Fix cost calculation when completion_token is None

[yiranwu0]

Why are these changes needed?

When using OpenAI, sometimes the response has a prompt token but the completion token is None. This would cause error when calculating the cost.
This PR fixes this issue.

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 0% with 4 lines in your changes are missing coverage. Please review.

Project coverage is 57.22%. Comparing base (16b1db3) to head (8afe469).
Report is 5 commits behind head on main.

Files	Patch %	Lines
autogen/oai/client.py	0.00%	2 Missing and 2 partials ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #2292       +/-   ##
===========================================
+ Coverage   38.16%   57.22%   +19.06%     
===========================================
  Files          78       78               
  Lines        7861     7865        +4     
  Branches     1681     1821      +140     
===========================================
+ Hits         3000     4501     +1501     
+ Misses       4611     2987     -1624     
- Partials      250      377      +127     

Flag	Coverage Δ
unittest	14.21% <0.00%> (?)
unittests	56.21% <0.00%> (+18.06%)	⬆️

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.