Allow users to set request option headers for Anthropic's LLMs

[FallDownTheSystem]

Description

Allow users to set request option headers for Anthropic's LLMs and add special handling for anthropic-beta headers

Checklist

• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created

Screenshots

No visual changes

Testing instructions

Add

"requestOptions": {
  "headers": {
    "anthropic-beta": "output-128k-2025-02-19"
  }
}

for the claude-3-7-sonnet-20250219 model, enable extended thinking, and ask it to think for as long as possible. You should see it go well past the typical 8k output token limit.

[netlify]

✅ Deploy Preview for continuedev canceled.

Name	Link
🔨 Latest commit	82b07e7
🔍 Latest deploy log	https://app.netlify.com/sites/continuedev/deploys/67e41d236fd9aa0008a385b5

[RomneyDa]

@FallDownTheSystem requestOptions is injected by this.fetch which uses the customFetch from the @continuedev/fetch package. This is pretty easy to miss

The anthropic beta changes look interesting, could you update it to just add them to this.requestOptions rather than spreading request option headers?

[FallDownTheSystem]

Oh I see. So the requestOption headers were always set, but they would overwrite the anthropic-beta header, so the prompt-caching wouldn't be set.

I did get another idea, you could set the output-128k-2025-02-19 value here automatically if the user has defined over 8k (or over 64k if reasoning is enabled) as their maxTokens.