Add response token count logic to OpenAI instrumentation.

[umaannamalai]

This PR updates OpenAI instrumentation and tests to pull token counts directly from the response object. If a customer has an LLM token counting callback function registered, this will still take priority over the response token count values.

It also removes token count calculations from error cases as the agent will consistently stop reporting token counts when a error was met during the creation of an embedding or chat completion.

[github-actions]

🦙 MegaLinter status: ✅ SUCCESS

Descriptor	Linter	Files	Fixed	Errors	Warnings	Elapsed time
✅ ACTION	actionlint	6		0	0	0.85s
✅ MARKDOWN	markdownlint	7	0	0	0	1.24s
✅ MARKDOWN	markdown-link-check	7		0	0	21.82s
✅ PYTHON	ruff	940	2	0	0	0.97s
✅ PYTHON	ruff-format	940	3	0	0	0.33s
✅ YAML	prettier	13	0	0	0	1.4s
✅ YAML	v8r	13		0	0	5.42s
✅ YAML	yamllint	13		0	0	0.6s

See detailed report in MegaLinter reports

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 81.46%. Comparing base (b1408de) to head (8a44e9a).

Additional details and impacted files

@@                     Coverage Diff                      @@
##           feature-llm-token-counts    #1498      +/-   ##
============================================================
- Coverage                     81.48%   81.46%   -0.03%     
============================================================
  Files                           209      209              
  Lines                         23815    23841      +26     
  Branches                       3753     3757       +4     
============================================================
+ Hits                          19406    19422      +16     
- Misses                         3153     3159       +6     
- Partials                       1256     1260       +4     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.