Per module lm history

[chenmoneygithub]

Make it possible to do module.inspect_history, which gives the LM history of the module. In nesting case, the same LM history message will be available to all the ancestor callers.

Example code:

import dspy


class MyProgram(dspy.Module):
    def __init__(self):
        super().__init__()
        self.cot = dspy.ChainOfThought("question -> answer")

    def forward(self, question: str, **kwargs) -> str:
        return self.cot(question=question)


dspy.settings.configure(lm=dspy.LM("openai/gpt-4o-mini", cache=False), adapter=dspy.JSONAdapter())
program = MyProgram()
program(question="What is the capital of France?")

program.inspect_history()

It will give:

[2025-05-08T14:21:06.581570]

System message:

Your input fields are:
1. `question` (str)
Your output fields are:
1. `reasoning` (str)
2. `answer` (str)
All interactions will be structured in the following way, with the appropriate values filled in.

Inputs will have the following structure:

[[ ## question ## ]]
{question}

Outputs will be a JSON object with the following fields.

{
  "reasoning": "{reasoning}",
  "answer": "{answer}"
}
In adhering to this structure, your objective is: 
        Given the fields `question`, produce the fields `answer`.


User message:

[[ ## question ## ]]
What is the capital of France?

Respond with a JSON object in the following order of fields: `reasoning`, then `answer`.


Response:

{"reasoning":"The capital of France is a well-known fact, commonly taught in geography. Paris is recognized globally as the capital city, serving as the political, economic, and cultural center of the country.","answer":"Paris"}

You can also access the history by program.cot.inspect_history.