Improve AI output

[anth-volk]

Fixes #2131
Fixes #2126
Fixes #2125
Required for PolicyEngine/policyengine-app#2325
Required for PolicyEngine/policyengine-app#2321

In an effort to make our AI output endpoints more sustainable, resilient, and modular, this PR does the following:

• Moves away from using f-string manipulation and toward using Python string.replace to provide clearer behavior
• Creates a new endpoint to be used for fetching AI prompts, de-linking the prompting and generation processes
• Refactors both society-wide and household analysis to return JSON outputs in cases where users are re-accessing previously generated AI outputs
• Creates an AIPromptBase class to be used for more systematized prompt generation and improved user interface
• Creates a superclass on top of this for the society-wide analysis prompt

The changes here are required to enable a front-end PR implementing fixes for PolicyEngine/policyengine-app#2325 and PolicyEngine/policyengine-app#2321.

This code does not yet add tests, hence opening in draft form. I'd like these tests to mirror the structure proposed in #2114, and thus will implement that folder and test structure for these tests, and then refactor based upon future movement on that PR.