More robust chunking

[chitalian]

In some environments, each chunk is not received as a single chunk, but rather the chunk is split up into two chunks.

Right now, the typescript SDK assumes each chunk is formatted as

event: ____
data:  _____

However, this is not always the case. Can we add more robust chunking algorithm that waits for all the parts of the chunks?

Proposed fix

Within _createMessage (

anthropic-sdk-typescript/src/lib/MessageStream.ts

Line 123 in c7db92c

protected async _createMessage(

)

We can wait and look for the whole chunk to arrive before adding the next stream event

Additional notes

The OpenAI Python and Typescript Packages handle this.

The Ruby OpenAI packages that are community ran, run into this issue: alexrudall/ruby-openai#411

[RobertCraigie]

Hey @chitalian can you share an example of something that breaks the SDK streaming logic? The SDK should handle events that come through multiple chunks.

Maybe you ran into #292? (which will be fixed in the next release)

[rattrayalex]

This should now be fixed; please try the latest release and provide details if you continue to see issues.