[CHORE] Fix Issue Notification action to use OPENAI_MODEL env var

[sbarrio]

What does this PR do?

This PR updates the issue_notification Github action with the following changes:

• Properly read the OPENAI_MODEL env variable, which was being ignored before. It also sets a new default model in case it was not provided.
• Updated the openai dependency to 2.17.0
• Changes OPENAI_MAX_RESPONSE_TOKENS into OPENAI_MAX_COMPLETION_TOKENS to be used setting max_completion_tokens
• Does not pass the temperature parameter as it is now available on the current model set.

Review checklist (to be filled by reviewers)

• Feature or bugfix MUST have appropriate tests
• Make sure you discussed the feature or bugfix with the maintaining team in an Issue
• Make sure each commit and the PR mention the Issue number (cf the CONTRIBUTING doc)
• If this PR is auto-generated, please make sure also to manually update the code related to the change

[mariedm]

nit: we could have kept the env var name the same and only update the param sent when calling the API

[sbarrio]

I initially did that, yes. But I think it could be very easy to forget why we did that change down the lane so I opted to properly rename it all.