refactor(gql): reuse new options for LLM-based generator

[danstarns]

I noticed that you made your own Anthropic Adapter in the text to query the implementation:

• feat(gql): introduce LLM-based generator for queries #665

GQLPT alpha.32 takes your version and exports it - this should increase maintainability for you.

[changeset-bot]

⚠️ No Changeset found

Latest commit: 75336ca

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
admin.ensnode.io	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 12, 2025 10:16am
ensnode.io	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 12, 2025 10:16am
ensrainbow.io	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 12, 2025 10:16am

[vercel]

@danstarns is attempting to deploy a commit to the NameHash Team on Vercel.

A member of the Team first needs to authorize it.

[djstrong]

Thank you! I think you have dropped cache: ephemeral and this is crucial because it saves >95% tokens. With this enhancement we easily get into rate limits so maybe we will change the API supplier. Also this is the first version of ENSNode query generator and we need full control of the prompt to make it more specific.

[danstarns]

Thank you! I think you have dropped cache: ephemeral and this is crucial because it saves >95% tokens. With this enhancement we easily get into rate limits so maybe we will change the API supplier. Also this is the first version of ENSNode query generator and we need full control of the prompt to make it more specific.

Good point about the cache, thanks for the extra pair of eyes.

I added the cache support in GQLPT alpha.33.

In the name of rebase gods, I reopened this PR with less noise #709