Dev 20260319 v2.0.10 (#1255)

## Description

Please include a summary of the change, the problem it solves, the
implementation approach, and relevant context. List any dependencies
required for this change.

Related Issue (Required):  Fixes @issue_number

## Type of change

Please delete options that are not relevant.

- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Refactor (does not change functionality, e.g. code style
improvements, linting)
- [ ] Documentation update

## How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. Please also list any relevant details
for your test configuration

- [ ] Unit Test
- [ ] Test Script Or Test Steps (please provide)
- [ ] Pipeline Automated API Test (please provide)

## Checklist

- [ ] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [ ] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have created related documentation issue/PR in
[MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) (if applicable) |
我已在 [MemOS-Docs](https://github.com/MemTensor/MemOS-Docs) 中创建了相关的文档
issue/PR（如果适用）
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR（如果适用）
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人

## Reviewer Checklist
- [ ] closes #xxxx (Replace xxxx with the GitHub issue number)
- [ ] Made sure Checks passed
- [ ] Tests have been provided

Author: CarltonXiang

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,7 +2,7 @@
 
 Please include a summary of the change, the problem it solves, the implementation approach, and relevant context. List any dependencies required for this change.
 
-Related Issue (Required):  Fixes @issue_number
+Related Issue (Required):  Fixes #issue_number
 
 ## Type of change
 

.github/workflows/python-tests.yml

@@ -102,7 +102,11 @@ jobs:
       if: ${{ !startsWith(matrix.os, 'macos-13') }}
       run: |
         poetry install --no-interaction --extras all
-    - name: PyTest unit tests
+    - name: PyTest unit tests with coverage
       if: ${{ !startsWith(matrix.os, 'macos-13') }}
+      shell: bash
       run: |
-        poetry run pytest tests -vv --durations=10
+        poetry run pytest tests -vv --durations=10 \
+          --cov=src/memos \
+          --cov-report=term-missing \
+          --cov-fail-under=28

.gitignore

@@ -63,6 +63,8 @@ pip-delete-this-directory.txt
 
 # Unit test / coverage reports
 htmlcov/
+report/
+cov-report/
 .tox/
 .nox/
 .coverage

Makefile

@@ -1,4 +1,4 @@
-.PHONY: test
+.PHONY: test test-report test-cov
 
 install:
 	poetry install --extras all --with dev --with test
@@ -9,10 +9,25 @@ clean:
 	rm -rf .pytest_cache
 	rm -rf .ruff_cache
 	rm -rf tmp
+	rm -rf report cov-report
+	rm -f .coverage .coverage.*
 
 test:
 	poetry run pytest tests
 
+test-report:
+	poetry run pytest tests -vv --durations=10 \
+		--html=report/index.html \
+		--cov=src/memos \
+		--cov-report=term-missing \
+		--cov-report=html:cov-report/src
+
+test-cov:
+	poetry run pytest tests \
+		--cov=src/memos \
+		--cov-report=term-missing \
+		--cov-report=html:cov-report/src
+
 format:
 	poetry run ruff check --fix
 	poetry run ruff format

poetry.lock

@@ -4,7 +4,7 @@
 ##############################################################################
 
 name = "MemoryOS"
-version = "2.0.9"
+version = "2.0.10"
 description = "Intelligence Begins with Memory"
 license = {text = "Apache-2.0"}
 readme = "README.md"
@@ -170,6 +170,8 @@ optional = true
 [tool.poetry.group.test.dependencies]
 pytest = "^8.3.5"
 pytest-asyncio = "^0.23.5"
+pytest-cov = "^6.1"
+pytest-html = "^4.2"
 ruff = "^0.11.8"
 
 [tool.poetry.group.eval]
@@ -208,6 +210,23 @@ filterwarnings = [
 ]
 
 
+[tool.coverage.run]
+source = ["src/memos"]
+branch = true
+
+[tool.coverage.report]
+show_missing = true
+skip_empty = true
+exclude_lines = [
+    "pragma: no cover",
+    "if TYPE_CHECKING:",
+    "if __name__ == .__main__.",
+]
+
+[tool.coverage.html]
+directory = "cov-report"
+
+
 [tool.ruff]
 ##############################################################################
 # Ruff is a fast Python linter and formatter.

pyproject.toml

@@ -1,4 +1,4 @@
-__version__ = "2.0.9"
+__version__ = "2.0.10"
 
 from memos.configs.mem_cube import GeneralMemCubeConfig
 from memos.configs.mem_os import MOSConfig

src/memos/__init__.py

@@ -321,23 +321,40 @@ def get_activation_config() -> dict[str, Any]:
 
     @staticmethod
     def get_memreader_config() -> dict[str, Any]:
-        """Get MemReader configuration for chat/doc extraction (fine-tuned 0.6B model)."""
-        return {
-            "backend": "openai",
-            "config": {
-                "model_name_or_path": os.getenv("MEMRADER_MODEL", "gpt-4o-mini"),
-                "temperature": 0.6,
-                "max_tokens": int(os.getenv("MEMRADER_MAX_TOKENS", "8000")),
-                "top_p": 0.95,
-                "top_k": 20,
-                "api_key": os.getenv("MEMRADER_API_KEY", "EMPTY"),
-                # Default to OpenAI base URL when env var is not provided to satisfy pydantic
-                # validation requirements during tests/import.
-                "api_base": os.getenv("MEMRADER_API_BASE", "https://api.openai.com/v1"),
-                "remove_think_prefix": True,
-            },
+        """Get MemReader configuration for chat/doc extraction (fine-tuned 0.6B model).
+
+        When MEMREADER_GENERAL_MODEL is configured (i.e. a separate stable LLM exists),
+        the backup client is automatically enabled so that primary failures (self-deployed
+        model) fall back to the general LLM.
+        """
+        config = {
+            "model_name_or_path": os.getenv("MEMRADER_MODEL", "gpt-4o-mini"),
+            "temperature": 0.6,
+            "max_tokens": int(os.getenv("MEMRADER_MAX_TOKENS", "8000")),
+            "top_p": 0.95,
+            "top_k": 20,
+            "api_key": os.getenv("MEMRADER_API_KEY", "EMPTY"),
+            # Default to OpenAI base URL when env var is not provided to satisfy pydantic
+            # validation requirements during tests/import.
+            "api_base": os.getenv("MEMRADER_API_BASE", "https://api.openai.com/v1"),
+            "remove_think_prefix": True,
         }
 
+        general_model = os.getenv("MEMREADER_GENERAL_MODEL")
+        enable_backup = os.getenv("MEMREADER_ENABLE_BACKUP", "false").lower() == "true"
+        if general_model and enable_backup:
+            config["backup_client"] = True
+            config["backup_model_name_or_path"] = general_model
+            config["backup_api_key"] = os.getenv(
+                "MEMREADER_GENERAL_API_KEY", os.getenv("OPENAI_API_KEY", "EMPTY")
+            )
+            config["backup_api_base"] = os.getenv(
+                "MEMREADER_GENERAL_API_BASE",
+                os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"),
+            )
+
+        return {"backend": "openai", "config": config}
+
     @staticmethod
     def get_memreader_general_llm_config() -> dict[str, Any]:
         """Get general LLM configuration for non-chat/doc tasks.
@@ -837,7 +854,7 @@ def get_scheduler_config() -> dict[str, Any]:
                 ),
                 "context_window_size": int(os.getenv("MOS_SCHEDULER_CONTEXT_WINDOW_SIZE", "5")),
                 "thread_pool_max_workers": int(
-                    os.getenv("MOS_SCHEDULER_THREAD_POOL_MAX_WORKERS", "10000")
+                    os.getenv("MOS_SCHEDULER_THREAD_POOL_MAX_WORKERS", "200")
                 ),
                 "consume_interval_seconds": float(
                     os.getenv("MOS_SCHEDULER_CONSUME_INTERVAL_SECONDS", "0.01")
@@ -850,6 +867,8 @@ def get_scheduler_config() -> dict[str, Any]:
                     "MOS_SCHEDULER_ENABLE_ACTIVATION_MEMORY", "false"
                 ).lower()
                 == "true",
+                "use_redis_queue": os.getenv("MEMSCHEDULER_USE_REDIS_QUEUE", "False").lower()
+                == "true",
             },
         }
 

src/memos/api/config.py

@@ -233,7 +233,7 @@ def init_server() -> dict[str, Any]:
     searcher: Searcher = tree_mem.get_searcher(
         manual_close_internet=os.getenv("ENABLE_INTERNET", "true").lower() == "false",
         moscube=False,
-        process_llm=mem_reader.llm,
+        process_llm=mem_reader.general_llm,
     )
     logger.debug("Searcher created")
 
@@ -255,12 +255,13 @@ def init_server() -> dict[str, Any]:
     # Initialize Scheduler
     scheduler_config_dict = APIConfig.get_scheduler_config()
     scheduler_config = SchedulerConfigFactory(
-        backend="optimized_scheduler", config=scheduler_config_dict
+        backend=scheduler_config_dict["backend"],
+        config=scheduler_config_dict["config"],
     )
     mem_scheduler: OptimizedScheduler = SchedulerFactory.from_config(scheduler_config)
     mem_scheduler.initialize_modules(
         chat_llm=llm,
-        process_llm=mem_reader.llm,
+        process_llm=mem_reader.general_llm,
         db_engine=BaseDBManager.create_default_sqlite_engine(),
         mem_reader=mem_reader,
         redis_client=redis_client,

src/memos/api/handlers/component_init.py

@@ -28,6 +28,22 @@ class OpenAILLMConfig(BaseLLMConfig):
         default="https://api.openai.com/v1", description="Base URL for OpenAI API"
     )
     extra_body: Any = Field(default=None, description="extra body")
+    backup_client: bool = Field(
+        default=False,
+        description="Whether to enable backup client for fallback on primary failure",
+    )
+    backup_api_key: str | None = Field(
+        default=None, description="API key for backup OpenAI-compatible endpoint"
+    )
+    backup_api_base: str | None = Field(
+        default=None, description="Base URL for backup OpenAI-compatible endpoint"
+    )
+    backup_model_name_or_path: str | None = Field(
+        default=None, description="Model name for backup endpoint"
+    )
+    backup_headers: dict[str, Any] | None = Field(
+        default=None, description="Default headers for backup client requests"
+    )
 
 
 class OpenAIResponsesLLMConfig(BaseLLMConfig):
@@ -42,22 +58,18 @@ class OpenAIResponsesLLMConfig(BaseLLMConfig):
     )
 
 
-class QwenLLMConfig(BaseLLMConfig):
-    api_key: str = Field(..., description="API key for DashScope (Qwen)")
+class QwenLLMConfig(OpenAILLMConfig):
     api_base: str = Field(
         default="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
         description="Base URL for Qwen OpenAI-compatible API",
     )
-    extra_body: Any = Field(default=None, description="extra body")
 
 
-class DeepSeekLLMConfig(BaseLLMConfig):
-    api_key: str = Field(..., description="API key for DeepSeek")
+class DeepSeekLLMConfig(OpenAILLMConfig):
     api_base: str = Field(
         default="https://api.deepseek.com",
         description="Base URL for DeepSeek OpenAI-compatible API",
     )
-    extra_body: Any = Field(default=None, description="Extra options for API")
 
 
 class AzureLLMConfig(BaseLLMConfig):