merge v2.0.17 into main

pyproject.toml

@@ -62,6 +62,9 @@ issues = "https://github.com/MemTensor/MemOS/issues"
 [project.scripts]
 memos = "memos.cli:main"
 
+[project.entry-points."memos.plugins"]
+dream = "memos.dream:CommunityDreamPlugin"
+
 [project.optional-dependencies]
 # These are optional dependencies for various features of MemoryOS.
 # Developers install: `poetry install --extras <feature>`. e.g., `poetry install --extras general-mem`

src/memos/api/handlers/chat_handler.py

@@ -60,6 +60,7 @@ def __init__(
         self,
         dependencies: HandlerDependencies,
         chat_llms: dict[str, Any],
+        playground_chat_llms: dict[str, Any] | None = None,
         search_handler=None,
         add_handler=None,
         online_bot=None,
@@ -70,6 +71,7 @@ def __init__(
         Args:
             dependencies: HandlerDependencies instance
             chat_llms: Dictionary mapping model names to LLM instances
+            playground_chat_llms: Optional model map for /chat/stream/playground
             search_handler: Optional SearchHandler instance (created if not provided)
             add_handler: Optional AddHandler instance (created if not provided)
             online_bot: Optional DingDing bot function for notifications
@@ -89,6 +91,7 @@ def __init__(
             add_handler = AddHandler(dependencies)
 
         self.chat_llms = chat_llms
+        self.playground_chat_llms = playground_chat_llms or chat_llms
         self.search_handler = search_handler
         self.add_handler = add_handler
         self.online_bot = online_bot
@@ -630,10 +633,11 @@ def generate_chat_response() -> Generator[str, None, None]:
 
                     # Step 3: Generate streaming response from LLM
                     try:
-                        model = next(iter(self.chat_llms.keys()))
+                        chat_llms = self.playground_chat_llms
+                        model = next(iter(chat_llms.keys()))
                         self.logger.info(f"[PLAYGROUND CHAT] Chat Playground Stream Model: {model}")
                         start = time.time()
-                        response_stream = self.chat_llms[model].generate_stream(
+                        response_stream = chat_llms[model].generate_stream(
                             current_messages, model_name_or_path=model
                         )
 

src/memos/api/handlers/component_init.py

@@ -157,6 +157,7 @@ def init_server() -> dict[str, Any]:
     graph_db_config = build_graph_db_config()
     llm_config = build_llm_config()
     chat_llm_config = build_chat_llm_config()
+    playground_chat_llm_config = build_chat_llm_config("PLAYGROUND_CHAT_MODEL_LIST")
     embedder_config = build_embedder_config()
     nli_client_config = build_nli_client_config()
     mem_reader_config = build_mem_reader_config()
@@ -174,6 +175,11 @@ def init_server() -> dict[str, Any]:
         if os.getenv("ENABLE_CHAT_API", "false") == "true"
         else None
     )
+    playground_chat_llms = (
+        _init_chat_llms(playground_chat_llm_config)
+        if os.getenv("ENABLE_CHAT_API", "false") == "true" and playground_chat_llm_config
+        else chat_llms
+    )
     embedder = EmbedderFactory.from_config(embedder_config)
 
     plugin_context = build_plugin_context(
@@ -317,6 +323,7 @@ def init_server() -> dict[str, Any]:
         "mem_reader": mem_reader,
         "llm": llm,
         "chat_llms": chat_llms,
+        "playground_chat_llms": playground_chat_llms,
         "embedder": embedder,
         "reranker": reranker,
         "internet_retriever": internet_retriever,

src/memos/api/handlers/config_builders.py

@@ -85,14 +85,17 @@ def build_llm_config() -> dict[str, Any]:
     )
 
 
-def build_chat_llm_config() -> list[dict[str, Any]]:
+def build_chat_llm_config(env_name: str = "CHAT_MODEL_LIST") -> list[dict[str, Any]]:
     """
     Build chat LLM configuration.
 
     Returns:
         Validated chat LLM configuration dictionary
+    Args:
+        env_name: Environment variable that contains the JSON chat model list.
+
     """
-    configs = json.loads(os.getenv("CHAT_MODEL_LIST", "[]"))
+    configs = json.loads(os.getenv(env_name, "[]"))
     return [
         {
             "config_class": LLMConfigFactory.model_validate(

src/memos/api/handlers/search_handler.py

@@ -20,7 +20,8 @@
 from memos.multi_mem_cube.composite_cube import CompositeCubeView
 from memos.multi_mem_cube.single_cube import SingleCubeView
 from memos.multi_mem_cube.views import MemCubeView
-from memos.plugins.hooks import hookable
+from memos.plugins.hook_defs import H
+from memos.plugins.hooks import hookable, trigger_hook
 
 
 logger = get_logger(__name__)
@@ -71,6 +72,14 @@ def handle_search_memories(self, search_req: APISearchRequest) -> SearchResponse
         # Search and deduplicate
         cube_view = self._build_cube_view(search_req_local)
         results = cube_view.search_memories(search_req_local)
+        hooked_results = trigger_hook(
+            H.SEARCH_MEMORY_RESULTS,
+            handler=self,
+            search_req=search_req_local,
+            results=results,
+        )
+        if hooked_results is not None:
+            results = hooked_results
         if not search_req_local.relativity:
             search_req_local.relativity = 0
         self.logger.info(f"[SearchHandler] Relativity filter: {search_req_local.relativity}")

src/memos/api/routers/server_router.py

@@ -76,10 +76,11 @@
 add_handler = AddHandler(dependencies)
 chat_handler = (
     ChatHandler(
-        dependencies,
-        components["chat_llms"],
-        search_handler,
-        add_handler,
+        dependencies=dependencies,
+        chat_llms=components["chat_llms"],
+        playground_chat_llms=components.get("playground_chat_llms"),
+        search_handler=search_handler,
+        add_handler=add_handler,
         online_bot=components.get("online_bot"),
     )
     if os.getenv("ENABLE_CHAT_API", "false") == "true"