MemoryOS 2.0.16__tar.gz → 2.0.17__tar.gz

{memoryos-2.0.16 → memoryos-2.0.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MemoryOS
-Version: 2.0.16
+Version: 2.0.17
 Summary: Intelligence Begins with Memory
 License: Apache-2.0
 License-File: LICENSE

{memoryos-2.0.16 → memoryos-2.0.17}/pyproject.toml

@@ -4,7 +4,7 @@
 ##############################################################################
 
 name = "MemoryOS"
-version = "2.0.16"
+version = "2.0.17"
 description = "Intelligence Begins with Memory"
 license = {text = "Apache-2.0"}
 readme = "README.md"
@@ -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`

{memoryos-2.0.16 → memoryos-2.0.17}/src/memos/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "2.0.16"
+__version__ = "2.0.17"
 
 from memos.configs.mem_cube import GeneralMemCubeConfig
 from memos.configs.mem_os import MOSConfig

{memoryos-2.0.16 → memoryos-2.0.17}/src/memos/api/handlers/chat_handler.py

@@ -60,6 +60,7 @@ class ChatHandler(BaseHandler):
         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 @@ class ChatHandler(BaseHandler):
         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 @@ class ChatHandler(BaseHandler):
             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 @@ class ChatHandler(BaseHandler):
 
                     # 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
                         )
 

{memoryos-2.0.16 → memoryos-2.0.17}/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,

{memoryos-2.0.16 → memoryos-2.0.17}/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(

{memoryos-2.0.16 → memoryos-2.0.17}/src/memos/api/handlers/search_handler.py

@@ -7,12 +7,15 @@ using dependency injection for better modularity and testability.
 
 import copy
 import math
+import os
 
+from contextlib import suppress
 from typing import Any
 
 from memos.api.handlers.base_handler import BaseHandler, HandlerDependencies
 from memos.api.handlers.formatters_handler import rerank_knowledge_mem
 from memos.api.product_models import APISearchRequest, SearchResponse
+from memos.dream.contextualization import CONTEXT_MEMORY_TYPE
 from memos.log import get_logger
 from memos.memories.textual.tree_text_memory.retrieve.retrieve_utils import (
     cosine_similarity_matrix,
@@ -20,11 +23,26 @@ from memos.memories.textual.tree_text_memory.retrieve.retrieve_utils import (
 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__)
 
+_ENV_CONTEXT_RECALL = "MEMOS_DREAM_CONTEXT_RECALL"
+_ENV_CONTEXT_RECALL_TOP_K = "MEMOS_DREAM_CONTEXT_RECALL_TOP_K"
+_DEFAULT_CONTEXT_RECALL_TOP_K = 2
+
+
+def _env_enabled(name: str, default: str = "off") -> bool:
+    return os.getenv(name, default).strip().lower() not in {"0", "false", "no", "off"}
+
+
+def _env_int(name: str, default: int) -> int:
+    with suppress(TypeError, ValueError):
+        return int(os.getenv(name, str(default)))
+    return default
+
 
 class SearchHandler(BaseHandler):
     """
@@ -71,6 +89,14 @@ class SearchHandler(BaseHandler):
         # 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}")
@@ -102,6 +128,105 @@ class SearchHandler(BaseHandler):
             data=results,
         )
 
+    def _merge_context_recall(
+        self, *, results: dict[str, Any], search_req: APISearchRequest
+    ) -> None:
+        if not _env_enabled(_ENV_CONTEXT_RECALL, "off"):
+            return
+
+        top_k = max(0, _env_int(_ENV_CONTEXT_RECALL_TOP_K, _DEFAULT_CONTEXT_RECALL_TOP_K))
+        if top_k <= 0:
+            return
+
+        context_buckets = self._recall_context_buckets(search_req=search_req, top_k=top_k)
+        if not context_buckets:
+            return
+
+        results.setdefault("text_mem", []).extend(context_buckets)
+
+    def _recall_context_buckets(
+        self, *, search_req: APISearchRequest, top_k: int
+    ) -> list[dict[str, Any]]:
+        graph_db = self.graph_db or getattr(self.searcher, "graph_store", None)
+        embedder = self.embedder or getattr(self.searcher, "embedder", None)
+        if graph_db is None or embedder is None:
+            self.logger.info(
+                "[SearchHandler] Context recall skipped: graph_db or embedder unavailable."
+            )
+            return []
+
+        try:
+            query_embedding = embedder.embed([search_req.query])[0]
+        except Exception:
+            self.logger.warning("[SearchHandler] Context recall embedding failed.", exc_info=True)
+            return []
+
+        buckets: list[dict[str, Any]] = []
+        for cube_id in self._resolve_cube_ids(search_req):
+            try:
+                hits = graph_db.search_by_embedding(
+                    query_embedding,
+                    top_k=top_k,
+                    scope=CONTEXT_MEMORY_TYPE,
+                    status="activated",
+                    user_name=cube_id,
+                    return_fields=[
+                        "memory",
+                        "key",
+                        "created_at",
+                        "updated_at",
+                        "source",
+                        "internal_info",
+                    ],
+                )
+            except Exception:
+                self.logger.warning(
+                    "[SearchHandler] Context recall search failed for cube=%s.",
+                    cube_id,
+                    exc_info=True,
+                )
+                continue
+
+            memories = [self._format_context_hit(hit) for hit in hits or [] if hit.get("memory")]
+            if not memories:
+                continue
+            buckets.append(
+                {
+                    "cube_id": cube_id,
+                    "memories": memories,
+                    "total_nodes": len(memories),
+                }
+            )
+        return buckets
+
+    @staticmethod
+    def _format_context_hit(hit: dict[str, Any]) -> dict[str, Any]:
+        context_id = str(hit.get("id", ""))
+        score = float(hit.get("score", 0.0) or 0.0)
+        metadata = {
+            "id": context_id,
+            "memory": hit.get("memory", ""),
+            "memory_type": CONTEXT_MEMORY_TYPE,
+            "source": hit.get("source") or "dream",
+            "key": hit.get("key", ""),
+            "relativity": score,
+            "score": score,
+            "embedding": [],
+            "sources": [],
+            "usage": [],
+            "ref_id": f"[{context_id.split('-')[0]}]" if context_id else "[context]",
+        }
+        for field in ("created_at", "updated_at", "internal_info"):
+            if hit.get(field) is not None:
+                metadata[field] = hit[field]
+
+        return {
+            "id": context_id,
+            "memory": hit.get("memory", ""),
+            "metadata": metadata,
+            "ref_id": metadata["ref_id"],
+        }
+
     @staticmethod
     def _apply_relativity_threshold(results: dict[str, Any], relativity: float) -> dict[str, Any]:
         if relativity <= 0:

{memoryos-2.0.16 → memoryos-2.0.17}/src/memos/api/routers/server_router.py

@@ -76,10 +76,11 @@ search_handler = SearchHandler(dependencies)
 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"