llms/cloudflare: Implement Cloudflare Workers AI LLM

[rajaiswal]

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.

This PR implements Cloudflare Workers AI LLM as documented here. Functionality is at parity with Langhain's Cloudflare Workers AI implementation.

[tmc]

@rajaiswal looking forward to this! can you get this over the line and mark it ready for review?

[rajaiswal]

@tmc I just need to add tests. What's the general acceptable test pattern here? I see some llms are spinning up a mock server, and some are testing against the real API with test tokens. Not sure which one to follow

[tmc]

The short answer is that we haven't solidified and recommended an approach yet. Would love contributions to help shape that, but in the short term do what you feel is expedient and appropriate.

[rajaiswal]

@tmc PR is ready for review. Some unrelated files got touched when I ran linting and gofumpt, would you like me to revert those files back to their original state and isolate the linting only to my changes?

[tmc]

This is looking great! No worries with the unrelated format fixes. Just a few small comments here but generally this looks like it's nearly good to go in!

Can you ensure that all introduced exported symbols (except those in internal packages) are commented?

[rajaiswal]

@tmc this should be good to merge now

[tmc]

Thanks, LGTM