fix(openai): correctly tag image inputs for chat completions [backport #7759 to 2.2]

[Yun-Kim]

This backports #7759 to 2.2.

This PR adds a step to stringify input messages before tagging in the OpenAI chat completions endpoint. Previously, we had assumed that messages.content would always be a string (which was true until OpenAI recently added the image input feature to the chat completions endpoint), but it can now be an array of str-str dictionaries.

Testing Strategy

Regression tests have been added, and manual testing has also confirmed that the error reported on #7737 does not appear.

Checklist

• Change(s) are motivated and described in the PR description.
• Testing strategy is described if automated tests are not included in the PR.
• Risk is outlined (performance impact, potential for breakage, maintainability, etc).
• Change is maintainable (easy to change, telemetry, documentation).
• Library release note guidelines are followed. If no release note is required, add label changelog/no-changelog.
• Documentation is included (in-code, generated user docs, public corp docs).
• Backport labels are set (if applicable)

Reviewer Checklist

• Title is accurate.
• No unnecessary changes are introduced.
• Description motivates each change.
• Avoids breaking API changes unless absolutely necessary.
• Testing strategy adequately addresses listed risk(s).
• Change is maintainable (easy to change, telemetry, documentation).
• Release note makes sense to a user of the library.
• Reviewer has explicitly acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment.
• Backport labels are set in a manner that is consistent with the release branch maintenance policy
• If this PR touches code that signs or publishes builds or packages, or handles credentials of any kind, I've requested a review from @DataDog/security-design-and-guidance.
• This PR doesn't touch any of that.

[pr-commenter]

Benchmarks

Benchmark execution time: 2023-12-04 18:43:21

Comparing candidate commit e1e5ff5 in PR branch yunkim/backport-7759-2-2 with baseline commit ee7d50e in branch 2.2.

Found 1 performance improvements and 0 performance regressions! Performance is the same for 89 metrics, 0 unstable metrics.

scenario:flasksimple-appsec-post

• 🟩 execution_time [-414.950µs; -270.593µs] or [-6.215%; -4.053%]