClient  # noqa: E402
-from daemon_manager import ensure_bridge_running, ensure_viewer_daemon, probe_viewer_status, kill_zombie_bridges, startup_lock_active  # noqa: E402
+from daemon_manager import (  # noqa: E402
+    ensure_bridge_running,
+    ensure_viewer_daemon,
+    kill_zombie_bridges,
+    probe_viewer_status,
+    startup_lock_active,
+)
 
 
 try:  # pragma: no cover — host-provided base class, absent in unit tests
@@ -428,13 +434,12 @@ def initialize(self, session_id: str, **kwargs: Any) -> None:  # type: ignore[ov
             if startup_lock_active():
                 time.sleep(1.0)
                 viewer_status = probe_viewer_status()
-            if viewer_status == "running_memos":
-                if self._connect_http_bridge(session_id):
-                    logger.info(
-                        "MemOS: bridge ready (HTTP, late probe) session=%s platform=%s (episode deferred)",
-                        self._session_id,
-                        self._platform,
-                    )
+            if viewer_status == "running_memos" and self._connect_http_bridge(session_id):
+                logger.info(
+                    "MemOS: bridge ready (HTTP, late probe) session=%s platform=%s (episode deferred)",
+                    self._session_id,
+                    self._platform,
+                )
 
         if self._bridge is None:
             try:
@@ -1955,10 +1960,11 @@ def _reconnect_bridge(self, session_id: str = "", *, timeout: float = 30.0) -> N
             ensure_bridge_running()
             # Try HTTP first if daemon is running
             viewer_status = probe_viewer_status()
-            if viewer_status == "running_memos":
-                if self._connect_http_bridge(session_id, timeout=timeout):
-                    logger.info("MemOS: reconnected via HTTP")
-                    return
+            if viewer_status == "running_memos" and self._connect_http_bridge(
+                session_id, timeout=timeout
+            ):
+                logger.info("MemOS: reconnected via HTTP")
+                return
 
             try:
                 ensure_viewer_daemon()

src/memos/api/config.py

@@ -260,6 +260,28 @@ def _auth_headers():
 class APIConfig:
     """Centralized configuration management for MemOS APIs."""
 
+    @staticmethod
+    def _preference_extractor_extra_body(model_name: str) -> dict[str, Any] | None:
+        normalized_model = model_name.strip().lower()
+        if normalized_model.startswith(("qwen3.5", "qwen3.6")):
+            return {"enable_thinking": False}
+        return None
+
+    @staticmethod
+    def get_profile_memory_reserved_top_k() -> int:
+        """Get profile-memory MMR reserve count.
+
+        This is intentionally read from environment/config at runtime so Nacos
+        property updates can take effect without changing request payloads.
+        """
+        raw = os.getenv("PROFILE_MEMORY_RESERVED_TOP_K", "0")
+        try:
+            value = int(raw)
+        except (TypeError, ValueError):
+            logger.warning("Invalid PROFILE_MEMORY_RESERVED_TOP_K=%r, using 0.", raw)
+            return 0
+        return max(0, value)
+
     @staticmethod
     def get_openai_config() -> dict[str, Any]:
         """Get OpenAI configuration."""
@@ -469,23 +491,27 @@ def get_preference_extractor_llm_config() -> dict[str, Any]:
         """
         pref_model = os.getenv("PREFERENCE_EXTRACTOR_MODEL")
         if pref_model:
+            extra_body = APIConfig._preference_extractor_extra_body(pref_model)
+            config = {
+                "model_name_or_path": pref_model,
+                "temperature": 0.6,
+                "max_tokens": int(os.getenv("PREFERENCE_EXTRACTOR_MAX_TOKENS", "8000")),
+                "top_p": 0.95,
+                "top_k": 20,
+                "api_key": os.getenv(
+                    "PREFERENCE_EXTRACTOR_API_KEY", os.getenv("OPENAI_API_KEY", "EMPTY")
+                ),
+                "api_base": os.getenv(
+                    "PREFERENCE_EXTRACTOR_API_BASE",
+                    os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"),
+                ),
+                "remove_think_prefix": True,
+            }
+            if extra_body is not None:
+                config["extra_body"] = extra_body
             return {
                 "backend": os.getenv("PREFERENCE_EXTRACTOR_BACKEND", "openai"),
-                "config": {
-                    "model_name_or_path": pref_model,
-                    "temperature": 0.6,
-                    "max_tokens": int(os.getenv("PREFERENCE_EXTRACTOR_MAX_TOKENS", "8000")),
-                    "top_p": 0.95,
-                    "top_k": 20,
-                    "api_key": os.getenv(
-                        "PREFERENCE_EXTRACTOR_API_KEY", os.getenv("OPENAI_API_KEY", "EMPTY")
-                    ),
-                    "api_base": os.getenv(
-                        "PREFERENCE_EXTRACTOR_API_BASE",
-                        os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"),
-                    ),
-                    "remove_think_prefix": True,
-                },
+                "config": config,
             }
         # Fallback to general_llm config (which itself falls back to OpenAI)
         return APIConfig.get_memreader_general_llm_config()

tests/mem_reader/test_preference_extractor_llm_config.py

@@ -12,6 +12,7 @@
     TextualMemoryItem,
     TreeNodeTextualMemoryMetadata,
 )
+from memos.types.general_types import MemoryView
 
 
 def test_product_default_config_wires_preference_extractor_model(monkeypatch):
@@ -28,6 +29,26 @@ def test_product_default_config_wires_preference_extractor_model(monkeypatch):
     assert pref_config["config"]["api_key"] == "pref-key"
 
 
+def test_preference_extractor_qwen35_disables_thinking(monkeypatch):
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_MODEL", "qwen3.5-flash")
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_API_BASE", "https://dashscope.example/v1")
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_API_KEY", "pref-key")
+
+    pref_config = APIConfig.get_preference_extractor_llm_config()
+
+    assert pref_config["config"]["extra_body"] == {"enable_thinking": False}
+
+
+def test_preference_extractor_qwen36_disables_thinking(monkeypatch):
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_MODEL", "qwen3.6-flash")
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_API_BASE", "https://dashscope.example/v1")
+    monkeypatch.setenv("PREFERENCE_EXTRACTOR_API_KEY", "pref-key")
+
+    pref_config = APIConfig.get_preference_extractor_llm_config()
+
+    assert pref_config["config"]["extra_body"] == {"enable_thinking": False}
+
+
 def test_product_default_config_leaves_preference_extractor_unset_without_model(monkeypatch):
     monkeypatch.delenv("PREFERENCE_EXTRACTOR_MODEL", raising=False)
     monkeypatch.delenv("PREFERENCE_EXTRACTOR_API_BASE", raising=False)
@@ -129,6 +150,8 @@ def test_multimodal_transfer_uses_preference_extractor_llm():
             "memos.mem_reader.multi_modal_struct.process_preference_fine", return_value=[]
         ) as mock_process_pref,
     ):
-        reader._process_transfer_multi_modal_data([raw_node])
+        reader._process_transfer_multi_modal_data(
+            [raw_node], allow_memory_view=[MemoryView.PREFERENCE]
+        )
 
     assert mock_process_pref.call_args.args[2] is reader.preference_extractor_llm