feat: View agent's static context

[joshua-mo-143]

• I have looked for existing issues (including closed) about this

Feature Request

ref Discord conversation https://discord.com/channels/896944341598208070/1330217496988352656

Users should be able to see what exactly gets sent to the API (as the prompt).

Motivation

Better observability for LLM calls

Proposal

I propose that we could add a new method to the AgentBuilder (or Agent struct) to be able to see what the underlying prompt is.

Alternatives

Not really sure what the alternative is here

[joshua-mo-143]

Closing because there's probably a better way to do this as previously discussed in eng sync.