PromptSmith

Instructions

Implementation Reference

• src/promptcore/main.py:62-85 (handler)

  Implementation of the recommend_strategy MCP tool in src/promptcore/main.py. It takes a task and context, uses the selector dependency to analyze them, and returns a dictionary with the recommended framework, complexity, and other analysis details.

  @mcp.tool()
  def recommend_strategy(
      task: Annotated[str, "The task or question to analyze"],
      context: Annotated[str, "Additional context about the task"] = "",
  ) -> dict:
      """
      Analyze a task and recommend the optimal reasoning framework.
      
      Returns the detected category, complexity_score, recommended framework,
      and alternative options.
      """
      deps = get_dependencies()
      analysis = deps.selector.analyze(task, context)
      
      return {
          "category": analysis.category.value,
          "complexity": {
              "score": analysis.complexity_score,
              "level": analysis.complexity_level.value,
          },
          "recommended_framework": analysis.recommended_framework,
          "reasoning": analysis.reasoning,
          "alternatives": analysis.alternative_frameworks,
      }