Add function calling token counting

[niieani]

fixes #21

Summary

• add a function-calling aware token counting API to GptEncoding
• introduce shared fixtures and a regression test suite that covers OpenAI function request shapes
• expose encodeChatCompletionTokens only on function-calling model entrypoints via the code generator
• extract the function calling token counting helpers and fixtures into dedicated modules with named token constants

Testing

• yarn test:code --run

---

Codex Task

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[github-actions]

🎉 This PR is included in version 3.4.0 🎉

The release is available on:

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

Your semantic-release bot 📦🚀