feat: Added token_count to LlmEmbedding and LlmChatCompletionMessage for openai

[bizob2828]

Description

To support calculating token counts downstream for Llm events that lack counts(i.e. streaming or disabling capturing content), we have added token_count to LlmEmbedding, and LlmChatCompletionMessage. This only adds and does not remove the old attributes for capturing token counts on prompts and completions. That will be handled in #2057

Related Issues

Closes #2056

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 97.16%. Comparing base (c5ab73c) to head (196d285).
Report is 2 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #2061   +/-   ##
=======================================
  Coverage   97.16%   97.16%           
=======================================
  Files         247      247           
  Lines       41755    41762    +7     
=======================================
+ Hits        40573    40580    +7     
  Misses       1182     1182           

Flag	Coverage Δ
integration-tests-16.x	78.40% <ø> (+0.01%)	⬆️
integration-tests-18.x	78.37% <ø> (ø)
integration-tests-20.x	78.38% <ø> (ø)
unit-tests-16.x	90.62% <100.00%> (+<0.01%)	⬆️
unit-tests-18.x	90.60% <100.00%> (+<0.01%)	⬆️
unit-tests-20.x	90.60% <100.00%> (+<0.01%)	⬆️
versioned-tests-16.x	74.59% <100.00%> (-0.02%)	⬇️
versioned-tests-18.x	75.45% <100.00%> (-0.02%)	⬇️
versioned-tests-20.x	75.46% <100.00%> (-0.02%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

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

[jsumners-nr]

Looks good to me.