feat: add static functions on the adapters to check for compatible model names

[jemc]

Both KurtOpenAI and KurtVertexAI support multiple different models, selectable by name. This change adds an isSupportedModel function to both, so that users of the libraries can easily check if a given string matches a supported model name.

This function also acts as a type guard that can be used from TypeScript to convert a string conditionally into a strongly typed type union of model ames.

Also, the exports for these packages have been expanded to include additional types like the aforementioned type union of model names.

These new features make it easier to build applications that have some functions dealing with model name strings in deciding which Kurt adapter to create, helping with Kurt's central mission to make it easy to build applications which switch between different LLMs.

[github-actions[bot]]

:tada: This PR is included in version @formula-monks/kurt-open-ai-v1.1.0 :tada:

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot :package::rocket:

[github-actions[bot]]

:tada: This PR is included in version @formula-monks/kurt-vertex-ai-v1.1.0 :tada:

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot :package::rocket: