Add ai agent v2

[ElyasRashno]

ai agent proposal #1256

[bact]

This is potentially be shared by non-AI use cases.
So we can consider to bring this up to Core namespace.

[bact]

For AgentTrustLevel, we can try to map it to some standard definitions.

• selfDeclared looks like related to ISO/IEC 17050 Conformity assessment — Supplier's declaration of conformity
• thirdPartyReviewed - ISO/IEC 17020 Conformity assessment — Requirements for bodies performing inspection / ISO/IEC 17021 Conformity assessment — Requirements for bodies providing audit and certification of management systems
• certified - ISO/IEC 17065 Conformity assessment — Requirements for bodies certifying products, processes and services

It is also potentially be useful for non-AI use cases as well.
So probably consider bring it up to /Core/TrustLevel and make the description more generic. We can discuss this in next call.

[stevenc-stb]

LGTM

[bact]

Btw, on the name, should we go AIAgent or AiAgent ?

Other classes like SpdxDocument, EpssVulnAssessmentRelationship, go by first letter of the word goes uppercase, the rest goes lowercase.

There's an exception from that pattern though, which is AIPackage.

[bact]

LGTM.

Note that we should revisit this again when #1280 and #1249 landed.

The agent, the prompt, and the interaction template should work together in the consistent way.

[bact]

We can have non-AI use cases for this trust level.
Maybe worth to move it to Core, as /Core/trustLevel.