PromptSmith

Instructions

Implementation Reference

• src/promptcore/main.py:140-162 (handler)

  The implementation of the log_execution_feedback tool, which uses the @mcp.tool() decorator for registration and updates feedback in the storage.

  @mcp.tool()
  def log_execution_feedback(
      task_id: Annotated[str, "The task ID from generate_meta_prompt"],
      feedback: Annotated[str, "Feedback about how well the prompt worked"],
  ) -> dict:
      """
      Log feedback about how a generated prompt performed.
      
      Used to track effectiveness and improve framework selection over time.
      """
      deps = get_dependencies()
      updated = deps.storage.update_feedback(task_id, feedback)
      
      if not updated:
          return {
              "success": False,
              "error": f"Task ID not found: {task_id}",
          }
      
      return {
          "success": True,
          "message": f"Feedback logged for task {task_id}",
      }