style(formatting): standardize code formatting and logging statements

reme_ai/core/embedding/base_embedding_model.py

@@ -42,7 +42,7 @@ class BaseEmbeddingModel(ABC):
         """Truncate text to max_input_length if it exceeds the limit."""
         if len(text) > self.max_input_length:
             logger.warning(
-                f"Text length {len(text)} exceeds max_input_length {self.max_input_length}, truncating"
+                f"Text length {len(text)} exceeds max_input_length {self.max_input_length}, truncating",
             )
             return text[: self.max_input_length]
         return text
@@ -77,7 +77,7 @@ class BaseEmbeddingModel(ABC):
         """Async get embeddings with automatic batching and exponential backoff retries."""
         # Truncate all input texts first
         truncated_texts = self._truncate_texts(input_text)
-        
+
         # Split into batches and process sequentially to respect rate limits
         results = []
         for i in range(0, len(truncated_texts), self.max_batch_size):
@@ -118,7 +118,7 @@ class BaseEmbeddingModel(ABC):
         """Synchronous get embeddings with automatic batching and retry logic."""
         # Truncate all input texts first
         truncated_texts = self._truncate_texts(input_text)
-        
+
         results = []
         for i in range(0, len(truncated_texts), self.max_batch_size):
             batch = truncated_texts[i : i + self.max_batch_size]

reme_ai/mem_agent/base_memory_agent.py

@@ -102,7 +102,10 @@ class BaseMemoryAgent(BaseOp, metaclass=ABCMeta):
             **kwargs,
         )
         messages.append(assistant_message)
-        logger.info(f"[{self.__class__.__name__}] step{step + 1}.assistant={assistant_message.simple_dump(enable_json_dump=True)}")
+        logger.info(
+            f"[{self.__class__.__name__}] "
+            f"step{step + 1}.assistant={assistant_message.simple_dump(enable_json_dump=True)}",
+        )
         should_act = bool(assistant_message.tool_calls)
         return assistant_message, should_act
 
@@ -119,7 +122,10 @@ class BaseMemoryAgent(BaseOp, metaclass=ABCMeta):
                 logger.warning(f"[{self.__class__.__name__}] unknown tool_call.name={tool_call.name}")
                 continue
 
-            logger.info(f"[{self.__class__.__name__}] step{step + 1}.{j} submit tool_calls={tool_call.name} argument={tool_call.arguments}")
+            logger.info(
+                f"[{self.__class__.__name__}] step{step + 1}.{j} "
+                f"submit tool_calls={tool_call.name} argument={tool_call.arguments}",
+            )
             tool_copy: BaseMemoryTool = tool_dict[tool_call.name].copy()
             tool_copy.tool_call.id = tool_call.id
             tool_list.append(tool_copy)
@@ -162,10 +168,15 @@ class BaseMemoryAgent(BaseOp, metaclass=ABCMeta):
     async def execute(self):
         messages = await self.build_messages()
         for i, message in enumerate(messages):
-            logger.info(f"[{self.__class__.__name__}] step0.{i} {message.role} {message.name or ''} "
-                        f"{message.simple_dump(enable_json_dump=True)}")
+            logger.info(
+                f"[{self.__class__.__name__}] step0.{i} {message.role} {message.name or ''} "
+                f"{message.simple_dump(enable_json_dump=True)}",
+            )
         for i, tool in enumerate(self.tools):
-            logger.info(f"[{self.__class__.__name__}] step0.{i} tool_call={json.dumps(tool.tool_call.simple_input_dump(), ensure_ascii=False)}")
+            logger.info(
+                f"[{self.__class__.__name__}] step0.{i} "
+                f"tool_call={json.dumps(tool.tool_call.simple_input_dump(), ensure_ascii=False)}",
+            )
 
         self.messages, self.success = await self.react(messages)
         if self.success and self.messages:

reme_ai/mem_agent/summarizer/reme_summarizer.py

@@ -1,6 +1,5 @@
 """Orchestrator for complete memory summarization workflow across all memory types."""
 
-import re
 from typing import List
 
 from loguru import logger

reme_ai/mem_tool/base_memory_tool.py

@@ -104,5 +104,7 @@ class BaseMemoryTool(BaseOp, metaclass=ABCMeta):
             metadata=metadata or {},
         )
 
-        logger.opt(depth=1).info(f"[{self.__class__.__name__}] build node={node.model_dump_json(indent=2, exclude_none=True)}")
-        return node
+        logger.opt(depth=1).info(
+            f"[{self.__class__.__name__}] build node={node.model_dump_json(indent=2, exclude_none=True)}",
+        )
+        return node

reme_ai/mem_tool/vector/add_summary_memory.py

@@ -64,14 +64,14 @@ class AddSummaryMemory(AddMemory):
         }
 
     def _build_memory_node(
-            self,
-            memory_content: str,
-            memory_type: MemoryType | None = None,
-            memory_target: str = "",
-            ref_memory_id: str = "",
-            when_to_use: str = "",
-            author: str = "",
-            metadata: dict | None = None,
+        self,
+        memory_content: str,
+        memory_type: MemoryType | None = None,
+        memory_target: str = "",
+        ref_memory_id: str = "",
+        when_to_use: str = "",
+        author: str = "",
+        metadata: dict | None = None,
     ) -> MemoryNode:
         """Build MemoryNode from content, when_to_use, and metadata."""
         node = MemoryNode(