fix(go): compat_oai plugin returns incomplete history when streaming

[MikeRez0]

Changes fix this issue
#4683

Checklist (if applicable):

• PR title is following https://www.conventionalcommits.org/en/v1.0.0/
• Tested (manually, unit tested, etc.)
• Docs updated (updated docs or a docs bug required)

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[gemini-code-assist]

Code Review

This pull request updates the generateStream and convertChatCompletionToModelResponse functions in go/plugins/compat_oai/generate.go to accept and utilize the ai.ModelRequest object, ensuring the request context is preserved in the model response. A review comment identifies that the signature change for convertChatCompletionToModelResponse breaks the generateComplete function, which was not updated in this PR. The feedback includes a code suggestion to fix the compilation error and improve error handling by wrapping errors with contextual information.

[MichaelDoyle]

Thanks @MikeRez0! Can you get the CLA taken care of? In the mean time we'll get the review done.

[MikeRez0]

Already signed