Serena

Instructions

Implementation Reference

• src/serena/tools/memory_tools.py:6-27 (handler)

  The WriteMemoryTool class provides the core handler logic for the 'write_memory' tool. Its 'apply' method validates input length and saves the content to a project-specific memory file using the agent's memories_manager.

  class WriteMemoryTool(Tool, ToolMarkerCanEdit):
      """
      Writes a named memory (for future reference) to Serena's project-specific memory store.
      """
  
      def apply(self, memory_file_name: str, content: str, max_answer_chars: int = -1) -> str:
          """
          Write some information (utf-8-encoded) about this project that can be useful for future tasks to a memory in md format.
          The memory name should be meaningful.
          """
          # NOTE: utf-8 encoding is configured in the MemoriesManager
          if max_answer_chars == -1:
              max_answer_chars = self.agent.serena_config.default_max_tool_answer_chars
          if len(content) > max_answer_chars:
              raise ValueError(
                  f"Content for {memory_file_name} is too long. Max length is {max_answer_chars} characters. "
                  + "Please make the content shorter."
              )
  
          return self.memories_manager.save_memory(memory_file_name, content)

• src/serena/tools/tools_base.py:356-367 (registration)

  ToolRegistry automatically discovers and registers all subclasses of Tool (including WriteMemoryTool) from the 'serena.tools' package, mapping them to tool names like 'write_memory'.

  class ToolRegistry:
      def __init__(self) -> None:
          self._tool_dict: dict[str, RegisteredTool] = {}
          for cls in iter_subclasses(Tool):
              if not any(cls.__module__.startswith(pkg) for pkg in tool_packages):
                  continue
              is_optional = issubclass(cls, ToolMarkerOptional)
              name = cls.get_name_from_cls()
              if name in self._tool_dict:
                  raise ValueError(f"Duplicate tool name found: {name}. Tool classes must have unique names.")
              self._tool_dict[name] = RegisteredTool(tool_class=cls, is_optional=is_optional, tool_name=name)

• src/serena/tools/tools_base.py:118-125 (helper)

  The get_name_from_cls method in the Tool base class derives the tool name 'write_memory' from the class name 'WriteMemoryTool' by removing 'Tool' suffix and converting to snake_case.

  @classmethod
  def get_name_from_cls(cls) -> str:
      name = cls.__name__
      if name.endswith("Tool"):
          name = name[:-4]
      # convert to snake_case
      name = "".join(["_" + c.lower() if c.isupper() else c for c in name]).lstrip("_")
      return name

• src/serena/tools/__init__.py:5-5 (registration)

  Import of memory_tools.py in tools/__init__.py ensures WriteMemoryTool is discoverable by ToolRegistry via module scanning.

  from .memory_tools import *

• src/serena/tools/memory_tools.py:11-25 (schema)

  The 'apply' method signature and docstring define the input schema (parameters: memory_file_name:str, content:str, max_answer_chars:int=-1) and output (str) for the write_memory tool, used for validation and MCP tool description.

  def apply(self, memory_file_name: str, content: str, max_answer_chars: int = -1) -> str:
      """
      Write some information (utf-8-encoded) about this project that can be useful for future tasks to a memory in md format.
      The memory name should be meaningful.
      """
      # NOTE: utf-8 encoding is configured in the MemoriesManager
      if max_answer_chars == -1:
          max_answer_chars = self.agent.serena_config.default_max_tool_answer_chars
      if len(content) > max_answer_chars:
          raise ValueError(
              f"Content for {memory_file_name} is too long. Max length is {max_answer_chars} characters. "
              + "Please make the content shorter."
          )
  
      return self.memories_manager.save_memory(memory_file_name, content)